From ccbfea78adf75d3d9e87aa739dab83254f5333fa Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 8 Jul 2024 23:18:57 +0200 Subject: [PATCH 001/562] Input: ads7846 - ratelimit the spi_sync error message In case the touch controller is not connected, this message keeps scrolling on the console indefinitelly. Ratelimit it to avoid filling kernel logs. " ads7846 spi2.1: spi_sync --> -22 " Signed-off-by: Marek Vasut Link: https://lore.kernel.org/r/20240708211913.171243-1-marex@denx.de Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/ads7846.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index 4247283c7271..f89c0dd15d8b 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -824,7 +824,7 @@ static void ads7846_read_state(struct ads7846 *ts) m = &ts->msg[msg_idx]; error = spi_sync(ts->spi, m); if (error) { - dev_err(&ts->spi->dev, "spi_sync --> %d\n", error); + dev_err_ratelimited(&ts->spi->dev, "spi_sync --> %d\n", error); packet->ignore = true; return; } From da897484557b34a54fabb81f6c223c19a69e546d Mon Sep 17 00:00:00 2001 From: Jonathan Denose Date: Tue, 23 Jul 2024 21:33:30 -0700 Subject: [PATCH 002/562] Input: synaptics - enable SMBus for HP Elitebook 840 G2 The kernel reports that the touchpad for this device can support a different bus. With SMBus enabled the touchpad movement is smoother and three-finger gestures are recognized. Signed-off-by: Jonathan Denose Link: https://lore.kernel.org/r/20240719180612.1.Ib652dd808c274076f32cd7fc6c1160d2cf71753b@changeid Signed-off-by: Dmitry Torokhov --- drivers/input/mouse/synaptics.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 38191c3b31bf..380aa1614442 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -189,6 +189,7 @@ static const char * const smbus_pnp_ids[] = { "LEN2054", /* E480 */ "LEN2055", /* E580 */ "LEN2068", /* T14 Gen 1 */ + "SYN3015", /* HP EliteBook 840 G2 */ "SYN3052", /* HP EliteBook 840 G4 */ "SYN3221", /* HP 15-ay000 */ "SYN323d", /* HP Spectre X360 13-w013dx */ From 5ce86c6c861352c9346ebb5c96ed70cb67414aa3 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 27 Jul 2024 23:02:59 +0900 Subject: [PATCH 003/562] rust: suppress error messages from CONFIG_{RUSTC,BINDGEN}_VERSION_TEXT While this is a somewhat unusual case, I encountered odd error messages when I ran Kconfig in a foreign architecture chroot. $ make allmodconfig sh: 1: rustc: not found sh: 1: bindgen: not found # # configuration written to .config # The successful execution of 'command -v rustc' does not necessarily mean that 'rustc --version' will succeed. $ sh -c 'command -v rustc' /home/masahiro/.cargo/bin/rustc $ sh -c 'rustc --version' sh: 1: rustc: not found Here, 'rustc' is built for x86, and I ran it in an arm64 system. The current code: command -v $(RUSTC) >/dev/null 2>&1 && $(RUSTC) --version || echo n can be turned into: command -v $(RUSTC) >/dev/null 2>&1 && $(RUSTC) --version 2>/dev/null || echo n However, I did not understand the necessity of 'command -v $(RUSTC)'. I simplified it to: $(RUSTC) --version 2>/dev/null || echo n Fixes: 2f7ab1267dc9 ("Kbuild: add Rust support") Signed-off-by: Masahiro Yamada Link: https://lore.kernel.org/r/20240727140302.1806011-1-masahiroy@kernel.org [ Rebased on top of v6.11-rc1. - Miguel ] Signed-off-by: Miguel Ojeda --- init/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/init/Kconfig b/init/Kconfig index a465ea9525bd..cddeec9fcb72 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1919,7 +1919,7 @@ config RUST config RUSTC_VERSION_TEXT string depends on RUST - default $(shell,command -v $(RUSTC) >/dev/null 2>&1 && $(RUSTC) --version || echo n) + default $(shell,$(RUSTC) --version 2>/dev/null || echo n) config BINDGEN_VERSION_TEXT string @@ -1927,7 +1927,7 @@ config BINDGEN_VERSION_TEXT # The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0 # (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when # the minimum version is upgraded past that (0.69.1 already fixed the issue). - default $(shell,command -v $(BINDGEN) >/dev/null 2>&1 && $(BINDGEN) --version workaround-for-0.69.0 || echo n) + default $(shell,$(BINDGEN) --version workaround-for-0.69.0 2>/dev/null || echo n) # # Place an empty function call at each tracepoint site. Can be From aacf93e87f0d808ef46e621aa56caea336b4433c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 27 Jul 2024 23:03:00 +0900 Subject: [PATCH 004/562] rust: fix the default format for CONFIG_{RUSTC,BINDGEN}_VERSION_TEXT Another oddity in these config entries is their default value can fall back to 'n', which is a value for bool or tristate symbols. The '|| echo n' is an incorrect workaround to avoid the syntax error. This is not a big deal, as the entry is hidden by 'depends on RUST' in situations where '$(RUSTC) --version' or '$(BINDGEN) --version' fails. Anyway, it looks odd. The default of a string type symbol should be a double-quoted string literal. Turn it into an empty string when the version command fails. Fixes: 2f7ab1267dc9 ("Kbuild: add Rust support") Signed-off-by: Masahiro Yamada Link: https://lore.kernel.org/r/20240727140302.1806011-2-masahiroy@kernel.org [ Rebased on top of v6.11-rc1. - Miguel ] Signed-off-by: Miguel Ojeda --- init/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/init/Kconfig b/init/Kconfig index cddeec9fcb72..3ada33b1d681 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1919,7 +1919,7 @@ config RUST config RUSTC_VERSION_TEXT string depends on RUST - default $(shell,$(RUSTC) --version 2>/dev/null || echo n) + default "$(shell,$(RUSTC) --version 2>/dev/null)" config BINDGEN_VERSION_TEXT string @@ -1927,7 +1927,7 @@ config BINDGEN_VERSION_TEXT # The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0 # (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when # the minimum version is upgraded past that (0.69.1 already fixed the issue). - default $(shell,$(BINDGEN) --version workaround-for-0.69.0 2>/dev/null || echo n) + default "$(shell,$(BINDGEN) --version workaround-for-0.69.0 2>/dev/null)" # # Place an empty function call at each tracepoint site. Can be From 0ba521d6948ecb4acf1276494dfed127fe096ca6 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 25 Jul 2024 20:46:44 +0200 Subject: [PATCH 005/562] rust: macros: indent list item in `module!`'s docs Like commit e516211f615f ("rust: macros: indent list item in `paste!`'s docs"), but for `module!`. Reviewed-by: Trevor Gross Link: https://lore.kernel.org/r/20240725184644.135185-1-ojeda@kernel.org Signed-off-by: Miguel Ojeda --- rust/macros/lib.rs | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs index 159e75292970..5be0cb9db3ee 100644 --- a/rust/macros/lib.rs +++ b/rust/macros/lib.rs @@ -94,7 +94,7 @@ use proc_macro::TokenStream; /// - `license`: ASCII string literal of the license of the kernel module (required). /// - `alias`: array of ASCII string literals of the alias names of the kernel module. /// - `firmware`: array of ASCII string literals of the firmware files of -/// the kernel module. +/// the kernel module. #[proc_macro] pub fn module(ts: TokenStream) -> TokenStream { module::module(ts) From 950aeefb34923fe3c28ade35fe05f24e2c5b1d55 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Wed, 17 Jul 2024 22:01:30 -0700 Subject: [PATCH 006/562] iommufd/device: Fix hwpt at err_unresv in iommufd_device_do_replace() The rewind routine should remove the reserved iovas added to the new hwpt. Fixes: 89db31635c87 ("iommufd: Derive iommufd_hwpt_paging from iommufd_hw_pagetable") Cc: stable@vger.kernel.org Link: https://patch.msgid.link/r/20240718050130.1956804-1-nicolinc@nvidia.com Signed-off-by: Nicolin Chen Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index 9a7ec5997c61..3214a4c17c6b 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -526,7 +526,7 @@ iommufd_device_do_replace(struct iommufd_device *idev, err_unresv: if (hwpt_is_paging(hwpt)) iommufd_group_remove_reserved_iova(igroup, - to_hwpt_paging(old_hwpt)); + to_hwpt_paging(hwpt)); err_unlock: mutex_unlock(&idev->igroup->lock); return ERR_PTR(rc); From 0710c3d304f67f9b68f5082214e311ec8f82bd82 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Fri, 26 Jul 2024 13:18:25 +0200 Subject: [PATCH 007/562] dt-bindings: Batch-update Konrad Dybcio's email Use my @kernel.org address everywhere. Signed-off-by: Konrad Dybcio Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20240726-topic-konrad_email-v1-3-f94665da2919@kernel.org Signed-off-by: Rob Herring (Arm) --- Documentation/devicetree/bindings/clock/qcom,dispcc-sm6350.yaml | 2 +- Documentation/devicetree/bindings/clock/qcom,gcc-msm8994.yaml | 2 +- Documentation/devicetree/bindings/clock/qcom,gcc-sm6125.yaml | 2 +- Documentation/devicetree/bindings/clock/qcom,gcc-sm6350.yaml | 2 +- Documentation/devicetree/bindings/clock/qcom,sm6115-gpucc.yaml | 2 +- Documentation/devicetree/bindings/clock/qcom,sm6125-gpucc.yaml | 2 +- Documentation/devicetree/bindings/clock/qcom,sm6350-camcc.yaml | 2 +- Documentation/devicetree/bindings/clock/qcom,sm6375-dispcc.yaml | 2 +- Documentation/devicetree/bindings/clock/qcom,sm6375-gcc.yaml | 2 +- Documentation/devicetree/bindings/clock/qcom,sm6375-gpucc.yaml | 2 +- .../devicetree/bindings/clock/qcom,sm8350-videocc.yaml | 2 +- Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml | 2 +- .../devicetree/bindings/display/msm/qcom,sm6375-mdss.yaml | 2 +- .../bindings/display/panel/asus,z00t-tm5p5-nt35596.yaml | 2 +- .../devicetree/bindings/display/panel/sony,td4353-jdi.yaml | 2 +- .../devicetree/bindings/interconnect/qcom,sc7280-rpmh.yaml | 2 +- .../devicetree/bindings/interconnect/qcom,sc8280xp-rpmh.yaml | 2 +- .../devicetree/bindings/interconnect/qcom,sm8450-rpmh.yaml | 2 +- Documentation/devicetree/bindings/iommu/qcom,iommu.yaml | 2 +- .../devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml | 2 +- Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml | 2 +- Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml | 2 +- Documentation/devicetree/bindings/remoteproc/qcom,rpm-proc.yaml | 2 +- .../devicetree/bindings/soc/qcom/qcom,rpm-master-stats.yaml | 2 +- 24 files changed, 24 insertions(+), 24 deletions(-) diff --git a/Documentation/devicetree/bindings/clock/qcom,dispcc-sm6350.yaml b/Documentation/devicetree/bindings/clock/qcom,dispcc-sm6350.yaml index a584b4953e68..46403b98411f 100644 --- a/Documentation/devicetree/bindings/clock/qcom,dispcc-sm6350.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,dispcc-sm6350.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Display Clock & Reset Controller on SM6350 maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | Qualcomm display clock control module provides the clocks, resets and power diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-msm8994.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-msm8994.yaml index 6b9c1d198b14..10afe984e2fb 100644 --- a/Documentation/devicetree/bindings/clock/qcom,gcc-msm8994.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,gcc-msm8994.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Global Clock & Reset Controller on MSM8994 maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | Qualcomm global clock control module provides the clocks, resets and power diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-sm6125.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-sm6125.yaml index a5a29dc75ae1..1fe68e07a2b2 100644 --- a/Documentation/devicetree/bindings/clock/qcom,gcc-sm6125.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,gcc-sm6125.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Global Clock & Reset Controller on SM6125 maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | Qualcomm global clock control module provides the clocks, resets and power diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-sm6350.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-sm6350.yaml index 2280b859b2ad..78e232fa95dc 100644 --- a/Documentation/devicetree/bindings/clock/qcom,gcc-sm6350.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,gcc-sm6350.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Global Clock & Reset Controller on SM6350 maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | Qualcomm global clock control module provides the clocks, resets and power diff --git a/Documentation/devicetree/bindings/clock/qcom,sm6115-gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm6115-gpucc.yaml index cf19f44af774..4ff17a91344b 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sm6115-gpucc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sm6115-gpucc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Graphics Clock & Reset Controller on SM6115 maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | Qualcomm graphics clock control module provides clocks, resets and power diff --git a/Documentation/devicetree/bindings/clock/qcom,sm6125-gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm6125-gpucc.yaml index 374a1844a159..10a9c96a97b6 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sm6125-gpucc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sm6125-gpucc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Graphics Clock & Reset Controller on SM6125 maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | Qualcomm graphics clock control module provides clocks and power domains on diff --git a/Documentation/devicetree/bindings/clock/qcom,sm6350-camcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm6350-camcc.yaml index fd6658cb793d..c03b30f64f35 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sm6350-camcc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sm6350-camcc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Camera Clock & Reset Controller on SM6350 maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | Qualcomm camera clock control module provides the clocks, resets and power diff --git a/Documentation/devicetree/bindings/clock/qcom,sm6375-dispcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm6375-dispcc.yaml index 183b1c75dbdf..3cd422a645fd 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sm6375-dispcc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sm6375-dispcc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Display Clock & Reset Controller on SM6375 maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | Qualcomm display clock control module provides the clocks, resets and power diff --git a/Documentation/devicetree/bindings/clock/qcom,sm6375-gcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm6375-gcc.yaml index 147b75a21508..de4e9066eeb8 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sm6375-gcc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sm6375-gcc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Global Clock & Reset Controller on SM6375 maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | Qualcomm global clock control module provides the clocks, resets and power diff --git a/Documentation/devicetree/bindings/clock/qcom,sm6375-gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm6375-gpucc.yaml index cf4cad76f6c9..d9dd479c17bd 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sm6375-gpucc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sm6375-gpucc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Graphics Clock & Reset Controller on SM6375 maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | Qualcomm graphics clock control module provides clocks, resets and power diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8350-videocc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8350-videocc.yaml index 46d1d91e3a01..5c2ecec0624e 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sm8350-videocc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sm8350-videocc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm SM8350 Video Clock & Reset Controller maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | Qualcomm video clock control module provides the clocks, resets and power diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml index 3c2cac14e6c3..d10bb002906e 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Graphics Clock & Reset Controller on SM8450 maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | Qualcomm graphics clock control module provides the clocks, resets and power diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm6375-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm6375-mdss.yaml index 8e8a288d318c..e22b4c433fd0 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,sm6375-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,sm6375-mdss.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm SM6375 Display MDSS maintainers: - - Konrad Dybcio + - Konrad Dybcio description: SM6375 MSM Mobile Display Subsystem (MDSS), which encapsulates sub-blocks diff --git a/Documentation/devicetree/bindings/display/panel/asus,z00t-tm5p5-nt35596.yaml b/Documentation/devicetree/bindings/display/panel/asus,z00t-tm5p5-nt35596.yaml index 2399cabf044c..dd614e077bbf 100644 --- a/Documentation/devicetree/bindings/display/panel/asus,z00t-tm5p5-nt35596.yaml +++ b/Documentation/devicetree/bindings/display/panel/asus,z00t-tm5p5-nt35596.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: ASUS Z00T TM5P5 NT35596 5.5" 1080×1920 LCD Panel maintainers: - - Konrad Dybcio + - Konrad Dybcio description: |+ This panel seems to only be found in the Asus Z00T diff --git a/Documentation/devicetree/bindings/display/panel/sony,td4353-jdi.yaml b/Documentation/devicetree/bindings/display/panel/sony,td4353-jdi.yaml index 191b692125e1..032a989184ff 100644 --- a/Documentation/devicetree/bindings/display/panel/sony,td4353-jdi.yaml +++ b/Documentation/devicetree/bindings/display/panel/sony,td4353-jdi.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Sony TD4353 JDI 5 / 5.7" 2160x1080 MIPI-DSI Panel maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | The Sony TD4353 JDI is a 5 (XZ2c) / 5.7 (XZ2) inch 2160x1080 diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sc7280-rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sc7280-rpmh.yaml index 9fce7203bd42..78210791496f 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,sc7280-rpmh.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,sc7280-rpmh.yaml @@ -8,7 +8,7 @@ title: Qualcomm RPMh Network-On-Chip Interconnect on SC7280 maintainers: - Bjorn Andersson - - Konrad Dybcio + - Konrad Dybcio description: | RPMh interconnect providers support system bandwidth requirements through diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sc8280xp-rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sc8280xp-rpmh.yaml index 6c2da03f0cd2..100c68636909 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,sc8280xp-rpmh.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,sc8280xp-rpmh.yaml @@ -8,7 +8,7 @@ title: Qualcomm RPMh Network-On-Chip Interconnect on SC8280XP maintainers: - Bjorn Andersson - - Konrad Dybcio + - Konrad Dybcio description: | RPMh interconnect providers support system bandwidth requirements through diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sm8450-rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sm8450-rpmh.yaml index 3cff7e662255..300640a533dd 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,sm8450-rpmh.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,sm8450-rpmh.yaml @@ -8,7 +8,7 @@ title: Qualcomm RPMh Network-On-Chip Interconnect on SM8450 maintainers: - Bjorn Andersson - - Konrad Dybcio + - Konrad Dybcio description: | RPMh interconnect providers support system bandwidth requirements through diff --git a/Documentation/devicetree/bindings/iommu/qcom,iommu.yaml b/Documentation/devicetree/bindings/iommu/qcom,iommu.yaml index 571e5746d177..f8cebc9e8cd9 100644 --- a/Documentation/devicetree/bindings/iommu/qcom,iommu.yaml +++ b/Documentation/devicetree/bindings/iommu/qcom,iommu.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Technologies legacy IOMMU implementations maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | Qualcomm "B" family devices which are not compatible with arm-smmu have diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml index bd3cbb44c99a..e75393b3d196 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Technologies, Inc. MDM9607 TLMM block maintainers: - - Konrad Dybcio + - Konrad Dybcio description: Top Level Mode Multiplexer pin controller in Qualcomm MDM9607 SoC. diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml index a4771f87d936..b262af6be97d 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Technologies, Inc. SM6350 TLMM block maintainers: - - Konrad Dybcio + - Konrad Dybcio description: Top Level Mode Multiplexer pin controller in Qualcomm SM6350 SoC. diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml index 047f82863f9b..c11af09c3f5b 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Technologies, Inc. SM6375 TLMM block maintainers: - - Konrad Dybcio + - Konrad Dybcio description: Top Level Mode Multiplexer pin controller in Qualcomm SM6375 SoC. diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,rpm-proc.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,rpm-proc.yaml index 7afafde17a38..61cf4fe19ca5 100644 --- a/Documentation/devicetree/bindings/remoteproc/qcom,rpm-proc.yaml +++ b/Documentation/devicetree/bindings/remoteproc/qcom,rpm-proc.yaml @@ -8,7 +8,7 @@ title: Qualcomm Resource Power Manager (RPM) Processor/Subsystem maintainers: - Bjorn Andersson - - Konrad Dybcio + - Konrad Dybcio - Stephan Gerhold description: | diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,rpm-master-stats.yaml b/Documentation/devicetree/bindings/soc/qcom/qcom,rpm-master-stats.yaml index 9410404f87f1..ad2dcc39a5f5 100644 --- a/Documentation/devicetree/bindings/soc/qcom/qcom,rpm-master-stats.yaml +++ b/Documentation/devicetree/bindings/soc/qcom/qcom,rpm-master-stats.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Technologies, Inc. (QTI) RPM Master Stats maintainers: - - Konrad Dybcio + - Konrad Dybcio description: | The Qualcomm RPM (Resource Power Manager) architecture includes a concept From e1cf752ede8e82c2d084868c50a1ca6cdb07c9c4 Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Wed, 12 Jun 2024 11:29:34 +0200 Subject: [PATCH 008/562] dt-bindings: eeprom: at25: add fujitsu,mb85rs256 compatible The fujitsu,mb85rs256 is a 256 Kbit SPI memory FRAM in the same family as the two existing fujitsu,mb85rs* compatibles and at25 compatible. Signed-off-by: Francesco Dolcini Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20240612092934.12282-1-francesco@dolcini.it Signed-off-by: Rob Herring (Arm) --- Documentation/devicetree/bindings/eeprom/at25.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/eeprom/at25.yaml b/Documentation/devicetree/bindings/eeprom/at25.yaml index 1715b0c9feea..c31e5e719525 100644 --- a/Documentation/devicetree/bindings/eeprom/at25.yaml +++ b/Documentation/devicetree/bindings/eeprom/at25.yaml @@ -28,6 +28,7 @@ properties: - anvo,anv32e61w - atmel,at25256B - fujitsu,mb85rs1mt + - fujitsu,mb85rs256 - fujitsu,mb85rs64 - microchip,at25160bn - microchip,25lc040 From 684890a0185dabf5920c43b639133adc4c2632cf Mon Sep 17 00:00:00 2001 From: John Keeping Date: Wed, 31 Jul 2024 10:33:09 +0100 Subject: [PATCH 009/562] Input: adc-joystick - fix optional value handling The abs-fuzz and abs-flat properties are documented as optional. When these are absent, fwnode_property_read_u32() will leave the input unchanged, meaning that an axis either picks up the value for the previous axis or an uninitialized value. Explicitly set these values to zero when they are unspecified to match the documented behaviour in the device tree bindings. Signed-off-by: John Keeping Link: https://lore.kernel.org/r/20240731093310.3696919-1-jkeeping@inmusicbrands.com Signed-off-by: Dmitry Torokhov --- drivers/input/joystick/adc-joystick.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/input/joystick/adc-joystick.c b/drivers/input/joystick/adc-joystick.c index 5f46a7104b52..de1fa4cf291b 100644 --- a/drivers/input/joystick/adc-joystick.c +++ b/drivers/input/joystick/adc-joystick.c @@ -182,8 +182,11 @@ static int adc_joystick_set_axes(struct device *dev, struct adc_joystick *joy) swap(range[0], range[1]); } - fwnode_property_read_u32(child, "abs-fuzz", &fuzz); - fwnode_property_read_u32(child, "abs-flat", &flat); + if (fwnode_property_read_u32(child, "abs-fuzz", &fuzz)) + fuzz = 0; + + if (fwnode_property_read_u32(child, "abs-flat", &flat)) + flat = 0; input_set_abs_params(joy->input, axes[i].code, range[0], range[1], fuzz, flat); From 39a3396558fb97e6e7d4c1eb04c2166da31904a9 Mon Sep 17 00:00:00 2001 From: Drew Fustini Date: Tue, 30 Jul 2024 23:14:40 -0700 Subject: [PATCH 010/562] clk: thead: fix dependency on clk_ignore_unused Add the CLK_IGNORE_UNUSED flag to the vp-axi clock (CLK_VP_AXI) to avoid depending on clk_ignore_unused in the cmdline. Without this fix, the emmc-sdio clock (CLK_EMMC_SDIO) fails to work after vp-axi is disabled. Signed-off-by: Drew Fustini Link: https://lore.kernel.org/r/20240731061439.3807172-1-drew@pdp7.com Fixes: ae81b69fd2b1 ("clk: thead: Add support for T-Head TH1520 AP_SUBSYS clocks") Signed-off-by: Stephen Boyd --- drivers/clk/thead/clk-th1520-ap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/thead/clk-th1520-ap.c b/drivers/clk/thead/clk-th1520-ap.c index cbc176b27c09..17e32ae08720 100644 --- a/drivers/clk/thead/clk-th1520-ap.c +++ b/drivers/clk/thead/clk-th1520-ap.c @@ -738,7 +738,7 @@ static struct ccu_div vp_axi_clk = { .hw.init = CLK_HW_INIT_PARENTS_HW("vp-axi", video_pll_clk_parent, &ccu_div_ops, - 0), + CLK_IGNORE_UNUSED), }, }; From 9374ae912dbb1eed8139ed75fd2c0f1b30ca454d Mon Sep 17 00:00:00 2001 From: Mengqi Zhang Date: Tue, 16 Jul 2024 09:37:04 +0800 Subject: [PATCH 011/562] mmc: mtk-sd: receive cmd8 data when hs400 tuning fail When we use cmd8 as the tuning command in hs400 mode, the command response sent back by some eMMC devices cannot be correctly sampled by MTK eMMC controller at some weak sample timing. In this case, command timeout error may occur. So we must receive the following data to make sure the next cmd8 send correctly. Signed-off-by: Mengqi Zhang Fixes: c4ac38c6539b ("mmc: mtk-sd: Add HS400 online tuning support") Cc: stable@vger.stable.com Link: https://lore.kernel.org/r/20240716013704.10578-1-mengqi.zhang@mediatek.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/mtk-sd.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index a94835b8ab93..e386f78e3267 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -1230,7 +1230,7 @@ static bool msdc_cmd_done(struct msdc_host *host, int events, } if (!sbc_error && !(events & MSDC_INT_CMDRDY)) { - if (events & MSDC_INT_CMDTMO || + if ((events & MSDC_INT_CMDTMO && !host->hs400_tuning) || (!mmc_op_tuning(cmd->opcode) && !host->hs400_tuning)) /* * should not clear fifo/interrupt as the tune data @@ -1323,9 +1323,9 @@ static void msdc_start_command(struct msdc_host *host, static void msdc_cmd_next(struct msdc_host *host, struct mmc_request *mrq, struct mmc_command *cmd) { - if ((cmd->error && - !(cmd->error == -EILSEQ && - (mmc_op_tuning(cmd->opcode) || host->hs400_tuning))) || + if ((cmd->error && !host->hs400_tuning && + !(cmd->error == -EILSEQ && + mmc_op_tuning(cmd->opcode))) || (mrq->sbc && mrq->sbc->error)) msdc_request_done(host, mrq); else if (cmd == mrq->sbc) From a6e9c391d45b5865b61e569146304cff72821a5d Mon Sep 17 00:00:00 2001 From: Camila Alvarez Date: Tue, 30 Jul 2024 19:42:43 -0400 Subject: [PATCH 012/562] HID: cougar: fix slab-out-of-bounds Read in cougar_report_fixup report_fixup for the Cougar 500k Gaming Keyboard was not verifying that the report descriptor size was correct before accessing it Reported-by: syzbot+24c0361074799d02c452@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=24c0361074799d02c452 Signed-off-by: Camila Alvarez Reviewed-by: Silvan Jegen Signed-off-by: Jiri Kosina --- drivers/hid/hid-cougar.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/hid-cougar.c b/drivers/hid/hid-cougar.c index cb8bd8aae15b..0fa785f52707 100644 --- a/drivers/hid/hid-cougar.c +++ b/drivers/hid/hid-cougar.c @@ -106,7 +106,7 @@ static void cougar_fix_g6_mapping(void) static __u8 *cougar_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { - if (rdesc[2] == 0x09 && rdesc[3] == 0x02 && + if (*rsize >= 117 && rdesc[2] == 0x09 && rdesc[3] == 0x02 && (rdesc[115] | rdesc[116] << 8) >= HID_MAX_USAGES) { hid_info(hdev, "usage count exceeds max: fixing up report descriptor\n"); From ab3de2c7ec91db6a3cf5fc07765852c81ca7d6ef Mon Sep 17 00:00:00 2001 From: Aapo Vienamo Date: Thu, 20 Jun 2024 13:43:03 +0300 Subject: [PATCH 013/562] thunderbolt: Fix memory leaks in {port|retimer}_sb_regs_write() Add missing free_page() call for the memory allocated by validate_and_copy_from_user(). Fixes: 6d241fa00159 ("thunderbolt: Add sideband register access to debugfs") Signed-off-by: Aapo Vienamo Reviewed-by: Przemek Kitszel Signed-off-by: Mika Westerberg --- drivers/thunderbolt/debugfs.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c index 11185cc1db92..9ed4bb2e8d05 100644 --- a/drivers/thunderbolt/debugfs.c +++ b/drivers/thunderbolt/debugfs.c @@ -323,16 +323,17 @@ static ssize_t port_sb_regs_write(struct file *file, const char __user *user_buf if (mutex_lock_interruptible(&tb->lock)) { ret = -ERESTARTSYS; - goto out_rpm_put; + goto out; } ret = sb_regs_write(port, port_sb_regs, ARRAY_SIZE(port_sb_regs), USB4_SB_TARGET_ROUTER, 0, buf, count, ppos); mutex_unlock(&tb->lock); -out_rpm_put: +out: pm_runtime_mark_last_busy(&sw->dev); pm_runtime_put_autosuspend(&sw->dev); + free_page((unsigned long)buf); return ret < 0 ? ret : count; } @@ -355,16 +356,17 @@ static ssize_t retimer_sb_regs_write(struct file *file, if (mutex_lock_interruptible(&tb->lock)) { ret = -ERESTARTSYS; - goto out_rpm_put; + goto out; } ret = sb_regs_write(rt->port, retimer_sb_regs, ARRAY_SIZE(retimer_sb_regs), USB4_SB_TARGET_RETIMER, rt->index, buf, count, ppos); mutex_unlock(&tb->lock); -out_rpm_put: +out: pm_runtime_mark_last_busy(&rt->dev); pm_runtime_put_autosuspend(&rt->dev); + free_page((unsigned long)buf); return ret < 0 ? ret : count; } From d1aa95e86f178dc597e80228cd9bd81fc3510f34 Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Thu, 25 Jul 2024 10:31:25 +1200 Subject: [PATCH 014/562] hid-asus: add ROG Ally X prod ID to quirk list The new ASUS ROG Ally X functions almost exactly the same as the previous model, so we can use the same quirks. Signed-off-by: Luke D. Jones Signed-off-by: Jiri Kosina --- drivers/hid/hid-asus.c | 3 +++ drivers/hid/hid-ids.h | 1 + 2 files changed, 4 insertions(+) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 37e6d25593c2..a282388b7aa5 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -1248,6 +1248,9 @@ static const struct hid_device_id asus_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY), QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD }, + { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, + USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X), + QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD }, { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD), QUIRK_ROG_CLAYMORE_II_KEYBOARD }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 72d56ee7ce1b..6e3223389080 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -210,6 +210,7 @@ #define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD3 0x1a30 #define USB_DEVICE_ID_ASUSTEK_ROG_Z13_LIGHTBAR 0x18c6 #define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY 0x1abe +#define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X 0x1b4c #define USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD 0x196b #define USB_DEVICE_ID_ASUSTEK_FX503VD_KEYBOARD 0x1869 From 97155021ae17b86985121b33cf8098bcde00d497 Mon Sep 17 00:00:00 2001 From: Olivier Sobrie Date: Tue, 23 Jul 2024 10:44:35 +0200 Subject: [PATCH 015/562] HID: amd_sfh: free driver_data after destroying hid device HID driver callbacks aren't called anymore once hid_destroy_device() has been called. Hence, hid driver_data should be freed only after the hid_destroy_device() function returned as driver_data is used in several callbacks. I observed a crash with kernel 6.10.0 on my T14s Gen 3, after enabling KASAN to debug memory allocation, I got this output: [ 13.050438] ================================================================== [ 13.054060] BUG: KASAN: slab-use-after-free in amd_sfh_get_report+0x3ec/0x530 [amd_sfh] [ 13.054809] psmouse serio1: trackpoint: Synaptics TrackPoint firmware: 0x02, buttons: 3/3 [ 13.056432] Read of size 8 at addr ffff88813152f408 by task (udev-worker)/479 [ 13.060970] CPU: 5 PID: 479 Comm: (udev-worker) Not tainted 6.10.0-arch1-2 #1 893bb55d7f0073f25c46adbb49eb3785fefd74b0 [ 13.063978] Hardware name: LENOVO 21CQCTO1WW/21CQCTO1WW, BIOS R22ET70W (1.40 ) 03/21/2024 [ 13.067860] Call Trace: [ 13.069383] input: TPPS/2 Synaptics TrackPoint as /devices/platform/i8042/serio1/input/input8 [ 13.071486] [ 13.071492] dump_stack_lvl+0x5d/0x80 [ 13.074870] snd_hda_intel 0000:33:00.6: enabling device (0000 -> 0002) [ 13.078296] ? amd_sfh_get_report+0x3ec/0x530 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38] [ 13.082199] print_report+0x174/0x505 [ 13.085776] ? __pfx__raw_spin_lock_irqsave+0x10/0x10 [ 13.089367] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.093255] ? amd_sfh_get_report+0x3ec/0x530 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38] [ 13.097464] kasan_report+0xc8/0x150 [ 13.101461] ? amd_sfh_get_report+0x3ec/0x530 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38] [ 13.105802] amd_sfh_get_report+0x3ec/0x530 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38] [ 13.110303] amdtp_hid_request+0xb8/0x110 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38] [ 13.114879] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.119450] sensor_hub_get_feature+0x1d3/0x540 [hid_sensor_hub 3f13be3016ff415bea03008d45d99da837ee3082] [ 13.124097] hid_sensor_parse_common_attributes+0x4d0/0xad0 [hid_sensor_iio_common c3a5cbe93969c28b122609768bbe23efe52eb8f5] [ 13.127404] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.131925] ? __pfx_hid_sensor_parse_common_attributes+0x10/0x10 [hid_sensor_iio_common c3a5cbe93969c28b122609768bbe23efe52eb8f5] [ 13.136455] ? _raw_spin_lock_irqsave+0x96/0xf0 [ 13.140197] ? __pfx__raw_spin_lock_irqsave+0x10/0x10 [ 13.143602] ? devm_iio_device_alloc+0x34/0x50 [industrialio 3d261d5e5765625d2b052be40e526d62b1d2123b] [ 13.147234] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.150446] ? __devm_add_action+0x167/0x1d0 [ 13.155061] hid_gyro_3d_probe+0x120/0x7f0 [hid_sensor_gyro_3d 63da36a143b775846ab2dbb86c343b401b5e3172] [ 13.158581] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.161814] platform_probe+0xa2/0x150 [ 13.165029] really_probe+0x1e3/0x8a0 [ 13.168243] __driver_probe_device+0x18c/0x370 [ 13.171500] driver_probe_device+0x4a/0x120 [ 13.175000] __driver_attach+0x190/0x4a0 [ 13.178521] ? __pfx___driver_attach+0x10/0x10 [ 13.181771] bus_for_each_dev+0x106/0x180 [ 13.185033] ? __pfx__raw_spin_lock+0x10/0x10 [ 13.188229] ? __pfx_bus_for_each_dev+0x10/0x10 [ 13.191446] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.194382] bus_add_driver+0x29e/0x4d0 [ 13.197328] driver_register+0x1a5/0x360 [ 13.200283] ? __pfx_hid_gyro_3d_platform_driver_init+0x10/0x10 [hid_sensor_gyro_3d 63da36a143b775846ab2dbb86c343b401b5e3172] [ 13.203362] do_one_initcall+0xa7/0x380 [ 13.206432] ? __pfx_do_one_initcall+0x10/0x10 [ 13.210175] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.213211] ? kasan_unpoison+0x44/0x70 [ 13.216688] do_init_module+0x238/0x750 [ 13.219696] load_module+0x5011/0x6af0 [ 13.223096] ? kasan_save_stack+0x30/0x50 [ 13.226743] ? kasan_save_track+0x14/0x30 [ 13.230080] ? kasan_save_free_info+0x3b/0x60 [ 13.233323] ? poison_slab_object+0x109/0x180 [ 13.236778] ? __pfx_load_module+0x10/0x10 [ 13.239703] ? poison_slab_object+0x109/0x180 [ 13.243070] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.245924] ? init_module_from_file+0x13d/0x150 [ 13.248745] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.251503] ? init_module_from_file+0xdf/0x150 [ 13.254198] init_module_from_file+0xdf/0x150 [ 13.256826] ? __pfx_init_module_from_file+0x10/0x10 [ 13.259428] ? kasan_save_track+0x14/0x30 [ 13.261959] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.264471] ? kasan_save_free_info+0x3b/0x60 [ 13.267026] ? poison_slab_object+0x109/0x180 [ 13.269494] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.271949] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.274324] ? _raw_spin_lock+0x85/0xe0 [ 13.276671] ? __pfx__raw_spin_lock+0x10/0x10 [ 13.278963] ? __rseq_handle_notify_resume+0x1a6/0xad0 [ 13.281193] idempotent_init_module+0x23b/0x650 [ 13.283420] ? __pfx_idempotent_init_module+0x10/0x10 [ 13.285619] ? __pfx___seccomp_filter+0x10/0x10 [ 13.287714] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.289828] ? __fget_light+0x57/0x420 [ 13.291870] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.293880] ? security_capable+0x74/0xb0 [ 13.295820] __x64_sys_finit_module+0xbe/0x130 [ 13.297874] do_syscall_64+0x82/0x190 [ 13.299898] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.301905] ? irqtime_account_irq+0x3d/0x1f0 [ 13.303877] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.305753] ? __irq_exit_rcu+0x4e/0x130 [ 13.307577] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.309489] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 13.311371] RIP: 0033:0x7a21f96ade9d [ 13.313234] Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 63 de 0c 00 f7 d8 64 89 01 48 [ 13.317051] RSP: 002b:00007ffeae934e78 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 [ 13.319024] RAX: ffffffffffffffda RBX: 00005987276bfcf0 RCX: 00007a21f96ade9d [ 13.321100] RDX: 0000000000000004 RSI: 00007a21f8eda376 RDI: 000000000000001c [ 13.323314] RBP: 00007a21f8eda376 R08: 0000000000000001 R09: 00007ffeae934ec0 [ 13.325505] R10: 0000000000000050 R11: 0000000000000246 R12: 0000000000020000 [ 13.327637] R13: 00005987276c1250 R14: 0000000000000000 R15: 00005987276c4530 [ 13.329737] [ 13.333945] Allocated by task 139: [ 13.336111] kasan_save_stack+0x30/0x50 [ 13.336121] kasan_save_track+0x14/0x30 [ 13.336125] __kasan_kmalloc+0xaa/0xb0 [ 13.336129] amdtp_hid_probe+0xb1/0x440 [amd_sfh] [ 13.336138] amd_sfh_hid_client_init+0xb8a/0x10f0 [amd_sfh] [ 13.336144] sfh_init_work+0x47/0x120 [amd_sfh] [ 13.336150] process_one_work+0x673/0xeb0 [ 13.336155] worker_thread+0x795/0x1250 [ 13.336160] kthread+0x290/0x350 [ 13.336164] ret_from_fork+0x34/0x70 [ 13.336169] ret_from_fork_asm+0x1a/0x30 [ 13.338175] Freed by task 139: [ 13.340064] kasan_save_stack+0x30/0x50 [ 13.340072] kasan_save_track+0x14/0x30 [ 13.340076] kasan_save_free_info+0x3b/0x60 [ 13.340081] poison_slab_object+0x109/0x180 [ 13.340085] __kasan_slab_free+0x32/0x50 [ 13.340089] kfree+0xe5/0x310 [ 13.340094] amdtp_hid_remove+0xb2/0x160 [amd_sfh] [ 13.340102] amd_sfh_hid_client_deinit+0x324/0x640 [amd_sfh] [ 13.340107] amd_sfh_hid_client_init+0x94a/0x10f0 [amd_sfh] [ 13.340113] sfh_init_work+0x47/0x120 [amd_sfh] [ 13.340118] process_one_work+0x673/0xeb0 [ 13.340123] worker_thread+0x795/0x1250 [ 13.340127] kthread+0x290/0x350 [ 13.340132] ret_from_fork+0x34/0x70 [ 13.340136] ret_from_fork_asm+0x1a/0x30 [ 13.342482] The buggy address belongs to the object at ffff88813152f400 which belongs to the cache kmalloc-64 of size 64 [ 13.347357] The buggy address is located 8 bytes inside of freed 64-byte region [ffff88813152f400, ffff88813152f440) [ 13.347367] The buggy address belongs to the physical page: [ 13.355409] page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x13152f [ 13.355416] anon flags: 0x2ffff8000000000(node=0|zone=2|lastcpupid=0x1ffff) [ 13.355423] page_type: 0xffffefff(slab) [ 13.355429] raw: 02ffff8000000000 ffff8881000428c0 ffffea0004c43a00 0000000000000005 [ 13.355435] raw: 0000000000000000 0000000000200020 00000001ffffefff 0000000000000000 [ 13.355439] page dumped because: kasan: bad access detected [ 13.357295] Memory state around the buggy address: [ 13.357299] ffff88813152f300: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc [ 13.357303] ffff88813152f380: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc [ 13.357306] >ffff88813152f400: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc [ 13.357309] ^ [ 13.357311] ffff88813152f480: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc [ 13.357315] ffff88813152f500: 00 00 00 00 00 00 00 06 fc fc fc fc fc fc fc fc [ 13.357318] ================================================================== [ 13.357405] Disabling lock debugging due to kernel taint [ 13.383534] Oops: general protection fault, probably for non-canonical address 0xe0a1bc4140000013: 0000 [#1] PREEMPT SMP KASAN NOPTI [ 13.383544] KASAN: maybe wild-memory-access in range [0x050e020a00000098-0x050e020a0000009f] [ 13.383551] CPU: 3 PID: 479 Comm: (udev-worker) Tainted: G B 6.10.0-arch1-2 #1 893bb55d7f0073f25c46adbb49eb3785fefd74b0 [ 13.383561] Hardware name: LENOVO 21CQCTO1WW/21CQCTO1WW, BIOS R22ET70W (1.40 ) 03/21/2024 [ 13.383565] RIP: 0010:amd_sfh_get_report+0x81/0x530 [amd_sfh] [ 13.383580] Code: 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 78 03 00 00 48 b8 00 00 00 00 00 fc ff df 4c 8b 63 08 49 8d 7c 24 10 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e 1a 03 00 00 45 8b 74 24 10 45 [ 13.383585] RSP: 0018:ffff8881261f7388 EFLAGS: 00010212 [ 13.383592] RAX: dffffc0000000000 RBX: ffff88813152f400 RCX: 0000000000000002 [ 13.383597] RDX: 00a1c04140000013 RSI: 0000000000000008 RDI: 050e020a0000009b [ 13.383600] RBP: ffff88814d010000 R08: 0000000000000002 R09: fffffbfff3ddb8c0 [ 13.383604] R10: ffffffff9eedc607 R11: ffff88810ce98000 R12: 050e020a0000008b [ 13.383607] R13: ffff88814d010000 R14: dffffc0000000000 R15: 0000000000000004 [ 13.383611] FS: 00007a21f94d0880(0000) GS:ffff8887e7d80000(0000) knlGS:0000000000000000 [ 13.383615] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 13.383618] CR2: 00007e0014c438f0 CR3: 000000012614c000 CR4: 0000000000f50ef0 [ 13.383622] PKRU: 55555554 [ 13.383625] Call Trace: [ 13.383629] [ 13.383632] ? __die_body.cold+0x19/0x27 [ 13.383644] ? die_addr+0x46/0x70 [ 13.383652] ? exc_general_protection+0x150/0x240 [ 13.383664] ? asm_exc_general_protection+0x26/0x30 [ 13.383674] ? amd_sfh_get_report+0x81/0x530 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38] [ 13.383686] ? amd_sfh_get_report+0x3ec/0x530 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38] [ 13.383697] amdtp_hid_request+0xb8/0x110 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38] [ 13.383706] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.383713] sensor_hub_get_feature+0x1d3/0x540 [hid_sensor_hub 3f13be3016ff415bea03008d45d99da837ee3082] [ 13.383727] hid_sensor_parse_common_attributes+0x4d0/0xad0 [hid_sensor_iio_common c3a5cbe93969c28b122609768bbe23efe52eb8f5] [ 13.383739] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.383745] ? __pfx_hid_sensor_parse_common_attributes+0x10/0x10 [hid_sensor_iio_common c3a5cbe93969c28b122609768bbe23efe52eb8f5] [ 13.383753] ? _raw_spin_lock_irqsave+0x96/0xf0 [ 13.383762] ? __pfx__raw_spin_lock_irqsave+0x10/0x10 [ 13.383768] ? devm_iio_device_alloc+0x34/0x50 [industrialio 3d261d5e5765625d2b052be40e526d62b1d2123b] [ 13.383790] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.383795] ? __devm_add_action+0x167/0x1d0 [ 13.383806] hid_gyro_3d_probe+0x120/0x7f0 [hid_sensor_gyro_3d 63da36a143b775846ab2dbb86c343b401b5e3172] [ 13.383818] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.383826] platform_probe+0xa2/0x150 [ 13.383832] really_probe+0x1e3/0x8a0 [ 13.383838] __driver_probe_device+0x18c/0x370 [ 13.383844] driver_probe_device+0x4a/0x120 [ 13.383851] __driver_attach+0x190/0x4a0 [ 13.383857] ? __pfx___driver_attach+0x10/0x10 [ 13.383863] bus_for_each_dev+0x106/0x180 [ 13.383868] ? __pfx__raw_spin_lock+0x10/0x10 [ 13.383874] ? __pfx_bus_for_each_dev+0x10/0x10 [ 13.383880] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.383887] bus_add_driver+0x29e/0x4d0 [ 13.383895] driver_register+0x1a5/0x360 [ 13.383902] ? __pfx_hid_gyro_3d_platform_driver_init+0x10/0x10 [hid_sensor_gyro_3d 63da36a143b775846ab2dbb86c343b401b5e3172] [ 13.383910] do_one_initcall+0xa7/0x380 [ 13.383919] ? __pfx_do_one_initcall+0x10/0x10 [ 13.383927] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.383933] ? kasan_unpoison+0x44/0x70 [ 13.383943] do_init_module+0x238/0x750 [ 13.383955] load_module+0x5011/0x6af0 [ 13.383962] ? kasan_save_stack+0x30/0x50 [ 13.383968] ? kasan_save_track+0x14/0x30 [ 13.383973] ? kasan_save_free_info+0x3b/0x60 [ 13.383980] ? poison_slab_object+0x109/0x180 [ 13.383993] ? __pfx_load_module+0x10/0x10 [ 13.384007] ? poison_slab_object+0x109/0x180 [ 13.384012] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.384018] ? init_module_from_file+0x13d/0x150 [ 13.384025] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.384032] ? init_module_from_file+0xdf/0x150 [ 13.384037] init_module_from_file+0xdf/0x150 [ 13.384044] ? __pfx_init_module_from_file+0x10/0x10 [ 13.384050] ? kasan_save_track+0x14/0x30 [ 13.384055] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.384060] ? kasan_save_free_info+0x3b/0x60 [ 13.384066] ? poison_slab_object+0x109/0x180 [ 13.384071] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.384080] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.384085] ? _raw_spin_lock+0x85/0xe0 [ 13.384091] ? __pfx__raw_spin_lock+0x10/0x10 [ 13.384096] ? __rseq_handle_notify_resume+0x1a6/0xad0 [ 13.384106] idempotent_init_module+0x23b/0x650 [ 13.384114] ? __pfx_idempotent_init_module+0x10/0x10 [ 13.384120] ? __pfx___seccomp_filter+0x10/0x10 [ 13.384129] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.384135] ? __fget_light+0x57/0x420 [ 13.384142] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.384147] ? security_capable+0x74/0xb0 [ 13.384157] __x64_sys_finit_module+0xbe/0x130 [ 13.384164] do_syscall_64+0x82/0x190 [ 13.384174] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.384179] ? irqtime_account_irq+0x3d/0x1f0 [ 13.384188] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.384193] ? __irq_exit_rcu+0x4e/0x130 [ 13.384201] ? srso_alias_return_thunk+0x5/0xfbef5 [ 13.384206] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 13.384212] RIP: 0033:0x7a21f96ade9d [ 13.384263] Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 63 de 0c 00 f7 d8 64 89 01 48 [ 13.384267] RSP: 002b:00007ffeae934e78 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 [ 13.384273] RAX: ffffffffffffffda RBX: 00005987276bfcf0 RCX: 00007a21f96ade9d [ 13.384277] RDX: 0000000000000004 RSI: 00007a21f8eda376 RDI: 000000000000001c [ 13.384280] RBP: 00007a21f8eda376 R08: 0000000000000001 R09: 00007ffeae934ec0 [ 13.384284] R10: 0000000000000050 R11: 0000000000000246 R12: 0000000000020000 [ 13.384288] R13: 00005987276c1250 R14: 0000000000000000 R15: 00005987276c4530 [ 13.384297] [ 13.384299] Modules linked in: soundwire_amd(+) hid_sensor_gyro_3d(+) hid_sensor_magn_3d hid_sensor_accel_3d soundwire_generic_allocation amdxcp hid_sensor_trigger drm_exec industrialio_triggered_buffer soundwire_bus gpu_sched kvm_amd kfifo_buf qmi_helpers joydev drm_buddy hid_sensor_iio_common mousedev snd_soc_core industrialio i2c_algo_bit mac80211 snd_compress drm_suballoc_helper kvm snd_hda_intel drm_ttm_helper ac97_bus snd_pcm_dmaengine snd_intel_dspcfg ttm thinkpad_acpi(+) snd_intel_sdw_acpi hid_sensor_hub snd_rpl_pci_acp6x drm_display_helper snd_hda_codec hid_multitouch libarc4 snd_acp_pci platform_profile think_lmi(+) hid_generic firmware_attributes_class wmi_bmof cec snd_acp_legacy_common sparse_keymap rapl snd_hda_core psmouse cfg80211 pcspkr snd_pci_acp6x snd_hwdep video snd_pcm snd_pci_acp5x snd_timer snd_rn_pci_acp3x ucsi_acpi snd_acp_config snd sp5100_tco rfkill snd_soc_acpi typec_ucsi thunderbolt amd_sfh k10temp mhi soundcore i2c_piix4 snd_pci_acp3x typec i2c_hid_acpi roles i2c_hid wmi acpi_tad amd_pmc [ 13.384454] mac_hid i2c_dev crypto_user loop nfnetlink zram ip_tables x_tables dm_crypt cbc encrypted_keys trusted asn1_encoder tee dm_mod crct10dif_pclmul crc32_pclmul polyval_clmulni polyval_generic gf128mul ghash_clmulni_intel serio_raw sha512_ssse3 atkbd sha256_ssse3 libps2 sha1_ssse3 vivaldi_fmap nvme aesni_intel crypto_simd nvme_core cryptd ccp xhci_pci i8042 nvme_auth xhci_pci_renesas serio vfat fat btrfs blake2b_generic libcrc32c crc32c_generic crc32c_intel xor raid6_pq [ 13.384552] ---[ end trace 0000000000000000 ]--- KASAN reports a use-after-free of hid->driver_data in function amd_sfh_get_report(). The backtrace indicates that the function is called by amdtp_hid_request() which is one of the callbacks of hid device. The current make sure that driver_data is freed only once hid_destroy_device() returned. Note that I observed the crash both on v6.9.9 and v6.10.0. The code seems to be as it was from the early days of the driver. Signed-off-by: Olivier Sobrie Acked-by: Basavaraj Natikar Signed-off-by: Jiri Kosina --- drivers/hid/amd-sfh-hid/amd_sfh_hid.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_hid.c b/drivers/hid/amd-sfh-hid/amd_sfh_hid.c index 705b52337068..81f3024b7b1b 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_hid.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_hid.c @@ -171,11 +171,13 @@ err_hid_data: void amdtp_hid_remove(struct amdtp_cl_data *cli_data) { int i; + struct amdtp_hid_data *hid_data; for (i = 0; i < cli_data->num_hid_devices; ++i) { if (cli_data->hid_sensor_hubs[i]) { - kfree(cli_data->hid_sensor_hubs[i]->driver_data); + hid_data = cli_data->hid_sensor_hubs[i]->driver_data; hid_destroy_device(cli_data->hid_sensor_hubs[i]); + kfree(hid_data); cli_data->hid_sensor_hubs[i] = NULL; } } From c8000deb68365b461b324d68c7ea89d730f0bb85 Mon Sep 17 00:00:00 2001 From: Dmitry Savin Date: Tue, 16 Jul 2024 23:27:57 +0100 Subject: [PATCH 016/562] HID: multitouch: Add support for GT7868Q GT7868Q has incorrect data in the report and needs a fixup. The change enables haptic touchpad on Lenovo ThinkBook 13x Gen 4 and has been tested on the device. Signed-off-by: Dmitry Savin Signed-off-by: Jiri Kosina --- drivers/hid/hid-ids.h | 2 ++ drivers/hid/hid-multitouch.c | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 6e3223389080..781c5aa29859 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -521,6 +521,8 @@ #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100 0xe100 #define I2C_VENDOR_ID_GOODIX 0x27c6 +#define I2C_DEVICE_ID_GOODIX_01E8 0x01e8 +#define I2C_DEVICE_ID_GOODIX_01E9 0x01e9 #define I2C_DEVICE_ID_GOODIX_01F0 0x01f0 #define USB_VENDOR_ID_GOODTOUCH 0x1aad diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 56fc78841f24..99812c0f830b 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1441,6 +1441,30 @@ static int mt_event(struct hid_device *hid, struct hid_field *field, return 0; } +static __u8 *mt_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *size) +{ + if (hdev->vendor == I2C_VENDOR_ID_GOODIX && + (hdev->product == I2C_DEVICE_ID_GOODIX_01E8 || + hdev->product == I2C_DEVICE_ID_GOODIX_01E9)) { + if (rdesc[607] == 0x15) { + rdesc[607] = 0x25; + dev_info( + &hdev->dev, + "GT7868Q report descriptor fixup is applied.\n"); + } else { + dev_info( + &hdev->dev, + "The byte is not expected for fixing the report descriptor. \ +It's possible that the touchpad firmware is not suitable for applying the fix. \ +got: %x\n", + rdesc[607]); + } + } + + return rdesc; +} + static void mt_report(struct hid_device *hid, struct hid_report *report) { struct mt_device *td = hid_get_drvdata(hid); @@ -2035,6 +2059,14 @@ static const struct hid_device_id mt_devices[] = { MT_BT_DEVICE(USB_VENDOR_ID_FRUCTEL, USB_DEVICE_ID_GAMETEL_MT_MODE) }, + /* Goodix GT7868Q devices */ + { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU, + HID_DEVICE(BUS_I2C, HID_GROUP_ANY, I2C_VENDOR_ID_GOODIX, + I2C_DEVICE_ID_GOODIX_01E8) }, + { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU, + HID_DEVICE(BUS_I2C, HID_GROUP_ANY, I2C_VENDOR_ID_GOODIX, + I2C_DEVICE_ID_GOODIX_01E8) }, + /* GoodTouch panels */ { .driver_data = MT_CLS_NSMU, MT_USB_DEVICE(USB_VENDOR_ID_GOODTOUCH, @@ -2270,6 +2302,7 @@ static struct hid_driver mt_driver = { .feature_mapping = mt_feature_mapping, .usage_table = mt_grabbed_usages, .event = mt_event, + .report_fixup = mt_report_fixup, .report = mt_report, .suspend = pm_ptr(mt_suspend), .reset_resume = pm_ptr(mt_reset_resume), From 1b8f9c1fb464968a5b18d3acc1da8c00bad24fad Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Tue, 30 Jul 2024 08:51:55 -0700 Subject: [PATCH 017/562] HID: wacom: Defer calculation of resolution until resolution_code is known The Wacom driver maps the HID_DG_TWIST usage to ABS_Z (rather than ABS_RZ) for historic reasons. When the code to support twist was introduced in commit 50066a042da5 ("HID: wacom: generic: Add support for height, tilt, and twist usages"), we were careful to write it in such a way that it had HID calculate the resolution of the twist axis assuming ABS_RZ instead (so that we would get correct angular behavior). This was broken with the introduction of commit 08a46b4190d3 ("HID: wacom: Set a default resolution for older tablets"), which moved the resolution calculation to occur *before* the adjustment from ABS_Z to ABS_RZ occurred. This commit moves the calculation of resolution after the point that we are finished setting things up for its proper use. Signed-off-by: Jason Gerecke Fixes: 08a46b4190d3 ("HID: wacom: Set a default resolution for older tablets") Cc: stable@vger.kernel.org Signed-off-by: Jiri Kosina --- drivers/hid/wacom_wac.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 1f4564982b95..2541fa2e0fa3 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1878,12 +1878,14 @@ static void wacom_map_usage(struct input_dev *input, struct hid_usage *usage, int fmax = field->logical_maximum; unsigned int equivalent_usage = wacom_equivalent_usage(usage->hid); int resolution_code = code; - int resolution = hidinput_calc_abs_res(field, resolution_code); + int resolution; if (equivalent_usage == HID_DG_TWIST) { resolution_code = ABS_RZ; } + resolution = hidinput_calc_abs_res(field, resolution_code); + if (equivalent_usage == HID_GD_X) { fmin += features->offset_left; fmax -= features->offset_right; From fca5b78511e98bdff2cdd55c172b23200a7b3404 Mon Sep 17 00:00:00 2001 From: Barak Biber Date: Thu, 1 Aug 2024 09:26:04 -0300 Subject: [PATCH 018/562] iommu: Restore lost return in iommu_report_device_fault() When iommu_report_device_fault gets called with a partial fault it is supposed to collect the fault into the group and then return. Instead the return was accidently deleted which results in trying to process the fault and an eventual crash. Deleting the return was a typo, put it back. Fixes: 3dfa64aecbaf ("iommu: Make iommu_report_device_fault() return void") Signed-off-by: Barak Biber Signed-off-by: Jason Gunthorpe Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/0-v1-e7153d9c8cee+1c6-iommu_fault_fix_jgg@nvidia.com Signed-off-by: Joerg Roedel --- drivers/iommu/io-pgfault.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c index cd679c13752e..81e9cc6e3164 100644 --- a/drivers/iommu/io-pgfault.c +++ b/drivers/iommu/io-pgfault.c @@ -170,6 +170,7 @@ void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) report_partial_fault(iopf_param, fault); iopf_put_dev_fault_param(iopf_param); /* A request that is not the last does not need to be ack'd */ + return; } /* From 90ec3a8a7fd0d43026fcca979713e077d4883b56 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Fri, 2 Aug 2024 16:22:13 +0100 Subject: [PATCH 019/562] spi: Add empty versions of ACPI functions Provide empty versions of acpi_spi_count_resources(), acpi_spi_device_alloc() and acpi_spi_find_controller_by_adev() if the real functions are not being built. This commit fixes two problems with the original definitions: 1) There wasn't an empty version of these functions 2) The #if only depended on CONFIG_ACPI. But the functions are implemented in the core spi.c so CONFIG_SPI_MASTER must also be enabled for the real functions to exist. Signed-off-by: Richard Fitzgerald Link: https://patch.msgid.link/20240802152215.20831-2-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index e4f3f3d30a03..d47d5f14ff99 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -902,12 +902,29 @@ extern int devm_spi_register_controller(struct device *dev, struct spi_controller *ctlr); extern void spi_unregister_controller(struct spi_controller *ctlr); -#if IS_ENABLED(CONFIG_ACPI) +#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_SPI_MASTER) extern struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev); extern struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, struct acpi_device *adev, int index); int acpi_spi_count_resources(struct acpi_device *adev); +#else +static inline struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev) +{ + return NULL; +} + +static inline struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, + struct acpi_device *adev, + int index) +{ + return ERR_PTR(-ENODEV); +} + +static inline int acpi_spi_count_resources(struct acpi_device *adev) +{ + return 0; +} #endif /* From 32b9a52f88a5713bf8a02dae66f2ad69705de69f Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Tue, 23 Jul 2024 16:20:52 +0200 Subject: [PATCH 020/562] KVM: arm64: free kvm->arch.nested_mmus with kvfree() kvm->arch.nested_mmus is allocated with kvrealloc(), hence free it with kvfree() instead of kfree(). Fixes: 4f128f8e1aaa ("KVM: arm64: nv: Support multiple nested Stage-2 mmu structures") Signed-off-by: Danilo Krummrich Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20240723142204.758796-1-dakr@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/kvm/nested.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index de789e0f1ae9..bab27f9d8cc6 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -786,7 +786,7 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm) if (!WARN_ON(atomic_read(&mmu->refcnt))) kvm_free_stage2_pgd(mmu); } - kfree(kvm->arch.nested_mmus); + kvfree(kvm->arch.nested_mmus); kvm->arch.nested_mmus = NULL; kvm->arch.nested_mmus_size = 0; kvm_uninit_stage2_mmu(kvm); From 963a08e586bd45fd55f4c1752e98029ce83fc091 Mon Sep 17 00:00:00 2001 From: Sebastian Ott Date: Tue, 23 Jul 2024 12:12:02 +0200 Subject: [PATCH 021/562] KVM: arm64: fix override-init warnings in W=1 builds Add -Wno-override-init to the build flags for sys_regs.c, handle_exit.c, and switch.c to fix warnings like the following: arch/arm64/kvm/hyp/vhe/switch.c:271:43: warning: initialized field overwritten [-Woverride-init] 271 | [ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32, | Signed-off-by: Sebastian Ott Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20240723101204.7356-2-sebott@redhat.com Signed-off-by: Oliver Upton --- arch/arm64/kvm/Makefile | 3 +++ arch/arm64/kvm/hyp/nvhe/Makefile | 2 ++ arch/arm64/kvm/hyp/vhe/Makefile | 2 ++ 3 files changed, 7 insertions(+) diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index a6497228c5a8..86a629aaf0a1 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -10,6 +10,9 @@ include $(srctree)/virt/kvm/Makefile.kvm obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM) += hyp/ +CFLAGS_sys_regs.o += -Wno-override-init +CFLAGS_handle_exit.o += -Wno-override-init + kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \ inject_fault.o va_layout.o handle_exit.o \ guest.o debug.o reset.o sys_regs.o stacktrace.o \ diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index 782b34b004be..b43426a493df 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -20,6 +20,8 @@ HOST_EXTRACFLAGS += -I$(objtree)/include lib-objs := clear_page.o copy_page.o memcpy.o memset.o lib-objs := $(addprefix ../../../lib/, $(lib-objs)) +CFLAGS_switch.nvhe.o += -Wno-override-init + hyp-obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \ hyp-main.o hyp-smp.o psci-relay.o early_alloc.o page_alloc.o \ cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o stacktrace.o ffa.o diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile index 3b9e5464b5b3..afc4aed9231a 100644 --- a/arch/arm64/kvm/hyp/vhe/Makefile +++ b/arch/arm64/kvm/hyp/vhe/Makefile @@ -6,6 +6,8 @@ asflags-y := -D__KVM_VHE_HYPERVISOR__ ccflags-y := -D__KVM_VHE_HYPERVISOR__ +CFLAGS_switch.o += -Wno-override-init + obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ ../fpsimd.o ../hyp-entry.o ../exception.o From 0aa34b37a78d063da58838b84b20a68a94d919fd Mon Sep 17 00:00:00 2001 From: Sebastian Ott Date: Tue, 23 Jul 2024 12:12:03 +0200 Subject: [PATCH 022/562] KVM: arm64: fix kdoc warnings in W=1 builds Fix kdoc warnings by adding missing function parameter descriptions or by conversion to a normal comment. Signed-off-by: Sebastian Ott Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20240723101204.7356-3-sebott@redhat.com Signed-off-by: Oliver Upton --- arch/arm64/kvm/arm.c | 1 + arch/arm64/kvm/vgic/vgic-irqfd.c | 7 ++++--- arch/arm64/kvm/vgic/vgic-its.c | 18 +++++++++++------- arch/arm64/kvm/vgic/vgic-v3.c | 2 +- 4 files changed, 17 insertions(+), 11 deletions(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index a7ca776b51ec..23e1fa56c02d 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -164,6 +164,7 @@ static int kvm_arm_default_max_vcpus(void) /** * kvm_arch_init_vm - initializes a VM data structure * @kvm: pointer to the KVM struct + * @type: kvm device type */ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { diff --git a/arch/arm64/kvm/vgic/vgic-irqfd.c b/arch/arm64/kvm/vgic/vgic-irqfd.c index 8c711deb25aa..c314c016659a 100644 --- a/arch/arm64/kvm/vgic/vgic-irqfd.c +++ b/arch/arm64/kvm/vgic/vgic-irqfd.c @@ -9,7 +9,7 @@ #include #include "vgic.h" -/** +/* * vgic_irqfd_set_irq: inject the IRQ corresponding to the * irqchip routing entry * @@ -75,7 +75,8 @@ static void kvm_populate_msi(struct kvm_kernel_irq_routing_entry *e, msi->flags = e->msi.flags; msi->devid = e->msi.devid; } -/** + +/* * kvm_set_msi: inject the MSI corresponding to the * MSI routing entry * @@ -98,7 +99,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, return vgic_its_inject_msi(kvm, &msi); } -/** +/* * kvm_arch_set_irq_inatomic: fast-path for irqfd injection */ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 40bb43f20bf3..ba945ba78cc7 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2040,6 +2040,7 @@ typedef int (*entry_fn_t)(struct vgic_its *its, u32 id, void *entry, * @start_id: the ID of the first entry in the table * (non zero for 2d level tables) * @fn: function to apply on each entry + * @opaque: pointer to opaque data * * Return: < 0 on error, 0 if last element was identified, 1 otherwise * (the last element may not be found on second level tables) @@ -2079,7 +2080,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz, return 1; } -/** +/* * vgic_its_save_ite - Save an interrupt translation entry at @gpa */ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, @@ -2099,6 +2100,8 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, /** * vgic_its_restore_ite - restore an interrupt translation entry + * + * @its: its handle * @event_id: id used for indexing * @ptr: pointer to the ITE entry * @opaque: pointer to the its_device @@ -2231,6 +2234,7 @@ static int vgic_its_restore_itt(struct vgic_its *its, struct its_device *dev) * @its: ITS handle * @dev: ITS device * @ptr: GPA + * @dte_esz: device table entry size */ static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev, gpa_t ptr, int dte_esz) @@ -2313,7 +2317,7 @@ static int vgic_its_device_cmp(void *priv, const struct list_head *a, return 1; } -/** +/* * vgic_its_save_device_tables - Save the device table and all ITT * into guest RAM * @@ -2386,7 +2390,7 @@ static int handle_l1_dte(struct vgic_its *its, u32 id, void *addr, return ret; } -/** +/* * vgic_its_restore_device_tables - Restore the device table and all ITT * from guest RAM to internal data structs */ @@ -2478,7 +2482,7 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz) return 1; } -/** +/* * vgic_its_save_collection_table - Save the collection table into * guest RAM */ @@ -2518,7 +2522,7 @@ static int vgic_its_save_collection_table(struct vgic_its *its) return ret; } -/** +/* * vgic_its_restore_collection_table - reads the collection table * in guest memory and restores the ITS internal state. Requires the * BASER registers to be restored before. @@ -2556,7 +2560,7 @@ static int vgic_its_restore_collection_table(struct vgic_its *its) return ret; } -/** +/* * vgic_its_save_tables_v0 - Save the ITS tables into guest ARM * according to v0 ABI */ @@ -2571,7 +2575,7 @@ static int vgic_its_save_tables_v0(struct vgic_its *its) return vgic_its_save_collection_table(its); } -/** +/* * vgic_its_restore_tables_v0 - Restore the ITS tables from guest RAM * to internal data structs according to V0 ABI * diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index ed6e412cd74b..3eecdd2f4b8f 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -370,7 +370,7 @@ static void map_all_vpes(struct kvm *kvm) dist->its_vm.vpes[i]->irq)); } -/** +/* * vgic_v3_save_pending_tables - Save the pending tables into guest RAM * kvm lock and all vcpu lock must be held */ From 19d837bc881b2f9f72f9eb506b46c2e2d983896d Mon Sep 17 00:00:00 2001 From: Sebastian Ott Date: Tue, 23 Jul 2024 12:12:04 +0200 Subject: [PATCH 023/562] KVM: arm64: vgic: fix unexpected unlock sparse warnings Get rid of unexpected unlock sparse warnings in vgic code by adding an annotation to vgic_queue_irq_unlock(). arch/arm64/kvm/vgic/vgic.c:334:17: warning: context imbalance in 'vgic_queue_irq_unlock' - unexpected unlock arch/arm64/kvm/vgic/vgic.c:419:5: warning: context imbalance in 'kvm_vgic_inject_irq' - different lock contexts for basic block Signed-off-by: Sebastian Ott Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20240723101204.7356-4-sebott@redhat.com Signed-off-by: Oliver Upton --- arch/arm64/kvm/vgic/vgic.c | 2 +- arch/arm64/kvm/vgic/vgic.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index f07b3ddff7d4..974849ea7101 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -313,7 +313,7 @@ static bool vgic_validate_injection(struct vgic_irq *irq, bool level, void *owne * with all locks dropped. */ bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, - unsigned long flags) + unsigned long flags) __releases(&irq->irq_lock) { struct kvm_vcpu *vcpu; diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 03d356a12377..ba8f790431bd 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -186,7 +186,7 @@ bool vgic_get_phys_line_level(struct vgic_irq *irq); void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending); void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active); bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, - unsigned long flags); + unsigned long flags) __releases(&irq->irq_lock); void vgic_kick_vcpus(struct kvm *kvm); void vgic_irq_handle_resampling(struct vgic_irq *irq, bool lr_deactivated, bool lr_pending); From 70d76b0e85ad126358baec1b44f797e61e3ebecc Mon Sep 17 00:00:00 2001 From: Felix Kaechele Date: Sat, 3 Aug 2024 23:13:09 -0400 Subject: [PATCH 024/562] dt-bindings: input: touchscreen: edt-ft5x06: Document FT8201 support Document FocalTech FT8201 support by adding the compatible. Signed-off-by: Felix Kaechele Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20240804031310.331871-2-felix@kaechele.ca Signed-off-by: Dmitry Torokhov --- .../devicetree/bindings/input/touchscreen/edt-ft5x06.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml index 379721027bf8..51d48d4130d3 100644 --- a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml +++ b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml @@ -42,6 +42,7 @@ properties: - focaltech,ft5426 - focaltech,ft5452 - focaltech,ft6236 + - focaltech,ft8201 - focaltech,ft8719 reg: From fc289d3e8698f9b11edad6d73f371ebf35944c57 Mon Sep 17 00:00:00 2001 From: Felix Kaechele Date: Sat, 3 Aug 2024 23:13:10 -0400 Subject: [PATCH 025/562] Input: edt-ft5x06 - add support for FocalTech FT8201 The driver supports the FT8201 chip as well. It registers up to 10 touch points. Tested on: Lenovo ThinkSmart View (CD-18781Y), LCM: BOE TV080WXM-LL4 Signed-off-by: Felix Kaechele Link: https://lore.kernel.org/r/20240804031310.331871-3-felix@kaechele.ca Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/edt-ft5x06.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index 42f99e57fbb7..e70415f189a5 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -1474,6 +1474,10 @@ static const struct edt_i2c_chip_data edt_ft6236_data = { .max_support_points = 2, }; +static const struct edt_i2c_chip_data edt_ft8201_data = { + .max_support_points = 10, +}; + static const struct edt_i2c_chip_data edt_ft8719_data = { .max_support_points = 10, }; @@ -1485,6 +1489,7 @@ static const struct i2c_device_id edt_ft5x06_ts_id[] = { { .name = "ft5452", .driver_data = (long)&edt_ft5452_data }, /* Note no edt- prefix for compatibility with the ft6236.c driver */ { .name = "ft6236", .driver_data = (long)&edt_ft6236_data }, + { .name = "ft8201", .driver_data = (long)&edt_ft8201_data }, { .name = "ft8719", .driver_data = (long)&edt_ft8719_data }, { /* sentinel */ } }; @@ -1500,6 +1505,7 @@ static const struct of_device_id edt_ft5x06_of_match[] = { { .compatible = "focaltech,ft5452", .data = &edt_ft5452_data }, /* Note focaltech vendor prefix for compatibility with ft6236.c */ { .compatible = "focaltech,ft6236", .data = &edt_ft6236_data }, + { .compatible = "focaltech,ft8201", .data = &edt_ft8201_data }, { .compatible = "focaltech,ft8719", .data = &edt_ft8719_data }, { /* sentinel */ } }; From 206f533a0a7c683982af473079c4111f4a0f9f5e Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sun, 4 Aug 2024 17:50:25 -0700 Subject: [PATCH 026/562] Input: uinput - reject requests with unreasonable number of slots From: Dmitry Torokhov When exercising uinput interface syzkaller may try setting up device with a really large number of slots, which causes memory allocation failure in input_mt_init_slots(). While this allocation failure is handled properly and request is rejected, it results in syzkaller reports. Additionally, such request may put undue burden on the system which will try to free a lot of memory for a bogus request. Fix it by limiting allowed number of slots to 100. This can easily be extended if we see devices that can track more than 100 contacts. Reported-by: Tetsuo Handa Reported-by: syzbot Closes: https://syzkaller.appspot.com/bug?extid=0122fa359a69694395d5 Link: https://lore.kernel.org/r/Zqgi7NYEbpRsJfa2@google.com Signed-off-by: Dmitry Torokhov --- drivers/input/misc/uinput.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index d23f3225b00f..445856c9127a 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -417,6 +417,20 @@ static int uinput_validate_absinfo(struct input_dev *dev, unsigned int code, return -EINVAL; } + /* + * Limit number of contacts to a reasonable value (100). This + * ensures that we need less than 2 pages for struct input_mt + * (we are not using in-kernel slot assignment so not going to + * allocate memory for the "red" table), and we should have no + * trouble getting this much memory. + */ + if (code == ABS_MT_SLOT && max > 99) { + printk(KERN_DEBUG + "%s: unreasonably large number of slots requested: %d\n", + UINPUT_NAME, max); + return -EINVAL; + } + return 0; } From 38055789d15155109b41602ad719d770af507030 Mon Sep 17 00:00:00 2001 From: Baochen Qiang Date: Thu, 1 Aug 2024 18:04:07 +0300 Subject: [PATCH 027/562] wifi: ath12k: use 128 bytes aligned iova in transmit path for WCN7850 In transmit path, it is likely that the iova is not aligned to PCIe TLP max payload size, which is 128 for WCN7850. Normally in such cases hardware is expected to split the packet into several parts in a manner such that they, other than the first one, have aligned iova. However due to hardware limitations, WCN7850 does not behave like that properly with some specific unaligned iova in transmit path. This easily results in target hang in a KPI transmit test: packet send/receive failure, WMI command send timeout etc. Also fatal error seen in PCIe level: ... Capabilities: ... ... DevSta: ... FatalErr+ ... ... ... Work around this by manually moving/reallocating payload buffer such that we can map it to a 128 bytes aligned iova. The moving requires sufficient head room or tail room in skb: for the former we can do ourselves a favor by asking some extra bytes when registering with mac80211, while for the latter we can do nothing. Moving/reallocating buffer consumes additional CPU cycles, but the good news is that an aligned iova increases PCIe efficiency. In my tests on some X86 platforms the KPI results are almost consistent. Since this is seen only with WCN7850, add a new hardware parameter to differentiate from others. Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3 Signed-off-by: Baochen Qiang Cc: Tested-by: Mark Pearson Signed-off-by: Kalle Valo Link: https://patch.msgid.link/20240715023814.20242-1-quic_bqiang@quicinc.com --- drivers/net/wireless/ath/ath12k/dp_tx.c | 72 +++++++++++++++++++++++++ drivers/net/wireless/ath/ath12k/hw.c | 6 +++ drivers/net/wireless/ath/ath12k/hw.h | 4 ++ drivers/net/wireless/ath/ath12k/mac.c | 1 + 4 files changed, 83 insertions(+) diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c index d08c04343e90..44406e0b4a34 100644 --- a/drivers/net/wireless/ath/ath12k/dp_tx.c +++ b/drivers/net/wireless/ath/ath12k/dp_tx.c @@ -162,6 +162,60 @@ static int ath12k_dp_prepare_htt_metadata(struct sk_buff *skb) return 0; } +static void ath12k_dp_tx_move_payload(struct sk_buff *skb, + unsigned long delta, + bool head) +{ + unsigned long len = skb->len; + + if (head) { + skb_push(skb, delta); + memmove(skb->data, skb->data + delta, len); + skb_trim(skb, len); + } else { + skb_put(skb, delta); + memmove(skb->data + delta, skb->data, len); + skb_pull(skb, delta); + } +} + +static int ath12k_dp_tx_align_payload(struct ath12k_base *ab, + struct sk_buff **pskb) +{ + u32 iova_mask = ab->hw_params->iova_mask; + unsigned long offset, delta1, delta2; + struct sk_buff *skb2, *skb = *pskb; + unsigned int headroom = skb_headroom(skb); + int tailroom = skb_tailroom(skb); + int ret = 0; + + offset = (unsigned long)skb->data & iova_mask; + delta1 = offset; + delta2 = iova_mask - offset + 1; + + if (headroom >= delta1) { + ath12k_dp_tx_move_payload(skb, delta1, true); + } else if (tailroom >= delta2) { + ath12k_dp_tx_move_payload(skb, delta2, false); + } else { + skb2 = skb_realloc_headroom(skb, iova_mask); + if (!skb2) { + ret = -ENOMEM; + goto out; + } + + dev_kfree_skb_any(skb); + + offset = (unsigned long)skb2->data & iova_mask; + if (offset) + ath12k_dp_tx_move_payload(skb2, offset, true); + *pskb = skb2; + } + +out: + return ret; +} + int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif, struct sk_buff *skb) { @@ -184,6 +238,7 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif, bool tcl_ring_retry; bool msdu_ext_desc = false; bool add_htt_metadata = false; + u32 iova_mask = ab->hw_params->iova_mask; if (test_bit(ATH12K_FLAG_CRASH_FLUSH, &ar->ab->dev_flags)) return -ESHUTDOWN; @@ -279,6 +334,23 @@ tcl_ring_sel: goto fail_remove_tx_buf; } + if (iova_mask && + (unsigned long)skb->data & iova_mask) { + ret = ath12k_dp_tx_align_payload(ab, &skb); + if (ret) { + ath12k_warn(ab, "failed to align TX buffer %d\n", ret); + /* don't bail out, give original buffer + * a chance even unaligned. + */ + goto map; + } + + /* hdr is pointing to a wrong place after alignment, + * so refresh it for later use. + */ + hdr = (void *)skb->data; + } +map: ti.paddr = dma_map_single(ab->dev, skb->data, skb->len, DMA_TO_DEVICE); if (dma_mapping_error(ab->dev, ti.paddr)) { atomic_inc(&ab->soc_stats.tx_err.misc_fail); diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c index 2e11ea763574..7b0b6a7f4701 100644 --- a/drivers/net/wireless/ath/ath12k/hw.c +++ b/drivers/net/wireless/ath/ath12k/hw.c @@ -924,6 +924,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = { .acpi_guid = NULL, .supports_dynamic_smps_6ghz = true, + + .iova_mask = 0, }, { .name = "wcn7850 hw2.0", @@ -1000,6 +1002,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = { .acpi_guid = &wcn7850_uuid, .supports_dynamic_smps_6ghz = false, + + .iova_mask = ATH12K_PCIE_MAX_PAYLOAD_SIZE - 1, }, { .name = "qcn9274 hw2.0", @@ -1072,6 +1076,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = { .acpi_guid = NULL, .supports_dynamic_smps_6ghz = true, + + .iova_mask = 0, }, }; diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h index e792eb6b249b..b1d302c48326 100644 --- a/drivers/net/wireless/ath/ath12k/hw.h +++ b/drivers/net/wireless/ath/ath12k/hw.h @@ -96,6 +96,8 @@ #define ATH12K_M3_FILE "m3.bin" #define ATH12K_REGDB_FILE_NAME "regdb.bin" +#define ATH12K_PCIE_MAX_PAYLOAD_SIZE 128 + enum ath12k_hw_rate_cck { ATH12K_HW_RATE_CCK_LP_11M = 0, ATH12K_HW_RATE_CCK_LP_5_5M, @@ -215,6 +217,8 @@ struct ath12k_hw_params { const guid_t *acpi_guid; bool supports_dynamic_smps_6ghz; + + u32 iova_mask; }; struct ath12k_hw_ops { diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index 8106297f0bc1..ce41c8153080 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -9193,6 +9193,7 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah) hw->vif_data_size = sizeof(struct ath12k_vif); hw->sta_data_size = sizeof(struct ath12k_sta); + hw->extra_tx_headroom = ab->hw_params->iova_mask; wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST); wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_STA_TX_PWR); From 50359c9c3cb3e55e840e3485f5ee37da5b2b16b6 Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Wed, 17 Jul 2024 10:03:33 +0200 Subject: [PATCH 028/562] pmdomain: imx: scu-pd: Remove duplicated clocks These clocks are already added to the list. Remove the duplicates ones. Fixes: a67d780720ff ("genpd: imx: scu-pd: add more PDs") Signed-off-by: Alexander Stein Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240717080334.2210988-1-alexander.stein@ew.tq-group.com Signed-off-by: Ulf Hansson --- drivers/pmdomain/imx/scu-pd.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/pmdomain/imx/scu-pd.c b/drivers/pmdomain/imx/scu-pd.c index 05841b0bf7f3..01d465d88f60 100644 --- a/drivers/pmdomain/imx/scu-pd.c +++ b/drivers/pmdomain/imx/scu-pd.c @@ -223,11 +223,6 @@ static const struct imx_sc_pd_range imx8qxp_scu_pd_ranges[] = { { "lvds1-pwm", IMX_SC_R_LVDS_1_PWM_0, 1, false, 0 }, { "lvds1-lpi2c", IMX_SC_R_LVDS_1_I2C_0, 2, true, 0 }, - { "mipi1", IMX_SC_R_MIPI_1, 1, 0 }, - { "mipi1-pwm0", IMX_SC_R_MIPI_1_PWM_0, 1, 0 }, - { "mipi1-i2c", IMX_SC_R_MIPI_1_I2C_0, 2, 1 }, - { "lvds1", IMX_SC_R_LVDS_1, 1, 0 }, - /* DC SS */ { "dc0", IMX_SC_R_DC_0, 1, false, 0 }, { "dc0-pll", IMX_SC_R_DC_0_PLL_0, 2, true, 0 }, From 042b8711a0beafb2c3b888bebe3c300ab4c817fa Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Thu, 18 Jul 2024 10:24:10 +0200 Subject: [PATCH 029/562] drm/mediatek: Set sensible cursor width/height values to fix crash Hardware-speaking, there is no feature-reduced cursor specific plane, so this driver reserves the last all Overlay plane as a Cursor plane, but sets the maximum cursor width/height to the maximum value that the full overlay plane can use. While this could be ok, it raises issues with common userspace using libdrm (especially Mutter, but other compositors too) which will crash upon performing allocations and/or using said cursor plane. Reduce the maximum width/height for the cursor to 512x512 pixels, value taken from IGT's maximum cursor size test, which succeeds. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Fei Shao Tested-by: Fei Shao Reviewed-by: Daniel Stone Reviewed-by: CK Hu Link: https://patchwork.kernel.org/project/dri-devel/patch/20240718082410.204459-1-angelogioacchino.delregno@collabora.com/ Signed-off-by: Chun-Kuang Hu --- drivers/gpu/drm/mediatek/mtk_drm_drv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index ae5c6ec24a1e..77b50c56c124 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -539,8 +539,8 @@ static int mtk_drm_kms_init(struct drm_device *drm) } /* IGT will check if the cursor size is configured */ - drm->mode_config.cursor_width = drm->mode_config.max_width; - drm->mode_config.cursor_height = drm->mode_config.max_height; + drm->mode_config.cursor_width = 512; + drm->mode_config.cursor_height = 512; /* Use OVL device for all DMA memory allocations */ crtc = drm_crtc_from_index(drm, 0); From 7fef1eb0b013eaa42019a95a08f71368e5a22dba Mon Sep 17 00:00:00 2001 From: Takahiro Itazuri Date: Tue, 6 Jun 2023 16:46:28 +0100 Subject: [PATCH 030/562] docs: KVM: Fix register ID of SPSR_FIQ Fixes the register ID of SPSR_FIQ. SPSR_FIQ is a 64-bit register and the 64-bit register size mask is 0x0030000000000000ULL. Fixes: fd3bc912d3d1 ("KVM: Documentation: Document arm64 core registers in detail") Signed-off-by: Takahiro Itazuri Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20230606154628.95498-1-itazur@amazon.com Signed-off-by: Oliver Upton --- Documentation/virt/kvm/api.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index fe722c5dada9..87865c8897ca 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -2592,7 +2592,7 @@ Specifically: 0x6030 0000 0010 004a SPSR_ABT 64 spsr[KVM_SPSR_ABT] 0x6030 0000 0010 004c SPSR_UND 64 spsr[KVM_SPSR_UND] 0x6030 0000 0010 004e SPSR_IRQ 64 spsr[KVM_SPSR_IRQ] - 0x6060 0000 0010 0050 SPSR_FIQ 64 spsr[KVM_SPSR_FIQ] + 0x6030 0000 0010 0050 SPSR_FIQ 64 spsr[KVM_SPSR_FIQ] 0x6040 0000 0010 0054 V0 128 fp_regs.vregs[0] [1]_ 0x6040 0000 0010 0058 V1 128 fp_regs.vregs[1] [1]_ ... From df24373435f5899a2a98b7d377479c8d4376613b Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 2 Aug 2024 22:47:34 +0300 Subject: [PATCH 031/562] drm/msm/dpu: don't play tricks with debug macros DPU debugging macros need to be converted to a proper drm_debug_* macros, however this is a going an intrusive patch, not suitable for a fix. Wire DPU_DEBUG and DPU_DEBUG_DRIVER to always use DRM_DEBUG_DRIVER to make sure that DPU debugging messages always end up in the drm debug messages and are controlled via the usual drm.debug mask. I don't think that it is a good idea for a generic DPU_DEBUG macro to be tied to DRM_UT_KMS. It is used to report a debug message from driver, so by default it should go to the DRM_UT_DRIVER channel. While refactoring debug macros later on we might end up with particular messages going to ATOMIC or KMS, but DRIVER should be the default. Fixes: 25fdd5933e4c ("drm/msm: Add SDM845 DPU support") Signed-off-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/606932/ Link: https://lore.kernel.org/r/20240802-dpu-fix-wb-v2-2-7eac9eb8e895@linaro.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h index e2adc937ea63..935ff6fd172c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -31,24 +31,14 @@ * @fmt: Pointer to format string */ #define DPU_DEBUG(fmt, ...) \ - do { \ - if (drm_debug_enabled(DRM_UT_KMS)) \ - DRM_DEBUG(fmt, ##__VA_ARGS__); \ - else \ - pr_debug(fmt, ##__VA_ARGS__); \ - } while (0) + DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__) /** * DPU_DEBUG_DRIVER - macro for hardware driver logging * @fmt: Pointer to format string */ #define DPU_DEBUG_DRIVER(fmt, ...) \ - do { \ - if (drm_debug_enabled(DRM_UT_DRIVER)) \ - DRM_ERROR(fmt, ##__VA_ARGS__); \ - else \ - pr_debug(fmt, ##__VA_ARGS__); \ - } while (0) + DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__) #define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__) #define DPU_ERROR_RATELIMITED(fmt, ...) pr_err_ratelimited("[dpu error]" fmt, ##__VA_ARGS__) From d19d5b8d8f6dab942ce5ddbcf34bf7275e778250 Mon Sep 17 00:00:00 2001 From: Abhinav Kumar Date: Mon, 5 Aug 2024 13:20:08 -0700 Subject: [PATCH 032/562] drm/msm/dp: fix the max supported bpp logic Fix the dp_panel_get_supported_bpp() API to return the minimum supported bpp correctly for relevant cases and use this API to correct the behavior of DP driver which hard-codes the max supported bpp to 30. This is incorrect because the number of lanes and max data rate supported by the lanes need to be taken into account. Replace the hardcoded limit with the appropriate math which accounts for the accurate number of lanes and max data rate. changes in v2: - Fix the dp_panel_get_supported_bpp() and use it - Drop the max_t usage as dp_panel_get_supported_bpp() already returns the min_bpp correctly now changes in v3: - replace min_t with just min as all params are u32 Fixes: c943b4948b58 ("drm/msm/dp: add displayPort driver support") Reported-by: Dmitry Baryshkov Closes: https://gitlab.freedesktop.org/drm/msm/-/issues/43 Tested-by: Dmitry Baryshkov # SM8350-HDK Reviewed-by: Stephen Boyd Patchwork: https://patchwork.freedesktop.org/patch/607073/ Link: https://lore.kernel.org/r/20240805202009.1120981-1-quic_abhinavk@quicinc.com Signed-off-by: Stephen Boyd Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/dp/dp_panel.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index a916b5f3b317..6ff6c9ef351f 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -90,22 +90,22 @@ static int dp_panel_read_dpcd(struct dp_panel *dp_panel) static u32 dp_panel_get_supported_bpp(struct dp_panel *dp_panel, u32 mode_edid_bpp, u32 mode_pclk_khz) { - struct dp_link_info *link_info; + const struct dp_link_info *link_info; const u32 max_supported_bpp = 30, min_supported_bpp = 18; - u32 bpp = 0, data_rate_khz = 0; + u32 bpp, data_rate_khz; - bpp = min_t(u32, mode_edid_bpp, max_supported_bpp); + bpp = min(mode_edid_bpp, max_supported_bpp); link_info = &dp_panel->link_info; data_rate_khz = link_info->num_lanes * link_info->rate * 8; - while (bpp > min_supported_bpp) { + do { if (mode_pclk_khz * bpp <= data_rate_khz) - break; + return bpp; bpp -= 6; - } + } while (bpp > min_supported_bpp); - return bpp; + return min_supported_bpp; } int dp_panel_read_sink_caps(struct dp_panel *dp_panel, @@ -423,8 +423,9 @@ int dp_panel_init_panel_info(struct dp_panel *dp_panel) drm_mode->clock); drm_dbg_dp(panel->drm_dev, "bpp = %d\n", dp_panel->dp_mode.bpp); - dp_panel->dp_mode.bpp = max_t(u32, 18, - min_t(u32, dp_panel->dp_mode.bpp, 30)); + dp_panel->dp_mode.bpp = dp_panel_get_mode_bpp(dp_panel, dp_panel->dp_mode.bpp, + dp_panel->dp_mode.drm_mode.clock); + drm_dbg_dp(panel->drm_dev, "updated bpp = %d\n", dp_panel->dp_mode.bpp); From 959ab6350add903e352890af53e86663739fcb9a Mon Sep 17 00:00:00 2001 From: Chen Ridong Date: Sun, 4 Aug 2024 21:30:15 -0400 Subject: [PATCH 033/562] cgroup/cpuset: fix panic caused by partcmd_update We find a bug as below: BUG: unable to handle page fault for address: 00000003 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 3 PID: 358 Comm: bash Tainted: G W I 6.6.0-10893-g60d6 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/4 RIP: 0010:partition_sched_domains_locked+0x483/0x600 Code: 01 48 85 d2 74 0d 48 83 05 29 3f f8 03 01 f3 48 0f bc c2 89 c0 48 9 RSP: 0018:ffffc90000fdbc58 EFLAGS: 00000202 RAX: 0000000100000003 RBX: ffff888100b3dfa0 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000000000002fe80 RBP: ffff888100b3dfb0 R08: 0000000000000001 R09: 0000000000000000 R10: ffffc90000fdbcb0 R11: 0000000000000004 R12: 0000000000000002 R13: ffff888100a92b48 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f44a5425740(0000) GS:ffff888237d80000(0000) knlGS:0000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000100030973 CR3: 000000010722c000 CR4: 00000000000006e0 Call Trace: ? show_regs+0x8c/0xa0 ? __die_body+0x23/0xa0 ? __die+0x3a/0x50 ? page_fault_oops+0x1d2/0x5c0 ? partition_sched_domains_locked+0x483/0x600 ? search_module_extables+0x2a/0xb0 ? search_exception_tables+0x67/0x90 ? kernelmode_fixup_or_oops+0x144/0x1b0 ? __bad_area_nosemaphore+0x211/0x360 ? up_read+0x3b/0x50 ? bad_area_nosemaphore+0x1a/0x30 ? exc_page_fault+0x890/0xd90 ? __lock_acquire.constprop.0+0x24f/0x8d0 ? __lock_acquire.constprop.0+0x24f/0x8d0 ? asm_exc_page_fault+0x26/0x30 ? partition_sched_domains_locked+0x483/0x600 ? partition_sched_domains_locked+0xf0/0x600 rebuild_sched_domains_locked+0x806/0xdc0 update_partition_sd_lb+0x118/0x130 cpuset_write_resmask+0xffc/0x1420 cgroup_file_write+0xb2/0x290 kernfs_fop_write_iter+0x194/0x290 new_sync_write+0xeb/0x160 vfs_write+0x16f/0x1d0 ksys_write+0x81/0x180 __x64_sys_write+0x21/0x30 x64_sys_call+0x2f25/0x4630 do_syscall_64+0x44/0xb0 entry_SYSCALL_64_after_hwframe+0x78/0xe2 RIP: 0033:0x7f44a553c887 It can be reproduced with cammands: cd /sys/fs/cgroup/ mkdir test cd test/ echo +cpuset > ../cgroup.subtree_control echo root > cpuset.cpus.partition cat /sys/fs/cgroup/cpuset.cpus.effective 0-3 echo 0-3 > cpuset.cpus // taking away all cpus from root This issue is caused by the incorrect rebuilding of scheduling domains. In this scenario, test/cpuset.cpus.partition should be an invalid root and should not trigger the rebuilding of scheduling domains. When calling update_parent_effective_cpumask with partcmd_update, if newmask is not null, it should recheck newmask whether there are cpus is available for parect/cs that has tasks. Fixes: 0c7f293efc87 ("cgroup/cpuset: Add cpuset.cpus.exclusive.effective for v2") Cc: stable@vger.kernel.org # v6.7+ Signed-off-by: Chen Ridong Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 40ec4abaf440..a9b6d56eeffa 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1991,6 +1991,8 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, part_error = PERR_CPUSEMPTY; goto write_error; } + /* Check newmask again, whether cpus are available for parent/cs */ + nocpu |= tasks_nocpu_error(parent, cs, newmask); /* * partcmd_update with newmask: From 311a1bdc44a8e06024df4fd3392be0dfc8298655 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Sun, 4 Aug 2024 21:30:16 -0400 Subject: [PATCH 034/562] cgroup/cpuset: Clear effective_xcpus on cpus_allowed clearing only if cpus.exclusive not set Commit e2ffe502ba45 ("cgroup/cpuset: Add cpuset.cpus.exclusive for v2") adds a user writable cpuset.cpus.exclusive file for setting exclusive CPUs to be used for the creation of partitions. Since then effective_xcpus depends on both the cpuset.cpus and cpuset.cpus.exclusive setting. If cpuset.cpus.exclusive is set, effective_xcpus will depend only on cpuset.cpus.exclusive. When it is not set, effective_xcpus will be set according to the cpuset.cpus value when the cpuset becomes a valid partition root. When cpuset.cpus is being cleared by the user, effective_xcpus should only be cleared when cpuset.cpus.exclusive is not set. However, that is not currently the case. # cd /sys/fs/cgroup/ # mkdir test # echo +cpuset > cgroup.subtree_control # cd test # echo 3 > cpuset.cpus.exclusive # cat cpuset.cpus.exclusive.effective 3 # echo > cpuset.cpus # cat cpuset.cpus.exclusive.effective // was cleared Fix it by clearing effective_xcpus only if cpuset.cpus.exclusive is not set. Fixes: e2ffe502ba45 ("cgroup/cpuset: Add cpuset.cpus.exclusive for v2") Cc: stable@vger.kernel.org # v6.7+ Reported-by: Chen Ridong Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index a9b6d56eeffa..97d02612b3a6 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2525,7 +2525,8 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, */ if (!*buf) { cpumask_clear(trialcs->cpus_allowed); - cpumask_clear(trialcs->effective_xcpus); + if (cpumask_empty(trialcs->exclusive_cpus)) + cpumask_clear(trialcs->effective_xcpus); } else { retval = cpulist_parse(buf, trialcs->cpus_allowed); if (retval < 0) From ff0ce721ec213499ec5a532041fb3a1db2dc5ecb Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Sun, 4 Aug 2024 21:30:17 -0400 Subject: [PATCH 035/562] cgroup/cpuset: Eliminate unncessary sched domains rebuilds in hotplug It was found that some hotplug operations may cause multiple rebuild_sched_domains_locked() calls. Some of those intermediate calls may use cpuset states not in the final correct form leading to incorrect sched domain setting. Fix this problem by using the existing force_rebuild flag to inhibit immediate rebuild_sched_domains_locked() calls if set and only doing one final call at the end. Also renaming the force_rebuild flag to force_sd_rebuild to make its meaning for clear. Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 97d02612b3a6..4bd9e50bcc8e 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -232,6 +232,13 @@ static cpumask_var_t isolated_cpus; /* List of remote partition root children */ static struct list_head remote_children; +/* + * A flag to force sched domain rebuild at the end of an operation while + * inhibiting it in the intermediate stages when set. Currently it is only + * set in hotplug code. + */ +static bool force_sd_rebuild; + /* * Partition root states: * @@ -1475,7 +1482,7 @@ static void update_partition_sd_lb(struct cpuset *cs, int old_prs) clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); } - if (rebuild_domains) + if (rebuild_domains && !force_sd_rebuild) rebuild_sched_domains_locked(); } @@ -1833,7 +1840,7 @@ static void remote_partition_check(struct cpuset *cs, struct cpumask *newmask, remote_partition_disable(child, tmp); disable_cnt++; } - if (disable_cnt) + if (disable_cnt && !force_sd_rebuild) rebuild_sched_domains_locked(); } @@ -2442,7 +2449,8 @@ get_css: } rcu_read_unlock(); - if (need_rebuild_sched_domains && !(flags & HIER_NO_SD_REBUILD)) + if (need_rebuild_sched_domains && !(flags & HIER_NO_SD_REBUILD) && + !force_sd_rebuild) rebuild_sched_domains_locked(); } @@ -3104,7 +3112,8 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, cs->flags = trialcs->flags; spin_unlock_irq(&callback_lock); - if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) + if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed && + !force_sd_rebuild) rebuild_sched_domains_locked(); if (spread_flag_changed) @@ -4501,11 +4510,9 @@ hotplug_update_tasks(struct cpuset *cs, update_tasks_nodemask(cs); } -static bool force_rebuild; - void cpuset_force_rebuild(void) { - force_rebuild = true; + force_sd_rebuild = true; } /** @@ -4653,15 +4660,9 @@ static void cpuset_handle_hotplug(void) !cpumask_empty(subpartitions_cpus); mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems); - /* - * In the rare case that hotplug removes all the cpus in - * subpartitions_cpus, we assumed that cpus are updated. - */ - if (!cpus_updated && !cpumask_empty(subpartitions_cpus)) - cpus_updated = true; - /* For v1, synchronize cpus_allowed to cpu_active_mask */ if (cpus_updated) { + cpuset_force_rebuild(); spin_lock_irq(&callback_lock); if (!on_dfl) cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); @@ -4717,8 +4718,8 @@ static void cpuset_handle_hotplug(void) } /* rebuild sched domains if cpus_allowed has changed */ - if (cpus_updated || force_rebuild) { - force_rebuild = false; + if (force_sd_rebuild) { + force_sd_rebuild = false; rebuild_sched_domains_cpuslocked(); } From aedf02e46eb549dac8db4821a6b9f0c6bf6e3990 Mon Sep 17 00:00:00 2001 From: Abhinav Kumar Date: Wed, 31 Jul 2024 12:17:22 -0700 Subject: [PATCH 036/562] drm/msm/dpu: move dpu_encoder's connector assignment to atomic_enable() For cases where the crtc's connectors_changed was set without enable/active getting toggled , there is an atomic_enable() call followed by an atomic_disable() but without an atomic_mode_set(). This results in a NULL ptr access for the dpu_encoder_get_drm_fmt() call in the atomic_enable() as the dpu_encoder's connector was cleared in the atomic_disable() but not re-assigned as there was no atomic_mode_set() call. Fix the NULL ptr access by moving the assignment for atomic_enable() and also use drm_atomic_get_new_connector_for_encoder() to get the connector from the atomic_state. Fixes: 25fdd5933e4c ("drm/msm: Add SDM845 DPU support") Reported-by: Dmitry Baryshkov Closes: https://gitlab.freedesktop.org/drm/msm/-/issues/59 Suggested-by: Dmitry Baryshkov Reviewed-by: Dmitry Baryshkov Tested-by: Dmitry Baryshkov # SM8350-HDK Patchwork: https://patchwork.freedesktop.org/patch/606729/ Link: https://lore.kernel.org/r/20240731191723.3050932-1-quic_abhinavk@quicinc.com Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 34c56e855af7..3b171bf227d1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -1171,8 +1171,6 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, cstate->num_mixers = num_lm; - dpu_enc->connector = conn_state->connector; - for (i = 0; i < dpu_enc->num_phys_encs; i++) { struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; @@ -1270,6 +1268,8 @@ static void dpu_encoder_virt_atomic_enable(struct drm_encoder *drm_enc, dpu_enc->commit_done_timedout = false; + dpu_enc->connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc); + cur_mode = &dpu_enc->base.crtc->state->adjusted_mode; dpu_enc->wide_bus_en = dpu_encoder_is_widebus_enabled(drm_enc); From 319aca883bfa1b85ee08411541b51b9a934ac858 Mon Sep 17 00:00:00 2001 From: Abhinav Kumar Date: Thu, 25 Jul 2024 15:04:50 -0700 Subject: [PATCH 037/562] drm/msm/dp: reset the link phy params before link training Before re-starting link training reset the link phy params namely the pre-emphasis and voltage swing levels otherwise the next link training begins at the previously cached levels which can result in link training failures. Fixes: 8ede2ecc3e5e ("drm/msm/dp: Add DP compliance tests on Snapdragon Chipsets") Reviewed-by: Dmitry Baryshkov Tested-by: Dmitry Baryshkov # SM8350-HDK Reviewed-by: Stephen Boyd Patchwork: https://patchwork.freedesktop.org/patch/605946/ Link: https://lore.kernel.org/r/20240725220450.131245-1-quic_abhinavk@quicinc.com Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/dp/dp_ctrl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index 7bc8a9f0657a..f342fc5ae41e 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -1286,6 +1286,8 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl, link_info.rate = ctrl->link->link_params.rate; link_info.capabilities = DP_LINK_CAP_ENHANCED_FRAMING; + dp_link_reset_phy_params_vx_px(ctrl->link); + dp_aux_link_configure(ctrl->aux, &link_info); if (drm_dp_max_downspread(dpcd)) From bfa1a6283be390947d3649c482e5167186a37016 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Tue, 25 Jun 2024 00:13:41 +0300 Subject: [PATCH 038/562] drm/msm/dpu: cleanup FB if dpu_format_populate_layout fails If the dpu_format_populate_layout() fails, then FB is prepared, but not cleaned up. This ends up leaking the pin_count on the GEM object and causes a splat during DRM file closure: msm_obj->pin_count WARNING: CPU: 2 PID: 569 at drivers/gpu/drm/msm/msm_gem.c:121 update_lru_locked+0xc4/0xcc [...] Call trace: update_lru_locked+0xc4/0xcc put_pages+0xac/0x100 msm_gem_free_object+0x138/0x180 drm_gem_object_free+0x1c/0x30 drm_gem_object_handle_put_unlocked+0x108/0x10c drm_gem_object_release_handle+0x58/0x70 idr_for_each+0x68/0xec drm_gem_release+0x28/0x40 drm_file_free+0x174/0x234 drm_release+0xb0/0x160 __fput+0xc0/0x2c8 __fput_sync+0x50/0x5c __arm64_sys_close+0x38/0x7c invoke_syscall+0x48/0x118 el0_svc_common.constprop.0+0x40/0xe0 do_el0_svc+0x1c/0x28 el0_svc+0x4c/0x120 el0t_64_sync_handler+0x100/0x12c el0t_64_sync+0x190/0x194 irq event stamp: 129818 hardirqs last enabled at (129817): [] console_unlock+0x118/0x124 hardirqs last disabled at (129818): [] el1_dbg+0x24/0x8c softirqs last enabled at (129808): [] handle_softirqs+0x4c8/0x4e8 softirqs last disabled at (129785): [] __do_softirq+0x14/0x20 Fixes: 25fdd5933e4c ("drm/msm: Add SDM845 DPU support") Signed-off-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/600714/ Link: https://lore.kernel.org/r/20240625-dpu-mode-config-width-v5-1-501d984d634f@linaro.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 40c4dd2c3139..a62ac0c0c06a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -681,6 +681,9 @@ static int dpu_plane_prepare_fb(struct drm_plane *plane, new_state->fb, &layout); if (ret) { DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret); + if (pstate->aspace) + msm_framebuffer_cleanup(new_state->fb, pstate->aspace, + pstate->needs_dirtyfb); return ret; } From 2db13c4a631505029ada9404e09a2b06a268c1c4 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Thu, 27 Jun 2024 00:45:55 +0300 Subject: [PATCH 039/562] drm/msm/dpu: limit QCM2290 to RGB formats only The QCM2290 doesn't have CSC blocks, so it can not support YUV formats even on ViG blocks. Fix the formats declared by _VIG_SBLK_NOSCALE(). Fixes: 5334087ee743 ("drm/msm: add support for QCM2290 MDSS") Signed-off-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/601048/ Link: https://lore.kernel.org/r/20240627-dpu-virtual-wide-v5-1-5efb90cbb8be@linaro.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index fc178ec73907..648c8d0a4c36 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -308,8 +308,8 @@ static const u32 wb2_formats_rgb_yuv[] = { { \ .maxdwnscale = SSPP_UNITY_SCALE, \ .maxupscale = SSPP_UNITY_SCALE, \ - .format_list = plane_formats_yuv, \ - .num_formats = ARRAY_SIZE(plane_formats_yuv), \ + .format_list = plane_formats, \ + .num_formats = ARRAY_SIZE(plane_formats), \ .virt_format_list = plane_formats, \ .virt_num_formats = ARRAY_SIZE(plane_formats), \ } From cb18195914e353ece0e789e365a5a16872169805 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Thu, 27 Jun 2024 00:45:56 +0300 Subject: [PATCH 040/562] drm/msm/dpu: relax YUV requirements YUV formats require only CSC to be enabled. Even decimated formats should not require scaler. Relax the requirement and don't check for the scaler block while checking if YUV format can be enabled. Fixes: 25fdd5933e4c ("drm/msm: Add SDM845 DPU support") Signed-off-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/601049/ Link: https://lore.kernel.org/r/20240627-dpu-virtual-wide-v5-2-5efb90cbb8be@linaro.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index a62ac0c0c06a..dc1fd95e767b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -747,10 +747,9 @@ static int dpu_plane_atomic_check_pipe(struct dpu_plane *pdpu, min_src_size = MSM_FORMAT_IS_YUV(fmt) ? 2 : 1; if (MSM_FORMAT_IS_YUV(fmt) && - (!pipe->sspp->cap->sblk->scaler_blk.len || - !pipe->sspp->cap->sblk->csc_blk.len)) { + !pipe->sspp->cap->sblk->csc_blk.len) { DPU_DEBUG_PLANE(pdpu, - "plane doesn't have scaler/csc for yuv\n"); + "plane doesn't have csc for yuv\n"); return -EINVAL; } From d3a785e4f983f523380e023d8a05fb6d04402957 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Thu, 27 Jun 2024 00:45:57 +0300 Subject: [PATCH 041/562] drm/msm/dpu: take plane rotation into account for wide planes Take into account the plane rotation and flipping when calculating src positions for the wide plane parts. This is not an issue yet, because rotation is only supported for the UBWC planes and wide UBWC planes are rejected anyway because in parallel multirect case only the half of the usual width is supported for tiled formats. However it's better to fix this now rather than stumbling upon it later. Fixes: 80e8ae3b38ab ("drm/msm/dpu: add support for wide planes") Reviewed-by: Abhinav Kumar Signed-off-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/601059/ Link: https://lore.kernel.org/r/20240627-dpu-virtual-wide-v5-3-5efb90cbb8be@linaro.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index dc1fd95e767b..29298e066163 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -866,6 +866,10 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, max_linewidth = pdpu->catalog->caps->max_linewidth; + drm_rect_rotate(&pipe_cfg->src_rect, + new_plane_state->fb->width, new_plane_state->fb->height, + new_plane_state->rotation); + if ((drm_rect_width(&pipe_cfg->src_rect) > max_linewidth) || _dpu_plane_calc_clk(&crtc_state->adjusted_mode, pipe_cfg) > max_mdp_clk_rate) { /* @@ -915,6 +919,14 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, r_pipe_cfg->dst_rect.x1 = pipe_cfg->dst_rect.x2; } + drm_rect_rotate_inv(&pipe_cfg->src_rect, + new_plane_state->fb->width, new_plane_state->fb->height, + new_plane_state->rotation); + if (r_pipe->sspp) + drm_rect_rotate_inv(&r_pipe_cfg->src_rect, + new_plane_state->fb->width, new_plane_state->fb->height, + new_plane_state->rotation); + ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, fmt, &crtc_state->adjusted_mode); if (ret) return ret; From f91f7ac900e7342e0fd66093dfbf7cb8cb585a99 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Wed, 17 Jul 2024 15:00:23 +0200 Subject: [PATCH 042/562] refcount: Report UAF for refcount_sub_and_test(0) when counter==0 When a reference counter is at zero and refcount_sub_and_test() is invoked to subtract zero, the function accepts this request without any warning and returns true. This behavior does not seem ideal because the counter being already at zero indicates a use-after-free. Furthermore, returning true by refcount_sub_and_test() in this case potentially results in a double-free done by its caller. Modify the underlying function __refcount_sub_and_test() to warn about this case as a use-after-free and have it return false to avoid the potential double-free. Signed-off-by: Petr Pavlu Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20240717130023.5675-1-petr.pavlu@suse.com Signed-off-by: Kees Cook --- drivers/misc/lkdtm/refcount.c | 16 ++++++++++++++++ include/linux/refcount.h | 4 ++-- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/drivers/misc/lkdtm/refcount.c b/drivers/misc/lkdtm/refcount.c index 5cd488f54cfa..8f744bee6fbd 100644 --- a/drivers/misc/lkdtm/refcount.c +++ b/drivers/misc/lkdtm/refcount.c @@ -182,6 +182,21 @@ static void lkdtm_REFCOUNT_SUB_AND_TEST_NEGATIVE(void) check_negative(&neg, 3); } +/* + * A refcount_sub_and_test() by zero when the counter is at zero should act like + * refcount_sub_and_test() above when going negative. + */ +static void lkdtm_REFCOUNT_SUB_AND_TEST_ZERO(void) +{ + refcount_t neg = REFCOUNT_INIT(0); + + pr_info("attempting bad refcount_sub_and_test() at zero\n"); + if (refcount_sub_and_test(0, &neg)) + pr_warn("Weird: refcount_sub_and_test() reported zero\n"); + + check_negative(&neg, 0); +} + static void check_from_zero(refcount_t *ref) { switch (refcount_read(ref)) { @@ -400,6 +415,7 @@ static struct crashtype crashtypes[] = { CRASHTYPE(REFCOUNT_DEC_NEGATIVE), CRASHTYPE(REFCOUNT_DEC_AND_TEST_NEGATIVE), CRASHTYPE(REFCOUNT_SUB_AND_TEST_NEGATIVE), + CRASHTYPE(REFCOUNT_SUB_AND_TEST_ZERO), CRASHTYPE(REFCOUNT_INC_ZERO), CRASHTYPE(REFCOUNT_ADD_ZERO), CRASHTYPE(REFCOUNT_INC_SATURATED), diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 59b3b752394d..35f039ecb272 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -266,12 +266,12 @@ bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) if (oldp) *oldp = old; - if (old == i) { + if (old > 0 && old == i) { smp_acquire__after_ctrl_dep(); return true; } - if (unlikely(old < 0 || old - i < 0)) + if (unlikely(old <= 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; From f32e90c0688a3d1f8079ac18ed39b752d22e92bd Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Tue, 23 Jul 2024 18:53:31 +0200 Subject: [PATCH 043/562] gcc-plugins: randstruct: Remove GCC 4.7 or newer requirement Since the kernel currently requires GCC 5.1 as a minimum, remove the unnecessary GCC version >= 4.7 check. Signed-off-by: Thorsten Blum Link: https://lore.kernel.org/r/20240723165332.1947-1-thorsten.blum@toblux.com Signed-off-by: Kees Cook --- scripts/gcc-plugins/randomize_layout_plugin.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/scripts/gcc-plugins/randomize_layout_plugin.c b/scripts/gcc-plugins/randomize_layout_plugin.c index 746ff2d272f2..5694df3da2e9 100644 --- a/scripts/gcc-plugins/randomize_layout_plugin.c +++ b/scripts/gcc-plugins/randomize_layout_plugin.c @@ -19,10 +19,6 @@ #include "gcc-common.h" #include "randomize_layout_seed.h" -#if BUILDING_GCC_MAJOR < 4 || (BUILDING_GCC_MAJOR == 4 && BUILDING_GCC_MINOR < 7) -#error "The RANDSTRUCT plugin requires GCC 4.7 or newer." -#endif - #define ORIG_TYPE_NAME(node) \ (TYPE_NAME(TYPE_MAIN_VARIANT(node)) != NULL_TREE ? ((const unsigned char *)IDENTIFIER_POINTER(TYPE_NAME(TYPE_MAIN_VARIANT(node)))) : (const unsigned char *)"anonymous") From 9a2fa1472083580b6c66bdaf291f591e1170123a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 3 Aug 2024 18:02:00 -0400 Subject: [PATCH 044/562] fix bitmap corruption on close_range() with CLOSE_RANGE_UNSHARE copy_fd_bitmaps(new, old, count) is expected to copy the first count/BITS_PER_LONG bits from old->full_fds_bits[] and fill the rest with zeroes. What it does is copying enough words (BITS_TO_LONGS(count/BITS_PER_LONG)), then memsets the rest. That works fine, *if* all bits past the cutoff point are clear. Otherwise we are risking garbage from the last word we'd copied. For most of the callers that is true - expand_fdtable() has count equal to old->max_fds, so there's no open descriptors past count, let alone fully occupied words in ->open_fds[], which is what bits in ->full_fds_bits[] correspond to. The other caller (dup_fd()) passes sane_fdtable_size(old_fdt, max_fds), which is the smallest multiple of BITS_PER_LONG that covers all opened descriptors below max_fds. In the common case (copying on fork()) max_fds is ~0U, so all opened descriptors will be below it and we are fine, by the same reasons why the call in expand_fdtable() is safe. Unfortunately, there is a case where max_fds is less than that and where we might, indeed, end up with junk in ->full_fds_bits[] - close_range(from, to, CLOSE_RANGE_UNSHARE) with * descriptor table being currently shared * 'to' being above the current capacity of descriptor table * 'from' being just under some chunk of opened descriptors. In that case we end up with observably wrong behaviour - e.g. spawn a child with CLONE_FILES, get all descriptors in range 0..127 open, then close_range(64, ~0U, CLOSE_RANGE_UNSHARE) and watch dup(0) ending up with descriptor #128, despite #64 being observably not open. The minimally invasive fix would be to deal with that in dup_fd(). If this proves to add measurable overhead, we can go that way, but let's try to fix copy_fd_bitmaps() first. * new helper: bitmap_copy_and_expand(to, from, bits_to_copy, size). * make copy_fd_bitmaps() take the bitmap size in words, rather than bits; it's 'count' argument is always a multiple of BITS_PER_LONG, so we are not losing any information, and that way we can use the same helper for all three bitmaps - compiler will see that count is a multiple of BITS_PER_LONG for the large ones, so it'll generate plain memcpy()+memset(). Reproducer added to tools/testing/selftests/core/close_range_test.c Cc: stable@vger.kernel.org Signed-off-by: Al Viro --- fs/file.c | 28 +++++++-------- include/linux/bitmap.h | 12 +++++++ .../testing/selftests/core/close_range_test.c | 35 +++++++++++++++++++ 3 files changed, 59 insertions(+), 16 deletions(-) diff --git a/fs/file.c b/fs/file.c index a11e59b5d602..655338effe9c 100644 --- a/fs/file.c +++ b/fs/file.c @@ -46,27 +46,23 @@ static void free_fdtable_rcu(struct rcu_head *rcu) #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) +#define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ -static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, - unsigned int count) +static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, + unsigned int copy_words) { - unsigned int cpy, set; + unsigned int nwords = fdt_words(nfdt); - cpy = count / BITS_PER_BYTE; - set = (nfdt->max_fds - count) / BITS_PER_BYTE; - memcpy(nfdt->open_fds, ofdt->open_fds, cpy); - memset((char *)nfdt->open_fds + cpy, 0, set); - memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); - memset((char *)nfdt->close_on_exec + cpy, 0, set); - - cpy = BITBIT_SIZE(count); - set = BITBIT_SIZE(nfdt->max_fds) - cpy; - memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); - memset((char *)nfdt->full_fds_bits + cpy, 0, set); + bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, + copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); + bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, + copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); + bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, + copy_words, nwords); } /* @@ -84,7 +80,7 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); - copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds); + copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); } /* @@ -379,7 +375,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int open_files = sane_fdtable_size(old_fdt, max_fds); } - copy_fd_bitmaps(new_fdt, old_fdt, open_files); + copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 8c4768c44a01..d3b66d77df7a 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -270,6 +270,18 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst, dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits); } +static inline void bitmap_copy_and_extend(unsigned long *to, + const unsigned long *from, + unsigned int count, unsigned int size) +{ + unsigned int copy = BITS_TO_LONGS(count); + + memcpy(to, from, copy * sizeof(long)); + if (count % BITS_PER_LONG) + to[copy - 1] &= BITMAP_LAST_WORD_MASK(count); + memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long)); +} + /* * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64 * machines the order of hi and lo parts of numbers match the bitmap structure. diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c index 991c473e3859..12b4eb9d0434 100644 --- a/tools/testing/selftests/core/close_range_test.c +++ b/tools/testing/selftests/core/close_range_test.c @@ -589,4 +589,39 @@ TEST(close_range_cloexec_unshare_syzbot) EXPECT_EQ(close(fd3), 0); } +TEST(close_range_bitmap_corruption) +{ + pid_t pid; + int status; + struct __clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + /* get the first 128 descriptors open */ + for (int i = 2; i < 128; i++) + EXPECT_GE(dup2(0, i), 0); + + /* get descriptor table shared */ + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + /* unshare and truncate descriptor table down to 64 */ + if (sys_close_range(64, ~0U, CLOSE_RANGE_UNSHARE)) + exit(EXIT_FAILURE); + + ASSERT_EQ(fcntl(64, F_GETFD), -1); + /* ... and verify that the range 64..127 is not + stuck "fully used" according to secondary bitmap */ + EXPECT_EQ(dup(0), 64) + exit(EXIT_FAILURE); + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + TEST_HARNESS_MAIN From 44732f1dad20457d64c525549cd63dcef2563c23 Mon Sep 17 00:00:00 2001 From: Nikita Shubin Date: Fri, 19 Jul 2024 17:30:16 +0300 Subject: [PATCH 045/562] workqueue: doc: Fix function name, remove markers - s/alloc_ordered_queue()/alloc_ordered_workqueue()/ - remove markers to convert it into a link. Signed-off-by: Nikita Shubin Signed-off-by: Tejun Heo --- Documentation/core-api/workqueue.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst index bcc370c876be..16f861c9791e 100644 --- a/Documentation/core-api/workqueue.rst +++ b/Documentation/core-api/workqueue.rst @@ -260,7 +260,7 @@ Some users depend on strict execution ordering where only one work item is in flight at any given time and the work items are processed in queueing order. While the combination of ``@max_active`` of 1 and ``WQ_UNBOUND`` used to achieve this behavior, this is no longer the -case. Use ``alloc_ordered_queue()`` instead. +case. Use alloc_ordered_workqueue() instead. Example Execution Scenarios From 38f7e14519d39cf524ddc02d4caee9b337dad703 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 30 Jul 2024 12:44:31 +0100 Subject: [PATCH 046/562] workqueue: Fix UBSAN 'subtraction overflow' error in shift_and_mask() UBSAN reports the following 'subtraction overflow' error when booting in a virtual machine on Android: | Internal error: UBSAN: integer subtraction overflow: 00000000f2005515 [#1] PREEMPT SMP | Modules linked in: | CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.10.0-00006-g3cbe9e5abd46-dirty #4 | Hardware name: linux,dummy-virt (DT) | pstate: 600000c5 (nZCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : cancel_delayed_work+0x34/0x44 | lr : cancel_delayed_work+0x2c/0x44 | sp : ffff80008002ba60 | x29: ffff80008002ba60 x28: 0000000000000000 x27: 0000000000000000 | x26: 0000000000000000 x25: 0000000000000000 x24: 0000000000000000 | x23: 0000000000000000 x22: 0000000000000000 x21: ffff1f65014cd3c0 | x20: ffffc0e84c9d0da0 x19: ffffc0e84cab3558 x18: ffff800080009058 | x17: 00000000247ee1f8 x16: 00000000247ee1f8 x15: 00000000bdcb279d | x14: 0000000000000001 x13: 0000000000000075 x12: 00000a0000000000 | x11: ffff1f6501499018 x10: 00984901651fffff x9 : ffff5e7cc35af000 | x8 : 0000000000000001 x7 : 3d4d455453595342 x6 : 000000004e514553 | x5 : ffff1f6501499265 x4 : ffff1f650ff60b10 x3 : 0000000000000620 | x2 : ffff80008002ba78 x1 : 0000000000000000 x0 : 0000000000000000 | Call trace: | cancel_delayed_work+0x34/0x44 | deferred_probe_extend_timeout+0x20/0x70 | driver_register+0xa8/0x110 | __platform_driver_register+0x28/0x3c | syscon_init+0x24/0x38 | do_one_initcall+0xe4/0x338 | do_initcall_level+0xac/0x178 | do_initcalls+0x5c/0xa0 | do_basic_setup+0x20/0x30 | kernel_init_freeable+0x8c/0xf8 | kernel_init+0x28/0x1b4 | ret_from_fork+0x10/0x20 | Code: f9000fbf 97fffa2f 39400268 37100048 (d42aa2a0) | ---[ end trace 0000000000000000 ]--- | Kernel panic - not syncing: UBSAN: integer subtraction overflow: Fatal exception This is due to shift_and_mask() using a signed immediate to construct the mask and being called with a shift of 31 (WORK_OFFQ_POOL_SHIFT) so that it ends up decrementing from INT_MIN. Use an unsigned constant '1U' to generate the mask in shift_and_mask(). Cc: Tejun Heo Cc: Lai Jiangshan Fixes: 1211f3b21c2a ("workqueue: Preserve OFFQ bits in cancel[_sync] paths") Signed-off-by: Will Deacon Signed-off-by: Tejun Heo --- kernel/workqueue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1745ca788ede..b35f8ce80bc7 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -897,7 +897,7 @@ static struct worker_pool *get_work_pool(struct work_struct *work) static unsigned long shift_and_mask(unsigned long v, u32 shift, u32 bits) { - return (v >> shift) & ((1 << bits) - 1); + return (v >> shift) & ((1U << bits) - 1); } static void work_offqd_unpack(struct work_offq_data *offqd, unsigned long data) From 98cc1730c89467fc26e2dc2ceb2a014f332daa97 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 25 Jul 2024 09:04:37 +0800 Subject: [PATCH 047/562] workqueue: Remove incorrect "WARN_ON_ONCE(!list_empty(&worker->entry));" from dying worker The commit 68f83057b913 ("workqueue: Reap workers via kthread_stop() and remove detach_completion") changes the procedure of destroying workers; the dying workers are kept in the cull_list in wake_dying_workers() with the pool lock held and removed from the cull_list by the newly added reap_dying_workers() without the pool lock. This can cause a warning if the dying worker is wokenup earlier than reaped as reported by Marc: 2024/07/23 18:01:21 [M83LP63]: [ 157.267727] ------------[ cut here ]------------ 2024/07/23 18:01:21 [M83LP63]: [ 157.267735] WARNING: CPU: 21 PID: 725 at kernel/workqueue.c:3340 worker_thread+0x54e/0x558 2024/07/23 18:01:21 [M83LP63]: [ 157.267746] Modules linked in: binfmt_misc nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables sunrpc dm_service_time s390_trng vfio_ccw mdev vfio_iommu_type1 vfio sch_fq_codel 2024/07/23 18:01:21 [M83LP63]: loop dm_multipath configfs nfnetlink lcs ctcm fsm zfcp scsi_transport_fc ghash_s390 prng chacha_s390 libchacha aes_s390 des_s390 libdes sha3_512_s390 sha3_256_s390 sha512_s390 sha256_s390 sha1_s390 sha_common scm_block eadm_sch scsi_dh_rdac scsi_dh_emc scsi_dh_alua pkey zcrypt rng_core autofs4 2024/07/23 18:01:21 [M83LP63]: [ 157.267792] CPU: 21 PID: 725 Comm: kworker/dying Not tainted 6.10.0-rc2-00239-g68f83057b913 #95 2024/07/23 18:01:21 [M83LP63]: [ 157.267796] Hardware name: IBM 3906 M04 704 (LPAR) 2024/07/23 18:01:21 [M83LP63]: [ 157.267802] R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:1 PM:0 RI:0 EA:3 2024/07/23 18:01:21 [M83LP63]: [ 157.267797] Krnl PSW : 0704d00180000000 000003d600fcd9fa (worker_thread+0x552/0x558) 2024/07/23 18:01:21 [M83LP63]: [ 157.267806] Krnl GPRS: 6479696e6700776f 000002c901b62780 000003d602493ec8 000002c914954600 2024/07/23 18:01:21 [M83LP63]: [ 157.267809] 0000000000000000 0000000000000008 000002c901a85400 000002c90719e840 2024/07/23 18:01:21 [M83LP63]: [ 157.267811] 000002c90719e880 000002c901a85420 000002c91127adf0 000002c901a85400 2024/07/23 18:01:21 [M83LP63]: [ 157.267813] 000002c914954600 0000000000000000 000003d600fcd772 000003560452bd98 2024/07/23 18:01:21 [M83LP63]: [ 157.267822] Krnl Code: 000003d600fcd9ec: c0e500674262 brasl %r14,000003d601cb5eb0 2024/07/23 18:01:21 [M83LP63]: [ 157.267822] 000003d600fcd9f2: a7f4ffc8 brc 15,000003d600fcd982 2024/07/23 18:01:21 [M83LP63]: [ 157.267822] #000003d600fcd9f6: af000000 mc 0,0 2024/07/23 18:01:21 [M83LP63]: [ 157.267822] >000003d600fcd9fa: a7f4fec2 brc 15,000003d600fcd77e 2024/07/23 18:01:21 [M83LP63]: [ 157.267822] 000003d600fcd9fe: 0707 bcr 0,%r7 2024/07/23 18:01:21 [M83LP63]: [ 157.267822] 000003d600fcda00: c00400682e10 brcl 0,000003d601cd3620 2024/07/23 18:01:21 [M83LP63]: [ 157.267822] 000003d600fcda06: eb7ff0500024 stmg %r7,%r15,80(%r15) 2024/07/23 18:01:21 [M83LP63]: [ 157.267822] 000003d600fcda0c: b90400ef lgr %r14,%r15 2024/07/23 18:01:21 [M83LP63]: [ 157.267853] Call Trace: 2024/07/23 18:01:21 [M83LP63]: [ 157.267855] [<000003d600fcd9fa>] worker_thread+0x552/0x558 2024/07/23 18:01:21 [M83LP63]: [ 157.267859] ([<000003d600fcd772>] worker_thread+0x2ca/0x558) 2024/07/23 18:01:21 [M83LP63]: [ 157.267862] [<000003d600fd6c80>] kthread+0x120/0x128 2024/07/23 18:01:21 [M83LP63]: [ 157.267865] [<000003d600f5305c>] __ret_from_fork+0x3c/0x58 2024/07/23 18:01:21 [M83LP63]: [ 157.267868] [<000003d601cc746a>] ret_from_fork+0xa/0x30 2024/07/23 18:01:21 [M83LP63]: [ 157.267873] Last Breaking-Event-Address: 2024/07/23 18:01:21 [M83LP63]: [ 157.267874] [<000003d600fcd778>] worker_thread+0x2d0/0x558 Since the procedure of destroying workers is changed, the WARN_ON_ONCE() becomes incorrect and should be removed. Cc: Marc Hartmayer Link: https://lore.kernel.org/lkml/87le1sjd2e.fsf@linux.ibm.com/ Reported-by: Marc Hartmayer Fixes: 68f83057b913 ("workqueue: Reap workers via kthread_stop() and remove detach_completion") Cc: stable@vger.kernel.org # v6.11+ Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo --- kernel/workqueue.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b35f8ce80bc7..d56bd2277e58 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3351,7 +3351,6 @@ woke_up: set_pf_worker(false); ida_free(&pool->worker_ida, worker->id); - WARN_ON_ONCE(!list_empty(&worker->entry)); return 0; } From 8bc35475ef1a23b0e224f3242eb11c76cab0ea88 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 5 Aug 2024 09:37:25 -1000 Subject: [PATCH 048/562] workqueue: Fix spruious data race in __flush_work() When flushing a work item for cancellation, __flush_work() knows that it exclusively owns the work item through its PENDING bit. 134874e2eee9 ("workqueue: Allow cancel_work_sync() and disable_work() from atomic contexts on BH work items") added a read of @work->data to determine whether to use busy wait for BH work items that are being canceled. While the read is safe when @from_cancel, @work->data was read before testing @from_cancel to simplify code structure: data = *work_data_bits(work); if (from_cancel && !WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) { While the read data was never used if !@from_cancel, this could trigger KCSAN data race detection spuriously: ================================================================== BUG: KCSAN: data-race in __flush_work / __flush_work write to 0xffff8881223aa3e8 of 8 bytes by task 3998 on cpu 0: instrument_write include/linux/instrumented.h:41 [inline] ___set_bit include/asm-generic/bitops/instrumented-non-atomic.h:28 [inline] insert_wq_barrier kernel/workqueue.c:3790 [inline] start_flush_work kernel/workqueue.c:4142 [inline] __flush_work+0x30b/0x570 kernel/workqueue.c:4178 flush_work kernel/workqueue.c:4229 [inline] ... read to 0xffff8881223aa3e8 of 8 bytes by task 50 on cpu 1: __flush_work+0x42a/0x570 kernel/workqueue.c:4188 flush_work kernel/workqueue.c:4229 [inline] flush_delayed_work+0x66/0x70 kernel/workqueue.c:4251 ... value changed: 0x0000000000400000 -> 0xffff88810006c00d Reorganize the code so that @from_cancel is tested before @work->data is accessed. The only problem is triggering KCSAN detection spuriously. This shouldn't need READ_ONCE() or other access qualifiers. No functional changes. Signed-off-by: Tejun Heo Reported-by: syzbot+b3e4f2f51ed645fd5df2@syzkaller.appspotmail.com Fixes: 134874e2eee9 ("workqueue: Allow cancel_work_sync() and disable_work() from atomic contexts on BH work items") Link: http://lkml.kernel.org/r/000000000000ae429e061eea2157@google.com Cc: Jens Axboe --- kernel/workqueue.c | 45 +++++++++++++++++++++++++-------------------- 1 file changed, 25 insertions(+), 20 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index d56bd2277e58..ef174d8c1f63 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4166,7 +4166,6 @@ already_gone: static bool __flush_work(struct work_struct *work, bool from_cancel) { struct wq_barrier barr; - unsigned long data; if (WARN_ON(!wq_online)) return false; @@ -4184,29 +4183,35 @@ static bool __flush_work(struct work_struct *work, bool from_cancel) * was queued on a BH workqueue, we also know that it was running in the * BH context and thus can be busy-waited. */ - data = *work_data_bits(work); - if (from_cancel && - !WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) { - /* - * On RT, prevent a live lock when %current preempted soft - * interrupt processing or prevents ksoftirqd from running by - * keeping flipping BH. If the BH work item runs on a different - * CPU then this has no effect other than doing the BH - * disable/enable dance for nothing. This is copied from - * kernel/softirq.c::tasklet_unlock_spin_wait(). - */ - while (!try_wait_for_completion(&barr.done)) { - if (IS_ENABLED(CONFIG_PREEMPT_RT)) { - local_bh_disable(); - local_bh_enable(); - } else { - cpu_relax(); + if (from_cancel) { + unsigned long data = *work_data_bits(work); + + if (!WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && + (data & WORK_OFFQ_BH)) { + /* + * On RT, prevent a live lock when %current preempted + * soft interrupt processing or prevents ksoftirqd from + * running by keeping flipping BH. If the BH work item + * runs on a different CPU then this has no effect other + * than doing the BH disable/enable dance for nothing. + * This is copied from + * kernel/softirq.c::tasklet_unlock_spin_wait(). + */ + while (!try_wait_for_completion(&barr.done)) { + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + local_bh_disable(); + local_bh_enable(); + } else { + cpu_relax(); + } } + goto out_destroy; } - } else { - wait_for_completion(&barr.done); } + wait_for_completion(&barr.done); + +out_destroy: destroy_work_on_stack(&barr.work); return true; } From c4c8f369b6a6d21ce27286de1501137771e01dc3 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Mon, 5 Aug 2024 09:30:29 +0200 Subject: [PATCH 049/562] workqueue: Correct declaration of cpu_pwq in struct workqueue_struct cpu_pwq is used in various percpu functions that expect variable in __percpu address space. Correct the declaration of cpu_pwq to struct pool_workqueue __rcu * __percpu *cpu_pwq to declare the variable as __percpu pointer. The patch also fixes following sparse errors: workqueue.c:380:37: warning: duplicate [noderef] workqueue.c:380:37: error: multiple address spaces given: __rcu & __percpu workqueue.c:2271:15: error: incompatible types in comparison expression (different address spaces): workqueue.c:2271:15: struct pool_workqueue [noderef] __rcu * workqueue.c:2271:15: struct pool_workqueue [noderef] __percpu * and uncovers a couple of exisiting "incorrect type in assignment" warnings (from __rcu address space), which this patch does not address. Found by GCC's named address space checks. There were no changes in the resulting object files. Signed-off-by: Uros Bizjak Cc: Tejun Heo Cc: Lai Jiangshan Signed-off-by: Tejun Heo --- kernel/workqueue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index ef174d8c1f63..e7b005ff3750 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -377,7 +377,7 @@ struct workqueue_struct { /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ - struct pool_workqueue __percpu __rcu **cpu_pwq; /* I: per-cpu pwqs */ + struct pool_workqueue __rcu * __percpu *cpu_pwq; /* I: per-cpu pwqs */ struct wq_node_nr_active *node_nr_active[]; /* I: per-node nr_active */ }; From 8fcd8d1e63c05c48b3ac16d0c3e2cd6a7a5c8ec4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 26 Jul 2024 04:23:14 +0900 Subject: [PATCH 050/562] kbuild: clean up code duplication in cmd_fdtoverlay When resolving a merge conflict, Linus noticed the fdtoverlay command duplication introduced by commit 49636c5680b9 ("kbuild: verify dtoverlay files against schema"). He suggested a clean-up. I eliminated the duplication and refactored the code a little further. No functional changes are intended, except for the short logs. The log will look as follows: $ make ARCH=arm64 defconfig dtbs_check [ snip ] DTC [C] arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxca.dtb DTC [C] arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dtb DTC [C] arch/arm64/boot/dts/freescale/imx93-var-som-symphony.dtb DTC [C] arch/arm64/boot/dts/freescale/imx95-19x19-evk.dtb DTC arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-imx219.dtbo OVL [C] arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-imx219.dtb The tag [C] indicates that the schema check is executed. Link: https://lore.kernel.org/lkml/CAHk-=wiF3yeWehcvqY-4X7WNb8n4yw_5t0H1CpEpKi7JMjaMfw@mail.gmail.com/#t Requested-by: Linus Torvalds Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Schier --- scripts/Makefile.lib | 28 ++++++++++------------------ 1 file changed, 10 insertions(+), 18 deletions(-) diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index fe3668dc4954..207325eaf1d1 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -400,26 +400,23 @@ $(obj)/%.dtb.S: $(obj)/%.dtb FORCE $(obj)/%.dtbo.S: $(obj)/%.dtbo FORCE $(call if_changed,wrap_S_dtb) -quiet_cmd_dtc = DTC $@ +quiet_dtb_check_tag = $(if $(dtb-check-enabled),[C], ) +cmd_dtb_check = $(if $(dtb-check-enabled),; $(DT_CHECKER) $(DT_CHECKER_FLAGS) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) $@ || true) + +quiet_cmd_dtc = DTC $(quiet_dtb_check_tag) $@ cmd_dtc = $(HOSTCC) -E $(dtc_cpp_flags) -x assembler-with-cpp -o $(dtc-tmp) $< ; \ $(DTC) -o $@ -b 0 \ $(addprefix -i,$(dir $<) $(DTC_INCLUDE)) $(DTC_FLAGS) \ -d $(depfile).dtc.tmp $(dtc-tmp) ; \ - cat $(depfile).pre.tmp $(depfile).dtc.tmp > $(depfile) - -DT_CHECK_CMD = $(DT_CHECKER) $(DT_CHECKER_FLAGS) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) + cat $(depfile).pre.tmp $(depfile).dtc.tmp > $(depfile) \ + $(cmd_dtb_check) # NOTE: # Do not replace $(filter %.dtb %.dtbo, $^) with $(real-prereqs). When a single # DTB is turned into a multi-blob DTB, $^ will contain header file dependencies # recorded in the .*.cmd file. -ifneq ($(CHECK_DTBS),) -quiet_cmd_fdtoverlay = DTOVLCH $@ - cmd_fdtoverlay = $(objtree)/scripts/dtc/fdtoverlay -o $@ -i $(filter %.dtb %.dtbo, $^) ; $(DT_CHECK_CMD) $@ || true -else -quiet_cmd_fdtoverlay = DTOVL $@ - cmd_fdtoverlay = $(objtree)/scripts/dtc/fdtoverlay -o $@ -i $(filter %.dtb %.dtbo, $^) -endif +quiet_cmd_fdtoverlay = OVL $(quiet_dtb_check_tag) $@ + cmd_fdtoverlay = $(objtree)/scripts/dtc/fdtoverlay -o $@ -i $(filter %.dtb %.dtbo, $^) $(cmd_dtb_check) $(multi-dtb-y): FORCE $(call if_changed,fdtoverlay) @@ -430,16 +427,11 @@ DT_CHECKER ?= dt-validate DT_CHECKER_FLAGS ?= $(if $(DT_SCHEMA_FILES),-l $(DT_SCHEMA_FILES),-m) DT_BINDING_DIR := Documentation/devicetree/bindings DT_TMP_SCHEMA := $(objtree)/$(DT_BINDING_DIR)/processed-schema.json - -quiet_cmd_dtb = DTC_CHK $@ - cmd_dtb = $(cmd_dtc) ; $(DT_CHECK_CMD) $@ || true -else -quiet_cmd_dtb = $(quiet_cmd_dtc) - cmd_dtb = $(cmd_dtc) +dtb-check-enabled = $(if $(filter %.dtb, $@),y) endif $(obj)/%.dtb: $(obj)/%.dts $(DTC) $(DT_TMP_SCHEMA) FORCE - $(call if_changed_dep,dtb) + $(call if_changed_dep,dtc) $(obj)/%.dtbo: $(src)/%.dtso $(DTC) FORCE $(call if_changed_dep,dtc) From 6fc9aacad49e3fbecd270c266850d50c453d52ef Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Sun, 4 Aug 2024 14:50:57 +0900 Subject: [PATCH 051/562] Makefile: add $(srctree) to dependency of compile_commands.json target When trying to build compile_commands.json for an external module against the kernel built in a separate output directory, the following error is displayed: make[1]: *** No rule to make target 'scripts/clang-tools/gen_compile_commands.py', needed by 'compile_commands.json'. Stop. This is because gen_compile_commands.py was previously looked up using a relative path to $(srctree), but commit b1992c3772e6 ("kbuild: use $(src) instead of $(srctree)/$(src) for source directory") stopped defining VPATH for external module builds. Prefixing gen_compile_commands.py with $(srctree) fixes the problem. Fixes: b1992c3772e6 ("kbuild: use $(src) instead of $(srctree)/$(src) for source directory") Signed-off-by: Alexandre Courbot Reviewed-by: Nicolas Schier Signed-off-by: Masahiro Yamada --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 44c02a6f60a1..44c33de28e93 100644 --- a/Makefile +++ b/Makefile @@ -1980,7 +1980,7 @@ nsdeps: modules quiet_cmd_gen_compile_commands = GEN $@ cmd_gen_compile_commands = $(PYTHON3) $< -a $(AR) -o $@ $(filter-out $<, $(real-prereqs)) -$(extmod_prefix)compile_commands.json: scripts/clang-tools/gen_compile_commands.py \ +$(extmod_prefix)compile_commands.json: $(srctree)/scripts/clang-tools/gen_compile_commands.py \ $(if $(KBUILD_EXTMOD),, vmlinux.a $(KBUILD_VMLINUX_LIBS)) \ $(if $(CONFIG_MODULES), $(MODORDER)) FORCE $(call if_changed,gen_compile_commands) From e2006140ad2e01a02ed0aff49cc2ae3ceeb11f8d Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 13 Jun 2024 15:05:03 +0300 Subject: [PATCH 052/562] thunderbolt: Mark XDomain as unplugged when router is removed I noticed that when we do discrete host router NVM upgrade and it gets hot-removed from the PCIe side as a result of NVM firmware authentication, if there is another host connected with enabled paths we hang in tearing them down. This is due to fact that the Thunderbolt networking driver also tries to cleanup the paths and ends up blocking in tb_disconnect_xdomain_paths() waiting for the domain lock. However, at this point we already cleaned the paths in tb_stop() so there is really no need for tb_disconnect_xdomain_paths() to do that anymore. Furthermore it already checks if the XDomain is unplugged and bails out early so take advantage of that and mark the XDomain as unplugged when we remove the parent router. Cc: stable@vger.kernel.org Signed-off-by: Mika Westerberg --- drivers/thunderbolt/switch.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 326433df5880..6a2116cbb06f 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -3392,6 +3392,7 @@ void tb_switch_remove(struct tb_switch *sw) tb_switch_remove(port->remote->sw); port->remote = NULL; } else if (port->xdomain) { + port->xdomain->is_unplugged = true; tb_xdomain_remove(port->xdomain); port->xdomain = NULL; } From 33330bcf031818e60a816db0cfd3add9eecc3b28 Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Mon, 5 Aug 2024 11:22:34 +0200 Subject: [PATCH 053/562] scripts: kconfig: merge_config: config files: add a trailing newline When merging files without trailing newlines at the end of the file, two config fragments end up at the same row if file1.config doens't have a trailing newline at the end of the file. file1.config "CONFIG_1=y" file2.config "CONFIG_2=y" ./scripts/kconfig/merge_config.sh -m .config file1.config file2.config This will generate a .config looking like this. cat .config ... CONFIG_1=yCONFIG_2=y" Making sure so we add a newline at the end of every config file that is passed into the script. Signed-off-by: Anders Roxell Signed-off-by: Masahiro Yamada --- scripts/kconfig/merge_config.sh | 2 ++ 1 file changed, 2 insertions(+) diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh index 902eb429b9db..0b7952471c18 100755 --- a/scripts/kconfig/merge_config.sh +++ b/scripts/kconfig/merge_config.sh @@ -167,6 +167,8 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do sed -i "/$CFG[ =]/d" $MERGE_FILE fi done + # In case the previous file lacks a new line at the end + echo >> $TMP_FILE cat $MERGE_FILE >> $TMP_FILE done From 5a44bb061d04b0306f2aa8add761d86d152b9377 Mon Sep 17 00:00:00 2001 From: Michael Mueller Date: Thu, 1 Aug 2024 14:31:09 +0200 Subject: [PATCH 054/562] KVM: s390: fix validity interception issue when gisa is switched off We might run into a SIE validity if gisa has been disabled either via using kernel parameter "kvm.use_gisa=0" or by setting the related sysfs attribute to N (echo N >/sys/module/kvm/parameters/use_gisa). The validity is caused by an invalid value in the SIE control block's gisa designation. That happens because we pass the uninitialized gisa origin to virt_to_phys() before writing it to the gisa designation. To fix this we return 0 in kvm_s390_get_gisa_desc() if the origin is 0. kvm_s390_get_gisa_desc() is used to determine which gisa designation to set in the SIE control block. A value of 0 in the gisa designation disables gisa usage. The issue surfaces in the host kernel with the following kernel message as soon a new kvm guest start is attemted. kvm: unhandled validity intercept 0x1011 WARNING: CPU: 0 PID: 781237 at arch/s390/kvm/intercept.c:101 kvm_handle_sie_intercept+0x42e/0x4d0 [kvm] Modules linked in: vhost_net tap tun xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT xt_tcpudp nft_compat x_tables nf_nat_tftp nf_conntrack_tftp vfio_pci_core irqbypass vhost_vsock vmw_vsock_virtio_transport_common vsock vhost vhost_iotlb kvm nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables sunrpc mlx5_ib ib_uverbs ib_core mlx5_core uvdevice s390_trng eadm_sch vfio_ccw zcrypt_cex4 mdev vfio_iommu_type1 vfio sch_fq_codel drm i2c_core loop drm_panel_orientation_quirks configfs nfnetlink lcs ctcm fsm dm_service_time ghash_s390 prng chacha_s390 libchacha aes_s390 des_s390 libdes sha3_512_s390 sha3_256_s390 sha512_s390 sha256_s390 sha1_s390 sha_common dm_mirror dm_region_hash dm_log zfcp scsi_transport_fc scsi_dh_rdac scsi_dh_emc scsi_dh_alua pkey zcrypt dm_multipath rng_core autofs4 [last unloaded: vfio_pci] CPU: 0 PID: 781237 Comm: CPU 0/KVM Not tainted 6.10.0-08682-gcad9f11498ea #6 Hardware name: IBM 3931 A01 701 (LPAR) Krnl PSW : 0704c00180000000 000003d93deb0122 (kvm_handle_sie_intercept+0x432/0x4d0 [kvm]) R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:0 PM:0 RI:0 EA:3 Krnl GPRS: 000003d900000027 000003d900000023 0000000000000028 000002cd00000000 000002d063a00900 00000359c6daf708 00000000000bebb5 0000000000001eff 000002cfd82e9000 000002cfd80bc000 0000000000001011 000003d93deda412 000003ff8962df98 000003d93de77ce0 000003d93deb011e 00000359c6daf960 Krnl Code: 000003d93deb0112: c020fffe7259 larl %r2,000003d93de7e5c4 000003d93deb0118: c0e53fa8beac brasl %r14,000003d9bd3c7e70 #000003d93deb011e: af000000 mc 0,0 >000003d93deb0122: a728ffea lhi %r2,-22 000003d93deb0126: a7f4fe24 brc 15,000003d93deafd6e 000003d93deb012a: 9101f0b0 tm 176(%r15),1 000003d93deb012e: a774fe48 brc 7,000003d93deafdbe 000003d93deb0132: 40a0f0ae sth %r10,174(%r15) Call Trace: [<000003d93deb0122>] kvm_handle_sie_intercept+0x432/0x4d0 [kvm] ([<000003d93deb011e>] kvm_handle_sie_intercept+0x42e/0x4d0 [kvm]) [<000003d93deacc10>] vcpu_post_run+0x1d0/0x3b0 [kvm] [<000003d93deaceda>] __vcpu_run+0xea/0x2d0 [kvm] [<000003d93dead9da>] kvm_arch_vcpu_ioctl_run+0x16a/0x430 [kvm] [<000003d93de93ee0>] kvm_vcpu_ioctl+0x190/0x7c0 [kvm] [<000003d9bd728b4e>] vfs_ioctl+0x2e/0x70 [<000003d9bd72a092>] __s390x_sys_ioctl+0xc2/0xd0 [<000003d9be0e9222>] __do_syscall+0x1f2/0x2e0 [<000003d9be0f9a90>] system_call+0x70/0x98 Last Breaking-Event-Address: [<000003d9bd3c7f58>] __warn_printk+0xe8/0xf0 Cc: stable@vger.kernel.org Reported-by: Christian Borntraeger Fixes: fe0ef0030463 ("KVM: s390: sort out physical vs virtual pointers usage") Signed-off-by: Michael Mueller Tested-by: Christian Borntraeger Reviewed-by: Janosch Frank Link: https://lore.kernel.org/r/20240801123109.2782155-1-mimu@linux.ibm.com Message-ID: <20240801123109.2782155-1-mimu@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/kvm/kvm-s390.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index bf8534218af3..e680c6bf0c9d 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -267,7 +267,12 @@ static inline unsigned long kvm_s390_get_gfn_end(struct kvm_memslots *slots) static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm) { - u32 gd = virt_to_phys(kvm->arch.gisa_int.origin); + u32 gd; + + if (!kvm->arch.gisa_int.origin) + return 0; + + gd = virt_to_phys(kvm->arch.gisa_int.origin); if (gd && sclp.has_gisaf) gd |= GISA_FORMAT1; From ee9a68394b4bea8b9044ec4bfdbaacf45297ecef Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Thu, 1 Aug 2024 21:14:04 +0200 Subject: [PATCH 055/562] riscv: Re-introduce global icache flush in patch_text_XXX() commit edf2d546bfd6 ("riscv: patch: Flush the icache right after patching to avoid illegal insns") mistakenly removed the global icache flush in patch_text_nosync() and patch_text_set_nosync() functions, so reintroduce them. Fixes: edf2d546bfd6 ("riscv: patch: Flush the icache right after patching to avoid illegal insns") Reported-by: Samuel Holland Closes: https://lore.kernel.org/linux-riscv/a28ddc26-d77a-470a-a33f-88144f717e86@sifive.com/ Signed-off-by: Alexandre Ghiti Reviewed-by: Samuel Holland Reviewed-by: Charlie Jenkins Link: https://lore.kernel.org/r/20240801191404.55181-1-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/patch.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 69e5796fc51f..34ef522f07a8 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -205,6 +205,8 @@ int patch_text_set_nosync(void *addr, u8 c, size_t len) int ret; ret = patch_insn_set(addr, c, len); + if (!ret) + flush_icache_range((uintptr_t)addr, (uintptr_t)addr + len); return ret; } @@ -239,6 +241,8 @@ int patch_text_nosync(void *addr, const void *insns, size_t len) int ret; ret = patch_insn_write(addr, insns, len); + if (!ret) + flush_icache_range((uintptr_t)addr, (uintptr_t)addr + len); return ret; } From fbc05142ccdd0061f6d0e489608935943d2984a1 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 6 Aug 2024 12:01:40 -0700 Subject: [PATCH 056/562] perf tools: Add tools/include/uapi/README Write down the reason why we keep a copy of headers to the README file instead of adding it to every commit messages. Suggested-by: Jani Nikula Original-by: Arnaldo Carvalho de Melo Original-by: Ingo Molnar Signed-off-by: Namhyung Kim --- tools/include/uapi/README | 73 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) create mode 100644 tools/include/uapi/README diff --git a/tools/include/uapi/README b/tools/include/uapi/README new file mode 100644 index 000000000000..7147b1b2cb28 --- /dev/null +++ b/tools/include/uapi/README @@ -0,0 +1,73 @@ +Why we want a copy of kernel headers in tools? +============================================== + +There used to be no copies, with tools/ code using kernel headers +directly. From time to time tools/perf/ broke due to legitimate kernel +hacking. At some point Linus complained about such direct usage. Then we +adopted the current model. + +The way these headers are used in perf are not restricted to just +including them to compile something. + +There are sometimes used in scripts that convert defines into string +tables, etc, so some change may break one of these scripts, or new MSRs +may use some different #define pattern, etc. + +E.g.: + + $ ls -1 tools/perf/trace/beauty/*.sh | head -5 + tools/perf/trace/beauty/arch_errno_names.sh + tools/perf/trace/beauty/drm_ioctl.sh + tools/perf/trace/beauty/fadvise.sh + tools/perf/trace/beauty/fsconfig.sh + tools/perf/trace/beauty/fsmount.sh + $ + $ tools/perf/trace/beauty/fadvise.sh + static const char *fadvise_advices[] = { + [0] = "NORMAL", + [1] = "RANDOM", + [2] = "SEQUENTIAL", + [3] = "WILLNEED", + [4] = "DONTNEED", + [5] = "NOREUSE", + }; + $ + +The tools/perf/check-headers.sh script, part of the tools/ build +process, points out changes in the original files. + +So its important not to touch the copies in tools/ when doing changes in +the original kernel headers, that will be done later, when +check-headers.sh inform about the change to the perf tools hackers. + +Another explanation from Ingo Molnar: +It's better than all the alternatives we tried so far: + + - Symbolic links and direct #includes: this was the original approach but + was pushed back on from the kernel side, when tooling modified the + headers and broke them accidentally for kernel builds. + + - Duplicate self-defined ABI headers like glibc: double the maintenance + burden, double the chance for mistakes, plus there's no tech-driven + notification mechanism to look at new kernel side changes. + +What we are doing now is a third option: + + - A software-enforced copy-on-write mechanism of kernel headers to + tooling, driven by non-fatal warnings on the tooling side build when + kernel headers get modified: + + Warning: Kernel ABI header differences: + diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h + diff -u tools/include/uapi/linux/fs.h include/uapi/linux/fs.h + diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h + ... + + The tooling policy is to always pick up the kernel side headers as-is, + and integate them into the tooling build. The warnings above serve as a + notification to tooling maintainers that there's changes on the kernel + side. + +We've been using this for many years now, and it might seem hacky, but +works surprisingly well. + From aef21f6b6a4aae648c890e74c2322d10ab267249 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 6 Aug 2024 09:59:26 -0700 Subject: [PATCH 057/562] tools/include: Sync uapi/drm/i915_drm.h with the kernel sources To pick up changes from: 0f1bb41bf396 drm/i915: Support replaying GPU hangs with captured context image This should be used to beautify DRM syscall arguments and it addresses these tools/perf build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h Please see tools/include/uapi/README for details (it's in the first patch of this series). Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Rodrigo Vivi Cc: intel-gfx@lists.freedesktop.org Signed-off-by: Namhyung Kim --- tools/include/uapi/drm/i915_drm.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index d4d86e566e07..535cb68fdb5c 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -2163,6 +2163,15 @@ struct drm_i915_gem_context_param { * supports this per context flag. */ #define I915_CONTEXT_PARAM_LOW_LATENCY 0xe + +/* + * I915_CONTEXT_PARAM_CONTEXT_IMAGE: + * + * Allows userspace to provide own context images. + * + * Note that this is a debug API not available on production kernel builds. + */ +#define I915_CONTEXT_PARAM_CONTEXT_IMAGE 0xf /* Must be kept compact -- no holes and well documented */ /** @value: Context parameter value to be set or queried */ @@ -2564,6 +2573,24 @@ struct i915_context_param_engines { struct i915_engine_class_instance engines[N__]; \ } __attribute__((packed)) name__ +struct i915_gem_context_param_context_image { + /** @engine: Engine class & instance to be configured. */ + struct i915_engine_class_instance engine; + + /** @flags: One of the supported flags or zero. */ + __u32 flags; +#define I915_CONTEXT_IMAGE_FLAG_ENGINE_INDEX (1u << 0) + + /** @size: Size of the image blob pointed to by @image. */ + __u32 size; + + /** @mbz: Must be zero. */ + __u32 mbz; + + /** @image: Userspace memory containing the context image. */ + __u64 image; +} __attribute__((packed)); + /** * struct drm_i915_gem_context_create_ext_setparam - Context parameter * to set or query during context creation. From a625df3995c31a5d8cf46f2337b207e93bef9bdd Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 6 Aug 2024 12:07:50 -0700 Subject: [PATCH 058/562] tools/include: Sync uapi/linux/kvm.h with the kernel sources And other arch-specific UAPI headers to pick up changes from: 4b23e0c199b2 KVM: Ensure new code that references immediate_exit gets extra scrutiny 85542adb65ec KVM: x86: Add KVM_RUN_X86_GUEST_MODE kvm_run flag 6fef518594bc KVM: x86: Add a capability to configure bus frequency for APIC timer 34ff65901735 x86/sev: Use kernel provided SVSM Calling Areas 5dcc1e76144f Merge tag 'kvm-x86-misc-6.11' of https://github.com/kvm-x86/linux into HEAD 9a0d2f4995dd KVM: PPC: Book3S HV: Add one-reg interface for HASHPKEYR register e9eb790b2557 KVM: PPC: Book3S HV: Add one-reg interface for HASHKEYR register 1a1e6865f516 KVM: PPC: Book3S HV: Add one-reg interface for DEXCR register This should be used to beautify KVM syscall arguments and it addresses these tools/perf build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h diff -u tools/arch/x86/include/uapi/asm/svm.h arch/x86/include/uapi/asm/svm.h diff -u tools/arch/powerpc/include/uapi/asm/kvm.h arch/powerpc/include/uapi/asm/kvm.h Please see tools/include/uapi/README for details (it's in the first patch of this series). Cc: Paolo Bonzini Cc: kvm@vger.kernel.org Signed-off-by: Namhyung Kim --- tools/arch/powerpc/include/uapi/asm/kvm.h | 3 ++ tools/arch/x86/include/uapi/asm/kvm.h | 49 +++++++++++++++++++++++ tools/arch/x86/include/uapi/asm/svm.h | 1 + tools/include/uapi/linux/kvm.h | 17 +++++++- 4 files changed, 69 insertions(+), 1 deletion(-) diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 1691297a766a..eaeda001784e 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -645,6 +645,9 @@ struct kvm_ppc_cpu_char { #define KVM_REG_PPC_SIER3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3) #define KVM_REG_PPC_DAWR1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc4) #define KVM_REG_PPC_DAWRX1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc5) +#define KVM_REG_PPC_DEXCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc6) +#define KVM_REG_PPC_HASHKEYR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc7) +#define KVM_REG_PPC_HASHPKEYR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc8) /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 9fae1b73b529..bf57a824f722 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -106,6 +106,7 @@ struct kvm_ioapic_state { #define KVM_RUN_X86_SMM (1 << 0) #define KVM_RUN_X86_BUS_LOCK (1 << 1) +#define KVM_RUN_X86_GUEST_MODE (1 << 2) /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { @@ -697,6 +698,11 @@ enum sev_cmd_id { /* Second time is the charm; improved versions of the above ioctls. */ KVM_SEV_INIT2, + /* SNP-specific commands */ + KVM_SEV_SNP_LAUNCH_START = 100, + KVM_SEV_SNP_LAUNCH_UPDATE, + KVM_SEV_SNP_LAUNCH_FINISH, + KVM_SEV_NR_MAX, }; @@ -824,6 +830,48 @@ struct kvm_sev_receive_update_data { __u32 pad2; }; +struct kvm_sev_snp_launch_start { + __u64 policy; + __u8 gosvw[16]; + __u16 flags; + __u8 pad0[6]; + __u64 pad1[4]; +}; + +/* Kept in sync with firmware values for simplicity. */ +#define KVM_SEV_SNP_PAGE_TYPE_NORMAL 0x1 +#define KVM_SEV_SNP_PAGE_TYPE_ZERO 0x3 +#define KVM_SEV_SNP_PAGE_TYPE_UNMEASURED 0x4 +#define KVM_SEV_SNP_PAGE_TYPE_SECRETS 0x5 +#define KVM_SEV_SNP_PAGE_TYPE_CPUID 0x6 + +struct kvm_sev_snp_launch_update { + __u64 gfn_start; + __u64 uaddr; + __u64 len; + __u8 type; + __u8 pad0; + __u16 flags; + __u32 pad1; + __u64 pad2[4]; +}; + +#define KVM_SEV_SNP_ID_BLOCK_SIZE 96 +#define KVM_SEV_SNP_ID_AUTH_SIZE 4096 +#define KVM_SEV_SNP_FINISH_DATA_SIZE 32 + +struct kvm_sev_snp_launch_finish { + __u64 id_block_uaddr; + __u64 id_auth_uaddr; + __u8 id_block_en; + __u8 auth_key_en; + __u8 vcek_disabled; + __u8 host_data[KVM_SEV_SNP_FINISH_DATA_SIZE]; + __u8 pad0[3]; + __u16 flags; + __u64 pad1[4]; +}; + #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) @@ -874,5 +922,6 @@ struct kvm_hyperv_eventfd { #define KVM_X86_SW_PROTECTED_VM 1 #define KVM_X86_SEV_VM 2 #define KVM_X86_SEV_ES_VM 3 +#define KVM_X86_SNP_VM 4 #endif /* _ASM_X86_KVM_H */ diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h index 80e1df482337..1814b413fd57 100644 --- a/tools/arch/x86/include/uapi/asm/svm.h +++ b/tools/arch/x86/include/uapi/asm/svm.h @@ -115,6 +115,7 @@ #define SVM_VMGEXIT_AP_CREATE_ON_INIT 0 #define SVM_VMGEXIT_AP_CREATE 1 #define SVM_VMGEXIT_AP_DESTROY 2 +#define SVM_VMGEXIT_SNP_RUN_VMPL 0x80000018 #define SVM_VMGEXIT_HV_FEATURES 0x8000fffd #define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe #define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index e5af8c692dc0..637efc055145 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -192,11 +192,24 @@ struct kvm_xen_exit { /* Flags that describe what fields in emulation_failure hold valid data. */ #define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0) +/* + * struct kvm_run can be modified by userspace at any time, so KVM must be + * careful to avoid TOCTOU bugs. In order to protect KVM, HINT_UNSAFE_IN_KVM() + * renames fields in struct kvm_run from to __unsafe when + * compiled into the kernel, ensuring that any use within KVM is obvious and + * gets extra scrutiny. + */ +#ifdef __KERNEL__ +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol##__unsafe +#else +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol +#endif + /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { /* in */ __u8 request_interrupt_window; - __u8 immediate_exit; + __u8 HINT_UNSAFE_IN_KVM(immediate_exit); __u8 padding1[6]; /* out */ @@ -918,6 +931,8 @@ struct kvm_enable_cap { #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 #define KVM_CAP_PRE_FAULT_MEMORY 236 +#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237 +#define KVM_CAP_X86_GUEST_MODE 238 struct kvm_irq_routing_irqchip { __u32 irqchip; From 8ec9497d3ef34fab216e277eca5035811f06b421 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 6 Aug 2024 12:07:50 -0700 Subject: [PATCH 059/562] tools/include: Sync uapi/linux/perf.h with the kernel sources To pick up changes from: 608f6976c309 perf/x86/intel: Support new data source for Lunar Lake This should be used to beautify perf syscall arguments and it addresses these tools/perf build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/linux/perf_event.h include/uapi/linux/perf_event.h Please see tools/include/uapi/README for details (it's in the first patch of this series). Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Ian Rogers Cc: Adrian Hunter Cc: "Liang, Kan" Cc: linux-perf-users@vger.kernel.org Signed-off-by: Namhyung Kim --- tools/include/uapi/linux/perf_event.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 3a64499b0f5d..4842c36fdf80 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1349,12 +1349,14 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ #define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ #define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ -/* 5-0x7 available */ +#define PERF_MEM_LVLNUM_L2_MHB 0x05 /* L2 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_MSC 0x06 /* Memory-side Cache */ +/* 0x7 available */ #define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */ #define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ #define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ -#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */ +#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB / L1 Miss Handling Buffer */ #define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ #define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */ #define PERF_MEM_LVLNUM_NA 0x0f /* N/A */ From b9735006762677c2cd794bfcb1463a9a6ed558dd Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 6 Aug 2024 12:07:50 -0700 Subject: [PATCH 060/562] tools/include: Sync uapi/sound/asound.h with the kernel sources To pick up changes from: f05c1ffc2745 ALSA: pcm: reinvent the stream synchronization ID API This should be used to beautify sound syscall arguments and it addresses these tools/perf build warnings: Warning: Kernel ABI header differences: diff -u tools/perf/trace/beauty/include/uapi/sound/asound.h include/uapi/sound/asound.h Please see tools/include/uapi/README for details (it's in the first patch of this series). Cc: Jaroslav Kysela Cc: Takashi Iwai Cc: linux-sound@vger.kernel.org Signed-off-by: Namhyung Kim --- tools/perf/trace/beauty/include/uapi/sound/asound.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/tools/perf/trace/beauty/include/uapi/sound/asound.h b/tools/perf/trace/beauty/include/uapi/sound/asound.h index 628d46a0da92..8bf7e8a0eb6f 100644 --- a/tools/perf/trace/beauty/include/uapi/sound/asound.h +++ b/tools/perf/trace/beauty/include/uapi/sound/asound.h @@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image { * * *****************************************************************************/ -#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 17) +#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 18) typedef unsigned long snd_pcm_uframes_t; typedef signed long snd_pcm_sframes_t; @@ -334,7 +334,7 @@ union snd_pcm_sync_id { unsigned char id[16]; unsigned short id16[8]; unsigned int id32[4]; -}; +} __attribute__((deprecated)); struct snd_pcm_info { unsigned int device; /* RO/WR (control): device number */ @@ -348,7 +348,7 @@ struct snd_pcm_info { int dev_subclass; /* SNDRV_PCM_SUBCLASS_* */ unsigned int subdevices_count; unsigned int subdevices_avail; - union snd_pcm_sync_id sync; /* hardware synchronization ID */ + unsigned char pad1[16]; /* was: hardware synchronization ID */ unsigned char reserved[64]; /* reserved for future... */ }; @@ -420,7 +420,8 @@ struct snd_pcm_hw_params { unsigned int rate_num; /* R: rate numerator */ unsigned int rate_den; /* R: rate denominator */ snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */ - unsigned char reserved[64]; /* reserved for future */ + unsigned char sync[16]; /* R: synchronization ID (perfect sync - one clock source) */ + unsigned char reserved[48]; /* reserved for future */ }; enum { From 379d9af3f3da2da1bbfa67baf1820c72a080d1f1 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Tue, 6 Aug 2024 14:51:13 +0800 Subject: [PATCH 061/562] selinux: fix potential counting error in avc_add_xperms_decision() The count increases only when a node is successfully added to the linked list. Cc: stable@vger.kernel.org Fixes: fa1aa143ac4a ("selinux: extended permissions for ioctls") Signed-off-by: Zhen Lei Acked-by: Stephen Smalley Signed-off-by: Paul Moore --- security/selinux/avc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/selinux/avc.c b/security/selinux/avc.c index 32eb67fb3e42..7087cd2b802d 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -330,12 +330,12 @@ static int avc_add_xperms_decision(struct avc_node *node, { struct avc_xperms_decision_node *dest_xpd; - node->ae.xp_node->xp.len++; dest_xpd = avc_xperms_decision_alloc(src->used); if (!dest_xpd) return -ENOMEM; avc_copy_xperms_decision(&dest_xpd->xpd, src); list_add(&dest_xpd->xpd_list, &node->ae.xp_node->xpd_head); + node->ae.xp_node->xp.len++; return 0; } From fe992163575b187405899c5abaad8ef6fb828ff6 Mon Sep 17 00:00:00 2001 From: Sarthak Singh Date: Wed, 24 Jul 2024 22:57:06 +0530 Subject: [PATCH 062/562] rust: Support latest version of `rust-analyzer` Sets the `sysroot` field in rust-project.json which is now needed in newer versions of rust-analyzer instead of the `sysroot_src` field. Till [1] `rust-analyzer` used to guess the `sysroot` based on the `sysroot_src` at [2]. Now `sysroot` is a required parameter for a `rust-project.json` file. It is required because `rust-analyzer` need it to find the proc-macro server [3]. In the current version of `rust-analyzer` the `sysroot_src` is only used to include the inbuilt library crates (std, core, alloc, etc) [4]. Since we already specify the core library to be included in the `rust-project.json` we don't need to define the `sysroot_src`. Code editors like VS Code try to use the latest version of rust-analyzer (which is updated every week) instead of the version of rust-analyzer that comes with the rustup toolchain (which is updated every six weeks along with the rust version). Without this change `rust-analyzer` is breaking for anyone using VS Code. As they are getting the latest version of `rust-analyzer` with the changes made in [1]. `rust-analyzer` will also start breaking for other developers as they update their rust version (assuming that also updates the rust-analyzer version on their system). This patch should work with every setup as there is no more guess work being done by `rust-analyzer`. [ Lukas, who leads the rust-analyzer team, says: `sysroot_src` is required now if you want to have the sysroot source libraries be loaded. I think we used to infer it as `{sysroot}/lib/rustlib/src/rust/library` before when only the `sysroot` field was given but that was since changed to make it possible in having a sysroot without the standard library sources (that is only have the binaries available). So if you want the library sources to be loaded by rust-analyzer you will have to set that field as well now. - Miguel ] Link: https://github.com/rust-lang/rust-analyzer/pull/17287 [1] Link: https://github.com/rust-lang/rust-analyzer/blob/f372a8a1176ff8dd5f45ab2ddd45f3530db0374f/crates/project-model/src/workspace.rs#L367-L374 [2] Link: https://github.com/rust-lang/rust-analyzer/blob/eeb192b79aeac47b40add66347022af17a74fbaf/crates/project-model/src/sysroot.rs#L180-L192 [3] Link: https://github.com/search?q=repo%3AVeykril%2Frust-analyzer%20src_root()&type=code [4] Tested-by: Dirk Behme Signed-off-by: Sarthak Singh Link: https://rust-for-linux.zulipchat.com/#narrow/stream/291565-Help/topic/How.20to.20rust-analyzer.20correctly.20working Link: https://lore.kernel.org/r/20240724172713.899399-1-sarthak.singh99@gmail.com [ Formatted comment, fixed typo and removed spurious empty line. - Miguel ] Signed-off-by: Miguel Ojeda --- rust/Makefile | 2 +- scripts/generate_rust_analyzer.py | 6 +++++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/rust/Makefile b/rust/Makefile index 1f10f92737f2..6c0644b6090c 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -350,7 +350,7 @@ rust-analyzer: $(Q)$(srctree)/scripts/generate_rust_analyzer.py \ --cfgs='core=$(core-cfgs)' --cfgs='alloc=$(alloc-cfgs)' \ $(realpath $(srctree)) $(realpath $(objtree)) \ - $(RUST_LIB_SRC) $(KBUILD_EXTMOD) > \ + $(rustc_sysroot) $(RUST_LIB_SRC) $(KBUILD_EXTMOD) > \ $(if $(KBUILD_EXTMOD),$(extmod_prefix),$(objtree))/rust-project.json redirect-intrinsics = \ diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py index f270c7b0cf34..d2bc63cde8c6 100755 --- a/scripts/generate_rust_analyzer.py +++ b/scripts/generate_rust_analyzer.py @@ -145,6 +145,7 @@ def main(): parser.add_argument('--cfgs', action='append', default=[]) parser.add_argument("srctree", type=pathlib.Path) parser.add_argument("objtree", type=pathlib.Path) + parser.add_argument("sysroot", type=pathlib.Path) parser.add_argument("sysroot_src", type=pathlib.Path) parser.add_argument("exttree", type=pathlib.Path, nargs="?") args = parser.parse_args() @@ -154,9 +155,12 @@ def main(): level=logging.INFO if args.verbose else logging.WARNING ) + # Making sure that the `sysroot` and `sysroot_src` belong to the same toolchain. + assert args.sysroot in args.sysroot_src.parents + rust_project = { "crates": generate_crates(args.srctree, args.objtree, args.sysroot_src, args.exttree, args.cfgs), - "sysroot_src": str(args.sysroot_src), + "sysroot": str(args.sysroot), } json.dump(rust_project, sys.stdout, sort_keys=True, indent=4) From cff59d8631e1409ffdd22d9d717e15810181b32c Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Thu, 1 Aug 2024 13:25:48 +0200 Subject: [PATCH 063/562] s390/uv: Panic for set and remove shared access UVC errors The return value uv_set_shared() and uv_remove_shared() (which are wrappers around the share() function) is not always checked. The system integrity of a protected guest depends on the Share and Unshare UVCs being successful. This means that any caller that fails to check the return value will compromise the security of the protected guest. No code path that would lead to such violation of the security guarantees is currently exercised, since all the areas that are shared never get unshared during the lifetime of the system. This might change and become an issue in the future. The Share and Unshare UVCs can only fail in case of hypervisor misbehaviour (either a bug or malicious behaviour). In such cases there is no reasonable way forward, and the system needs to panic. This patch replaces the return at the end of the share() function with a panic, to guarantee system integrity. Fixes: 5abb9351dfd9 ("s390/uv: introduce guest side ultravisor code") Signed-off-by: Claudio Imbrenda Reviewed-by: Christian Borntraeger Reviewed-by: Steffen Eiden Reviewed-by: Janosch Frank Link: https://lore.kernel.org/r/20240801112548.85303-1-imbrenda@linux.ibm.com Message-ID: <20240801112548.85303-1-imbrenda@linux.ibm.com> [frankja@linux.ibm.com: Fixed up patch subject] Signed-off-by: Janosch Frank --- arch/s390/include/asm/uv.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 0b5f8f3e84f1..153d93468b77 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -441,7 +441,10 @@ static inline int share(unsigned long addr, u16 cmd) if (!uv_call(0, (u64)&uvcb)) return 0; - return -EINVAL; + pr_err("%s UVC failed (rc: 0x%x, rrc: 0x%x), possible hypervisor bug.\n", + uvcb.header.cmd == UVC_CMD_SET_SHARED_ACCESS ? "Share" : "Unshare", + uvcb.header.rc, uvcb.header.rrc); + panic("System security cannot be guaranteed unless the system panics now.\n"); } /* From f1cb9d5aefba07fc52b06b7bd5fdcd9ef91157b4 Mon Sep 17 00:00:00 2001 From: Bitterblue Smith Date: Tue, 6 Aug 2024 19:20:11 +0300 Subject: [PATCH 064/562] wifi: rtlwifi: rtl8192du: Initialise value32 in _rtl92du_init_queue_reserved_page GCC complains: In file included from include/linux/ieee80211.h:21, from include/net/mac80211.h:20, from drivers/net/wireless/realtek/rtlwifi/rtl8192du/../wifi.h:14, from drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c:4: In function 'u32p_replace_bits', inlined from '_rtl92du_init_queue_reserved_page.isra' at drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c:225:2: >> include/linux/bitfield.h:189:18: warning: 'value32' is used uninitialized [-Wuninitialized] Part of the variable is indeed left uninitialised. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202408062100.DWhN0CYH-lkp@intel.com/ Fixes: e769c67105d3 ("wifi: rtlwifi: Add rtl8192du/hw.{c,h}") Signed-off-by: Bitterblue Smith Acked-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://patch.msgid.link/2a808244-93d0-492c-b304-ae1974df5df9@gmail.com --- drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c index 700c6e2bcad1..ff458fb8514d 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c @@ -181,11 +181,11 @@ static void _rtl92du_init_queue_reserved_page(struct ieee80211_hw *hw, struct rtl_hal *rtlhal = rtl_hal(rtlpriv); u32 txqpagenum, txqpageunit; u32 txqremainingpage; + u32 value32 = 0; u32 numhq = 0; u32 numlq = 0; u32 numnq = 0; u32 numpubq; - u32 value32; if (rtlhal->macphymode != SINGLEMAC_SINGLEPHY) { numpubq = NORMAL_PAGE_NUM_PUBQ_92D_DUAL_MAC; From 568901e709d7fa564dfdc75816ea59fec65d20a0 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 6 Aug 2024 12:07:50 -0700 Subject: [PATCH 065/562] tools/include: Sync uapi/asm-generic/unistd.h with the kernel sources And arch syscall tables to pick up changes from: b1e31c134a8a powerpc: restore some missing spu syscalls d3882564a77c syscalls: fix compat_sys_io_pgetevents_time64 usage 54233a425403 uretprobe: change syscall number, again 63ded110979b uprobe: Change uretprobe syscall scope and number 9142be9e6443 x86/syscall: Mark exit[_group] syscall handlers __noreturn 9aae1baa1c5d x86, arm: Add missing license tag to syscall tables files 5c28424e9a34 syscalls: Fix to add sys_uretprobe to syscall.tbl 190fec72df4a uprobe: Wire up uretprobe system call This should be used to beautify syscall arguments and it addresses these tools/perf build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl diff -u tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl Please see tools/include/uapi/README for details (it's in the first patch of this series). Cc: Arnd Bergmann Cc: linux-arch@vger.kernel.org Signed-off-by: Namhyung Kim --- tools/include/uapi/asm-generic/unistd.h | 2 +- tools/perf/arch/powerpc/entry/syscalls/syscall.tbl | 6 +++++- tools/perf/arch/s390/entry/syscalls/syscall.tbl | 2 +- tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 8 +++++--- 4 files changed, 12 insertions(+), 6 deletions(-) diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index a00d53d02723..5bf6148cac2b 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -737,7 +737,7 @@ __SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64) #define __NR_ppoll_time64 414 __SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64) #define __NR_io_pgetevents_time64 416 -__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents) +__SC_COMP(__NR_io_pgetevents_time64, sys_io_pgetevents, compat_sys_io_pgetevents_time64) #define __NR_recvmmsg_time64 417 __SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64) #define __NR_mq_timedsend_time64 418 diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 3656f1ca7a21..ebae8415dfbb 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -230,8 +230,10 @@ 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64 179 64 pread64 sys_pread64 +179 spu pread64 sys_pread64 180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64 180 64 pwrite64 sys_pwrite64 +180 spu pwrite64 sys_pwrite64 181 common chown sys_chown 182 common getcwd sys_getcwd 183 common capget sys_capget @@ -246,6 +248,7 @@ 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit 191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead 191 64 readahead sys_readahead +191 spu readahead sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64 194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64 @@ -293,6 +296,7 @@ 232 nospu set_tid_address sys_set_tid_address 233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64 233 64 fadvise64 sys_fadvise64 +233 spu fadvise64 sys_fadvise64 234 nospu exit_group sys_exit_group 235 nospu lookup_dcookie sys_ni_syscall 236 common epoll_create sys_epoll_create @@ -502,7 +506,7 @@ 412 32 utimensat_time64 sys_utimensat sys_utimensat 413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend 419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index bd0fee24ad10..01071182763e 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -418,7 +418,7 @@ 412 32 utimensat_time64 - sys_utimensat 413 32 pselect6_time64 - compat_sys_pselect6_time64 414 32 ppoll_time64 - compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 - sys_io_pgetevents +416 32 io_pgetevents_time64 - compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 - sys_mq_timedsend 419 32 mq_timedreceive_time64 - sys_mq_timedreceive diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index a396f6e6ab5b..7093ee21c0d1 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -1,8 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note # # 64-bit system call numbers and entry vectors # # The format is: -# +# [ [noreturn]] # # The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls # @@ -68,7 +69,7 @@ 57 common fork sys_fork 58 common vfork sys_vfork 59 64 execve sys_execve -60 common exit sys_exit +60 common exit sys_exit - noreturn 61 common wait4 sys_wait4 62 common kill sys_kill 63 common uname sys_newuname @@ -239,7 +240,7 @@ 228 common clock_gettime sys_clock_gettime 229 common clock_getres sys_clock_getres 230 common clock_nanosleep sys_clock_nanosleep -231 common exit_group sys_exit_group +231 common exit_group sys_exit_group - noreturn 232 common epoll_wait sys_epoll_wait 233 common epoll_ctl sys_epoll_ctl 234 common tgkill sys_tgkill @@ -343,6 +344,7 @@ 332 common statx sys_statx 333 common io_pgetevents sys_io_pgetevents 334 common rseq sys_rseq +335 common uretprobe sys_uretprobe # don't use numbers 387 through 423, add new calls after the last # 'common' entry 424 common pidfd_send_signal sys_pidfd_send_signal From ed86525f1f4b738bae75c73e89f25430bd0af1b0 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 6 Aug 2024 12:07:50 -0700 Subject: [PATCH 066/562] tools/include: Sync network socket headers with the kernel sources To pick up changes from: d25a92ccae6b net/smc: Introduce IPPROTO_SMC 060f4ba6e403 io_uring/net: move charging socket out of zc io_uring bb6aaf736680 net: Split a __sys_listen helper for io_uring dc2e77979412 net: Split a __sys_bind helper for io_uring This should be used to beautify socket syscall arguments and it addresses these tools/perf build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/linux/in.h include/uapi/linux/in.h diff -u tools/perf/trace/beauty/include/linux/socket.h include/linux/socket.h Please see tools/include/uapi/README for details (it's in the first patch of this series). Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: netdev@vger.kernel.org Signed-off-by: Namhyung Kim --- tools/include/uapi/linux/in.h | 2 ++ tools/perf/trace/beauty/include/linux/socket.h | 5 ++++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index e682ab628dfa..d358add1611c 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -81,6 +81,8 @@ enum { #define IPPROTO_ETHERNET IPPROTO_ETHERNET IPPROTO_RAW = 255, /* Raw IP packets */ #define IPPROTO_RAW IPPROTO_RAW + IPPROTO_SMC = 256, /* Shared Memory Communications */ +#define IPPROTO_SMC IPPROTO_SMC IPPROTO_MPTCP = 262, /* Multipath TCP connection */ #define IPPROTO_MPTCP IPPROTO_MPTCP IPPROTO_MAX diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 89d16b90370b..df9cdb8bbfb8 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -76,7 +76,7 @@ struct msghdr { __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ struct ubuf_info *msg_ubuf; - int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb, + int (*sg_from_iter)(struct sk_buff *skb, struct iov_iter *from, size_t length); }; @@ -442,11 +442,14 @@ extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, extern int __sys_socket(int family, int type, int protocol); extern struct file *__sys_socket_file(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); +extern int __sys_bind_socket(struct socket *sock, struct sockaddr_storage *address, + int addrlen); extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, int addrlen, int file_flags); extern int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen); extern int __sys_listen(int fd, int backlog); +extern int __sys_listen_socket(struct socket *sock, int backlog); extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len); extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, From 845295f4004c7e1591bab4bad01b51f37d32272f Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 6 Aug 2024 12:07:50 -0700 Subject: [PATCH 067/562] tools/include: Sync filesystem headers with the kernel sources To pick up changes from: 0f9ca80fa4f9 fs: Add initial atomic write support info to statx f9af549d1fd3 fs: export mount options via statmount() 0a3deb11858a fs: Allow listmount() in foreign mount namespace 09b31295f833 fs: export the mount ns id via statmount d04bccd8c19d listmount: allow listing in reverse order bfc69fd05ef9 fs/procfs: add build ID fetching to PROCMAP_QUERY API ed5d583a88a9 fs/procfs: implement efficient VMA querying API for /proc//maps This should be used to beautify FS syscall arguments and it addresses these tools/perf build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/linux/stat.h include/uapi/linux/stat.h diff -u tools/perf/trace/beauty/include/uapi/linux/fs.h include/uapi/linux/fs.h diff -u tools/perf/trace/beauty/include/uapi/linux/mount.h include/uapi/linux/mount.h diff -u tools/perf/trace/beauty/include/uapi/linux/stat.h include/uapi/linux/stat.h Please see tools/include/uapi/README for details (it's in the first patch of this series). Cc: Alexander Viro Cc: Christian Brauner Cc: Jan Kara Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Namhyung Kim --- tools/include/uapi/linux/stat.h | 12 +- .../perf/trace/beauty/include/uapi/linux/fs.h | 163 +++++++++++++++++- .../trace/beauty/include/uapi/linux/mount.h | 10 +- .../trace/beauty/include/uapi/linux/stat.h | 12 +- 4 files changed, 189 insertions(+), 8 deletions(-) diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index 67626d535316..887a25286441 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -126,9 +126,15 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ - __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[11]; /* Spare space for future expansion */ + __u64 stx_subvol; /* Subvolume identifier */ + __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */ + /* 0xb0 */ + __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */ + __u32 __spare1[1]; + /* 0xb8 */ + __u64 __spare3[9]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -157,6 +163,7 @@ struct statx { #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ +#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ @@ -192,6 +199,7 @@ struct statx { #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ +#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */ #endif /* _UAPI_LINUX_STAT_H */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h index 45e4e64fd664..753971770733 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fs.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h @@ -329,12 +329,17 @@ typedef int __bitwise __kernel_rwf_t; /* per-IO negation of O_APPEND */ #define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020) +/* Atomic Write */ +#define RWF_ATOMIC ((__force __kernel_rwf_t)0x00000040) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND | RWF_NOAPPEND) + RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC) + +#define PROCFS_IOCTL_MAGIC 'f' /* Pagemap ioctl */ -#define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) +#define PAGEMAP_SCAN _IOWR(PROCFS_IOCTL_MAGIC, 16, struct pm_scan_arg) /* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */ #define PAGE_IS_WPALLOWED (1 << 0) @@ -393,4 +398,158 @@ struct pm_scan_arg { __u64 return_mask; }; +/* /proc//maps ioctl */ +#define PROCMAP_QUERY _IOWR(PROCFS_IOCTL_MAGIC, 17, struct procmap_query) + +enum procmap_query_flags { + /* + * VMA permission flags. + * + * Can be used as part of procmap_query.query_flags field to look up + * only VMAs satisfying specified subset of permissions. E.g., specifying + * PROCMAP_QUERY_VMA_READABLE only will return both readable and read/write VMAs, + * while having PROCMAP_QUERY_VMA_READABLE | PROCMAP_QUERY_VMA_WRITABLE will only + * return read/write VMAs, though both executable/non-executable and + * private/shared will be ignored. + * + * PROCMAP_QUERY_VMA_* flags are also returned in procmap_query.vma_flags + * field to specify actual VMA permissions. + */ + PROCMAP_QUERY_VMA_READABLE = 0x01, + PROCMAP_QUERY_VMA_WRITABLE = 0x02, + PROCMAP_QUERY_VMA_EXECUTABLE = 0x04, + PROCMAP_QUERY_VMA_SHARED = 0x08, + /* + * Query modifier flags. + * + * By default VMA that covers provided address is returned, or -ENOENT + * is returned. With PROCMAP_QUERY_COVERING_OR_NEXT_VMA flag set, closest + * VMA with vma_start > addr will be returned if no covering VMA is + * found. + * + * PROCMAP_QUERY_FILE_BACKED_VMA instructs query to consider only VMAs that + * have file backing. Can be combined with PROCMAP_QUERY_COVERING_OR_NEXT_VMA + * to iterate all VMAs with file backing. + */ + PROCMAP_QUERY_COVERING_OR_NEXT_VMA = 0x10, + PROCMAP_QUERY_FILE_BACKED_VMA = 0x20, +}; + +/* + * Input/output argument structured passed into ioctl() call. It can be used + * to query a set of VMAs (Virtual Memory Areas) of a process. + * + * Each field can be one of three kinds, marked in a short comment to the + * right of the field: + * - "in", input argument, user has to provide this value, kernel doesn't modify it; + * - "out", output argument, kernel sets this field with VMA data; + * - "in/out", input and output argument; user provides initial value (used + * to specify maximum allowable buffer size), and kernel sets it to actual + * amount of data written (or zero, if there is no data). + * + * If matching VMA is found (according to criterias specified by + * query_addr/query_flags, all the out fields are filled out, and ioctl() + * returns 0. If there is no matching VMA, -ENOENT will be returned. + * In case of any other error, negative error code other than -ENOENT is + * returned. + * + * Most of the data is similar to the one returned as text in /proc//maps + * file, but procmap_query provides more querying flexibility. There are no + * consistency guarantees between subsequent ioctl() calls, but data returned + * for matched VMA is self-consistent. + */ +struct procmap_query { + /* Query struct size, for backwards/forward compatibility */ + __u64 size; + /* + * Query flags, a combination of enum procmap_query_flags values. + * Defines query filtering and behavior, see enum procmap_query_flags. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_flags; /* in */ + /* + * Query address. By default, VMA that covers this address will + * be looked up. PROCMAP_QUERY_* flags above modify this default + * behavior further. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_addr; /* in */ + /* VMA starting (inclusive) and ending (exclusive) address, if VMA is found. */ + __u64 vma_start; /* out */ + __u64 vma_end; /* out */ + /* VMA permissions flags. A combination of PROCMAP_QUERY_VMA_* flags. */ + __u64 vma_flags; /* out */ + /* VMA backing page size granularity. */ + __u64 vma_page_size; /* out */ + /* + * VMA file offset. If VMA has file backing, this specifies offset + * within the file that VMA's start address corresponds to. + * Is set to zero if VMA has no backing file. + */ + __u64 vma_offset; /* out */ + /* Backing file's inode number, or zero, if VMA has no backing file. */ + __u64 inode; /* out */ + /* Backing file's device major/minor number, or zero, if VMA has no backing file. */ + __u32 dev_major; /* out */ + __u32 dev_minor; /* out */ + /* + * If set to non-zero value, signals the request to return VMA name + * (i.e., VMA's backing file's absolute path, with " (deleted)" suffix + * appended, if file was unlinked from FS) for matched VMA. VMA name + * can also be some special name (e.g., "[heap]", "[stack]") or could + * be even user-supplied with prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME). + * + * Kernel will set this field to zero, if VMA has no associated name. + * Otherwise kernel will return actual amount of bytes filled in + * user-supplied buffer (see vma_name_addr field below), including the + * terminating zero. + * + * If VMA name is longer that user-supplied maximum buffer size, + * -E2BIG error is returned. + * + * If this field is set to non-zero value, vma_name_addr should point + * to valid user space memory buffer of at least vma_name_size bytes. + * If set to zero, vma_name_addr should be set to zero as well + */ + __u32 vma_name_size; /* in/out */ + /* + * If set to non-zero value, signals the request to extract and return + * VMA's backing file's build ID, if the backing file is an ELF file + * and it contains embedded build ID. + * + * Kernel will set this field to zero, if VMA has no backing file, + * backing file is not an ELF file, or ELF file has no build ID + * embedded. + * + * Build ID is a binary value (not a string). Kernel will set + * build_id_size field to exact number of bytes used for build ID. + * If build ID is requested and present, but needs more bytes than + * user-supplied maximum buffer size (see build_id_addr field below), + * -E2BIG error will be returned. + * + * If this field is set to non-zero value, build_id_addr should point + * to valid user space memory buffer of at least build_id_size bytes. + * If set to zero, build_id_addr should be set to zero as well + */ + __u32 build_id_size; /* in/out */ + /* + * User-supplied address of a buffer of at least vma_name_size bytes + * for kernel to fill with matched VMA's name (see vma_name_size field + * description above for details). + * + * Should be set to zero if VMA name should not be returned. + */ + __u64 vma_name_addr; /* in */ + /* + * User-supplied address of a buffer of at least build_id_size bytes + * for kernel to fill with matched VMA's ELF build ID, if available + * (see build_id_size field description above for details). + * + * Should be set to zero if build ID should not be returned. + */ + __u64 build_id_addr; /* in */ +}; + #endif /* _UAPI_LINUX_FS_H */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h index ad5478dbad00..225bc366ffcb 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/mount.h +++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h @@ -154,7 +154,7 @@ struct mount_attr { */ struct statmount { __u32 size; /* Total size, including strings */ - __u32 __spare1; + __u32 mnt_opts; /* [str] Mount options of the mount */ __u64 mask; /* What results were written */ __u32 sb_dev_major; /* Device ID */ __u32 sb_dev_minor; @@ -172,7 +172,8 @@ struct statmount { __u64 propagate_from; /* Propagation from in current namespace */ __u32 mnt_root; /* [str] Root of mount relative to root of fs */ __u32 mnt_point; /* [str] Mountpoint relative to current root */ - __u64 __spare2[50]; + __u64 mnt_ns_id; /* ID of the mount namespace */ + __u64 __spare2[49]; char str[]; /* Variable size part containing strings */ }; @@ -188,10 +189,12 @@ struct mnt_id_req { __u32 spare; __u64 mnt_id; __u64 param; + __u64 mnt_ns_id; }; /* List of all mnt_id_req versions. */ #define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first published struct */ +#define MNT_ID_REQ_SIZE_VER1 32 /* sizeof second published struct */ /* * @mask bits for statmount(2) @@ -202,10 +205,13 @@ struct mnt_id_req { #define STATMOUNT_MNT_ROOT 0x00000008U /* Want/got mnt_root */ #define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */ #define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ +#define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */ +#define STATMOUNT_MNT_OPTS 0x00000080U /* Want/got mnt_opts */ /* * Special @mnt_id values that can be passed to listmount */ #define LSMT_ROOT 0xffffffffffffffff /* root mount */ +#define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */ #endif /* _UAPI_LINUX_MOUNT_H */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h index 67626d535316..887a25286441 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/stat.h +++ b/tools/perf/trace/beauty/include/uapi/linux/stat.h @@ -126,9 +126,15 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ - __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[11]; /* Spare space for future expansion */ + __u64 stx_subvol; /* Subvolume identifier */ + __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */ + /* 0xb0 */ + __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */ + __u32 __spare1[1]; + /* 0xb8 */ + __u64 __spare3[9]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -157,6 +163,7 @@ struct statx { #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ +#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ @@ -192,6 +199,7 @@ struct statx { #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ +#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */ #endif /* _UAPI_LINUX_STAT_H */ From f6d9883f8e680460be4714d4d35c7acac1dffeaf Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 6 Aug 2024 12:07:50 -0700 Subject: [PATCH 068/562] tools/include: Sync x86 headers with the kernel sources To pick up changes from: 149fd4712bcd perf/x86/intel: Support Perfmon MSRs aliasing 21b362cc762a x86/resctrl: Enable shared RMID mode on Sub-NUMA Cluster (SNC) systems 4f460bff7b6a cpufreq: acpi: move MSR_K7_HWCR_CPB_DIS_BIT into msr-index.h 7ea81936b853 x86/cpufeatures: Add HWP highest perf change feature flag 78ce84b9e0a5 x86/cpufeatures: Flip the /proc/cpuinfo appearance logic 1beb348d5c7f x86/sev: Provide SVSM discovery support This should be used to beautify x86 syscall arguments and it addresses these tools/perf build warnings: Warning: Kernel ABI header differences: diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h Please see tools/include/uapi/README for details (it's in the first patch of this series). Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: x86@kernel.org Signed-off-by: Namhyung Kim --- tools/arch/x86/include/asm/cpufeatures.h | 803 ++++++++++++----------- tools/arch/x86/include/asm/msr-index.h | 11 + 2 files changed, 414 insertions(+), 400 deletions(-) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 3c7434329661..dd4682857c12 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -18,170 +18,170 @@ /* * Note: If the comment begins with a quoted string, that string is used - * in /proc/cpuinfo instead of the macro name. If the string is "", - * this feature bit is not displayed in /proc/cpuinfo at all. + * in /proc/cpuinfo instead of the macro name. Otherwise, this feature + * bit is not displayed in /proc/cpuinfo at all. * * When adding new features here that depend on other features, * please update the table in kernel/cpu/cpuid-deps.c as well. */ /* Intel-defined CPU features, CPUID level 0x00000001 (EDX), word 0 */ -#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */ -#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */ -#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */ -#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */ -#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */ -#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */ -#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */ -#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */ -#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */ -#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */ -#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */ -#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */ -#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */ -#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */ -#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions (plus FCMOVcc, FCOMI with FPU) */ -#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */ -#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */ -#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */ -#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */ +#define X86_FEATURE_FPU ( 0*32+ 0) /* "fpu" Onboard FPU */ +#define X86_FEATURE_VME ( 0*32+ 1) /* "vme" Virtual Mode Extensions */ +#define X86_FEATURE_DE ( 0*32+ 2) /* "de" Debugging Extensions */ +#define X86_FEATURE_PSE ( 0*32+ 3) /* "pse" Page Size Extensions */ +#define X86_FEATURE_TSC ( 0*32+ 4) /* "tsc" Time Stamp Counter */ +#define X86_FEATURE_MSR ( 0*32+ 5) /* "msr" Model-Specific Registers */ +#define X86_FEATURE_PAE ( 0*32+ 6) /* "pae" Physical Address Extensions */ +#define X86_FEATURE_MCE ( 0*32+ 7) /* "mce" Machine Check Exception */ +#define X86_FEATURE_CX8 ( 0*32+ 8) /* "cx8" CMPXCHG8 instruction */ +#define X86_FEATURE_APIC ( 0*32+ 9) /* "apic" Onboard APIC */ +#define X86_FEATURE_SEP ( 0*32+11) /* "sep" SYSENTER/SYSEXIT */ +#define X86_FEATURE_MTRR ( 0*32+12) /* "mtrr" Memory Type Range Registers */ +#define X86_FEATURE_PGE ( 0*32+13) /* "pge" Page Global Enable */ +#define X86_FEATURE_MCA ( 0*32+14) /* "mca" Machine Check Architecture */ +#define X86_FEATURE_CMOV ( 0*32+15) /* "cmov" CMOV instructions (plus FCMOVcc, FCOMI with FPU) */ +#define X86_FEATURE_PAT ( 0*32+16) /* "pat" Page Attribute Table */ +#define X86_FEATURE_PSE36 ( 0*32+17) /* "pse36" 36-bit PSEs */ +#define X86_FEATURE_PN ( 0*32+18) /* "pn" Processor serial number */ +#define X86_FEATURE_CLFLUSH ( 0*32+19) /* "clflush" CLFLUSH instruction */ #define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */ -#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */ -#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */ -#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */ +#define X86_FEATURE_ACPI ( 0*32+22) /* "acpi" ACPI via MSR */ +#define X86_FEATURE_MMX ( 0*32+23) /* "mmx" Multimedia Extensions */ +#define X86_FEATURE_FXSR ( 0*32+24) /* "fxsr" FXSAVE/FXRSTOR, CR4.OSFXSR */ #define X86_FEATURE_XMM ( 0*32+25) /* "sse" */ #define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */ #define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */ -#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */ +#define X86_FEATURE_HT ( 0*32+28) /* "ht" Hyper-Threading */ #define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */ -#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */ -#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */ +#define X86_FEATURE_IA64 ( 0*32+30) /* "ia64" IA-64 processor */ +#define X86_FEATURE_PBE ( 0*32+31) /* "pbe" Pending Break Enable */ /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */ /* Don't duplicate feature flags which are redundant with Intel! */ -#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */ -#define X86_FEATURE_MP ( 1*32+19) /* MP Capable */ -#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */ -#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */ -#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */ +#define X86_FEATURE_SYSCALL ( 1*32+11) /* "syscall" SYSCALL/SYSRET */ +#define X86_FEATURE_MP ( 1*32+19) /* "mp" MP Capable */ +#define X86_FEATURE_NX ( 1*32+20) /* "nx" Execute Disable */ +#define X86_FEATURE_MMXEXT ( 1*32+22) /* "mmxext" AMD MMX extensions */ +#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* "fxsr_opt" FXSAVE/FXRSTOR optimizations */ #define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */ -#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */ -#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64, 64-bit support) */ -#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow extensions */ -#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow */ +#define X86_FEATURE_RDTSCP ( 1*32+27) /* "rdtscp" RDTSCP */ +#define X86_FEATURE_LM ( 1*32+29) /* "lm" Long Mode (x86-64, 64-bit support) */ +#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* "3dnowext" AMD 3DNow extensions */ +#define X86_FEATURE_3DNOW ( 1*32+31) /* "3dnow" 3DNow */ /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */ -#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */ -#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */ -#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */ +#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* "recovery" CPU in recovery mode */ +#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* "longrun" Longrun power control */ +#define X86_FEATURE_LRTI ( 2*32+ 3) /* "lrti" LongRun table interface */ /* Other features, Linux-defined mapping, word 3 */ /* This range is used for feature bits which conflict or are synthesized */ -#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */ -#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ -#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ -#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ -#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* "" CPU based on Zen5 microarchitecture */ -#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ -#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ -#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ -#define X86_FEATURE_UP ( 3*32+ 9) /* SMP kernel running on UP */ -#define X86_FEATURE_ART ( 3*32+10) /* Always running timer (ART) */ -#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */ -#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */ -#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */ -#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ -#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ -#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ -#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */ -#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ -#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ -#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ -#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* CPU topology enum extensions */ -#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ -#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ -#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */ -#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* Extended APICID (8 bits) */ -#define X86_FEATURE_AMD_DCM ( 3*32+27) /* AMD multi-node processor */ -#define X86_FEATURE_APERFMPERF ( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */ -#define X86_FEATURE_RAPL ( 3*32+29) /* AMD/Hygon RAPL interface */ -#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ -#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */ +#define X86_FEATURE_CXMMX ( 3*32+ 0) /* "cxmmx" Cyrix MMX extensions */ +#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* "k6_mtrr" AMD K6 nonstandard MTRRs */ +#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* "cyrix_arr" Cyrix ARRs (= MTRRs) */ +#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */ +#define X86_FEATURE_K8 ( 3*32+ 4) /* Opteron, Athlon64 */ +#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* CPU based on Zen5 microarchitecture */ +#define X86_FEATURE_P3 ( 3*32+ 6) /* P3 */ +#define X86_FEATURE_P4 ( 3*32+ 7) /* P4 */ +#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */ +#define X86_FEATURE_UP ( 3*32+ 9) /* "up" SMP kernel running on UP */ +#define X86_FEATURE_ART ( 3*32+10) /* "art" Always running timer (ART) */ +#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* "arch_perfmon" Intel Architectural PerfMon */ +#define X86_FEATURE_PEBS ( 3*32+12) /* "pebs" Precise-Event Based Sampling */ +#define X86_FEATURE_BTS ( 3*32+13) /* "bts" Branch Trace Store */ +#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* syscall in IA32 userspace */ +#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* sysenter in IA32 userspace */ +#define X86_FEATURE_REP_GOOD ( 3*32+16) /* "rep_good" REP microcode works well */ +#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* "amd_lbr_v2" AMD Last Branch Record Extension Version 2 */ +#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* Clear CPU buffers using VERW */ +#define X86_FEATURE_ACC_POWER ( 3*32+19) /* "acc_power" AMD Accumulated Power Mechanism */ +#define X86_FEATURE_NOPL ( 3*32+20) /* "nopl" The NOPL (0F 1F) instructions */ +#define X86_FEATURE_ALWAYS ( 3*32+21) /* Always-present feature */ +#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* "xtopology" CPU topology enum extensions */ +#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* "tsc_reliable" TSC is known to be reliable */ +#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* "nonstop_tsc" TSC does not stop in C states */ +#define X86_FEATURE_CPUID ( 3*32+25) /* "cpuid" CPU has CPUID instruction itself */ +#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* "extd_apicid" Extended APICID (8 bits) */ +#define X86_FEATURE_AMD_DCM ( 3*32+27) /* "amd_dcm" AMD multi-node processor */ +#define X86_FEATURE_APERFMPERF ( 3*32+28) /* "aperfmperf" P-State hardware coordination feedback capability (APERF/MPERF MSRs) */ +#define X86_FEATURE_RAPL ( 3*32+29) /* "rapl" AMD/Hygon RAPL interface */ +#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* "nonstop_tsc_s3" TSC doesn't stop in S3 state */ +#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* "tsc_known_freq" TSC has known frequency */ /* Intel-defined CPU features, CPUID level 0x00000001 (ECX), word 4 */ #define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ -#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */ -#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */ +#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* "pclmulqdq" PCLMULQDQ instruction */ +#define X86_FEATURE_DTES64 ( 4*32+ 2) /* "dtes64" 64-bit Debug Store */ #define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" MONITOR/MWAIT support */ #define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL-qualified (filtered) Debug Store */ -#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */ -#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer Mode eXtensions */ -#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */ -#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ -#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ -#define X86_FEATURE_CID ( 4*32+10) /* Context ID */ -#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */ -#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ -#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B instruction */ -#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */ -#define X86_FEATURE_PDCM ( 4*32+15) /* Perf/Debug Capabilities MSR */ -#define X86_FEATURE_PCID ( 4*32+17) /* Process Context Identifiers */ -#define X86_FEATURE_DCA ( 4*32+18) /* Direct Cache Access */ +#define X86_FEATURE_VMX ( 4*32+ 5) /* "vmx" Hardware virtualization */ +#define X86_FEATURE_SMX ( 4*32+ 6) /* "smx" Safer Mode eXtensions */ +#define X86_FEATURE_EST ( 4*32+ 7) /* "est" Enhanced SpeedStep */ +#define X86_FEATURE_TM2 ( 4*32+ 8) /* "tm2" Thermal Monitor 2 */ +#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* "ssse3" Supplemental SSE-3 */ +#define X86_FEATURE_CID ( 4*32+10) /* "cid" Context ID */ +#define X86_FEATURE_SDBG ( 4*32+11) /* "sdbg" Silicon Debug */ +#define X86_FEATURE_FMA ( 4*32+12) /* "fma" Fused multiply-add */ +#define X86_FEATURE_CX16 ( 4*32+13) /* "cx16" CMPXCHG16B instruction */ +#define X86_FEATURE_XTPR ( 4*32+14) /* "xtpr" Send Task Priority Messages */ +#define X86_FEATURE_PDCM ( 4*32+15) /* "pdcm" Perf/Debug Capabilities MSR */ +#define X86_FEATURE_PCID ( 4*32+17) /* "pcid" Process Context Identifiers */ +#define X86_FEATURE_DCA ( 4*32+18) /* "dca" Direct Cache Access */ #define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */ #define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */ -#define X86_FEATURE_X2APIC ( 4*32+21) /* X2APIC */ -#define X86_FEATURE_MOVBE ( 4*32+22) /* MOVBE instruction */ -#define X86_FEATURE_POPCNT ( 4*32+23) /* POPCNT instruction */ -#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* TSC deadline timer */ -#define X86_FEATURE_AES ( 4*32+25) /* AES instructions */ -#define X86_FEATURE_XSAVE ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV instructions */ -#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE instruction enabled in the OS */ -#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */ -#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit FP conversions */ -#define X86_FEATURE_RDRAND ( 4*32+30) /* RDRAND instruction */ -#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */ +#define X86_FEATURE_X2APIC ( 4*32+21) /* "x2apic" X2APIC */ +#define X86_FEATURE_MOVBE ( 4*32+22) /* "movbe" MOVBE instruction */ +#define X86_FEATURE_POPCNT ( 4*32+23) /* "popcnt" POPCNT instruction */ +#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* "tsc_deadline_timer" TSC deadline timer */ +#define X86_FEATURE_AES ( 4*32+25) /* "aes" AES instructions */ +#define X86_FEATURE_XSAVE ( 4*32+26) /* "xsave" XSAVE/XRSTOR/XSETBV/XGETBV instructions */ +#define X86_FEATURE_OSXSAVE ( 4*32+27) /* XSAVE instruction enabled in the OS */ +#define X86_FEATURE_AVX ( 4*32+28) /* "avx" Advanced Vector Extensions */ +#define X86_FEATURE_F16C ( 4*32+29) /* "f16c" 16-bit FP conversions */ +#define X86_FEATURE_RDRAND ( 4*32+30) /* "rdrand" RDRAND instruction */ +#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* "hypervisor" Running on a hypervisor */ /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ #define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */ #define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */ #define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ #define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */ -#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */ -#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */ -#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */ -#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */ -#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */ -#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */ +#define X86_FEATURE_ACE2 ( 5*32+ 8) /* "ace2" Advanced Cryptography Engine v2 */ +#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* "ace2_en" ACE v2 enabled */ +#define X86_FEATURE_PHE ( 5*32+10) /* "phe" PadLock Hash Engine */ +#define X86_FEATURE_PHE_EN ( 5*32+11) /* "phe_en" PHE enabled */ +#define X86_FEATURE_PMM ( 5*32+12) /* "pmm" PadLock Montgomery Multiplier */ +#define X86_FEATURE_PMM_EN ( 5*32+13) /* "pmm_en" PMM enabled */ /* More extended AMD flags: CPUID level 0x80000001, ECX, word 6 */ -#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */ -#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */ -#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure Virtual Machine */ -#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */ -#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */ -#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */ -#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */ -#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */ -#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */ -#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */ -#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */ -#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */ -#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */ -#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */ -#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */ -#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */ -#define X86_FEATURE_TCE ( 6*32+17) /* Translation Cache Extension */ -#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */ -#define X86_FEATURE_TBM ( 6*32+21) /* Trailing Bit Manipulations */ -#define X86_FEATURE_TOPOEXT ( 6*32+22) /* Topology extensions CPUID leafs */ -#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* Core performance counter extensions */ -#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ -#define X86_FEATURE_BPEXT ( 6*32+26) /* Data breakpoint extension */ -#define X86_FEATURE_PTSC ( 6*32+27) /* Performance time-stamp counter */ -#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */ -#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX instructions) */ +#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* "lahf_lm" LAHF/SAHF in long mode */ +#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* "cmp_legacy" If yes HyperThreading not valid */ +#define X86_FEATURE_SVM ( 6*32+ 2) /* "svm" Secure Virtual Machine */ +#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* "extapic" Extended APIC space */ +#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* "cr8_legacy" CR8 in 32-bit mode */ +#define X86_FEATURE_ABM ( 6*32+ 5) /* "abm" Advanced bit manipulation */ +#define X86_FEATURE_SSE4A ( 6*32+ 6) /* "sse4a" SSE-4A */ +#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* "misalignsse" Misaligned SSE mode */ +#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* "3dnowprefetch" 3DNow prefetch instructions */ +#define X86_FEATURE_OSVW ( 6*32+ 9) /* "osvw" OS Visible Workaround */ +#define X86_FEATURE_IBS ( 6*32+10) /* "ibs" Instruction Based Sampling */ +#define X86_FEATURE_XOP ( 6*32+11) /* "xop" Extended AVX instructions */ +#define X86_FEATURE_SKINIT ( 6*32+12) /* "skinit" SKINIT/STGI instructions */ +#define X86_FEATURE_WDT ( 6*32+13) /* "wdt" Watchdog timer */ +#define X86_FEATURE_LWP ( 6*32+15) /* "lwp" Light Weight Profiling */ +#define X86_FEATURE_FMA4 ( 6*32+16) /* "fma4" 4 operands MAC instructions */ +#define X86_FEATURE_TCE ( 6*32+17) /* "tce" Translation Cache Extension */ +#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* "nodeid_msr" NodeId MSR */ +#define X86_FEATURE_TBM ( 6*32+21) /* "tbm" Trailing Bit Manipulations */ +#define X86_FEATURE_TOPOEXT ( 6*32+22) /* "topoext" Topology extensions CPUID leafs */ +#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* "perfctr_core" Core performance counter extensions */ +#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* "perfctr_nb" NB performance counter extensions */ +#define X86_FEATURE_BPEXT ( 6*32+26) /* "bpext" Data breakpoint extension */ +#define X86_FEATURE_PTSC ( 6*32+27) /* "ptsc" Performance time-stamp counter */ +#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* "perfctr_llc" Last Level Cache performance counter extensions */ +#define X86_FEATURE_MWAITX ( 6*32+29) /* "mwaitx" MWAIT extension (MONITORX/MWAITX instructions) */ /* * Auxiliary flags: Linux defined - For features scattered in various @@ -189,93 +189,93 @@ * * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT instructions */ -#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */ -#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ -#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ -#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ -#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ -#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ -#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* Platform supports being a TDX host */ -#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ -#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ -#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ -#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */ -#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ -#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ -#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ -#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ -#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ -#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ -#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* AMD Performance Monitoring Version 2 */ -#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ -#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ -#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ -#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation via LS_CFG MSR */ -#define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ -#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ -#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_ZEN ( 7*32+28) /* "" Generic flag for all Zen and newer */ -#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ -#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ -#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */ +#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* "ring3mwait" Ring 3 MONITOR/MWAIT instructions */ +#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* "cpuid_fault" Intel CPUID faulting */ +#define X86_FEATURE_CPB ( 7*32+ 2) /* "cpb" AMD Core Performance Boost */ +#define X86_FEATURE_EPB ( 7*32+ 3) /* "epb" IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* "cat_l3" Cache Allocation Technology L3 */ +#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* "cat_l2" Cache Allocation Technology L2 */ +#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* "cdp_l3" Code and Data Prioritization L3 */ +#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* "tdx_host_platform" Platform supports being a TDX host */ +#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* "hw_pstate" AMD HW-PState */ +#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* "proc_feedback" AMD ProcFeedbackInterface */ +#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* Use compacted XSTATE (XSAVES or XSAVEC) */ +#define X86_FEATURE_PTI ( 7*32+11) /* "pti" Kernel Page Table Isolation enabled */ +#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* Set/clear IBRS on kernel entry/exit */ +#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* Fill RSB on VM-Exit */ +#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* "intel_ppin" Intel Processor Inventory Number */ +#define X86_FEATURE_CDP_L2 ( 7*32+15) /* "cdp_l2" Code and Data Prioritization L2 */ +#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* MSR SPEC_CTRL is implemented */ +#define X86_FEATURE_SSBD ( 7*32+17) /* "ssbd" Speculative Store Bypass Disable */ +#define X86_FEATURE_MBA ( 7*32+18) /* "mba" Memory Bandwidth Allocation */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ +#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* "perfmon_v2" AMD Performance Monitoring Version 2 */ +#define X86_FEATURE_USE_IBPB ( 7*32+21) /* Indirect Branch Prediction Barrier enabled */ +#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* Use IBRS during runtime firmware calls */ +#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* Disable Speculative Store Bypass. */ +#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* AMD SSBD implementation via LS_CFG MSR */ +#define X86_FEATURE_IBRS ( 7*32+25) /* "ibrs" Indirect Branch Restricted Speculation */ +#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier */ +#define X86_FEATURE_STIBP ( 7*32+27) /* "stibp" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ZEN ( 7*32+28) /* Generic flag for all Zen and newer */ +#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* L1TF workaround PTE inversion */ +#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* "ibrs_enhanced" Enhanced IBRS */ +#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* MSR IA32_FEAT_CTL configured */ /* Virtualization flags: Linux defined, word 8 */ -#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 2) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 3) /* Intel Virtual Processor ID */ +#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* "tpr_shadow" Intel TPR Shadow */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */ -#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ -#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ -#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ -#define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ -#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ -#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */ -#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */ -#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* Intel Trust Domain Extensions Guest */ +#define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */ +#define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */ +#define X86_FEATURE_EPT_AD ( 8*32+17) /* "ept_ad" Intel Extended Page Table access-dirty bit */ +#define X86_FEATURE_VMCALL ( 8*32+18) /* Hypervisor supports the VMCALL instruction */ +#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* VMware prefers VMMCALL hypercall instruction */ +#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* PV unlock function */ +#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* PV vcpu_is_preempted function */ +#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* "tdx_guest" Intel Trust Domain Extensions Guest */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ -#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ -#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3B */ -#define X86_FEATURE_SGX ( 9*32+ 2) /* Software Guard Extensions */ -#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ -#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ -#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ -#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* "" FPU data pointer updated only on x87 exceptions */ -#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */ -#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */ -#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */ -#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ -#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ -#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ -#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* "" Zero out FPU CS and FPU DS */ -#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ -#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */ -#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ -#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */ -#define X86_FEATURE_RDSEED ( 9*32+18) /* RDSEED instruction */ -#define X86_FEATURE_ADX ( 9*32+19) /* ADCX and ADOX instructions */ -#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ -#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ -#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ -#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ -#define X86_FEATURE_INTEL_PT ( 9*32+25) /* Intel Processor Trace */ -#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ -#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ -#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ -#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ -#define X86_FEATURE_AVX512BW ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */ -#define X86_FEATURE_AVX512VL ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */ +#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* "fsgsbase" RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ +#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* "tsc_adjust" TSC adjustment MSR 0x3B */ +#define X86_FEATURE_SGX ( 9*32+ 2) /* "sgx" Software Guard Extensions */ +#define X86_FEATURE_BMI1 ( 9*32+ 3) /* "bmi1" 1st group bit manipulation extensions */ +#define X86_FEATURE_HLE ( 9*32+ 4) /* "hle" Hardware Lock Elision */ +#define X86_FEATURE_AVX2 ( 9*32+ 5) /* "avx2" AVX2 instructions */ +#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* FPU data pointer updated only on x87 exceptions */ +#define X86_FEATURE_SMEP ( 9*32+ 7) /* "smep" Supervisor Mode Execution Protection */ +#define X86_FEATURE_BMI2 ( 9*32+ 8) /* "bmi2" 2nd group bit manipulation extensions */ +#define X86_FEATURE_ERMS ( 9*32+ 9) /* "erms" Enhanced REP MOVSB/STOSB instructions */ +#define X86_FEATURE_INVPCID ( 9*32+10) /* "invpcid" Invalidate Processor Context ID */ +#define X86_FEATURE_RTM ( 9*32+11) /* "rtm" Restricted Transactional Memory */ +#define X86_FEATURE_CQM ( 9*32+12) /* "cqm" Cache QoS Monitoring */ +#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* Zero out FPU CS and FPU DS */ +#define X86_FEATURE_MPX ( 9*32+14) /* "mpx" Memory Protection Extension */ +#define X86_FEATURE_RDT_A ( 9*32+15) /* "rdt_a" Resource Director Technology Allocation */ +#define X86_FEATURE_AVX512F ( 9*32+16) /* "avx512f" AVX-512 Foundation */ +#define X86_FEATURE_AVX512DQ ( 9*32+17) /* "avx512dq" AVX-512 DQ (Double/Quad granular) Instructions */ +#define X86_FEATURE_RDSEED ( 9*32+18) /* "rdseed" RDSEED instruction */ +#define X86_FEATURE_ADX ( 9*32+19) /* "adx" ADCX and ADOX instructions */ +#define X86_FEATURE_SMAP ( 9*32+20) /* "smap" Supervisor Mode Access Prevention */ +#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* "avx512ifma" AVX-512 Integer Fused Multiply-Add instructions */ +#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* "clflushopt" CLFLUSHOPT instruction */ +#define X86_FEATURE_CLWB ( 9*32+24) /* "clwb" CLWB instruction */ +#define X86_FEATURE_INTEL_PT ( 9*32+25) /* "intel_pt" Intel Processor Trace */ +#define X86_FEATURE_AVX512PF ( 9*32+26) /* "avx512pf" AVX-512 Prefetch */ +#define X86_FEATURE_AVX512ER ( 9*32+27) /* "avx512er" AVX-512 Exponential and Reciprocal */ +#define X86_FEATURE_AVX512CD ( 9*32+28) /* "avx512cd" AVX-512 Conflict Detection */ +#define X86_FEATURE_SHA_NI ( 9*32+29) /* "sha_ni" SHA1/SHA256 Instruction Extensions */ +#define X86_FEATURE_AVX512BW ( 9*32+30) /* "avx512bw" AVX-512 BW (Byte/Word granular) Instructions */ +#define X86_FEATURE_AVX512VL ( 9*32+31) /* "avx512vl" AVX-512 VL (128/256 Vector Length) Extensions */ /* Extended state features, CPUID level 0x0000000d:1 (EAX), word 10 */ -#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT instruction */ -#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC instruction */ -#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */ -#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */ -#define X86_FEATURE_XFD (10*32+ 4) /* "" eXtended Feature Disabling */ +#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* "xsaveopt" XSAVEOPT instruction */ +#define X86_FEATURE_XSAVEC (10*32+ 1) /* "xsavec" XSAVEC instruction */ +#define X86_FEATURE_XGETBV1 (10*32+ 2) /* "xgetbv1" XGETBV with ECX = 1 instruction */ +#define X86_FEATURE_XSAVES (10*32+ 3) /* "xsaves" XSAVES/XRSTORS instructions */ +#define X86_FEATURE_XFD (10*32+ 4) /* eXtended Feature Disabling */ /* * Extended auxiliary flags: Linux defined - for features scattered in various @@ -283,181 +283,183 @@ * * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_CQM_LLC (11*32+ 0) /* LLC QoS if 1 */ -#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */ -#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */ -#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ -#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ -#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ -#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ -#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ -#define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */ -#define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */ -#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* "" Issue an IBPB on kernel entry */ -#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* "" RET prediction control */ -#define X86_FEATURE_RETPOLINE (11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */ -#define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */ -#define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ -#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ -#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ -#define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* "" SGX EDECCSSA user leaf function */ -#define X86_FEATURE_CALL_DEPTH (11*32+19) /* "" Call depth tracking for RSB stuffing */ -#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ -#define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ -#define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ -#define X86_FEATURE_USER_SHSTK (11*32+23) /* Shadow stack support for user mode applications */ -#define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ -#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ -#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */ -#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */ -#define X86_FEATURE_ZEN2 (11*32+28) /* "" CPU based on Zen2 microarchitecture */ -#define X86_FEATURE_ZEN3 (11*32+29) /* "" CPU based on Zen3 microarchitecture */ -#define X86_FEATURE_ZEN4 (11*32+30) /* "" CPU based on Zen4 microarchitecture */ -#define X86_FEATURE_ZEN1 (11*32+31) /* "" CPU based on Zen1 microarchitecture */ +#define X86_FEATURE_CQM_LLC (11*32+ 0) /* "cqm_llc" LLC QoS if 1 */ +#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* "cqm_occup_llc" LLC occupancy monitoring */ +#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* "cqm_mbm_total" LLC Total MBM monitoring */ +#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* "cqm_mbm_local" LLC Local MBM monitoring */ +#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* LFENCE in user entry SWAPGS path */ +#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* LFENCE in kernel entry SWAPGS path */ +#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* "split_lock_detect" #AC for split lock */ +#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* Per-thread Memory Bandwidth Allocation */ +#define X86_FEATURE_SGX1 (11*32+ 8) /* Basic SGX */ +#define X86_FEATURE_SGX2 (11*32+ 9) /* SGX Enclave Dynamic Memory Management (EDMM) */ +#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* Issue an IBPB on kernel entry */ +#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* RET prediction control */ +#define X86_FEATURE_RETPOLINE (11*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_RETHUNK (11*32+14) /* Use REturn THUNK */ +#define X86_FEATURE_UNRET (11*32+15) /* AMD BTB untrain return */ +#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* Use IBPB during runtime firmware calls */ +#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* Fill RSB on VM exit when EIBRS is enabled */ +#define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* SGX EDECCSSA user leaf function */ +#define X86_FEATURE_CALL_DEPTH (11*32+19) /* Call depth tracking for RSB stuffing */ +#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SMBA (11*32+21) /* Slow Memory Bandwidth Allocation */ +#define X86_FEATURE_BMEC (11*32+22) /* Bandwidth Monitoring Event Configuration */ +#define X86_FEATURE_USER_SHSTK (11*32+23) /* "user_shstk" Shadow stack support for user mode applications */ +#define X86_FEATURE_SRSO (11*32+24) /* AMD BTB untrain RETs */ +#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* AMD BTB untrain RETs through aliasing */ +#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* Issue an IBPB only on VMEXIT */ +#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* IA32_TSC_DEADLINE and X2APIC MSRs need fencing */ +#define X86_FEATURE_ZEN2 (11*32+28) /* CPU based on Zen2 microarchitecture */ +#define X86_FEATURE_ZEN3 (11*32+29) /* CPU based on Zen3 microarchitecture */ +#define X86_FEATURE_ZEN4 (11*32+30) /* CPU based on Zen4 microarchitecture */ +#define X86_FEATURE_ZEN1 (11*32+31) /* CPU based on Zen1 microarchitecture */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ -#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ -#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ -#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ -#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* "" Intel Architectural PerfMon Extension */ -#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ -#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ -#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ -#define X86_FEATURE_FRED (12*32+17) /* Flexible Return and Event Delivery */ -#define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ -#define X86_FEATURE_WRMSRNS (12*32+19) /* "" Non-serializing WRMSR */ -#define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ -#define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ -#define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ +#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* "avx_vnni" AVX VNNI instructions */ +#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* "avx512_bf16" AVX512 BFLOAT16 instructions */ +#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* CMPccXADD instructions */ +#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* Intel Architectural PerfMon Extension */ +#define X86_FEATURE_FZRM (12*32+10) /* Fast zero-length REP MOVSB */ +#define X86_FEATURE_FSRS (12*32+11) /* Fast short REP STOSB */ +#define X86_FEATURE_FSRC (12*32+12) /* Fast short REP {CMPSB,SCASB} */ +#define X86_FEATURE_FRED (12*32+17) /* "fred" Flexible Return and Event Delivery */ +#define X86_FEATURE_LKGS (12*32+18) /* Load "kernel" (userspace) GS */ +#define X86_FEATURE_WRMSRNS (12*32+19) /* Non-serializing WRMSR */ +#define X86_FEATURE_AMX_FP16 (12*32+21) /* AMX fp16 Support */ +#define X86_FEATURE_AVX_IFMA (12*32+23) /* Support for VPMADD52[H,L]UQ */ +#define X86_FEATURE_LAM (12*32+26) /* "lam" Linear Address Masking */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ -#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ -#define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ -#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ -#define X86_FEATURE_RDPRU (13*32+ 4) /* Read processor register at user level */ -#define X86_FEATURE_WBNOINVD (13*32+ 9) /* WBNOINVD instruction */ -#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */ -#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ -#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */ -#define X86_FEATURE_AMD_PPIN (13*32+23) /* Protected Processor Inventory Number */ -#define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ -#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ -#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ -#define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ -#define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */ -#define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ -#define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ +#define X86_FEATURE_CLZERO (13*32+ 0) /* "clzero" CLZERO instruction */ +#define X86_FEATURE_IRPERF (13*32+ 1) /* "irperf" Instructions Retired Count */ +#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* "xsaveerptr" Always save/restore FP error pointers */ +#define X86_FEATURE_RDPRU (13*32+ 4) /* "rdpru" Read processor register at user level */ +#define X86_FEATURE_WBNOINVD (13*32+ 9) /* "wbnoinvd" WBNOINVD instruction */ +#define X86_FEATURE_AMD_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_AMD_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */ +#define X86_FEATURE_AMD_PPIN (13*32+23) /* "amd_ppin" Protected Processor Inventory Number */ +#define X86_FEATURE_AMD_SSBD (13*32+24) /* Speculative Store Bypass Disable */ +#define X86_FEATURE_VIRT_SSBD (13*32+25) /* "virt_ssbd" Virtualized Speculative Store Bypass Disable */ +#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* Speculative Store Bypass is fixed in hardware. */ +#define X86_FEATURE_CPPC (13*32+27) /* "cppc" Collaborative Processor Performance Control */ +#define X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */ +#define X86_FEATURE_BTC_NO (13*32+29) /* Not vulnerable to Branch Type Confusion */ +#define X86_FEATURE_BRS (13*32+31) /* "brs" Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ -#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ -#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ -#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ -#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ -#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ -#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ -#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ -#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ -#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ -#define X86_FEATURE_HFI (14*32+19) /* Hardware Feedback Interface */ +#define X86_FEATURE_DTHERM (14*32+ 0) /* "dtherm" Digital Thermal Sensor */ +#define X86_FEATURE_IDA (14*32+ 1) /* "ida" Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (14*32+ 2) /* "arat" Always Running APIC Timer */ +#define X86_FEATURE_PLN (14*32+ 4) /* "pln" Intel Power Limit Notification */ +#define X86_FEATURE_PTS (14*32+ 6) /* "pts" Intel Package Thermal Status */ +#define X86_FEATURE_HWP (14*32+ 7) /* "hwp" Intel Hardware P-states */ +#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* "hwp_notify" HWP Notification */ +#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* "hwp_act_window" HWP Activity Window */ +#define X86_FEATURE_HWP_EPP (14*32+10) /* "hwp_epp" HWP Energy Perf. Preference */ +#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* "hwp_pkg_req" HWP Package Level Request */ +#define X86_FEATURE_HWP_HIGHEST_PERF_CHANGE (14*32+15) /* HWP Highest perf change */ +#define X86_FEATURE_HFI (14*32+19) /* "hfi" Hardware Feedback Interface */ /* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */ -#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ -#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ +#define X86_FEATURE_NPT (15*32+ 0) /* "npt" Nested Page Table support */ +#define X86_FEATURE_LBRV (15*32+ 1) /* "lbrv" LBR Virtualization support */ #define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ #define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ #define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ #define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ -#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ -#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ -#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ -#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ -#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ -#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ -#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ -#define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */ -#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ -#define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */ -#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ +#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* "flushbyasid" Flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* "decodeassists" Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (15*32+10) /* "pausefilter" Filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* "pfthreshold" Pause filter threshold */ +#define X86_FEATURE_AVIC (15*32+13) /* "avic" Virtual Interrupt Controller */ +#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* "v_vmsave_vmload" Virtual VMSAVE VMLOAD */ +#define X86_FEATURE_VGIF (15*32+16) /* "vgif" Virtual GIF */ +#define X86_FEATURE_X2AVIC (15*32+18) /* "x2avic" Virtual x2apic */ +#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */ +#define X86_FEATURE_VNMI (15*32+25) /* "vnmi" Virtual NMI */ +#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ -#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ -#define X86_FEATURE_UMIP (16*32+ 2) /* User Mode Instruction Protection */ -#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ -#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ -#define X86_FEATURE_WAITPKG (16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */ -#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */ -#define X86_FEATURE_SHSTK (16*32+ 7) /* "" Shadow stack */ -#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */ -#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */ -#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* Carry-Less Multiplication Double Quadword */ -#define X86_FEATURE_AVX512_VNNI (16*32+11) /* Vector Neural Network Instructions */ -#define X86_FEATURE_AVX512_BITALG (16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */ -#define X86_FEATURE_TME (16*32+13) /* Intel Total Memory Encryption */ -#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ -#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ -#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ -#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* Bus Lock detect */ -#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */ -#define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */ -#define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */ -#define X86_FEATURE_ENQCMD (16*32+29) /* ENQCMD and ENQCMDS instructions */ -#define X86_FEATURE_SGX_LC (16*32+30) /* Software Guard Extensions Launch Control */ +#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* "avx512vbmi" AVX512 Vector Bit Manipulation instructions*/ +#define X86_FEATURE_UMIP (16*32+ 2) /* "umip" User Mode Instruction Protection */ +#define X86_FEATURE_PKU (16*32+ 3) /* "pku" Protection Keys for Userspace */ +#define X86_FEATURE_OSPKE (16*32+ 4) /* "ospke" OS Protection Keys Enable */ +#define X86_FEATURE_WAITPKG (16*32+ 5) /* "waitpkg" UMONITOR/UMWAIT/TPAUSE Instructions */ +#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* "avx512_vbmi2" Additional AVX512 Vector Bit Manipulation Instructions */ +#define X86_FEATURE_SHSTK (16*32+ 7) /* Shadow stack */ +#define X86_FEATURE_GFNI (16*32+ 8) /* "gfni" Galois Field New Instructions */ +#define X86_FEATURE_VAES (16*32+ 9) /* "vaes" Vector AES */ +#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* "vpclmulqdq" Carry-Less Multiplication Double Quadword */ +#define X86_FEATURE_AVX512_VNNI (16*32+11) /* "avx512_vnni" Vector Neural Network Instructions */ +#define X86_FEATURE_AVX512_BITALG (16*32+12) /* "avx512_bitalg" Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */ +#define X86_FEATURE_TME (16*32+13) /* "tme" Intel Total Memory Encryption */ +#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* "avx512_vpopcntdq" POPCNT for vectors of DW/QW */ +#define X86_FEATURE_LA57 (16*32+16) /* "la57" 5-level page tables */ +#define X86_FEATURE_RDPID (16*32+22) /* "rdpid" RDPID instruction */ +#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* "bus_lock_detect" Bus Lock detect */ +#define X86_FEATURE_CLDEMOTE (16*32+25) /* "cldemote" CLDEMOTE instruction */ +#define X86_FEATURE_MOVDIRI (16*32+27) /* "movdiri" MOVDIRI instruction */ +#define X86_FEATURE_MOVDIR64B (16*32+28) /* "movdir64b" MOVDIR64B instruction */ +#define X86_FEATURE_ENQCMD (16*32+29) /* "enqcmd" ENQCMD and ENQCMDS instructions */ +#define X86_FEATURE_SGX_LC (16*32+30) /* "sgx_lc" Software Guard Extensions Launch Control */ /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */ -#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */ -#define X86_FEATURE_SUCCOR (17*32+ 1) /* Uncorrectable error containment and recovery */ -#define X86_FEATURE_SMCA (17*32+ 3) /* Scalable MCA */ +#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* "overflow_recov" MCA overflow recovery support */ +#define X86_FEATURE_SUCCOR (17*32+ 1) /* "succor" Uncorrectable error containment and recovery */ +#define X86_FEATURE_SMCA (17*32+ 3) /* "smca" Scalable MCA */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ -#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ -#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ -#define X86_FEATURE_FSRM (18*32+ 4) /* Fast Short Rep Mov */ -#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */ -#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* "" SRBDS mitigation MSR available */ -#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ -#define X86_FEATURE_RTM_ALWAYS_ABORT (18*32+11) /* "" RTM transaction always aborts */ -#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ -#define X86_FEATURE_SERIALIZE (18*32+14) /* SERIALIZE instruction */ -#define X86_FEATURE_HYBRID_CPU (18*32+15) /* "" This part has CPUs of more than one type */ -#define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ -#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ -#define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ -#define X86_FEATURE_IBT (18*32+20) /* Indirect Branch Tracking */ -#define X86_FEATURE_AMX_BF16 (18*32+22) /* AMX bf16 Support */ -#define X86_FEATURE_AVX512_FP16 (18*32+23) /* AVX512 FP16 */ -#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */ -#define X86_FEATURE_AMX_INT8 (18*32+25) /* AMX int8 Support */ -#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ -#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */ -#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ -#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */ -#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ +#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* "avx512_4vnniw" AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* "avx512_4fmaps" AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_FSRM (18*32+ 4) /* "fsrm" Fast Short Rep Mov */ +#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* "avx512_vp2intersect" AVX-512 Intersect for D/Q */ +#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* SRBDS mitigation MSR available */ +#define X86_FEATURE_MD_CLEAR (18*32+10) /* "md_clear" VERW clears CPU buffers */ +#define X86_FEATURE_RTM_ALWAYS_ABORT (18*32+11) /* RTM transaction always aborts */ +#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* TSX_FORCE_ABORT */ +#define X86_FEATURE_SERIALIZE (18*32+14) /* "serialize" SERIALIZE instruction */ +#define X86_FEATURE_HYBRID_CPU (18*32+15) /* This part has CPUs of more than one type */ +#define X86_FEATURE_TSXLDTRK (18*32+16) /* "tsxldtrk" TSX Suspend Load Address Tracking */ +#define X86_FEATURE_PCONFIG (18*32+18) /* "pconfig" Intel PCONFIG */ +#define X86_FEATURE_ARCH_LBR (18*32+19) /* "arch_lbr" Intel ARCH LBR */ +#define X86_FEATURE_IBT (18*32+20) /* "ibt" Indirect Branch Tracking */ +#define X86_FEATURE_AMX_BF16 (18*32+22) /* "amx_bf16" AMX bf16 Support */ +#define X86_FEATURE_AVX512_FP16 (18*32+23) /* "avx512_fp16" AVX512 FP16 */ +#define X86_FEATURE_AMX_TILE (18*32+24) /* "amx_tile" AMX tile Support */ +#define X86_FEATURE_AMX_INT8 (18*32+25) /* "amx_int8" AMX int8 Support */ +#define X86_FEATURE_SPEC_CTRL (18*32+26) /* Speculation Control (IBRS + IBPB) */ +#define X86_FEATURE_INTEL_STIBP (18*32+27) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_FLUSH_L1D (18*32+28) /* "flush_l1d" Flush L1D cache */ +#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* "arch_capabilities" IA32_ARCH_CAPABILITIES MSR (Intel) */ +#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* IA32_CORE_CAPABILITIES MSR */ +#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* Speculative Store Bypass Disable */ /* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */ -#define X86_FEATURE_SME (19*32+ 0) /* AMD Secure Memory Encryption */ -#define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */ -#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */ -#define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ -#define X86_FEATURE_SEV_SNP (19*32+ 4) /* AMD Secure Encrypted Virtualization - Secure Nested Paging */ -#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ -#define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ -#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* AMD SEV-ES full debug state swap support */ +#define X86_FEATURE_SME (19*32+ 0) /* "sme" AMD Secure Memory Encryption */ +#define X86_FEATURE_SEV (19*32+ 1) /* "sev" AMD Secure Encrypted Virtualization */ +#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* VM Page Flush MSR is supported */ +#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" AMD Secure Encrypted Virtualization - Secure Nested Paging */ +#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* Virtual TSC_AUX */ +#define X86_FEATURE_SME_COHERENT (19*32+10) /* AMD hardware-enforced cache coherency */ +#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */ +#define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */ /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ -#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ -#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* "" WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */ -#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */ -#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */ -#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ -#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */ +#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */ +#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */ +#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* Null Selector Clears Base */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* Automatic IBRS */ +#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */ -#define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */ -#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ -#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ +#define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */ +#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */ +#define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */ /* * Extended auxiliary flags: Linux defined - for features scattered in various @@ -465,59 +467,60 @@ * * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */ -#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */ -#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ -#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ -#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */ +#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* "amd_lbr_pmc_freeze" AMD LBR and PMC Freeze */ +#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* Clear branch history at syscall entry using SW loop */ +#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* BHI_DIS_S HW control available */ +#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* BHI_DIS_S HW control enabled */ +#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */ +#define X86_FEATURE_FAST_CPPC (21*32 + 5) /* AMD Fast CPPC */ /* * BUG word(s) */ #define X86_BUG(x) (NCAPINTS*32 + (x)) -#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */ -#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */ -#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */ +#define X86_BUG_F00F X86_BUG(0) /* "f00f" Intel F00F */ +#define X86_BUG_FDIV X86_BUG(1) /* "fdiv" FPU FDIV */ +#define X86_BUG_COMA X86_BUG(2) /* "coma" Cyrix 6x86 coma */ #define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */ #define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */ -#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */ -#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ -#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ -#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ +#define X86_BUG_11AP X86_BUG(5) /* "11ap" Bad local APIC aka 11AP */ +#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* "fxsave_leak" FXSAVE leaks FOP/FIP/FOP */ +#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* "clflush_monitor" AAI65, CLFLUSH required before MONITOR */ +#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* "sysret_ss_attrs" SYSRET doesn't fix up SS attrs */ #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional * to avoid confusion. */ -#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ +#define X86_BUG_ESPFIX X86_BUG(9) /* IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif -#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ -#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ -#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ -#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */ -#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ -#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ -#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */ -#define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ -#define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ -#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ -#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ -#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ -#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ -#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ -#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ -#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ -#define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ -#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ -#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ -#define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */ -#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */ +#define X86_BUG_NULL_SEG X86_BUG(10) /* "null_seg" Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* "swapgs_fence" SWAPGS without input dep on GS */ +#define X86_BUG_MONITOR X86_BUG(12) /* "monitor" IPI required to wake up remote CPU */ +#define X86_BUG_AMD_E400 X86_BUG(13) /* "amd_e400" CPU is among the affected by Erratum 400 */ +#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* "cpu_meltdown" CPU is affected by meltdown attack and needs kernel page table isolation */ +#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* "spectre_v1" CPU is affected by Spectre variant 1 attack with conditional branches */ +#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* "spectre_v2" CPU is affected by Spectre variant 2 attack with indirect branches */ +#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* "spec_store_bypass" CPU is affected by speculative store bypass attack */ +#define X86_BUG_L1TF X86_BUG(18) /* "l1tf" CPU is affected by L1 Terminal Fault */ +#define X86_BUG_MDS X86_BUG(19) /* "mds" CPU is affected by Microarchitectural data sampling */ +#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* "msbds_only" CPU is only affected by the MSDBS variant of BUG_MDS */ +#define X86_BUG_SWAPGS X86_BUG(21) /* "swapgs" CPU is affected by speculation through SWAPGS */ +#define X86_BUG_TAA X86_BUG(22) /* "taa" CPU is affected by TSX Async Abort(TAA) */ +#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* "itlb_multihit" CPU may incur MCE during certain page attribute changes */ +#define X86_BUG_SRBDS X86_BUG(24) /* "srbds" CPU may leak RNG bits if not mitigated */ +#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* "mmio_stale_data" CPU is affected by Processor MMIO Stale Data vulnerabilities */ +#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */ +#define X86_BUG_RETBLEED X86_BUG(27) /* "retbleed" CPU is affected by RETBleed */ +#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* "eibrs_pbrsb" EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_SMT_RSB X86_BUG(29) /* "smt_rsb" CPU is vulnerable to Cross-Thread Return Address Predictions */ +#define X86_BUG_GDS X86_BUG(30) /* "gds" CPU is affected by Gather Data Sampling */ +#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* "tdx_pw_mce" CPU may incur #MC if non-TD software does partial write to TDX private memory */ /* BUG word 2 */ -#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ -#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ -#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ -#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ +#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* "srso" AMD SRSO bug */ +#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */ +#define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index e022e6eb766c..82c6a4d350e0 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -566,6 +566,12 @@ #define MSR_RELOAD_PMC0 0x000014c1 #define MSR_RELOAD_FIXED_CTR0 0x00001309 +/* V6 PMON MSR range */ +#define MSR_IA32_PMC_V6_GP0_CTR 0x1900 +#define MSR_IA32_PMC_V6_GP0_CFG_A 0x1901 +#define MSR_IA32_PMC_V6_FX0_CTR 0x1980 +#define MSR_IA32_PMC_V6_STEP 4 + /* KeyID partitioning between MKTME and TDX */ #define MSR_IA32_MKTME_KEYID_PARTITIONING 0x00000087 @@ -660,6 +666,8 @@ #define MSR_AMD64_RMP_BASE 0xc0010132 #define MSR_AMD64_RMP_END 0xc0010133 +#define MSR_SVSM_CAA 0xc001f000 + /* AMD Collaborative Processor Performance Control MSRs */ #define MSR_AMD_CPPC_CAP1 0xc00102b0 #define MSR_AMD_CPPC_ENABLE 0xc00102b1 @@ -781,6 +789,8 @@ #define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT) #define MSR_K7_FID_VID_CTL 0xc0010041 #define MSR_K7_FID_VID_STATUS 0xc0010042 +#define MSR_K7_HWCR_CPB_DIS_BIT 25 +#define MSR_K7_HWCR_CPB_DIS BIT_ULL(MSR_K7_HWCR_CPB_DIS_BIT) /* K6 MSRs */ #define MSR_K6_WHCR 0xc0000082 @@ -1164,6 +1174,7 @@ #define MSR_IA32_QM_CTR 0xc8e #define MSR_IA32_PQR_ASSOC 0xc8f #define MSR_IA32_L3_CBM_BASE 0xc90 +#define MSR_RMID_SNC_CONFIG 0xca0 #define MSR_IA32_L2_CBM_BASE 0xd10 #define MSR_IA32_MBA_THRTL_BASE 0xd50 From d5b854893d27b4030943a10cf28a07189aab0c36 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 6 Aug 2024 12:07:50 -0700 Subject: [PATCH 069/562] tools/include: Sync arm64 headers with the kernel sources To pick up changes from: 9ef54a384526 arm64: cputype: Add Cortex-A725 definitions 58d245e03c32 arm64: cputype: Add Cortex-X1C definitions fd2ff5f0b320 arm64: cputype: Add Cortex-X925 definitions add332c40328 arm64: cputype: Add Cortex-A720 definitions be5a6f238700 arm64: cputype: Add Cortex-X3 definitions This should be used to beautify x86 syscall arguments and it addresses these tools/perf build warnings: Warning: Kernel ABI header differences: diff -u tools/arch/arm64/include/asm/cputype.h arch/arm64/include/asm/cputype.h Please see tools/include/uapi/README for details (it's in the first patch of this series). Cc: Catalin Marinas Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Namhyung Kim --- tools/arch/arm64/include/asm/cputype.h | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 7b32b99023a2..5fd7caea4419 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -86,9 +86,14 @@ #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B +#define ARM_CPU_PART_CORTEX_X1C 0xD4C +#define ARM_CPU_PART_CORTEX_X3 0xD4E #define ARM_CPU_PART_NEOVERSE_V2 0xD4F +#define ARM_CPU_PART_CORTEX_A720 0xD81 #define ARM_CPU_PART_CORTEX_X4 0xD82 #define ARM_CPU_PART_NEOVERSE_V3 0xD84 +#define ARM_CPU_PART_CORTEX_X925 0xD85 +#define ARM_CPU_PART_CORTEX_A725 0xD87 #define APM_CPU_PART_XGENE 0x000 #define APM_CPU_VAR_POTENZA 0x00 @@ -162,9 +167,14 @@ #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) +#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C) +#define MIDR_CORTEX_X3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X3) #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) +#define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720) #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) +#define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925) +#define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) From 10f2ad032defe906240d0c3b62dcbceace96b230 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 7 Aug 2024 12:51:44 +0100 Subject: [PATCH 070/562] KVM: arm64: Enforce dependency on an ARMv8.4-aware toolchain With the NV support of TLBI-range operations, KVM makes use of instructions that are only supported by binutils versions >= 2.30. This breaks the build for very old toolchains. Make KVM support conditional on having ARMv8.4 support in the assembler, side-stepping the issue. Fixes: 5d476ca57d7d ("KVM: arm64: nv: Add handling of range-based TLBI operations") Reported-by: Viresh Kumar Suggested-by: Arnd Bergmann Signed-off-by: Marc Zyngier Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20240807115144.3237260-1-maz@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/kvm/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 58f09370d17e..8304eb342be9 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -19,6 +19,7 @@ if VIRTUALIZATION menuconfig KVM bool "Kernel-based Virtual Machine (KVM) support" + depends on AS_HAS_ARMV8_4 select KVM_COMMON select KVM_GENERIC_HARDWARE_ENABLING select KVM_GENERIC_MMU_NOTIFIER From 01ab08cafeced7ae1d6c01a08218742c8182f8da Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Wed, 7 Aug 2024 13:20:24 +0800 Subject: [PATCH 071/562] KVM: arm64: vgic-debug: Exit the iterator properly w/o LPI In case the guest doesn't have any LPI, we previously relied on the iterator setting 'intid = nr_spis + VGIC_NR_PRIVATE_IRQS' && 'lpi_idx = 1' to exit the iterator. But it was broken with commit 85d3ccc8b75b ("KVM: arm64: vgic-debug: Use an xarray mark for debug iterator") -- the intid remains at 'nr_spis + VGIC_NR_PRIVATE_IRQS - 1', and we end up endlessly printing the last SPI's state. Consider that it's meaningless to search the LPI xarray and populate lpi_idx when there is no LPI, let's just skip the process for that case. The result is that * If there's no LPI, we focus on the intid and exit the iterator when it runs out of the valid SPI range. * Otherwise we keep the current logic and let the xarray drive the iterator. Fixes: 85d3ccc8b75b ("KVM: arm64: vgic-debug: Use an xarray mark for debug iterator") Signed-off-by: Zenghui Yu Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20240807052024.2084-1-yuzenghui@huawei.com Signed-off-by: Oliver Upton --- arch/arm64/kvm/vgic/vgic-debug.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c index bcbc8c986b1d..bc74d06398ef 100644 --- a/arch/arm64/kvm/vgic/vgic-debug.c +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -45,7 +45,8 @@ static void iter_next(struct kvm *kvm, struct vgic_state_iter *iter) * Let the xarray drive the iterator after the last SPI, as the iterator * has exhausted the sequentially-allocated INTID space. */ - if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS - 1)) { + if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS - 1) && + iter->nr_lpis) { if (iter->lpi_idx < iter->nr_lpis) xa_find_after(&dist->lpi_xa, &iter->intid, VGIC_LPI_MAX_INTID, @@ -112,7 +113,7 @@ static bool end_of_vgic(struct vgic_state_iter *iter) return iter->dist_id > 0 && iter->vcpu_id == iter->nr_cpus && iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS) && - iter->lpi_idx > iter->nr_lpis; + (!iter->nr_lpis || iter->lpi_idx > iter->nr_lpis); } static void *vgic_debug_start(struct seq_file *s, loff_t *pos) From 7e814a20f6da2bd2044b1a4682dd92a6f0df5a92 Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Mon, 22 Jul 2024 17:33:11 +0100 Subject: [PATCH 072/562] KVM: arm64: Tidying up PAuth code in KVM Tidy up some of the PAuth trapping code to clear up some comments and avoid clang/checkpatch warnings. Also, don't bother setting PAuth HCR_EL2 bits in pKVM, since it's handled by the hypervisor. Signed-off-by: Fuad Tabba Link: https://lore.kernel.org/r/20240722163311.1493879-1-tabba@google.com Signed-off-by: Oliver Upton --- arch/arm64/include/asm/kvm_ptrauth.h | 2 +- arch/arm64/kvm/arm.c | 14 ++++---------- arch/arm64/kvm/hyp/include/hyp/switch.h | 1 - arch/arm64/kvm/hyp/nvhe/switch.c | 5 ++--- 4 files changed, 7 insertions(+), 15 deletions(-) diff --git a/arch/arm64/include/asm/kvm_ptrauth.h b/arch/arm64/include/asm/kvm_ptrauth.h index d81bac256abc..6199c9f7ec6e 100644 --- a/arch/arm64/include/asm/kvm_ptrauth.h +++ b/arch/arm64/include/asm/kvm_ptrauth.h @@ -104,7 +104,7 @@ alternative_else_nop_endif #define __ptrauth_save_key(ctxt, key) \ do { \ - u64 __val; \ + u64 __val; \ __val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1); \ ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val; \ __val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1); \ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 23e1fa56c02d..9bef7638342e 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -522,10 +522,10 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) static void vcpu_set_pauth_traps(struct kvm_vcpu *vcpu) { - if (vcpu_has_ptrauth(vcpu)) { + if (vcpu_has_ptrauth(vcpu) && !is_protected_kvm_enabled()) { /* - * Either we're running running an L2 guest, and the API/APK - * bits come from L1's HCR_EL2, or API/APK are both set. + * Either we're running an L2 guest, and the API/APK bits come + * from L1's HCR_EL2, or API/APK are both set. */ if (unlikely(vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))) { u64 val; @@ -542,16 +542,10 @@ static void vcpu_set_pauth_traps(struct kvm_vcpu *vcpu) * Save the host keys if there is any chance for the guest * to use pauth, as the entry code will reload the guest * keys in that case. - * Protected mode is the exception to that rule, as the - * entry into the EL2 code eagerly switch back and forth - * between host and hyp keys (and kvm_hyp_ctxt is out of - * reach anyway). */ - if (is_protected_kvm_enabled()) - return; - if (vcpu->arch.hcr_el2 & (HCR_API | HCR_APK)) { struct kvm_cpu_context *ctxt; + ctxt = this_cpu_ptr_hyp_sym(kvm_hyp_ctxt); ptrauth_save_keys(ctxt); } diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index f59ccfe11ab9..37ff87d782b6 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 6af179c6356d..8f5c56d5b1cd 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -173,9 +173,8 @@ static void __pmu_switch_to_host(struct kvm_vcpu *vcpu) static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code) { /* - * Make sure we handle the exit for workarounds and ptrauth - * before the pKVM handling, as the latter could decide to - * UNDEF. + * Make sure we handle the exit for workarounds before the pKVM + * handling, as the latter could decide to UNDEF. */ return (kvm_hyp_handle_sysreg(vcpu, exit_code) || kvm_handle_pvm_sysreg(vcpu, exit_code)); From ad518452fd263766946346324810f14bd8bb8b34 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 31 Jul 2024 17:21:13 +0100 Subject: [PATCH 073/562] KVM: selftests: arm64: Correct feature test for S1PIE in get-reg-list The ID register for S1PIE is ID_AA64MMFR3_EL1.S1PIE which is bits 11:8 but get-reg-list uses a shift of 4, checking SCTLRX instead. Use a shift of 8 instead. Fixes: 5f0419a0083b ("KVM: selftests: get-reg-list: add Permission Indirection registers") Signed-off-by: Mark Brown Reviewed-by: Joey Gouly Link: https://lore.kernel.org/r/20240731-kvm-arm64-fix-s1pie-test-v1-1-a9253f3b7db4@kernel.org Signed-off-by: Oliver Upton --- tools/testing/selftests/kvm/aarch64/get-reg-list.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index 709d7d721760..4abebde78187 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -32,13 +32,13 @@ static struct feature_id_reg feat_id_regs[] = { { ARM64_SYS_REG(3, 0, 10, 2, 2), /* PIRE0_EL1 */ ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ - 4, + 8, 1 }, { ARM64_SYS_REG(3, 0, 10, 2, 3), /* PIR_EL1 */ ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ - 4, + 8, 1 } }; From 6dd1e4c045afa6a4ba5d46f044c83bd357c593c2 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Wed, 7 Aug 2024 17:00:56 +0800 Subject: [PATCH 074/562] selinux: add the processing of the failure of avc_add_xperms_decision() When avc_add_xperms_decision() fails, the information recorded by the new avc node is incomplete. In this case, the new avc node should be released instead of replacing the old avc node. Cc: stable@vger.kernel.org Fixes: fa1aa143ac4a ("selinux: extended permissions for ioctls") Suggested-by: Stephen Smalley Signed-off-by: Zhen Lei Acked-by: Stephen Smalley Signed-off-by: Paul Moore --- security/selinux/avc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/security/selinux/avc.c b/security/selinux/avc.c index 7087cd2b802d..b49c44869dc4 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -907,7 +907,11 @@ static int avc_update_node(u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid, node->ae.avd.auditdeny &= ~perms; break; case AVC_CALLBACK_ADD_XPERMS: - avc_add_xperms_decision(node, xpd); + rc = avc_add_xperms_decision(node, xpd); + if (rc) { + avc_node_kill(node); + goto out_unlock; + } break; } avc_node_replace(node, orig); From e037a26ead187901f83cad9c503ccece5ff6817a Mon Sep 17 00:00:00 2001 From: Faizal Rahim Date: Sat, 6 Jul 2024 11:38:07 -0400 Subject: [PATCH 075/562] igc: Fix packet still tx after gate close by reducing i226 MAC retry buffer Testing uncovered that even when the taprio gate is closed, some packets still transmit. According to i225/6 hardware errata [1], traffic might overflow the planned QBV window. This happens because MAC maintains an internal buffer, primarily for supporting half duplex retries. Therefore, even when the gate closes, residual MAC data in the buffer may still transmit. To mitigate this for i226, reduce the MAC's internal buffer from 192 bytes to the recommended 88 bytes by modifying the RETX_CTL register value. This follows guidelines from: [1] Ethernet Controller I225/I22 Spec Update Rev 2.1 Errata Item 9: TSN: Packet Transmission Might Cross Qbv Window [2] I225/6 SW User Manual Rev 1.2.4: Section 8.11.5 Retry Buffer Control Note that the RETX_CTL register can't be used in TSN mode because half duplex feature cannot coexist with TSN. Test Steps: 1. Send taprio cmd to board A: tc qdisc replace dev enp1s0 parent root handle 100 taprio \ num_tc 4 \ map 3 2 1 0 3 3 3 3 3 3 3 3 3 3 3 3 \ queues 1@0 1@1 1@2 1@3 \ base-time 0 \ sched-entry S 0x07 500000 \ sched-entry S 0x0f 500000 \ flags 0x2 \ txtime-delay 0 Note that for TC3, gate should open for 500us and close for another 500us. 3. Take tcpdump log on Board B. 4. Send udp packets via UDP tai app from Board A to Board B. 5. Analyze tcpdump log via wireshark log on Board B. Ensure that the total time from the first to the last packet received during one cycle for TC3 does not exceed 500us. Fixes: 43546211738e ("igc: Add new device ID's") Signed-off-by: Faizal Rahim Acked-by: Vinicius Costa Gomes Tested-by: Mor Bar-Gabay Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_defines.h | 6 ++++ drivers/net/ethernet/intel/igc/igc_tsn.c | 34 ++++++++++++++++++++ 2 files changed, 40 insertions(+) diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 5f92b3c7c3d4..511384f3ec5c 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -404,6 +404,12 @@ #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */ #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */ +/* Retry Buffer Control */ +#define IGC_RETX_CTL 0x041C +#define IGC_RETX_CTL_WATERMARK_MASK 0xF +#define IGC_RETX_CTL_QBVFULLTH_SHIFT 8 /* QBV Retry Buffer Full Threshold */ +#define IGC_RETX_CTL_QBVFULLEN 0x1000 /* Enable QBV Retry Buffer Full Threshold */ + /* Transmit Scheduling Latency */ /* Latency between transmission scheduling (LaunchTime) and the time * the packet is transmitted to the network in nanosecond. diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 22cefb1eeedf..46d4c3275bbb 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -78,6 +78,15 @@ void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) wr32(IGC_GTXOFFSET, txoffset); } +static void igc_tsn_restore_retx_default(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl; + + retxctl = rd32(IGC_RETX_CTL) & IGC_RETX_CTL_WATERMARK_MASK; + wr32(IGC_RETX_CTL, retxctl); +} + /* Returns the TSN specific registers to their default values after * the adapter is reset. */ @@ -91,6 +100,9 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT); + if (igc_is_device_id_i226(hw)) + igc_tsn_restore_retx_default(adapter); + tqavctrl = rd32(IGC_TQAVCTRL); tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS); @@ -111,6 +123,25 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) return 0; } +/* To partially fix i226 HW errata, reduce MAC internal buffering from 192 Bytes + * to 88 Bytes by setting RETX_CTL register using the recommendation from: + * a) Ethernet Controller I225/I226 Specification Update Rev 2.1 + * Item 9: TSN: Packet Transmission Might Cross the Qbv Window + * b) I225/6 SW User Manual Rev 1.2.4: Section 8.11.5 Retry Buffer Control + */ +static void igc_tsn_set_retx_qbvfullthreshold(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl, watermark; + + retxctl = rd32(IGC_RETX_CTL); + watermark = retxctl & IGC_RETX_CTL_WATERMARK_MASK; + /* Set QBVFULLTH value using watermark and set QBVFULLEN */ + retxctl |= (watermark << IGC_RETX_CTL_QBVFULLTH_SHIFT) | + IGC_RETX_CTL_QBVFULLEN; + wr32(IGC_RETX_CTL, retxctl); +} + static int igc_tsn_enable_offload(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; @@ -123,6 +154,9 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN); wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN); + if (igc_is_device_id_i226(hw)) + igc_tsn_set_retx_qbvfullthreshold(adapter); + for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; u32 txqctl = 0; From f8d6acaee9d35cbff3c3cfad94641666c596f8da Mon Sep 17 00:00:00 2001 From: Faizal Rahim Date: Sun, 7 Jul 2024 08:53:16 -0400 Subject: [PATCH 076/562] igc: Fix qbv_config_change_errors logics When user issues these cmds: 1. Either a) or b) a) mqprio with hardware offload disabled b) taprio with txtime-assist feature enabled 2. etf 3. tc qdisc delete 4. taprio with base time in the past At step 4, qbv_config_change_errors wrongly increased by 1. Excerpt from IEEE 802.1Q-2018 8.6.9.3.1: "If AdminBaseTime specifies a time in the past, and the current schedule is running, then: Increment ConfigChangeError counter" qbv_config_change_errors should only increase if base time is in the past and no taprio is active. In user perspective, taprio was not active when first triggered at step 4. However, i225/6 reuses qbv for etf, so qbv is enabled with a dummy schedule at step 2 where it enters igc_tsn_enable_offload() and qbv_count got incremented to 1. At step 4, it enters igc_tsn_enable_offload() again, qbv_count is incremented to 2. Because taprio is running, tc_setup_type is TC_SETUP_QDISC_ETF and qbv_count > 1, qbv_config_change_errors value got incremented. This issue happens due to reliance on qbv_count field where a non-zero value indicates that taprio is running. But qbv_count increases regardless if taprio is triggered by user or by other tsn feature. It does not align with qbv_config_change_errors expectation where it is only concerned with taprio triggered by user. Fixing this by relocating the qbv_config_change_errors logic to igc_save_qbv_schedule(), eliminating reliance on qbv_count and its inaccuracies from i225/6's multiple uses of qbv feature for other TSN features. The new function created: igc_tsn_is_taprio_activated_by_user() uses taprio_offload_enable field to indicate that the current running taprio was triggered by user, instead of triggered by non-qbv feature like etf. Fixes: ae4fe4698300 ("igc: Add qbv_config_change_errors counter") Signed-off-by: Faizal Rahim Reviewed-by: Simon Horman Acked-by: Vinicius Costa Gomes Tested-by: Mor Bar-Gabay Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_main.c | 8 ++++++-- drivers/net/ethernet/intel/igc/igc_tsn.c | 16 ++++++++-------- drivers/net/ethernet/intel/igc/igc_tsn.h | 1 + 3 files changed, 15 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 8daf938afc36..dfd6c00b4205 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6315,12 +6315,16 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, if (!validate_schedule(adapter, qopt)) return -EINVAL; + igc_ptp_read(adapter, &now); + + if (igc_tsn_is_taprio_activated_by_user(adapter) && + is_base_time_past(qopt->base_time, &now)) + adapter->qbv_config_change_errors++; + adapter->cycle_time = qopt->cycle_time; adapter->base_time = qopt->base_time; adapter->taprio_offload_enable = true; - igc_ptp_read(adapter, &now); - for (n = 0; n < qopt->num_entries; n++) { struct tc_taprio_sched_entry *e = &qopt->entries[n]; diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 46d4c3275bbb..8ed7b965484d 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -87,6 +87,14 @@ static void igc_tsn_restore_retx_default(struct igc_adapter *adapter) wr32(IGC_RETX_CTL, retxctl); } +bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return (rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && + adapter->taprio_offload_enable; +} + /* Returns the TSN specific registers to their default values after * the adapter is reset. */ @@ -296,14 +304,6 @@ skip_cbs: s64 n = div64_s64(ktime_sub_ns(systim, base_time), cycle); base_time = ktime_add_ns(base_time, (n + 1) * cycle); - - /* Increase the counter if scheduling into the past while - * Gate Control List (GCL) is running. - */ - if ((rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && - (adapter->tc_setup_type == TC_SETUP_QDISC_TAPRIO) && - (adapter->qbv_count > 1)) - adapter->qbv_config_change_errors++; } else { if (igc_is_device_id_i226(hw)) { ktime_t adjust_time, expires_time; diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h index b53e6af560b7..98ec845a86bf 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.h +++ b/drivers/net/ethernet/intel/igc/igc_tsn.h @@ -7,5 +7,6 @@ int igc_tsn_offload_apply(struct igc_adapter *adapter); int igc_tsn_reset(struct igc_adapter *adapter); void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter); +bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter); #endif /* _IGC_BASE_H */ From 0afeaeb5dae86aceded0d5f0c3a54d27858c0c6f Mon Sep 17 00:00:00 2001 From: Faizal Rahim Date: Sun, 7 Jul 2024 08:53:17 -0400 Subject: [PATCH 077/562] igc: Fix reset adapter logics when tx mode change Following the "igc: Fix TX Hang issue when QBV Gate is close" changes, remaining issues with the reset adapter logic in igc_tsn_offload_apply() have been observed: 1. The reset adapter logics for i225 and i226 differ, although they should be the same according to the guidelines in I225/6 HW Design Section 7.5.2.1 on software initialization during tx mode changes. 2. The i225 resets adapter every time, even though tx mode doesn't change. This occurs solely based on the condition igc_is_device_id_i225() when calling schedule_work(). 3. i226 doesn't reset adapter for tsn->legacy tx mode changes. It only resets adapter for legacy->tsn tx mode transitions. 4. qbv_count introduced in the patch is actually not needed; in this context, a non-zero value of qbv_count is used to indicate if tx mode was unconditionally set to tsn in igc_tsn_enable_offload(). This could be replaced by checking the existing register IGC_TQAVCTRL_TRANSMIT_MODE_TSN bit. This patch resolves all issues and enters schedule_work() to reset the adapter only when changing tx mode. It also removes reliance on qbv_count. qbv_count field will be removed in a future patch. Test ran: 1. Verify reset adapter behaviour in i225/6: a) Enrol a new GCL Reset adapter observed (tx mode change legacy->tsn) b) Enrol a new GCL without deleting qdisc No reset adapter observed (tx mode remain tsn->tsn) c) Delete qdisc Reset adapter observed (tx mode change tsn->legacy) 2. Tested scenario from "igc: Fix TX Hang issue when QBV Gate is closed" to confirm it remains resolved. Fixes: 175c241288c0 ("igc: Fix TX Hang issue when QBV Gate is closed") Signed-off-by: Faizal Rahim Reviewed-by: Simon Horman Acked-by: Vinicius Costa Gomes Tested-by: Mor Bar-Gabay Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_tsn.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 8ed7b965484d..ada751430517 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -49,6 +49,13 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter) return new_flags; } +static bool igc_tsn_is_tx_mode_in_tsn(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return !!(rd32(IGC_TQAVCTRL) & IGC_TQAVCTRL_TRANSMIT_MODE_TSN); +} + void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; @@ -365,15 +372,22 @@ int igc_tsn_reset(struct igc_adapter *adapter) return err; } +static bool igc_tsn_will_tx_mode_change(struct igc_adapter *adapter) +{ + bool any_tsn_enabled = !!(igc_tsn_new_flags(adapter) & + IGC_FLAG_TSN_ANY_ENABLED); + + return (any_tsn_enabled && !igc_tsn_is_tx_mode_in_tsn(adapter)) || + (!any_tsn_enabled && igc_tsn_is_tx_mode_in_tsn(adapter)); +} + int igc_tsn_offload_apply(struct igc_adapter *adapter) { - struct igc_hw *hw = &adapter->hw; - - /* Per I225/6 HW Design Section 7.5.2.1, transmit mode - * cannot be changed dynamically. Require reset the adapter. + /* Per I225/6 HW Design Section 7.5.2.1 guideline, if tx mode change + * from legacy->tsn or tsn->legacy, then reset adapter is needed. */ if (netif_running(adapter->netdev) && - (igc_is_device_id_i225(hw) || !adapter->qbv_count)) { + igc_tsn_will_tx_mode_change(adapter)) { schedule_work(&adapter->reset_task); return 0; } From 6c3fc0b1c3d073bd6fc3bf43dbd0e64240537464 Mon Sep 17 00:00:00 2001 From: Faizal Rahim Date: Sun, 7 Jul 2024 08:53:18 -0400 Subject: [PATCH 078/562] igc: Fix qbv tx latency by setting gtxoffset A large tx latency issue was discovered during testing when only QBV was enabled. The issue occurs because gtxoffset was not set when QBV is active, it was only set when launch time is active. The patch "igc: Correct the launchtime offset" only sets gtxoffset when the launchtime_enable field is set by the user. Enabling launchtime_enable ultimately sets the register IGC_TXQCTL_QUEUE_MODE_LAUNCHT (referred to as LaunchT in the SW user manual). Section 7.5.2.6 of the IGC i225/6 SW User Manual Rev 1.2.4 states: "The latency between transmission scheduling (launch time) and the time the packet is transmitted to the network is listed in Table 7-61." However, the patch misinterprets the phrase "launch time" in that section by assuming it specifically refers to the LaunchT register, whereas it actually denotes the generic term for when a packet is released from the internal buffer to the MAC transmit logic. This launch time, as per that section, also implicitly refers to the QBV gate open time, where a packet waits in the buffer for the QBV gate to open. Therefore, latency applies whenever QBV is in use. TSN features such as QBU and QAV reuse QBV, making the latency universal to TSN features. Discussed with i226 HW owner (Shalev, Avi) and we were in agreement that the term "launch time" used in Section 7.5.2.6 is not clear and can be easily misinterpreted. Avi will update this section to: "When TQAVCTRL.TRANSMIT_MODE = TSN, the latency between transmission scheduling and the time the packet is transmitted to the network is listed in Table 7-61." Fix this issue by using igc_tsn_is_tx_mode_in_tsn() as a condition to write to gtxoffset, aligning with the newly updated SW User Manual. Tested: 1. Enrol taprio on talker board base-time 0 cycle-time 1000000 flags 0x2 index 0 cmd S gatemask 0x1 interval1 index 0 cmd S gatemask 0x1 interval2 Note: interval1 = interval for a 64 bytes packet to go through interval2 = cycle-time - interval1 2. Take tcpdump on listener board 3. Use udp tai app on talker to send packets to listener 4. Check the timestamp on listener via wireshark Test Result: 100 Mbps: 113 ~193 ns 1000 Mbps: 52 ~ 84 ns 2500 Mbps: 95 ~ 223 ns Note that the test result is similar to the patch "igc: Correct the launchtime offset". Fixes: 790835fcc0cb ("igc: Correct the launchtime offset") Signed-off-by: Faizal Rahim Reviewed-by: Simon Horman Acked-by: Vinicius Costa Gomes Tested-by: Mor Bar-Gabay Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_tsn.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index ada751430517..d68fa7f3d5f0 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -61,7 +61,7 @@ void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) struct igc_hw *hw = &adapter->hw; u16 txoffset; - if (!is_any_launchtime(adapter)) + if (!igc_tsn_is_tx_mode_in_tsn(adapter)) return; switch (adapter->link_speed) { From 06ce0af34177a110d6a5cf71f924965b9b230691 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Wed, 29 May 2024 00:11:23 +0100 Subject: [PATCH 079/562] soc: fsl: qbman: remove unused struct 'cgr_comp' 'cgr_comp' has been unused since commit 96f413f47677 ("soc/fsl/qbman: fix issue in qman_delete_cgr_safe()"). Remove it. Signed-off-by: Dr. David Alan Gilbert Reviewed-by: Sean Anderson Signed-off-by: Michael Ellerman Link: https://msgid.link/20240528231123.136664-1-linux@treblig.org --- drivers/soc/fsl/qbman/qman.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index 7e9074519ad2..4dc8aba33d9b 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -2546,11 +2546,6 @@ release_lock: } EXPORT_SYMBOL(qman_delete_cgr); -struct cgr_comp { - struct qman_cgr *cgr; - struct completion completion; -}; - static void qman_delete_cgr_smp_call(void *p) { qman_delete_cgr((struct qman_cgr *)p); From 78296429e20052b029211b0aca64aadc5052d581 Mon Sep 17 00:00:00 2001 From: Shyam Sundar S K Date: Tue, 30 Jul 2024 19:53:16 +0530 Subject: [PATCH 080/562] platform/x86/amd/pmf: Fix to Update HPD Data When ALS is Disabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If the Ambient Light Sensor (ALS) is disabled, the current code in the PMF driver does not query for Human Presence Detection (HPD) data in amd_pmf_get_sensor_info(). As a result, stale HPD data is used by PMF-TA to evaluate policy conditions, leading to unexpected behavior in the policy output actions. To resolve this issue, modify the PMF driver to query HPD data independently of ALS. Since user_present is a boolean, modify the current code to return true if the user is present and false if the user is away or if the sensor is not detected, and report this status to the PMF TA firmware accordingly. With this change, amd_pmf_get_sensor_info() now returns void instead of int. Fixes: cedecdba60f4 ("platform/x86/amd/pmf: Get ambient light information from AMD SFH driver") Co-developed-by: Patil Rajesh Reddy Signed-off-by: Patil Rajesh Reddy Signed-off-by: Shyam Sundar S K Link: https://lore.kernel.org/r/20240730142316.3846259-1-Shyam-sundar.S-k@amd.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/amd/pmf/spc.c | 32 ++++++++++-------------------- 1 file changed, 11 insertions(+), 21 deletions(-) diff --git a/drivers/platform/x86/amd/pmf/spc.c b/drivers/platform/x86/amd/pmf/spc.c index a3dec14c3004..3c153fb1425e 100644 --- a/drivers/platform/x86/amd/pmf/spc.c +++ b/drivers/platform/x86/amd/pmf/spc.c @@ -150,36 +150,26 @@ static int amd_pmf_get_slider_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_ return 0; } -static int amd_pmf_get_sensor_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in) +static void amd_pmf_get_sensor_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in) { struct amd_sfh_info sfh_info; - int ret; + + /* Get the latest information from SFH */ + in->ev_info.user_present = false; /* Get ALS data */ - ret = amd_get_sfh_info(&sfh_info, MT_ALS); - if (!ret) + if (!amd_get_sfh_info(&sfh_info, MT_ALS)) in->ev_info.ambient_light = sfh_info.ambient_light; else - return ret; + dev_dbg(dev->dev, "ALS is not enabled/detected\n"); /* get HPD data */ - ret = amd_get_sfh_info(&sfh_info, MT_HPD); - if (ret) - return ret; - - switch (sfh_info.user_present) { - case SFH_NOT_DETECTED: - in->ev_info.user_present = 0xff; /* assume no sensors connected */ - break; - case SFH_USER_PRESENT: - in->ev_info.user_present = 1; - break; - case SFH_USER_AWAY: - in->ev_info.user_present = 0; - break; + if (!amd_get_sfh_info(&sfh_info, MT_HPD)) { + if (sfh_info.user_present == SFH_USER_PRESENT) + in->ev_info.user_present = true; + } else { + dev_dbg(dev->dev, "HPD is not enabled/detected\n"); } - - return 0; } void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in) From 613e3900c24bb1379d994f44d75d31c3223cc263 Mon Sep 17 00:00:00 2001 From: Gergo Koteles Date: Thu, 25 Jul 2024 11:21:07 +0200 Subject: [PATCH 081/562] platform/x86: ideapad-laptop: introduce a generic notification chain MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are several cases where a notification chain can simplify Lenovo WMI drivers. Add a generic notification chain into ideapad-laptop. Signed-off-by: Gergo Koteles Link: https://lore.kernel.org/r/c5a43efae8a32bd034c3d19c0a686941347575a7.1721898747.git.soyer@irl.hu Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/ideapad-laptop.c | 37 +++++++++++++++++++++++++++ drivers/platform/x86/ideapad-laptop.h | 5 ++++ 2 files changed, 42 insertions(+) diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 1ace711f7442..866b32bfe2c9 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1592,6 +1592,39 @@ static void ideapad_sync_touchpad_state(struct ideapad_private *priv, bool send_ priv->r_touchpad_val = value; } +static int ideapad_laptop_nb_notify(struct notifier_block *nb, + unsigned long action, void *data) +{ + switch (action) { + } + + return 0; +} + +static struct notifier_block ideapad_laptop_notifier = { + .notifier_call = ideapad_laptop_nb_notify, +}; + +static BLOCKING_NOTIFIER_HEAD(ideapad_laptop_chain_head); + +int ideapad_laptop_register_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&ideapad_laptop_chain_head, nb); +} +EXPORT_SYMBOL_NS_GPL(ideapad_laptop_register_notifier, IDEAPAD_LAPTOP); + +int ideapad_laptop_unregister_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&ideapad_laptop_chain_head, nb); +} +EXPORT_SYMBOL_NS_GPL(ideapad_laptop_unregister_notifier, IDEAPAD_LAPTOP); + +void ideapad_laptop_call_notifier(unsigned long action, void *data) +{ + blocking_notifier_call_chain(&ideapad_laptop_chain_head, action, data); +} +EXPORT_SYMBOL_NS_GPL(ideapad_laptop_call_notifier, IDEAPAD_LAPTOP); + static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data) { struct ideapad_private *priv = data; @@ -1974,6 +2007,8 @@ static int ideapad_acpi_add(struct platform_device *pdev) if (err) goto shared_init_failed; + ideapad_laptop_register_notifier(&ideapad_laptop_notifier); + return 0; shared_init_failed: @@ -2006,6 +2041,8 @@ static void ideapad_acpi_remove(struct platform_device *pdev) struct ideapad_private *priv = dev_get_drvdata(&pdev->dev); int i; + ideapad_laptop_unregister_notifier(&ideapad_laptop_notifier); + ideapad_shared_exit(priv); acpi_remove_notify_handler(priv->adev->handle, diff --git a/drivers/platform/x86/ideapad-laptop.h b/drivers/platform/x86/ideapad-laptop.h index 4498a96de597..3eb0dcd6bf7b 100644 --- a/drivers/platform/x86/ideapad-laptop.h +++ b/drivers/platform/x86/ideapad-laptop.h @@ -12,6 +12,11 @@ #include #include #include +#include + +int ideapad_laptop_register_notifier(struct notifier_block *nb); +int ideapad_laptop_unregister_notifier(struct notifier_block *nb); +void ideapad_laptop_call_notifier(unsigned long action, void *data); enum { VPCCMD_R_VPC1 = 0x10, From cde7886b35176d56e72bfc68dc104fa08e7b072c Mon Sep 17 00:00:00 2001 From: Gergo Koteles Date: Thu, 25 Jul 2024 11:21:08 +0200 Subject: [PATCH 082/562] platform/x86: ideapad-laptop: move ymc_trigger_ec from lenovo-ymc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some models need to trigger the EC after each YMC event for the yoga mode control to work properly. EC triggering consist of a VPC call from the lenovo-ymc module. Except for this, all VPC calls are in the ideapad-laptop module. Since ideapad-laptop has a notification chain, a new YMC_EVENT action can be added and triggered from the lenovo-ymc module. Then the ideapad-laptop can trigger the EC. If the triggering is in the ideapad-laptop module, then the ec_trigger module parameter should be there as well. Move the ymc_trigger_ec functionality and the ec_trigger module parameter to the ideapad-laptop module. Signed-off-by: Gergo Koteles Reviewed-by: Ilpo Järvinen Link: https://lore.kernel.org/r/d980ab3ac32b5e554f456b0ff17279bfdbe2a203.1721898747.git.soyer@irl.hu Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/Kconfig | 1 + drivers/platform/x86/ideapad-laptop.c | 49 ++++++++++++++++++++++ drivers/platform/x86/ideapad-laptop.h | 4 ++ drivers/platform/x86/lenovo-ymc.c | 60 +-------------------------- 4 files changed, 56 insertions(+), 58 deletions(-) diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 665fa9524986..ddfccc226751 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -477,6 +477,7 @@ config LENOVO_YMC tristate "Lenovo Yoga Tablet Mode Control" depends on ACPI_WMI depends on INPUT + depends on IDEAPAD_LAPTOP select INPUT_SPARSEKMAP help This driver maps the Tablet Mode Control switch to SW_TABLET_MODE input diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 866b32bfe2c9..9fc1bb990e47 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -146,6 +146,7 @@ struct ideapad_private { bool touchpad_ctrl_via_ec : 1; bool ctrl_ps2_aux_port : 1; bool usb_charging : 1; + bool ymc_ec_trigger : 1; } features; struct { bool initialized; @@ -194,6 +195,12 @@ MODULE_PARM_DESC(touchpad_ctrl_via_ec, "Enable registering a 'touchpad' sysfs-attribute which can be used to manually " "tell the EC to enable/disable the touchpad. This may not work on all models."); +static bool ymc_ec_trigger __read_mostly; +module_param(ymc_ec_trigger, bool, 0444); +MODULE_PARM_DESC(ymc_ec_trigger, + "Enable EC triggering work-around to force emitting tablet mode events. " + "If you need this please report this to: platform-driver-x86@vger.kernel.org"); + /* * shared data */ @@ -1592,10 +1599,50 @@ static void ideapad_sync_touchpad_state(struct ideapad_private *priv, bool send_ priv->r_touchpad_val = value; } +static const struct dmi_system_id ymc_ec_trigger_quirk_dmi_table[] = { + { + /* Lenovo Yoga 7 14ARB7 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82QF"), + }, + }, + { + /* Lenovo Yoga 7 14ACN6 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82N7"), + }, + }, + { } +}; + +static void ideapad_laptop_trigger_ec(void) +{ + struct ideapad_private *priv; + int ret; + + guard(mutex)(&ideapad_shared_mutex); + + priv = ideapad_shared; + if (!priv) + return; + + if (!priv->features.ymc_ec_trigger) + return; + + ret = write_ec_cmd(priv->adev->handle, VPCCMD_W_YMC, 1); + if (ret) + dev_warn(&priv->platform_device->dev, "Could not write YMC: %d\n", ret); +} + static int ideapad_laptop_nb_notify(struct notifier_block *nb, unsigned long action, void *data) { switch (action) { + case IDEAPAD_LAPTOP_YMC_EVENT: + ideapad_laptop_trigger_ec(); + break; } return 0; @@ -1761,6 +1808,8 @@ static void ideapad_check_features(struct ideapad_private *priv) priv->features.ctrl_ps2_aux_port = ctrl_ps2_aux_port || dmi_check_system(ctrl_ps2_aux_port_list); priv->features.touchpad_ctrl_via_ec = touchpad_ctrl_via_ec; + priv->features.ymc_ec_trigger = + ymc_ec_trigger || dmi_check_system(ymc_ec_trigger_quirk_dmi_table); if (!read_ec_data(handle, VPCCMD_R_FAN, &val)) priv->features.fan_mode = true; diff --git a/drivers/platform/x86/ideapad-laptop.h b/drivers/platform/x86/ideapad-laptop.h index 3eb0dcd6bf7b..948cc61800a9 100644 --- a/drivers/platform/x86/ideapad-laptop.h +++ b/drivers/platform/x86/ideapad-laptop.h @@ -14,6 +14,10 @@ #include #include +enum ideapad_laptop_notifier_actions { + IDEAPAD_LAPTOP_YMC_EVENT, +}; + int ideapad_laptop_register_notifier(struct notifier_block *nb); int ideapad_laptop_unregister_notifier(struct notifier_block *nb); void ideapad_laptop_call_notifier(unsigned long action, void *data); diff --git a/drivers/platform/x86/lenovo-ymc.c b/drivers/platform/x86/lenovo-ymc.c index e1fbc35504d4..e0bbd6a14a89 100644 --- a/drivers/platform/x86/lenovo-ymc.c +++ b/drivers/platform/x86/lenovo-ymc.c @@ -20,32 +20,10 @@ #define LENOVO_YMC_QUERY_INSTANCE 0 #define LENOVO_YMC_QUERY_METHOD 0x01 -static bool ec_trigger __read_mostly; -module_param(ec_trigger, bool, 0444); -MODULE_PARM_DESC(ec_trigger, "Enable EC triggering work-around to force emitting tablet mode events"); - static bool force; module_param(force, bool, 0444); MODULE_PARM_DESC(force, "Force loading on boards without a convertible DMI chassis-type"); -static const struct dmi_system_id ec_trigger_quirk_dmi_table[] = { - { - /* Lenovo Yoga 7 14ARB7 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "82QF"), - }, - }, - { - /* Lenovo Yoga 7 14ACN6 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "82N7"), - }, - }, - { } -}; - static const struct dmi_system_id allowed_chasis_types_dmi_table[] = { { .matches = { @@ -62,21 +40,8 @@ static const struct dmi_system_id allowed_chasis_types_dmi_table[] = { struct lenovo_ymc_private { struct input_dev *input_dev; - struct acpi_device *ec_acpi_dev; }; -static void lenovo_ymc_trigger_ec(struct wmi_device *wdev, struct lenovo_ymc_private *priv) -{ - int err; - - if (!priv->ec_acpi_dev) - return; - - err = write_ec_cmd(priv->ec_acpi_dev->handle, VPCCMD_W_YMC, 1); - if (err) - dev_warn(&wdev->dev, "Could not write YMC: %d\n", err); -} - static const struct key_entry lenovo_ymc_keymap[] = { /* Laptop */ { KE_SW, 0x01, { .sw = { SW_TABLET_MODE, 0 } } }, @@ -125,11 +90,9 @@ static void lenovo_ymc_notify(struct wmi_device *wdev, union acpi_object *data) free_obj: kfree(obj); - lenovo_ymc_trigger_ec(wdev, priv); + ideapad_laptop_call_notifier(IDEAPAD_LAPTOP_YMC_EVENT, &code); } -static void acpi_dev_put_helper(void *p) { acpi_dev_put(p); } - static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx) { struct lenovo_ymc_private *priv; @@ -143,29 +106,10 @@ static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx) return -ENODEV; } - ec_trigger |= dmi_check_system(ec_trigger_quirk_dmi_table); - priv = devm_kzalloc(&wdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; - if (ec_trigger) { - pr_debug("Lenovo YMC enable EC triggering.\n"); - priv->ec_acpi_dev = acpi_dev_get_first_match_dev("VPC2004", NULL, -1); - - if (!priv->ec_acpi_dev) { - dev_err(&wdev->dev, "Could not find EC ACPI device.\n"); - return -ENODEV; - } - err = devm_add_action_or_reset(&wdev->dev, - acpi_dev_put_helper, priv->ec_acpi_dev); - if (err) { - dev_err(&wdev->dev, - "Could not clean up EC ACPI device: %d\n", err); - return err; - } - } - input_dev = devm_input_allocate_device(&wdev->dev); if (!input_dev) return -ENOMEM; @@ -192,7 +136,6 @@ static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx) dev_set_drvdata(&wdev->dev, priv); /* Report the state for the first time on probe */ - lenovo_ymc_trigger_ec(wdev, priv); lenovo_ymc_notify(wdev, NULL); return 0; } @@ -217,3 +160,4 @@ module_wmi_driver(lenovo_ymc_driver); MODULE_AUTHOR("Gergo Koteles "); MODULE_DESCRIPTION("Lenovo Yoga Mode Control driver"); MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS(IDEAPAD_LAPTOP); From 7cc06e729460a209b84d3db4db56c9f85f048cc2 Mon Sep 17 00:00:00 2001 From: Gergo Koteles Date: Thu, 25 Jul 2024 11:21:10 +0200 Subject: [PATCH 083/562] platform/x86: ideapad-laptop: add a mutex to synchronize VPC commands MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Calling VPC commands consists of several VPCW and VPCR ACPI calls. These calls and their results can get mixed up if they are called simultaneously from different threads, like acpi notify handler, sysfs, debugfs, notification chain. The commit e2ffcda16290 ("ACPI: OSL: Allow Notify () handlers to run on all CPUs") made the race issues much worse than before it but some races were possible even before that commit. Add a mutex to synchronize VPC commands. Fixes: e2ffcda16290 ("ACPI: OSL: Allow Notify () handlers to run on all CPUs") Fixes: e82882cdd241 ("platform/x86: Add driver for Yoga Tablet Mode switch") Signed-off-by: Gergo Koteles Link: https://lore.kernel.org/r/f26782fa1194ad11ed5d9ba121a804e59b58b026.1721898747.git.soyer@irl.hu Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/ideapad-laptop.c | 64 ++++++++++++++++++++------- 1 file changed, 47 insertions(+), 17 deletions(-) diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 9fc1bb990e47..98ec30fce9fd 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -126,6 +126,7 @@ struct ideapad_rfk_priv { struct ideapad_private { struct acpi_device *adev; + struct mutex vpc_mutex; /* protects the VPC calls */ struct rfkill *rfk[IDEAPAD_RFKILL_DEV_NUM]; struct ideapad_rfk_priv rfk_priv[IDEAPAD_RFKILL_DEV_NUM]; struct platform_device *platform_device; @@ -301,6 +302,8 @@ static int debugfs_status_show(struct seq_file *s, void *data) struct ideapad_private *priv = s->private; unsigned long value; + guard(mutex)(&priv->vpc_mutex); + if (!read_ec_data(priv->adev->handle, VPCCMD_R_BL_MAX, &value)) seq_printf(s, "Backlight max: %lu\n", value); if (!read_ec_data(priv->adev->handle, VPCCMD_R_BL, &value)) @@ -419,7 +422,8 @@ static ssize_t camera_power_show(struct device *dev, unsigned long result; int err; - err = read_ec_data(priv->adev->handle, VPCCMD_R_CAMERA, &result); + scoped_guard(mutex, &priv->vpc_mutex) + err = read_ec_data(priv->adev->handle, VPCCMD_R_CAMERA, &result); if (err) return err; @@ -438,7 +442,8 @@ static ssize_t camera_power_store(struct device *dev, if (err) return err; - err = write_ec_cmd(priv->adev->handle, VPCCMD_W_CAMERA, state); + scoped_guard(mutex, &priv->vpc_mutex) + err = write_ec_cmd(priv->adev->handle, VPCCMD_W_CAMERA, state); if (err) return err; @@ -491,7 +496,8 @@ static ssize_t fan_mode_show(struct device *dev, unsigned long result; int err; - err = read_ec_data(priv->adev->handle, VPCCMD_R_FAN, &result); + scoped_guard(mutex, &priv->vpc_mutex) + err = read_ec_data(priv->adev->handle, VPCCMD_R_FAN, &result); if (err) return err; @@ -513,7 +519,8 @@ static ssize_t fan_mode_store(struct device *dev, if (state > 4 || state == 3) return -EINVAL; - err = write_ec_cmd(priv->adev->handle, VPCCMD_W_FAN, state); + scoped_guard(mutex, &priv->vpc_mutex) + err = write_ec_cmd(priv->adev->handle, VPCCMD_W_FAN, state); if (err) return err; @@ -598,7 +605,8 @@ static ssize_t touchpad_show(struct device *dev, unsigned long result; int err; - err = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &result); + scoped_guard(mutex, &priv->vpc_mutex) + err = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &result); if (err) return err; @@ -619,7 +627,8 @@ static ssize_t touchpad_store(struct device *dev, if (err) return err; - err = write_ec_cmd(priv->adev->handle, VPCCMD_W_TOUCHPAD, state); + scoped_guard(mutex, &priv->vpc_mutex) + err = write_ec_cmd(priv->adev->handle, VPCCMD_W_TOUCHPAD, state); if (err) return err; @@ -1012,6 +1021,8 @@ static int ideapad_rfk_set(void *data, bool blocked) struct ideapad_rfk_priv *priv = data; int opcode = ideapad_rfk_data[priv->dev].opcode; + guard(mutex)(&priv->priv->vpc_mutex); + return write_ec_cmd(priv->priv->adev->handle, opcode, !blocked); } @@ -1025,6 +1036,8 @@ static void ideapad_sync_rfk_state(struct ideapad_private *priv) int i; if (priv->features.hw_rfkill_switch) { + guard(mutex)(&priv->vpc_mutex); + if (read_ec_data(priv->adev->handle, VPCCMD_R_RF, &hw_blocked)) return; hw_blocked = !hw_blocked; @@ -1198,8 +1211,9 @@ static void ideapad_input_novokey(struct ideapad_private *priv) { unsigned long long_pressed; - if (read_ec_data(priv->adev->handle, VPCCMD_R_NOVO, &long_pressed)) - return; + scoped_guard(mutex, &priv->vpc_mutex) + if (read_ec_data(priv->adev->handle, VPCCMD_R_NOVO, &long_pressed)) + return; if (long_pressed) ideapad_input_report(priv, 17); @@ -1211,8 +1225,9 @@ static void ideapad_check_special_buttons(struct ideapad_private *priv) { unsigned long bit, value; - if (read_ec_data(priv->adev->handle, VPCCMD_R_SPECIAL_BUTTONS, &value)) - return; + scoped_guard(mutex, &priv->vpc_mutex) + if (read_ec_data(priv->adev->handle, VPCCMD_R_SPECIAL_BUTTONS, &value)) + return; for_each_set_bit (bit, &value, 16) { switch (bit) { @@ -1245,6 +1260,8 @@ static int ideapad_backlight_get_brightness(struct backlight_device *blightdev) unsigned long now; int err; + guard(mutex)(&priv->vpc_mutex); + err = read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now); if (err) return err; @@ -1257,6 +1274,8 @@ static int ideapad_backlight_update_status(struct backlight_device *blightdev) struct ideapad_private *priv = bl_get_data(blightdev); int err; + guard(mutex)(&priv->vpc_mutex); + err = write_ec_cmd(priv->adev->handle, VPCCMD_W_BL, blightdev->props.brightness); if (err) @@ -1334,6 +1353,8 @@ static void ideapad_backlight_notify_power(struct ideapad_private *priv) if (!blightdev) return; + guard(mutex)(&priv->vpc_mutex); + if (read_ec_data(priv->adev->handle, VPCCMD_R_BL_POWER, &power)) return; @@ -1346,7 +1367,8 @@ static void ideapad_backlight_notify_brightness(struct ideapad_private *priv) /* if we control brightness via acpi video driver */ if (!priv->blightdev) - read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now); + scoped_guard(mutex, &priv->vpc_mutex) + read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now); else backlight_force_update(priv->blightdev, BACKLIGHT_UPDATE_HOTKEY); } @@ -1571,7 +1593,8 @@ static void ideapad_sync_touchpad_state(struct ideapad_private *priv, bool send_ int ret; /* Without reading from EC touchpad LED doesn't switch state */ - ret = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &value); + scoped_guard(mutex, &priv->vpc_mutex) + ret = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &value); if (ret) return; @@ -1631,7 +1654,8 @@ static void ideapad_laptop_trigger_ec(void) if (!priv->features.ymc_ec_trigger) return; - ret = write_ec_cmd(priv->adev->handle, VPCCMD_W_YMC, 1); + scoped_guard(mutex, &priv->vpc_mutex) + ret = write_ec_cmd(priv->adev->handle, VPCCMD_W_YMC, 1); if (ret) dev_warn(&priv->platform_device->dev, "Could not write YMC: %d\n", ret); } @@ -1677,11 +1701,13 @@ static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data) struct ideapad_private *priv = data; unsigned long vpc1, vpc2, bit; - if (read_ec_data(handle, VPCCMD_R_VPC1, &vpc1)) - return; + scoped_guard(mutex, &priv->vpc_mutex) { + if (read_ec_data(handle, VPCCMD_R_VPC1, &vpc1)) + return; - if (read_ec_data(handle, VPCCMD_R_VPC2, &vpc2)) - return; + if (read_ec_data(handle, VPCCMD_R_VPC2, &vpc2)) + return; + } vpc1 = (vpc2 << 8) | vpc1; @@ -1988,6 +2014,10 @@ static int ideapad_acpi_add(struct platform_device *pdev) priv->adev = adev; priv->platform_device = pdev; + err = devm_mutex_init(&pdev->dev, &priv->vpc_mutex); + if (err) + return err; + ideapad_check_features(priv); err = ideapad_sysfs_init(priv); From 1cb6ab446424649f03c82334634360c2e3043684 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 23 Jul 2024 17:15:44 +0800 Subject: [PATCH 084/562] MIPS: Loongson64: Set timer mode in cpu-probe Loongson64 C and G processors have EXTIMER feature which is conflicting with CP0 counter. Although the processor resets in EXTIMER disabled & INTIMER enabled mode, which is compatible with MIPS CP0 compare, firmware may attempt to enable EXTIMER and interfere CP0 compare. Set timer mode back to MIPS compatible mode to fix booting on systems with such firmware before we have an actual driver for EXTIMER. Cc: stable@vger.kernel.org Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/cpu-probe.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index bda7f193baab..af7412549e6e 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1724,12 +1724,16 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM | MIPS_ASE_LOONGSON_EXT | MIPS_ASE_LOONGSON_EXT2); c->ases &= ~MIPS_ASE_VZ; /* VZ of Loongson-3A2000/3000 is incomplete */ + change_c0_config6(LOONGSON_CONF6_EXTIMER | LOONGSON_CONF6_INTIMER, + LOONGSON_CONF6_INTIMER); break; case PRID_IMP_LOONGSON_64G: __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); decode_cpucfg(c); + change_c0_config6(LOONGSON_CONF6_EXTIMER | LOONGSON_CONF6_INTIMER, + LOONGSON_CONF6_INTIMER); break; default: panic("Unknown Loongson Processor ID!"); From 9eb18136af9fe4dd688724070f2bfba271bd1542 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 8 Aug 2024 10:15:46 +0100 Subject: [PATCH 085/562] KVM: arm64: vgic: Hold config_lock while tearing down a CPU interface Tearing down a vcpu CPU interface involves freeing the private interrupt array. If we don't hold the lock, we may race against another thread trying to configure it. Yeah, fuzzers do wonderful things... Taking the lock early solves this particular problem. Fixes: 03b3d00a70b5 ("KVM: arm64: vgic: Allocate private interrupts on demand") Reported-by: Alexander Potapenko Tested-by: Alexander Potapenko Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20240808091546.3262111-1-maz@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/kvm/vgic/vgic-init.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 7f68cf58b978..41feb858ff9a 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -438,14 +438,13 @@ void kvm_vgic_destroy(struct kvm *kvm) unsigned long i; mutex_lock(&kvm->slots_lock); + mutex_lock(&kvm->arch.config_lock); vgic_debug_destroy(kvm); kvm_for_each_vcpu(i, vcpu, kvm) __kvm_vgic_vcpu_destroy(vcpu); - mutex_lock(&kvm->arch.config_lock); - kvm_vgic_dist_destroy(kvm); mutex_unlock(&kvm->arch.config_lock); From cd9aae921ab6b614e56ce690dedfe82e79db9354 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Thu, 8 Aug 2024 11:44:07 -0700 Subject: [PATCH 086/562] dt-bindings: display: panel: samsung,atna45dc02: Fix indentation The yaml had indentation errors: ./Documentation/devicetree/bindings/display/panel/samsung,atna33xc20.yaml:21:9: [warning] wrong indentation: expected 10 but found 8 (indentation) ./Documentation/devicetree/bindings/display/panel/samsung,atna33xc20.yaml:23:11: [warning] wrong indentation: expected 12 but found 10 (indentation) Fix them. Reported-by: Rob Herring Closes: https://lore.kernel.org/r/CAL_JsqLRTgQRPcfXy4G9hLoHMd-Uax4_C90BV_OZn4mK+-82kw@mail.gmail.com Fixes: 1c4a057d01f4 ("dt-bindings: display: panel: samsung,atna45dc02: Document ATNA45DC02") Reviewed-by: Rob Clark Signed-off-by: Douglas Anderson Link: https://patchwork.freedesktop.org/patch/msgid/20240808114407.1.I099e8e9e36407a0785d846b953031d40ea71e559@changeid --- .../bindings/display/panel/samsung,atna33xc20.yaml | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/Documentation/devicetree/bindings/display/panel/samsung,atna33xc20.yaml b/Documentation/devicetree/bindings/display/panel/samsung,atna33xc20.yaml index 87c601bcf20a..032f783eefc4 100644 --- a/Documentation/devicetree/bindings/display/panel/samsung,atna33xc20.yaml +++ b/Documentation/devicetree/bindings/display/panel/samsung,atna33xc20.yaml @@ -18,12 +18,12 @@ properties: # Samsung 13.3" FHD (1920x1080 pixels) eDP AMOLED panel - const: samsung,atna33xc20 - items: - - enum: - # Samsung 14.5" WQXGA+ (2880x1800 pixels) eDP AMOLED panel - - samsung,atna45af01 - # Samsung 14.5" 3K (2944x1840 pixels) eDP AMOLED panel - - samsung,atna45dc02 - - const: samsung,atna33xc20 + - enum: + # Samsung 14.5" WQXGA+ (2880x1800 pixels) eDP AMOLED panel + - samsung,atna45af01 + # Samsung 14.5" 3K (2944x1840 pixels) eDP AMOLED panel + - samsung,atna45dc02 + - const: samsung,atna33xc20 enable-gpios: true port: true From 0c84bde4f37ba27d50e4c70ecacd33fe4a57030d Mon Sep 17 00:00:00 2001 From: Sean Young Date: Thu, 8 Aug 2024 10:35:19 +0200 Subject: [PATCH 087/562] media: Revert "media: dvb-usb: Fix unexpected infinite loop in dvb_usb_read_remote_control()" This reverts commit 2052138b7da52ad5ccaf74f736d00f39a1c9198c. This breaks the TeVii s480 dual DVB-S2 S660. The device has a bulk in endpoint but no corresponding out endpoint, so the device does not pass the "has both receive and send bulk endpoint" test. Seemingly this device does not use dvb_usb_generic_rw() so I have tried removing the generic_bulk_ctrl_endpoint entry, but this resulted in different problems. As we have no explanation yet, revert. $ dmesg | grep -i -e dvb -e dw21 -e usb\ 4 [ 0.999122] usb 1-1: new high-speed USB device number 2 using ehci-pci [ 1.023123] usb 4-1: new high-speed USB device number 2 using ehci-pci [ 1.130247] usb 1-1: New USB device found, idVendor=9022, idProduct=d482, +bcdDevice= 0.01 [ 1.130257] usb 1-1: New USB device strings: Mfr=0, Product=0, SerialNumber=0 [ 1.152323] usb 4-1: New USB device found, idVendor=9022, idProduct=d481, +bcdDevice= 0.01 [ 1.152329] usb 4-1: New USB device strings: Mfr=0, Product=0, SerialNumber=0 [ 6.701033] dvb-usb: found a 'TeVii S480.2 USB' in cold state, will try to +load a firmware [ 6.701178] dvb-usb: downloading firmware from file 'dvb-usb-s660.fw' [ 6.701179] dw2102: start downloading DW210X firmware [ 6.703715] dvb-usb: found a 'Microsoft Xbox One Digital TV Tuner' in cold +state, will try to load a firmware [ 6.703974] dvb-usb: downloading firmware from file 'dvb-usb-dib0700-1.20.fw' [ 6.756432] usb 1-1: USB disconnect, device number 2 [ 6.862119] dvb-usb: found a 'TeVii S480.2 USB' in warm state. [ 6.862194] dvb-usb: TeVii S480.2 USB error while loading driver (-22) [ 6.862209] dvb-usb: found a 'TeVii S480.1 USB' in cold state, will try to +load a firmware [ 6.862244] dvb-usb: downloading firmware from file 'dvb-usb-s660.fw' [ 6.862245] dw2102: start downloading DW210X firmware [ 6.914811] usb 4-1: USB disconnect, device number 2 [ 7.014131] dvb-usb: found a 'TeVii S480.1 USB' in warm state. [ 7.014487] dvb-usb: TeVii S480.1 USB error while loading driver (-22) [ 7.014538] usbcore: registered new interface driver dw2102 Closes: https://lore.kernel.org/stable/20240801165146.38991f60@mir/ Fixes: 2052138b7da5 ("media: dvb-usb: Fix unexpected infinite loop in dvb_usb_read_remote_control()") Reported-by: Stefan Lippers-Hollmann Cc: stable@vger.kernel.org Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb/dvb-usb-init.c | 35 +++--------------------- 1 file changed, 4 insertions(+), 31 deletions(-) diff --git a/drivers/media/usb/dvb-usb/dvb-usb-init.c b/drivers/media/usb/dvb-usb/dvb-usb-init.c index 22d83ac18eb7..fbf58012becd 100644 --- a/drivers/media/usb/dvb-usb/dvb-usb-init.c +++ b/drivers/media/usb/dvb-usb/dvb-usb-init.c @@ -23,40 +23,11 @@ static int dvb_usb_force_pid_filter_usage; module_param_named(force_pid_filter_usage, dvb_usb_force_pid_filter_usage, int, 0444); MODULE_PARM_DESC(force_pid_filter_usage, "force all dvb-usb-devices to use a PID filter, if any (default: 0)."); -static int dvb_usb_check_bulk_endpoint(struct dvb_usb_device *d, u8 endpoint) -{ - if (endpoint) { - int ret; - - ret = usb_pipe_type_check(d->udev, usb_sndbulkpipe(d->udev, endpoint)); - if (ret) - return ret; - ret = usb_pipe_type_check(d->udev, usb_rcvbulkpipe(d->udev, endpoint)); - if (ret) - return ret; - } - return 0; -} - -static void dvb_usb_clear_halt(struct dvb_usb_device *d, u8 endpoint) -{ - if (endpoint) { - usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, endpoint)); - usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, endpoint)); - } -} - static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs) { struct dvb_usb_adapter *adap; int ret, n, o; - ret = dvb_usb_check_bulk_endpoint(d, d->props.generic_bulk_ctrl_endpoint); - if (ret) - return ret; - ret = dvb_usb_check_bulk_endpoint(d, d->props.generic_bulk_ctrl_endpoint_response); - if (ret) - return ret; for (n = 0; n < d->props.num_adapters; n++) { adap = &d->adapter[n]; adap->dev = d; @@ -132,8 +103,10 @@ static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs) * when reloading the driver w/o replugging the device * sometimes a timeout occurs, this helps */ - dvb_usb_clear_halt(d, d->props.generic_bulk_ctrl_endpoint); - dvb_usb_clear_halt(d, d->props.generic_bulk_ctrl_endpoint_response); + if (d->props.generic_bulk_ctrl_endpoint != 0) { + usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint)); + usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint)); + } return 0; From 05a3d6e9307250a5911d75308e4363466794ab21 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 8 Aug 2024 11:57:38 -0400 Subject: [PATCH 088/562] selinux: revert our use of vma_is_initial_heap() Unfortunately it appears that vma_is_initial_heap() is currently broken for applications that do not currently have any heap allocated, e.g. brk == start_brk. The breakage is such that it will cause SELinux to check for the process/execheap permission on memory regions that cross brk/start_brk even when there is no heap. The proper fix would be to correct vma_is_initial_heap(), but as there are multiple callers I am hesitant to unilaterally modify the helper out of concern that I would end up breaking some other subsystem. The mm developers have been made aware of the situation and hopefully they will have a fix at some point in the future, but we need a fix soon so we are simply going to revert our use of vma_is_initial_heap() in favor of our old logic/code which works as expected, even in the face of a zero size heap. We can return to using vma_is_initial_heap() at some point in the future when it is fixed. Cc: stable@vger.kernel.org Reported-by: Marc Reisner Closes: https://lore.kernel.org/all/ZrPmoLKJEf1wiFmM@marcreisner.com Fixes: 68df1baf158f ("selinux: use vma_is_initial_stack() and vma_is_initial_heap()") Signed-off-by: Paul Moore --- security/selinux/hooks.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 55c78c318ccd..bfa61e005aac 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3852,7 +3852,17 @@ static int selinux_file_mprotect(struct vm_area_struct *vma, if (default_noexec && (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) { int rc = 0; - if (vma_is_initial_heap(vma)) { + /* + * We don't use the vma_is_initial_heap() helper as it has + * a history of problems and is currently broken on systems + * where there is no heap, e.g. brk == start_brk. Before + * replacing the conditional below with vma_is_initial_heap(), + * or something similar, please ensure that the logic is the + * same as what we have below or you have tested every possible + * corner case you can think to test. + */ + if (vma->vm_start >= vma->vm_mm->start_brk && + vma->vm_end <= vma->vm_mm->brk) { rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECHEAP, NULL); } else if (!vma->vm_file && (vma_is_initial_stack(vma) || From a018c1b636e79b60149b41151ded7c2606d8606e Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Mon, 5 Aug 2024 08:56:18 +0900 Subject: [PATCH 089/562] ksmbd: override fsids for share path check Sangsoo reported that a DAC denial error occurred when accessing files through the ksmbd thread. This patch override fsids for share path check. Reported-by: Sangsoo Lee Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/mgmt/share_config.c | 15 ++++++++++++--- fs/smb/server/mgmt/share_config.h | 4 +++- fs/smb/server/mgmt/tree_connect.c | 9 +++++---- fs/smb/server/mgmt/tree_connect.h | 4 ++-- fs/smb/server/smb2pdu.c | 2 +- fs/smb/server/smb_common.c | 9 +++++++-- fs/smb/server/smb_common.h | 2 ++ 7 files changed, 32 insertions(+), 13 deletions(-) diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index e0a6b758094f..d8d03070ae44 100644 --- a/fs/smb/server/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c @@ -15,6 +15,7 @@ #include "share_config.h" #include "user_config.h" #include "user_session.h" +#include "../connection.h" #include "../transport_ipc.h" #include "../misc.h" @@ -120,12 +121,13 @@ static int parse_veto_list(struct ksmbd_share_config *share, return 0; } -static struct ksmbd_share_config *share_config_request(struct unicode_map *um, +static struct ksmbd_share_config *share_config_request(struct ksmbd_work *work, const char *name) { struct ksmbd_share_config_response *resp; struct ksmbd_share_config *share = NULL; struct ksmbd_share_config *lookup; + struct unicode_map *um = work->conn->um; int ret; resp = ksmbd_ipc_share_config_request(name); @@ -181,7 +183,14 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um, KSMBD_SHARE_CONFIG_VETO_LIST(resp), resp->veto_list_sz); if (!ret && share->path) { + if (__ksmbd_override_fsids(work, share)) { + kill_share(share); + share = NULL; + goto out; + } + ret = kern_path(share->path, 0, &share->vfs_path); + ksmbd_revert_fsids(work); if (ret) { ksmbd_debug(SMB, "failed to access '%s'\n", share->path); @@ -214,7 +223,7 @@ out: return share; } -struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um, +struct ksmbd_share_config *ksmbd_share_config_get(struct ksmbd_work *work, const char *name) { struct ksmbd_share_config *share; @@ -227,7 +236,7 @@ struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um, if (share) return share; - return share_config_request(um, name); + return share_config_request(work, name); } bool ksmbd_share_veto_filename(struct ksmbd_share_config *share, diff --git a/fs/smb/server/mgmt/share_config.h b/fs/smb/server/mgmt/share_config.h index 5f591751b923..d4ac2dd4de20 100644 --- a/fs/smb/server/mgmt/share_config.h +++ b/fs/smb/server/mgmt/share_config.h @@ -11,6 +11,8 @@ #include #include +struct ksmbd_work; + struct ksmbd_share_config { char *name; char *path; @@ -68,7 +70,7 @@ static inline void ksmbd_share_config_put(struct ksmbd_share_config *share) __ksmbd_share_config_put(share); } -struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um, +struct ksmbd_share_config *ksmbd_share_config_get(struct ksmbd_work *work, const char *name); bool ksmbd_share_veto_filename(struct ksmbd_share_config *share, const char *filename); diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c index d2c81a8a11dd..94a52a75014a 100644 --- a/fs/smb/server/mgmt/tree_connect.c +++ b/fs/smb/server/mgmt/tree_connect.c @@ -16,17 +16,18 @@ #include "user_session.h" struct ksmbd_tree_conn_status -ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, - const char *share_name) +ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name) { struct ksmbd_tree_conn_status status = {-ENOENT, NULL}; struct ksmbd_tree_connect_response *resp = NULL; struct ksmbd_share_config *sc; struct ksmbd_tree_connect *tree_conn = NULL; struct sockaddr *peer_addr; + struct ksmbd_conn *conn = work->conn; + struct ksmbd_session *sess = work->sess; int ret; - sc = ksmbd_share_config_get(conn->um, share_name); + sc = ksmbd_share_config_get(work, share_name); if (!sc) return status; @@ -61,7 +62,7 @@ ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, struct ksmbd_share_config *new_sc; ksmbd_share_config_del(sc); - new_sc = ksmbd_share_config_get(conn->um, share_name); + new_sc = ksmbd_share_config_get(work, share_name); if (!new_sc) { pr_err("Failed to update stale share config\n"); status.ret = -ESTALE; diff --git a/fs/smb/server/mgmt/tree_connect.h b/fs/smb/server/mgmt/tree_connect.h index 6377a70b811c..a42cdd051041 100644 --- a/fs/smb/server/mgmt/tree_connect.h +++ b/fs/smb/server/mgmt/tree_connect.h @@ -13,6 +13,7 @@ struct ksmbd_share_config; struct ksmbd_user; struct ksmbd_conn; +struct ksmbd_work; enum { TREE_NEW = 0, @@ -50,8 +51,7 @@ static inline int test_tree_conn_flag(struct ksmbd_tree_connect *tree_conn, struct ksmbd_session; struct ksmbd_tree_conn_status -ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, - const char *share_name); +ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name); void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon); int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 37a39ab4ee65..54154d36ea2f 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1955,7 +1955,7 @@ int smb2_tree_connect(struct ksmbd_work *work) ksmbd_debug(SMB, "tree connect request for tree %s treename %s\n", name, treename); - status = ksmbd_tree_conn_connect(conn, sess, name); + status = ksmbd_tree_conn_connect(work, name); if (status.ret == KSMBD_TREE_CONN_STATUS_OK) rsp->hdr.Id.SyncId.TreeId = cpu_to_le32(status.tree_conn->id); else diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index 474dadf6b7b8..13818ecb6e1b 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -732,10 +732,10 @@ bool is_asterisk(char *p) return p && p[0] == '*'; } -int ksmbd_override_fsids(struct ksmbd_work *work) +int __ksmbd_override_fsids(struct ksmbd_work *work, + struct ksmbd_share_config *share) { struct ksmbd_session *sess = work->sess; - struct ksmbd_share_config *share = work->tcon->share_conf; struct cred *cred; struct group_info *gi; unsigned int uid; @@ -775,6 +775,11 @@ int ksmbd_override_fsids(struct ksmbd_work *work) return 0; } +int ksmbd_override_fsids(struct ksmbd_work *work) +{ + return __ksmbd_override_fsids(work, work->tcon->share_conf); +} + void ksmbd_revert_fsids(struct ksmbd_work *work) { const struct cred *cred; diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h index f1092519c0c2..4a3148b0167f 100644 --- a/fs/smb/server/smb_common.h +++ b/fs/smb/server/smb_common.h @@ -447,6 +447,8 @@ int ksmbd_extract_shortname(struct ksmbd_conn *conn, int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command); int ksmbd_smb_check_shared_mode(struct file *filp, struct ksmbd_file *curr_fp); +int __ksmbd_override_fsids(struct ksmbd_work *work, + struct ksmbd_share_config *share); int ksmbd_override_fsids(struct ksmbd_work *work); void ksmbd_revert_fsids(struct ksmbd_work *work); From f6bd41280a44dcc2e0a25ed72617d25f586974a7 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Mon, 5 Aug 2024 08:57:03 +0900 Subject: [PATCH 090/562] ksmbd: override fsids for smb2_query_info() Sangsoo reported that a DAC denial error occurred when accessing files through the ksmbd thread. This patch override fsids for smb2_query_info(). Reported-by: Sangsoo Lee Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 54154d36ea2f..2df1354288e6 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -5596,6 +5596,11 @@ int smb2_query_info(struct ksmbd_work *work) ksmbd_debug(SMB, "GOT query info request\n"); + if (ksmbd_override_fsids(work)) { + rc = -ENOMEM; + goto err_out; + } + switch (req->InfoType) { case SMB2_O_INFO_FILE: ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n"); @@ -5614,6 +5619,7 @@ int smb2_query_info(struct ksmbd_work *work) req->InfoType); rc = -EOPNOTSUPP; } + ksmbd_revert_fsids(work); if (!rc) { rsp->StructureSize = cpu_to_le16(9); @@ -5623,6 +5629,7 @@ int smb2_query_info(struct ksmbd_work *work) le32_to_cpu(rsp->OutputBufferLength)); } +err_out: if (rc < 0) { if (rc == -EACCES) rsp->hdr.Status = STATUS_ACCESS_DENIED; From e5876b088ba03a62124266fa20d00e65533c7269 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Tue, 6 Aug 2024 19:28:05 +0200 Subject: [PATCH 091/562] usbnet: ipheth: race between ipheth_close and error handling ipheth_sndbulk_callback() can submit carrier_work as a part of its error handling. That means that the driver must make sure that the work is cancelled after it has made sure that no more URB can terminate with an error condition. Hence the order of actions in ipheth_close() needs to be inverted. Signed-off-by: Oliver Neukum Signed-off-by: Foster Snowhill Tested-by: Georgi Valkov Signed-off-by: David S. Miller --- drivers/net/usb/ipheth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index 687d70cfc556..6eeef10edada 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -475,8 +475,8 @@ static int ipheth_close(struct net_device *net) { struct ipheth_device *dev = netdev_priv(net); - cancel_delayed_work_sync(&dev->carrier_work); netif_stop_queue(net); + cancel_delayed_work_sync(&dev->carrier_work); return 0; } From 655b46d7a39ac6f049698b27c1568c0f7ff85d1e Mon Sep 17 00:00:00 2001 From: Foster Snowhill Date: Tue, 6 Aug 2024 19:28:06 +0200 Subject: [PATCH 092/562] usbnet: ipheth: remove extraneous rx URB length check Rx URB length was already checked in ipheth_rcvbulk_callback_legacy() and ipheth_rcvbulk_callback_ncm(), depending on the current mode. The check in ipheth_rcvbulk_callback() was thus mostly a duplicate. The only place in ipheth_rcvbulk_callback() where we care about the URB length is for the initial control frame. These frames are always 4 bytes long. This has been checked as far back as iOS 4.2.1 on iPhone 3G. Remove the extraneous URB length check. For control frames, check for the specific 4-byte length instead. Signed-off-by: Foster Snowhill Tested-by: Georgi Valkov Signed-off-by: David S. Miller --- drivers/net/usb/ipheth.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index 6eeef10edada..017255615508 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -286,11 +286,6 @@ static void ipheth_rcvbulk_callback(struct urb *urb) return; } - if (urb->actual_length <= IPHETH_IP_ALIGN) { - dev->net->stats.rx_length_errors++; - return; - } - /* RX URBs starting with 0x00 0x01 do not encapsulate Ethernet frames, * but rather are control frames. Their purpose is not documented, and * they don't affect driver functionality, okay to drop them. @@ -298,7 +293,8 @@ static void ipheth_rcvbulk_callback(struct urb *urb) * URB received from the bulk IN endpoint. */ if (unlikely - (((char *)urb->transfer_buffer)[0] == 0 && + (urb->actual_length == 4 && + ((char *)urb->transfer_buffer)[0] == 0 && ((char *)urb->transfer_buffer)[1] == 1)) goto rx_submit; From 94d7eeb6c0ef0310992944f0d0296929816a2cb0 Mon Sep 17 00:00:00 2001 From: Foster Snowhill Date: Tue, 6 Aug 2024 19:28:07 +0200 Subject: [PATCH 093/562] usbnet: ipheth: drop RX URBs with no payload On iPhone 15 Pro Max one can observe periodic URBs with no payload on the "bulk in" (RX) endpoint. These don't seem to do anything meaningful. Reproduced on iOS 17.5.1 and 17.6. This behaviour isn't observed on iPhone 11 on the same iOS version. The nature of these zero-length URBs is so far unknown. Drop RX URBs with no payload. Signed-off-by: Foster Snowhill Signed-off-by: David S. Miller --- drivers/net/usb/ipheth.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index 017255615508..f04c7bf79665 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -286,6 +286,12 @@ static void ipheth_rcvbulk_callback(struct urb *urb) return; } + /* iPhone may periodically send URBs with no payload + * on the "bulk in" endpoint. It is safe to ignore them. + */ + if (urb->actual_length == 0) + goto rx_submit; + /* RX URBs starting with 0x00 0x01 do not encapsulate Ethernet frames, * but rather are control frames. Their purpose is not documented, and * they don't affect driver functionality, okay to drop them. From 74efed51e0a4d62f998f806c307778b47fc73395 Mon Sep 17 00:00:00 2001 From: Foster Snowhill Date: Tue, 6 Aug 2024 19:28:08 +0200 Subject: [PATCH 094/562] usbnet: ipheth: do not stop RX on failing RX callback RX callbacks can fail for multiple reasons: * Payload too short * Payload formatted incorrecly (e.g. bad NCM framing) * Lack of memory None of these should cause the driver to seize up. Make such failures non-critical and continue processing further incoming URBs. Signed-off-by: Foster Snowhill Signed-off-by: David S. Miller --- drivers/net/usb/ipheth.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index f04c7bf79665..cdc72559790a 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -308,7 +308,6 @@ static void ipheth_rcvbulk_callback(struct urb *urb) if (retval != 0) { dev_err(&dev->intf->dev, "%s: callback retval: %d\n", __func__, retval); - return; } rx_submit: From 67927a1b255d883881be9467508e0af9a5e0be9d Mon Sep 17 00:00:00 2001 From: Foster Snowhill Date: Tue, 6 Aug 2024 19:28:09 +0200 Subject: [PATCH 095/562] usbnet: ipheth: fix carrier detection in modes 1 and 4 Apart from the standard "configurations", "interfaces" and "alternate interface settings" in USB, iOS devices also have a notion of "modes". In different modes, the device exposes a different set of available configurations. Depending on the iOS version, and depending on the current mode, the length and contents of the carrier state control message differs: * 1 byte (seen on iOS 4.2.1, 8.4): * 03: carrier off (mode 0) * 04: carrier on (mode 0) * 3 bytes (seen on iOS 10.3.4, 15.7.6): * 03 03 03: carrier off (mode 0) * 04 04 03: carrier on (mode 0) * 4 bytes (seen on iOS 16.5, 17.6): * 03 03 03 00: carrier off (mode 0) * 04 03 03 00: carrier off (mode 1) * 06 03 03 00: carrier off (mode 4) * 04 04 03 04: carrier on (mode 0 and 1) * 06 04 03 04: carrier on (mode 4) Before this change, the driver always used the first byte of the response to determine carrier state. From this larger sample, the first byte seems to indicate the number of available USB configurations in the current mode (with the exception of the default mode 0), and in some cases (namely mode 1 and 4) does not correlate with the carrier state. Previous logic erroneously counted `04 03 03 00` as "carrier on" and `06 04 03 04` as "carrier off" on iOS versions that support mode 1 and mode 4 respectively. Only modes 0, 1 and 4 expose the USB Ethernet interfaces necessary for the ipheth driver. Check the second byte of the control message where possible, and fall back to checking the first byte on older iOS versions. Signed-off-by: Foster Snowhill Tested-by: Georgi Valkov Signed-off-by: David S. Miller --- drivers/net/usb/ipheth.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index cdc72559790a..46afb95ffabe 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -355,13 +355,14 @@ static int ipheth_carrier_set(struct ipheth_device *dev) 0x02, /* index */ dev->ctrl_buf, IPHETH_CTRL_BUF_SIZE, IPHETH_CTRL_TIMEOUT); - if (retval < 0) { + if (retval <= 0) { dev_err(&dev->intf->dev, "%s: usb_control_msg: %d\n", __func__, retval); return retval; } - if (dev->ctrl_buf[0] == IPHETH_CARRIER_ON) { + if ((retval == 1 && dev->ctrl_buf[0] == IPHETH_CARRIER_ON) || + (retval >= 2 && dev->ctrl_buf[1] == IPHETH_CARRIER_ON)) { netif_carrier_on(dev->net); if (dev->tx_urb->status != -EINPROGRESS) netif_wake_queue(dev->net); From d0949cd44a62c4c41b30ea7ae94d8c887f586882 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 8 Aug 2024 23:57:30 -0400 Subject: [PATCH 096/562] tracing: Return from tracing_buffers_read() if the file has been closed When running the following: # cd /sys/kernel/tracing/ # echo 1 > events/sched/sched_waking/enable # echo 1 > events/sched/sched_switch/enable # echo 0 > tracing_on # dd if=per_cpu/cpu0/trace_pipe_raw of=/tmp/raw0.dat The dd task would get stuck in an infinite loop in the kernel. What would happen is the following: When ring_buffer_read_page() returns -1 (no data) then a check is made to see if the buffer is empty (as happens when the page is not full), it will call wait_on_pipe() to wait until the ring buffer has data. When it is it will try again to read data (unless O_NONBLOCK is set). The issue happens when there's a reader and the file descriptor is closed. The wait_on_pipe() will return when that is the case. But this loop will continue to try again and wait_on_pipe() will again return immediately and the loop will continue and never stop. Simply check if the file was closed before looping and exit out if it is. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20240808235730.78bf63e5@rorschach.local.home Fixes: 2aa043a55b9a7 ("tracing/ring-buffer: Fix wait_on_pipe() race") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 10cd38bce2f1..ebe7ce2f5f4a 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7956,7 +7956,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, trace_access_unlock(iter->cpu_file); if (ret < 0) { - if (trace_empty(iter)) { + if (trace_empty(iter) && !iter->closed) { if ((filp->f_flags & O_NONBLOCK)) return -EAGAIN; From 90574d2a675947858b47008df8d07f75ea50d0d0 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 9 Aug 2024 15:34:30 +0300 Subject: [PATCH 097/562] rtla/osnoise: Prevent NULL dereference in error handling If the "tool->data" allocation fails then there is no need to call osnoise_free_top() and, in fact, doing so will lead to a NULL dereference. Cc: stable@vger.kernel.org Cc: John Kacur Cc: "Luis Claudio R. Goncalves" Cc: Clark Williams Fixes: 1eceb2fc2ca5 ("rtla/osnoise: Add osnoise top mode") Link: https://lore.kernel.org/f964ed1f-64d2-4fde-ad3e-708331f8f358@stanley.mountain Signed-off-by: Dan Carpenter Signed-off-by: Steven Rostedt (Google) --- tools/tracing/rtla/src/osnoise_top.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index f594a44df840..2f756628613d 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -651,8 +651,10 @@ struct osnoise_tool *osnoise_init_top(struct osnoise_top_params *params) return NULL; tool->data = osnoise_alloc_top(nr_cpus); - if (!tool->data) - goto out_err; + if (!tool->data) { + osnoise_destroy_tool(tool); + return NULL; + } tool->params = params; @@ -660,11 +662,6 @@ struct osnoise_tool *osnoise_init_top(struct osnoise_top_params *params) osnoise_top_handler, NULL); return tool; - -out_err: - osnoise_free_top(tool->data); - osnoise_destroy_tool(tool); - return NULL; } static int stop_tracing; From d5240fa65db071909e9d1d5adcc5fd1abc8e96fe Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Fri, 9 Aug 2024 11:11:55 +0800 Subject: [PATCH 098/562] nvdimm/pmem: Set dax flag for all 'PFN_MAP' cases The dax is only supported on pfn type pmem devices since commit f467fee48da4 ("block: move the dax flag to queue_limits"). Trying to mount DAX filesystem fails with this error: mount: : wrong fs type, bad option, bad superblock on /dev/pmem7, missing codepage or helper program, or other error. dmesg(1) may have more information after failed mount system call. dmesg: EXT4-fs (pmem7): DAX unsupported by block device. Fix the problem by adding dax flag setting for the missed case. Fixes: f467fee48da4 ("block: move the dax flag to queue_limits") Signed-off-by: Zhihao Cheng Reviewed-by: Christoph Hellwig Reviewed-by: Dave Jiang Reviewed-by: Ira Weiny Tested-by: Ira Weiny Tested-by: Alison Schofield Link: https://patch.msgid.link/20240809031155.2837271-1-chengzhihao1@huawei.com Signed-off-by: Ira Weiny --- drivers/nvdimm/pmem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 1ae8b2351654..210fb77f51ba 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -498,7 +498,7 @@ static int pmem_attach_disk(struct device *dev, } if (fua) lim.features |= BLK_FEAT_FUA; - if (is_nd_pfn(dev)) + if (is_nd_pfn(dev) || pmem_should_map_pages(dev)) lim.features |= BLK_FEAT_DAX; if (!devm_request_mem_region(dev, res->start, resource_size(res), From 869b5016e94eced02f2cf99bf53c69b49adcee32 Mon Sep 17 00:00:00 2001 From: Zehui Xu Date: Wed, 31 Jul 2024 16:43:46 +0300 Subject: [PATCH 099/562] kbuild: rust: skip -fmin-function-alignment in bindgen flags GCC 14 recently added -fmin-function-alignment option and the root Makefile uses it to replace -falign-functions when available. However, this flag can cause issues when passed to the Rust Makefile and affect the bindgen process. Bindgen relies on libclang to parse C code, and currently does not support the -fmin-function-alignment flag, leading to compilation failures when GCC 14 is used. This patch addresses the issue by adding -fmin-function-alignment to the bindgen_skip_c_flags in rust/Makefile. This prevents the flag from causing compilation issues. [ Matthew and Gary confirm function alignment should not change the ABI in a way that bindgen would care about, thus we did not need the extra logic for bindgen from v2. - Miguel ] Link: https://lore.kernel.org/linux-kbuild/20240222133500.16991-1-petr.pavlu@suse.com/ Signed-off-by: Zehui Xu Reviewed-by: Alice Ryhl Reviewed-by: Neal Gompa Reviewed-by: Gary Guo Link: https://lore.kernel.org/r/20240731134346.10630-1-zehuixu@whu.edu.cn [ Reworded title. - Miguel ] Signed-off-by: Miguel Ojeda --- rust/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/rust/Makefile b/rust/Makefile index 6c0644b6090c..c41bae7ca8a3 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -227,7 +227,7 @@ bindgen_skip_c_flags := -mno-fp-ret-in-387 -mpreferred-stack-boundary=% \ -fno-reorder-blocks -fno-allow-store-data-races -fasan-shadow-offset=% \ -fzero-call-used-regs=% -fno-stack-clash-protection \ -fno-inline-functions-called-once -fsanitize=bounds-strict \ - -fstrict-flex-arrays=% \ + -fstrict-flex-arrays=% -fmin-function-alignment=% \ --param=% --param asan-% # Derived from `scripts/Makefile.clang`. From 02dfd63afe65f7bacad543ba2b10f77083ae7929 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Tue, 6 Aug 2024 17:06:19 +0200 Subject: [PATCH 100/562] rust: add intrinsics to fix `-Os` builds Alice reported [1] that an arm64 build failed with: ld.lld: error: undefined symbol: __extendsfdf2 >>> referenced by core.a6f5fc5794e7b7b3-cgu.0 >>> rust/core.o:(::midpoint) in archive vmlinux.a >>> referenced by core.a6f5fc5794e7b7b3-cgu.0 >>> rust/core.o:(::midpoint) in archive vmlinux.a ld.lld: error: undefined symbol: __truncdfsf2 >>> referenced by core.a6f5fc5794e7b7b3-cgu.0 >>> rust/core.o:(::midpoint) in archive vmlinux.a Rust 1.80.0 or later together with `CONFIG_CC_OPTIMIZE_FOR_SIZE=y` is what triggers it. In addition, x86_64 builds also fail the same way. Similarly, compiling with Rust 1.82.0 (currently in nightly) makes another one appear, possibly due to the LLVM 19 upgrade there: ld.lld: error: undefined symbol: __eqdf2 >>> referenced by core.20495ea57a9f069d-cgu.0 >>> rust/core.o:(::next_up) in archive vmlinux.a >>> referenced by core.20495ea57a9f069d-cgu.0 >>> rust/core.o:(::next_down) in archive vmlinux.a Gary adds [1]: > Usually the fix on rustc side is to mark those functions as `#[inline]` > > All of {midpoint,next_up,next_down} are indeed unstable functions not > marked as inline... Fix all those by adding those intrinsics to our usual workaround. [ Trevor quickly submitted a fix to upstream Rust [2] that has already been merged, to be released in Rust 1.82.0 (2024-10-17). - Miguel ] Cc: Gary Guo Reported-by: Alice Ryhl Closes: https://rust-for-linux.zulipchat.com/#narrow/stream/x/topic/x/near/455637364 [1] Reviewed-by: Trevor Gross Tested-by: Alice Ryhl Tested-by: Boqun Feng Reviewed-by: Gary Guo Link: https://github.com/rust-lang/rust/pull/128749 [2] Link: https://lore.kernel.org/r/20240806150619.192882-1-ojeda@kernel.org [ Shortened Zulip link. - Miguel ] Signed-off-by: Miguel Ojeda --- rust/Makefile | 4 ++-- rust/compiler_builtins.rs | 3 +++ 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/rust/Makefile b/rust/Makefile index c41bae7ca8a3..8de3ebba9551 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -354,8 +354,8 @@ rust-analyzer: $(if $(KBUILD_EXTMOD),$(extmod_prefix),$(objtree))/rust-project.json redirect-intrinsics = \ - __addsf3 __eqsf2 __gesf2 __lesf2 __ltsf2 __mulsf3 __nesf2 __unordsf2 \ - __adddf3 __ledf2 __ltdf2 __muldf3 __unorddf2 \ + __addsf3 __eqsf2 __extendsfdf2 __gesf2 __lesf2 __ltsf2 __mulsf3 __nesf2 __truncdfsf2 __unordsf2 \ + __adddf3 __eqdf2 __ledf2 __ltdf2 __muldf3 __unorddf2 \ __muloti4 __multi3 \ __udivmodti4 __udivti3 __umodti3 diff --git a/rust/compiler_builtins.rs b/rust/compiler_builtins.rs index bba2922c6ef7..f14b8d7caf89 100644 --- a/rust/compiler_builtins.rs +++ b/rust/compiler_builtins.rs @@ -40,16 +40,19 @@ macro_rules! define_panicking_intrinsics( define_panicking_intrinsics!("`f32` should not be used", { __addsf3, __eqsf2, + __extendsfdf2, __gesf2, __lesf2, __ltsf2, __mulsf3, __nesf2, + __truncdfsf2, __unordsf2, }); define_panicking_intrinsics!("`f64` should not be used", { __adddf3, + __eqdf2, __ledf2, __ltdf2, __muldf3, From d734422b7dd7d033fc02e421924e70dabf665b4c Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Wed, 7 Aug 2024 01:35:59 +0200 Subject: [PATCH 101/562] kbuild: rust-analyzer: mark `rust_is_available.sh` invocation as recursive When calling the `rust_is_available.sh` script, we need to make the jobserver available to it, as commit ecab4115c44c ("kbuild: mark `rustc` (and others) invocations as recursive") explains and did for the others. Otherwise, we get a warning from `rustc` when calling `make rust-analyzer` with parallel jobs, e.g. `-j8`. Using several jobs for that target does not really matter, but developers may call `make` with jobs enabled in all cases. Thus fix it. Fixes: 6dc9d9ca9a72 ("kbuild: rust-analyzer: better error handling") Reviewed-by: Alice Ryhl Link: https://lore.kernel.org/r/20240806233559.246705-1-ojeda@kernel.org [ Reworded to add a couple more details mentioned in the list. - Miguel ] Signed-off-by: Miguel Ojeda --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 8ad55d6e7b60..8ed76eb9d438 100644 --- a/Makefile +++ b/Makefile @@ -1963,7 +1963,7 @@ tags TAGS cscope gtags: FORCE # Protocol). PHONY += rust-analyzer rust-analyzer: - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh + +$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh $(Q)$(MAKE) $(build)=rust $@ # Script to generate missing namespace dependencies From 0eba65f0310d3c7d5516c7fd4c172d0bfa8b285b Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Tue, 6 Aug 2024 16:45:58 +0200 Subject: [PATCH 102/562] rust: x86: remove `-3dnow{,a}` from target features LLVM 19 is dropping support for 3DNow! in commit f0eb5587ceeb ("Remove support for 3DNow!, both intrinsics and builtins. (#96246)"): Remove support for 3DNow!, both intrinsics and builtins. (#96246) This set of instructions was only supported by AMD chips starting in the K6-2 (introduced 1998), and before the "Bulldozer" family (2011). They were never much used, as they were effectively superseded by the more-widely-implemented SSE (first implemented on the AMD side in Athlon XP in 2001). This is being done as a predecessor towards general removal of MMX register usage. Since there is almost no usage of the 3DNow! intrinsics, and no modern hardware even implements them, simple removal seems like the best option. Thus we should avoid passing these to the backend, since otherwise we get a diagnostic about it: '-3dnow' is not a recognized feature for this target (ignoring feature) '-3dnowa' is not a recognized feature for this target (ignoring feature) We could try to disable them only up to LLVM 19 (not the C side one, but the one used by `rustc`, which may be built with a range of LLVMs). However, to avoid more complexity, we can likely just remove them altogether. According to Nikita [2]: > I don't think it's needed because LLVM should not generate 3dnow > instructions unless specifically asked to, using intrinsics that > Rust does not provide in the first place. Thus do so, like Rust did for one of their builtin targets [3]. For those curious: Clang will warn only about trying to enable them (`-m3dnow{,a}`), but not about disabling them (`-mno-3dnow{,a}`), so there is no change needed there. Cc: Nikita Popov Cc: Nathan Chancellor Cc: x86@kernel.org Link: https://github.com/llvm/llvm-project/commit/f0eb5587ceeb641445b64cb264c822b4751de04a [1] Link: https://github.com/rust-lang/rust/pull/127864#issuecomment-2235898760 [2] Link: https://github.com/rust-lang/rust/pull/127864 [3] Closes: https://github.com/Rust-for-Linux/linux/issues/1094 Tested-by: Benno Lossin Tested-by: Alice Ryhl Link: https://lore.kernel.org/r/20240806144558.114461-1-ojeda@kernel.org Signed-off-by: Miguel Ojeda --- scripts/generate_rust_target.rs | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs index 87f34925eb7b..404edf7587e0 100644 --- a/scripts/generate_rust_target.rs +++ b/scripts/generate_rust_target.rs @@ -162,7 +162,7 @@ fn main() { "data-layout", "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128", ); - let mut features = "-3dnow,-3dnowa,-mmx,+soft-float".to_string(); + let mut features = "-mmx,+soft-float".to_string(); if cfg.has("MITIGATION_RETPOLINE") { features += ",+retpoline-external-thunk"; } @@ -179,7 +179,7 @@ fn main() { "data-layout", "e-m:e-p:32:32-p270:32:32-p271:32:32-p272:64:64-i128:128-f64:32:64-f80:32-n8:16:32-S128", ); - let mut features = "-3dnow,-3dnowa,-mmx,+soft-float".to_string(); + let mut features = "-mmx,+soft-float".to_string(); if cfg.has("MITIGATION_RETPOLINE") { features += ",+retpoline-external-thunk"; } From 8c251c5ab1b7cd204231e4ee936bfe078a33f234 Mon Sep 17 00:00:00 2001 From: Li Ming Date: Fri, 9 Aug 2024 08:27:49 +0000 Subject: [PATCH 103/562] cxl/pci: Get AER capability address from RCRB only for RCH dport cxl_setup_parent_dport() needs to get RCH dport AER capability address from RCRB to disable AER interrupt. The function does not check if dport is RCH dport, it will get a wrong pci_host_bridge structure by dport_dev in VH case because dport_dev points to a pci device(RP or switch DSP) rather than a pci host bridge device. Fixes: f05fd10d138d ("cxl/pci: Add RCH downstream port AER register discovery") Signed-off-by: Li Ming Reviewed-by: Dan Williams Reviewed-by: Ira Weiny Tested-by: Ira Weiny Tested-by: Alison Schofield Link: https://patch.msgid.link/20240809082750.3015641-2-ming4.li@intel.com Signed-off-by: Dave Jiang --- drivers/cxl/core/pci.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index a663e7566c48..51132a575b27 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -834,11 +834,13 @@ static void cxl_disable_rch_root_ints(struct cxl_dport *dport) void cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport) { struct device *dport_dev = dport->dport_dev; - struct pci_host_bridge *host_bridge; - host_bridge = to_pci_host_bridge(dport_dev); - if (host_bridge->native_aer) - dport->rcrb.aer_cap = cxl_rcrb_to_aer(dport_dev, dport->rcrb.base); + if (dport->rch) { + struct pci_host_bridge *host_bridge = to_pci_host_bridge(dport_dev); + + if (host_bridge->native_aer) + dport->rcrb.aer_cap = cxl_rcrb_to_aer(dport_dev, dport->rcrb.base); + } dport->reg_map.host = host; cxl_dport_map_regs(dport); From 2c402bd2e85b44dc00ef85b5c0e217de684b5372 Mon Sep 17 00:00:00 2001 From: Li Ming Date: Fri, 9 Aug 2024 08:27:50 +0000 Subject: [PATCH 104/562] cxl/test: Skip cxl_setup_parent_dport() for emulated dports The cxl_test unit test environment on qemu always hits below call trace with KASAN enabled: BUG: KASAN: slab-out-of-bounds in cxl_setup_parent_dport+0x480/0x530 [cxl_core] Read of size 1 at addr ff110000676014f8 by task (udev-worker)/676[ 24.424403] CPU: 2 PID: 676 Comm: (udev-worker) Tainted: G O N 6.10.0-qemucxl #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS edk2-20240214-2.el9 02/14/2024 Call Trace: dump_stack_lvl+0xea/0x150 print_report+0xce/0x610 ? kasan_complete_mode_report_info+0x40/0x200 kasan_report+0xcc/0x110 __asan_report_load1_noabort+0x18/0x20 cxl_setup_parent_dport+0x480/0x530 [cxl_core] cxl_mem_probe+0x49b/0xaa0 [cxl_mem] cxl_test module models a CXL topology for testing, it creates some emulated dports with platform devices in the CXL topology, so the dport_dev of an emulated dport points to a platform device rather than a pci device or a pci host bridge in the case. Currently, cxl_setup_parent_dport() is used to set up RAS and AER capability on the dport connected to the CXL memory device, but cxl_test does not support RAS or AER functionality yet, so the fix is implementing a __wrap_cxl_setup_parent_dport() to filter out all emulated dports, guarantees only real dports can be handled by cxl_setup_parent_dport(). Fixes: f05fd10d138d ("cxl/pci: Add RCH downstream port AER register discovery") Reported-by: Pengfei Xu Closes: https://lore.kernel.org/linux-cxl/ZrHTBp2O+HtUe6kt@xpf.sh.intel.com/T/#t Signed-off-by: Li Ming Reviewed-by: Dan Williams Reviewed-by: Ira Weiny Reviewed-by: Alison Schofield Tested-by: Ira Weiny Tested-by: Alison Schofield Link: https://patch.msgid.link/20240809082750.3015641-3-ming4.li@intel.com Signed-off-by: Dave Jiang --- tools/testing/cxl/Kbuild | 1 + tools/testing/cxl/test/mock.c | 12 ++++++++++++ 2 files changed, 13 insertions(+) diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index 030b388800f0..3d1ca9e38b1f 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -14,6 +14,7 @@ ldflags-y += --wrap=cxl_dvsec_rr_decode ldflags-y += --wrap=devm_cxl_add_rch_dport ldflags-y += --wrap=cxl_rcd_component_reg_phys ldflags-y += --wrap=cxl_endpoint_parse_cdat +ldflags-y += --wrap=cxl_setup_parent_dport DRIVERS := ../../../drivers CXL_SRC := $(DRIVERS)/cxl diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index 6f737941dc0e..d619672faa49 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -299,6 +299,18 @@ void __wrap_cxl_endpoint_parse_cdat(struct cxl_port *port) } EXPORT_SYMBOL_NS_GPL(__wrap_cxl_endpoint_parse_cdat, CXL); +void __wrap_cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport) +{ + int index; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (!ops || !ops->is_mock_port(dport->dport_dev)) + cxl_setup_parent_dport(host, dport); + + put_cxl_mock_ops(index); +} +EXPORT_SYMBOL_NS_GPL(__wrap_cxl_setup_parent_dport, CXL); + MODULE_LICENSE("GPL v2"); MODULE_IMPORT_NS(ACPI); MODULE_IMPORT_NS(CXL); From 4bbe6002931954bbe82b25f25990b987b0392e18 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 18 Jul 2024 16:38:07 -0300 Subject: [PATCH 105/562] perf daemon: Fix the build on 32-bit architectures Noticed with: 1 6.22 debian:experimental-x-mipsel : FAIL gcc version 13.2.0 (Debian 13.2.0-25) builtin-daemon.c: In function 'cmd_session_list': builtin-daemon.c:691:35: error: format '%lu' expects argument of type 'long unsigned int', but argument 4 has type 'time_t' {aka 'long long int'} [-Werror=format=] Use inttypes.h's PRIu64 to deal with that. Signed-off-by: Arnaldo Carvalho de Melo Link: https://lore.kernel.org/r/ZplvH21aQ8pzmza_@x1 Signed-off-by: Namhyung Kim --- tools/perf/builtin-daemon.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c index de76bbc50bfb..5c9335fff2d3 100644 --- a/tools/perf/builtin-daemon.c +++ b/tools/perf/builtin-daemon.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #include #include @@ -688,7 +689,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out) /* lock */ csv_sep, daemon->base, "lock"); - fprintf(out, "%c%lu", + fprintf(out, "%c%" PRIu64, /* session up time */ csv_sep, (curr - daemon->start) / 60); @@ -700,7 +701,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out) daemon->base, SESSION_OUTPUT); fprintf(out, " lock: %s/lock\n", daemon->base); - fprintf(out, " up: %lu minutes\n", + fprintf(out, " up: %" PRIu64 " minutes\n", (curr - daemon->start) / 60); } } @@ -727,7 +728,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out) /* session ack */ csv_sep, session->base, SESSION_ACK); - fprintf(out, "%c%lu", + fprintf(out, "%c%" PRIu64, /* session up time */ csv_sep, (curr - session->start) / 60); @@ -745,7 +746,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out) session->base, SESSION_CONTROL); fprintf(out, " ack: %s/%s\n", session->base, SESSION_ACK); - fprintf(out, " up: %lu minutes\n", + fprintf(out, " up: %" PRIu64 " minutes\n", (curr - session->start) / 60); } } From 3eb3cd5992f7a0c37edc8d05b4c38c98758d8671 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 7 Aug 2024 12:51:23 -0700 Subject: [PATCH 106/562] binfmt_flat: Fix corruption when not offsetting data start Commit 04d82a6d0881 ("binfmt_flat: allow not offsetting data start") introduced a RISC-V specific variant of the FLAT format which does not allocate any space for the (obsolete) array of shared library pointers. However, it did not disable the code which initializes the array, resulting in the corruption of sizeof(long) bytes before the DATA segment, generally the end of the TEXT segment. Introduce MAX_SHARED_LIBS_UPDATE which depends on the state of CONFIG_BINFMT_FLAT_NO_DATA_START_OFFSET to guard the initialization of the shared library pointer region so that it will only be initialized if space is reserved for it. Fixes: 04d82a6d0881 ("binfmt_flat: allow not offsetting data start") Co-developed-by: Stefan O'Rear Signed-off-by: Stefan O'Rear Reviewed-by: Damien Le Moal Acked-by: Greg Ungerer Link: https://lore.kernel.org/r/20240807195119.it.782-kees@kernel.org Signed-off-by: Kees Cook --- fs/binfmt_flat.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index c26545d71d39..cd6d5bbb4b9d 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -72,8 +72,10 @@ #ifdef CONFIG_BINFMT_FLAT_NO_DATA_START_OFFSET #define DATA_START_OFFSET_WORDS (0) +#define MAX_SHARED_LIBS_UPDATE (0) #else #define DATA_START_OFFSET_WORDS (MAX_SHARED_LIBS) +#define MAX_SHARED_LIBS_UPDATE (MAX_SHARED_LIBS) #endif struct lib_info { @@ -880,7 +882,7 @@ static int load_flat_binary(struct linux_binprm *bprm) return res; /* Update data segment pointers for all libraries */ - for (i = 0; i < MAX_SHARED_LIBS; i++) { + for (i = 0; i < MAX_SHARED_LIBS_UPDATE; i++) { if (!libinfo.lib_list[i].loaded) continue; for (j = 0; j < MAX_SHARED_LIBS; j++) { From 3a3be7ff9224f424e485287b54be00d2c6bd9c40 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Aug 2024 13:24:55 +0000 Subject: [PATCH 107/562] gtp: pull network headers in gtp_dev_xmit() syzbot/KMSAN reported use of uninit-value in get_dev_xmit() [1] We must make sure the IPv4 or Ipv6 header is pulled in skb->head before accessing fields in them. Use pskb_inet_may_pull() to fix this issue. [1] BUG: KMSAN: uninit-value in ipv6_pdp_find drivers/net/gtp.c:220 [inline] BUG: KMSAN: uninit-value in gtp_build_skb_ip6 drivers/net/gtp.c:1229 [inline] BUG: KMSAN: uninit-value in gtp_dev_xmit+0x1424/0x2540 drivers/net/gtp.c:1281 ipv6_pdp_find drivers/net/gtp.c:220 [inline] gtp_build_skb_ip6 drivers/net/gtp.c:1229 [inline] gtp_dev_xmit+0x1424/0x2540 drivers/net/gtp.c:1281 __netdev_start_xmit include/linux/netdevice.h:4913 [inline] netdev_start_xmit include/linux/netdevice.h:4922 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x247/0xa20 net/core/dev.c:3596 __dev_queue_xmit+0x358c/0x5610 net/core/dev.c:4423 dev_queue_xmit include/linux/netdevice.h:3105 [inline] packet_xmit+0x9c/0x6c0 net/packet/af_packet.c:276 packet_snd net/packet/af_packet.c:3145 [inline] packet_sendmsg+0x90e3/0xa3a0 net/packet/af_packet.c:3177 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x30f/0x380 net/socket.c:745 __sys_sendto+0x685/0x830 net/socket.c:2204 __do_sys_sendto net/socket.c:2216 [inline] __se_sys_sendto net/socket.c:2212 [inline] __x64_sys_sendto+0x125/0x1d0 net/socket.c:2212 x64_sys_call+0x3799/0x3c10 arch/x86/include/generated/asm/syscalls_64.h:45 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x1e0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f Uninit was created at: slab_post_alloc_hook mm/slub.c:3994 [inline] slab_alloc_node mm/slub.c:4037 [inline] kmem_cache_alloc_node_noprof+0x6bf/0xb80 mm/slub.c:4080 kmalloc_reserve+0x13d/0x4a0 net/core/skbuff.c:583 __alloc_skb+0x363/0x7b0 net/core/skbuff.c:674 alloc_skb include/linux/skbuff.h:1320 [inline] alloc_skb_with_frags+0xc8/0xbf0 net/core/skbuff.c:6526 sock_alloc_send_pskb+0xa81/0xbf0 net/core/sock.c:2815 packet_alloc_skb net/packet/af_packet.c:2994 [inline] packet_snd net/packet/af_packet.c:3088 [inline] packet_sendmsg+0x749c/0xa3a0 net/packet/af_packet.c:3177 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x30f/0x380 net/socket.c:745 __sys_sendto+0x685/0x830 net/socket.c:2204 __do_sys_sendto net/socket.c:2216 [inline] __se_sys_sendto net/socket.c:2212 [inline] __x64_sys_sendto+0x125/0x1d0 net/socket.c:2212 x64_sys_call+0x3799/0x3c10 arch/x86/include/generated/asm/syscalls_64.h:45 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x1e0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f CPU: 0 UID: 0 PID: 7115 Comm: syz.1.515 Not tainted 6.11.0-rc1-syzkaller-00043-g94ede2a3e913 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 06/27/2024 Fixes: 999cb275c807 ("gtp: add IPv6 support") Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)") Signed-off-by: Eric Dumazet Cc: Harald Welte Reviewed-by: Pablo Neira Ayuso Link: https://patch.msgid.link/20240808132455.3413916-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- drivers/net/gtp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 427b91aca50d..0696faf60013 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1269,6 +1269,9 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) if (skb_cow_head(skb, dev->needed_headroom)) goto tx_err; + if (!pskb_inet_may_pull(skb)) + goto tx_err; + skb_reset_inner_headers(skb); /* PDP context lookups in gtp_build_skb_*() need rcu read-side lock. */ From 2b2bc3bab158b7e036508742b16cd8a3c2f59a12 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Thu, 8 Aug 2024 11:56:21 +0200 Subject: [PATCH 108/562] net: Make USO depend on CSUM offload UDP segmentation offload inherently depends on checksum offload. It should not be possible to disable checksum offload while leaving USO enabled. Enforce this dependency in code. There is a single tx-udp-segmentation feature flag to indicate support for both IPv4/6, hence the devices wishing to support USO must offer checksum offload for both IP versions. Fixes: 10154dbded6d ("udp: Allow GSO transmit from devices with no checksum offload") Suggested-by: Willem de Bruijn Signed-off-by: Jakub Sitnicki Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20240808-udp-gso-egress-from-tunnel-v4-1-f5c5b4149ab9@cloudflare.com Signed-off-by: Jakub Kicinski --- net/core/dev.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 751d9b70e6ad..f66e61407883 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9912,6 +9912,15 @@ static void netdev_sync_lower_features(struct net_device *upper, } } +static bool netdev_has_ip_or_hw_csum(netdev_features_t features) +{ + netdev_features_t ip_csum_mask = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + bool ip_csum = (features & ip_csum_mask) == ip_csum_mask; + bool hw_csum = features & NETIF_F_HW_CSUM; + + return ip_csum || hw_csum; +} + static netdev_features_t netdev_fix_features(struct net_device *dev, netdev_features_t features) { @@ -9993,15 +10002,9 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~NETIF_F_LRO; } - if (features & NETIF_F_HW_TLS_TX) { - bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) == - (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - bool hw_csum = features & NETIF_F_HW_CSUM; - - if (!ip_csum && !hw_csum) { - netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); - features &= ~NETIF_F_HW_TLS_TX; - } + if ((features & NETIF_F_HW_TLS_TX) && !netdev_has_ip_or_hw_csum(features)) { + netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); + features &= ~NETIF_F_HW_TLS_TX; } if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) { @@ -10009,6 +10012,11 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~NETIF_F_HW_TLS_RX; } + if ((features & NETIF_F_GSO_UDP_L4) && !netdev_has_ip_or_hw_csum(features)) { + netdev_dbg(dev, "Dropping USO feature since no CSUM feature.\n"); + features &= ~NETIF_F_GSO_UDP_L4; + } + return features; } From 30b03f2a0592eee1267298298eac9dd655f55ab2 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Thu, 8 Aug 2024 11:56:22 +0200 Subject: [PATCH 109/562] udp: Fall back to software USO if IPv6 extension headers are present In commit 10154dbded6d ("udp: Allow GSO transmit from devices with no checksum offload") we have intentionally allowed UDP GSO packets marked CHECKSUM_NONE to pass to the GSO stack, so that they can be segmented and checksummed by a software fallback when the egress device lacks these features. What was not taken into consideration is that a CHECKSUM_NONE skb can be handed over to the GSO stack also when the egress device advertises the tx-udp-segmentation / NETIF_F_GSO_UDP_L4 feature. This will happen when there are IPv6 extension headers present, which we check for in __ip6_append_data(). Syzbot has discovered this scenario, producing a warning as below: ip6tnl0: caps=(0x00000006401d7869, 0x00000006401d7869) WARNING: CPU: 0 PID: 5112 at net/core/dev.c:3293 skb_warn_bad_offload+0x166/0x1a0 net/core/dev.c:3291 Modules linked in: CPU: 0 PID: 5112 Comm: syz-executor391 Not tainted 6.10.0-rc7-syzkaller-01603-g80ab5445da62 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 06/07/2024 RIP: 0010:skb_warn_bad_offload+0x166/0x1a0 net/core/dev.c:3291 [...] Call Trace: __skb_gso_segment+0x3be/0x4c0 net/core/gso.c:127 skb_gso_segment include/net/gso.h:83 [inline] validate_xmit_skb+0x585/0x1120 net/core/dev.c:3661 __dev_queue_xmit+0x17a4/0x3e90 net/core/dev.c:4415 neigh_output include/net/neighbour.h:542 [inline] ip6_finish_output2+0xffa/0x1680 net/ipv6/ip6_output.c:137 ip6_finish_output+0x41e/0x810 net/ipv6/ip6_output.c:222 ip6_send_skb+0x112/0x230 net/ipv6/ip6_output.c:1958 udp_v6_send_skb+0xbf5/0x1870 net/ipv6/udp.c:1292 udpv6_sendmsg+0x23b3/0x3270 net/ipv6/udp.c:1588 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0xef/0x270 net/socket.c:745 ____sys_sendmsg+0x525/0x7d0 net/socket.c:2585 ___sys_sendmsg net/socket.c:2639 [inline] __sys_sendmmsg+0x3b2/0x740 net/socket.c:2725 __do_sys_sendmmsg net/socket.c:2754 [inline] __se_sys_sendmmsg net/socket.c:2751 [inline] __x64_sys_sendmmsg+0xa0/0xb0 net/socket.c:2751 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f [...] We are hitting the bad offload warning because when an egress device is capable of handling segmentation offload requested by skb_shinfo(skb)->gso_type, the chain of gso_segment callbacks won't produce any segment skbs and return NULL. See the skb_gso_ok() branch in {__udp,tcp,sctp}_gso_segment helpers. To fix it, force a fallback to software USO when processing a packet with IPv6 extension headers, since we don't know if these can checksummed by all devices which offer USO. Fixes: 10154dbded6d ("udp: Allow GSO transmit from devices with no checksum offload") Reported-by: syzbot+e15b7e15b8a751a91d9a@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/000000000000e1609a061d5330ce@google.com/ Reviewed-by: Willem de Bruijn Signed-off-by: Jakub Sitnicki Link: https://patch.msgid.link/20240808-udp-gso-egress-from-tunnel-v4-2-f5c5b4149ab9@cloudflare.com Signed-off-by: Jakub Kicinski --- net/ipv4/udp_offload.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index bc8a9da750fe..b254a5dadfcf 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -282,6 +282,12 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, skb_transport_header(gso_skb))) return ERR_PTR(-EINVAL); + /* We don't know if egress device can segment and checksum the packet + * when IPv6 extension headers are present. Fall back to software GSO. + */ + if (gso_skb->ip_summed != CHECKSUM_PARTIAL) + features &= ~(NETIF_F_GSO_UDP_L4 | NETIF_F_CSUM_MASK); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), From 1d2c46c1bc5680335f20f64089c161fdfcd3e8ab Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Thu, 8 Aug 2024 11:56:23 +0200 Subject: [PATCH 110/562] selftests/net: Add coverage for UDP GSO with IPv6 extension headers After enabling UDP GSO for devices not offering checksum offload, we have hit a regression where a bad offload warning can be triggered when sending a datagram with IPv6 extension headers. Extend the UDP GSO IPv6 tests to cover this scenario. Reviewed-by: Willem de Bruijn Signed-off-by: Jakub Sitnicki Link: https://patch.msgid.link/20240808-udp-gso-egress-from-tunnel-v4-3-f5c5b4149ab9@cloudflare.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/udpgso.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 3e74cfa1a2bf..3f2fca02fec5 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -67,6 +67,7 @@ struct testcase { int gso_len; /* mss after applying gso */ int r_num_mss; /* recv(): number of calls of full mss */ int r_len_last; /* recv(): size of last non-mss dgram, if any */ + bool v6_ext_hdr; /* send() dgrams with IPv6 extension headers */ }; const struct in6_addr addr6 = { @@ -77,6 +78,8 @@ const struct in_addr addr4 = { __constant_htonl(0x0a000001), /* 10.0.0.1 */ }; +static const char ipv6_hopopts_pad1[8] = { 0 }; + struct testcase testcases_v4[] = { { /* no GSO: send a single byte */ @@ -255,6 +258,13 @@ struct testcase testcases_v6[] = { .gso_len = 1, .r_num_mss = 2, }, + { + /* send 2 1B segments with extension headers */ + .tlen = 2, + .gso_len = 1, + .r_num_mss = 2, + .v6_ext_hdr = true, + }, { /* send 2B + 2B + 1B segments */ .tlen = 5, @@ -396,11 +406,18 @@ static void run_one(struct testcase *test, int fdt, int fdr, int i, ret, val, mss; bool sent; - fprintf(stderr, "ipv%d tx:%d gso:%d %s\n", + fprintf(stderr, "ipv%d tx:%d gso:%d %s%s\n", addr->sa_family == AF_INET ? 4 : 6, test->tlen, test->gso_len, + test->v6_ext_hdr ? "ext-hdr " : "", test->tfail ? "(fail)" : ""); + if (test->v6_ext_hdr) { + if (setsockopt(fdt, IPPROTO_IPV6, IPV6_HOPOPTS, + ipv6_hopopts_pad1, sizeof(ipv6_hopopts_pad1))) + error(1, errno, "setsockopt ipv6 hopopts"); + } + val = test->gso_len; if (cfg_do_setsockopt) { if (setsockopt(fdt, SOL_UDP, UDP_SEGMENT, &val, sizeof(val))) @@ -412,6 +429,12 @@ static void run_one(struct testcase *test, int fdt, int fdr, error(1, 0, "send succeeded while expecting failure"); if (!sent && !test->tfail) error(1, 0, "send failed while expecting success"); + + if (test->v6_ext_hdr) { + if (setsockopt(fdt, IPPROTO_IPV6, IPV6_HOPOPTS, NULL, 0)) + error(1, errno, "setsockopt ipv6 hopopts clear"); + } + if (!sent) return; From c31fe2b5095d8c84562ce90db07600f7e9f318df Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Thu, 8 Aug 2024 17:41:02 +0300 Subject: [PATCH 111/562] net/mlx5: SD, Do not query MPIR register if no sd_group Unconditionally calling the MPIR query on BF separate mode yields the FW syndrome below [1]. Do not call it unless admin clearly specified the SD group, i.e. expressing the intention of using the multi-PF netdev feature. This fix covers cases not covered in commit fca3b4791850 ("net/mlx5: Do not query MPIR on embedded CPU function"). [1] mlx5_cmd_out_err:808:(pid 8267): ACCESS_REG(0x805) op_mod(0x1) failed, status bad system state(0x4), syndrome (0x685f19), err(-5) Fixes: 678eb448055a ("net/mlx5: SD, Implement basic query and instantiation") Signed-off-by: Tariq Toukan Reviewed-by: Gal Pressman Link: https://patch.msgid.link/20240808144107.2095424-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/mellanox/mlx5/core/lib/sd.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index f6deb5a3f820..eeb0b7ea05f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -126,7 +126,7 @@ static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses) } static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm, - u8 *host_buses, u8 *sd_group) + u8 *host_buses) { u32 out[MLX5_ST_SZ_DW(mpir_reg)]; int err; @@ -135,10 +135,6 @@ static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm, if (err) return err; - err = mlx5_query_nic_vport_sd_group(dev, sd_group); - if (err) - return err; - *sdm = MLX5_GET(mpir_reg, out, sdm); *host_buses = MLX5_GET(mpir_reg, out, host_buses); @@ -166,19 +162,23 @@ static int sd_init(struct mlx5_core_dev *dev) if (mlx5_core_is_ecpf(dev)) return 0; + err = mlx5_query_nic_vport_sd_group(dev, &sd_group); + if (err) + return err; + + if (!sd_group) + return 0; + if (!MLX5_CAP_MCAM_REG(dev, mpir)) return 0; - err = mlx5_query_sd(dev, &sdm, &host_buses, &sd_group); + err = mlx5_query_sd(dev, &sdm, &host_buses); if (err) return err; if (!sdm) return 0; - if (!sd_group) - return 0; - group_id = mlx5_sd_group_id(dev, sd_group); if (!mlx5_sd_is_supported(dev, host_buses)) { From ab6013a59b4d0947fda409c29426dc904959e632 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Thu, 8 Aug 2024 17:41:03 +0300 Subject: [PATCH 112/562] net/mlx5e: SHAMPO, Increase timeout to improve latency During latency tests (netperf TCP_RR) a 30% degradation of HW GRO vs SW GRO was observed. This is due to SHAMPO triggering timeout filler CQEs instead of delivering the CQE for the packet. Having a short timeout for SHAMPO doesn't bring any benefits as it is the driver that does the merging, not the hardware. On the contrary, it can have a negative impact: additional filler CQEs are generated due to the timeout. As there is no way to disable this timeout, this change sets it to the maximum value. Instead of using the packet_merge.timeout parameter which is also used for LRO, set the value directly when filling in the rest of the SHAMPO parameters in mlx5e_build_rq_param(). Fixes: 99be56171fa9 ("net/mlx5e: SHAMPO, Re-enable HW-GRO") Signed-off-by: Dragos Tatulea Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240808144107.2095424-3-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +- .../net/ethernet/mellanox/mlx5/core/en/params.c | 16 +++++++++++++++- .../net/ethernet/mellanox/mlx5/core/en/params.h | 1 + .../net/ethernet/mellanox/mlx5/core/en_main.c | 12 ------------ 4 files changed, 17 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 5fd82c67b6ab..bb5da42edc23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -130,7 +130,7 @@ struct page_pool; #define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW 0x2 #define MLX5E_DEFAULT_LRO_TIMEOUT 32 -#define MLX5E_LRO_TIMEOUT_ARR_SIZE 4 +#define MLX5E_DEFAULT_SHAMPO_TIMEOUT 1024 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC 0x10 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE 0x3 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 6c9ccccca81e..64b62ed17b07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -928,7 +928,7 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, MLX5_SET(wq, wq, log_headers_entry_size, mlx5e_shampo_get_log_hd_entry_size(mdev, params)); MLX5_SET(rqc, rqc, reservation_timeout, - params->packet_merge.timeout); + mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_SHAMPO_TIMEOUT)); MLX5_SET(rqc, rqc, shampo_match_criteria_type, params->packet_merge.shampo.match_criteria_type); MLX5_SET(rqc, rqc, shampo_no_match_alignment_granularity, @@ -1087,6 +1087,20 @@ static u32 mlx5e_shampo_icosq_sz(struct mlx5_core_dev *mdev, return wqebbs; } +#define MLX5E_LRO_TIMEOUT_ARR_SIZE 4 + +u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) +{ + int i; + + /* The supported periods are organized in ascending order */ + for (i = 0; i < MLX5E_LRO_TIMEOUT_ARR_SIZE - 1; i++) + if (MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]) >= wanted_timeout) + break; + + return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]); +} + static u32 mlx5e_mpwrq_total_umr_wqebbs(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index 749b2ec0436e..3f8986f9d862 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -108,6 +108,7 @@ u32 mlx5e_shampo_hd_per_wqe(struct mlx5_core_dev *mdev, u32 mlx5e_shampo_hd_per_wq(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_rq_param *rq_param); +u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout); u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 6f686fabed44..f04decca39f2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5167,18 +5167,6 @@ const struct net_device_ops mlx5e_netdev_ops = { #endif }; -static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) -{ - int i; - - /* The supported periods are organized in ascending order */ - for (i = 0; i < MLX5E_LRO_TIMEOUT_ARR_SIZE - 1; i++) - if (MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]) >= wanted_timeout) - break; - - return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]); -} - void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu) { struct mlx5e_params *params = &priv->channels.params; From e6b5afd30b99b43682a7764e1a74a42fe4d5f4b3 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Thu, 8 Aug 2024 17:41:04 +0300 Subject: [PATCH 113/562] net/mlx5e: Take state lock during tx timeout reporter mlx5e_safe_reopen_channels() requires the state lock taken. The referenced changed in the Fixes tag removed the lock to fix another issue. This patch adds it back but at a later point (when calling mlx5e_safe_reopen_channels()) to avoid the deadlock referenced in the Fixes tag. Fixes: eab0da38912e ("net/mlx5e: Fix possible deadlock on mlx5e_tx_timeout_work") Signed-off-by: Dragos Tatulea Link: https://lore.kernel.org/all/ZplpKq8FKi3vwfxv@gmail.com/T/ Reviewed-by: Breno Leitao Reviewed-by: Moshe Shemesh Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240808144107.2095424-4-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 22918b2ef7f1..09433b91be17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -146,7 +146,9 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) return err; } + mutex_lock(&priv->state_lock); err = mlx5e_safe_reopen_channels(priv); + mutex_unlock(&priv->state_lock); if (!err) { to_ctx->status = 1; /* all channels recovered */ return err; From cbc796be1779c4dbc9a482c7233995e2a8b6bfb3 Mon Sep 17 00:00:00 2001 From: Cosmin Ratiu Date: Thu, 8 Aug 2024 17:41:05 +0300 Subject: [PATCH 114/562] net/mlx5e: Correctly report errors for ethtool rx flows Previously, an ethtool rx flow with no attrs would not be added to the NIC as it has no rules to configure the hw with, but it would be reported as successful to the caller (return code 0). This is confusing for the user as ethtool then reports "Added rule $num", but no rule was actually added. This change corrects that by instead reporting these wrong rules as -EINVAL. Fixes: b29c61dac3a2 ("net/mlx5e: Ethtool steering flow validation refactoring") Signed-off-by: Cosmin Ratiu Reviewed-by: Saeed Mahameed Reviewed-by: Dragos Tatulea Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240808144107.2095424-5-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 3eccdadc0357..773624bb2c5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -734,7 +734,7 @@ mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv, if (num_tuples <= 0) { netdev_warn(priv->netdev, "%s: flow is not valid %d\n", __func__, num_tuples); - return num_tuples; + return num_tuples < 0 ? num_tuples : -EINVAL; } eth_ft = get_flow_table(priv, fs, num_tuples); From 0b4a4534d083e055831b3bc29c5eafc918ed4d86 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 8 Aug 2024 17:41:06 +0300 Subject: [PATCH 115/562] net/mlx5e: Fix queue stats access to non-existing channels splat The queue stats API queries the queues according to the real_num_[tr]x_queues, in case the device is down and channels were not yet created, don't try to query their statistics. To trigger the panic, run this command before the interface is brought up: ./cli.py --spec ../../../Documentation/netlink/specs/netdev.yaml --dump qstats-get --json '{"ifindex": 4}' BUG: kernel NULL pointer dereference, address: 0000000000000c00 PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP PTI CPU: 3 UID: 0 PID: 977 Comm: python3 Not tainted 6.10.0+ #40 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:mlx5e_get_queue_stats_rx+0x3c/0xb0 [mlx5_core] Code: fc 55 48 63 ee 53 48 89 d3 e8 40 3d 70 e1 85 c0 74 58 4c 89 ef e8 d4 07 04 00 84 c0 75 41 49 8b 84 24 f8 39 00 00 48 8b 04 e8 <48> 8b 90 00 0c 00 00 48 03 90 40 0a 00 00 48 89 53 08 48 8b 90 08 RSP: 0018:ffff888116be37d0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff888116be3868 RCX: 0000000000000004 RDX: ffff88810ada4000 RSI: 0000000000000000 RDI: ffff888109df09c0 RBP: 0000000000000000 R08: 0000000000000004 R09: 0000000000000004 R10: ffff88813461901c R11: ffffffffffffffff R12: ffff888109df0000 R13: ffff888109df09c0 R14: ffff888116be38d0 R15: 0000000000000000 FS: 00007f4375d5c740(0000) GS:ffff88852c980000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000c00 CR3: 0000000106ada006 CR4: 0000000000370eb0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? __die+0x1f/0x60 ? page_fault_oops+0x14e/0x3d0 ? exc_page_fault+0x73/0x130 ? asm_exc_page_fault+0x22/0x30 ? mlx5e_get_queue_stats_rx+0x3c/0xb0 [mlx5_core] netdev_nl_stats_by_netdev+0x2a6/0x4c0 ? __rmqueue_pcplist+0x351/0x6f0 netdev_nl_qstats_get_dumpit+0xc4/0x1b0 genl_dumpit+0x2d/0x80 netlink_dump+0x199/0x410 __netlink_dump_start+0x1aa/0x2c0 genl_family_rcv_msg_dumpit+0x94/0xf0 ? __pfx_genl_start+0x10/0x10 ? __pfx_genl_dumpit+0x10/0x10 ? __pfx_genl_done+0x10/0x10 genl_rcv_msg+0x116/0x2b0 ? __pfx_netdev_nl_qstats_get_dumpit+0x10/0x10 ? __pfx_genl_rcv_msg+0x10/0x10 netlink_rcv_skb+0x54/0x100 genl_rcv+0x24/0x40 netlink_unicast+0x21a/0x340 netlink_sendmsg+0x1f4/0x440 __sys_sendto+0x1b6/0x1c0 ? do_sock_setsockopt+0xc3/0x180 ? __sys_setsockopt+0x60/0xb0 __x64_sys_sendto+0x20/0x30 do_syscall_64+0x50/0x110 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f43757132b0 Code: c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 1d 45 31 c9 45 31 c0 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 68 c3 0f 1f 80 00 00 00 00 41 54 48 83 ec 20 RSP: 002b:00007ffd258da048 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007ffd258da0f8 RCX: 00007f43757132b0 RDX: 000000000000001c RSI: 00007f437464b850 RDI: 0000000000000003 RBP: 00007f4375085de0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: ffffffffc4653600 R14: 0000000000000001 R15: 00007f43751a6147 Modules linked in: netconsole xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_registry overlay rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm mlx5_ib ib_uverbs ib_core zram zsmalloc mlx5_core fuse [last unloaded: netconsole] CR2: 0000000000000c00 ---[ end trace 0000000000000000 ]--- RIP: 0010:mlx5e_get_queue_stats_rx+0x3c/0xb0 [mlx5_core] Code: fc 55 48 63 ee 53 48 89 d3 e8 40 3d 70 e1 85 c0 74 58 4c 89 ef e8 d4 07 04 00 84 c0 75 41 49 8b 84 24 f8 39 00 00 48 8b 04 e8 <48> 8b 90 00 0c 00 00 48 03 90 40 0a 00 00 48 89 53 08 48 8b 90 08 RSP: 0018:ffff888116be37d0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff888116be3868 RCX: 0000000000000004 RDX: ffff88810ada4000 RSI: 0000000000000000 RDI: ffff888109df09c0 RBP: 0000000000000000 R08: 0000000000000004 R09: 0000000000000004 R10: ffff88813461901c R11: ffffffffffffffff R12: ffff888109df0000 R13: ffff888109df09c0 R14: ffff888116be38d0 R15: 0000000000000000 FS: 00007f4375d5c740(0000) GS:ffff88852c980000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000c00 CR3: 0000000106ada006 CR4: 0000000000370eb0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Fixes: 7b66ae536a78 ("net/mlx5e: Add per queue netdev-genl stats") Signed-off-by: Gal Pressman Signed-off-by: Tariq Toukan Reviewed-by: Joe Damato Link: https://patch.msgid.link/20240808144107.2095424-6-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index f04decca39f2..5df904639b0c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5296,7 +5296,7 @@ static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i, struct mlx5e_rq_stats *rq_stats; ASSERT_RTNL(); - if (mlx5e_is_uplink_rep(priv)) + if (mlx5e_is_uplink_rep(priv) || !priv->stats_nch) return; channel_stats = priv->channel_stats[i]; @@ -5316,6 +5316,9 @@ static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i, struct mlx5e_sq_stats *sq_stats; ASSERT_RTNL(); + if (!priv->stats_nch) + return; + /* no special case needed for ptp htb etc since txq2sq_stats is kept up * to date for active sq_stats, otherwise get_base_stats takes care of * inactive sqs. From ccbfcac05866ebe6eb3bc6d07b51d4ed4fcde436 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sat, 10 Aug 2024 10:48:32 +0200 Subject: [PATCH 116/562] ALSA: timer: Relax start tick time check for slave timer elements The recent addition of a sanity check for a too low start tick time seems breaking some applications that uses aloop with a certain slave timer setup. They may have the initial resolution 0, hence it's treated as if it were a too low value. Relax and skip the check for the slave timer instance for addressing the regression. Fixes: 4a63bd179fa8 ("ALSA: timer: Set lower bound of start tick time") Cc: Link: https://github.com/raspberrypi/linux/issues/6294 Link: https://patch.msgid.link/20240810084833.10939-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/core/timer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/core/timer.c b/sound/core/timer.c index d104adc75a8b..71a07c1662f5 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -547,7 +547,7 @@ static int snd_timer_start1(struct snd_timer_instance *timeri, /* check the actual time for the start tick; * bail out as error if it's way too low (< 100us) */ - if (start) { + if (start && !(timer->hw.flags & SNDRV_TIMER_HW_SLAVE)) { if ((u64)snd_timer_hw_resolution(timer) * ticks < 100000) return -EINVAL; } From 2ad4e1ada8eebafa2d75a4b75eeeca882de6ada1 Mon Sep 17 00:00:00 2001 From: Janne Grunau Date: Sat, 3 Aug 2024 21:52:55 +0200 Subject: [PATCH 117/562] wifi: brcmfmac: cfg80211: Handle SSID based pmksa deletion wpa_supplicant 2.11 sends since 1efdba5fdc2c ("Handle PMKSA flush in the driver for SAE/OWE offload cases") SSID based PMKSA del commands. brcmfmac is not prepared and tries to dereference the NULL bssid and pmkid pointers in cfg80211_pmksa. PMKID_V3 operations support SSID based updates so copy the SSID. Fixes: a96202acaea4 ("wifi: brcmfmac: cfg80211: Add support for PMKID_V3 operations") Cc: stable@vger.kernel.org # 6.4.x Signed-off-by: Janne Grunau Reviewed-by: Neal Gompa Acked-by: Arend van Spriel Signed-off-by: Kalle Valo Link: https://patch.msgid.link/20240803-brcmfmac_pmksa_del_ssid-v1-1-4e85f19135e1@jannau.net --- .../wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 1585a5653ee4..d4cc5fa92341 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -4320,9 +4320,16 @@ brcmf_pmksa_v3_op(struct brcmf_if *ifp, struct cfg80211_pmksa *pmksa, /* Single PMK operation */ pmk_op->count = cpu_to_le16(1); length += sizeof(struct brcmf_pmksa_v3); - memcpy(pmk_op->pmk[0].bssid, pmksa->bssid, ETH_ALEN); - memcpy(pmk_op->pmk[0].pmkid, pmksa->pmkid, WLAN_PMKID_LEN); - pmk_op->pmk[0].pmkid_len = WLAN_PMKID_LEN; + if (pmksa->bssid) + memcpy(pmk_op->pmk[0].bssid, pmksa->bssid, ETH_ALEN); + if (pmksa->pmkid) { + memcpy(pmk_op->pmk[0].pmkid, pmksa->pmkid, WLAN_PMKID_LEN); + pmk_op->pmk[0].pmkid_len = WLAN_PMKID_LEN; + } + if (pmksa->ssid && pmksa->ssid_len) { + memcpy(pmk_op->pmk[0].ssid.SSID, pmksa->ssid, pmksa->ssid_len); + pmk_op->pmk[0].ssid.SSID_len = pmksa->ssid_len; + } pmk_op->pmk[0].time_left = cpu_to_le32(alive ? BRCMF_PMKSA_NO_EXPIRY : 0); } From aad41832326723627ad8ac9ee8a543b6dca4454d Mon Sep 17 00:00:00 2001 From: Asmaa Mnebhi Date: Tue, 11 Jun 2024 13:15:09 -0400 Subject: [PATCH 118/562] gpio: mlxbf3: Support shutdown() function During Linux graceful reboot, the GPIO interrupts are not disabled. Since the drivers are not removed during graceful reboot, the logic to call mlxbf3_gpio_irq_disable() is not triggered. Interrupts that remain enabled can cause issues on subsequent boots. For example, the mlxbf-gige driver contains PHY logic to bring up the link. If the gpio-mlxbf3 driver loads first, the mlxbf-gige driver will use a GPIO interrupt to bring up the link. Otherwise, it will use polling. The next time Linux boots and loads the drivers in this order, we encounter the issue: - mlxbf-gige loads first and uses polling while the GPIO10 interrupt is still enabled from the previous boot. So if the interrupt triggers, there is nothing to clear it. - gpio-mlxbf3 loads. - i2c-mlxbf loads. The interrupt doesn't trigger for I2C because it is shared with the GPIO interrupt line which was not cleared. The solution is to add a shutdown function to the GPIO driver to clear and disable all interrupts. Also clear the interrupt after disabling it in mlxbf3_gpio_irq_disable(). Fixes: 38a700efc510 ("gpio: mlxbf3: Add gpio driver support") Signed-off-by: Asmaa Mnebhi Reviewed-by: David Thompson Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20240611171509.22151-1-asmaa@nvidia.com Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-mlxbf3.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/gpio/gpio-mlxbf3.c b/drivers/gpio/gpio-mlxbf3.c index d5906d419b0a..10ea71273c89 100644 --- a/drivers/gpio/gpio-mlxbf3.c +++ b/drivers/gpio/gpio-mlxbf3.c @@ -39,6 +39,8 @@ #define MLXBF_GPIO_CAUSE_OR_EVTEN0 0x14 #define MLXBF_GPIO_CAUSE_OR_CLRCAUSE 0x18 +#define MLXBF_GPIO_CLR_ALL_INTS GENMASK(31, 0) + struct mlxbf3_gpio_context { struct gpio_chip gc; @@ -82,6 +84,8 @@ static void mlxbf3_gpio_irq_disable(struct irq_data *irqd) val = readl(gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0); val &= ~BIT(offset); writel(val, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0); + + writel(BIT(offset), gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_CLRCAUSE); raw_spin_unlock_irqrestore(&gs->gc.bgpio_lock, flags); gpiochip_disable_irq(gc, offset); @@ -253,6 +257,15 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev) return 0; } +static void mlxbf3_gpio_shutdown(struct platform_device *pdev) +{ + struct mlxbf3_gpio_context *gs = platform_get_drvdata(pdev); + + /* Disable and clear all interrupts */ + writel(0, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0); + writel(MLXBF_GPIO_CLR_ALL_INTS, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_CLRCAUSE); +} + static const struct acpi_device_id mlxbf3_gpio_acpi_match[] = { { "MLNXBF33", 0 }, {} @@ -265,6 +278,7 @@ static struct platform_driver mlxbf3_gpio_driver = { .acpi_match_table = mlxbf3_gpio_acpi_match, }, .probe = mlxbf3_gpio_probe, + .shutdown = mlxbf3_gpio_shutdown, }; module_platform_driver(mlxbf3_gpio_driver); From 9a039eeb71a42c8b13408a1976e300f3898e1be0 Mon Sep 17 00:00:00 2001 From: Moon Yeounsu Date: Wed, 7 Aug 2024 19:07:21 +0900 Subject: [PATCH 119/562] net: ethernet: use ip_hdrlen() instead of bit shift `ip_hdr(skb)->ihl << 2` is the same as `ip_hdrlen(skb)` Therefore, we should use a well-defined function not a bit shift to find the header length. It also compresses two lines to a single line. Signed-off-by: Moon Yeounsu Reviewed-by: Christophe JAILLET Signed-off-by: David S. Miller --- drivers/net/ethernet/jme.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index b06e24562973..d8be0e4dcb07 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -946,15 +946,13 @@ jme_udpsum(struct sk_buff *skb) if (skb->protocol != htons(ETH_P_IP)) return csum; skb_set_network_header(skb, ETH_HLEN); - if ((ip_hdr(skb)->protocol != IPPROTO_UDP) || - (skb->len < (ETH_HLEN + - (ip_hdr(skb)->ihl << 2) + - sizeof(struct udphdr)))) { + + if (ip_hdr(skb)->protocol != IPPROTO_UDP || + skb->len < (ETH_HLEN + ip_hdrlen(skb) + sizeof(struct udphdr))) { skb_reset_network_header(skb); return csum; } - skb_set_transport_header(skb, - ETH_HLEN + (ip_hdr(skb)->ihl << 2)); + skb_set_transport_header(skb, ETH_HLEN + ip_hdrlen(skb)); csum = udp_hdr(skb)->check; skb_reset_transport_header(skb); skb_reset_network_header(skb); From ef9718b3d54e822de294351251f3a574f8a082ce Mon Sep 17 00:00:00 2001 From: Parsa Poorshikhian Date: Sat, 10 Aug 2024 18:39:06 +0330 Subject: [PATCH 120/562] ALSA: hda/realtek: Fix noise from speakers on Lenovo IdeaPad 3 15IAU7 Fix noise from speakers connected to AUX port when no sound is playing. The problem occurs because the `alc_shutup_pins` function includes a 0x10ec0257 vendor ID, which causes noise on Lenovo IdeaPad 3 15IAU7 with Realtek ALC257 codec when no sound is playing. Removing this vendor ID from the function fixes the bug. Fixes: 70794b9563fe ("ALSA: hda/realtek: Add more codec ID to no shutup pins list") Signed-off-by: Parsa Poorshikhian Link: https://patch.msgid.link/20240810150939.330693-1-parsa.poorsh@gmail.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 480e82df7a4c..6e19598e23b7 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -583,7 +583,6 @@ static void alc_shutup_pins(struct hda_codec *codec) switch (codec->core.vendor_id) { case 0x10ec0236: case 0x10ec0256: - case 0x10ec0257: case 0x19e58326: case 0x10ec0283: case 0x10ec0285: From 03c5c350e38d9346b69357d0e52c3c40495c14a0 Mon Sep 17 00:00:00 2001 From: Simon Trimmer Date: Fri, 2 Aug 2024 16:22:15 +0100 Subject: [PATCH 121/562] ALSA: hda/realtek: Add support for new HP G12 laptops Some of these laptop models have quirk IDs that are identical but have different amplifier parts fitted, this difference is described in the ACPI information. The solution introduced for this product family can derive the required component binding information from ACPI instead of hardcoding it, supports the new variants of the CS35L56 being used and has generalized naming that makes it applicable to other ALC+amp combinations. Signed-off-by: Simon Trimmer Signed-off-by: Richard Fitzgerald Link: https://patch.msgid.link/20240802152215.20831-4-rf@opensource.cirrus.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 99 +++++++++++++++++++++++++++++++++++ 1 file changed, 99 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 480e82df7a4c..24eb71efac6c 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -11,15 +11,18 @@ */ #include +#include #include #include #include #include #include #include +#include #include #include #include +#include #include #include #include @@ -6856,6 +6859,86 @@ static void comp_generic_fixup(struct hda_codec *cdc, int action, const char *bu } } +static void cs35lxx_autodet_fixup(struct hda_codec *cdc, + const struct hda_fixup *fix, + int action) +{ + struct device *dev = hda_codec_dev(cdc); + struct acpi_device *adev; + struct fwnode_handle *fwnode __free(fwnode_handle) = NULL; + const char *bus = NULL; + static const struct { + const char *hid; + const char *name; + } acpi_ids[] = {{ "CSC3554", "cs35l54-hda" }, + { "CSC3556", "cs35l56-hda" }, + { "CSC3557", "cs35l57-hda" }}; + char *match; + int i, count = 0, count_devindex = 0; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + for (i = 0; i < ARRAY_SIZE(acpi_ids); ++i) { + adev = acpi_dev_get_first_match_dev(acpi_ids[i].hid, NULL, -1); + if (adev) + break; + } + if (!adev) { + dev_err(dev, "Failed to find ACPI entry for a Cirrus Amp\n"); + return; + } + + count = i2c_acpi_client_count(adev); + if (count > 0) { + bus = "i2c"; + } else { + count = acpi_spi_count_resources(adev); + if (count > 0) + bus = "spi"; + } + + fwnode = fwnode_handle_get(acpi_fwnode_handle(adev)); + acpi_dev_put(adev); + + if (!bus) { + dev_err(dev, "Did not find any buses for %s\n", acpi_ids[i].hid); + return; + } + + if (!fwnode) { + dev_err(dev, "Could not get fwnode for %s\n", acpi_ids[i].hid); + return; + } + + /* + * When available the cirrus,dev-index property is an accurate + * count of the amps in a system and is used in preference to + * the count of bus devices that can contain additional address + * alias entries. + */ + count_devindex = fwnode_property_count_u32(fwnode, "cirrus,dev-index"); + if (count_devindex > 0) + count = count_devindex; + + match = devm_kasprintf(dev, GFP_KERNEL, "-%%s:00-%s.%%d", acpi_ids[i].name); + if (!match) + return; + dev_info(dev, "Found %d %s on %s (%s)\n", count, acpi_ids[i].hid, bus, match); + comp_generic_fixup(cdc, action, bus, acpi_ids[i].hid, match, count); + + break; + case HDA_FIXUP_ACT_FREE: + /* + * Pass the action on to comp_generic_fixup() so that + * hda_component_manager functions can be called in just once + * place. In this context the bus, hid, match_str or count + * values do not need to be calculated. + */ + comp_generic_fixup(cdc, action, NULL, NULL, NULL, 0); + break; + } +} + static void cs35l41_fixup_i2c_two(struct hda_codec *cdc, const struct hda_fixup *fix, int action) { comp_generic_fixup(cdc, action, "i2c", "CSC3551", "-%s:00-cs35l41-hda.%d", 2); @@ -7528,6 +7611,7 @@ enum { ALC256_FIXUP_CHROME_BOOK, ALC287_FIXUP_LENOVO_14ARP8_LEGION_IAH7, ALC287_FIXUP_LENOVO_SSID_17AA3820, + ALCXXX_FIXUP_CS35LXX, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -9857,6 +9941,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc287_fixup_lenovo_ssid_17aa3820, }, + [ALCXXX_FIXUP_CS35LXX] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs35lxx_autodet_fixup, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -10271,6 +10359,17 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8cdf, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ce0, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8d01, "HP ZBook Power 14 G12", ALCXXX_FIXUP_CS35LXX), + SND_PCI_QUIRK(0x103c, 0x8d08, "HP EliteBook 1045 14 G12", ALCXXX_FIXUP_CS35LXX), + SND_PCI_QUIRK(0x103c, 0x8d85, "HP EliteBook 1040 14 G12", ALCXXX_FIXUP_CS35LXX), + SND_PCI_QUIRK(0x103c, 0x8d86, "HP Elite x360 1040 14 G12", ALCXXX_FIXUP_CS35LXX), + SND_PCI_QUIRK(0x103c, 0x8d8c, "HP EliteBook 830 13 G12", ALCXXX_FIXUP_CS35LXX), + SND_PCI_QUIRK(0x103c, 0x8d8d, "HP Elite x360 830 13 G12", ALCXXX_FIXUP_CS35LXX), + SND_PCI_QUIRK(0x103c, 0x8d8e, "HP EliteBook 840 14 G12", ALCXXX_FIXUP_CS35LXX), + SND_PCI_QUIRK(0x103c, 0x8d8f, "HP EliteBook 840 14 G12", ALCXXX_FIXUP_CS35LXX), + SND_PCI_QUIRK(0x103c, 0x8d90, "HP EliteBook 860 16 G12", ALCXXX_FIXUP_CS35LXX), + SND_PCI_QUIRK(0x103c, 0x8d91, "HP ZBook Firefly 14 G12", ALCXXX_FIXUP_CS35LXX), + SND_PCI_QUIRK(0x103c, 0x8d92, "HP ZBook Firefly 16 G12", ALCXXX_FIXUP_CS35LXX), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), From 004eb8ba776ccd3e296ea6f78f7ae7985b12824e Mon Sep 17 00:00:00 2001 From: Lianqin Hu Date: Sun, 11 Aug 2024 08:30:11 +0000 Subject: [PATCH 122/562] ALSA: usb-audio: Add delay quirk for VIVO USB-C-XE710 HEADSET Audio control requests that sets sampling frequency sometimes fail on this card. Adding delay between control messages eliminates that problem. Signed-off-by: Lianqin Hu Cc: Link: https://patch.msgid.link/TYUPR06MB6217FF67076AF3E49E12C877D2842@TYUPR06MB6217.apcprd06.prod.outlook.com Signed-off-by: Takashi Iwai --- sound/usb/quirks.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index ea063a14cdd8..e7b68c67852e 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2221,6 +2221,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x2d95, 0x8021, /* VIVO USB-C-XE710 HEADSET */ + QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */ From b86aa4140f6a8f01f35bfb05af60e01a55b48803 Mon Sep 17 00:00:00 2001 From: Bouke Sybren Haarsma Date: Sun, 28 Jul 2024 14:47:30 +0200 Subject: [PATCH 123/562] drm: panel-orientation-quirks: Add quirk for Ayn Loki Zero Add quirk orientation for the Ayn Loki Zero. This also has been tested/used by the JELOS team. Signed-off-by: Bouke Sybren Haarsma Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Link: https://patchwork.freedesktop.org/patch/msgid/20240728124731.168452-2-boukehaarsma23@gmail.com --- drivers/gpu/drm/drm_panel_orientation_quirks.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index c16c7678237e..a1dfeaae644d 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -208,6 +208,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_MATCH(DMI_BOARD_NAME, "KUN"), }, .driver_data = (void *)&lcd1600x2560_rightside_up, + }, { /* AYN Loki Zero */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ayn"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Loki Zero"), + }, + .driver_data = (void *)&lcd1080x1920_leftside_up, }, { /* Chuwi HiBook (CWI514) */ .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Hampoo"), From 2c71c8459c8ca66bd8f597effaac892ee8448a9f Mon Sep 17 00:00:00 2001 From: Bouke Sybren Haarsma Date: Sun, 28 Jul 2024 14:47:31 +0200 Subject: [PATCH 124/562] drm: panel-orientation-quirks: Add quirk for Ayn Loki Max Add quirk orientation for Ayn Loki Max model. This has been tested by JELOS team that uses their own patched kernel for a while now and confirmed by users in the ChimeraOS discord servers. Signed-off-by: Bouke Sybren Haarsma Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Link: https://patchwork.freedesktop.org/patch/msgid/20240728124731.168452-3-boukehaarsma23@gmail.com --- drivers/gpu/drm/drm_panel_orientation_quirks.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index a1dfeaae644d..0830cae9a4d0 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -208,6 +208,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_MATCH(DMI_BOARD_NAME, "KUN"), }, .driver_data = (void *)&lcd1600x2560_rightside_up, + }, { /* AYN Loki Max */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ayn"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Loki Max"), + }, + .driver_data = (void *)&lcd1080x1920_leftside_up, }, { /* AYN Loki Zero */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ayn"), From e332a5aba83500e8d422c90d2a84d8a5f888673e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 8 Aug 2024 02:47:28 +0900 Subject: [PATCH 125/562] treewide: remove unnecessary inclusion These files do not use any macros defined in . Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Schier --- drivers/accessibility/speakup/genmap.c | 1 - drivers/accessibility/speakup/makemapdata.c | 1 - drivers/staging/media/atomisp/include/linux/atomisp.h | 1 - samples/trace_events/trace_custom_sched.c | 1 - sound/soc/codecs/cs42l42.c | 1 - 5 files changed, 5 deletions(-) diff --git a/drivers/accessibility/speakup/genmap.c b/drivers/accessibility/speakup/genmap.c index 0125000e00d9..0882bab10fb8 100644 --- a/drivers/accessibility/speakup/genmap.c +++ b/drivers/accessibility/speakup/genmap.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include "utils.h" diff --git a/drivers/accessibility/speakup/makemapdata.c b/drivers/accessibility/speakup/makemapdata.c index d7d41bb9b05f..55e4ef8a93dc 100644 --- a/drivers/accessibility/speakup/makemapdata.c +++ b/drivers/accessibility/speakup/makemapdata.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include "utils.h" diff --git a/drivers/staging/media/atomisp/include/linux/atomisp.h b/drivers/staging/media/atomisp/include/linux/atomisp.h index 16c9da172c03..fefbe3cd08f3 100644 --- a/drivers/staging/media/atomisp/include/linux/atomisp.h +++ b/drivers/staging/media/atomisp/include/linux/atomisp.h @@ -20,7 +20,6 @@ #define _ATOM_ISP_H #include -#include /* struct media_device_info.hw_revision */ #define ATOMISP_HW_REVISION_MASK 0x0000ff00 diff --git a/samples/trace_events/trace_custom_sched.c b/samples/trace_events/trace_custom_sched.c index b99d9ab7db85..dd409b704b35 100644 --- a/samples/trace_events/trace_custom_sched.c +++ b/samples/trace_events/trace_custom_sched.c @@ -8,7 +8,6 @@ #define pr_fmt(fmt) fmt #include -#include #include #include diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index 60d366e53526..6400ac875e6f 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -11,7 +11,6 @@ #include #include -#include #include #include #include From 1472464c6248575bf2d01c7f076b94704bb32c95 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 8 Aug 2024 03:03:00 +0900 Subject: [PATCH 126/562] kbuild: avoid scripts/kallsyms parsing /dev/null On macOS, as reported by Daniel Gomez, getline() sets ENOTTY to errno if it is requested to read from /dev/null. If this is worth fixing, I would rather pass an empty file to scripts/kallsyms instead of adding the ugly #ifdef __APPLE__. Fixes: c442db3f49f2 ("kbuild: remove PROVIDE() for kallsyms symbols") Reported-by: Daniel Gomez Closes: https://lore.kernel.org/all/20240807-macos-build-support-v1-12-4cd1ded85694@samsung.com/ Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Schier Reviewed-by: Daniel Gomez --- scripts/link-vmlinux.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index f7b2503cdba9..41c68ae3415d 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -219,7 +219,8 @@ kallsymso= strip_debug= if is_enabled CONFIG_KALLSYMS; then - kallsyms /dev/null .tmp_vmlinux0.kallsyms + truncate -s0 .tmp_vmlinux.kallsyms0.syms + kallsyms .tmp_vmlinux.kallsyms0.syms .tmp_vmlinux0.kallsyms fi if is_enabled CONFIG_KALLSYMS || is_enabled CONFIG_DEBUG_INFO_BTF; then From a9a18e8f770c9b0703dab93580d0b02e199a4c79 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 9 Aug 2024 15:28:19 +0300 Subject: [PATCH 127/562] atm: idt77252: prevent use after free in dequeue_rx() We can't dereference "skb" after calling vcc->push() because the skb is released. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- drivers/atm/idt77252.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index e7f713cd70d3..a876024d8a05 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -1118,8 +1118,8 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) rpp->len += skb->len; if (stat & SAR_RSQE_EPDU) { + unsigned int len, truesize; unsigned char *l1l2; - unsigned int len; l1l2 = (unsigned char *) ((unsigned long) skb->data + skb->len - 6); @@ -1189,14 +1189,15 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) ATM_SKB(skb)->vcc = vcc; __net_timestamp(skb); + truesize = skb->truesize; vcc->push(vcc, skb); atomic_inc(&vcc->stats->rx); - if (skb->truesize > SAR_FB_SIZE_3) + if (truesize > SAR_FB_SIZE_3) add_rx_skb(card, 3, SAR_FB_SIZE_3, 1); - else if (skb->truesize > SAR_FB_SIZE_2) + else if (truesize > SAR_FB_SIZE_2) add_rx_skb(card, 2, SAR_FB_SIZE_2, 1); - else if (skb->truesize > SAR_FB_SIZE_1) + else if (truesize > SAR_FB_SIZE_1) add_rx_skb(card, 1, SAR_FB_SIZE_1, 1); else add_rx_skb(card, 0, SAR_FB_SIZE_0, 1); From 9ff2f816e2aa65ca9a1cdf0954842f8173c0f48d Mon Sep 17 00:00:00 2001 From: Radhey Shyam Pandey Date: Fri, 9 Aug 2024 11:56:09 +0530 Subject: [PATCH 128/562] net: axienet: Fix register defines comment description In axiethernet header fix register defines comment description to be inline with IP documentation. It updates MAC configuration register, MDIO configuration register and frame filter control description. Fixes: 8a3b7a252dca ("drivers/net/ethernet/xilinx: added Xilinx AXI Ethernet driver") Signed-off-by: Radhey Shyam Pandey Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/ethernet/xilinx/xilinx_axienet.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index fa5500decc96..c7d9221fafdc 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -160,16 +160,16 @@ #define XAE_RCW1_OFFSET 0x00000404 /* Rx Configuration Word 1 */ #define XAE_TC_OFFSET 0x00000408 /* Tx Configuration */ #define XAE_FCC_OFFSET 0x0000040C /* Flow Control Configuration */ -#define XAE_EMMC_OFFSET 0x00000410 /* EMAC mode configuration */ -#define XAE_PHYC_OFFSET 0x00000414 /* RGMII/SGMII configuration */ +#define XAE_EMMC_OFFSET 0x00000410 /* MAC speed configuration */ +#define XAE_PHYC_OFFSET 0x00000414 /* RX Max Frame Configuration */ #define XAE_ID_OFFSET 0x000004F8 /* Identification register */ -#define XAE_MDIO_MC_OFFSET 0x00000500 /* MII Management Config */ -#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MII Management Control */ -#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MII Management Write Data */ -#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MII Management Read Data */ +#define XAE_MDIO_MC_OFFSET 0x00000500 /* MDIO Setup */ +#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MDIO Control */ +#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MDIO Write Data */ +#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MDIO Read Data */ #define XAE_UAW0_OFFSET 0x00000700 /* Unicast address word 0 */ #define XAE_UAW1_OFFSET 0x00000704 /* Unicast address word 1 */ -#define XAE_FMI_OFFSET 0x00000708 /* Filter Mask Index */ +#define XAE_FMI_OFFSET 0x00000708 /* Frame Filter Control */ #define XAE_AF0_OFFSET 0x00000710 /* Address Filter 0 */ #define XAE_AF1_OFFSET 0x00000714 /* Address Filter 1 */ @@ -308,7 +308,7 @@ */ #define XAE_UAW1_UNICASTADDR_MASK 0x0000FFFF -/* Bit masks for Axi Ethernet FMI register */ +/* Bit masks for Axi Ethernet FMC register */ #define XAE_FMI_PM_MASK 0x80000000 /* Promis. mode enable */ #define XAE_FMI_IND_MASK 0x00000003 /* Index Mask */ From 63796bc2e97cd5ebcef60bad4953259d4ad11cb4 Mon Sep 17 00:00:00 2001 From: Pawel Dembicki Date: Fri, 9 Aug 2024 21:38:02 +0200 Subject: [PATCH 129/562] net: dsa: vsc73xx: fix port MAC configuration in full duplex mode According to the datasheet description ("Port Mode Procedure" in 5.6.2), the VSC73XX_MAC_CFG_WEXC_DIS bit is configured only for half duplex mode. The WEXC_DIS bit is responsible for MAC behavior after an excessive collision. Let's set it as described in the datasheet. Fixes: 05bd97fc559d ("net: dsa: Add Vitesse VSC73xx DSA router driver") Reviewed-by: Linus Walleij Reviewed-by: Florian Fainelli Signed-off-by: Pawel Dembicki Signed-off-by: David S. Miller --- drivers/net/dsa/vitesse-vsc73xx-core.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index d9d3e30fd47a..f548ed4cb23f 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -957,6 +957,11 @@ static void vsc73xx_mac_link_up(struct phylink_config *config, if (duplex == DUPLEX_FULL) val |= VSC73XX_MAC_CFG_FDX; + else + /* In datasheet description ("Port Mode Procedure" in 5.6.2) + * this bit is configured only for half duplex. + */ + val |= VSC73XX_MAC_CFG_WEXC_DIS; /* This routine is described in the datasheet (below ARBDISC register * description) @@ -967,7 +972,6 @@ static void vsc73xx_mac_link_up(struct phylink_config *config, get_random_bytes(&seed, 1); val |= seed << VSC73XX_MAC_CFG_SEED_OFFSET; val |= VSC73XX_MAC_CFG_SEED_LOAD; - val |= VSC73XX_MAC_CFG_WEXC_DIS; /* Those bits are responsible for MTU only. Kernel takes care about MTU, * let's enable +8 bytes frame length unconditionally. From 5b9eebc2c7a5f0cc7950d918c1e8a4ad4bed5010 Mon Sep 17 00:00:00 2001 From: Pawel Dembicki Date: Fri, 9 Aug 2024 21:38:03 +0200 Subject: [PATCH 130/562] net: dsa: vsc73xx: pass value in phy_write operation In the 'vsc73xx_phy_write' function, the register value is missing, and the phy write operation always sends zeros. This commit passes the value variable into the proper register. Fixes: 05bd97fc559d ("net: dsa: Add Vitesse VSC73xx DSA router driver") Reviewed-by: Linus Walleij Reviewed-by: Florian Fainelli Signed-off-by: Pawel Dembicki Signed-off-by: David S. Miller --- drivers/net/dsa/vitesse-vsc73xx-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index f548ed4cb23f..4b300c293dec 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -574,7 +574,7 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum, return 0; } - cmd = (phy << 21) | (regnum << 16); + cmd = (phy << 21) | (regnum << 16) | val; ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd); if (ret) return ret; From fa63c6434b6f6aaf9d8d599dc899bc0a074cc0ad Mon Sep 17 00:00:00 2001 From: Pawel Dembicki Date: Fri, 9 Aug 2024 21:38:04 +0200 Subject: [PATCH 131/562] net: dsa: vsc73xx: check busy flag in MDIO operations The VSC73xx has a busy flag used during MDIO operations. It is raised when MDIO read/write operations are in progress. Without it, PHYs are misconfigured and bus operations do not work as expected. Fixes: 05bd97fc559d ("net: dsa: Add Vitesse VSC73xx DSA router driver") Reviewed-by: Linus Walleij Reviewed-by: Florian Fainelli Signed-off-by: Pawel Dembicki Signed-off-by: David S. Miller --- drivers/net/dsa/vitesse-vsc73xx-core.c | 37 +++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index 4b300c293dec..a789b2da9b7d 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -40,6 +40,10 @@ #define VSC73XX_BLOCK_ARBITER 0x5 /* Only subblock 0 */ #define VSC73XX_BLOCK_SYSTEM 0x7 /* Only subblock 0 */ +/* MII Block subblock */ +#define VSC73XX_BLOCK_MII_INTERNAL 0x0 /* Internal MDIO subblock */ +#define VSC73XX_BLOCK_MII_EXTERNAL 0x1 /* External MDIO subblock */ + #define CPU_PORT 6 /* CPU port */ /* MAC Block registers */ @@ -225,6 +229,8 @@ #define VSC73XX_MII_CMD 0x1 #define VSC73XX_MII_DATA 0x2 +#define VSC73XX_MII_STAT_BUSY BIT(3) + /* Arbiter block 5 registers */ #define VSC73XX_ARBEMPTY 0x0c #define VSC73XX_ARBDISC 0x0e @@ -299,6 +305,7 @@ #define IS_739X(a) (IS_7395(a) || IS_7398(a)) #define VSC73XX_POLL_SLEEP_US 1000 +#define VSC73XX_MDIO_POLL_SLEEP_US 5 #define VSC73XX_POLL_TIMEOUT_US 10000 struct vsc73xx_counter { @@ -527,6 +534,22 @@ static int vsc73xx_detect(struct vsc73xx *vsc) return 0; } +static int vsc73xx_mdio_busy_check(struct vsc73xx *vsc) +{ + int ret, err; + u32 val; + + ret = read_poll_timeout(vsc73xx_read, err, + err < 0 || !(val & VSC73XX_MII_STAT_BUSY), + VSC73XX_MDIO_POLL_SLEEP_US, + VSC73XX_POLL_TIMEOUT_US, false, vsc, + VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL, + VSC73XX_MII_STAT, &val); + if (ret) + return ret; + return err; +} + static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum) { struct vsc73xx *vsc = ds->priv; @@ -534,12 +557,20 @@ static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum) u32 val; int ret; + ret = vsc73xx_mdio_busy_check(vsc); + if (ret) + return ret; + /* Setting bit 26 means "read" */ cmd = BIT(26) | (phy << 21) | (regnum << 16); ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd); if (ret) return ret; - msleep(2); + + ret = vsc73xx_mdio_busy_check(vsc); + if (ret) + return ret; + ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, 0, 2, &val); if (ret) return ret; @@ -563,6 +594,10 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum, u32 cmd; int ret; + ret = vsc73xx_mdio_busy_check(vsc); + if (ret) + return ret; + /* It was found through tedious experiments that this router * chip really hates to have it's PHYs reset. They * never recover if that happens: autonegotiation stops From 9f9a72654622bae75adb1e1923d709e96ede3042 Mon Sep 17 00:00:00 2001 From: Pawel Dembicki Date: Fri, 9 Aug 2024 21:38:05 +0200 Subject: [PATCH 132/562] net: dsa: vsc73xx: allow phy resetting Resetting the VSC73xx PHY was problematic because the MDIO bus, without a busy check, read and wrote incorrect register values. My investigation indicates that resetting the PHY only triggers changes in configuration. However, improper register values written earlier were only exposed after a soft reset. The reset itself wasn't the issue; rather, the problem stemmed from incorrect read and write operations. A 'soft_reset' can now proceed normally. There are no reasons to keep the VSC73xx from being reset. This commit removes the reset blockade in the 'vsc73xx_phy_write' function. Reviewed-by: Linus Walleij Reviewed-by: Florian Fainelli Signed-off-by: Pawel Dembicki Signed-off-by: David S. Miller --- drivers/net/dsa/vitesse-vsc73xx-core.c | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index a789b2da9b7d..e3f95d2cc2c1 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -598,17 +598,6 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum, if (ret) return ret; - /* It was found through tedious experiments that this router - * chip really hates to have it's PHYs reset. They - * never recover if that happens: autonegotiation stops - * working after a reset. Just filter out this command. - * (Resetting the whole chip is OK.) - */ - if (regnum == 0 && (val & BIT(15))) { - dev_info(vsc->dev, "reset PHY - disallowed\n"); - return 0; - } - cmd = (phy << 21) | (regnum << 16) | val; ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd); if (ret) From de7a670f8defe4ed2115552ad23dea0f432f7be4 Mon Sep 17 00:00:00 2001 From: Pawel Dembicki Date: Fri, 9 Aug 2024 21:38:06 +0200 Subject: [PATCH 133/562] net: phy: vitesse: repair vsc73xx autonegotiation When the vsc73xx mdio bus work properly, the generic autonegotiation configuration works well. Reviewed-by: Linus Walleij Signed-off-by: Pawel Dembicki Signed-off-by: David S. Miller --- drivers/net/phy/vitesse.c | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 897b979ec03c..3b5fcaf0dd36 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -237,16 +237,6 @@ static int vsc739x_config_init(struct phy_device *phydev) return 0; } -static int vsc73xx_config_aneg(struct phy_device *phydev) -{ - /* The VSC73xx switches does not like to be instructed to - * do autonegotiation in any way, it prefers that you just go - * with the power-on/reset defaults. Writing some registers will - * just make autonegotiation permanently fail. - */ - return 0; -} - /* This adds a skew for both TX and RX clocks, so the skew should only be * applied to "rgmii-id" interfaces. It may not work as expected * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces. @@ -444,7 +434,6 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc738x_config_init, - .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, }, { @@ -453,7 +442,6 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc738x_config_init, - .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, }, { @@ -462,7 +450,6 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc739x_config_init, - .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, }, { @@ -471,7 +458,6 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc739x_config_init, - .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, }, { From e7a9af8c93aa9f408f9972809b642faeec5287e1 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 8 Aug 2024 11:32:47 +0200 Subject: [PATCH 134/562] powerpc/mm: Fix size of allocated PGDIR Commit 6b0e82791bd0 ("powerpc/e500: switch to 64 bits PGD on 85xx (32 bits)") increased the size of PGD entries but failed to increase the PGD directory. Use the size of pgd_t instead of the size of pointers to calculate the allocated size. Reported-by: Guenter Roeck Fixes: 6b0e82791bd0 ("powerpc/e500: switch to 64 bits PGD on 85xx (32 bits)") Signed-off-by: Christophe Leroy Tested-by: Guenter Roeck Signed-off-by: Michael Ellerman Link: https://msgid.link/1cdaacb391cbd3e0240f0e0faf691202874e9422.1723109462.git.christophe.leroy@csgroup.eu --- arch/powerpc/mm/init-common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c index 9b4a675eb8f8..2978fcbe307e 100644 --- a/arch/powerpc/mm/init-common.c +++ b/arch/powerpc/mm/init-common.c @@ -73,7 +73,7 @@ void setup_kup(void) #define CTOR(shift) static void ctor_##shift(void *addr) \ { \ - memset(addr, 0, sizeof(void *) << (shift)); \ + memset(addr, 0, sizeof(pgd_t) << (shift)); \ } CTOR(0); CTOR(1); CTOR(2); CTOR(3); CTOR(4); CTOR(5); CTOR(6); CTOR(7); @@ -117,7 +117,7 @@ EXPORT_SYMBOL_GPL(pgtable_cache); /* used by kvm_hv module */ void pgtable_cache_add(unsigned int shift) { char *name; - unsigned long table_size = sizeof(void *) << shift; + unsigned long table_size = sizeof(pgd_t) << shift; unsigned long align = table_size; /* When batching pgtable pointers for RCU freeing, we store From e7e846dc6c73fbc94ae8b4ec20d05627646416f2 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 8 Aug 2024 09:05:08 +0200 Subject: [PATCH 135/562] powerpc/mm: Fix boot warning with hugepages and CONFIG_DEBUG_VIRTUAL Booting with CONFIG_DEBUG_VIRTUAL leads to following warning when passing hugepage reservation on command line: Kernel command line: hugepagesz=1g hugepages=1 hugepagesz=64m hugepages=1 hugepagesz=256m hugepages=1 noreboot HugeTLB: allocating 1 of page size 1.00 GiB failed. Only allocated 0 hugepages. ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at arch/powerpc/include/asm/io.h:948 __alloc_bootmem_huge_page+0xd4/0x284 Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 6.10.0-rc6-00396-g6b0e82791bd0-dirty #936 Hardware name: MPC8544DS e500v2 0x80210030 MPC8544 DS NIP: c1020240 LR: c10201d0 CTR: 00000000 REGS: c13fdd30 TRAP: 0700 Not tainted (6.10.0-rc6-00396-g6b0e82791bd0-dirty) MSR: 00021000 CR: 44084288 XER: 20000000 GPR00: c10201d0 c13fde20 c130b560 e8000000 e8001000 00000000 00000000 c1420000 GPR08: 00000000 00028001 00000000 00000004 44084282 01066ac0 c0eb7c9c efffe149 GPR16: c0fc4228 0000005f ffffffff c0eb7d0c c0eb7cc0 c0eb7ce0 ffffffff 00000000 GPR24: c1441cec efffe153 e8001000 c14240c0 00000000 c1441d64 00000000 e8000000 NIP [c1020240] __alloc_bootmem_huge_page+0xd4/0x284 LR [c10201d0] __alloc_bootmem_huge_page+0x64/0x284 Call Trace: [c13fde20] [c10201d0] __alloc_bootmem_huge_page+0x64/0x284 (unreliable) [c13fde50] [c10207b8] hugetlb_hstate_alloc_pages+0x8c/0x3e8 [c13fdeb0] [c1021384] hugepages_setup+0x240/0x2cc [c13fdef0] [c1000574] unknown_bootoption+0xfc/0x280 [c13fdf30] [c0078904] parse_args+0x200/0x4c4 [c13fdfa0] [c1000d9c] start_kernel+0x238/0x7d0 [c13fdff0] [c0000434] set_ivor+0x12c/0x168 Code: 554aa33e 7c042840 3ce0c142 80a7427c 5109a016 50caa016 7c9a2378 7fdcf378 4180000c 7c052040 41810160 7c095040 <0fe00000> 38c00000 40800108 3c60c0eb ---[ end trace 0000000000000000 ]--- This is due to virt_addr_valid() using high_memory before it is set. high_memory is set in mem_init() using max_low_pfn, but max_low_pfn is available long before, it is set in mem_topology_setup(). So just like commit daa9ada2093e ("powerpc/mm: Fix boot crash with FLATMEM") moved the setting of max_mapnr immediately after the call to mem_topology_setup(), the same can be done for high_memory. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/62b69c4baad067093f39e7e60df0fe27a86b8d2a.1723100702.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/setup-common.c | 1 + arch/powerpc/mm/mem.c | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 4bd2f87616ba..943430077375 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -959,6 +959,7 @@ void __init setup_arch(char **cmdline_p) mem_topology_setup(); /* Set max_mapnr before paging_init() */ set_max_mapnr(max_pfn); + high_memory = (void *)__va(max_low_pfn * PAGE_SIZE); /* * Release secondary cpus out of their spinloops at 0x60 now that diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index d325217ab201..da21cb018984 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -290,8 +290,6 @@ void __init mem_init(void) swiotlb_init(ppc_swiotlb_enable, ppc_swiotlb_flags); #endif - high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - kasan_late_init(); memblock_free_all(); From c25504a0ba36968f919aa30caff172ef23346299 Mon Sep 17 00:00:00 2001 From: Frank Li Date: Fri, 9 Aug 2024 16:06:53 -0400 Subject: [PATCH 136/562] dt-bindings: net: fsl,qoriq-mc-dpmac: add missed property phys Add missed property phys, which indicate how connect to serdes phy. Fix below warning: arch/arm64/boot/dts/freescale/fsl-lx2160a-honeycomb.dtb: fsl-mc@80c000000: dpmacs:ethernet@7: Unevaluated properties are not allowed ('phys' was unexpected) Signed-off-by: Frank Li Reviewed-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml index a1b71b35319e..42f9843d1868 100644 --- a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml +++ b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml @@ -38,6 +38,10 @@ properties: managed: true + phys: + description: A reference to the SerDes lane(s) + maxItems: 1 + required: - reg From 32316f676b4ee87c0404d333d248ccf777f739bc Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Fri, 9 Aug 2024 14:01:24 -0700 Subject: [PATCH 137/562] net: mana: Fix RX buf alloc_size alignment and atomic op panic The MANA driver's RX buffer alloc_size is passed into napi_build_skb() to create SKB. skb_shinfo(skb) is located at the end of skb, and its alignment is affected by the alloc_size passed into napi_build_skb(). The size needs to be aligned properly for better performance and atomic operations. Otherwise, on ARM64 CPU, for certain MTU settings like 4000, atomic operations may panic on the skb_shinfo(skb)->dataref due to alignment fault. To fix this bug, add proper alignment to the alloc_size calculation. Sample panic info: [ 253.298819] Unable to handle kernel paging request at virtual address ffff000129ba5cce [ 253.300900] Mem abort info: [ 253.301760] ESR = 0x0000000096000021 [ 253.302825] EC = 0x25: DABT (current EL), IL = 32 bits [ 253.304268] SET = 0, FnV = 0 [ 253.305172] EA = 0, S1PTW = 0 [ 253.306103] FSC = 0x21: alignment fault Call trace: __skb_clone+0xfc/0x198 skb_clone+0x78/0xe0 raw6_local_deliver+0xfc/0x228 ip6_protocol_deliver_rcu+0x80/0x500 ip6_input_finish+0x48/0x80 ip6_input+0x48/0xc0 ip6_sublist_rcv_finish+0x50/0x78 ip6_sublist_rcv+0x1cc/0x2b8 ipv6_list_rcv+0x100/0x150 __netif_receive_skb_list_core+0x180/0x220 netif_receive_skb_list_internal+0x198/0x2a8 __napi_poll+0x138/0x250 net_rx_action+0x148/0x330 handle_softirqs+0x12c/0x3a0 Cc: stable@vger.kernel.org Fixes: 80f6215b450e ("net: mana: Add support for jumbo frame") Signed-off-by: Haiyang Zhang Reviewed-by: Long Li Signed-off-by: David S. Miller --- drivers/net/ethernet/microsoft/mana/mana_en.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index d2f07e179e86..ae717d06e66f 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -599,7 +599,11 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size, else *headroom = XDP_PACKET_HEADROOM; - *alloc_size = mtu + MANA_RXBUF_PAD + *headroom; + *alloc_size = SKB_DATA_ALIGN(mtu + MANA_RXBUF_PAD + *headroom); + + /* Using page pool in this case, so alloc_size is PAGE_SIZE */ + if (*alloc_size < PAGE_SIZE) + *alloc_size = PAGE_SIZE; *datasize = mtu + ETH_HLEN; } From db1b4bedb9b97c6d34b03d03815147c04fffe8b4 Mon Sep 17 00:00:00 2001 From: Zheng Zhang Date: Sat, 10 Aug 2024 13:26:51 +0800 Subject: [PATCH 138/562] net: ethernet: mtk_wed: fix use-after-free panic in mtk_wed_setup_tc_block_cb() When there are multiple ap interfaces on one band and with WED on, turning the interface down will cause a kernel panic on MT798X. Previously, cb_priv was freed in mtk_wed_setup_tc_block() without marking NULL,and mtk_wed_setup_tc_block_cb() didn't check the value, too. Assign NULL after free cb_priv in mtk_wed_setup_tc_block() and check NULL in mtk_wed_setup_tc_block_cb(). ---------- Unable to handle kernel paging request at virtual address 0072460bca32b4f5 Call trace: mtk_wed_setup_tc_block_cb+0x4/0x38 0xffffffc0794084bc tcf_block_playback_offloads+0x70/0x1e8 tcf_block_unbind+0x6c/0xc8 ... --------- Fixes: 799684448e3e ("net: ethernet: mtk_wed: introduce wed wo support") Signed-off-by: Zheng Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_wed.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 61334a71058c..e212a4ba9275 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -2666,14 +2666,15 @@ mtk_wed_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_pri { struct mtk_wed_flow_block_priv *priv = cb_priv; struct flow_cls_offload *cls = type_data; - struct mtk_wed_hw *hw = priv->hw; + struct mtk_wed_hw *hw = NULL; - if (!tc_can_offload(priv->dev)) + if (!priv || !tc_can_offload(priv->dev)) return -EOPNOTSUPP; if (type != TC_SETUP_CLSFLOWER) return -EOPNOTSUPP; + hw = priv->hw; return mtk_flow_offload_cmd(hw->eth, cls, hw->index); } @@ -2729,6 +2730,7 @@ mtk_wed_setup_tc_block(struct mtk_wed_hw *hw, struct net_device *dev, flow_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); kfree(block_cb->cb_priv); + block_cb->cb_priv = NULL; } return 0; default: From 497d370a644d95a9f04271aa92cb96d32e84c770 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ma=C3=ADra=20Canal?= Date: Fri, 9 Aug 2024 12:18:45 -0300 Subject: [PATCH 139/562] drm/v3d: Fix out-of-bounds read in `v3d_csd_job_run()` MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When enabling UBSAN on Raspberry Pi 5, we get the following warning: [ 387.894977] UBSAN: array-index-out-of-bounds in drivers/gpu/drm/v3d/v3d_sched.c:320:3 [ 387.903868] index 7 is out of range for type '__u32 [7]' [ 387.909692] CPU: 0 PID: 1207 Comm: kworker/u16:2 Tainted: G WC 6.10.3-v8-16k-numa #151 [ 387.919166] Hardware name: Raspberry Pi 5 Model B Rev 1.0 (DT) [ 387.925961] Workqueue: v3d_csd drm_sched_run_job_work [gpu_sched] [ 387.932525] Call trace: [ 387.935296] dump_backtrace+0x170/0x1b8 [ 387.939403] show_stack+0x20/0x38 [ 387.942907] dump_stack_lvl+0x90/0xd0 [ 387.946785] dump_stack+0x18/0x28 [ 387.950301] __ubsan_handle_out_of_bounds+0x98/0xd0 [ 387.955383] v3d_csd_job_run+0x3a8/0x438 [v3d] [ 387.960707] drm_sched_run_job_work+0x520/0x6d0 [gpu_sched] [ 387.966862] process_one_work+0x62c/0xb48 [ 387.971296] worker_thread+0x468/0x5b0 [ 387.975317] kthread+0x1c4/0x1e0 [ 387.978818] ret_from_fork+0x10/0x20 [ 387.983014] ---[ end trace ]--- This happens because the UAPI provides only seven configuration registers and we are reading the eighth position of this u32 array. Therefore, fix the out-of-bounds read in `v3d_csd_job_run()` by accessing only seven positions on the '__u32 [7]' array. The eighth register exists indeed on V3D 7.1, but it isn't currently used. That being so, let's guarantee that it remains unused and add a note that it could be set in a future patch. Fixes: 0ad5bc1ce463 ("drm/v3d: fix up register addresses for V3D 7.x") Reported-by: Tvrtko Ursulin Signed-off-by: Maíra Canal Reviewed-by: Iago Toral Quiroga Link: https://patchwork.freedesktop.org/patch/msgid/20240809152001.668314-1-mcanal@igalia.com --- drivers/gpu/drm/v3d/v3d_sched.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 9bd7453b25ad..b8682818bafa 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -315,7 +315,7 @@ v3d_csd_job_run(struct drm_sched_job *sched_job) struct v3d_dev *v3d = job->base.v3d; struct drm_device *dev = &v3d->drm; struct dma_fence *fence; - int i, csd_cfg0_reg, csd_cfg_reg_count; + int i, csd_cfg0_reg; v3d->csd_job = job; @@ -335,9 +335,17 @@ v3d_csd_job_run(struct drm_sched_job *sched_job) v3d_switch_perfmon(v3d, &job->base); csd_cfg0_reg = V3D_CSD_QUEUED_CFG0(v3d->ver); - csd_cfg_reg_count = v3d->ver < 71 ? 6 : 7; - for (i = 1; i <= csd_cfg_reg_count; i++) + for (i = 1; i <= 6; i++) V3D_CORE_WRITE(0, csd_cfg0_reg + 4 * i, job->args.cfg[i]); + + /* Although V3D 7.1 has an eighth configuration register, we are not + * using it. Therefore, make sure it remains unused. + * + * XXX: Set the CFG7 register + */ + if (v3d->ver >= 71) + V3D_CORE_WRITE(0, V3D_V7_CSD_QUEUED_CFG7, 0); + /* CFG0 write kicks off the job. */ V3D_CORE_WRITE(0, csd_cfg0_reg, job->args.cfg[0]); From 2a07bb64d80152701d507b1498237ed1b8d83866 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Mon, 12 Aug 2024 14:57:32 +0200 Subject: [PATCH 140/562] s390/dasd: Remove DMA alignment This reverts commit bc792884b76f ("s390/dasd: Establish DMA alignment"). Quoting the original commit: linux-next commit bf8d08532bc1 ("iomap: add support for dma aligned direct-io") changes the alignment requirement to come from the block device rather than the block size, and the default alignment requirement is 512-byte boundaries. Since DASD I/O has page alignments for IDAW/TIDAW requests, let's override this value to restore the expected behavior. I mentioned TIDAW, but that was wrong. TIDAWs have no distinct alignment requirement (per p. 15-70 of POPS SA22-7832-13): Unless otherwise specified, TIDAWs may designate a block of main storage on any boundary and length up to 4K bytes, provided the specified block does not cross a 4 K-byte boundary. IDAWs do, but the original commit neglected that while ECKD DASD are typically formatted in 4096-byte blocks, they don't HAVE to be. Formatting an ECKD volume with smaller blocks is permitted (dasdfmt -b xxx), and the problematic commit enforces alignment properties to such a device that will result in errors, such as: [test@host ~]# lsdasd -l a367 | grep blksz blksz: 512 [test@host ~]# mkfs.xfs -f /dev/disk/by-path/ccw-0.0.a367-part1 meta-data=/dev/dasdc1 isize=512 agcount=4, agsize=230075 blks = sectsz=512 attr=2, projid32bit=1 = crc=1 finobt=1, sparse=1, rmapbt=1 = reflink=1 bigtime=1 inobtcount=1 nrext64=1 data = bsize=4096 blocks=920299, imaxpct=25 = sunit=0 swidth=0 blks naming =version 2 bsize=4096 ascii-ci=0, ftype=1 log =internal log bsize=4096 blocks=16384, version=2 = sectsz=512 sunit=0 blks, lazy-count=1 realtime =none extsz=4096 blocks=0, rtextents=0 error reading existing superblock: Invalid argument mkfs.xfs: pwrite failed: Invalid argument libxfs_bwrite: write failed on (unknown) bno 0x70565c/0x100, err=22 mkfs.xfs: Releasing dirty buffer to free list! found dirty buffer (bulk) on free list! mkfs.xfs: pwrite failed: Invalid argument ...snipped... The original commit omitted the FBA discipline for just this reason, but the formatted block size of the other disciplines was overlooked. The solution to all of this is to revert to the original behavior, such that the block size can be respected. There were two commits [1] that moved this code in the interim, so a straight git-revert is not possible, but the change is straightforward. But what of the original problem? That was manifested with a direct-io QEMU guest, where QEMU itself was changed a month or two later with commit 25474d90aa ("block: use the request length for iov alignment") such that the blamed kernel commit is unnecessary. [1] commit 0127a47f58c6 ("dasd: move queue setup to common code") commit fde07a4d74e3 ("dasd: use the atomic queue limits API") Fixes: bc792884b76f ("s390/dasd: Establish DMA alignment") Reviewed-by: Stefan Haberland Signed-off-by: Eric Farman Signed-off-by: Stefan Haberland Link: https://lore.kernel.org/r/20240812125733.126431-2-sth@linux.ibm.com Signed-off-by: Jens Axboe --- drivers/s390/block/dasd_genhd.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 1aa426b1dedd..6da47a65af61 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -41,7 +41,6 @@ int dasd_gendisk_alloc(struct dasd_block *block) */ .max_segment_size = PAGE_SIZE, .seg_boundary_mask = PAGE_SIZE - 1, - .dma_alignment = PAGE_SIZE - 1, .max_segments = USHRT_MAX, }; struct gendisk *gdp; From 7db4042336580dfd75cb5faa82c12cd51098c90b Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Mon, 12 Aug 2024 14:57:33 +0200 Subject: [PATCH 141/562] s390/dasd: fix error recovery leading to data corruption on ESE devices Extent Space Efficient (ESE) or thin provisioned volumes need to be formatted on demand during usual IO processing. The dasd_ese_needs_format function checks for error codes that signal the non existence of a proper track format. The check for incorrect length is to imprecise since other error cases leading to transport of insufficient data also have this flag set. This might lead to data corruption in certain error cases for example during a storage server warmstart. Fix by removing the check for incorrect length and replacing by explicitly checking for invalid track format in transport mode. Also remove the check for file protected since this is not a valid ESE handling case. Cc: stable@vger.kernel.org # 5.3+ Fixes: 5e2b17e712cf ("s390/dasd: Add dynamic formatting support for ESE volumes") Reviewed-by: Jan Hoeppner Signed-off-by: Stefan Haberland Link: https://lore.kernel.org/r/20240812125733.126431-3-sth@linux.ibm.com Signed-off-by: Jens Axboe --- drivers/s390/block/dasd.c | 36 ++++++++++++------- drivers/s390/block/dasd_3990_erp.c | 10 ++---- drivers/s390/block/dasd_eckd.c | 57 +++++++++++++----------------- drivers/s390/block/dasd_int.h | 2 +- 4 files changed, 51 insertions(+), 54 deletions(-) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 0a97cfedd706..42a4a996defb 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -1601,9 +1601,15 @@ static int dasd_ese_needs_format(struct dasd_block *block, struct irb *irb) if (!sense) return 0; - return !!(sense[1] & SNS1_NO_REC_FOUND) || - !!(sense[1] & SNS1_FILE_PROTECTED) || - scsw_cstat(&irb->scsw) == SCHN_STAT_INCORR_LEN; + if (sense[1] & SNS1_NO_REC_FOUND) + return 1; + + if ((sense[1] & SNS1_INV_TRACK_FORMAT) && + scsw_is_tm(&irb->scsw) && + !(sense[2] & SNS2_ENV_DATA_PRESENT)) + return 1; + + return 0; } static int dasd_ese_oos_cond(u8 *sense) @@ -1624,7 +1630,7 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, struct dasd_device *device; unsigned long now; int nrf_suppressed = 0; - int fp_suppressed = 0; + int it_suppressed = 0; struct request *req; u8 *sense = NULL; int expires; @@ -1679,8 +1685,9 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, */ sense = dasd_get_sense(irb); if (sense) { - fp_suppressed = (sense[1] & SNS1_FILE_PROTECTED) && - test_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags); + it_suppressed = (sense[1] & SNS1_INV_TRACK_FORMAT) && + !(sense[2] & SNS2_ENV_DATA_PRESENT) && + test_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags); nrf_suppressed = (sense[1] & SNS1_NO_REC_FOUND) && test_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags); @@ -1695,7 +1702,7 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, return; } } - if (!(fp_suppressed || nrf_suppressed)) + if (!(it_suppressed || nrf_suppressed)) device->discipline->dump_sense_dbf(device, irb, "int"); if (device->features & DASD_FEATURE_ERPLOG) @@ -2459,14 +2466,17 @@ retry: rc = 0; list_for_each_entry_safe(cqr, n, ccw_queue, blocklist) { /* - * In some cases the 'File Protected' or 'Incorrect Length' - * error might be expected and error recovery would be - * unnecessary in these cases. Check if the according suppress - * bit is set. + * In some cases certain errors might be expected and + * error recovery would be unnecessary in these cases. + * Check if the according suppress bit is set. */ sense = dasd_get_sense(&cqr->irb); - if (sense && sense[1] & SNS1_FILE_PROTECTED && - test_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags)) + if (sense && (sense[1] & SNS1_INV_TRACK_FORMAT) && + !(sense[2] & SNS2_ENV_DATA_PRESENT) && + test_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags)) + continue; + if (sense && (sense[1] & SNS1_NO_REC_FOUND) && + test_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags)) continue; if (scsw_cstat(&cqr->irb.scsw) == 0x40 && test_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags)) diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c index bbbacfc386f2..d0aa267462c5 100644 --- a/drivers/s390/block/dasd_3990_erp.c +++ b/drivers/s390/block/dasd_3990_erp.c @@ -1386,14 +1386,8 @@ dasd_3990_erp_file_prot(struct dasd_ccw_req * erp) struct dasd_device *device = erp->startdev; - /* - * In some cases the 'File Protected' error might be expected and - * log messages shouldn't be written then. - * Check if the according suppress bit is set. - */ - if (!test_bit(DASD_CQR_SUPPRESS_FP, &erp->flags)) - dev_err(&device->cdev->dev, - "Accessing the DASD failed because of a hardware error\n"); + dev_err(&device->cdev->dev, + "Accessing the DASD failed because of a hardware error\n"); return dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED); diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 9388b5c383ca..90b106408992 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -2275,6 +2275,7 @@ dasd_eckd_analysis_ccw(struct dasd_device *device) cqr->status = DASD_CQR_FILLED; /* Set flags to suppress output for expected errors */ set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags); + set_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags); return cqr; } @@ -2556,7 +2557,6 @@ dasd_eckd_build_check_tcw(struct dasd_device *base, struct format_data_t *fdata, cqr->buildclk = get_tod_clock(); cqr->status = DASD_CQR_FILLED; /* Set flags to suppress output for expected errors */ - set_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags); set_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags); return cqr; @@ -4130,8 +4130,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single( /* Set flags to suppress output for expected errors */ if (dasd_eckd_is_ese(basedev)) { - set_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags); - set_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags); set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags); } @@ -4633,9 +4631,8 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track( /* Set flags to suppress output for expected errors */ if (dasd_eckd_is_ese(basedev)) { - set_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags); - set_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags); set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags); + set_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags); } return cqr; @@ -5780,36 +5777,32 @@ static void dasd_eckd_dump_sense(struct dasd_device *device, { u8 *sense = dasd_get_sense(irb); - if (scsw_is_tm(&irb->scsw)) { - /* - * In some cases the 'File Protected' or 'Incorrect Length' - * error might be expected and log messages shouldn't be written - * then. Check if the according suppress bit is set. - */ - if (sense && (sense[1] & SNS1_FILE_PROTECTED) && - test_bit(DASD_CQR_SUPPRESS_FP, &req->flags)) - return; - if (scsw_cstat(&irb->scsw) == 0x40 && - test_bit(DASD_CQR_SUPPRESS_IL, &req->flags)) - return; + /* + * In some cases certain errors might be expected and + * log messages shouldn't be written then. + * Check if the according suppress bit is set. + */ + if (sense && (sense[1] & SNS1_INV_TRACK_FORMAT) && + !(sense[2] & SNS2_ENV_DATA_PRESENT) && + test_bit(DASD_CQR_SUPPRESS_IT, &req->flags)) + return; + if (sense && sense[0] & SNS0_CMD_REJECT && + test_bit(DASD_CQR_SUPPRESS_CR, &req->flags)) + return; + + if (sense && sense[1] & SNS1_NO_REC_FOUND && + test_bit(DASD_CQR_SUPPRESS_NRF, &req->flags)) + return; + + if (scsw_cstat(&irb->scsw) == 0x40 && + test_bit(DASD_CQR_SUPPRESS_IL, &req->flags)) + return; + + if (scsw_is_tm(&irb->scsw)) dasd_eckd_dump_sense_tcw(device, req, irb); - } else { - /* - * In some cases the 'Command Reject' or 'No Record Found' - * error might be expected and log messages shouldn't be - * written then. Check if the according suppress bit is set. - */ - if (sense && sense[0] & SNS0_CMD_REJECT && - test_bit(DASD_CQR_SUPPRESS_CR, &req->flags)) - return; - - if (sense && sense[1] & SNS1_NO_REC_FOUND && - test_bit(DASD_CQR_SUPPRESS_NRF, &req->flags)) - return; - + else dasd_eckd_dump_sense_ccw(device, req, irb); - } } static int dasd_eckd_reload_device(struct dasd_device *device) diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index e5f40536b425..81cfb5c89681 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -196,7 +196,7 @@ struct dasd_ccw_req { * The following flags are used to suppress output of certain errors. */ #define DASD_CQR_SUPPRESS_NRF 4 /* Suppress 'No Record Found' error */ -#define DASD_CQR_SUPPRESS_FP 5 /* Suppress 'File Protected' error*/ +#define DASD_CQR_SUPPRESS_IT 5 /* Suppress 'Invalid Track' error*/ #define DASD_CQR_SUPPRESS_IL 6 /* Suppress 'Incorrect Length' error */ #define DASD_CQR_SUPPRESS_CR 7 /* Suppress 'Command Reject' error */ From 84f2eecf95018386c145ada19bb45b03bdb80d9e Mon Sep 17 00:00:00 2001 From: Olivier Langlois Date: Sun, 11 Aug 2024 14:07:11 -0400 Subject: [PATCH 142/562] io_uring/napi: check napi_enabled in io_napi_add() before proceeding doing so avoids the overhead of adding napi ids to all the rings that do not enable napi. if no id is added to napi_list because napi is disabled, __io_napi_busy_loop() will not be called. Signed-off-by: Olivier Langlois Fixes: b4ccc4dd1330 ("io_uring/napi: enable even with a timeout of 0") Link: https://lore.kernel.org/r/bd989ccef5fda14f5fd9888faf4fefcf66bd0369.1723400131.git.olivier@trillion01.com Signed-off-by: Jens Axboe --- io_uring/napi.c | 2 +- io_uring/napi.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/io_uring/napi.c b/io_uring/napi.c index a3dc3762008f..73c4159e8405 100644 --- a/io_uring/napi.c +++ b/io_uring/napi.c @@ -302,7 +302,7 @@ void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) { iowq->napi_prefer_busy_poll = READ_ONCE(ctx->napi_prefer_busy_poll); - if (!(ctx->flags & IORING_SETUP_SQPOLL) && ctx->napi_enabled) + if (!(ctx->flags & IORING_SETUP_SQPOLL)) io_napi_blocking_busy_loop(ctx, iowq); } diff --git a/io_uring/napi.h b/io_uring/napi.h index 88f1c21d5548..27b88c3eb428 100644 --- a/io_uring/napi.h +++ b/io_uring/napi.h @@ -55,7 +55,7 @@ static inline void io_napi_add(struct io_kiocb *req) struct io_ring_ctx *ctx = req->ctx; struct socket *sock; - if (!READ_ONCE(ctx->napi_busy_poll_dt)) + if (!READ_ONCE(ctx->napi_enabled)) return; sock = sock_from_file(req->file); From 48cc7ecd3a68e0fbfa281ef1ed6f6b6cb7638390 Mon Sep 17 00:00:00 2001 From: Olivier Langlois Date: Sun, 11 Aug 2024 20:34:46 -0400 Subject: [PATCH 143/562] io_uring/napi: remove duplicate io_napi_entry timeout assignation io_napi_entry() has 2 calling sites. One of them is unlikely to find an entry and if it does, the timeout should arguable not be updated. The other io_napi_entry() calling site is overwriting the update made by io_napi_entry() so the io_napi_entry() timeout value update has no or little value and therefore is removed. Signed-off-by: Olivier Langlois Link: https://lore.kernel.org/r/145b54ff179f87609e20dffaf5563c07cdbcad1a.1723423275.git.olivier@trillion01.com Signed-off-by: Jens Axboe --- io_uring/napi.c | 1 - 1 file changed, 1 deletion(-) diff --git a/io_uring/napi.c b/io_uring/napi.c index 73c4159e8405..1de1d4d62925 100644 --- a/io_uring/napi.c +++ b/io_uring/napi.c @@ -26,7 +26,6 @@ static struct io_napi_entry *io_napi_hash_find(struct hlist_head *hash_list, hlist_for_each_entry_rcu(e, hash_list, node) { if (e->napi_id != napi_id) continue; - e->timeout = jiffies + NAPI_TIMEOUT; return e; } From 98055bc3595500bcf2126b93b1595354bdb86a66 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 27 May 2024 21:17:32 +0100 Subject: [PATCH 144/562] netfs: Fault in smaller chunks for non-large folio mappings As in commit 4e527d5841e2 ("iomap: fault in smaller chunks for non-large folio mappings"), we can see a performance loss for filesystems which have not yet been converted to large folios. Fixes: c38f4e96e605 ("netfs: Provide func to copy data to pagecache for buffered write") Signed-off-by: Matthew Wilcox (Oracle) Link: https://lore.kernel.org/r/20240527201735.1898381-1-willy@infradead.org Reviewed-by: Jeff Layton Signed-off-by: Christian Brauner --- fs/netfs/buffered_write.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 4726c315453c..ca53c5d1622e 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -184,7 +184,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0; ssize_t written = 0, ret, ret2; loff_t i_size, pos = iocb->ki_pos, from, to; - size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER; + size_t max_chunk = mapping_max_folio_size(mapping); bool maybe_trouble = false; if (unlikely(test_bit(NETFS_ICTX_WRITETHROUGH, &ctx->flags) || From 3f65f3c099bcb27949e712f39ba836f21785924a Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Mon, 29 Jul 2024 15:48:12 -0700 Subject: [PATCH 145/562] filelock: fix name of file_lease slab cache When struct file_lease was split out from struct file_lock, the name of the file_lock slab cache was copied to the new slab cache for file_lease. This name conflict causes confusion in /proc/slabinfo and /sys/kernel/slab. In particular, it caused failures in drgn's test case for slab cache merging. Link: https://github.com/osandov/drgn/blob/9ad29fd86499eb32847473e928b6540872d3d59a/tests/linux_kernel/helpers/test_slab.py#L81 Fixes: c69ff4071935 ("filelock: split leases out of struct file_lock") Signed-off-by: Omar Sandoval Link: https://lore.kernel.org/r/2d1d053da1cafb3e7940c4f25952da4f0af34e38.1722293276.git.osandov@fb.com Reviewed-by: Chuck Lever Reviewed-by: Jeff Layton Signed-off-by: Christian Brauner --- fs/locks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/locks.c b/fs/locks.c index 9afb16e0683f..e45cad40f8b6 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2984,7 +2984,7 @@ static int __init filelock_init(void) filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL); - filelease_cache = kmem_cache_create("file_lock_cache", + filelease_cache = kmem_cache_create("file_lease_cache", sizeof(struct file_lease), 0, SLAB_PANIC, NULL); for_each_possible_cpu(i) { From f71aa06398aabc2e3eaac25acdf3d62e0094ba70 Mon Sep 17 00:00:00 2001 From: Max Kellermann Date: Mon, 29 Jul 2024 17:19:30 +0100 Subject: [PATCH 146/562] fs/netfs/fscache_cookie: add missing "n_accesses" check This fixes a NULL pointer dereference bug due to a data race which looks like this: BUG: kernel NULL pointer dereference, address: 0000000000000008 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 33 PID: 16573 Comm: kworker/u97:799 Not tainted 6.8.7-cm4all1-hp+ #43 Hardware name: HP ProLiant DL380 Gen9/ProLiant DL380 Gen9, BIOS P89 10/17/2018 Workqueue: events_unbound netfs_rreq_write_to_cache_work RIP: 0010:cachefiles_prepare_write+0x30/0xa0 Code: 57 41 56 45 89 ce 41 55 49 89 cd 41 54 49 89 d4 55 53 48 89 fb 48 83 ec 08 48 8b 47 08 48 83 7f 10 00 48 89 34 24 48 8b 68 20 <48> 8b 45 08 4c 8b 38 74 45 49 8b 7f 50 e8 4e a9 b0 ff 48 8b 73 10 RSP: 0018:ffffb4e78113bde0 EFLAGS: 00010286 RAX: ffff976126be6d10 RBX: ffff97615cdb8438 RCX: 0000000000020000 RDX: ffff97605e6c4c68 RSI: ffff97605e6c4c60 RDI: ffff97615cdb8438 RBP: 0000000000000000 R08: 0000000000278333 R09: 0000000000000001 R10: ffff97605e6c4600 R11: 0000000000000001 R12: ffff97605e6c4c68 R13: 0000000000020000 R14: 0000000000000001 R15: ffff976064fe2c00 FS: 0000000000000000(0000) GS:ffff9776dfd40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 000000005942c002 CR4: 00000000001706f0 Call Trace: ? __die+0x1f/0x70 ? page_fault_oops+0x15d/0x440 ? search_module_extables+0xe/0x40 ? fixup_exception+0x22/0x2f0 ? exc_page_fault+0x5f/0x100 ? asm_exc_page_fault+0x22/0x30 ? cachefiles_prepare_write+0x30/0xa0 netfs_rreq_write_to_cache_work+0x135/0x2e0 process_one_work+0x137/0x2c0 worker_thread+0x2e9/0x400 ? __pfx_worker_thread+0x10/0x10 kthread+0xcc/0x100 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x30/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 Modules linked in: CR2: 0000000000000008 ---[ end trace 0000000000000000 ]--- This happened because fscache_cookie_state_machine() was slow and was still running while another process invoked fscache_unuse_cookie(); this led to a fscache_cookie_lru_do_one() call, setting the FSCACHE_COOKIE_DO_LRU_DISCARD flag, which was picked up by fscache_cookie_state_machine(), withdrawing the cookie via cachefiles_withdraw_cookie(), clearing cookie->cache_priv. At the same time, yet another process invoked cachefiles_prepare_write(), which found a NULL pointer in this code line: struct cachefiles_object *object = cachefiles_cres_object(cres); The next line crashes, obviously: struct cachefiles_cache *cache = object->volume->cache; During cachefiles_prepare_write(), the "n_accesses" counter is non-zero (via fscache_begin_operation()). The cookie must not be withdrawn until it drops to zero. The counter is checked by fscache_cookie_state_machine() before switching to FSCACHE_COOKIE_STATE_RELINQUISHING and FSCACHE_COOKIE_STATE_WITHDRAWING (in "case FSCACHE_COOKIE_STATE_FAILED"), but not for FSCACHE_COOKIE_STATE_LRU_DISCARDING ("case FSCACHE_COOKIE_STATE_ACTIVE"). This patch adds the missing check. With a non-zero access counter, the function returns and the next fscache_end_cookie_access() call will queue another fscache_cookie_state_machine() call to handle the still-pending FSCACHE_COOKIE_DO_LRU_DISCARD. Fixes: 12bb21a29c19 ("fscache: Implement cookie user counting and resource pinning") Signed-off-by: Max Kellermann Signed-off-by: David Howells Link: https://lore.kernel.org/r/20240729162002.3436763-2-dhowells@redhat.com cc: Jeff Layton cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org cc: stable@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/fscache_cookie.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/netfs/fscache_cookie.c b/fs/netfs/fscache_cookie.c index bce2492186d0..d4d4b3a8b106 100644 --- a/fs/netfs/fscache_cookie.c +++ b/fs/netfs/fscache_cookie.c @@ -741,6 +741,10 @@ again_locked: spin_lock(&cookie->lock); } if (test_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags)) { + if (atomic_read(&cookie->n_accesses) != 0) + /* still being accessed: postpone it */ + break; + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_LRU_DISCARDING); wake = true; From 42b0f8da3acc87953161baeb24f756936eb4d4b2 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 31 Jul 2024 07:47:27 +0200 Subject: [PATCH 147/562] nsfs: fix ioctl declaration The kernel is writing an object of type __u64, so the ioctl has to be defined to _IOR(NSIO, 0x5, __u64) instead of _IO(NSIO, 0x5). Reported-by: Dmitry V. Levin Link: https://lore.kernel.org/r/20240730164554.GA18486@altlinux.org Signed-off-by: Christian Brauner --- include/uapi/linux/nsfs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index b133211331f6..5fad3d0fcd70 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -3,6 +3,7 @@ #define __LINUX_NSFS_H #include +#include #define NSIO 0xb7 @@ -16,7 +17,7 @@ /* Get owner UID (in the caller's user namespace) for a user namespace */ #define NS_GET_OWNER_UID _IO(NSIO, 0x4) /* Get the id for a mount namespace */ -#define NS_GET_MNTNS_ID _IO(NSIO, 0x5) +#define NS_GET_MNTNS_ID _IOR(NSIO, 0x5, __u64) /* Translate pid from target pid namespace into the caller's pid namespace. */ #define NS_GET_PID_FROM_PIDNS _IOR(NSIO, 0x6, int) /* Return thread-group leader id of pid in the callers pid namespace. */ From 64a7ce76fb901bf9f9c36cf5d681328fc0fd4b5a Mon Sep 17 00:00:00 2001 From: yangerkun Date: Wed, 31 Jul 2024 12:38:35 +0800 Subject: [PATCH 148/562] libfs: fix infinite directory reads for offset dir After we switch tmpfs dir operations from simple_dir_operations to simple_offset_dir_operations, every rename happened will fill new dentry to dest dir's maple tree(&SHMEM_I(inode)->dir_offsets->mt) with a free key starting with octx->newx_offset, and then set newx_offset equals to free key + 1. This will lead to infinite readdir combine with rename happened at the same time, which fail generic/736 in xfstests(detail show as below). 1. create 5000 files(1 2 3...) under one dir 2. call readdir(man 3 readdir) once, and get one entry 3. rename(entry, "TEMPFILE"), then rename("TEMPFILE", entry) 4. loop 2~3, until readdir return nothing or we loop too many times(tmpfs break test with the second condition) We choose the same logic what commit 9b378f6ad48cf ("btrfs: fix infinite directory reads") to fix it, record the last_index when we open dir, and do not emit the entry which index >= last_index. The file->private_data now used in offset dir can use directly to do this, and we also update the last_index when we llseek the dir file. Fixes: a2e459555c5f ("shmem: stable directory offsets") Signed-off-by: yangerkun Link: https://lore.kernel.org/r/20240731043835.1828697-1-yangerkun@huawei.com Reviewed-by: Chuck Lever [brauner: only update last_index after seek when offset is zero like Jan suggested] Signed-off-by: Christian Brauner --- fs/libfs.c | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) diff --git a/fs/libfs.c b/fs/libfs.c index 8aa34870449f..02602d00939e 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -450,6 +450,14 @@ void simple_offset_destroy(struct offset_ctx *octx) mtree_destroy(&octx->mt); } +static int offset_dir_open(struct inode *inode, struct file *file) +{ + struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); + + file->private_data = (void *)ctx->next_offset; + return 0; +} + /** * offset_dir_llseek - Advance the read position of a directory descriptor * @file: an open directory whose position is to be updated @@ -463,6 +471,9 @@ void simple_offset_destroy(struct offset_ctx *octx) */ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) { + struct inode *inode = file->f_inode; + struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); + switch (whence) { case SEEK_CUR: offset += file->f_pos; @@ -476,7 +487,8 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) } /* In this case, ->private_data is protected by f_pos_lock */ - file->private_data = NULL; + if (!offset) + file->private_data = (void *)ctx->next_offset; return vfs_setpos(file, offset, LONG_MAX); } @@ -507,7 +519,7 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) inode->i_ino, fs_umode_to_dtype(inode->i_mode)); } -static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) +static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, long last_index) { struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *dentry; @@ -515,17 +527,21 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) while (true) { dentry = offset_find_next(octx, ctx->pos); if (!dentry) - return ERR_PTR(-ENOENT); + return; + + if (dentry2offset(dentry) >= last_index) { + dput(dentry); + return; + } if (!offset_dir_emit(ctx, dentry)) { dput(dentry); - break; + return; } ctx->pos = dentry2offset(dentry) + 1; dput(dentry); } - return NULL; } /** @@ -552,22 +568,19 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) static int offset_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; + long last_index = (long)file->private_data; lockdep_assert_held(&d_inode(dir)->i_rwsem); if (!dir_emit_dots(file, ctx)) return 0; - /* In this case, ->private_data is protected by f_pos_lock */ - if (ctx->pos == DIR_OFFSET_MIN) - file->private_data = NULL; - else if (file->private_data == ERR_PTR(-ENOENT)) - return 0; - file->private_data = offset_iterate_dir(d_inode(dir), ctx); + offset_iterate_dir(d_inode(dir), ctx, last_index); return 0; } const struct file_operations simple_offset_dir_operations = { + .open = offset_dir_open, .llseek = offset_dir_llseek, .iterate_shared = offset_readdir, .read = generic_read_dir, From 889ced4c9388785952d78d20d338bda2df209bb5 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Wed, 31 Jul 2024 09:39:02 +0200 Subject: [PATCH 149/562] netfs: clean up after renaming FSCACHE_DEBUG config Commit 6b8e61472529 ("netfs: Rename CONFIG_FSCACHE_DEBUG to CONFIG_NETFS_DEBUG") renames the config, but introduces two issues: First, NETFS_DEBUG mistakenly depends on the non-existing config NETFS, whereas the actual intended config is called NETFS_SUPPORT. Second, the config renaming misses to adjust the documentation of the functionality of this config. Clean up those two points. Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20240731073902.69262-1-lukas.bulwahn@redhat.com Signed-off-by: Christian Brauner --- Documentation/filesystems/caching/fscache.rst | 8 ++++---- fs/netfs/Kconfig | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/Documentation/filesystems/caching/fscache.rst b/Documentation/filesystems/caching/fscache.rst index a74d7b052dc1..de1f32526cc1 100644 --- a/Documentation/filesystems/caching/fscache.rst +++ b/Documentation/filesystems/caching/fscache.rst @@ -318,10 +318,10 @@ where the columns are: Debugging ========= -If CONFIG_FSCACHE_DEBUG is enabled, the FS-Cache facility can have runtime -debugging enabled by adjusting the value in:: +If CONFIG_NETFS_DEBUG is enabled, the FS-Cache facility and NETFS support can +have runtime debugging enabled by adjusting the value in:: - /sys/module/fscache/parameters/debug + /sys/module/netfs/parameters/debug This is a bitmask of debugging streams to enable: @@ -343,6 +343,6 @@ This is a bitmask of debugging streams to enable: The appropriate set of values should be OR'd together and the result written to the control file. For example:: - echo $((1|8|512)) >/sys/module/fscache/parameters/debug + echo $((1|8|512)) >/sys/module/netfs/parameters/debug will turn on all function entry debugging. diff --git a/fs/netfs/Kconfig b/fs/netfs/Kconfig index 1b78e8b65ebc..7701c037c328 100644 --- a/fs/netfs/Kconfig +++ b/fs/netfs/Kconfig @@ -24,7 +24,7 @@ config NETFS_STATS config NETFS_DEBUG bool "Enable dynamic debugging netfslib and FS-Cache" - depends on NETFS + depends on NETFS_SUPPORT help This permits debugging to be dynamically enabled in the local caching management module. If this is set, the debugging output may be From 3b5bbe798b2451820e74243b738268f51901e7d0 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 31 Jul 2024 12:01:12 +0200 Subject: [PATCH 150/562] pidfd: prevent creation of pidfds for kthreads It's currently possible to create pidfds for kthreads but it is unclear what that is supposed to mean. Until we have use-cases for it and we figured out what behavior we want block the creation of pidfds for kthreads. Link: https://lore.kernel.org/r/20240731-gleis-mehreinnahmen-6bbadd128383@brauner Fixes: 32fcb426ec00 ("pid: add pidfd_open()") Cc: stable@vger.kernel.org Signed-off-by: Christian Brauner --- kernel/fork.c | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index cc760491f201..18bdc87209d0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2053,11 +2053,24 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { - bool thread = flags & PIDFD_THREAD; - - if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID)) + if (!pid) return -EINVAL; + scoped_guard(rcu) { + struct task_struct *tsk; + + if (flags & PIDFD_THREAD) + tsk = pid_task(pid, PIDTYPE_PID); + else + tsk = pid_task(pid, PIDTYPE_TGID); + if (!tsk) + return -EINVAL; + + /* Don't create pidfds for kernel threads for now. */ + if (tsk->flags & PF_KTHREAD) + return -EINVAL; + } + return __pidfd_prepare(pid, flags, ret); } @@ -2403,6 +2416,12 @@ __latent_entropy struct task_struct *copy_process( if (clone_flags & CLONE_PIDFD) { int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0; + /* Don't create pidfds for kernel threads for now. */ + if (args->kthread) { + retval = -EINVAL; + goto bad_fork_free_pid; + } + /* Note that no task has been attached to @pid yet. */ retval = __pidfd_prepare(pid, flags, &pidfile); if (retval < 0) From 86509e38a80da34d7800985fa2be183475242c8c Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Fri, 9 Aug 2024 15:50:35 +0200 Subject: [PATCH 151/562] file: fix typo in take_fd() comment The explanatory comment above take_fd() contains a typo, fix that to not confuse readers. Signed-off-by: Mathias Krause Link: https://lore.kernel.org/r/20240809135035.748109-1-minipli@grsecurity.net Signed-off-by: Christian Brauner --- include/linux/file.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/file.h b/include/linux/file.h index 237931f20739..59b146a14dca 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -110,7 +110,7 @@ DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), * * f = dentry_open(&path, O_RDONLY, current_cred()); * if (IS_ERR(f)) - * return PTR_ERR(fd); + * return PTR_ERR(f); * * fd_install(fd, f); * return take_fd(fd); From 8e5ced7804cb9184c4a23f8054551240562a8eda Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 30 Jul 2024 17:01:40 +0100 Subject: [PATCH 152/562] netfs, ceph: Revert "netfs: Remove deprecated use of PG_private_2 as a second writeback flag" This reverts commit ae678317b95e760607c7b20b97c9cd4ca9ed6e1a. Revert the patch that removes the deprecated use of PG_private_2 in netfslib for the moment as Ceph is actually still using this to track data copied to the cache. Fixes: ae678317b95e ("netfs: Remove deprecated use of PG_private_2 as a second writeback flag") Reported-by: Max Kellermann Signed-off-by: David Howells cc: Ilya Dryomov cc: Xiubo Li cc: Jeff Layton cc: Matthew Wilcox cc: ceph-devel@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org https: //lore.kernel.org/r/3575457.1722355300@warthog.procyon.org.uk Signed-off-by: Christian Brauner --- fs/ceph/addr.c | 19 ++++- fs/netfs/buffered_read.c | 8 +- fs/netfs/io.c | 144 +++++++++++++++++++++++++++++++++++ include/trace/events/netfs.h | 1 + 4 files changed, 170 insertions(+), 2 deletions(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8c16bc5250ef..73b5a07bf94d 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -498,6 +498,11 @@ const struct netfs_request_ops ceph_netfs_ops = { }; #ifdef CONFIG_CEPH_FSCACHE +static void ceph_set_page_fscache(struct page *page) +{ + folio_start_private_2(page_folio(page)); /* [DEPRECATED] */ +} + static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async) { struct inode *inode = priv; @@ -515,6 +520,10 @@ static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, b ceph_fscache_write_terminated, inode, true, caching); } #else +static inline void ceph_set_page_fscache(struct page *page) +{ +} + static inline void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching) { } @@ -706,6 +715,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) len = wlen; set_page_writeback(page); + if (caching) + ceph_set_page_fscache(page); ceph_fscache_write_to_cache(inode, page_off, len, caching); if (IS_ENCRYPTED(inode)) { @@ -789,6 +800,8 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc) return AOP_WRITEPAGE_ACTIVATE; } + folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */ + err = writepage_nounlock(page, wbc); if (err == -ERESTARTSYS) { /* direct memory reclaimer was killed by SIGKILL. return 0 @@ -1062,7 +1075,8 @@ get_more_pages: unlock_page(page); break; } - if (PageWriteback(page)) { + if (PageWriteback(page) || + PagePrivate2(page) /* [DEPRECATED] */) { if (wbc->sync_mode == WB_SYNC_NONE) { doutc(cl, "%p under writeback\n", page); unlock_page(page); @@ -1070,6 +1084,7 @@ get_more_pages: } doutc(cl, "waiting on writeback %p\n", page); wait_on_page_writeback(page); + folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */ } if (!clear_page_dirty_for_io(page)) { @@ -1254,6 +1269,8 @@ new_request: } set_page_writeback(page); + if (caching) + ceph_set_page_fscache(page); len += thp_size(page); } ceph_fscache_write_to_cache(inode, offset, len, caching); diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index a688d4c75d99..424048f9ed1f 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -466,7 +466,7 @@ retry: if (!netfs_is_cache_enabled(ctx) && netfs_skip_folio_read(folio, pos, len, false)) { netfs_stat(&netfs_n_rh_write_zskip); - goto have_folio; + goto have_folio_no_wait; } rreq = netfs_alloc_request(mapping, file, @@ -507,6 +507,12 @@ retry: netfs_put_request(rreq, false, netfs_rreq_trace_put_return); have_folio: + if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags)) { + ret = folio_wait_private_2_killable(folio); + if (ret < 0) + goto error; + } +have_folio_no_wait: *_folio = folio; _leave(" = 0"); return 0; diff --git a/fs/netfs/io.c b/fs/netfs/io.c index c93851b98368..c179a1c73fa7 100644 --- a/fs/netfs/io.c +++ b/fs/netfs/io.c @@ -98,6 +98,146 @@ static void netfs_rreq_completed(struct netfs_io_request *rreq, bool was_async) netfs_put_request(rreq, was_async, netfs_rreq_trace_put_complete); } +/* + * [DEPRECATED] Deal with the completion of writing the data to the cache. We + * have to clear the PG_fscache bits on the folios involved and release the + * caller's ref. + * + * May be called in softirq mode and we inherit a ref from the caller. + */ +static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq, + bool was_async) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + pgoff_t unlocked = 0; + bool have_unlocked = false; + + rcu_read_lock(); + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); + + xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { + if (xas_retry(&xas, folio)) + continue; + + /* We might have multiple writes from the same huge + * folio, but we mustn't unlock a folio more than once. + */ + if (have_unlocked && folio->index <= unlocked) + continue; + unlocked = folio_next_index(folio) - 1; + trace_netfs_folio(folio, netfs_folio_trace_end_copy); + folio_end_private_2(folio); + have_unlocked = true; + } + } + + rcu_read_unlock(); + netfs_rreq_completed(rreq, was_async); +} + +static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error, + bool was_async) /* [DEPRECATED] */ +{ + struct netfs_io_subrequest *subreq = priv; + struct netfs_io_request *rreq = subreq->rreq; + + if (IS_ERR_VALUE(transferred_or_error)) { + netfs_stat(&netfs_n_rh_write_failed); + trace_netfs_failure(rreq, subreq, transferred_or_error, + netfs_fail_copy_to_cache); + } else { + netfs_stat(&netfs_n_rh_write_done); + } + + trace_netfs_sreq(subreq, netfs_sreq_trace_write_term); + + /* If we decrement nr_copy_ops to 0, the ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, was_async); + + netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); +} + +/* + * [DEPRECATED] Perform any outstanding writes to the cache. We inherit a ref + * from the caller. + */ +static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + struct netfs_io_subrequest *subreq, *next, *p; + struct iov_iter iter; + int ret; + + trace_netfs_rreq(rreq, netfs_rreq_trace_copy); + + /* We don't want terminating writes trying to wake us up whilst we're + * still going through the list. + */ + atomic_inc(&rreq->nr_copy_ops); + + list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) { + if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { + list_del_init(&subreq->rreq_link); + netfs_put_subrequest(subreq, false, + netfs_sreq_trace_put_no_copy); + } + } + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + /* Amalgamate adjacent writes */ + while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + next = list_next_entry(subreq, rreq_link); + if (next->start != subreq->start + subreq->len) + break; + subreq->len += next->len; + list_del_init(&next->rreq_link); + netfs_put_subrequest(next, false, + netfs_sreq_trace_put_merged); + } + + ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, + subreq->len, rreq->i_size, true); + if (ret < 0) { + trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); + trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); + continue; + } + + iov_iter_xarray(&iter, ITER_SOURCE, &rreq->mapping->i_pages, + subreq->start, subreq->len); + + atomic_inc(&rreq->nr_copy_ops); + netfs_stat(&netfs_n_rh_write); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_copy_to_cache); + trace_netfs_sreq(subreq, netfs_sreq_trace_write); + cres->ops->write(cres, subreq->start, &iter, + netfs_rreq_copy_terminated, subreq); + } + + /* If we decrement nr_copy_ops to 0, the usage ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, false); +} + +static void netfs_rreq_write_to_cache_work(struct work_struct *work) /* [DEPRECATED] */ +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + + netfs_rreq_do_write_to_cache(rreq); +} + +static void netfs_rreq_write_to_cache(struct netfs_io_request *rreq) /* [DEPRECATED] */ +{ + rreq->work.func = netfs_rreq_write_to_cache_work; + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); +} + /* * Handle a short read. */ @@ -275,6 +415,10 @@ again: clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags) && + test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) + return netfs_rreq_write_to_cache(rreq); + netfs_rreq_completed(rreq, was_async); } diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index da23484268df..24ec3434d32e 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -145,6 +145,7 @@ EM(netfs_folio_trace_clear_g, "clear-g") \ EM(netfs_folio_trace_clear_s, "clear-s") \ EM(netfs_folio_trace_copy_to_cache, "mark-copy") \ + EM(netfs_folio_trace_end_copy, "end-copy") \ EM(netfs_folio_trace_filled_gaps, "filled-gaps") \ EM(netfs_folio_trace_kill, "kill") \ EM(netfs_folio_trace_kill_cc, "kill-cc") \ From 7b589a9b45ae32aa9d7bece597490e141198d7a6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 7 Aug 2024 19:38:46 +0100 Subject: [PATCH 153/562] netfs: Fix handling of USE_PGPRIV2 and WRITE_TO_CACHE flags The NETFS_RREQ_USE_PGPRIV2 and NETFS_RREQ_WRITE_TO_CACHE flags aren't used correctly. The problem is that we try to set them up in the request initialisation, but we the cache may be in the process of setting up still, and so the state may not be correct. Further, we secondarily sample the cache state and make contradictory decisions later. The issue arises because we set up the cache resources, which allows the cache's ->prepare_read() to switch on NETFS_SREQ_COPY_TO_CACHE - which triggers cache writing even if we didn't set the flags when allocating. Fix this in the following way: (1) Drop NETFS_ICTX_USE_PGPRIV2 and instead set NETFS_RREQ_USE_PGPRIV2 in ->init_request() rather than trying to juggle that in netfs_alloc_request(). (2) Repurpose NETFS_RREQ_USE_PGPRIV2 to merely indicate that if caching is to be done, then PG_private_2 is to be used rather than only setting it if we decide to cache and then having netfs_rreq_unlock_folios() set the non-PG_private_2 writeback-to-cache if it wasn't set. (3) Split netfs_rreq_unlock_folios() into two functions, one of which contains the deprecated code for using PG_private_2 to avoid accidentally doing the writeback path - and always use it if USE_PGPRIV2 is set. (4) As NETFS_ICTX_USE_PGPRIV2 is removed, make netfs_write_begin() always wait for PG_private_2. This function is deprecated and only used by ceph anyway, and so label it so. (5) Drop the NETFS_RREQ_WRITE_TO_CACHE flag and use fscache_operation_valid() on the cache_resources instead. This has the advantage of picking up the result of netfs_begin_cache_read() and fscache_begin_write_operation() - which are called after the object is initialised and will wait for the cache to come to a usable state. Just reverting ae678317b95e[1] isn't a sufficient fix, so this need to be applied on top of that. Without this as well, things like: rcu: INFO: rcu_sched detected expedited stalls on CPUs/tasks: { and: WARNING: CPU: 13 PID: 3621 at fs/ceph/caps.c:3386 may happen, along with some UAFs due to PG_private_2 not getting used to wait on writeback completion. Fixes: 2ff1e97587f4 ("netfs: Replace PG_fscache by setting folio->private and marking dirty") Reported-by: Max Kellermann Signed-off-by: David Howells cc: Ilya Dryomov cc: Xiubo Li cc: Hristo Venev cc: Jeff Layton cc: Matthew Wilcox cc: ceph-devel@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org Link: https://lore.kernel.org/r/3575457.1722355300@warthog.procyon.org.uk/ [1] Link: https://lore.kernel.org/r/1173209.1723152682@warthog.procyon.org.uk Signed-off-by: Christian Brauner --- fs/ceph/addr.c | 3 + fs/ceph/inode.c | 2 - fs/netfs/buffered_read.c | 125 ++++++++++++++++++++++++++++++----- fs/netfs/objects.c | 10 --- fs/netfs/write_issue.c | 4 +- fs/nfs/fscache.c | 2 + fs/nfs/fscache.h | 2 - include/linux/netfs.h | 3 - include/trace/events/netfs.h | 1 + 9 files changed, 116 insertions(+), 36 deletions(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 73b5a07bf94d..cc0a2240de98 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -424,6 +424,9 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) struct ceph_netfs_request_data *priv; int ret = 0; + /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ + __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); + if (rreq->origin != NETFS_READAHEAD) return 0; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 8f8de8f33abb..71cd70514efa 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -577,8 +577,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb) /* Set parameters for the netfs library */ netfs_inode_init(&ci->netfs, &ceph_netfs_ops, false); - /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ - __set_bit(NETFS_ICTX_USE_PGPRIV2, &ci->netfs.flags); spin_lock_init(&ci->i_ceph_lock); diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 424048f9ed1f..27c750d39476 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -9,6 +9,97 @@ #include #include "internal.h" +/* + * [DEPRECATED] Unlock the folios in a read operation for when the filesystem + * is using PG_private_2 and direct writing to the cache from here rather than + * marking the page for writeback. + * + * Note that we don't touch folio->private in this code. + */ +static void netfs_rreq_unlock_folios_pgpriv2(struct netfs_io_request *rreq, + size_t *account) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + pgoff_t start_page = rreq->start / PAGE_SIZE; + pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; + bool subreq_failed = false; + + XA_STATE(xas, &rreq->mapping->i_pages, start_page); + + /* Walk through the pagecache and the I/O request lists simultaneously. + * We may have a mixture of cached and uncached sections and we only + * really want to write out the uncached sections. This is slightly + * complicated by the possibility that we might have huge pages with a + * mixture inside. + */ + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + subreq_failed = (subreq->error < 0); + + trace_netfs_rreq(rreq, netfs_rreq_trace_unlock_pgpriv2); + + rcu_read_lock(); + xas_for_each(&xas, folio, last_page) { + loff_t pg_end; + bool pg_failed = false; + bool folio_started = false; + + if (xas_retry(&xas, folio)) + continue; + + pg_end = folio_pos(folio) + folio_size(folio) - 1; + + for (;;) { + loff_t sreq_end; + + if (!subreq) { + pg_failed = true; + break; + } + + if (!folio_started && + test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags) && + fscache_operation_valid(&rreq->cache_resources)) { + trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); + folio_start_private_2(folio); + folio_started = true; + } + + pg_failed |= subreq_failed; + sreq_end = subreq->start + subreq->len - 1; + if (pg_end < sreq_end) + break; + + *account += subreq->transferred; + if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + subreq = list_next_entry(subreq, rreq_link); + subreq_failed = (subreq->error < 0); + } else { + subreq = NULL; + subreq_failed = false; + } + + if (pg_end == sreq_end) + break; + } + + if (!pg_failed) { + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + } + + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { + if (folio->index == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) + _debug("no unlock"); + else + folio_unlock(folio); + } + } + rcu_read_unlock(); +} + /* * Unlock the folios in a read operation. We need to set PG_writeback on any * folios we're going to write back before we unlock them. @@ -35,6 +126,12 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) } } + /* Handle deprecated PG_private_2 case. */ + if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { + netfs_rreq_unlock_folios_pgpriv2(rreq, &account); + goto out; + } + /* Walk through the pagecache and the I/O request lists simultaneously. * We may have a mixture of cached and uncached sections and we only * really want to write out the uncached sections. This is slightly @@ -52,7 +149,6 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) loff_t pg_end; bool pg_failed = false; bool wback_to_cache = false; - bool folio_started = false; if (xas_retry(&xas, folio)) continue; @@ -66,17 +162,8 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) pg_failed = true; break; } - if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { - if (!folio_started && test_bit(NETFS_SREQ_COPY_TO_CACHE, - &subreq->flags)) { - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_start_private_2(folio); - folio_started = true; - } - } else { - wback_to_cache |= - test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); - } + + wback_to_cache |= test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); pg_failed |= subreq_failed; sreq_end = subreq->start + subreq->len - 1; if (pg_end < sreq_end) @@ -124,6 +211,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) } rcu_read_unlock(); +out: task_io_account_read(account); if (rreq->netfs_ops->done) rreq->netfs_ops->done(rreq); @@ -395,7 +483,7 @@ zero_out: } /** - * netfs_write_begin - Helper to prepare for writing + * netfs_write_begin - Helper to prepare for writing [DEPRECATED] * @ctx: The netfs context * @file: The file to read from * @mapping: The mapping to read from @@ -426,6 +514,9 @@ zero_out: * inode before calling this. * * This is usable whether or not caching is enabled. + * + * Note that this should be considered deprecated and netfs_perform_write() + * used instead. */ int netfs_write_begin(struct netfs_inode *ctx, struct file *file, struct address_space *mapping, @@ -507,11 +598,9 @@ retry: netfs_put_request(rreq, false, netfs_rreq_trace_put_return); have_folio: - if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags)) { - ret = folio_wait_private_2_killable(folio); - if (ret < 0) - goto error; - } + ret = folio_wait_private_2_killable(folio); + if (ret < 0) + goto error; have_folio_no_wait: *_folio = folio; _leave(" = 0"); diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index f4a642727479..0294df70c3ff 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -24,10 +24,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, struct netfs_io_request *rreq; mempool_t *mempool = ctx->ops->request_pool ?: &netfs_request_pool; struct kmem_cache *cache = mempool->pool_data; - bool is_unbuffered = (origin == NETFS_UNBUFFERED_WRITE || - origin == NETFS_DIO_READ || - origin == NETFS_DIO_WRITE); - bool cached = !is_unbuffered && netfs_is_cache_enabled(ctx); int ret; for (;;) { @@ -56,12 +52,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, refcount_set(&rreq->ref, 1); __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - if (cached) { - __set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags); - if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags)) - /* Filesystem uses deprecated PG_private_2 marking. */ - __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); - } if (file && file->f_flags & O_NONBLOCK) __set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags); if (rreq->netfs_ops->init_request) { diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 9258d30cffe3..3f7e37e50c7d 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -94,6 +94,8 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, { struct netfs_io_request *wreq; struct netfs_inode *ictx; + bool is_buffered = (origin == NETFS_WRITEBACK || + origin == NETFS_WRITETHROUGH); wreq = netfs_alloc_request(mapping, file, start, 0, origin); if (IS_ERR(wreq)) @@ -102,7 +104,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, _enter("R=%x", wreq->debug_id); ictx = netfs_inode(wreq->inode); - if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags)) + if (is_buffered && netfs_is_cache_enabled(ictx)) fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx)); wreq->contiguity = wreq->start; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 7202ce84d0eb..bf29a65c5027 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -265,6 +265,8 @@ static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *fi { rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file)); rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id); + /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ + __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); return 0; } diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index fbed0027996f..e8adae1bc260 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -81,8 +81,6 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs) static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi) { netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops, false); - /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ - __set_bit(NETFS_ICTX_USE_PGPRIV2, &nfsi->netfs.flags); } extern void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr); extern void nfs_netfs_read_completion(struct nfs_pgio_header *hdr); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 5d0288938cc2..983816608f15 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -73,8 +73,6 @@ struct netfs_inode { #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ #define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ -#define NETFS_ICTX_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark - * write to cache on read */ }; /* @@ -269,7 +267,6 @@ struct netfs_io_request { #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ -#define NETFS_RREQ_WRITE_TO_CACHE 7 /* Need to write to the cache */ #define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ #define NETFS_RREQ_NONBLOCK 9 /* Don't block if possible (O_NONBLOCK) */ #define NETFS_RREQ_BLOCKED 10 /* We blocked */ diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 24ec3434d32e..606b4a0f92da 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -51,6 +51,7 @@ EM(netfs_rreq_trace_resubmit, "RESUBMT") \ EM(netfs_rreq_trace_set_pause, "PAUSE ") \ EM(netfs_rreq_trace_unlock, "UNLOCK ") \ + EM(netfs_rreq_trace_unlock_pgpriv2, "UNLCK-2") \ EM(netfs_rreq_trace_unmark, "UNMARK ") \ EM(netfs_rreq_trace_wait_ip, "WAIT-IP") \ EM(netfs_rreq_trace_wait_pause, "WT-PAUS") \ From 6b9935da2a6b2a72774c15c844ae201a3fc362ac Mon Sep 17 00:00:00 2001 From: Shin'ichiro Kawasaki Date: Sat, 10 Aug 2024 13:27:00 +0900 Subject: [PATCH 154/562] scsi: mpi3mr: Add missing spin_lock_init() for mrioc->trigger_lock Commit fc4444941140 ("scsi: mpi3mr: HDB allocation and posting for hardware and firmware buffers") added the spinlock trigger_lock to the struct mpi3mr_ioc. However, spin_lock_init() call was not added for it, then the lock does not work as expected. Also, the kernel reports the message below when lockdep is enabled. INFO: trying to register non-static key. The code is fine but needs lockdep annotation, or maybe you didn't initialize this object before use? To fix the issue and to avoid the INFO message, add the missing spin_lock_init() call. Fixes: fc4444941140 ("scsi: mpi3mr: HDB allocation and posting for hardware and firmware buffers") Signed-off-by: Shin'ichiro Kawasaki Link: https://lore.kernel.org/r/20240810042701.661841-2-shinichiro.kawasaki@wdc.com Acked-by: Sathya Prakash Veerichetty Signed-off-by: Martin K. Petersen --- drivers/scsi/mpi3mr/mpi3mr_os.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c index ca8f132e03ae..616894571c6a 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_os.c +++ b/drivers/scsi/mpi3mr/mpi3mr_os.c @@ -5234,6 +5234,7 @@ mpi3mr_probe(struct pci_dev *pdev, const struct pci_device_id *id) spin_lock_init(&mrioc->watchdog_lock); spin_lock_init(&mrioc->chain_buf_lock); spin_lock_init(&mrioc->sas_node_lock); + spin_lock_init(&mrioc->trigger_lock); INIT_LIST_HEAD(&mrioc->fwevt_list); INIT_LIST_HEAD(&mrioc->tgtdev_list); From fdad456cbcca739bae1849549c7a999857c56f88 Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Sun, 28 Jul 2024 19:46:11 +0800 Subject: [PATCH 155/562] bpf: Fix updating attached freplace prog in prog_array map MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The commit f7866c358733 ("bpf: Fix null pointer dereference in resolve_prog_type() for BPF_PROG_TYPE_EXT") fixed a NULL pointer dereference panic, but didn't fix the issue that fails to update attached freplace prog to prog_array map. Since commit 1c123c567fb1 ("bpf: Resolve fext program type when checking map compatibility"), freplace prog and its target prog are able to tail call each other. And the commit 3aac1ead5eb6 ("bpf: Move prog->aux->linked_prog and trampoline into bpf_link on attach") sets prog->aux->dst_prog as NULL after attaching freplace prog to its target prog. After loading freplace the prog_array's owner type is BPF_PROG_TYPE_SCHED_CLS. Then, after attaching freplace its prog->aux->dst_prog is NULL. Then, while updating freplace in prog_array the bpf_prog_map_compatible() incorrectly returns false because resolve_prog_type() returns BPF_PROG_TYPE_EXT instead of BPF_PROG_TYPE_SCHED_CLS. After this patch the resolve_prog_type() returns BPF_PROG_TYPE_SCHED_CLS and update to prog_array can succeed. Fixes: f7866c358733 ("bpf: Fix null pointer dereference in resolve_prog_type() for BPF_PROG_TYPE_EXT") Cc: Toke Høiland-Jørgensen Cc: Martin KaFai Lau Acked-by: Yonghong Song Signed-off-by: Leon Hwang Link: https://lore.kernel.org/r/20240728114612.48486-2-leon.hwang@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 6503c85b10a3..7b776dae36e5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -856,8 +856,8 @@ static inline u32 type_flag(u32 type) /* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog) { - return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->dst_prog) ? - prog->aux->dst_prog->type : prog->type; + return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ? + prog->aux->saved_dst_prog_type : prog->type; } static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) From 6c17ea1f3eaa330d445ac14a9428402ce4e3055e Mon Sep 17 00:00:00 2001 From: "Nysal Jan K.A" Date: Wed, 31 Jul 2024 08:31:12 +0530 Subject: [PATCH 156/562] cpu/SMT: Enable SMT only if a core is online If a core is offline then enabling SMT should not online CPUs of this core. By enabling SMT, what is intended is either changing the SMT value from "off" to "on" or setting the SMT level (threads per core) from a lower to higher value. On PowerPC the ppc64_cpu utility can be used, among other things, to perform the following functions: ppc64_cpu --cores-on # Get the number of online cores ppc64_cpu --cores-on=X # Put exactly X cores online ppc64_cpu --offline-cores=X[,Y,...] # Put specified cores offline ppc64_cpu --smt={on|off|value} # Enable, disable or change SMT level If the user has decided to offline certain cores, enabling SMT should not online CPUs in those cores. This patch fixes the issue and changes the behaviour as described, by introducing an arch specific function topology_is_core_online(). It is currently implemented only for PowerPC. Fixes: 73c58e7e1412 ("powerpc: Add HOTPLUG_SMT support") Reported-by: Tyrel Datwyler Closes: https://groups.google.com/g/powerpc-utils-devel/c/wrwVzAAnRlI/m/5KJSoqP4BAAJ Signed-off-by: Nysal Jan K.A Reviewed-by: Shrikanth Hegde Reviewed-by: Thomas Gleixner Signed-off-by: Michael Ellerman Link: https://msgid.link/20240731030126.956210-2-nysal@linux.ibm.com --- Documentation/ABI/testing/sysfs-devices-system-cpu | 3 ++- kernel/cpu.c | 12 +++++++++++- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 325873385b71..de725ca3be82 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -562,7 +562,8 @@ Description: Control Symmetric Multi Threading (SMT) ================ ========================================= If control status is "forceoff" or "notsupported" writes - are rejected. + are rejected. Note that enabling SMT on PowerPC skips + offline cores. What: /sys/devices/system/cpu/cpuX/power/energy_perf_bias Date: March 2019 diff --git a/kernel/cpu.c b/kernel/cpu.c index 1209ddaec026..b1fd2a3db91a 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2689,6 +2689,16 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) return ret; } +/** + * Check if the core a CPU belongs to is online + */ +#if !defined(topology_is_core_online) +static inline bool topology_is_core_online(unsigned int cpu) +{ + return true; +} +#endif + int cpuhp_smt_enable(void) { int cpu, ret = 0; @@ -2699,7 +2709,7 @@ int cpuhp_smt_enable(void) /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) continue; - if (!cpu_smt_thread_allowed(cpu)) + if (!cpu_smt_thread_allowed(cpu) || !topology_is_core_online(cpu)) continue; ret = _cpu_up(cpu, 0, CPUHP_ONLINE); if (ret) From 227bbaabe64b6f9cd98aa051454c1d4a194a8c6a Mon Sep 17 00:00:00 2001 From: "Nysal Jan K.A" Date: Wed, 31 Jul 2024 08:31:13 +0530 Subject: [PATCH 157/562] powerpc/topology: Check if a core is online topology_is_core_online() checks if the core a CPU belongs to is online. The core is online if at least one of the sibling CPUs is online. The first CPU of an online core is also online in the common case, so this should be fairly quick. Fixes: 73c58e7e1412 ("powerpc: Add HOTPLUG_SMT support") Signed-off-by: Nysal Jan K.A Reviewed-by: Shrikanth Hegde Signed-off-by: Michael Ellerman Link: https://msgid.link/20240731030126.956210-3-nysal@linux.ibm.com --- arch/powerpc/include/asm/topology.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index f4e6f2dd04b7..16bacfe8c7a2 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -145,6 +145,7 @@ static inline int cpu_to_coregroup_id(int cpu) #ifdef CONFIG_HOTPLUG_SMT #include +#include #include static inline bool topology_is_primary_thread(unsigned int cpu) @@ -156,6 +157,18 @@ static inline bool topology_smt_thread_allowed(unsigned int cpu) { return cpu_thread_in_core(cpu) < cpu_smt_num_threads; } + +#define topology_is_core_online topology_is_core_online +static inline bool topology_is_core_online(unsigned int cpu) +{ + int i, first_cpu = cpu_first_thread_sibling(cpu); + + for (i = first_cpu; i < first_cpu + threads_per_core; ++i) { + if (cpu_online(i)) + return true; + } + return false; +} #endif #endif /* __KERNEL__ */ From 8c6b808c8c2a9de21503944bd6308979410fd812 Mon Sep 17 00:00:00 2001 From: Shin'ichiro Kawasaki Date: Sat, 10 Aug 2024 13:27:01 +0900 Subject: [PATCH 158/562] scsi: mpi3mr: Avoid MAX_PAGE_ORDER WARNING for buffer allocations Commit fc4444941140 ("scsi: mpi3mr: HDB allocation and posting for hardware and firmware buffers") added mpi3mr_alloc_diag_bufs() which calls dma_alloc_coherent() to allocate the trace buffer and the firmware buffer. mpi3mr_alloc_diag_bufs() decides the buffer sizes from the driver configuration. In my environment, the sizes are 8MB. With the sizes, dma_alloc_coherent() fails and report this WARNING: WARNING: CPU: 4 PID: 438 at mm/page_alloc.c:4676 __alloc_pages_noprof+0x52f/0x640 The WARNING indicates that the order of the allocation size is larger than MAX_PAGE_ORDER. After this failure, mpi3mr_alloc_diag_bufs() reduces the buffer sizes and retries dma_alloc_coherent(). In the end, the buffer allocations succeed with 4MB size in my environment, which corresponds to MAX_PAGE_ORDER=10. Though the allocations succeed, the WARNING message is misleading and should be avoided. To avoid the WARNING, check the orders of the buffer allocation sizes before calling dma_alloc_coherent(). If the orders are larger than MAX_PAGE_ORDER, fall back to the retry path. Fixes: fc4444941140 ("scsi: mpi3mr: HDB allocation and posting for hardware and firmware buffers") Signed-off-by: Shin'ichiro Kawasaki Link: https://lore.kernel.org/r/20240810042701.661841-3-shinichiro.kawasaki@wdc.com Acked-by: Sathya Prakash Veerichetty Signed-off-by: Martin K. Petersen --- drivers/scsi/mpi3mr/mpi3mr_app.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c index 8b0eded6ef36..01f035f9330e 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_app.c +++ b/drivers/scsi/mpi3mr/mpi3mr_app.c @@ -100,7 +100,8 @@ retry_trace: dprint_init(mrioc, "trying to allocate trace diag buffer of size = %dKB\n", trace_size / 1024); - if (mpi3mr_alloc_trace_buffer(mrioc, trace_size)) { + if (get_order(trace_size) > MAX_PAGE_ORDER || + mpi3mr_alloc_trace_buffer(mrioc, trace_size)) { retry = true; trace_size -= trace_dec_size; dprint_init(mrioc, "trace diag buffer allocation failed\n" @@ -118,8 +119,12 @@ retry_fw: diag_buffer->type = MPI3_DIAG_BUFFER_TYPE_FW; diag_buffer->status = MPI3MR_HDB_BUFSTATUS_NOT_ALLOCATED; if ((mrioc->facts.diag_fw_sz < fw_size) && (fw_size >= fw_min_size)) { - diag_buffer->addr = dma_alloc_coherent(&mrioc->pdev->dev, - fw_size, &diag_buffer->dma_addr, GFP_KERNEL); + if (get_order(fw_size) <= MAX_PAGE_ORDER) { + diag_buffer->addr + = dma_alloc_coherent(&mrioc->pdev->dev, fw_size, + &diag_buffer->dma_addr, + GFP_KERNEL); + } if (!retry) dprint_init(mrioc, "%s:trying to allocate firmware diag buffer of size = %dKB\n", From bed2eb964c70b780fb55925892a74f26cb590b25 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 12 Aug 2024 14:48:47 -0700 Subject: [PATCH 159/562] bpf: Fix a kernel verifier crash in stacksafe() Daniel Hodges reported a kernel verifier crash when playing with sched-ext. Further investigation shows that the crash is due to invalid memory access in stacksafe(). More specifically, it is the following code: if (exact != NOT_EXACT && old->stack[spi].slot_type[i % BPF_REG_SIZE] != cur->stack[spi].slot_type[i % BPF_REG_SIZE]) return false; The 'i' iterates old->allocated_stack. If cur->allocated_stack < old->allocated_stack the out-of-bound access will happen. To fix the issue add 'i >= cur->allocated_stack' check such that if the condition is true, stacksafe() should fail. Otherwise, cur->stack[spi].slot_type[i % BPF_REG_SIZE] memory access is legal. Fixes: 2793a8b015f7 ("bpf: exact states comparison for iterator convergence checks") Cc: Eduard Zingerman Reported-by: Daniel Hodges Acked-by: Eduard Zingerman Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20240812214847.213612-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4cb5441ad75f..d8520095ca03 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -16884,8 +16884,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, spi = i / BPF_REG_SIZE; if (exact != NOT_EXACT && - old->stack[spi].slot_type[i % BPF_REG_SIZE] != - cur->stack[spi].slot_type[i % BPF_REG_SIZE]) + (i >= cur->allocated_stack || + old->stack[spi].slot_type[i % BPF_REG_SIZE] != + cur->stack[spi].slot_type[i % BPF_REG_SIZE])) return false; if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ) From 662c3e2db00f92e50c26e9dc4fe47c52223d9982 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 12 Aug 2024 14:48:52 -0700 Subject: [PATCH 160/562] selftests/bpf: Add a test to verify previous stacksafe() fix A selftest is added such that without the previous patch, a crash can happen. With the previous patch, the test can run successfully. The new test is written in a way which mimics original crash case: main_prog static_prog_1 static_prog_2 where static_prog_1 has different paths to static_prog_2 and some path has stack allocated and some other path does not. A stacksafe() checking in static_prog_2() triggered the crash. Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20240812214852.214037-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/progs/iters.c | 54 +++++++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index 16bdc3e25591..ef70b88bccb2 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -1432,4 +1432,58 @@ int iter_arr_with_actual_elem_count(const void *ctx) return sum; } +__u32 upper, select_n, result; +__u64 global; + +static __noinline bool nest_2(char *str) +{ + /* some insns (including branch insns) to ensure stacksafe() is triggered + * in nest_2(). This way, stacksafe() can compare frame associated with nest_1(). + */ + if (str[0] == 't') + return true; + if (str[1] == 'e') + return true; + if (str[2] == 's') + return true; + if (str[3] == 't') + return true; + return false; +} + +static __noinline bool nest_1(int n) +{ + /* case 0: allocate stack, case 1: no allocate stack */ + switch (n) { + case 0: { + char comm[16]; + + if (bpf_get_current_comm(comm, 16)) + return false; + return nest_2(comm); + } + case 1: + return nest_2((char *)&global); + default: + return false; + } +} + +SEC("raw_tp") +__success +int iter_subprog_check_stacksafe(const void *ctx) +{ + long i; + + bpf_for(i, 0, upper) { + if (!nest_1(select_n)) { + result = 1; + return 0; + } + } + + result = 2; + return 0; +} + char _license[] SEC("license") = "GPL"; From 6e1918ff680527ce4be77426aa537012b5aa997c Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 7 Aug 2024 21:00:21 -0700 Subject: [PATCH 161/562] net: macb: Use rcu_dereference() for idev->ifa_list in macb_suspend(). In macb_suspend(), idev->ifa_list is fetched with rcu_access_pointer() and later the pointer is dereferenced as ifa->ifa_local. So, idev->ifa_list must be fetched with rcu_dereference(). Fixes: 0cb8de39a776 ("net: macb: Add ARP support to WOL") Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20240808040021.6971-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 11665be3a22c..dcd3f54ed0cf 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -5250,8 +5250,8 @@ static int __maybe_unused macb_suspend(struct device *dev) if (bp->wol & MACB_WOL_ENABLED) { /* Check for IP address in WOL ARP mode */ idev = __in_dev_get_rcu(bp->dev); - if (idev && idev->ifa_list) - ifa = rcu_access_pointer(idev->ifa_list); + if (idev) + ifa = rcu_dereference(idev->ifa_list); if ((bp->wolopts & WAKE_ARP) && !ifa) { netdev_err(netdev, "IP address not assigned as required by WoL walk ARP\n"); return -EOPNOTSUPP; From 046667c4d3196938e992fba0dfcde570aa85cd0e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 21 Jul 2024 14:45:08 -0400 Subject: [PATCH 162/562] memcg_write_event_control(): fix a user-triggerable oops we are *not* guaranteed that anything past the terminating NUL is mapped (let alone initialized with anything sane). Fixes: 0dea116876ee ("cgroup: implement eventfd-based generic API for notifications") Cc: stable@vger.kernel.org Cc: Andrew Morton Acked-by: Michal Hocko Signed-off-by: Al Viro --- mm/memcontrol-v1.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c index 2aeea4d8bf8e..417c96f2da28 100644 --- a/mm/memcontrol-v1.c +++ b/mm/memcontrol-v1.c @@ -1842,9 +1842,12 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, buf = endp + 1; cfd = simple_strtoul(buf, &endp, 10); - if ((*endp != ' ') && (*endp != '\0')) + if (*endp == '\0') + buf = endp; + else if (*endp == ' ') + buf = endp + 1; + else return -EINVAL; - buf = endp + 1; event = kzalloc(sizeof(*event), GFP_KERNEL); if (!event) From 3beddef84d90590270465a907de1cfe2539ac70d Mon Sep 17 00:00:00 2001 From: Baojun Xu Date: Tue, 13 Aug 2024 12:37:48 +0800 Subject: [PATCH 163/562] ALSA: hda/tas2781: fix wrong calibrated data order Wrong calibration data order cause sound too low in some device. Fix wrong calibrated data order, add calibration data converssion by get_unaligned_be32() after reading from UEFI. Fixes: 5be27f1e3ec9 ("ALSA: hda/tas2781: Add tas2781 HDA driver") Cc: Signed-off-by: Baojun Xu Link: https://patch.msgid.link/20240813043749.108-1-shenghao-ding@ti.com Signed-off-by: Takashi Iwai --- sound/pci/hda/tas2781_hda_i2c.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index 49bd7097d892..7dbfc92d9d55 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -2,10 +2,12 @@ // // TAS2781 HDA I2C driver // -// Copyright 2023 Texas Instruments, Inc. +// Copyright 2023 - 2024 Texas Instruments, Inc. // // Author: Shenghao Ding +// Current maintainer: Baojun Xu +#include #include #include #include @@ -519,20 +521,22 @@ static void tas2781_apply_calib(struct tasdevice_priv *tas_priv) static const unsigned char rgno_array[CALIB_MAX] = { 0x74, 0x0c, 0x14, 0x70, 0x7c, }; - unsigned char *data; + int offset = 0; int i, j, rc; + __be32 data; for (i = 0; i < tas_priv->ndev; i++) { - data = tas_priv->cali_data.data + - i * TASDEVICE_SPEAKER_CALIBRATION_SIZE; for (j = 0; j < CALIB_MAX; j++) { + data = get_unaligned_be32( + &tas_priv->cali_data.data[offset]); rc = tasdevice_dev_bulk_write(tas_priv, i, TASDEVICE_REG(0, page_array[j], rgno_array[j]), - &(data[4 * j]), 4); + (unsigned char *)&data, 4); if (rc < 0) dev_err(tas_priv->dev, "chn %d calib %d bulk_wr err = %d\n", i, j, rc); + offset += 4; } } } From d2dfed310aae0739dc87b68c660357e6a4f29819 Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Tue, 6 Aug 2024 11:46:03 +1200 Subject: [PATCH 164/562] platform/x86: asus-wmi: Add quirk for ROG Ally X MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The new ROG Ally X functions the same as the previus model so we can use the same method to ensure the MCU USB devices wake and reconnect correctly. Given that two devices marks the start of a trend, this patch also adds a quirk table to make future additions easier if the MCU is the same. Signed-off-by: Luke D. Jones Reviewed-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20240805234603.38736-1-luke@ljones.dev Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/asus-wmi.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index cc735931f97b..37636e5a38e3 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -146,6 +146,20 @@ static const char * const ashs_ids[] = { "ATK4001", "ATK4002", NULL }; static int throttle_thermal_policy_write(struct asus_wmi *); +static const struct dmi_system_id asus_ally_mcu_quirk[] = { + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "RC71L"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "RC72L"), + }, + }, + { }, +}; + static bool ashs_present(void) { int i = 0; @@ -4685,7 +4699,7 @@ static int asus_wmi_add(struct platform_device *pdev) asus->dgpu_disable_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_DGPU); asus->kbd_rgb_state_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_TUF_RGB_STATE); asus->ally_mcu_usb_switch = acpi_has_method(NULL, ASUS_USB0_PWR_EC0_CSEE) - && dmi_match(DMI_BOARD_NAME, "RC71L"); + && dmi_check_system(asus_ally_mcu_quirk); if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_MINI_LED_MODE)) asus->mini_led_dev_id = ASUS_WMI_DEVID_MINI_LED_MODE; From 9c8e022567bbec53bee8ae75c44b3d6cd2080d42 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Sun, 11 Aug 2024 15:19:44 +0200 Subject: [PATCH 165/562] platform/surface: aggregator_registry: Add Support for Surface Pro 10 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add SAM client device nodes for the Surface Pro 10. It seems to use the same SAM client devices as the Surface Pro 9, so re-use its node group. Signed-off-by: Maximilian Luz Link: https://lore.kernel.org/r/20240811131948.261806-2-luzmaximilian@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/surface/surface_aggregator_registry.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/platform/surface/surface_aggregator_registry.c b/drivers/platform/surface/surface_aggregator_registry.c index 1c4d74db08c9..fa5b896e5f4e 100644 --- a/drivers/platform/surface/surface_aggregator_registry.c +++ b/drivers/platform/surface/surface_aggregator_registry.c @@ -324,7 +324,7 @@ static const struct software_node *ssam_node_group_sp8[] = { NULL, }; -/* Devices for Surface Pro 9 */ +/* Devices for Surface Pro 9 and 10 */ static const struct software_node *ssam_node_group_sp9[] = { &ssam_node_root, &ssam_node_hub_kip, @@ -365,6 +365,9 @@ static const struct acpi_device_id ssam_platform_hub_match[] = { /* Surface Pro 9 */ { "MSHW0343", (unsigned long)ssam_node_group_sp9 }, + /* Surface Pro 10 */ + { "MSHW0510", (unsigned long)ssam_node_group_sp9 }, + /* Surface Book 2 */ { "MSHW0107", (unsigned long)ssam_node_group_gen5 }, From ed235163c3f02329d5e37ed4485bbc39ed2568d4 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Sun, 11 Aug 2024 15:19:45 +0200 Subject: [PATCH 166/562] platform/surface: aggregator_registry: Add support for Surface Laptop Go 3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add SAM client device nodes for the Surface Laptop Go 3. It seems to use the same SAM client devices as the Surface Laptop Go 1 and 2, so re-use their node group. Signed-off-by: Maximilian Luz Link: https://lore.kernel.org/r/20240811131948.261806-3-luzmaximilian@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/surface/surface_aggregator_registry.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/platform/surface/surface_aggregator_registry.c b/drivers/platform/surface/surface_aggregator_registry.c index fa5b896e5f4e..4d36810c2308 100644 --- a/drivers/platform/surface/surface_aggregator_registry.c +++ b/drivers/platform/surface/surface_aggregator_registry.c @@ -398,6 +398,9 @@ static const struct acpi_device_id ssam_platform_hub_match[] = { /* Surface Laptop Go 2 */ { "MSHW0290", (unsigned long)ssam_node_group_slg1 }, + /* Surface Laptop Go 3 */ + { "MSHW0440", (unsigned long)ssam_node_group_slg1 }, + /* Surface Laptop Studio */ { "MSHW0123", (unsigned long)ssam_node_group_sls }, From 28d04b4a2cc20981c95787f9c449e6fc51d904f9 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Sun, 11 Aug 2024 15:19:46 +0200 Subject: [PATCH 167/562] platform/surface: aggregator_registry: Add support for Surface Laptop Studio 2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add SAM client device nodes for the Surface Laptop Studio 2 (SLS2). The SLS2 is quite similar to the SLS1, but it does not provide the touchpad as a SAM-HID device. Therefore, add a new node group for the SLS2 and update the comments accordingly. In addition, it uses the new fan control interface. Signed-off-by: Maximilian Luz Link: https://lore.kernel.org/r/20240811131948.261806-4-luzmaximilian@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- .../surface/surface_aggregator_registry.c | 27 ++++++++++++++++--- 1 file changed, 23 insertions(+), 4 deletions(-) diff --git a/drivers/platform/surface/surface_aggregator_registry.c b/drivers/platform/surface/surface_aggregator_registry.c index 4d36810c2308..892ba9549f6a 100644 --- a/drivers/platform/surface/surface_aggregator_registry.c +++ b/drivers/platform/surface/surface_aggregator_registry.c @@ -273,8 +273,8 @@ static const struct software_node *ssam_node_group_sl5[] = { NULL, }; -/* Devices for Surface Laptop Studio. */ -static const struct software_node *ssam_node_group_sls[] = { +/* Devices for Surface Laptop Studio 1. */ +static const struct software_node *ssam_node_group_sls1[] = { &ssam_node_root, &ssam_node_bat_ac, &ssam_node_bat_main, @@ -289,6 +289,22 @@ static const struct software_node *ssam_node_group_sls[] = { NULL, }; +/* Devices for Surface Laptop Studio 2. */ +static const struct software_node *ssam_node_group_sls2[] = { + &ssam_node_root, + &ssam_node_bat_ac, + &ssam_node_bat_main, + &ssam_node_tmp_perf_profile_with_fan, + &ssam_node_tmp_sensors, + &ssam_node_fan_speed, + &ssam_node_pos_tablet_switch, + &ssam_node_hid_sam_keyboard, + &ssam_node_hid_sam_penstash, + &ssam_node_hid_sam_sensors, + &ssam_node_hid_sam_ucm_ucsi, + NULL, +}; + /* Devices for Surface Laptop Go. */ static const struct software_node *ssam_node_group_slg1[] = { &ssam_node_root, @@ -401,8 +417,11 @@ static const struct acpi_device_id ssam_platform_hub_match[] = { /* Surface Laptop Go 3 */ { "MSHW0440", (unsigned long)ssam_node_group_slg1 }, - /* Surface Laptop Studio */ - { "MSHW0123", (unsigned long)ssam_node_group_sls }, + /* Surface Laptop Studio 1 */ + { "MSHW0123", (unsigned long)ssam_node_group_sls1 }, + + /* Surface Laptop Studio 2 */ + { "MSHW0360", (unsigned long)ssam_node_group_sls2 }, { }, }; From 002adda09bc1c983c75c82a7e12285c7423aec31 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Sun, 11 Aug 2024 15:19:47 +0200 Subject: [PATCH 168/562] platform/surface: aggregator_registry: Add fan and thermal sensor support for Surface Laptop 5 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The EC on the Surface Laptop 5 exposes the fan interface. With the recently introduced driver for it, we can now also enable it here. In addition, also enable the thermal sensor interface. Signed-off-by: Maximilian Luz Link: https://lore.kernel.org/r/20240811131948.261806-5-luzmaximilian@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/surface/surface_aggregator_registry.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/platform/surface/surface_aggregator_registry.c b/drivers/platform/surface/surface_aggregator_registry.c index 892ba9549f6a..4d3f5b3111ba 100644 --- a/drivers/platform/surface/surface_aggregator_registry.c +++ b/drivers/platform/surface/surface_aggregator_registry.c @@ -265,7 +265,9 @@ static const struct software_node *ssam_node_group_sl5[] = { &ssam_node_root, &ssam_node_bat_ac, &ssam_node_bat_main, - &ssam_node_tmp_perf_profile, + &ssam_node_tmp_perf_profile_with_fan, + &ssam_node_tmp_sensors, + &ssam_node_fan_speed, &ssam_node_hid_main_keyboard, &ssam_node_hid_main_touchpad, &ssam_node_hid_main_iid5, From 99ae7b9ba047ad029a0a23b2bd51608ce79c8e97 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Sun, 11 Aug 2024 15:19:48 +0200 Subject: [PATCH 169/562] platform/surface: aggregator_registry: Add support for Surface Laptop 6 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add SAM client device nodes for the Surface Laptop Studio 6 (SL6). The SL6 is similar to the SL5, with the typical battery/AC, platform profile, and HID nodes. It also has support for the newly supported fan interface. Signed-off-by: Maximilian Luz Link: https://lore.kernel.org/r/20240811131948.261806-6-luzmaximilian@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- .../surface/surface_aggregator_registry.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/platform/surface/surface_aggregator_registry.c b/drivers/platform/surface/surface_aggregator_registry.c index 4d3f5b3111ba..a23dff35f8ca 100644 --- a/drivers/platform/surface/surface_aggregator_registry.c +++ b/drivers/platform/surface/surface_aggregator_registry.c @@ -275,6 +275,22 @@ static const struct software_node *ssam_node_group_sl5[] = { NULL, }; +/* Devices for Surface Laptop 6. */ +static const struct software_node *ssam_node_group_sl6[] = { + &ssam_node_root, + &ssam_node_bat_ac, + &ssam_node_bat_main, + &ssam_node_tmp_perf_profile_with_fan, + &ssam_node_tmp_sensors, + &ssam_node_fan_speed, + &ssam_node_hid_main_keyboard, + &ssam_node_hid_main_touchpad, + &ssam_node_hid_main_iid5, + &ssam_node_hid_sam_sensors, + &ssam_node_hid_sam_ucm_ucsi, + NULL, +}; + /* Devices for Surface Laptop Studio 1. */ static const struct software_node *ssam_node_group_sls1[] = { &ssam_node_root, @@ -410,6 +426,9 @@ static const struct acpi_device_id ssam_platform_hub_match[] = { /* Surface Laptop 5 */ { "MSHW0350", (unsigned long)ssam_node_group_sl5 }, + /* Surface Laptop 6 */ + { "MSHW0530", (unsigned long)ssam_node_group_sl6 }, + /* Surface Laptop Go 1 */ { "MSHW0118", (unsigned long)ssam_node_group_slg1 }, From ccbde4b128ef9c73d14d0d7817d68ef795f6d131 Mon Sep 17 00:00:00 2001 From: Eli Billauer Date: Thu, 1 Aug 2024 15:11:26 +0300 Subject: [PATCH 170/562] char: xillybus: Don't destroy workqueue from work item running on it Triggered by a kref decrement, destroy_workqueue() may be called from within a work item for destroying its own workqueue. This illegal situation is averted by adding a module-global workqueue for exclusive use of the offending work item. Other work items continue to be queued on per-device workqueues to ensure performance. Reported-by: syzbot+91dbdfecdd3287734d8e@syzkaller.appspotmail.com Cc: stable Closes: https://lore.kernel.org/lkml/0000000000000ab25a061e1dfe9f@google.com/ Signed-off-by: Eli Billauer Link: https://lore.kernel.org/r/20240801121126.60183-1-eli.billauer@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/char/xillybus/xillyusb.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/char/xillybus/xillyusb.c b/drivers/char/xillybus/xillyusb.c index 5a5afa14ca8c..33ca0f4af390 100644 --- a/drivers/char/xillybus/xillyusb.c +++ b/drivers/char/xillybus/xillyusb.c @@ -50,6 +50,7 @@ MODULE_LICENSE("GPL v2"); static const char xillyname[] = "xillyusb"; static unsigned int fifo_buf_order; +static struct workqueue_struct *wakeup_wq; #define USB_VENDOR_ID_XILINX 0x03fd #define USB_VENDOR_ID_ALTERA 0x09fb @@ -569,10 +570,6 @@ static void cleanup_dev(struct kref *kref) * errors if executed. The mechanism relies on that xdev->error is assigned * a non-zero value by report_io_error() prior to queueing wakeup_all(), * which prevents bulk_in_work() from calling process_bulk_in(). - * - * The fact that wakeup_all() and bulk_in_work() are queued on the same - * workqueue makes their concurrent execution very unlikely, however the - * kernel's API doesn't seem to ensure this strictly. */ static void wakeup_all(struct work_struct *work) @@ -627,7 +624,7 @@ static void report_io_error(struct xillyusb_dev *xdev, if (do_once) { kref_get(&xdev->kref); /* xdev is used by work item */ - queue_work(xdev->workq, &xdev->wakeup_workitem); + queue_work(wakeup_wq, &xdev->wakeup_workitem); } } @@ -2258,6 +2255,10 @@ static int __init xillyusb_init(void) { int rc = 0; + wakeup_wq = alloc_workqueue(xillyname, 0, 0); + if (!wakeup_wq) + return -ENOMEM; + if (LOG2_INITIAL_FIFO_BUF_SIZE > PAGE_SHIFT) fifo_buf_order = LOG2_INITIAL_FIFO_BUF_SIZE - PAGE_SHIFT; else @@ -2265,11 +2266,16 @@ static int __init xillyusb_init(void) rc = usb_register(&xillyusb_driver); + if (rc) + destroy_workqueue(wakeup_wq); + return rc; } static void __exit xillyusb_exit(void) { + destroy_workqueue(wakeup_wq); + usb_deregister(&xillyusb_driver); } From bc923d594db21bee0ead128eb4bb78f7e77467a4 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Sun, 11 Aug 2024 14:46:44 +0200 Subject: [PATCH 171/562] platform/surface: aggregator: Fix warning when controller is destroyed in probe MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a small window in ssam_serial_hub_probe() where the controller is initialized but has not been started yet. Specifically, between ssam_controller_init() and ssam_controller_start(). Any failure in this window, for example caused by a failure of serdev_device_open(), currently results in an incorrect warning being emitted. In particular, any failure in this window results in the controller being destroyed via ssam_controller_destroy(). This function checks the state of the controller and, in an attempt to validate that the controller has been cleanly shut down before we try and deallocate any resources, emits a warning if that state is not SSAM_CONTROLLER_STOPPED. However, since we have only just initialized the controller and have not yet started it, its state is SSAM_CONTROLLER_INITIALIZED. Note that this is the only point at which the controller has this state, as it will change after we start the controller with ssam_controller_start() and never revert back. Further, at this point no communication has taken place and the sender and receiver threads have not been started yet (and we may not even have an open serdev device either). Therefore, it is perfectly safe to call ssam_controller_destroy() with a state of SSAM_CONTROLLER_INITIALIZED. This, however, means that the warning currently being emitted is incorrect. Fix it by extending the check. Fixes: c167b9c7e3d6 ("platform/surface: Add Surface Aggregator subsystem") Signed-off-by: Maximilian Luz Link: https://lore.kernel.org/r/20240811124645.246016-1-luzmaximilian@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/surface/aggregator/controller.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/platform/surface/aggregator/controller.c b/drivers/platform/surface/aggregator/controller.c index 7fc602e01487..7e89f547999b 100644 --- a/drivers/platform/surface/aggregator/controller.c +++ b/drivers/platform/surface/aggregator/controller.c @@ -1354,7 +1354,8 @@ void ssam_controller_destroy(struct ssam_controller *ctrl) if (ctrl->state == SSAM_CONTROLLER_UNINITIALIZED) return; - WARN_ON(ctrl->state != SSAM_CONTROLLER_STOPPED); + WARN_ON(ctrl->state != SSAM_CONTROLLER_STOPPED && + ctrl->state != SSAM_CONTROLLER_INITIALIZED); /* * Note: New events could still have been received after the previous From dcdb52d948f3a17ccd3fce757d9bd981d7c32039 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 9 Aug 2024 15:44:07 +0300 Subject: [PATCH 172/562] usb: xhci: Check for xhci->interrupters being allocated in xhci_mem_clearup() If xhci_mem_init() fails, it calls into xhci_mem_cleanup() to mop up the damage. If it fails early enough, before xhci->interrupters is allocated but after xhci->max_interrupters has been set, which happens in most (all?) cases, things get uglier, as xhci_mem_cleanup() unconditionally derefences xhci->interrupters. With prejudice. Gate the interrupt freeing loop with a check on xhci->interrupters being non-NULL. Found while debugging a DMA allocation issue that led the XHCI driver on this exact path. Fixes: c99b38c41234 ("xhci: add support to allocate several interrupters") Cc: Mathias Nyman Cc: Wesley Cheng Cc: Greg Kroah-Hartman Signed-off-by: Marc Zyngier Cc: stable@vger.kernel.org # 6.8+ Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20240809124408.505786-2-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-mem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index d7654f475daf..937ce5fd5809 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1872,7 +1872,7 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci) cancel_delayed_work_sync(&xhci->cmd_timer); - for (i = 0; i < xhci->max_interrupters; i++) { + for (i = 0; xhci->interrupters && i < xhci->max_interrupters; i++) { if (xhci->interrupters[i]) { xhci_remove_interrupter(xhci, xhci->interrupters[i]); xhci_free_interrupter(xhci, xhci->interrupters[i]); From 741b41b48faf41c0bcf3c26fbb3448b0fda4fc5d Mon Sep 17 00:00:00 2001 From: Niklas Neronin Date: Fri, 9 Aug 2024 15:44:08 +0300 Subject: [PATCH 173/562] usb: xhci: fix duplicate stall handling in handle_tx_event() Stall handling is managed in the 'process_*' functions, which are called right before the 'goto' stall handling code snippet. Thus, there should be a return after the 'process_*' functions. Otherwise, the stall code may run twice. Fixes: 1b349f214ac7 ("usb: xhci: add 'goto' for halted endpoint check in handle_tx_event()") Reported-by: Michal Pecio Signed-off-by: Niklas Neronin Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20240809124408.505786-3-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-ring.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index b7517c3c8059..4ea2c3e072a9 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2910,6 +2910,7 @@ static int handle_tx_event(struct xhci_hcd *xhci, process_isoc_td(xhci, ep, ep_ring, td, ep_trb, event); else process_bulk_intr_td(xhci, ep, ep_ring, td, ep_trb, event); + return 0; check_endpoint_halted: if (xhci_halted_host_endpoint(ep_ctx, trb_comp_code)) From d209d1634e6562eafc369b28f8a1f67a2e9e5222 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Fri, 9 Aug 2024 18:03:43 +0300 Subject: [PATCH 174/562] usb: typec: ucsi: Fix the return value of ucsi_run_command() The command execution routines need to return the amount of data that was transferred when succesful. This fixes an issue where the alternate modes and the power delivery capabilities are not getting registered. Fixes: 5e9c1662a89b ("usb: typec: ucsi: rework command execution functions") Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20240809150343.286942-1-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/ucsi/ucsi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 432a2d6266d7..4039851551c1 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -137,7 +137,7 @@ static int ucsi_run_command(struct ucsi *ucsi, u64 command, u32 *cci, if (ret) return ret; - return err; + return err ?: UCSI_CCI_LENGTH(*cci); } static int ucsi_read_error(struct ucsi *ucsi, u8 connector_num) From 21ea1ce37fc267dc45fe27517bbde926211683df Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Fri, 9 Aug 2024 19:29:01 +0800 Subject: [PATCH 175/562] Revert "usb: typec: tcpm: clear pd_event queue in PORT_RESET" This reverts commit bf20c69cf3cf9c6445c4925dd9a8a6ca1b78bfdf. During tcpm_init() stage, if the VBUS is still present after tcpm_reset_port(), then we assume that VBUS will off and goto safe0v after a specific discharge time. Following a TCPM_VBUS_EVENT event if VBUS reach to off state. TCPM_VBUS_EVENT event may be set during PORT_RESET handling stage. If pd_events reset to 0 after TCPM_VBUS_EVENT set, we will lost this VBUS event. Then the port state machine may stuck at one state. Before: [ 2.570172] pending state change PORT_RESET -> PORT_RESET_WAIT_OFF @ 100 ms [rev1 NONE_AMS] [ 2.570179] state change PORT_RESET -> PORT_RESET_WAIT_OFF [delayed 100 ms] [ 2.570182] pending state change PORT_RESET_WAIT_OFF -> SNK_UNATTACHED @ 920 ms [rev1 NONE_AMS] [ 3.490213] state change PORT_RESET_WAIT_OFF -> SNK_UNATTACHED [delayed 920 ms] [ 3.490220] Start toggling [ 3.546050] CC1: 0 -> 0, CC2: 0 -> 2 [state TOGGLING, polarity 0, connected] [ 3.546057] state change TOGGLING -> SRC_ATTACH_WAIT [rev1 NONE_AMS] After revert this patch, we can see VBUS off event and the port will goto expected state. [ 2.441992] pending state change PORT_RESET -> PORT_RESET_WAIT_OFF @ 100 ms [rev1 NONE_AMS] [ 2.441999] state change PORT_RESET -> PORT_RESET_WAIT_OFF [delayed 100 ms] [ 2.442002] pending state change PORT_RESET_WAIT_OFF -> SNK_UNATTACHED @ 920 ms [rev1 NONE_AMS] [ 2.442122] VBUS off [ 2.442125] state change PORT_RESET_WAIT_OFF -> SNK_UNATTACHED [rev1 NONE_AMS] [ 2.442127] VBUS VSAFE0V [ 2.442351] CC1: 0 -> 0, CC2: 0 -> 0 [state SNK_UNATTACHED, polarity 0, disconnected] [ 2.442357] Start toggling [ 2.491850] CC1: 0 -> 0, CC2: 0 -> 2 [state TOGGLING, polarity 0, connected] [ 2.491858] state change TOGGLING -> SRC_ATTACH_WAIT [rev1 NONE_AMS] [ 2.491863] pending state change SRC_ATTACH_WAIT -> SNK_TRY @ 200 ms [rev1 NONE_AMS] [ 2.691905] state change SRC_ATTACH_WAIT -> SNK_TRY [delayed 200 ms] Fixes: bf20c69cf3cf ("usb: typec: tcpm: clear pd_event queue in PORT_RESET") Cc: stable@vger.kernel.org Signed-off-by: Xu Yang Acked-by: Heikki Krogerus Link: https://lore.kernel.org/r/20240809112901.535072-1-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index cce39818e99a..4b02d6474259 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -5655,7 +5655,6 @@ static void run_state_machine(struct tcpm_port *port) break; case PORT_RESET: tcpm_reset_port(port); - port->pd_events = 0; if (port->self_powered) tcpm_set_cc(port, TYPEC_CC_OPEN); else From 3ed486e383ccee9b0c8d727608f12a937c6603ca Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 12 Aug 2024 11:50:38 +0200 Subject: [PATCH 176/562] usb: misc: ljca: Add Lunar Lake ljca GPIO HID to ljca_gpio_hids[] Add LJCA GPIO support for the Lunar Lake platform. New HID taken from out of tree ivsc-driver git repo. Link: https://github.com/intel/ivsc-driver/commit/47e7c4a446c8ea8c741ff5a32fa7b19f9e6fd47e Cc: stable Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20240812095038.555837-1-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/misc/usb-ljca.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/misc/usb-ljca.c b/drivers/usb/misc/usb-ljca.c index 2d30fc1be306..1a8d5e80b9ae 100644 --- a/drivers/usb/misc/usb-ljca.c +++ b/drivers/usb/misc/usb-ljca.c @@ -169,6 +169,7 @@ static const struct acpi_device_id ljca_gpio_hids[] = { { "INTC1096" }, { "INTC100B" }, { "INTC10D1" }, + { "INTC10B5" }, {}, }; From 92567a5f92bc947fb7aa4351979db1b7b71a554c Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Thu, 8 Aug 2024 22:06:19 +0800 Subject: [PATCH 177/562] iommu: Remove unused declaration iommu_sva_unbind_gpasid() Commit 0c9f17877891 ("iommu: Remove guest pasid related interfaces and definitions") removed the implementation but leave declaration. Signed-off-by: Yue Haibing Reviewed-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20240808140619.2498535-1-yuehaibing@huawei.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 4d47f2c33311..04cbdae0052e 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -795,8 +795,6 @@ extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); -extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, From dc98d76a15bc29a9a4e76f2f65f39f3e590fb15c Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 8 Aug 2024 22:03:25 +0800 Subject: [PATCH 178/562] tty: serial: fsl_lpuart: mark last busy before uart_add_one_port With "earlycon initcall_debug=1 loglevel=8" in bootargs, kernel sometimes boot hang. It is because normal console still is not ready, but runtime suspend is called, so early console putchar will hang in waiting TRDE set in UARTSTAT. The lpuart driver has auto suspend delay set to 3000ms, but during uart_add_one_port, a child device serial ctrl will added and probed with its pm runtime enabled(see serial_ctrl.c). The runtime suspend call path is: device_add |-> bus_probe_device |->device_initial_probe |->__device_attach |-> pm_runtime_get_sync(dev->parent); |-> pm_request_idle(dev); |-> pm_runtime_put(dev->parent); So in the end, before normal console ready, the lpuart get runtime suspended. And earlycon putchar will hang. To address the issue, mark last busy just after pm_runtime_enable, three seconds is long enough to switch from bootconsole to normal console. Fixes: 43543e6f539b ("tty: serial: fsl_lpuart: Add runtime pm support") Cc: stable Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/20240808140325.580105-1-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/fsl_lpuart.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 615291ea9b5e..77efa7ee6eda 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2923,6 +2923,7 @@ static int lpuart_probe(struct platform_device *pdev) pm_runtime_set_autosuspend_delay(&pdev->dev, UART_AUTOSUSPEND_TIMEOUT); pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); + pm_runtime_mark_last_busy(&pdev->dev); ret = lpuart_global_reset(sport); if (ret) From 7258fdd7d7459616b3fe1a603e33900584b10c13 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 10 Aug 2024 01:07:20 +0900 Subject: [PATCH 179/562] tty: vt: conmakehash: remove non-portable code printing comment header Commit 6e20753da6bc ("tty: vt: conmakehash: cope with abs_srctree no longer in env") included , which invoked another (wrong) patch that tried to address a build error on macOS. According to the specification [1], the correct header to use PATH_MAX is . The minimal fix would be to replace with . However, the following commits seem questionable to me: - 3bd85c6c97b2 ("tty: vt: conmakehash: Don't mention the full path of the input in output") - 6e20753da6bc ("tty: vt: conmakehash: cope with abs_srctree no longer in env") These commits made too many efforts to cope with a comment header in drivers/tty/vt/consolemap_deftbl.c: /* * Do not edit this file; it was automatically generated by * * conmakehash drivers/tty/vt/cp437.uni > [this file] * */ With this commit, the header part of the generate C file will be simplified as follows: /* * Automatically generated file; Do not edit. */ BTW, another series of excessive efforts for a comment header can be seen in the following: - 5ef6dc08cfde ("lib/build_OID_registry: don't mention the full path of the script in output") - 2fe29fe94563 ("lib/build_OID_registry: avoid non-destructive substitution for Perl < 5.13.2 compat") [1]: https://pubs.opengroup.org/onlinepubs/009695399/basedefs/limits.h.html Fixes: 6e20753da6bc ("tty: vt: conmakehash: cope with abs_srctree no longer in env") Cc: stable Reported-by: Daniel Gomez Closes: https://lore.kernel.org/all/20240807-macos-build-support-v1-11-4cd1ded85694@samsung.com/ Signed-off-by: Masahiro Yamada Link: https://lore.kernel.org/r/20240809160853.1269466-1-masahiroy@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/conmakehash.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/drivers/tty/vt/conmakehash.c b/drivers/tty/vt/conmakehash.c index 82d9db68b2ce..a931fcde7ad9 100644 --- a/drivers/tty/vt/conmakehash.c +++ b/drivers/tty/vt/conmakehash.c @@ -11,8 +11,6 @@ * Copyright (C) 1995-1997 H. Peter Anvin */ -#include -#include #include #include #include @@ -79,7 +77,6 @@ int main(int argc, char *argv[]) { FILE *ctbl; const char *tblname; - char base_tblname[PATH_MAX]; char buffer[65536]; int fontlen; int i, nuni, nent; @@ -245,20 +242,15 @@ int main(int argc, char *argv[]) for ( i = 0 ; i < fontlen ; i++ ) nuni += unicount[i]; - strncpy(base_tblname, tblname, PATH_MAX); - base_tblname[PATH_MAX - 1] = 0; printf("\ /*\n\ - * Do not edit this file; it was automatically generated by\n\ - *\n\ - * conmakehash %s > [this file]\n\ - *\n\ + * Automatically generated file; Do not edit.\n\ */\n\ \n\ #include \n\ \n\ u8 dfont_unicount[%d] = \n\ -{\n\t", basename(base_tblname), fontlen); +{\n\t", fontlen); for ( i = 0 ; i < fontlen ; i++ ) { From c9f6613b16123989f2c3bd04b1d9b2365d6914e7 Mon Sep 17 00:00:00 2001 From: Mathieu Othacehe Date: Thu, 8 Aug 2024 08:06:37 +0200 Subject: [PATCH 180/562] tty: atmel_serial: use the correct RTS flag. In RS485 mode, the RTS pin is driven high by hardware when the transmitter is operating. This behaviour cannot be changed. This means that the driver should claim that it supports SER_RS485_RTS_ON_SEND and not SER_RS485_RTS_AFTER_SEND. Otherwise, when configuring the port with the SER_RS485_RTS_ON_SEND, one get the following warning: kern.warning kernel: atmel_usart_serial atmel_usart_serial.2.auto: ttyS1 (1): invalid RTS setting, using RTS_AFTER_SEND instead which is contradictory with what's really happening. Signed-off-by: Mathieu Othacehe Cc: stable Tested-by: Alexander Dahl Fixes: af47c491e3c7 ("serial: atmel: Fill in rs485_supported") Link: https://lore.kernel.org/r/20240808060637.19886-1-othacehe@gnu.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/atmel_serial.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index 0a90964d6d10..09b246c9e389 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -2514,7 +2514,7 @@ static const struct uart_ops atmel_pops = { }; static const struct serial_rs485 atmel_rs485_supported = { - .flags = SER_RS485_ENABLED | SER_RS485_RTS_AFTER_SEND | SER_RS485_RX_DURING_TX, + .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RX_DURING_TX, .delay_rts_before_send = 1, .delay_rts_after_send = 1, }; From abfceba0a7a246ac082bf569807738ff7416f59f Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 5 Aug 2024 16:20:20 -0700 Subject: [PATCH 181/562] ARM: riscpc: ecard: Fix the build Fix a recently introduced build failure. Cc: Russell King Fixes: d69d80484598 ("driver core: have match() callback in struct bus_type take a const *") Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20240805232026.65087-2-bvanassche@acm.org Signed-off-by: Greg Kroah-Hartman --- arch/arm/mach-rpc/ecard.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c index c30df1097c52..9f7454b8efa7 100644 --- a/arch/arm/mach-rpc/ecard.c +++ b/arch/arm/mach-rpc/ecard.c @@ -1109,7 +1109,7 @@ void ecard_remove_driver(struct ecard_driver *drv) driver_unregister(&drv->drv); } -static int ecard_match(struct device *_dev, struct device_driver *_drv) +static int ecard_match(struct device *_dev, const struct device_driver *_drv) { struct expansion_card *ec = ECARD_DEV(_dev); struct ecard_driver *drv = ECARD_DRV(_drv); From cdd1fa91a6b8c7cd93b3abf9f3ef05b8ce741b61 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 5 Aug 2024 16:20:21 -0700 Subject: [PATCH 182/562] mips: sgi-ip22: Fix the build Fix a recently introduced build failure. Fixes: d69d80484598 ("driver core: have match() callback in struct bus_type take a const *") Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20240805232026.65087-3-bvanassche@acm.org Signed-off-by: Greg Kroah-Hartman --- arch/mips/sgi-ip22/ip22-gio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/sgi-ip22/ip22-gio.c b/arch/mips/sgi-ip22/ip22-gio.c index 2738325e98dd..d20eec742bfa 100644 --- a/arch/mips/sgi-ip22/ip22-gio.c +++ b/arch/mips/sgi-ip22/ip22-gio.c @@ -111,7 +111,7 @@ void gio_device_unregister(struct gio_device *giodev) } EXPORT_SYMBOL_GPL(gio_device_unregister); -static int gio_bus_match(struct device *dev, struct device_driver *drv) +static int gio_bus_match(struct device *dev, const struct device_driver *drv) { struct gio_device *gio_dev = to_gio_device(dev); struct gio_driver *gio_drv = to_gio_driver(drv); From 479ffee68d59c599f8aed8fa2dcc8e13e7bd13c3 Mon Sep 17 00:00:00 2001 From: Bert Karwatzki Date: Mon, 12 Aug 2024 12:45:41 +0200 Subject: [PATCH 183/562] wifi: mt76: mt7921: fix NULL pointer access in mt7921_ipv6_addr_change When disabling wifi mt7921_ipv6_addr_change() is called as a notifier. At this point mvif->phy is already NULL so we cannot use it here. Signed-off-by: Bert Karwatzki Signed-off-by: Felix Fietkau Signed-off-by: Kalle Valo Link: https://patch.msgid.link/20240812104542.80760-1-spasswolf@web.de --- drivers/net/wireless/mediatek/mt76/mt7921/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 1bab93d049df..23b228804289 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -1183,7 +1183,7 @@ static void mt7921_ipv6_addr_change(struct ieee80211_hw *hw, struct inet6_dev *idev) { struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; - struct mt792x_dev *dev = mvif->phy->dev; + struct mt792x_dev *dev = mt792x_hw_dev(hw); struct inet6_ifaddr *ifa; struct in6_addr ns_addrs[IEEE80211_BSS_ARP_ADDR_LIST_LEN]; struct sk_buff *skb; From 38c8d02501c09454e4fbf0f67de03de35e94d384 Mon Sep 17 00:00:00 2001 From: Benjamin Berg Date: Mon, 12 Aug 2024 13:06:40 +0200 Subject: [PATCH 184/562] wifi: iwlwifi: correctly lookup DMA address in SG table The code to lookup the scatter gather table entry assumed that it was possible to use sg_virt() in order to lookup the DMA address in a mapped scatter gather table. However, this assumption is incorrect as the DMA mapping code may merge multiple entries into one. In that case, the DMA address space may have e.g. two consecutive pages which is correctly represented by the scatter gather list entry, however the virtual addresses for these two pages may differ and the relationship cannot be resolved anymore. Avoid this problem entirely by working with the offset into the mapped area instead of using virtual addresses. With that we only use the DMA length and DMA address from the scatter gather list entries. The underlying DMA/IOMMU code is therefore free to merge two entries into one even if the virtual addresses space for the area is not continuous. Fixes: 90db50755228 ("wifi: iwlwifi: use already mapped data when TXing an AMSDU") Reported-by: Chris Bainbridge Closes: https://lore.kernel.org/r/ZrNRoEbdkxkKFMBi@debian.local Signed-off-by: Benjamin Berg Tested-by: Chris Bainbridge Signed-off-by: Kalle Valo Link: https://patch.msgid.link/20240812110640.460514-1-benjamin@sipsolutions.net --- .../wireless/intel/iwlwifi/pcie/internal.h | 3 +- .../net/wireless/intel/iwlwifi/pcie/tx-gen2.c | 5 ++- drivers/net/wireless/intel/iwlwifi/pcie/tx.c | 32 +++++++++++++------ 3 files changed, 28 insertions(+), 12 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h index b59de4f80b4b..27a7e0b5b3d5 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h @@ -639,7 +639,8 @@ void iwl_trans_pcie_tx_reset(struct iwl_trans *trans); int iwl_pcie_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq, int slots_num, bool cmd_queue); -dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, void *addr); +dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset, + unsigned int len); struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb, struct iwl_cmd_meta *cmd_meta, u8 **hdr, unsigned int hdr_room); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c index 2e780fb2da42..b1846abb99b7 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c @@ -168,6 +168,7 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans, struct ieee80211_hdr *hdr = (void *)skb->data; unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room; unsigned int mss = skb_shinfo(skb)->gso_size; + unsigned int data_offset = 0; dma_addr_t start_hdr_phys; u16 length, amsdu_pad; u8 *start_hdr; @@ -260,7 +261,8 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans, int ret; tb_len = min_t(unsigned int, tso.size, data_left); - tb_phys = iwl_pcie_get_sgt_tb_phys(sgt, tso.data); + tb_phys = iwl_pcie_get_sgt_tb_phys(sgt, data_offset, + tb_len); /* Not a real mapping error, use direct comparison */ if (unlikely(tb_phys == DMA_MAPPING_ERROR)) goto out_err; @@ -272,6 +274,7 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans, goto out_err; data_left -= tb_len; + data_offset += tb_len; tso_build_data(skb, &tso, tb_len); } } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index 22d482ae53d9..9fe050f0ddc1 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -1814,23 +1814,31 @@ out: /** * iwl_pcie_get_sgt_tb_phys - Find TB address in mapped SG list * @sgt: scatter gather table - * @addr: Virtual address + * @offset: Offset into the mapped memory (i.e. SKB payload data) + * @len: Length of the area * - * Find the entry that includes the address for the given address and return - * correct physical address for the TB entry. + * Find the DMA address that corresponds to the SKB payload data at the + * position given by @offset. * * Returns: Address for TB entry */ -dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, void *addr) +dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset, + unsigned int len) { struct scatterlist *sg; + unsigned int sg_offset = 0; int i; + /* + * Search the mapped DMA areas in the SG for the area that contains the + * data at offset with the given length. + */ for_each_sgtable_dma_sg(sgt, sg, i) { - if (addr >= sg_virt(sg) && - (u8 *)addr < (u8 *)sg_virt(sg) + sg_dma_len(sg)) - return sg_dma_address(sg) + - ((unsigned long)addr - (unsigned long)sg_virt(sg)); + if (offset >= sg_offset && + offset + len <= sg_offset + sg_dma_len(sg)) + return sg_dma_address(sg) + offset - sg_offset; + + sg_offset += sg_dma_len(sg); } WARN_ON_ONCE(1); @@ -1875,7 +1883,9 @@ struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb, sg_init_table(sgt->sgl, skb_shinfo(skb)->nr_frags + 1); - sgt->orig_nents = skb_to_sgvec(skb, sgt->sgl, 0, skb->len); + /* Only map the data, not the header (it is copied to the TSO page) */ + sgt->orig_nents = skb_to_sgvec(skb, sgt->sgl, skb_headlen(skb), + skb->data_len); if (WARN_ON_ONCE(sgt->orig_nents <= 0)) return NULL; @@ -1900,6 +1910,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb, struct ieee80211_hdr *hdr = (void *)skb->data; unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room; unsigned int mss = skb_shinfo(skb)->gso_size; + unsigned int data_offset = 0; u16 length, iv_len, amsdu_pad; dma_addr_t start_hdr_phys; u8 *start_hdr, *pos_hdr; @@ -2000,7 +2011,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb, data_left); dma_addr_t tb_phys; - tb_phys = iwl_pcie_get_sgt_tb_phys(sgt, tso.data); + tb_phys = iwl_pcie_get_sgt_tb_phys(sgt, data_offset, size); /* Not a real mapping error, use direct comparison */ if (unlikely(tb_phys == DMA_MAPPING_ERROR)) return -EINVAL; @@ -2011,6 +2022,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb, tb_phys, size); data_left -= size; + data_offset += size; tso_build_data(skb, &tso, size); } } From 92b6c2f0076c50aaa919d16b595f34f3e9967bea Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 12 Jun 2024 14:50:38 +0300 Subject: [PATCH 185/562] KVM: SVM: Fix uninitialized variable bug If snp_lookup_rmpentry() fails then "assigned" is printed in the error message but it was never initialized. Initialize it to false. Fixes: dee5a47cc7a4 ("KVM: SEV: Add KVM_SEV_SNP_LAUNCH_UPDATE command") Signed-off-by: Dan Carpenter Message-ID: <20240612115040.2423290-3-dan.carpenter@linaro.org> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 532df12b43c5..393f450adbc3 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2276,7 +2276,7 @@ static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pf for (gfn = gfn_start, i = 0; gfn < gfn_start + npages; gfn++, i++) { struct sev_data_snp_launch_update fw_args = {0}; - bool assigned; + bool assigned = false; int level; ret = snp_lookup_rmpentry((u64)pfn + i, &assigned, &level); From cd2d00606553e631e9b5d11cca7da38fc95433e6 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 12 Jun 2024 14:50:39 +0300 Subject: [PATCH 186/562] KVM: SVM: Fix an error code in sev_gmem_post_populate() The copy_from_user() function returns the number of bytes which it was not able to copy. Return -EFAULT instead. Fixes: dee5a47cc7a4 ("KVM: SEV: Add KVM_SEV_SNP_LAUNCH_UPDATE command") Signed-off-by: Dan Carpenter Message-ID: <20240612115040.2423290-4-dan.carpenter@linaro.org> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 393f450adbc3..714c517dd4b7 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2290,9 +2290,10 @@ static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pf if (src) { void *vaddr = kmap_local_pfn(pfn + i); - ret = copy_from_user(vaddr, src + i * PAGE_SIZE, PAGE_SIZE); - if (ret) + if (copy_from_user(vaddr, src + i * PAGE_SIZE, PAGE_SIZE)) { + ret = -EFAULT; goto err; + } kunmap_local(vaddr); } From 58a63729c957621f1990c3494c702711188ca347 Mon Sep 17 00:00:00 2001 From: Long Li Date: Fri, 9 Aug 2024 08:58:58 -0700 Subject: [PATCH 187/562] net: mana: Fix doorbell out of order violation and avoid unnecessary doorbell rings After napi_complete_done() is called when NAPI is polling in the current process context, another NAPI may be scheduled and start running in softirq on another CPU and may ring the doorbell before the current CPU does. When combined with unnecessary rings when there is no need to arm the CQ, it triggers error paths in the hardware. This patch fixes this by calling napi_complete_done() after doorbell rings. It limits the number of unnecessary rings when there is no need to arm. MANA hardware specifies that there must be one doorbell ring every 8 CQ wraparounds. This driver guarantees one doorbell ring as soon as the number of consumed CQEs exceeds 4 CQ wraparounds. In practical workloads, the 4 CQ wraparounds proves to be big enough that it rarely exceeds this limit before all the napi weight is consumed. To implement this, add a per-CQ counter cq->work_done_since_doorbell, and make sure the CQ is armed as soon as passing 4 wraparounds of the CQ. Cc: stable@vger.kernel.org Fixes: e1b5683ff62e ("net: mana: Move NAPI from EQ to CQ") Reviewed-by: Haiyang Zhang Signed-off-by: Long Li Link: https://patch.msgid.link/1723219138-29887-1-git-send-email-longli@linuxonhyperv.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/microsoft/mana/mana_en.c | 22 ++++++++++++------- include/net/mana/mana.h | 1 + 2 files changed, 15 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index ae717d06e66f..39f56973746d 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1792,7 +1792,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq) static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) { struct mana_cq *cq = context; - u8 arm_bit; int w; WARN_ON_ONCE(cq->gdma_cq != gdma_queue); @@ -1803,16 +1802,23 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) mana_poll_tx_cq(cq); w = cq->work_done; + cq->work_done_since_doorbell += w; - if (w < cq->budget && - napi_complete_done(&cq->napi, w)) { - arm_bit = SET_ARM_BIT; - } else { - arm_bit = 0; + if (w < cq->budget) { + mana_gd_ring_cq(gdma_queue, SET_ARM_BIT); + cq->work_done_since_doorbell = 0; + napi_complete_done(&cq->napi, w); + } else if (cq->work_done_since_doorbell > + cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) { + /* MANA hardware requires at least one doorbell ring every 8 + * wraparounds of CQ even if there is no need to arm the CQ. + * This driver rings the doorbell as soon as we have exceeded + * 4 wraparounds. + */ + mana_gd_ring_cq(gdma_queue, 0); + cq->work_done_since_doorbell = 0; } - mana_gd_ring_cq(gdma_queue, arm_bit); - return w; } diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 6439fd8b437b..7caa334f4888 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -275,6 +275,7 @@ struct mana_cq { /* NAPI data */ struct napi_struct napi; int work_done; + int work_done_since_doorbell; int budget; }; From 12d82c7b0a612372f594e4ff00983a1da3a1d929 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 13 Aug 2024 12:07:50 +0100 Subject: [PATCH 188/562] ALSA: hda: cs35l56: Remove redundant call to hda_cs_dsp_control_remove() The driver doesn't create any ALSA controls for firmware controls, so it shouldn't be calling hda_cs_dsp_control_remove(). commit 34e1b1bb7324 ("ALSA: hda: cs35l56: Stop creating ALSA controls for firmware coefficients") removed the call to hda_cs_dsp_add_controls() but didn't remove the call for destroying those controls. Signed-off-by: Richard Fitzgerald Fixes: 34e1b1bb7324 ("ALSA: hda: cs35l56: Stop creating ALSA controls for firmware coefficients") Link: https://patch.msgid.link/20240813110750.2814-1-rf@opensource.cirrus.com Signed-off-by: Takashi Iwai --- sound/pci/hda/cs35l56_hda.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c index 31cc92bac89a..a9dfd62637cf 100644 --- a/sound/pci/hda/cs35l56_hda.c +++ b/sound/pci/hda/cs35l56_hda.c @@ -413,7 +413,7 @@ static void cs35l56_hda_remove_controls(struct cs35l56_hda *cs35l56) } static const struct cs_dsp_client_ops cs35l56_hda_client_ops = { - .control_remove = hda_cs_dsp_control_remove, + /* cs_dsp requires the client to provide this even if it is empty */ }; static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56, From 42fac187b5c746227c92d024f1caf33bc1d337e4 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 11 Apr 2024 16:41:20 -0400 Subject: [PATCH 189/562] btrfs: check delayed refs when we're checking if a ref exists In the patch 78c52d9eb6b7 ("btrfs: check for refs on snapshot delete resume") I added some code to handle file systems that had been corrupted by a bug that incorrectly skipped updating the drop progress key while dropping a snapshot. This code would check to see if we had already deleted our reference for a child block, and skip the deletion if we had already. Unfortunately there is a bug, as the check would only check the on-disk references. I made an incorrect assumption that blocks in an already deleted snapshot that was having the deletion resume on mount wouldn't be modified. If we have 2 pending deleted snapshots that share blocks, we can easily modify the rules for a block. Take the following example subvolume a exists, and subvolume b is a snapshot of subvolume a. They share references to block 1. Block 1 will have 2 full references, one for subvolume a and one for subvolume b, and it belongs to subvolume a (btrfs_header_owner(block 1) == subvolume a). When deleting subvolume a, we will drop our full reference for block 1, and because we are the owner we will drop our full reference for all of block 1's children, convert block 1 to FULL BACKREF, and add a shared reference to all of block 1's children. Then we will start the snapshot deletion of subvolume b. We look up the extent info for block 1, which checks delayed refs and tells us that FULL BACKREF is set, so sets parent to the bytenr of block 1. However because this is a resumed snapshot deletion, we call into check_ref_exists(). Because check_ref_exists() only looks at the disk, it doesn't find the shared backref for the child of block 1, and thus returns 0 and we skip deleting the reference for the child of block 1 and continue. This orphans the child of block 1. The fix is to lookup the delayed refs, similar to what we do in btrfs_lookup_extent_info(). However we only care about whether the reference exists or not. If we fail to find our reference on disk, go look up the bytenr in the delayed refs, and if it exists look for an existing ref in the delayed ref head. If that exists then we know we can delete the reference safely and carry on. If it doesn't exist we know we have to skip over this block. This bug has existed since I introduced this fix, however requires having multiple deleted snapshots pending when we unmount. We noticed this in production because our shutdown path stops the container on the system, which deletes a bunch of subvolumes, and then reboots the box. This gives us plenty of opportunities to hit this issue. Looking at the history we've seen this occasionally in production, but we had a big spike recently thanks to faster machines getting jobs with multiple subvolumes in the job. Chris Mason wrote a reproducer which does the following mount /dev/nvme4n1 /btrfs btrfs subvol create /btrfs/s1 simoop -E -f 4k -n 200000 -z /btrfs/s1 while(true) ; do btrfs subvol snap /btrfs/s1 /btrfs/s2 simoop -f 4k -n 200000 -r 10 -z /btrfs/s2 btrfs subvol snap /btrfs/s2 /btrfs/s3 btrfs balance start -dusage=80 /btrfs btrfs subvol del /btrfs/s2 /btrfs/s3 umount /btrfs btrfsck /dev/nvme4n1 || exit 1 mount /dev/nvme4n1 /btrfs done On the second loop this would fail consistently, with my patch it has been running for hours and hasn't failed. I also used dm-log-writes to capture the state of the failure so I could debug the problem. Using the existing failure case to test my patch validated that it fixes the problem. Fixes: 78c52d9eb6b7 ("btrfs: check for refs on snapshot delete resume") CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Filipe Manana Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/delayed-ref.c | 67 ++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/delayed-ref.h | 2 ++ fs/btrfs/extent-tree.c | 51 ++++++++++++++++++++++++++++---- 3 files changed, 114 insertions(+), 6 deletions(-) diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 2ac9296edccb..06a9e0542d70 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -1134,6 +1134,73 @@ btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs, u64 byt return find_ref_head(delayed_refs, bytenr, false); } +static int find_comp(struct btrfs_delayed_ref_node *entry, u64 root, u64 parent) +{ + int type = parent ? BTRFS_SHARED_BLOCK_REF_KEY : BTRFS_TREE_BLOCK_REF_KEY; + + if (type < entry->type) + return -1; + if (type > entry->type) + return 1; + + if (type == BTRFS_TREE_BLOCK_REF_KEY) { + if (root < entry->ref_root) + return -1; + if (root > entry->ref_root) + return 1; + } else { + if (parent < entry->parent) + return -1; + if (parent > entry->parent) + return 1; + } + return 0; +} + +/* + * Check to see if a given root/parent reference is attached to the head. This + * only checks for BTRFS_ADD_DELAYED_REF references that match, as that + * indicates the reference exists for the given root or parent. This is for + * tree blocks only. + * + * @head: the head of the bytenr we're searching. + * @root: the root objectid of the reference if it is a normal reference. + * @parent: the parent if this is a shared backref. + */ +bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head, + u64 root, u64 parent) +{ + struct rb_node *node; + bool found = false; + + lockdep_assert_held(&head->mutex); + + spin_lock(&head->lock); + node = head->ref_tree.rb_root.rb_node; + while (node) { + struct btrfs_delayed_ref_node *entry; + int ret; + + entry = rb_entry(node, struct btrfs_delayed_ref_node, ref_node); + ret = find_comp(entry, root, parent); + if (ret < 0) { + node = node->rb_left; + } else if (ret > 0) { + node = node->rb_right; + } else { + /* + * We only want to count ADD actions, as drops mean the + * ref doesn't exist. + */ + if (entry->action == BTRFS_ADD_DELAYED_REF) + found = true; + break; + } + } + spin_unlock(&head->lock); + return found; +} + void __cold btrfs_delayed_ref_exit(void) { kmem_cache_destroy(btrfs_delayed_ref_head_cachep); diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index ef15e998be03..05f634eb472d 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -389,6 +389,8 @@ void btrfs_dec_delayed_refs_rsv_bg_updates(struct btrfs_fs_info *fs_info); int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, enum btrfs_reserve_flush_enum flush); bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info); +bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head, + u64 root, u64 parent); static inline u64 btrfs_delayed_ref_owner(struct btrfs_delayed_ref_node *node) { diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index ff9f0d41987e..feec49e6f9c8 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5472,23 +5472,62 @@ static int check_ref_exists(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 parent, int level) { + struct btrfs_delayed_ref_root *delayed_refs; + struct btrfs_delayed_ref_head *head; struct btrfs_path *path; struct btrfs_extent_inline_ref *iref; int ret; + bool exists = false; path = btrfs_alloc_path(); if (!path) return -ENOMEM; - +again: ret = lookup_extent_backref(trans, path, &iref, bytenr, root->fs_info->nodesize, parent, btrfs_root_id(root), level, 0); + if (ret != -ENOENT) { + /* + * If we get 0 then we found our reference, return 1, else + * return the error if it's not -ENOENT; + */ + btrfs_free_path(path); + return (ret < 0 ) ? ret : 1; + } + + /* + * We could have a delayed ref with this reference, so look it up while + * we're holding the path open to make sure we don't race with the + * delayed ref running. + */ + delayed_refs = &trans->transaction->delayed_refs; + spin_lock(&delayed_refs->lock); + head = btrfs_find_delayed_ref_head(delayed_refs, bytenr); + if (!head) + goto out; + if (!mutex_trylock(&head->mutex)) { + /* + * We're contended, means that the delayed ref is running, get a + * reference and wait for the ref head to be complete and then + * try again. + */ + refcount_inc(&head->refs); + spin_unlock(&delayed_refs->lock); + + btrfs_release_path(path); + + mutex_lock(&head->mutex); + mutex_unlock(&head->mutex); + btrfs_put_delayed_ref_head(head); + goto again; + } + + exists = btrfs_find_delayed_tree_ref(head, root->root_key.objectid, parent); + mutex_unlock(&head->mutex); +out: + spin_unlock(&delayed_refs->lock); btrfs_free_path(path); - if (ret == -ENOENT) - return 0; - if (ret < 0) - return ret; - return 1; + return exists ? 1 : 0; } /* From 31723c9542dba1681cc3720571fdf12ffe0eddd9 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 12 Aug 2024 08:52:44 +0930 Subject: [PATCH 190/562] btrfs: tree-checker: reject BTRFS_FT_UNKNOWN dir type [REPORT] There is a bug report that kernel is rejecting a mismatching inode mode and its dir item: [ 1881.553937] BTRFS critical (device dm-0): inode mode mismatch with dir: inode mode=040700 btrfs type=2 dir type=0 [CAUSE] It looks like the inode mode is correct, while the dir item type 0 is BTRFS_FT_UNKNOWN, which should not be generated by btrfs at all. This may be caused by a memory bit flip. [ENHANCEMENT] Although tree-checker is not able to do any cross-leaf verification, for this particular case we can at least reject any dir type with BTRFS_FT_UNKNOWN. So here we enhance the dir type check from [0, BTRFS_FT_MAX), to (0, BTRFS_FT_MAX). Although the existing corruption can not be fixed just by such enhanced checking, it should prevent the same 0x2->0x0 bitflip for dir type to reach disk in the future. Reported-by: Kota Link: https://lore.kernel.org/linux-btrfs/CACsxjPYnQF9ZF-0OhH16dAx50=BXXOcP74MxBc3BG+xae4vTTw@mail.gmail.com/ CC: stable@vger.kernel.org # 5.4+ Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/tree-checker.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index a825fa598e3c..6f1e2f2215d9 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -569,9 +569,10 @@ static int check_dir_item(struct extent_buffer *leaf, /* dir type check */ dir_type = btrfs_dir_ftype(leaf, di); - if (unlikely(dir_type >= BTRFS_FT_MAX)) { + if (unlikely(dir_type <= BTRFS_FT_UNKNOWN || + dir_type >= BTRFS_FT_MAX)) { dir_item_err(leaf, slot, - "invalid dir item type, have %u expect [0, %u)", + "invalid dir item type, have %u expect (0, %u)", dir_type, BTRFS_FT_MAX); return -EUCLEAN; } From 8475a1d9bb7acf1cb15842dd24baab0e8ea4e4ff Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 13 Aug 2024 12:32:09 +0100 Subject: [PATCH 191/562] ALSA: hda: cs35l41: Remove redundant call to hda_cs_dsp_control_remove() The driver doesn't create any ALSA controls for firmware controls, so it shouldn't be calling hda_cs_dsp_control_remove(). commit 312c04cee408 ("ALSA: hda: cs35l41: Stop creating ALSA Controls for firmware coefficients") removed the call to hda_cs_dsp_add_controls() but didn't remove the call for destroying those controls. Signed-off-by: Richard Fitzgerald Fixes: 312c04cee408 ("ALSA: hda: cs35l41: Stop creating ALSA Controls for firmware coefficients") Link: https://patch.msgid.link/20240813113209.648-1-rf@opensource.cirrus.com Signed-off-by: Takashi Iwai --- sound/pci/hda/cs35l41_hda.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c index 3a92e98da72d..d68bf7591d90 100644 --- a/sound/pci/hda/cs35l41_hda.c +++ b/sound/pci/hda/cs35l41_hda.c @@ -134,7 +134,7 @@ static const struct reg_sequence cs35l41_hda_mute[] = { }; static const struct cs_dsp_client_ops client_ops = { - .control_remove = hda_cs_dsp_control_remove, + /* cs_dsp requires the client to provide this even if it is empty */ }; static int cs35l41_request_tuning_param_file(struct cs35l41_hda *cs35l41, char *tuning_filename, From ae1e766f623f7a2a889a0b09eb076dd9a60efbe9 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Sun, 11 Aug 2024 11:53:42 +0100 Subject: [PATCH 192/562] btrfs: only run the extent map shrinker from kswapd tasks Currently the extent map shrinker can be run by any task when attempting to allocate memory and there's enough memory pressure to trigger it. To avoid too much latency we stop iterating over extent maps and removing them once the task needs to reschedule. This logic was introduced in commit b3ebb9b7e92a ("btrfs: stop extent map shrinker if reschedule is needed"). While that solved high latency problems for some use cases, it's still not enough because with a too high number of tasks entering the extent map shrinker code, either due to memory allocations or because they are a kswapd task, we end up having a very high level of contention on some spin locks, namely: 1) The fs_info->fs_roots_radix_lock spin lock, which we need to find roots to iterate over their inodes; 2) The spin lock of the xarray used to track open inodes for a root (struct btrfs_root::inodes) - on 6.10 kernels and below, it used to be a red black tree and the spin lock was root->inode_lock; 3) The fs_info->delayed_iput_lock spin lock since the shrinker adds delayed iputs (calls btrfs_add_delayed_iput()). Instead of allowing the extent map shrinker to be run by any task, make it run only by kswapd tasks. This still solves the problem of running into OOM situations due to an unbounded extent map creation, which is simple to trigger by direct IO writes, as described in the changelog of commit 956a17d9d050 ("btrfs: add a shrinker for extent maps"), and by a similar case when doing buffered IO on files with a very large number of holes (keeping the file open and creating many holes, whose extent maps are only released when the file is closed). Reported-by: kzd Link: https://bugzilla.kernel.org/show_bug.cgi?id=219121 Reported-by: Octavia Togami Link: https://lore.kernel.org/linux-btrfs/CAHPNGSSt-a4ZZWrtJdVyYnJFscFjP9S7rMcvEMaNSpR556DdLA@mail.gmail.com/ Fixes: 956a17d9d050 ("btrfs: add a shrinker for extent maps") CC: stable@vger.kernel.org # 6.10+ Tested-by: kzd Tested-by: Octavia Togami Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent_map.c | 22 ++++++---------------- fs/btrfs/super.c | 10 ++++++++++ 2 files changed, 16 insertions(+), 16 deletions(-) diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 23b65dc73c00..10ac5f657e38 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -1147,8 +1147,7 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c return 0; /* - * We want to be fast because we can be called from any path trying to - * allocate memory, so if the lock is busy we don't want to spend time + * We want to be fast so if the lock is busy we don't want to spend time * waiting for it - either some task is about to do IO for the inode or * we may have another task shrinking extent maps, here in this code, so * skip this inode. @@ -1191,9 +1190,7 @@ next: /* * Stop if we need to reschedule or there's contention on the * lock. This is to avoid slowing other tasks trying to take the - * lock and because the shrinker might be called during a memory - * allocation path and we want to avoid taking a very long time - * and slowing down all sorts of tasks. + * lock. */ if (need_resched() || rwlock_needbreak(&tree->lock)) break; @@ -1222,12 +1219,7 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx if (ctx->scanned >= ctx->nr_to_scan) break; - /* - * We may be called from memory allocation paths, so we don't - * want to take too much time and slowdown tasks. - */ - if (need_resched()) - break; + cond_resched(); inode = btrfs_find_first_inode(root, min_ino); } @@ -1285,14 +1277,12 @@ long btrfs_free_extent_maps(struct btrfs_fs_info *fs_info, long nr_to_scan) ctx.last_ino); } - /* - * We may be called from memory allocation paths, so we don't want to - * take too much time and slowdown tasks, so stop if we need reschedule. - */ - while (ctx.scanned < ctx.nr_to_scan && !need_resched()) { + while (ctx.scanned < ctx.nr_to_scan) { struct btrfs_root *root; unsigned long count; + cond_resched(); + spin_lock(&fs_info->fs_roots_radix_lock); count = radix_tree_gang_lookup(&fs_info->fs_roots_radix, (void **)&root, diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 83478deada3b..11044e9e2cb1 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -28,6 +28,7 @@ #include #include #include +#include #include "messages.h" #include "delayed-inode.h" #include "ctree.h" @@ -2409,6 +2410,15 @@ static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_cont const long nr_to_scan = min_t(unsigned long, LONG_MAX, sc->nr_to_scan); struct btrfs_fs_info *fs_info = btrfs_sb(sb); + /* + * We may be called from any task trying to allocate memory and we don't + * want to slow it down with scanning and dropping extent maps. It would + * also cause heavy lock contention if many tasks concurrently enter + * here. Therefore only allow kswapd tasks to scan and drop extent maps. + */ + if (!current_is_kswapd()) + return 0; + return btrfs_free_extent_maps(fs_info, nr_to_scan); } From 779bac9994452f6a894524f70c00cfb0cd4b6364 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 12 Aug 2024 15:08:04 +0200 Subject: [PATCH 193/562] Revert "ACPI: EC: Evaluate orphan _REG under EC device" This reverts commit 0e6b6dedf168 ("Revert "ACPI: EC: Evaluate orphan _REG under EC device") because the problem addressed by it will be addressed differently in what follows. Signed-off-by: Rafael J. Wysocki Reviewed-by: Hans de Goede Cc: All applicable Link: https://patch.msgid.link/3236716.5fSG56mABF@rjwysocki.net --- drivers/acpi/acpica/acevents.h | 4 --- drivers/acpi/acpica/evregion.c | 6 +++- drivers/acpi/acpica/evxfregn.c | 54 ---------------------------------- drivers/acpi/ec.c | 3 -- include/acpi/acpixf.h | 4 --- 5 files changed, 5 insertions(+), 66 deletions(-) diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h index 2133085deda7..ddd072cbc738 100644 --- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -191,10 +191,6 @@ void acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, acpi_adr_space_type space_id, u32 function); -void -acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *node, - acpi_adr_space_type space_id); - acpi_status acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function); diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index dc6004daf624..18fdf2bc2d49 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -20,6 +20,10 @@ extern u8 acpi_gbl_default_address_spaces[]; /* Local prototypes */ +static void +acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node, + acpi_adr_space_type space_id); + static acpi_status acpi_ev_reg_run(acpi_handle obj_handle, u32 level, void *context, void **return_value); @@ -814,7 +818,7 @@ acpi_ev_reg_run(acpi_handle obj_handle, * ******************************************************************************/ -void +static void acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node, acpi_adr_space_type space_id) { diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index 624361a5f34d..3197e6303c5b 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -306,57 +306,3 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id) } ACPI_EXPORT_SYMBOL(acpi_execute_reg_methods) - -/******************************************************************************* - * - * FUNCTION: acpi_execute_orphan_reg_method - * - * PARAMETERS: device - Handle for the device - * space_id - The address space ID - * - * RETURN: Status - * - * DESCRIPTION: Execute an "orphan" _REG method that appears under an ACPI - * device. This is a _REG method that has no corresponding region - * within the device's scope. - * - ******************************************************************************/ -acpi_status -acpi_execute_orphan_reg_method(acpi_handle device, acpi_adr_space_type space_id) -{ - struct acpi_namespace_node *node; - acpi_status status; - - ACPI_FUNCTION_TRACE(acpi_execute_orphan_reg_method); - - /* Parameter validation */ - - if (!device) { - return_ACPI_STATUS(AE_BAD_PARAMETER); - } - - status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE); - if (ACPI_FAILURE(status)) { - return_ACPI_STATUS(status); - } - - /* Convert and validate the device handle */ - - node = acpi_ns_validate_handle(device); - if (node) { - - /* - * If an "orphan" _REG method is present in the device's scope - * for the given address space ID, run it. - */ - - acpi_ev_execute_orphan_reg_method(node, space_id); - } else { - status = AE_BAD_PARAMETER; - } - - (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); - return_ACPI_STATUS(status); -} - -ACPI_EXPORT_SYMBOL(acpi_execute_orphan_reg_method) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 299ec653388c..68dd17f96f63 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1507,9 +1507,6 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) { acpi_execute_reg_methods(scope_handle, ACPI_ADR_SPACE_EC); - if (scope_handle != ec->handle) - acpi_execute_orphan_reg_method(ec->handle, ACPI_ADR_SPACE_EC); - set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags); } diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 80dc36f9d527..94d0fc3bd412 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -662,10 +662,6 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id)) -ACPI_EXTERNAL_RETURN_STATUS(acpi_status - acpi_execute_orphan_reg_method(acpi_handle device, - acpi_adr_space_type - space_id)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_remove_address_space_handler(acpi_handle device, From 5d61841c74db8b5bbbf9403f1bd4879f614617d2 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Fri, 9 Aug 2024 16:15:39 -0400 Subject: [PATCH 194/562] spi: zynqmp-gqspi: Scale timeout by data size Large blocks of data time out when reading because we don't wait long enough for the transfer to complete. Scale our timeouts based on the amount of data we are tranferring, with a healthy dose of pessimism. Signed-off-by: Sean Anderson Link: https://patch.msgid.link/20240809201540.3363243-1-sean.anderson@linux.dev Signed-off-by: Mark Brown --- drivers/spi/spi-zynqmp-gqspi.c | 30 ++++++++++++++++++++++++------ 1 file changed, 24 insertions(+), 6 deletions(-) diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c index 99524a3c9f38..558c466135a5 100644 --- a/drivers/spi/spi-zynqmp-gqspi.c +++ b/drivers/spi/spi-zynqmp-gqspi.c @@ -1033,6 +1033,18 @@ static int __maybe_unused zynqmp_runtime_resume(struct device *dev) return 0; } +static unsigned long zynqmp_qspi_timeout(struct zynqmp_qspi *xqspi, u8 bits, + unsigned long bytes) +{ + unsigned long timeout; + + /* Assume we are at most 2x slower than the nominal bus speed */ + timeout = mult_frac(bytes, 2 * 8 * MSEC_PER_SEC, + bits * xqspi->speed_hz); + /* And add 100 ms for scheduling delays */ + return msecs_to_jiffies(timeout + 100); +} + /** * zynqmp_qspi_exec_op() - Initiates the QSPI transfer * @mem: The SPI memory @@ -1049,6 +1061,7 @@ static int zynqmp_qspi_exec_op(struct spi_mem *mem, { struct zynqmp_qspi *xqspi = spi_controller_get_devdata (mem->spi->controller); + unsigned long timeout; int err = 0, i; u32 genfifoentry = 0; u16 opcode = op->cmd.opcode; @@ -1077,8 +1090,10 @@ static int zynqmp_qspi_exec_op(struct spi_mem *mem, zynqmp_gqspi_write(xqspi, GQSPI_IER_OFST, GQSPI_IER_GENFIFOEMPTY_MASK | GQSPI_IER_TXNOT_FULL_MASK); - if (!wait_for_completion_timeout - (&xqspi->data_completion, msecs_to_jiffies(1000))) { + timeout = zynqmp_qspi_timeout(xqspi, op->cmd.buswidth, + op->cmd.nbytes); + if (!wait_for_completion_timeout(&xqspi->data_completion, + timeout)) { err = -ETIMEDOUT; goto return_err; } @@ -1104,8 +1119,10 @@ static int zynqmp_qspi_exec_op(struct spi_mem *mem, GQSPI_IER_TXEMPTY_MASK | GQSPI_IER_GENFIFOEMPTY_MASK | GQSPI_IER_TXNOT_FULL_MASK); - if (!wait_for_completion_timeout - (&xqspi->data_completion, msecs_to_jiffies(1000))) { + timeout = zynqmp_qspi_timeout(xqspi, op->addr.buswidth, + op->addr.nbytes); + if (!wait_for_completion_timeout(&xqspi->data_completion, + timeout)) { err = -ETIMEDOUT; goto return_err; } @@ -1173,8 +1190,9 @@ static int zynqmp_qspi_exec_op(struct spi_mem *mem, GQSPI_IER_RXEMPTY_MASK); } } - if (!wait_for_completion_timeout - (&xqspi->data_completion, msecs_to_jiffies(1000))) + timeout = zynqmp_qspi_timeout(xqspi, op->data.buswidth, + op->data.nbytes); + if (!wait_for_completion_timeout(&xqspi->data_completion, timeout)) err = -ETIMEDOUT; } From cdf65d73e001fde600b18d7e45afadf559425ce5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 12 Aug 2024 15:11:42 +0200 Subject: [PATCH 195/562] ACPICA: Add a depth argument to acpi_execute_reg_methods() A subsequent change will need to pass a depth argument to acpi_execute_reg_methods(), so prepare that function for it. No intentional functional changes. Signed-off-by: Rafael J. Wysocki Reviewed-by: Hans de Goede Cc: All applicable Link: https://patch.msgid.link/8451567.NyiUUSuA9g@rjwysocki.net --- drivers/acpi/acpica/acevents.h | 2 +- drivers/acpi/acpica/evregion.c | 6 ++++-- drivers/acpi/acpica/evxfregn.c | 10 +++++++--- drivers/acpi/ec.c | 2 +- include/acpi/acpixf.h | 1 + 5 files changed, 14 insertions(+), 7 deletions(-) diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h index ddd072cbc738..1c5218b79fc2 100644 --- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -188,7 +188,7 @@ acpi_ev_detach_region(union acpi_operand_object *region_obj, u8 acpi_ns_is_locked); void -acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, +acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, u32 max_depth, acpi_adr_space_type space_id, u32 function); acpi_status diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index 18fdf2bc2d49..cf53b9535f18 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -65,6 +65,7 @@ acpi_status acpi_ev_initialize_op_regions(void) acpi_gbl_default_address_spaces [i])) { acpi_ev_execute_reg_methods(acpi_gbl_root_node, + ACPI_UINT32_MAX, acpi_gbl_default_address_spaces [i], ACPI_REG_CONNECT); } @@ -672,6 +673,7 @@ cleanup1: * FUNCTION: acpi_ev_execute_reg_methods * * PARAMETERS: node - Namespace node for the device + * max_depth - Depth to which search for _REG * space_id - The address space ID * function - Passed to _REG: On (1) or Off (0) * @@ -683,7 +685,7 @@ cleanup1: ******************************************************************************/ void -acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, +acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, u32 max_depth, acpi_adr_space_type space_id, u32 function) { struct acpi_reg_walk_info info; @@ -717,7 +719,7 @@ acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, * regions and _REG methods. (i.e. handlers must be installed for all * regions of this Space ID before we can run any _REG methods) */ - (void)acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, ACPI_UINT32_MAX, + (void)acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, max_depth, ACPI_NS_WALK_UNLOCK, acpi_ev_reg_run, NULL, &info, NULL); diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index 3197e6303c5b..95f78383bbdb 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -85,7 +85,8 @@ acpi_install_address_space_handler_internal(acpi_handle device, /* Run all _REG methods for this address space */ if (run_reg) { - acpi_ev_execute_reg_methods(node, space_id, ACPI_REG_CONNECT); + acpi_ev_execute_reg_methods(node, ACPI_UINT32_MAX, space_id, + ACPI_REG_CONNECT); } unlock_and_exit: @@ -263,6 +264,7 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_space_handler) * FUNCTION: acpi_execute_reg_methods * * PARAMETERS: device - Handle for the device + * max_depth - Depth to which search for _REG * space_id - The address space ID * * RETURN: Status @@ -271,7 +273,8 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_space_handler) * ******************************************************************************/ acpi_status -acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id) +acpi_execute_reg_methods(acpi_handle device, u32 max_depth, + acpi_adr_space_type space_id) { struct acpi_namespace_node *node; acpi_status status; @@ -296,7 +299,8 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id) /* Run all _REG methods for this address space */ - acpi_ev_execute_reg_methods(node, space_id, ACPI_REG_CONNECT); + acpi_ev_execute_reg_methods(node, max_depth, space_id, + ACPI_REG_CONNECT); } else { status = AE_BAD_PARAMETER; } diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 68dd17f96f63..d9c12db80f11 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1506,7 +1506,7 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, } if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) { - acpi_execute_reg_methods(scope_handle, ACPI_ADR_SPACE_EC); + acpi_execute_reg_methods(scope_handle, ACPI_UINT32_MAX, ACPI_ADR_SPACE_EC); set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags); } diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 94d0fc3bd412..9f1c1d225e32 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -660,6 +660,7 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status void *context)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_execute_reg_methods(acpi_handle device, + u32 nax_depth, acpi_adr_space_type space_id)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status From 71bf41b8e913ec9fc91f0d39ab8fb320229ec604 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 12 Aug 2024 15:16:21 +0200 Subject: [PATCH 196/562] ACPI: EC: Evaluate _REG outside the EC scope more carefully Commit 60fa6ae6e6d0 ("ACPI: EC: Install address space handler at the namespace root") caused _REG methods for EC operation regions outside the EC device scope to be evaluated which on some systems leads to the evaluation of _REG methods in the scopes of device objects representing devices that are not present and not functional according to the _STA return values. Some of those device objects represent EC "alternatives" and if _REG is evaluated for their operation regions, the platform firmware may be confused and the platform may start to behave incorrectly. To avoid this problem, only evaluate _REG for EC operation regions located in the scopes of device objects representing known-to-be-present devices. For this purpose, partially revert commit 60fa6ae6e6d0 and trigger the evaluation of _REG for EC operation regions from acpi_bus_attach() for the known-valid devices. Fixes: 60fa6ae6e6d0 ("ACPI: EC: Install address space handler at the namespace root") Link: https://lore.kernel.org/linux-acpi/1f76b7e2-1928-4598-8037-28a1785c2d13@redhat.com Link: https://bugzilla.redhat.com/show_bug.cgi?id=2298938 Link: https://bugzilla.redhat.com/show_bug.cgi?id=2302253 Reported-by: Hans de Goede Signed-off-by: Rafael J. Wysocki Reviewed-by: Hans de Goede Cc: All applicable Link: https://patch.msgid.link/23612351.6Emhk5qWAg@rjwysocki.net --- drivers/acpi/ec.c | 11 +++++++++-- drivers/acpi/internal.h | 1 + drivers/acpi/scan.c | 2 ++ 3 files changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index d9c12db80f11..38d2f6e6b12b 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1487,12 +1487,13 @@ static bool install_gpio_irq_event_handler(struct acpi_ec *ec) static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, bool call_reg) { - acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle; acpi_status status; acpi_ec_start(ec, false); if (!test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) { + acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle; + acpi_ec_enter_noirq(ec); status = acpi_install_address_space_handler_no_reg(scope_handle, ACPI_ADR_SPACE_EC, @@ -1506,7 +1507,7 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, } if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) { - acpi_execute_reg_methods(scope_handle, ACPI_UINT32_MAX, ACPI_ADR_SPACE_EC); + acpi_execute_reg_methods(ec->handle, ACPI_UINT32_MAX, ACPI_ADR_SPACE_EC); set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags); } @@ -1721,6 +1722,12 @@ static void acpi_ec_remove(struct acpi_device *device) } } +void acpi_ec_register_opregions(struct acpi_device *adev) +{ + if (first_ec && first_ec->handle != adev->handle) + acpi_execute_reg_methods(adev->handle, 1, ACPI_ADR_SPACE_EC); +} + static acpi_status ec_parse_io_ports(struct acpi_resource *resource, void *context) { diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 601b670356e5..aadd4c218b32 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -223,6 +223,7 @@ int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit, acpi_handle handle, acpi_ec_query_func func, void *data); void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit); +void acpi_ec_register_opregions(struct acpi_device *adev); #ifdef CONFIG_PM_SLEEP void acpi_ec_flush_work(void); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 59771412686b..22ae7829a915 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2273,6 +2273,8 @@ static int acpi_bus_attach(struct acpi_device *device, void *first_pass) if (device->handler) goto ok; + acpi_ec_register_opregions(device); + if (!device->flags.initialized) { device->flags.power_manageable = device->power.states[ACPI_STATE_D0].flags.valid; From 46a6e10a1ab16cc71d4a3cab73e79aabadd6b8ea Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 12 Aug 2024 14:18:06 +0100 Subject: [PATCH 197/562] btrfs: send: allow cloning non-aligned extent if it ends at i_size If we a find that an extent is shared but its end offset is not sector size aligned, then we don't clone it and issue write operations instead. This is because the reflink (remap_file_range) operation does not allow to clone unaligned ranges, except if the end offset of the range matches the i_size of the source and destination files (and the start offset is sector size aligned). While this is not incorrect because send can only guarantee that a file has the same data in the source and destination snapshots, it's not optimal and generates confusion and surprising behaviour for users. For example, running this test: $ cat test.sh #!/bin/bash DEV=/dev/sdi MNT=/mnt/sdi mkfs.btrfs -f $DEV mount $DEV $MNT # Use a file size not aligned to any possible sector size. file_size=$((1 * 1024 * 1024 + 5)) # 1MB + 5 bytes dd if=/dev/random of=$MNT/foo bs=$file_size count=1 cp --reflink=always $MNT/foo $MNT/bar btrfs subvolume snapshot -r $MNT/ $MNT/snap rm -f /tmp/send-test btrfs send -f /tmp/send-test $MNT/snap umount $MNT mkfs.btrfs -f $DEV mount $DEV $MNT btrfs receive -vv -f /tmp/send-test $MNT xfs_io -r -c "fiemap -v" $MNT/snap/bar umount $MNT Gives the following result: (...) mkfile o258-7-0 rename o258-7-0 -> bar write bar - offset=0 length=49152 write bar - offset=49152 length=49152 write bar - offset=98304 length=49152 write bar - offset=147456 length=49152 write bar - offset=196608 length=49152 write bar - offset=245760 length=49152 write bar - offset=294912 length=49152 write bar - offset=344064 length=49152 write bar - offset=393216 length=49152 write bar - offset=442368 length=49152 write bar - offset=491520 length=49152 write bar - offset=540672 length=49152 write bar - offset=589824 length=49152 write bar - offset=638976 length=49152 write bar - offset=688128 length=49152 write bar - offset=737280 length=49152 write bar - offset=786432 length=49152 write bar - offset=835584 length=49152 write bar - offset=884736 length=49152 write bar - offset=933888 length=49152 write bar - offset=983040 length=49152 write bar - offset=1032192 length=16389 chown bar - uid=0, gid=0 chmod bar - mode=0644 utimes bar utimes BTRFS_IOC_SET_RECEIVED_SUBVOL uuid=06d640da-9ca1-604c-b87c-3375175a8eb3, stransid=7 /mnt/sdi/snap/bar: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..2055]: 26624..28679 2056 0x1 There's no clone operation to clone extents from the file foo into file bar and fiemap confirms there's no shared flag (0x2000). So update send_write_or_clone() so that it proceeds with cloning if the source and destination ranges end at the i_size of the respective files. After this changes the result of the test is: (...) mkfile o258-7-0 rename o258-7-0 -> bar clone bar - source=foo source offset=0 offset=0 length=1048581 chown bar - uid=0, gid=0 chmod bar - mode=0644 utimes bar utimes BTRFS_IOC_SET_RECEIVED_SUBVOL uuid=582420f3-ea7d-564e-bbe5-ce440d622190, stransid=7 /mnt/sdi/snap/bar: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..2055]: 26624..28679 2056 0x2001 A test case for fstests will also follow up soon. Link: https://github.com/kdave/btrfs-progs/issues/572#issuecomment-2282841416 CC: stable@vger.kernel.org # 5.10+ Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/send.c | 52 ++++++++++++++++++++++++++++++++++++------------- 1 file changed, 39 insertions(+), 13 deletions(-) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 4ca711a773ef..7fc692fc76e1 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6157,25 +6157,51 @@ static int send_write_or_clone(struct send_ctx *sctx, u64 offset = key->offset; u64 end; u64 bs = sctx->send_root->fs_info->sectorsize; + struct btrfs_file_extent_item *ei; + u64 disk_byte; + u64 data_offset; + u64 num_bytes; + struct btrfs_inode_info info = { 0 }; end = min_t(u64, btrfs_file_extent_end(path), sctx->cur_inode_size); if (offset >= end) return 0; - if (clone_root && IS_ALIGNED(end, bs)) { - struct btrfs_file_extent_item *ei; - u64 disk_byte; - u64 data_offset; + num_bytes = end - offset; - ei = btrfs_item_ptr(path->nodes[0], path->slots[0], - struct btrfs_file_extent_item); - disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei); - data_offset = btrfs_file_extent_offset(path->nodes[0], ei); - ret = clone_range(sctx, path, clone_root, disk_byte, - data_offset, offset, end - offset); - } else { - ret = send_extent_data(sctx, path, offset, end - offset); - } + if (!clone_root) + goto write_data; + + if (IS_ALIGNED(end, bs)) + goto clone_data; + + /* + * If the extent end is not aligned, we can clone if the extent ends at + * the i_size of the inode and the clone range ends at the i_size of the + * source inode, otherwise the clone operation fails with -EINVAL. + */ + if (end != sctx->cur_inode_size) + goto write_data; + + ret = get_inode_info(clone_root->root, clone_root->ino, &info); + if (ret < 0) + return ret; + + if (clone_root->offset + num_bytes == info.size) + goto clone_data; + +write_data: + ret = send_extent_data(sctx, path, offset, num_bytes); + sctx->cur_inode_next_write_offset = end; + return ret; + +clone_data: + ei = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_file_extent_item); + disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei); + data_offset = btrfs_file_extent_offset(path->nodes[0], ei); + ret = clone_range(sctx, path, clone_root, disk_byte, data_offset, offset, + num_bytes); sctx->cur_inode_next_write_offset = end; return ret; } From 1e1fd567d32fcf7544c6e09e0e5bc6c650da6e23 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 13 Aug 2024 12:38:51 +0200 Subject: [PATCH 198/562] dm suspend: return -ERESTARTSYS instead of -EINTR This commit changes device mapper, so that it returns -ERESTARTSYS instead of -EINTR when it is interrupted by a signal (so that the ioctl can be restarted). The manpage signal(7) says that the ioctl function should be restarted if the signal was handled with SA_RESTART. Signed-off-by: Mikulas Patocka Cc: stable@vger.kernel.org --- drivers/md/dm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 97fab2087df8..87bb90303435 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2737,7 +2737,7 @@ static int dm_wait_for_bios_completion(struct mapped_device *md, unsigned int ta break; if (signal_pending_state(task_state, current)) { - r = -EINTR; + r = -ERESTARTSYS; break; } @@ -2762,7 +2762,7 @@ static int dm_wait_for_completion(struct mapped_device *md, unsigned int task_st break; if (signal_pending_state(task_state, current)) { - r = -EINTR; + r = -ERESTARTSYS; break; } From 7a636b4f03af9d541205f69e373672e7b2b60a8a Mon Sep 17 00:00:00 2001 From: Khazhismel Kumykov Date: Tue, 13 Aug 2024 12:39:52 +0200 Subject: [PATCH 199/562] dm resume: don't return EINVAL when signalled If the dm_resume method is called on a device that is not suspended, the method will suspend the device briefly, before resuming it (so that the table will be swapped). However, there was a bug that the return value of dm_suspended_md was not checked. dm_suspended_md may return an error when it is interrupted by a signal. In this case, do_resume would call dm_swap_table, which would return -EINVAL. This commit fixes the logic, so that error returned by dm_suspend is checked and the resume operation is undone. Signed-off-by: Mikulas Patocka Signed-off-by: Khazhismel Kumykov Cc: stable@vger.kernel.org --- drivers/md/dm-ioctl.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index c2c07bfa6471..f299ff393a6a 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1181,8 +1181,26 @@ static int do_resume(struct dm_ioctl *param) suspend_flags &= ~DM_SUSPEND_LOCKFS_FLAG; if (param->flags & DM_NOFLUSH_FLAG) suspend_flags |= DM_SUSPEND_NOFLUSH_FLAG; - if (!dm_suspended_md(md)) - dm_suspend(md, suspend_flags); + if (!dm_suspended_md(md)) { + r = dm_suspend(md, suspend_flags); + if (r) { + down_write(&_hash_lock); + hc = dm_get_mdptr(md); + if (hc && !hc->new_map) { + hc->new_map = new_map; + new_map = NULL; + } else { + r = -ENXIO; + } + up_write(&_hash_lock); + if (new_map) { + dm_sync_table(md); + dm_table_destroy(new_map); + } + dm_put(md); + return r; + } + } old_size = dm_get_size(md); old_map = dm_swap_table(md, new_map); From 2a0629834cd82f05d424bbc193374f9a43d1f87d Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Fri, 9 Aug 2024 11:16:28 +0800 Subject: [PATCH 200/562] vfs: Don't evict inode under the inode lru traversing context MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The inode reclaiming process(See function prune_icache_sb) collects all reclaimable inodes and mark them with I_FREEING flag at first, at that time, other processes will be stuck if they try getting these inodes (See function find_inode_fast), then the reclaiming process destroy the inodes by function dispose_list(). Some filesystems(eg. ext4 with ea_inode feature, ubifs with xattr) may do inode lookup in the inode evicting callback function, if the inode lookup is operated under the inode lru traversing context, deadlock problems may happen. Case 1: In function ext4_evict_inode(), the ea inode lookup could happen if ea_inode feature is enabled, the lookup process will be stuck under the evicting context like this: 1. File A has inode i_reg and an ea inode i_ea 2. getfattr(A, xattr_buf) // i_ea is added into lru // lru->i_ea 3. Then, following three processes running like this: PA PB echo 2 > /proc/sys/vm/drop_caches shrink_slab prune_dcache_sb // i_reg is added into lru, lru->i_ea->i_reg prune_icache_sb list_lru_walk_one inode_lru_isolate i_ea->i_state |= I_FREEING // set inode state inode_lru_isolate __iget(i_reg) spin_unlock(&i_reg->i_lock) spin_unlock(lru_lock) rm file A i_reg->nlink = 0 iput(i_reg) // i_reg->nlink is 0, do evict ext4_evict_inode ext4_xattr_delete_inode ext4_xattr_inode_dec_ref_all ext4_xattr_inode_iget ext4_iget(i_ea->i_ino) iget_locked find_inode_fast __wait_on_freeing_inode(i_ea) ----→ AA deadlock dispose_list // cannot be executed by prune_icache_sb wake_up_bit(&i_ea->i_state) Case 2: In deleted inode writing function ubifs_jnl_write_inode(), file deleting process holds BASEHD's wbuf->io_mutex while getting the xattr inode, which could race with inode reclaiming process(The reclaiming process could try locking BASEHD's wbuf->io_mutex in inode evicting function), then an ABBA deadlock problem would happen as following: 1. File A has inode ia and a xattr(with inode ixa), regular file B has inode ib and a xattr. 2. getfattr(A, xattr_buf) // ixa is added into lru // lru->ixa 3. Then, following three processes running like this: PA PB PC echo 2 > /proc/sys/vm/drop_caches shrink_slab prune_dcache_sb // ib and ia are added into lru, lru->ixa->ib->ia prune_icache_sb list_lru_walk_one inode_lru_isolate ixa->i_state |= I_FREEING // set inode state inode_lru_isolate __iget(ib) spin_unlock(&ib->i_lock) spin_unlock(lru_lock) rm file B ib->nlink = 0 rm file A iput(ia) ubifs_evict_inode(ia) ubifs_jnl_delete_inode(ia) ubifs_jnl_write_inode(ia) make_reservation(BASEHD) // Lock wbuf->io_mutex ubifs_iget(ixa->i_ino) iget_locked find_inode_fast __wait_on_freeing_inode(ixa) | iput(ib) // ib->nlink is 0, do evict | ubifs_evict_inode | ubifs_jnl_delete_inode(ib) ↓ ubifs_jnl_write_inode ABBA deadlock ←-----make_reservation(BASEHD) dispose_list // cannot be executed by prune_icache_sb wake_up_bit(&ixa->i_state) Fix the possible deadlock by using new inode state flag I_LRU_ISOLATING to pin the inode in memory while inode_lru_isolate() reclaims its pages instead of using ordinary inode reference. This way inode deletion cannot be triggered from inode_lru_isolate() thus avoiding the deadlock. evict() is made to wait for I_LRU_ISOLATING to be cleared before proceeding with inode cleanup. Link: https://lore.kernel.org/all/37c29c42-7685-d1f0-067d-63582ffac405@huaweicloud.com/ Link: https://bugzilla.kernel.org/show_bug.cgi?id=219022 Fixes: e50e5129f384 ("ext4: xattr-in-inode support") Fixes: 7959cf3a7506 ("ubifs: journal: Handle xattrs like files") Cc: stable@vger.kernel.org Signed-off-by: Zhihao Cheng Link: https://lore.kernel.org/r/20240809031628.1069873-1-chengzhihao@huaweicloud.com Reviewed-by: Jan Kara Suggested-by: Jan Kara Suggested-by: Mateusz Guzik Signed-off-by: Christian Brauner --- fs/inode.c | 39 +++++++++++++++++++++++++++++++++++++-- include/linux/fs.h | 5 +++++ 2 files changed, 42 insertions(+), 2 deletions(-) diff --git a/fs/inode.c b/fs/inode.c index 86670941884b..10c4619faeef 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -488,6 +488,39 @@ static void inode_lru_list_del(struct inode *inode) this_cpu_dec(nr_unused); } +static void inode_pin_lru_isolating(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); + inode->i_state |= I_LRU_ISOLATING; +} + +static void inode_unpin_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + WARN_ON(!(inode->i_state & I_LRU_ISOLATING)); + inode->i_state &= ~I_LRU_ISOLATING; + smp_mb(); + wake_up_bit(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); +} + +static void inode_wait_for_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + if (inode->i_state & I_LRU_ISOLATING) { + DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING); + wait_queue_head_t *wqh; + + wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); + __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); + spin_lock(&inode->i_lock); + WARN_ON(inode->i_state & I_LRU_ISOLATING); + } + spin_unlock(&inode->i_lock); +} + /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add @@ -657,6 +690,8 @@ static void evict(struct inode *inode) inode_sb_list_del(inode); + inode_wait_for_lru_isolating(inode); + /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since @@ -855,7 +890,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, * be under pressure before the cache inside the highmem zone. */ if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) { - __iget(inode); + inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); spin_unlock(lru_lock); if (remove_inode_buffers(inode)) { @@ -867,7 +902,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, __count_vm_events(PGINODESTEAL, reap); mm_account_reclaimed_pages(reap); } - iput(inode); + inode_unpin_lru_isolating(inode); spin_lock(lru_lock); return LRU_RETRY; } diff --git a/include/linux/fs.h b/include/linux/fs.h index fd34b5755c0b..fb0426f349fc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2392,6 +2392,9 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * + * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding + * i_count. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2415,6 +2418,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) #define I_PINNING_NETFS_WB (1 << 18) +#define __I_LRU_ISOLATING 19 +#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) From e3786b29c54cdae3490b07180a54e2461f42144c Mon Sep 17 00:00:00 2001 From: Dominique Martinet Date: Thu, 8 Aug 2024 14:29:38 +0100 Subject: [PATCH 201/562] 9p: Fix DIO read through netfs If a program is watching a file on a 9p mount, it won't see any change in size if the file being exported by the server is changed directly in the source filesystem, presumably because 9p doesn't have change notifications, and because netfs skips the reads if the file is empty. Fix this by attempting to read the full size specified when a DIO read is requested (such as when 9p is operating in unbuffered mode) and dealing with a short read if the EOF was less than the expected read. To make this work, filesystems using netfslib must not set NETFS_SREQ_CLEAR_TAIL if performing a DIO read where that read hit the EOF. I don't want to mandatorily clear this flag in netfslib for DIO because, say, ceph might make a read from an object that is not completely filled, but does not reside at the end of file - and so we need to clear the excess. This can be tested by watching an empty file over 9p within a VM (such as in the ktest framework): while true; do read content; if [ -n "$content" ]; then echo $content; break; fi; done < /host/tmp/foo then writing something into the empty file. The watcher should immediately display the file content and break out of the loop. Without this fix, it remains in the loop indefinitely. Fixes: 80105ed2fd27 ("9p: Use netfslib read/write_iter") Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218916 Signed-off-by: David Howells Link: https://lore.kernel.org/r/1229195.1723211769@warthog.procyon.org.uk cc: Eric Van Hensbergen cc: Latchesar Ionkov cc: Christian Schoenebeck cc: Marc Dionne cc: Ilya Dryomov cc: Steve French cc: Paulo Alcantara cc: Trond Myklebust cc: v9fs@lists.linux.dev cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: linux-nfs@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Dominique Martinet Signed-off-by: Christian Brauner --- fs/9p/vfs_addr.c | 3 ++- fs/afs/file.c | 3 ++- fs/ceph/addr.c | 6 ++++-- fs/netfs/io.c | 17 +++++++++++------ fs/nfs/fscache.c | 3 ++- fs/smb/client/file.c | 3 ++- 6 files changed, 23 insertions(+), 12 deletions(-) diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index a97ceb105cd8..24fdc74caeba 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -75,7 +75,8 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq) /* if we just extended the file size, any portion not in * cache won't be on server and is zeroes */ - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + if (subreq->rreq->origin != NETFS_DIO_READ) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); netfs_subreq_terminated(subreq, err ?: total, false); } diff --git a/fs/afs/file.c b/fs/afs/file.c index c3f0c45ae9a9..ec1be0091fdb 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -242,7 +242,8 @@ static void afs_fetch_data_notify(struct afs_operation *op) req->error = error; if (subreq) { - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + if (subreq->rreq->origin != NETFS_DIO_READ) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); netfs_subreq_terminated(subreq, error ?: req->actual_len, false); req->subreq = NULL; } else if (req->done) { diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index cc0a2240de98..c4744a02db75 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -246,7 +246,8 @@ static void finish_netfs_read(struct ceph_osd_request *req) if (err >= 0) { if (sparse && err > 0) err = ceph_sparse_ext_map_end(op); - if (err < subreq->len) + if (err < subreq->len && + subreq->rreq->origin != NETFS_DIO_READ) __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); if (IS_ENCRYPTED(inode) && err > 0) { err = ceph_fscrypt_decrypt_extents(inode, @@ -282,7 +283,8 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq) size_t len; int mode; - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + if (rreq->origin != NETFS_DIO_READ) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); __clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); if (subreq->start >= inode->i_size) diff --git a/fs/netfs/io.c b/fs/netfs/io.c index c179a1c73fa7..5367caf3fa28 100644 --- a/fs/netfs/io.c +++ b/fs/netfs/io.c @@ -530,7 +530,8 @@ incomplete: if (transferred_or_error == 0) { if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { - subreq->error = -ENODATA; + if (rreq->origin != NETFS_DIO_READ) + subreq->error = -ENODATA; goto failed; } } else { @@ -601,9 +602,14 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq, } if (subreq->len > ictx->zero_point - subreq->start) subreq->len = ictx->zero_point - subreq->start; + + /* We limit buffered reads to the EOF, but let the + * server deal with larger-than-EOF DIO/unbuffered + * reads. + */ + if (subreq->len > rreq->i_size - subreq->start) + subreq->len = rreq->i_size - subreq->start; } - if (subreq->len > rreq->i_size - subreq->start) - subreq->len = rreq->i_size - subreq->start; if (rreq->rsize && subreq->len > rreq->rsize) subreq->len = rreq->rsize; @@ -739,11 +745,10 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync) do { _debug("submit %llx + %llx >= %llx", rreq->start, rreq->submitted, rreq->i_size); - if (rreq->origin == NETFS_DIO_READ && - rreq->start + rreq->submitted >= rreq->i_size) - break; if (!netfs_rreq_submit_slice(rreq, &io_iter)) break; + if (test_bit(NETFS_SREQ_NO_PROGRESS, &rreq->flags)) + break; if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) && test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags)) break; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index bf29a65c5027..7a558dea75c4 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -363,7 +363,8 @@ void nfs_netfs_read_completion(struct nfs_pgio_header *hdr) return; sreq = netfs->sreq; - if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) + if (test_bit(NFS_IOHDR_EOF, &hdr->flags) && + sreq->rreq->origin != NETFS_DIO_READ) __set_bit(NETFS_SREQ_CLEAR_TAIL, &sreq->flags); if (hdr->error) diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index b2405dd4d4d4..3f3842e7b44a 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -217,7 +217,8 @@ static void cifs_req_issue_read(struct netfs_io_subrequest *subreq) goto out; } - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + if (subreq->rreq->origin != NETFS_DIO_READ) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); rc = rdata->server->ops->async_readv(rdata); out: From 810ee43d9cd245d138a2733d87a24858a23f577d Mon Sep 17 00:00:00 2001 From: Phillip Lougher Date: Mon, 12 Aug 2024 00:28:21 +0100 Subject: [PATCH 202/562] Squashfs: sanity check symbolic link size Syzkiller reports a "KMSAN: uninit-value in pick_link" bug. This is caused by an uninitialised page, which is ultimately caused by a corrupted symbolic link size read from disk. The reason why the corrupted symlink size causes an uninitialised page is due to the following sequence of events: 1. squashfs_read_inode() is called to read the symbolic link from disk. This assigns the corrupted value 3875536935 to inode->i_size. 2. Later squashfs_symlink_read_folio() is called, which assigns this corrupted value to the length variable, which being a signed int, overflows producing a negative number. 3. The following loop that fills in the page contents checks that the copied bytes is less than length, which being negative means the loop is skipped, producing an uninitialised page. This patch adds a sanity check which checks that the symbolic link size is not larger than expected. -- Signed-off-by: Phillip Lougher Link: https://lore.kernel.org/r/20240811232821.13903-1-phillip@squashfs.org.uk Reported-by: Lizhi Xu Reported-by: syzbot+24ac24ff58dc5b0d26b9@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/000000000000a90e8c061e86a76b@google.com/ V2: fix spelling mistake. Signed-off-by: Christian Brauner --- fs/squashfs/inode.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index 16bd693d0b3a..d5918eba27e3 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -279,8 +279,13 @@ int squashfs_read_inode(struct inode *inode, long long ino) if (err < 0) goto failed_read; - set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_size = le32_to_cpu(sqsh_ino->symlink_size); + if (inode->i_size > PAGE_SIZE) { + ERROR("Corrupted symlink\n"); + return -EINVAL; + } + + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_op = &squashfs_symlink_inode_ops; inode_nohighmem(inode); inode->i_data.a_ops = &squashfs_symlink_aops; From e4956dc7a84da074fd8dc10f7abd147f15b3ae58 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 13 Aug 2024 06:10:59 -0600 Subject: [PATCH 203/562] io_uring/sqpoll: annotate debug task == current with data_race() There's a debug check in io_sq_thread_park() checking if it's the SQPOLL thread itself calling park. KCSAN warns about this, as we should not be reading sqd->thread outside of sqd->lock. Just silence this with data_race(). The pointer isn't used for anything but this debug check. Reported-by: syzbot+2b946a3fd80caf971b21@syzkaller.appspotmail.com Signed-off-by: Jens Axboe --- io_uring/sqpoll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index b3722e5275e7..3b50dc9586d1 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -44,7 +44,7 @@ void io_sq_thread_unpark(struct io_sq_data *sqd) void io_sq_thread_park(struct io_sq_data *sqd) __acquires(&sqd->lock) { - WARN_ON_ONCE(sqd->thread == current); + WARN_ON_ONCE(data_race(sqd->thread) == current); atomic_inc(&sqd->park_pending); set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); From bcc954c6caba01fca143162d5fbb90e46aa1ad80 Mon Sep 17 00:00:00 2001 From: Ryo Takakura Date: Mon, 12 Aug 2024 16:27:03 +0900 Subject: [PATCH 204/562] printk/panic: Allow cpu backtraces to be written into ringbuffer during panic commit 779dbc2e78d7 ("printk: Avoid non-panic CPUs writing to ringbuffer") disabled non-panic CPUs to further write messages to ringbuffer after panicked. Since the commit, non-panicked CPU's are not allowed to write to ring buffer after panicked and CPU backtrace which is triggered after panicked to sample non-panicked CPUs' backtrace no longer serves its function as it has nothing to print. Fix the issue by allowing non-panicked CPUs to write into ringbuffer while CPU backtrace is in flight. Fixes: 779dbc2e78d7 ("printk: Avoid non-panic CPUs writing to ringbuffer") Signed-off-by: Ryo Takakura Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240812072703.339690-1-takakura@valinux.co.jp Signed-off-by: Petr Mladek --- include/linux/panic.h | 1 + kernel/panic.c | 8 +++++++- kernel/printk/printk.c | 2 +- 3 files changed, 9 insertions(+), 2 deletions(-) diff --git a/include/linux/panic.h b/include/linux/panic.h index 3130e0b5116b..54d90b6c5f47 100644 --- a/include/linux/panic.h +++ b/include/linux/panic.h @@ -16,6 +16,7 @@ extern void oops_enter(void); extern void oops_exit(void); extern bool oops_may_print(void); +extern bool panic_triggering_all_cpu_backtrace; extern int panic_timeout; extern unsigned long panic_print; extern int panic_on_oops; diff --git a/kernel/panic.c b/kernel/panic.c index f861bedc1925..2a0449144f82 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -64,6 +64,8 @@ unsigned long panic_on_taint; bool panic_on_taint_nousertaint = false; static unsigned int warn_limit __read_mostly; +bool panic_triggering_all_cpu_backtrace; + int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); @@ -253,8 +255,12 @@ void check_panic_on_warn(const char *origin) */ static void panic_other_cpus_shutdown(bool crash_kexec) { - if (panic_print & PANIC_PRINT_ALL_CPU_BT) + if (panic_print & PANIC_PRINT_ALL_CPU_BT) { + /* Temporary allow non-panic CPUs to write their backtraces. */ + panic_triggering_all_cpu_backtrace = true; trigger_all_cpu_backtrace(); + panic_triggering_all_cpu_backtrace = false; + } /* * Note that smp_send_stop() is the usual SMP shutdown function, diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 054c0e7784fd..c22b07049c38 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2316,7 +2316,7 @@ asmlinkage int vprintk_emit(int facility, int level, * non-panic CPUs are generating any messages, they will be * silently dropped. */ - if (other_cpu_in_panic()) + if (other_cpu_in_panic() && !panic_triggering_all_cpu_backtrace) return 0; if (level == LOGLEVEL_SCHED) { From b098495e69491c2225681f43228312d32477217b Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Sat, 3 Aug 2024 19:32:33 +0800 Subject: [PATCH 205/562] KVM: x86: hyper-v: Remove unused inline function kvm_hv_free_pa_page() There is no caller in tree since introduction in commit b4f69df0f65e ("KVM: x86: Make Hyper-V emulation optional") Signed-off-by: Yue Haibing Message-ID: <20240803113233.128185-1-yuehaibing@huawei.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/hyperv.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 923e64903da9..913bfc96959c 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -286,7 +286,6 @@ static inline int kvm_hv_hypercall(struct kvm_vcpu *vcpu) return HV_STATUS_ACCESS_DENIED; } static inline void kvm_hv_vcpu_purge_flush_tlb(struct kvm_vcpu *vcpu) {} -static inline void kvm_hv_free_pa_page(struct kvm *kvm) {} static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector) { return false; From 6252690f7e1b173b86a4c27dfc046b351ab423e7 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Fri, 9 Aug 2024 16:54:22 +0900 Subject: [PATCH 206/562] btrfs: fix invalid mapping of extent xarray state In __extent_writepage_io(), we call btrfs_set_range_writeback() -> folio_start_writeback(), which clears PAGECACHE_TAG_DIRTY mark from the mapping xarray if the folio is not dirty. This worked fine before commit 97713b1a2ced ("btrfs: do not clear page dirty inside extent_write_locked_range()"). After the commit, however, the folio is still dirty at this point, so the mapping DIRTY tag is not cleared anymore. Then, __extent_writepage_io() calls btrfs_folio_clear_dirty() to clear the folio's dirty flag. That results in the page being unlocked with a "strange" state. The page is not PageDirty, but the mapping tag is set as PAGECACHE_TAG_DIRTY. This strange state looks like causing a hang with a call trace below when running fstests generic/091 on a null_blk device. It is waiting for a folio lock. While I don't have an exact relation between this hang and the strange state, fixing the state also fixes the hang. And, that state is worth fixing anyway. This commit reorders btrfs_folio_clear_dirty() and btrfs_set_range_writeback() in __extent_writepage_io(), so that the PAGECACHE_TAG_DIRTY tag is properly removed from the xarray. [464.274] task:fsx state:D stack:0 pid:3034 tgid:3034 ppid:2853 flags:0x00004002 [464.286] Call Trace: [464.291] [464.295] __schedule+0x10ed/0x6260 [464.301] ? __pfx___blk_flush_plug+0x10/0x10 [464.308] ? __submit_bio+0x37c/0x450 [464.314] ? __pfx___schedule+0x10/0x10 [464.321] ? lock_release+0x567/0x790 [464.327] ? __pfx_lock_acquire+0x10/0x10 [464.334] ? __pfx_lock_release+0x10/0x10 [464.340] ? __pfx_lock_acquire+0x10/0x10 [464.347] ? __pfx_lock_release+0x10/0x10 [464.353] ? do_raw_spin_lock+0x12e/0x270 [464.360] schedule+0xdf/0x3b0 [464.365] io_schedule+0x8f/0xf0 [464.371] folio_wait_bit_common+0x2ca/0x6d0 [464.378] ? folio_wait_bit_common+0x1cc/0x6d0 [464.385] ? __pfx_folio_wait_bit_common+0x10/0x10 [464.392] ? __pfx_filemap_get_folios_tag+0x10/0x10 [464.400] ? __pfx_wake_page_function+0x10/0x10 [464.407] ? __pfx___might_resched+0x10/0x10 [464.414] ? do_raw_spin_unlock+0x58/0x1f0 [464.420] extent_write_cache_pages+0xe49/0x1620 [btrfs] [464.428] ? lock_acquire+0x435/0x500 [464.435] ? __pfx_extent_write_cache_pages+0x10/0x10 [btrfs] [464.443] ? btrfs_do_write_iter+0x493/0x640 [btrfs] [464.451] ? orc_find.part.0+0x1d4/0x380 [464.457] ? __pfx_lock_release+0x10/0x10 [464.464] ? __pfx_lock_release+0x10/0x10 [464.471] ? btrfs_do_write_iter+0x493/0x640 [btrfs] [464.478] btrfs_writepages+0x1cc/0x460 [btrfs] [464.485] ? __pfx_btrfs_writepages+0x10/0x10 [btrfs] [464.493] ? is_bpf_text_address+0x6e/0x100 [464.500] ? kernel_text_address+0x145/0x160 [464.507] ? unwind_get_return_address+0x5e/0xa0 [464.514] ? arch_stack_walk+0xac/0x100 [464.521] do_writepages+0x176/0x780 [464.527] ? lock_release+0x567/0x790 [464.533] ? __pfx_do_writepages+0x10/0x10 [464.540] ? __pfx_lock_acquire+0x10/0x10 [464.546] ? __pfx_stack_trace_save+0x10/0x10 [464.553] ? do_raw_spin_lock+0x12e/0x270 [464.560] ? do_raw_spin_unlock+0x58/0x1f0 [464.566] ? _raw_spin_unlock+0x23/0x40 [464.573] ? wbc_attach_and_unlock_inode+0x3da/0x7d0 [464.580] filemap_fdatawrite_wbc+0x113/0x180 [464.587] ? prepare_pages.constprop.0+0x13c/0x5c0 [btrfs] [464.596] __filemap_fdatawrite_range+0xaf/0xf0 [464.603] ? __pfx___filemap_fdatawrite_range+0x10/0x10 [464.611] ? trace_irq_enable.constprop.0+0xce/0x110 [464.618] ? kasan_quarantine_put+0xd7/0x1e0 [464.625] btrfs_start_ordered_extent+0x46f/0x570 [btrfs] [464.633] ? __pfx_btrfs_start_ordered_extent+0x10/0x10 [btrfs] [464.642] ? __clear_extent_bit+0x2c0/0x9d0 [btrfs] [464.650] btrfs_lock_and_flush_ordered_range+0xc6/0x180 [btrfs] [464.659] ? __pfx_btrfs_lock_and_flush_ordered_range+0x10/0x10 [btrfs] [464.669] btrfs_read_folio+0x12a/0x1d0 [btrfs] [464.676] ? __pfx_btrfs_read_folio+0x10/0x10 [btrfs] [464.684] ? __pfx_filemap_add_folio+0x10/0x10 [464.691] ? __pfx___might_resched+0x10/0x10 [464.698] ? __filemap_get_folio+0x1c5/0x450 [464.705] prepare_uptodate_page+0x12e/0x4d0 [btrfs] [464.713] prepare_pages.constprop.0+0x13c/0x5c0 [btrfs] [464.721] ? fault_in_iov_iter_readable+0xd2/0x240 [464.729] btrfs_buffered_write+0x5bd/0x12f0 [btrfs] [464.737] ? __pfx_btrfs_buffered_write+0x10/0x10 [btrfs] [464.745] ? __pfx_lock_release+0x10/0x10 [464.752] ? generic_write_checks+0x275/0x400 [464.759] ? down_write+0x118/0x1f0 [464.765] ? up_write+0x19b/0x500 [464.770] btrfs_direct_write+0x731/0xba0 [btrfs] [464.778] ? __pfx_btrfs_direct_write+0x10/0x10 [btrfs] [464.785] ? __pfx___might_resched+0x10/0x10 [464.792] ? lock_acquire+0x435/0x500 [464.798] ? lock_acquire+0x435/0x500 [464.804] btrfs_do_write_iter+0x494/0x640 [btrfs] [464.811] ? __pfx_btrfs_do_write_iter+0x10/0x10 [btrfs] [464.819] ? __pfx___might_resched+0x10/0x10 [464.825] ? rw_verify_area+0x6d/0x590 [464.831] vfs_write+0x5d7/0xf50 [464.837] ? __might_fault+0x9d/0x120 [464.843] ? __pfx_vfs_write+0x10/0x10 [464.849] ? btrfs_file_llseek+0xb1/0xfb0 [btrfs] [464.856] ? lock_release+0x567/0x790 [464.862] ksys_write+0xfb/0x1d0 [464.867] ? __pfx_ksys_write+0x10/0x10 [464.873] ? _raw_spin_unlock+0x23/0x40 [464.879] ? btrfs_getattr+0x4af/0x670 [btrfs] [464.886] ? vfs_getattr_nosec+0x79/0x340 [464.892] do_syscall_64+0x95/0x180 [464.898] ? __do_sys_newfstat+0xde/0xf0 [464.904] ? __pfx___do_sys_newfstat+0x10/0x10 [464.911] ? trace_irq_enable.constprop.0+0xce/0x110 [464.918] ? syscall_exit_to_user_mode+0xac/0x2a0 [464.925] ? do_syscall_64+0xa1/0x180 [464.931] ? trace_irq_enable.constprop.0+0xce/0x110 [464.939] ? trace_irq_enable.constprop.0+0xce/0x110 [464.946] ? syscall_exit_to_user_mode+0xac/0x2a0 [464.953] ? btrfs_file_llseek+0xb1/0xfb0 [btrfs] [464.960] ? do_syscall_64+0xa1/0x180 [464.966] ? btrfs_file_llseek+0xb1/0xfb0 [btrfs] [464.973] ? trace_irq_enable.constprop.0+0xce/0x110 [464.980] ? syscall_exit_to_user_mode+0xac/0x2a0 [464.987] ? __pfx_btrfs_file_llseek+0x10/0x10 [btrfs] [464.995] ? trace_irq_enable.constprop.0+0xce/0x110 [465.002] ? __pfx_btrfs_file_llseek+0x10/0x10 [btrfs] [465.010] ? do_syscall_64+0xa1/0x180 [465.016] ? lock_release+0x567/0x790 [465.022] ? __pfx_lock_acquire+0x10/0x10 [465.028] ? __pfx_lock_release+0x10/0x10 [465.034] ? trace_irq_enable.constprop.0+0xce/0x110 [465.042] ? syscall_exit_to_user_mode+0xac/0x2a0 [465.049] ? do_syscall_64+0xa1/0x180 [465.055] ? syscall_exit_to_user_mode+0xac/0x2a0 [465.062] ? do_syscall_64+0xa1/0x180 [465.068] ? syscall_exit_to_user_mode+0xac/0x2a0 [465.075] ? do_syscall_64+0xa1/0x180 [465.081] ? clear_bhb_loop+0x25/0x80 [465.087] ? clear_bhb_loop+0x25/0x80 [465.093] ? clear_bhb_loop+0x25/0x80 [465.099] entry_SYSCALL_64_after_hwframe+0x76/0x7e [465.106] RIP: 0033:0x7f093b8ee784 [465.111] RSP: 002b:00007ffc29d31b28 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 [465.122] RAX: ffffffffffffffda RBX: 0000000000006000 RCX: 00007f093b8ee784 [465.131] RDX: 000000000001de00 RSI: 00007f093b6ed200 RDI: 0000000000000003 [465.141] RBP: 000000000001de00 R08: 0000000000006000 R09: 0000000000000000 [465.150] R10: 0000000000023e00 R11: 0000000000000202 R12: 0000000000006000 [465.160] R13: 0000000000023e00 R14: 0000000000023e00 R15: 0000000000000001 [465.170] [465.174] INFO: lockdep is turned off. Reported-by: Shinichiro Kawasaki Fixes: 97713b1a2ced ("btrfs: do not clear page dirty inside extent_write_locked_range()") Reviewed-by: Qu Wenruo Signed-off-by: Naohiro Aota Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index aa7f8148cd0d..c73cd4f89015 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1496,6 +1496,13 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, free_extent_map(em); em = NULL; + /* + * Although the PageDirty bit might be cleared before entering + * this function, subpage dirty bit is not cleared. + * So clear subpage dirty bit here so next time we won't submit + * page for range already written to disk. + */ + btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize); btrfs_set_range_writeback(inode, cur, cur + iosize - 1); if (!PageWriteback(page)) { btrfs_err(inode->root->fs_info, @@ -1503,13 +1510,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, page->index, cur, end); } - /* - * Although the PageDirty bit is cleared before entering this - * function, subpage dirty bit is not cleared. - * So clear subpage dirty bit here so next time we won't submit - * page for range already written to disk. - */ - btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize); submit_extent_page(bio_ctrl, disk_bytenr, page, iosize, cur - page_offset(page)); From df934abb185c71c9f2fa07a5013672d0cbd36560 Mon Sep 17 00:00:00 2001 From: David Thompson Date: Fri, 9 Aug 2024 12:36:12 -0400 Subject: [PATCH 207/562] mlxbf_gige: disable RX filters until RX path initialized A recent change to the driver exposed a bug where the MAC RX filters (unicast MAC, broadcast MAC, and multicast MAC) are configured and enabled before the RX path is fully initialized. The result of this bug is that after the PHY is started packets that match these MAC RX filters start to flow into the RX FIFO. And then, after rx_init() is completed, these packets will go into the driver RX ring as well. If enough packets are received to fill the RX ring (default size is 128 packets) before the call to request_irq() completes, the driver RX function becomes stuck. This bug is intermittent but is most likely to be seen where the oob_net0 interface is connected to a busy network with lots of broadcast and multicast traffic. All the MAC RX filters must be disabled until the RX path is ready, i.e. all initialization is done and all the IRQs are installed. Fixes: f7442a634ac0 ("mlxbf_gige: call request_irq() after NAPI initialized") Reviewed-by: Asmaa Mnebhi Signed-off-by: David Thompson Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240809163612.12852-1-davthompson@nvidia.com Signed-off-by: Paolo Abeni --- .../ethernet/mellanox/mlxbf_gige/mlxbf_gige.h | 8 +++ .../mellanox/mlxbf_gige/mlxbf_gige_main.c | 10 ++++ .../mellanox/mlxbf_gige/mlxbf_gige_regs.h | 2 + .../mellanox/mlxbf_gige/mlxbf_gige_rx.c | 50 ++++++++++++++++--- 4 files changed, 64 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h index bc94e75a7aeb..e7777700ee18 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h @@ -40,6 +40,7 @@ */ #define MLXBF_GIGE_BCAST_MAC_FILTER_IDX 0 #define MLXBF_GIGE_LOCAL_MAC_FILTER_IDX 1 +#define MLXBF_GIGE_MAX_FILTER_IDX 3 /* Define for broadcast MAC literal */ #define BCAST_MAC_ADDR 0xFFFFFFFFFFFF @@ -175,6 +176,13 @@ enum mlxbf_gige_res { int mlxbf_gige_mdio_probe(struct platform_device *pdev, struct mlxbf_gige *priv); void mlxbf_gige_mdio_remove(struct mlxbf_gige *priv); + +void mlxbf_gige_enable_multicast_rx(struct mlxbf_gige *priv); +void mlxbf_gige_disable_multicast_rx(struct mlxbf_gige *priv); +void mlxbf_gige_enable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index); +void mlxbf_gige_disable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index); void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, unsigned int index, u64 dmac); void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv, diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index b157f0f1c5a8..385a56ac7348 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -168,6 +168,10 @@ static int mlxbf_gige_open(struct net_device *netdev) if (err) goto napi_deinit; + mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_BCAST_MAC_FILTER_IDX); + mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_LOCAL_MAC_FILTER_IDX); + mlxbf_gige_enable_multicast_rx(priv); + /* Set bits in INT_EN that we care about */ int_en = MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR | MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS | @@ -379,6 +383,7 @@ static int mlxbf_gige_probe(struct platform_device *pdev) void __iomem *plu_base; void __iomem *base; int addr, phy_irq; + unsigned int i; int err; base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MAC); @@ -423,6 +428,11 @@ static int mlxbf_gige_probe(struct platform_device *pdev) priv->rx_q_entries = MLXBF_GIGE_DEFAULT_RXQ_SZ; priv->tx_q_entries = MLXBF_GIGE_DEFAULT_TXQ_SZ; + for (i = 0; i <= MLXBF_GIGE_MAX_FILTER_IDX; i++) + mlxbf_gige_disable_mac_rx_filter(priv, i); + mlxbf_gige_disable_multicast_rx(priv); + mlxbf_gige_disable_promisc(priv); + /* Write initial MAC address to hardware */ mlxbf_gige_initial_mac(priv); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h index 98a8681c21b9..4d14cb13fd64 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h @@ -62,6 +62,8 @@ #define MLXBF_GIGE_TX_STATUS_DATA_FIFO_FULL BIT(1) #define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_START 0x0520 #define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_END 0x0528 +#define MLXBF_GIGE_RX_MAC_FILTER_GENERAL 0x0530 +#define MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST BIT(1) #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC 0x0540 #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC_EN BIT(0) #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS 0x0548 diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c index 699984358493..eb62620b63c7 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c @@ -11,22 +11,60 @@ #include "mlxbf_gige.h" #include "mlxbf_gige_regs.h" -void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, - unsigned int index, u64 dmac) +void mlxbf_gige_enable_multicast_rx(struct mlxbf_gige *priv) +{ + void __iomem *base = priv->base; + u64 data; + + data = readq(base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); + data |= MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST; + writeq(data, base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); +} + +void mlxbf_gige_disable_multicast_rx(struct mlxbf_gige *priv) +{ + void __iomem *base = priv->base; + u64 data; + + data = readq(base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); + data &= ~MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST; + writeq(data, base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); +} + +void mlxbf_gige_enable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index) { void __iomem *base = priv->base; u64 control; - /* Write destination MAC to specified MAC RX filter */ - writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER + - (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE)); - /* Enable MAC receive filter mask for specified index */ control = readq(base + MLXBF_GIGE_CONTROL); control |= (MLXBF_GIGE_CONTROL_EN_SPECIFIC_MAC << index); writeq(control, base + MLXBF_GIGE_CONTROL); } +void mlxbf_gige_disable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index) +{ + void __iomem *base = priv->base; + u64 control; + + /* Disable MAC receive filter mask for specified index */ + control = readq(base + MLXBF_GIGE_CONTROL); + control &= ~(MLXBF_GIGE_CONTROL_EN_SPECIFIC_MAC << index); + writeq(control, base + MLXBF_GIGE_CONTROL); +} + +void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index, u64 dmac) +{ + void __iomem *base = priv->base; + + /* Write destination MAC to specified MAC RX filter */ + writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER + + (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE)); +} + void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv, unsigned int index, u64 *dmac) { From 15e1c3d65975524c5c792fcd59f7d89f00402261 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Fri, 2 Aug 2024 13:16:30 -0700 Subject: [PATCH 208/562] KVM: x86: Use this_cpu_ptr() instead of per_cpu_ptr(smp_processor_id()) Use this_cpu_ptr() instead of open coding the equivalent in various user return MSR helpers. Signed-off-by: Isaku Yamahata Reviewed-by: Chao Gao Reviewed-by: Yuan Yao [sean: massage changelog] Signed-off-by: Sean Christopherson Reviewed-by: Pankaj Gupta Message-ID: <20240802201630.339306-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ef3d3511e4af..70219e406987 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -427,8 +427,7 @@ static void kvm_user_return_msr_cpu_online(void) int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask) { - unsigned int cpu = smp_processor_id(); - struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu); + struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs); int err; value = (value & mask) | (msrs->values[slot].host & ~mask); @@ -450,8 +449,7 @@ EXPORT_SYMBOL_GPL(kvm_set_user_return_msr); static void drop_user_return_notifiers(void) { - unsigned int cpu = smp_processor_id(); - struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu); + struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs); if (msrs->registered) kvm_on_user_return(&msrs->urn); From 86cfa9a85fb04fa61e7c6b5a8ecf812437cdad78 Mon Sep 17 00:00:00 2001 From: Daniel Yang Date: Wed, 7 Aug 2024 02:01:21 -0700 Subject: [PATCH 209/562] Documentation: dm-crypt.rst warning + error fix While building kernel documention using make htmldocs command, I was getting unexpected indentation error. Single description was given for two module parameters with wrong indentation. So, I corrected the indentation of both parameters and the description. Signed-off-by: Shibu kumar Signed-off-by: Daniel Yang Signed-off-by: Mikulas Patocka Fixes: 0d815e3400e6 ("dm-crypt: limit the size of encryption requests") --- .../admin-guide/device-mapper/dm-crypt.rst | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/Documentation/admin-guide/device-mapper/dm-crypt.rst b/Documentation/admin-guide/device-mapper/dm-crypt.rst index e625830d335e..552c9155165d 100644 --- a/Documentation/admin-guide/device-mapper/dm-crypt.rst +++ b/Documentation/admin-guide/device-mapper/dm-crypt.rst @@ -162,13 +162,14 @@ iv_large_sectors Module parameters:: -max_read_size -max_write_size - Maximum size of read or write requests. When a request larger than this size - is received, dm-crypt will split the request. The splitting improves - concurrency (the split requests could be encrypted in parallel by multiple - cores), but it also causes overhead. The user should tune these parameters to - fit the actual workload. + + max_read_size + max_write_size + Maximum size of read or write requests. When a request larger than this size + is received, dm-crypt will split the request. The splitting improves + concurrency (the split requests could be encrypted in parallel by multiple + cores), but it also causes overhead. The user should tune these parameters to + fit the actual workload. Example scripts From 4b7c3f6d04bd53f2e5b228b6821fb8f5d1ba3071 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 2 Aug 2024 13:29:40 -0700 Subject: [PATCH 210/562] KVM: x86: Make x2APIC ID 100% readonly Ignore the userspace provided x2APIC ID when fixing up APIC state for KVM_SET_LAPIC, i.e. make the x2APIC fully readonly in KVM. Commit a92e2543d6a8 ("KVM: x86: use hardware-compatible format for APIC ID register"), which added the fixup, didn't intend to allow userspace to modify the x2APIC ID. In fact, that commit is when KVM first started treating the x2APIC ID as readonly, apparently to fix some race: static inline u32 kvm_apic_id(struct kvm_lapic *apic) { - return (kvm_lapic_get_reg(apic, APIC_ID) >> 24) & 0xff; + /* To avoid a race between apic_base and following APIC_ID update when + * switching to x2apic_mode, the x2apic mode returns initial x2apic id. + */ + if (apic_x2apic_mode(apic)) + return apic->vcpu->vcpu_id; + + return kvm_lapic_get_reg(apic, APIC_ID) >> 24; } Furthermore, KVM doesn't support delivering interrupts to vCPUs with a modified x2APIC ID, but KVM *does* return the modified value on a guest RDMSR and for KVM_GET_LAPIC. I.e. no remotely sane setup can actually work with a modified x2APIC ID. Making the x2APIC ID fully readonly fixes a WARN in KVM's optimized map calculation, which expects the LDR to align with the x2APIC ID. WARNING: CPU: 2 PID: 958 at arch/x86/kvm/lapic.c:331 kvm_recalculate_apic_map+0x609/0xa00 [kvm] CPU: 2 PID: 958 Comm: recalc_apic_map Not tainted 6.4.0-rc3-vanilla+ #35 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.16.2-1-1 04/01/2014 RIP: 0010:kvm_recalculate_apic_map+0x609/0xa00 [kvm] Call Trace: kvm_apic_set_state+0x1cf/0x5b0 [kvm] kvm_arch_vcpu_ioctl+0x1806/0x2100 [kvm] kvm_vcpu_ioctl+0x663/0x8a0 [kvm] __x64_sys_ioctl+0xb8/0xf0 do_syscall_64+0x56/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7fade8b9dd6f Unfortunately, the WARN can still trigger for other CPUs than the current one by racing against KVM_SET_LAPIC, so remove it completely. Reported-by: Michal Luczaj Closes: https://lore.kernel.org/all/814baa0c-1eaa-4503-129f-059917365e80@rbox.co Reported-by: Haoyu Wu Closes: https://lore.kernel.org/all/20240126161633.62529-1-haoyuwu254@gmail.com Reported-by: syzbot+545f1326f405db4e1c3e@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/000000000000c2a6b9061cbca3c3@google.com Signed-off-by: Sean Christopherson Message-ID: <20240802202941.344889-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/lapic.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4915acdbfcd8..5bb481aefcbc 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -351,10 +351,8 @@ static void kvm_recalculate_logical_map(struct kvm_apic_map *new, * reversing the LDR calculation to get cluster of APICs, i.e. no * additional work is required. */ - if (apic_x2apic_mode(apic)) { - WARN_ON_ONCE(ldr != kvm_apic_calc_x2apic_ldr(kvm_x2apic_id(apic))); + if (apic_x2apic_mode(apic)) return; - } if (WARN_ON_ONCE(!kvm_apic_map_get_logical_dest(new, ldr, &cluster, &mask))) { @@ -2966,18 +2964,28 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s, bool set) { if (apic_x2apic_mode(vcpu->arch.apic)) { + u32 x2apic_id = kvm_x2apic_id(vcpu->arch.apic); u32 *id = (u32 *)(s->regs + APIC_ID); u32 *ldr = (u32 *)(s->regs + APIC_LDR); u64 icr; if (vcpu->kvm->arch.x2apic_format) { - if (*id != vcpu->vcpu_id) + if (*id != x2apic_id) return -EINVAL; } else { + /* + * Ignore the userspace value when setting APIC state. + * KVM's model is that the x2APIC ID is readonly, e.g. + * KVM only supports delivering interrupts to KVM's + * version of the x2APIC ID. However, for backwards + * compatibility, don't reject attempts to set a + * mismatched ID for userspace that hasn't opted into + * x2apic_format. + */ if (set) - *id >>= 24; + *id = x2apic_id; else - *id <<= 24; + *id = x2apic_id << 24; } /* @@ -2986,7 +2994,7 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, * split to ICR+ICR2 in userspace for backwards compatibility. */ if (set) { - *ldr = kvm_apic_calc_x2apic_ldr(*id); + *ldr = kvm_apic_calc_x2apic_ldr(x2apic_id); icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) | (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32; From 238d3d63d1e27c8d9733b48f7b682fc6aba86672 Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Fri, 2 Aug 2024 13:29:41 -0700 Subject: [PATCH 211/562] KVM: selftests: Add a testcase to verify x2APIC is fully readonly Add a test to verify that userspace can't change a vCPU's x2APIC ID by abusing KVM_SET_LAPIC. KVM models the x2APIC ID (and x2APIC LDR) as readonly, and silently ignores userspace attempts to change the x2APIC ID for backwards compatibility. Signed-off-by: Michal Luczaj [sean: write changelog, add to existing test] Signed-off-by: Sean Christopherson Message-ID: <20240802202941.344889-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- .../selftests/kvm/x86_64/xapic_state_test.c | 28 +++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c index 69849acd95b0..618cd2442390 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -184,6 +184,33 @@ static void test_apic_id(void) kvm_vm_free(vm); } +static void test_x2apic_id(void) +{ + struct kvm_lapic_state lapic = {}; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int i; + + vm = vm_create_with_one_vcpu(&vcpu, NULL); + vcpu_set_msr(vcpu, MSR_IA32_APICBASE, MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); + + /* + * Try stuffing a modified x2APIC ID, KVM should ignore the value and + * always return the vCPU's default/readonly x2APIC ID. + */ + for (i = 0; i <= 0xff; i++) { + *(u32 *)(lapic.regs + APIC_ID) = i << 24; + *(u32 *)(lapic.regs + APIC_SPIV) = APIC_SPIV_APIC_ENABLED; + vcpu_ioctl(vcpu, KVM_SET_LAPIC, &lapic); + + vcpu_ioctl(vcpu, KVM_GET_LAPIC, &lapic); + TEST_ASSERT(*((u32 *)&lapic.regs[APIC_ID]) == vcpu->id << 24, + "x2APIC ID should be fully readonly"); + } + + kvm_vm_free(vm); +} + int main(int argc, char *argv[]) { struct xapic_vcpu x = { @@ -211,4 +238,5 @@ int main(int argc, char *argv[]) kvm_vm_free(vm); test_apic_id(); + test_x2apic_id(); } From c9b35a6f4edea698a5bb4dd8029e7104ee0a3726 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Thu, 11 Jul 2024 20:11:30 +0800 Subject: [PATCH 212/562] KVM: eventfd: Use synchronize_srcu_expedited() on shutdown When hot-unplug a device which has many queues, and guest CPU will has huge jitter, and unplugging is very slow. It turns out synchronize_srcu() in irqfd_shutdown() caused the guest jitter and unplugging latency, so replace synchronize_srcu() with synchronize_srcu_expedited(), to accelerate the unplugging, and reduce the guest OS jitter, this accelerates the VM reboot too. Signed-off-by: Li RongQing Message-ID: <20240711121130.38917-1-lirongqing@baidu.com> [Call it just once in irqfd_resampler_shutdown. - Paolo] Signed-off-by: Paolo Bonzini --- virt/kvm/eventfd.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 229570059a1b..992f9beb3e7d 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -97,18 +97,19 @@ irqfd_resampler_shutdown(struct kvm_kernel_irqfd *irqfd) mutex_lock(&kvm->irqfds.resampler_lock); list_del_rcu(&irqfd->resampler_link); - synchronize_srcu(&kvm->irq_srcu); if (list_empty(&resampler->list)) { list_del_rcu(&resampler->link); kvm_unregister_irq_ack_notifier(kvm, &resampler->notifier); /* - * synchronize_srcu(&kvm->irq_srcu) already called + * synchronize_srcu_expedited(&kvm->irq_srcu) already called * in kvm_unregister_irq_ack_notifier(). */ kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, resampler->notifier.gsi, 0, false); kfree(resampler); + } else { + synchronize_srcu_expedited(&kvm->irq_srcu); } mutex_unlock(&kvm->irqfds.resampler_lock); @@ -126,7 +127,7 @@ irqfd_shutdown(struct work_struct *work) u64 cnt; /* Make sure irqfd has been initialized in assign path. */ - synchronize_srcu(&kvm->irq_srcu); + synchronize_srcu_expedited(&kvm->irq_srcu); /* * Synchronize with the wait-queue and unhook ourselves to prevent @@ -384,7 +385,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) } list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list); - synchronize_srcu(&kvm->irq_srcu); + synchronize_srcu_expedited(&kvm->irq_srcu); mutex_unlock(&kvm->irqfds.resampler_lock); } @@ -523,7 +524,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm, mutex_lock(&kvm->irq_lock); hlist_del_init_rcu(&kian->link); mutex_unlock(&kvm->irq_lock); - synchronize_srcu(&kvm->irq_srcu); + synchronize_srcu_expedited(&kvm->irq_srcu); kvm_arch_post_irq_ack_notifier_list_update(kvm); } @@ -608,7 +609,7 @@ kvm_irqfd_release(struct kvm *kvm) /* * Take note of a change in irq routing. - * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards. + * Caller must invoke synchronize_srcu_expedited(&kvm->irq_srcu) afterwards. */ void kvm_irq_routing_update(struct kvm *kvm) { From 11752c013f562a1124088a35bd314aa0e9f0e88f Mon Sep 17 00:00:00 2001 From: Jack Xiao Date: Thu, 18 Jul 2024 16:38:50 +0800 Subject: [PATCH 213/562] drm/amdgpu/mes: fix mes ring buffer overflow wait memory room until enough before writing mes packets to avoid ring buffer overflow. v2: squash in sched_hw_submission fix Fixes: de3246254156 ("drm/amdgpu: cleanup MES11 command submission") Fixes: fffe347e1478 ("drm/amdgpu: cleanup MES12 command submission") Signed-off-by: Jack Xiao Acked-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit 34e087e8920e635c62e2ed6a758b0cd27f836d13) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 2 ++ drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 18 ++++++++++++++---- drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 18 ++++++++++++++---- 3 files changed, 30 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index ad49cecb20b8..e6344a6b0a9f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -212,6 +212,8 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, */ if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ) sched_hw_submission = max(sched_hw_submission, 256); + if (ring->funcs->type == AMDGPU_RING_TYPE_MES) + sched_hw_submission = 8; else if (ring == &adev->sdma.instance[0].page) sched_hw_submission = 256; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index f9343642ae7e..1a5ad5be33bf 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -168,7 +168,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, const char *op_str, *misc_op_str; unsigned long flags; u64 status_gpu_addr; - u32 status_offset; + u32 seq, status_offset; u64 *status_ptr; signed long r; int ret; @@ -196,6 +196,13 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, if (r) goto error_unlock_free; + seq = ++ring->fence_drv.sync_seq; + r = amdgpu_fence_wait_polling(ring, + seq - ring->fence_drv.num_fences_mask, + timeout); + if (r < 1) + goto error_undo; + api_status = (struct MES_API_STATUS *)((char *)pkt + api_status_off); api_status->api_completion_fence_addr = status_gpu_addr; api_status->api_completion_fence_value = 1; @@ -208,8 +215,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, mes_status_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS; mes_status_pkt.api_status.api_completion_fence_addr = ring->fence_drv.gpu_addr; - mes_status_pkt.api_status.api_completion_fence_value = - ++ring->fence_drv.sync_seq; + mes_status_pkt.api_status.api_completion_fence_value = seq; amdgpu_ring_write_multiple(ring, &mes_status_pkt, sizeof(mes_status_pkt) / 4); @@ -229,7 +235,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, dev_dbg(adev->dev, "MES msg=%d was emitted\n", x_pkt->header.opcode); - r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq, timeout); + r = amdgpu_fence_wait_polling(ring, seq, timeout); if (r < 1 || !*status_ptr) { if (misc_op_str) @@ -252,6 +258,10 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, amdgpu_device_wb_free(adev, status_offset); return 0; +error_undo: + dev_err(adev->dev, "MES ring buffer is full.\n"); + amdgpu_ring_undo(ring); + error_unlock_free: spin_unlock_irqrestore(&mes->ring_lock, flags); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index 0713bc3eb263..249e5a66205c 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -154,7 +154,7 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, const char *op_str, *misc_op_str; unsigned long flags; u64 status_gpu_addr; - u32 status_offset; + u32 seq, status_offset; u64 *status_ptr; signed long r; int ret; @@ -182,6 +182,13 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, if (r) goto error_unlock_free; + seq = ++ring->fence_drv.sync_seq; + r = amdgpu_fence_wait_polling(ring, + seq - ring->fence_drv.num_fences_mask, + timeout); + if (r < 1) + goto error_undo; + api_status = (struct MES_API_STATUS *)((char *)pkt + api_status_off); api_status->api_completion_fence_addr = status_gpu_addr; api_status->api_completion_fence_value = 1; @@ -194,8 +201,7 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, mes_status_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS; mes_status_pkt.api_status.api_completion_fence_addr = ring->fence_drv.gpu_addr; - mes_status_pkt.api_status.api_completion_fence_value = - ++ring->fence_drv.sync_seq; + mes_status_pkt.api_status.api_completion_fence_value = seq; amdgpu_ring_write_multiple(ring, &mes_status_pkt, sizeof(mes_status_pkt) / 4); @@ -215,7 +221,7 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, dev_dbg(adev->dev, "MES msg=%d was emitted\n", x_pkt->header.opcode); - r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq, timeout); + r = amdgpu_fence_wait_polling(ring, seq, timeout); if (r < 1 || !*status_ptr) { if (misc_op_str) @@ -238,6 +244,10 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, amdgpu_device_wb_free(adev, status_offset); return 0; +error_undo: + dev_err(adev->dev, "MES ring buffer is full.\n"); + amdgpu_ring_undo(ring); + error_unlock_free: spin_unlock_irqrestore(&mes->ring_lock, flags); From f6098641d3e1e4d4052ff9378857c831f9675f6b Mon Sep 17 00:00:00 2001 From: Hamza Mahfooz Date: Tue, 6 Aug 2024 09:55:55 -0400 Subject: [PATCH 214/562] drm/amd/display: fix s2idle entry for DCN3.5+ To be able to get to the lowest power state when suspending systems with DCN3.5+, we must be in IPS before the display hardware is put into D3cold. So, to ensure that the system always reaches the lowest power state while suspending, force systems that support IPS to enter idle optimizations before entering D3cold. Reviewed-by: Roman Li Signed-off-by: Hamza Mahfooz Signed-off-by: Alex Deucher (cherry picked from commit 237193e21b29d4aa0617ffeea3d6f49e72999708) Cc: stable@vger.kernel.org # 6.10+ --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 7e7929f24ae4..983a977632ff 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2893,6 +2893,9 @@ static int dm_suspend(void *handle) hpd_rx_irq_work_suspend(dm); + if (adev->dm.dc->caps.ips_support) + dc_allow_idle_optimizations(adev->dm.dc, true); + dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D3); dc_dmub_srv_set_power_state(dm->dc->ctx->dmub_srv, DC_ACPI_CM_POWER_STATE_D3); From 0dbb81d44108a2a1004e5b485ef3fca5bc078424 Mon Sep 17 00:00:00 2001 From: Loan Chen Date: Fri, 2 Aug 2024 13:57:40 +0800 Subject: [PATCH 215/562] drm/amd/display: Enable otg synchronization logic for DCN321 [Why] Tiled display cannot synchronize properly after S3. The fix for commit 5f0c74915815 ("drm/amd/display: Fix for otg synchronization logic") is not enable in DCN321, which causes the otg is excluded from synchronization. [How] Enable otg synchronization logic in dcn321. Fixes: 5f0c74915815 ("drm/amd/display: Fix for otg synchronization logic") Cc: Mario Limonciello Cc: Alex Deucher Reviewed-by: Alvin Lee Signed-off-by: Loan Chen Signed-off-by: Tom Chung Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher (cherry picked from commit d6ed53712f583423db61fbb802606759e023bf7b) Cc: stable@vger.kernel.org --- .../gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c index 9a3cc0514a36..8e0588b1cf30 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c @@ -1778,6 +1778,9 @@ static bool dcn321_resource_construct( dc->caps.color.mpc.ogam_rom_caps.hlg = 0; dc->caps.color.mpc.ocsc = 1; + /* Use pipe context based otg sync logic */ + dc->config.use_pipe_ctx_sync_logic = true; + dc->config.dc_mode_clk_limit_support = true; dc->config.enable_windowed_mpo_odm = true; /* read VBIOS LTTPR caps */ From 338567d17627064dba63cf063459605e782f71d2 Mon Sep 17 00:00:00 2001 From: Fangzhi Zuo Date: Mon, 29 Jul 2024 10:23:03 -0400 Subject: [PATCH 216/562] drm/amd/display: Fix MST BW calculation Regression [Why & How] Revert commit 8b2cb32cf0c6 ("drm/amd/display: FEC overhead should be checked once for mst slot nums") Because causes bw calculation regression Cc: mario.limonciello@amd.com Cc: alexander.deucher@amd.com Reported-by: jirislaby@kernel.org Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3495 Closes: https://bugzilla.suse.com/show_bug.cgi?id=1228093 Reviewed-by: Wayne Lin Signed-off-by: Fangzhi Zuo Signed-off-by: Tom Chung Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher (cherry picked from commit 12dbb3ed212fc7655fce421542a5add637f8af7a) Cc: stable@vger.kernel.org --- .../display/amdgpu_dm/amdgpu_dm_mst_types.c | 33 ++++++++++++++----- .../display/amdgpu_dm/amdgpu_dm_mst_types.h | 3 ++ 2 files changed, 27 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 915eb2c08ece..2e9f6da1acdc 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -804,12 +804,25 @@ struct dsc_mst_fairness_params { }; #if defined(CONFIG_DRM_AMD_DC_FP) -static int kbps_to_peak_pbn(int kbps) +static uint16_t get_fec_overhead_multiplier(struct dc_link *dc_link) +{ + u8 link_coding_cap; + uint16_t fec_overhead_multiplier_x1000 = PBN_FEC_OVERHEAD_MULTIPLIER_8B_10B; + + link_coding_cap = dc_link_dp_mst_decide_link_encoding_format(dc_link); + if (link_coding_cap == DP_128b_132b_ENCODING) + fec_overhead_multiplier_x1000 = PBN_FEC_OVERHEAD_MULTIPLIER_128B_132B; + + return fec_overhead_multiplier_x1000; +} + +static int kbps_to_peak_pbn(int kbps, uint16_t fec_overhead_multiplier_x1000) { u64 peak_kbps = kbps; peak_kbps *= 1006; - peak_kbps = div_u64(peak_kbps, 1000); + peak_kbps *= fec_overhead_multiplier_x1000; + peak_kbps = div_u64(peak_kbps, 1000 * 1000); return (int) DIV64_U64_ROUND_UP(peak_kbps * 64, (54 * 8 * 1000)); } @@ -910,11 +923,12 @@ static int increase_dsc_bpp(struct drm_atomic_state *state, int link_timeslots_used; int fair_pbn_alloc; int ret = 0; + uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); for (i = 0; i < count; i++) { if (vars[i + k].dsc_enabled) { initial_slack[i] = - kbps_to_peak_pbn(params[i].bw_range.max_kbps) - vars[i + k].pbn; + kbps_to_peak_pbn(params[i].bw_range.max_kbps, fec_overhead_multiplier_x1000) - vars[i + k].pbn; bpp_increased[i] = false; remaining_to_increase += 1; } else { @@ -1010,6 +1024,7 @@ static int try_disable_dsc(struct drm_atomic_state *state, int next_index; int remaining_to_try = 0; int ret; + uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); for (i = 0; i < count; i++) { if (vars[i + k].dsc_enabled @@ -1039,7 +1054,7 @@ static int try_disable_dsc(struct drm_atomic_state *state, if (next_index == -1) break; - vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps); + vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps, fec_overhead_multiplier_x1000); ret = drm_dp_atomic_find_time_slots(state, params[next_index].port->mgr, params[next_index].port, @@ -1052,8 +1067,7 @@ static int try_disable_dsc(struct drm_atomic_state *state, vars[next_index].dsc_enabled = false; vars[next_index].bpp_x16 = 0; } else { - vars[next_index].pbn = kbps_to_peak_pbn( - params[next_index].bw_range.max_kbps); + vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps, fec_overhead_multiplier_x1000); ret = drm_dp_atomic_find_time_slots(state, params[next_index].port->mgr, params[next_index].port, @@ -1082,6 +1096,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, int count = 0; int i, k, ret; bool debugfs_overwrite = false; + uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); memset(params, 0, sizeof(params)); @@ -1146,7 +1161,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, /* Try no compression */ for (i = 0; i < count; i++) { vars[i + k].aconnector = params[i].aconnector; - vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); + vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps, fec_overhead_multiplier_x1000); vars[i + k].dsc_enabled = false; vars[i + k].bpp_x16 = 0; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, params[i].port, @@ -1165,7 +1180,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, /* Try max compression */ for (i = 0; i < count; i++) { if (params[i].compression_possible && params[i].clock_force_enable != DSC_CLK_FORCE_DISABLE) { - vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps); + vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps, fec_overhead_multiplier_x1000); vars[i + k].dsc_enabled = true; vars[i + k].bpp_x16 = params[i].bw_range.min_target_bpp_x16; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, @@ -1173,7 +1188,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, if (ret < 0) return ret; } else { - vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); + vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps, fec_overhead_multiplier_x1000); vars[i + k].dsc_enabled = false; vars[i + k].bpp_x16 = 0; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h index fa84d34b7373..600d6e221011 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h @@ -46,6 +46,9 @@ #define SYNAPTICS_CASCADED_HUB_ID 0x5A #define IS_SYNAPTICS_CASCADED_PANAMERA(devName, data) ((IS_SYNAPTICS_PANAMERA(devName) && ((int)data[2] == SYNAPTICS_CASCADED_HUB_ID)) ? 1 : 0) +#define PBN_FEC_OVERHEAD_MULTIPLIER_8B_10B 1031 +#define PBN_FEC_OVERHEAD_MULTIPLIER_128B_132B 1000 + enum mst_msg_ready_type { NONE_MSG_RDY_EVENT = 0, DOWN_REP_MSG_RDY_EVENT = 1, From 737222cebecbdbcdde2b69475c52bcb9ecfeb830 Mon Sep 17 00:00:00 2001 From: Melissa Wen Date: Tue, 31 Jan 2023 15:05:46 -0100 Subject: [PATCH 217/562] drm/amd/display: fix cursor offset on rotation 180 [why & how] Cursor gets clipped off in the middle of the screen with hw rotation 180. Fix a miscalculation of cursor offset when it's placed near the edges in the pipe split case. Cursor bugs with hw rotation were reported on AMD issue tracker: https://gitlab.freedesktop.org/drm/amd/-/issues/2247 The issues on rotation 270 was fixed by: https://lore.kernel.org/amd-gfx/20221118125935.4013669-22-Brian.Chang@amd.com/ that partially addressed the rotation 180 too. So, this patch is the final bits for rotation 180. Reported-by: Xaver Hugl Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/2247 Reviewed-by: Harry Wentland Fixes: 9d84c7ef8a87 ("drm/amd/display: Correct cursor position on horizontal mirror") Signed-off-by: Melissa Wen Signed-off-by: Hamza Mahfooz Signed-off-by: Tom Chung Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher (cherry picked from commit 1fd2cf090096af8a25bf85564341cfc21cec659d) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c index ff03b1d98aa7..1b9ac8812f5b 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c @@ -3589,7 +3589,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) (int)hubp->curs_attr.width || pos_cpy.x <= (int)hubp->curs_attr.width + pipe_ctx->plane_state->src_rect.x) { - pos_cpy.x = temp_x + viewport_width; + pos_cpy.x = 2 * viewport_width - temp_x; } } } else { From 56fb276d0244d430496f249335a44ae114dd5f54 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Thu, 1 Aug 2024 16:16:35 -0600 Subject: [PATCH 218/562] drm/amd/display: Adjust cursor position [why & how] When the commit 9d84c7ef8a87 ("drm/amd/display: Correct cursor position on horizontal mirror") was introduced, it used the wrong calculation for the position copy for X. This commit uses the correct calculation for that based on the original patch. Fixes: 9d84c7ef8a87 ("drm/amd/display: Correct cursor position on horizontal mirror") Cc: Mario Limonciello Cc: Alex Deucher Acked-by: Wayne Lin Signed-off-by: Rodrigo Siqueira Signed-off-by: Tom Chung Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher (cherry picked from commit 8f9b23abbae5ffcd64856facd26a86b67195bc2f) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c index 1b9ac8812f5b..14a902ff3b8a 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c @@ -3682,7 +3682,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) (int)hubp->curs_attr.width || pos_cpy.x <= (int)hubp->curs_attr.width + pipe_ctx->plane_state->src_rect.x) { - pos_cpy.x = 2 * viewport_width - temp_x; + pos_cpy.x = temp_x + viewport_width; } } } else { From e414a304f2c5368a84f03ad34d29b89f965a33c9 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 12 Jul 2024 10:00:33 -0400 Subject: [PATCH 219/562] drm/amdgpu/jpeg2: properly set atomics vmid field This needs to be set as well if the IB uses atomics. Reviewed-by: Leo Liu Signed-off-by: Alex Deucher (cherry picked from commit 35c628774e50b3784c59e8ca7973f03bcb067132) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c index 99adf3625657..98aa3ccd0d20 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c @@ -538,11 +538,11 @@ void jpeg_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8))); amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8))); amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); From e6c6bd6253e792cee6c5c065e106e87b9f0d9ae9 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 12 Jul 2024 10:06:05 -0400 Subject: [PATCH 220/562] drm/amdgpu/jpeg4: properly set atomics vmid field This needs to be set as well if the IB uses atomics. Reviewed-by: Leo Liu Signed-off-by: Alex Deucher (cherry picked from commit c6c2e8b6a427d4fecc7c36cffccb908185afcab2) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c index ad524ddc9760..f4662920c653 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c @@ -782,11 +782,11 @@ void jpeg_v4_0_3_dec_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8))); amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JPEG_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8))); amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); From 0573a1e2ea7e35bff08944a40f1adf2bb35cea61 Mon Sep 17 00:00:00 2001 From: Bas Nieuwenhuizen Date: Tue, 6 Aug 2024 22:27:32 +0200 Subject: [PATCH 221/562] drm/amdgpu: Actually check flags for all context ops. Missing validation ... Checked libdrm and it clears all the structs, so we should be safe to just check everything. Signed-off-by: Bas Nieuwenhuizen Signed-off-by: Alex Deucher (cherry picked from commit c6b86421f1f9ddf9d706f2453159813ee39d0cf9) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 5cb33ac99f70..c43d1b6e5d66 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -685,16 +685,24 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data, switch (args->in.op) { case AMDGPU_CTX_OP_ALLOC_CTX: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_alloc(adev, fpriv, filp, priority, &id); args->out.alloc.ctx_id = id; break; case AMDGPU_CTX_OP_FREE_CTX: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_free(fpriv, id); break; case AMDGPU_CTX_OP_QUERY_STATE: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_query(adev, fpriv, id, &args->out); break; case AMDGPU_CTX_OP_QUERY_STATE2: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_query2(adev, fpriv, id, &args->out); break; case AMDGPU_CTX_OP_GET_STABLE_PSTATE: From 278e1865b7a2124ea783b75ea8b3ee0bc2da5d85 Mon Sep 17 00:00:00 2001 From: Jack Xiao Date: Wed, 7 Aug 2024 11:43:45 +0800 Subject: [PATCH 222/562] drm/amdgpu/mes12: update mes_v12_api_def.h Update mes12 api definition. Signed-off-by: Jack Xiao Acked-by: Alex Deucher Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher (cherry picked from commit 2ab5dc59177419d8a49e89585e82ff41524270fc) --- drivers/gpu/drm/amd/include/mes_v12_api_def.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/include/mes_v12_api_def.h b/drivers/gpu/drm/amd/include/mes_v12_api_def.h index 4cf2c9f30b3d..101e2fe962c6 100644 --- a/drivers/gpu/drm/amd/include/mes_v12_api_def.h +++ b/drivers/gpu/drm/amd/include/mes_v12_api_def.h @@ -97,6 +97,7 @@ enum MES_QUEUE_TYPE { MES_QUEUE_TYPE_SDMA, MES_QUEUE_TYPE_MAX, + MES_QUEUE_TYPE_SCHQ = MES_QUEUE_TYPE_MAX, }; struct MES_API_STATUS { @@ -242,8 +243,12 @@ union MESAPI_SET_HW_RESOURCES { uint32_t send_write_data : 1; uint32_t os_tdr_timeout_override : 1; uint32_t use_rs64mem_for_proc_gang_ctx : 1; + uint32_t halt_on_misaligned_access : 1; + uint32_t use_add_queue_unmap_flag_addr : 1; + uint32_t enable_mes_sch_stb_log : 1; + uint32_t limit_single_process : 1; uint32_t unmapped_doorbell_handling: 2; - uint32_t reserved : 15; + uint32_t reserved : 11; }; uint32_t uint32_all; }; From 2029b3d7e1358bcca30f74978543ba35b4bbc43d Mon Sep 17 00:00:00 2001 From: Jack Xiao Date: Wed, 7 Aug 2024 11:53:35 +0800 Subject: [PATCH 223/562] drm/amdgpu/mes: add multiple mes ring instances support Add multiple mes ring instances in mes structure to support multiple mes pipes. Signed-off-by: Jack Xiao Acked-by: Alex Deucher Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher (cherry picked from commit c7d4355648ffa02a1551495b05c71ea6c884d29c) --- drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 4 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 5 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 4 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h | 4 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 2 +- drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 34 ++++++++++++------------ drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 34 ++++++++++++------------ 9 files changed, 47 insertions(+), 44 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 82452606ae6c..f165b9d49e29 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -995,7 +995,7 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg, uint32_t xcc_ if (amdgpu_device_skip_hw_access(adev)) return 0; - if (adev->mes.ring.sched.ready) + if (adev->mes.ring[0].sched.ready) return amdgpu_mes_rreg(adev, reg); BUG_ON(!ring->funcs->emit_rreg); @@ -1065,7 +1065,7 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v, uint3 if (amdgpu_device_skip_hw_access(adev)) return; - if (adev->mes.ring.sched.ready) { + if (adev->mes.ring[0].sched.ready) { amdgpu_mes_wreg(adev, reg, v); return; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index c02659025656..b49b3650fd62 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -589,7 +589,8 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev) ring = adev->rings[i]; vmhub = ring->vm_hub; - if (ring == &adev->mes.ring || + if (ring == &adev->mes.ring[0] || + ring == &adev->mes.ring[1] || ring == &adev->umsch_mm.ring) continue; @@ -761,7 +762,7 @@ void amdgpu_gmc_fw_reg_write_reg_wait(struct amdgpu_device *adev, unsigned long flags; uint32_t seq; - if (adev->mes.ring.sched.ready) { + if (adev->mes.ring[0].sched.ready) { amdgpu_mes_reg_write_reg_wait(adev, reg0, reg1, ref, mask); return; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index dac88d2dd70d..8ef53f48ce15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -135,9 +135,11 @@ int amdgpu_mes_init(struct amdgpu_device *adev) idr_init(&adev->mes.queue_id_idr); ida_init(&adev->mes.doorbell_ida); spin_lock_init(&adev->mes.queue_id_lock); - spin_lock_init(&adev->mes.ring_lock); mutex_init(&adev->mes.mutex_hidden); + for (i = 0; i < AMDGPU_MAX_MES_PIPES; i++) + spin_lock_init(&adev->mes.ring_lock[i]); + adev->mes.total_max_queue = AMDGPU_FENCE_MES_QUEUE_ID_MASK; adev->mes.vmid_mask_mmhub = 0xffffff00; adev->mes.vmid_mask_gfxhub = 0xffffff00; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h index 2d659c612f03..f89e3f61fe46 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h @@ -82,8 +82,8 @@ struct amdgpu_mes { uint64_t default_process_quantum; uint64_t default_gang_quantum; - struct amdgpu_ring ring; - spinlock_t ring_lock; + struct amdgpu_ring ring[AMDGPU_MAX_MES_PIPES]; + spinlock_t ring_lock[AMDGPU_MAX_MES_PIPES]; const struct firmware *fw[AMDGPU_MAX_MES_PIPES]; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index 111c380f929b..b287a82e6177 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -858,7 +858,7 @@ void amdgpu_virt_post_reset(struct amdgpu_device *adev) adev->gfx.is_poweron = false; } - adev->mes.ring.sched.ready = false; + adev->mes.ring[0].sched.ready = false; } bool amdgpu_virt_fw_load_skip_check(struct amdgpu_device *adev, uint32_t ucode_id) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index b88a6fa173b3..2797fd84432b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -231,7 +231,7 @@ static void gmc_v11_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, /* This is necessary for SRIOV as well as for GFXOFF to function * properly under bare metal */ - if ((adev->gfx.kiq[0].ring.sched.ready || adev->mes.ring.sched.ready) && + if ((adev->gfx.kiq[0].ring.sched.ready || adev->mes.ring[0].sched.ready) && (amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev))) { amdgpu_gmc_fw_reg_write_reg_wait(adev, req, ack, inv_req, 1 << vmid, GET_INST(GC, 0)); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c index 26efce9aa410..edcb5351f8cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c @@ -299,7 +299,7 @@ static void gmc_v12_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, /* This is necessary for SRIOV as well as for GFXOFF to function * properly under bare metal */ - if ((adev->gfx.kiq[0].ring.sched.ready || adev->mes.ring.sched.ready) && + if ((adev->gfx.kiq[0].ring.sched.ready || adev->mes.ring[0].sched.ready) && (amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev))) { struct amdgpu_vmhub *hub = &adev->vmhub[vmhub]; const unsigned eng = 17; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 1a5ad5be33bf..44bdfa0b263a 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -162,7 +162,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, union MESAPI__QUERY_MES_STATUS mes_status_pkt; signed long timeout = 3000000; /* 3000 ms */ struct amdgpu_device *adev = mes->adev; - struct amdgpu_ring *ring = &mes->ring; + struct amdgpu_ring *ring = &mes->ring[0]; struct MES_API_STATUS *api_status; union MESAPI__MISC *x_pkt = pkt; const char *op_str, *misc_op_str; @@ -191,7 +191,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, status_ptr = (u64 *)&adev->wb.wb[status_offset]; *status_ptr = 0; - spin_lock_irqsave(&mes->ring_lock, flags); + spin_lock_irqsave(&mes->ring_lock[0], flags); r = amdgpu_ring_alloc(ring, (size + sizeof(mes_status_pkt)) / 4); if (r) goto error_unlock_free; @@ -221,7 +221,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, sizeof(mes_status_pkt) / 4); amdgpu_ring_commit(ring); - spin_unlock_irqrestore(&mes->ring_lock, flags); + spin_unlock_irqrestore(&mes->ring_lock[0], flags); op_str = mes_v11_0_get_op_string(x_pkt); misc_op_str = mes_v11_0_get_misc_op_string(x_pkt); @@ -263,7 +263,7 @@ error_undo: amdgpu_ring_undo(ring); error_unlock_free: - spin_unlock_irqrestore(&mes->ring_lock, flags); + spin_unlock_irqrestore(&mes->ring_lock[0], flags); error_wb_free: amdgpu_device_wb_free(adev, status_offset); @@ -1025,7 +1025,7 @@ static int mes_v11_0_kiq_enable_queue(struct amdgpu_device *adev) return r; } - kiq->pmf->kiq_map_queues(kiq_ring, &adev->mes.ring); + kiq->pmf->kiq_map_queues(kiq_ring, &adev->mes.ring[0]); return amdgpu_ring_test_helper(kiq_ring); } @@ -1039,7 +1039,7 @@ static int mes_v11_0_queue_init(struct amdgpu_device *adev, if (pipe == AMDGPU_MES_KIQ_PIPE) ring = &adev->gfx.kiq[0].ring; else if (pipe == AMDGPU_MES_SCHED_PIPE) - ring = &adev->mes.ring; + ring = &adev->mes.ring[0]; else BUG(); @@ -1081,7 +1081,7 @@ static int mes_v11_0_ring_init(struct amdgpu_device *adev) { struct amdgpu_ring *ring; - ring = &adev->mes.ring; + ring = &adev->mes.ring[0]; ring->funcs = &mes_v11_0_ring_funcs; @@ -1134,7 +1134,7 @@ static int mes_v11_0_mqd_sw_init(struct amdgpu_device *adev, if (pipe == AMDGPU_MES_KIQ_PIPE) ring = &adev->gfx.kiq[0].ring; else if (pipe == AMDGPU_MES_SCHED_PIPE) - ring = &adev->mes.ring; + ring = &adev->mes.ring[0]; else BUG(); @@ -1226,12 +1226,12 @@ static int mes_v11_0_sw_fini(void *handle) &adev->gfx.kiq[0].ring.mqd_gpu_addr, &adev->gfx.kiq[0].ring.mqd_ptr); - amdgpu_bo_free_kernel(&adev->mes.ring.mqd_obj, - &adev->mes.ring.mqd_gpu_addr, - &adev->mes.ring.mqd_ptr); + amdgpu_bo_free_kernel(&adev->mes.ring[0].mqd_obj, + &adev->mes.ring[0].mqd_gpu_addr, + &adev->mes.ring[0].mqd_ptr); amdgpu_ring_fini(&adev->gfx.kiq[0].ring); - amdgpu_ring_fini(&adev->mes.ring); + amdgpu_ring_fini(&adev->mes.ring[0]); if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) { mes_v11_0_free_ucode_buffers(adev, AMDGPU_MES_KIQ_PIPE); @@ -1342,9 +1342,9 @@ failure: static int mes_v11_0_kiq_hw_fini(struct amdgpu_device *adev) { - if (adev->mes.ring.sched.ready) { - mes_v11_0_kiq_dequeue(&adev->mes.ring); - adev->mes.ring.sched.ready = false; + if (adev->mes.ring[0].sched.ready) { + mes_v11_0_kiq_dequeue(&adev->mes.ring[0]); + adev->mes.ring[0].sched.ready = false; } if (amdgpu_sriov_vf(adev)) { @@ -1362,7 +1362,7 @@ static int mes_v11_0_hw_init(void *handle) int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (adev->mes.ring.sched.ready) + if (adev->mes.ring[0].sched.ready) goto out; if (!adev->enable_mes_kiq) { @@ -1407,7 +1407,7 @@ out: * with MES enabled. */ adev->gfx.kiq[0].ring.sched.ready = false; - adev->mes.ring.sched.ready = true; + adev->mes.ring[0].sched.ready = true; return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index 249e5a66205c..515de65d8aa0 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -148,7 +148,7 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, union MESAPI__QUERY_MES_STATUS mes_status_pkt; signed long timeout = 3000000; /* 3000 ms */ struct amdgpu_device *adev = mes->adev; - struct amdgpu_ring *ring = &mes->ring; + struct amdgpu_ring *ring = &mes->ring[0]; struct MES_API_STATUS *api_status; union MESAPI__MISC *x_pkt = pkt; const char *op_str, *misc_op_str; @@ -177,7 +177,7 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, status_ptr = (u64 *)&adev->wb.wb[status_offset]; *status_ptr = 0; - spin_lock_irqsave(&mes->ring_lock, flags); + spin_lock_irqsave(&mes->ring_lock[0], flags); r = amdgpu_ring_alloc(ring, (size + sizeof(mes_status_pkt)) / 4); if (r) goto error_unlock_free; @@ -207,7 +207,7 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, sizeof(mes_status_pkt) / 4); amdgpu_ring_commit(ring); - spin_unlock_irqrestore(&mes->ring_lock, flags); + spin_unlock_irqrestore(&mes->ring_lock[0], flags); op_str = mes_v12_0_get_op_string(x_pkt); misc_op_str = mes_v12_0_get_misc_op_string(x_pkt); @@ -249,7 +249,7 @@ error_undo: amdgpu_ring_undo(ring); error_unlock_free: - spin_unlock_irqrestore(&mes->ring_lock, flags); + spin_unlock_irqrestore(&mes->ring_lock[0], flags); error_wb_free: amdgpu_device_wb_free(adev, status_offset); @@ -1095,7 +1095,7 @@ static int mes_v12_0_kiq_enable_queue(struct amdgpu_device *adev) return r; } - kiq->pmf->kiq_map_queues(kiq_ring, &adev->mes.ring); + kiq->pmf->kiq_map_queues(kiq_ring, &adev->mes.ring[0]); r = amdgpu_ring_test_ring(kiq_ring); if (r) { @@ -1114,7 +1114,7 @@ static int mes_v12_0_queue_init(struct amdgpu_device *adev, if (pipe == AMDGPU_MES_KIQ_PIPE) ring = &adev->gfx.kiq[0].ring; else if (pipe == AMDGPU_MES_SCHED_PIPE) - ring = &adev->mes.ring; + ring = &adev->mes.ring[0]; else BUG(); @@ -1160,7 +1160,7 @@ static int mes_v12_0_ring_init(struct amdgpu_device *adev) { struct amdgpu_ring *ring; - ring = &adev->mes.ring; + ring = &adev->mes.ring[0]; ring->funcs = &mes_v12_0_ring_funcs; @@ -1213,7 +1213,7 @@ static int mes_v12_0_mqd_sw_init(struct amdgpu_device *adev, if (pipe == AMDGPU_MES_KIQ_PIPE) ring = &adev->gfx.kiq[0].ring; else if (pipe == AMDGPU_MES_SCHED_PIPE) - ring = &adev->mes.ring; + ring = &adev->mes.ring[0]; else BUG(); @@ -1302,12 +1302,12 @@ static int mes_v12_0_sw_fini(void *handle) &adev->gfx.kiq[0].ring.mqd_gpu_addr, &adev->gfx.kiq[0].ring.mqd_ptr); - amdgpu_bo_free_kernel(&adev->mes.ring.mqd_obj, - &adev->mes.ring.mqd_gpu_addr, - &adev->mes.ring.mqd_ptr); + amdgpu_bo_free_kernel(&adev->mes.ring[0].mqd_obj, + &adev->mes.ring[0].mqd_gpu_addr, + &adev->mes.ring[0].mqd_ptr); amdgpu_ring_fini(&adev->gfx.kiq[0].ring); - amdgpu_ring_fini(&adev->mes.ring); + amdgpu_ring_fini(&adev->mes.ring[0]); if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) { mes_v12_0_free_ucode_buffers(adev, AMDGPU_MES_KIQ_PIPE); @@ -1351,7 +1351,7 @@ static void mes_v12_0_kiq_dequeue_sched(struct amdgpu_device *adev) soc21_grbm_select(adev, 0, 0, 0, 0); mutex_unlock(&adev->srbm_mutex); - adev->mes.ring.sched.ready = false; + adev->mes.ring[0].sched.ready = false; } static void mes_v12_0_kiq_setting(struct amdgpu_ring *ring) @@ -1415,9 +1415,9 @@ failure: static int mes_v12_0_kiq_hw_fini(struct amdgpu_device *adev) { - if (adev->mes.ring.sched.ready) { + if (adev->mes.ring[0].sched.ready) { mes_v12_0_kiq_dequeue_sched(adev); - adev->mes.ring.sched.ready = false; + adev->mes.ring[0].sched.ready = false; } mes_v12_0_enable(adev, false); @@ -1430,7 +1430,7 @@ static int mes_v12_0_hw_init(void *handle) int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (adev->mes.ring.sched.ready) + if (adev->mes.ring[0].sched.ready) goto out; if (!adev->enable_mes_kiq || adev->enable_uni_mes) { @@ -1482,7 +1482,7 @@ out: * with MES enabled. */ adev->gfx.kiq[0].ring.sched.ready = false; - adev->mes.ring.sched.ready = true; + adev->mes.ring[0].sched.ready = true; return 0; From a13d91bf3c1910212e45a69d04ad40d99878f8da Mon Sep 17 00:00:00 2001 From: Jack Xiao Date: Wed, 7 Aug 2024 13:19:59 +0800 Subject: [PATCH 224/562] drm/amdgpu/mes12: load unified mes fw on pipe0 and pipe1 Enable unified mes firmware to load on pipe0 and pipe1. Signed-off-by: Jack Xiao Acked-by: Alex Deucher Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher (cherry picked from commit e69c2dd7534f3fcabf7bb801db2a7ac71e7e5da6) --- drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 2 +- drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 27 +++---------------------- 2 files changed, 4 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index 8ef53f48ce15..81bed8e8478d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -1501,7 +1501,7 @@ int amdgpu_mes_init_microcode(struct amdgpu_device *adev, int pipe) amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix)); - if (adev->enable_uni_mes && pipe == AMDGPU_MES_SCHED_PIPE) { + if (adev->enable_uni_mes) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_uni_mes.bin", ucode_prefix); } else if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(11, 0, 0) && diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index 515de65d8aa0..28bb72d2cffd 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -744,16 +744,11 @@ static void mes_v12_0_enable(struct amdgpu_device *adev, bool enable) if (enable) { data = RREG32_SOC15(GC, 0, regCP_MES_CNTL); data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE0_RESET, 1); - data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_RESET, - (!adev->enable_uni_mes && adev->enable_mes_kiq) ? 1 : 0); + data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_RESET, 1); WREG32_SOC15(GC, 0, regCP_MES_CNTL, data); mutex_lock(&adev->srbm_mutex); for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) { - if ((!adev->enable_mes_kiq || adev->enable_uni_mes) && - pipe == AMDGPU_MES_KIQ_PIPE) - continue; - soc21_grbm_select(adev, 3, pipe, 0, 0); ucode_addr = adev->mes.uc_start_addr[pipe] >> 2; @@ -767,8 +762,7 @@ static void mes_v12_0_enable(struct amdgpu_device *adev, bool enable) /* unhalt MES and activate pipe0 */ data = REG_SET_FIELD(0, CP_MES_CNTL, MES_PIPE0_ACTIVE, 1); - data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_ACTIVE, - (!adev->enable_uni_mes && adev->enable_mes_kiq) ? 1 : 0); + data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_ACTIVE, 1); WREG32_SOC15(GC, 0, regCP_MES_CNTL, data); if (amdgpu_emu_mode) @@ -784,8 +778,7 @@ static void mes_v12_0_enable(struct amdgpu_device *adev, bool enable) data = REG_SET_FIELD(data, CP_MES_CNTL, MES_INVALIDATE_ICACHE, 1); data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE0_RESET, 1); - data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_RESET, - (!adev->enable_uni_mes && adev->enable_mes_kiq) ? 1 : 0); + data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_RESET, 1); data = REG_SET_FIELD(data, CP_MES_CNTL, MES_HALT, 1); WREG32_SOC15(GC, 0, regCP_MES_CNTL, data); } @@ -800,10 +793,6 @@ static void mes_v12_0_set_ucode_start_addr(struct amdgpu_device *adev) mutex_lock(&adev->srbm_mutex); for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) { - if ((!adev->enable_mes_kiq || adev->enable_uni_mes) && - pipe == AMDGPU_MES_KIQ_PIPE) - continue; - /* me=3, queue=0 */ soc21_grbm_select(adev, 3, pipe, 0, 0); @@ -1525,17 +1514,7 @@ static int mes_v12_0_early_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int pipe, r; - if (adev->enable_uni_mes) { - r = amdgpu_mes_init_microcode(adev, AMDGPU_MES_SCHED_PIPE); - if (!r) - return 0; - - adev->enable_uni_mes = false; - } - for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) { - if (!adev->enable_mes_kiq && pipe == AMDGPU_MES_KIQ_PIPE) - continue; r = amdgpu_mes_init_microcode(adev, pipe); if (r) return r; From 3738a7f0ddb920bde538d3f78a02edbc6ad1307e Mon Sep 17 00:00:00 2001 From: Jack Xiao Date: Wed, 7 Aug 2024 14:15:48 +0800 Subject: [PATCH 225/562] drm/amdgpu/mes12: add mes pipe switch support Add mes pipe switch to let caller choose pipe to submit packet. Signed-off-by: Jack Xiao Acked-by: Alex Deucher Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher (cherry picked from commit b2dee0837a4be63e8d3e00550a9f057644f962c4) --- drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 59 ++++++++++++++------------ 1 file changed, 33 insertions(+), 26 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index 28bb72d2cffd..1213f35e2900 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -142,13 +142,14 @@ static const char *mes_v12_0_get_misc_op_string(union MESAPI__MISC *x_pkt) } static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, - void *pkt, int size, - int api_status_off) + int pipe, void *pkt, int size, + int api_status_off) { union MESAPI__QUERY_MES_STATUS mes_status_pkt; signed long timeout = 3000000; /* 3000 ms */ struct amdgpu_device *adev = mes->adev; - struct amdgpu_ring *ring = &mes->ring[0]; + struct amdgpu_ring *ring = &mes->ring[pipe]; + spinlock_t *ring_lock = &mes->ring_lock[pipe]; struct MES_API_STATUS *api_status; union MESAPI__MISC *x_pkt = pkt; const char *op_str, *misc_op_str; @@ -177,7 +178,7 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, status_ptr = (u64 *)&adev->wb.wb[status_offset]; *status_ptr = 0; - spin_lock_irqsave(&mes->ring_lock[0], flags); + spin_lock_irqsave(ring_lock, flags); r = amdgpu_ring_alloc(ring, (size + sizeof(mes_status_pkt)) / 4); if (r) goto error_unlock_free; @@ -207,32 +208,33 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, sizeof(mes_status_pkt) / 4); amdgpu_ring_commit(ring); - spin_unlock_irqrestore(&mes->ring_lock[0], flags); + spin_unlock_irqrestore(ring_lock, flags); op_str = mes_v12_0_get_op_string(x_pkt); misc_op_str = mes_v12_0_get_misc_op_string(x_pkt); if (misc_op_str) - dev_dbg(adev->dev, "MES msg=%s (%s) was emitted\n", op_str, - misc_op_str); + dev_dbg(adev->dev, "MES(%d) msg=%s (%s) was emitted\n", + pipe, op_str, misc_op_str); else if (op_str) - dev_dbg(adev->dev, "MES msg=%s was emitted\n", op_str); + dev_dbg(adev->dev, "MES(%d) msg=%s was emitted\n", + pipe, op_str); else - dev_dbg(adev->dev, "MES msg=%d was emitted\n", - x_pkt->header.opcode); + dev_dbg(adev->dev, "MES(%d) msg=%d was emitted\n", + pipe, x_pkt->header.opcode); r = amdgpu_fence_wait_polling(ring, seq, timeout); if (r < 1 || !*status_ptr) { if (misc_op_str) - dev_err(adev->dev, "MES failed to respond to msg=%s (%s)\n", - op_str, misc_op_str); + dev_err(adev->dev, "MES(%d) failed to respond to msg=%s (%s)\n", + pipe, op_str, misc_op_str); else if (op_str) - dev_err(adev->dev, "MES failed to respond to msg=%s\n", - op_str); + dev_err(adev->dev, "MES(%d) failed to respond to msg=%s\n", + pipe, op_str); else - dev_err(adev->dev, "MES failed to respond to msg=%d\n", - x_pkt->header.opcode); + dev_err(adev->dev, "MES(%d) failed to respond to msg=%d\n", + pipe, x_pkt->header.opcode); while (halt_if_hws_hang) schedule(); @@ -249,7 +251,7 @@ error_undo: amdgpu_ring_undo(ring); error_unlock_free: - spin_unlock_irqrestore(&mes->ring_lock[0], flags); + spin_unlock_irqrestore(ring_lock, flags); error_wb_free: amdgpu_device_wb_free(adev, status_offset); @@ -321,6 +323,7 @@ static int mes_v12_0_add_hw_queue(struct amdgpu_mes *mes, mes_add_queue_pkt.gds_size = input->queue_size; return mes_v12_0_submit_pkt_and_poll_completion(mes, + AMDGPU_MES_SCHED_PIPE, &mes_add_queue_pkt, sizeof(mes_add_queue_pkt), offsetof(union MESAPI__ADD_QUEUE, api_status)); } @@ -340,6 +343,7 @@ static int mes_v12_0_remove_hw_queue(struct amdgpu_mes *mes, mes_remove_queue_pkt.gang_context_addr = input->gang_context_addr; return mes_v12_0_submit_pkt_and_poll_completion(mes, + AMDGPU_MES_SCHED_PIPE, &mes_remove_queue_pkt, sizeof(mes_remove_queue_pkt), offsetof(union MESAPI__REMOVE_QUEUE, api_status)); } @@ -365,6 +369,7 @@ static int mes_v12_0_map_legacy_queue(struct amdgpu_mes *mes, mes_add_queue_pkt.map_legacy_kq = 1; return mes_v12_0_submit_pkt_and_poll_completion(mes, + AMDGPU_MES_SCHED_PIPE, &mes_add_queue_pkt, sizeof(mes_add_queue_pkt), offsetof(union MESAPI__ADD_QUEUE, api_status)); } @@ -398,6 +403,7 @@ static int mes_v12_0_unmap_legacy_queue(struct amdgpu_mes *mes, } return mes_v12_0_submit_pkt_and_poll_completion(mes, + AMDGPU_MES_SCHED_PIPE, &mes_remove_queue_pkt, sizeof(mes_remove_queue_pkt), offsetof(union MESAPI__REMOVE_QUEUE, api_status)); } @@ -414,7 +420,7 @@ static int mes_v12_0_resume_gang(struct amdgpu_mes *mes, return 0; } -static int mes_v12_0_query_sched_status(struct amdgpu_mes *mes) +static int mes_v12_0_query_sched_status(struct amdgpu_mes *mes, int pipe) { union MESAPI__QUERY_MES_STATUS mes_status_pkt; @@ -424,7 +430,7 @@ static int mes_v12_0_query_sched_status(struct amdgpu_mes *mes) mes_status_pkt.header.opcode = MES_SCH_API_QUERY_SCHEDULER_STATUS; mes_status_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS; - return mes_v12_0_submit_pkt_and_poll_completion(mes, + return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe, &mes_status_pkt, sizeof(mes_status_pkt), offsetof(union MESAPI__QUERY_MES_STATUS, api_status)); } @@ -486,11 +492,12 @@ static int mes_v12_0_misc_op(struct amdgpu_mes *mes, } return mes_v12_0_submit_pkt_and_poll_completion(mes, + AMDGPU_MES_SCHED_PIPE, &misc_pkt, sizeof(misc_pkt), offsetof(union MESAPI__MISC, api_status)); } -static int mes_v12_0_set_hw_resources_1(struct amdgpu_mes *mes) +static int mes_v12_0_set_hw_resources_1(struct amdgpu_mes *mes, int pipe) { union MESAPI_SET_HW_RESOURCES_1 mes_set_hw_res_1_pkt; @@ -501,12 +508,12 @@ static int mes_v12_0_set_hw_resources_1(struct amdgpu_mes *mes) mes_set_hw_res_1_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS; mes_set_hw_res_1_pkt.mes_kiq_unmap_timeout = 100; - return mes_v12_0_submit_pkt_and_poll_completion(mes, + return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe, &mes_set_hw_res_1_pkt, sizeof(mes_set_hw_res_1_pkt), offsetof(union MESAPI_SET_HW_RESOURCES_1, api_status)); } -static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes) +static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe) { int i; struct amdgpu_device *adev = mes->adev; @@ -566,7 +573,7 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes) mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr = mes->event_log_gpu_addr; } - return mes_v12_0_submit_pkt_and_poll_completion(mes, + return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe, &mes_set_hw_res_pkt, sizeof(mes_set_hw_res_pkt), offsetof(union MESAPI_SET_HW_RESOURCES, api_status)); } @@ -1446,19 +1453,19 @@ static int mes_v12_0_hw_init(void *handle) if (r) goto failure; - r = mes_v12_0_set_hw_resources(&adev->mes); + r = mes_v12_0_set_hw_resources(&adev->mes, AMDGPU_MES_SCHED_PIPE); if (r) goto failure; if (adev->enable_uni_mes) - mes_v12_0_set_hw_resources_1(&adev->mes); + mes_v12_0_set_hw_resources_1(&adev->mes, AMDGPU_MES_SCHED_PIPE); mes_v12_0_init_aggregated_doorbell(&adev->mes); /* Enable the MES to handle doorbell ring on unmapped queue */ mes_v12_0_enable_unmapped_doorbell_handling(&adev->mes, true); - r = mes_v12_0_query_sched_status(&adev->mes); + r = mes_v12_0_query_sched_status(&adev->mes, AMDGPU_MES_SCHED_PIPE); if (r) { DRM_ERROR("MES is busy\n"); goto failure; From 1097727d6d0c13eca25321fff46714fc5047d6e8 Mon Sep 17 00:00:00 2001 From: Jack Xiao Date: Wed, 7 Aug 2024 14:44:07 +0800 Subject: [PATCH 226/562] drm/amdgpu/mes12: adjust mes12 sw/hw init for multiple pipes Adjust mes12 sw/hw initiailization for both pipe0 and pipe1 enablement. The two pipes are almost identical pipe. Pipe0 behaves like schq and pipe1 like kiq, pipe0 was mapped by pipe1. Signed-off-by: Jack Xiao Acked-by: Alex Deucher Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher (cherry picked from commit aa539da8aff07ab08def6490e8c9b441439e70ba) --- drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 106 +++++++++++++++---------- 1 file changed, 62 insertions(+), 44 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index 1213f35e2900..d18ec5855193 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -266,6 +266,8 @@ static int convert_to_mes_queue_type(int queue_type) return MES_QUEUE_TYPE_COMPUTE; else if (queue_type == AMDGPU_RING_TYPE_SDMA) return MES_QUEUE_TYPE_SDMA; + else if (queue_type == AMDGPU_RING_TYPE_MES) + return MES_QUEUE_TYPE_SCHQ; else BUG(); return -1; @@ -352,6 +354,7 @@ static int mes_v12_0_map_legacy_queue(struct amdgpu_mes *mes, struct mes_map_legacy_queue_input *input) { union MESAPI__ADD_QUEUE mes_add_queue_pkt; + int pipe; memset(&mes_add_queue_pkt, 0, sizeof(mes_add_queue_pkt)); @@ -368,8 +371,12 @@ static int mes_v12_0_map_legacy_queue(struct amdgpu_mes *mes, convert_to_mes_queue_type(input->queue_type); mes_add_queue_pkt.map_legacy_kq = 1; - return mes_v12_0_submit_pkt_and_poll_completion(mes, - AMDGPU_MES_SCHED_PIPE, + if (mes->adev->enable_uni_mes) + pipe = AMDGPU_MES_KIQ_PIPE; + else + pipe = AMDGPU_MES_SCHED_PIPE; + + return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe, &mes_add_queue_pkt, sizeof(mes_add_queue_pkt), offsetof(union MESAPI__ADD_QUEUE, api_status)); } @@ -378,6 +385,7 @@ static int mes_v12_0_unmap_legacy_queue(struct amdgpu_mes *mes, struct mes_unmap_legacy_queue_input *input) { union MESAPI__REMOVE_QUEUE mes_remove_queue_pkt; + int pipe; memset(&mes_remove_queue_pkt, 0, sizeof(mes_remove_queue_pkt)); @@ -402,8 +410,12 @@ static int mes_v12_0_unmap_legacy_queue(struct amdgpu_mes *mes, convert_to_mes_queue_type(input->queue_type); } - return mes_v12_0_submit_pkt_and_poll_completion(mes, - AMDGPU_MES_SCHED_PIPE, + if (mes->adev->enable_uni_mes) + pipe = AMDGPU_MES_KIQ_PIPE; + else + pipe = AMDGPU_MES_SCHED_PIPE; + + return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe, &mes_remove_queue_pkt, sizeof(mes_remove_queue_pkt), offsetof(union MESAPI__REMOVE_QUEUE, api_status)); } @@ -439,6 +451,7 @@ static int mes_v12_0_misc_op(struct amdgpu_mes *mes, struct mes_misc_op_input *input) { union MESAPI__MISC misc_pkt; + int pipe; memset(&misc_pkt, 0, sizeof(misc_pkt)); @@ -491,8 +504,12 @@ static int mes_v12_0_misc_op(struct amdgpu_mes *mes, return -EINVAL; } - return mes_v12_0_submit_pkt_and_poll_completion(mes, - AMDGPU_MES_SCHED_PIPE, + if (mes->adev->enable_uni_mes) + pipe = AMDGPU_MES_KIQ_PIPE; + else + pipe = AMDGPU_MES_SCHED_PIPE; + + return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe, &misc_pkt, sizeof(misc_pkt), offsetof(union MESAPI__MISC, api_status)); } @@ -1107,14 +1124,12 @@ static int mes_v12_0_queue_init(struct amdgpu_device *adev, struct amdgpu_ring *ring; int r; - if (pipe == AMDGPU_MES_KIQ_PIPE) + if (!adev->enable_uni_mes && pipe == AMDGPU_MES_KIQ_PIPE) ring = &adev->gfx.kiq[0].ring; - else if (pipe == AMDGPU_MES_SCHED_PIPE) - ring = &adev->mes.ring[0]; else - BUG(); + ring = &adev->mes.ring[pipe]; - if ((pipe == AMDGPU_MES_SCHED_PIPE) && + if ((adev->enable_uni_mes || pipe == AMDGPU_MES_SCHED_PIPE) && (amdgpu_in_reset(adev) || adev->in_suspend)) { *(ring->wptr_cpu_addr) = 0; *(ring->rptr_cpu_addr) = 0; @@ -1126,13 +1141,12 @@ static int mes_v12_0_queue_init(struct amdgpu_device *adev, return r; if (pipe == AMDGPU_MES_SCHED_PIPE) { - if (adev->enable_uni_mes) { - mes_v12_0_queue_init_register(ring); - } else { + if (adev->enable_uni_mes) + r = amdgpu_mes_map_legacy_queue(adev, ring); + else r = mes_v12_0_kiq_enable_queue(adev); - if (r) - return r; - } + if (r) + return r; } else { mes_v12_0_queue_init_register(ring); } @@ -1152,25 +1166,29 @@ static int mes_v12_0_queue_init(struct amdgpu_device *adev, return 0; } -static int mes_v12_0_ring_init(struct amdgpu_device *adev) +static int mes_v12_0_ring_init(struct amdgpu_device *adev, int pipe) { struct amdgpu_ring *ring; - ring = &adev->mes.ring[0]; + ring = &adev->mes.ring[pipe]; ring->funcs = &mes_v12_0_ring_funcs; ring->me = 3; - ring->pipe = 0; + ring->pipe = pipe; ring->queue = 0; ring->ring_obj = NULL; ring->use_doorbell = true; - ring->doorbell_index = adev->doorbell_index.mes_ring0 << 1; - ring->eop_gpu_addr = adev->mes.eop_gpu_addr[AMDGPU_MES_SCHED_PIPE]; + ring->eop_gpu_addr = adev->mes.eop_gpu_addr[pipe]; ring->no_scheduler = true; sprintf(ring->name, "mes_%d.%d.%d", ring->me, ring->pipe, ring->queue); + if (pipe == AMDGPU_MES_SCHED_PIPE) + ring->doorbell_index = adev->doorbell_index.mes_ring0 << 1; + else + ring->doorbell_index = adev->doorbell_index.mes_ring1 << 1; + return amdgpu_ring_init(adev, ring, 1024, NULL, 0, AMDGPU_RING_PRIO_DEFAULT, NULL); } @@ -1184,7 +1202,7 @@ static int mes_v12_0_kiq_ring_init(struct amdgpu_device *adev) ring = &adev->gfx.kiq[0].ring; ring->me = 3; - ring->pipe = adev->enable_uni_mes ? 0 : 1; + ring->pipe = 1; ring->queue = 0; ring->adev = NULL; @@ -1206,12 +1224,10 @@ static int mes_v12_0_mqd_sw_init(struct amdgpu_device *adev, int r, mqd_size = sizeof(struct v12_compute_mqd); struct amdgpu_ring *ring; - if (pipe == AMDGPU_MES_KIQ_PIPE) + if (!adev->enable_uni_mes && pipe == AMDGPU_MES_KIQ_PIPE) ring = &adev->gfx.kiq[0].ring; - else if (pipe == AMDGPU_MES_SCHED_PIPE) - ring = &adev->mes.ring[0]; else - BUG(); + ring = &adev->mes.ring[pipe]; if (ring->mqd_obj) return 0; @@ -1252,9 +1268,6 @@ static int mes_v12_0_sw_init(void *handle) return r; for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) { - if (!adev->enable_mes_kiq && pipe == AMDGPU_MES_KIQ_PIPE) - continue; - r = mes_v12_0_allocate_eop_buf(adev, pipe); if (r) return r; @@ -1262,18 +1275,15 @@ static int mes_v12_0_sw_init(void *handle) r = mes_v12_0_mqd_sw_init(adev, pipe); if (r) return r; - } - if (adev->enable_mes_kiq) { - r = mes_v12_0_kiq_ring_init(adev); + if (!adev->enable_uni_mes && pipe == AMDGPU_MES_KIQ_PIPE) + r = mes_v12_0_kiq_ring_init(adev); + else + r = mes_v12_0_ring_init(adev, pipe); if (r) return r; } - r = mes_v12_0_ring_init(adev); - if (r) - return r; - return 0; } @@ -1368,10 +1378,10 @@ static int mes_v12_0_kiq_hw_init(struct amdgpu_device *adev) { int r = 0; - mes_v12_0_kiq_setting(&adev->gfx.kiq[0].ring); - if (adev->enable_uni_mes) - return mes_v12_0_hw_init(adev); + mes_v12_0_kiq_setting(&adev->mes.ring[AMDGPU_MES_KIQ_PIPE]); + else + mes_v12_0_kiq_setting(&adev->gfx.kiq[0].ring); if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) { @@ -1398,6 +1408,14 @@ static int mes_v12_0_kiq_hw_init(struct amdgpu_device *adev) if (r) goto failure; + if (adev->enable_uni_mes) { + r = mes_v12_0_set_hw_resources(&adev->mes, AMDGPU_MES_KIQ_PIPE); + if (r) + goto failure; + + mes_v12_0_set_hw_resources_1(&adev->mes, AMDGPU_MES_KIQ_PIPE); + } + r = mes_v12_0_hw_init(adev); if (r) goto failure; @@ -1429,7 +1447,7 @@ static int mes_v12_0_hw_init(void *handle) if (adev->mes.ring[0].sched.ready) goto out; - if (!adev->enable_mes_kiq || adev->enable_uni_mes) { + if (!adev->enable_mes_kiq) { if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) { r = mes_v12_0_load_microcode(adev, AMDGPU_MES_SCHED_PIPE, true); @@ -1449,6 +1467,9 @@ static int mes_v12_0_hw_init(void *handle) mes_v12_0_enable(adev, true); } + /* Enable the MES to handle doorbell ring on unmapped queue */ + mes_v12_0_enable_unmapped_doorbell_handling(&adev->mes, true); + r = mes_v12_0_queue_init(adev, AMDGPU_MES_SCHED_PIPE); if (r) goto failure; @@ -1462,9 +1483,6 @@ static int mes_v12_0_hw_init(void *handle) mes_v12_0_init_aggregated_doorbell(&adev->mes); - /* Enable the MES to handle doorbell ring on unmapped queue */ - mes_v12_0_enable_unmapped_doorbell_handling(&adev->mes, true); - r = mes_v12_0_query_sched_status(&adev->mes, AMDGPU_MES_SCHED_PIPE); if (r) { DRM_ERROR("MES is busy\n"); From 7254027e1e6edbff54f5930a5f13f14ac6f1694c Mon Sep 17 00:00:00 2001 From: Jack Xiao Date: Wed, 7 Aug 2024 14:49:30 +0800 Subject: [PATCH 227/562] drm/amdgpu/mes12: configure two pipes hardware resources Configure two pipes with different hardware resources. Signed-off-by: Jack Xiao Acked-by: Alex Deucher Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher (cherry picked from commit ea5d6db17a8e3635ad91e8c53faa1fdc9570fbbb) --- drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 77 +++++++++++++++---------- drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h | 12 ++-- drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 7 +-- drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 49 ++++++++-------- 4 files changed, 81 insertions(+), 64 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index 81bed8e8478d..1cb1ec7beefe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -165,36 +165,38 @@ int amdgpu_mes_init(struct amdgpu_device *adev) adev->mes.sdma_hqd_mask[i] = 0xfc; } - r = amdgpu_device_wb_get(adev, &adev->mes.sch_ctx_offs); - if (r) { - dev_err(adev->dev, - "(%d) ring trail_fence_offs wb alloc failed\n", r); - goto error_ids; - } - adev->mes.sch_ctx_gpu_addr = - adev->wb.gpu_addr + (adev->mes.sch_ctx_offs * 4); - adev->mes.sch_ctx_ptr = - (uint64_t *)&adev->wb.wb[adev->mes.sch_ctx_offs]; + for (i = 0; i < AMDGPU_MAX_MES_PIPES; i++) { + r = amdgpu_device_wb_get(adev, &adev->mes.sch_ctx_offs[i]); + if (r) { + dev_err(adev->dev, + "(%d) ring trail_fence_offs wb alloc failed\n", + r); + goto error; + } + adev->mes.sch_ctx_gpu_addr[i] = + adev->wb.gpu_addr + (adev->mes.sch_ctx_offs[i] * 4); + adev->mes.sch_ctx_ptr[i] = + (uint64_t *)&adev->wb.wb[adev->mes.sch_ctx_offs[i]]; - r = amdgpu_device_wb_get(adev, &adev->mes.query_status_fence_offs); - if (r) { - amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs); - dev_err(adev->dev, - "(%d) query_status_fence_offs wb alloc failed\n", r); - goto error_ids; + r = amdgpu_device_wb_get(adev, + &adev->mes.query_status_fence_offs[i]); + if (r) { + dev_err(adev->dev, + "(%d) query_status_fence_offs wb alloc failed\n", + r); + goto error; + } + adev->mes.query_status_fence_gpu_addr[i] = adev->wb.gpu_addr + + (adev->mes.query_status_fence_offs[i] * 4); + adev->mes.query_status_fence_ptr[i] = + (uint64_t *)&adev->wb.wb[adev->mes.query_status_fence_offs[i]]; } - adev->mes.query_status_fence_gpu_addr = - adev->wb.gpu_addr + (adev->mes.query_status_fence_offs * 4); - adev->mes.query_status_fence_ptr = - (uint64_t *)&adev->wb.wb[adev->mes.query_status_fence_offs]; r = amdgpu_device_wb_get(adev, &adev->mes.read_val_offs); if (r) { - amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs); - amdgpu_device_wb_free(adev, adev->mes.query_status_fence_offs); dev_err(adev->dev, "(%d) read_val_offs alloc failed\n", r); - goto error_ids; + goto error; } adev->mes.read_val_gpu_addr = adev->wb.gpu_addr + (adev->mes.read_val_offs * 4); @@ -214,10 +216,16 @@ int amdgpu_mes_init(struct amdgpu_device *adev) error_doorbell: amdgpu_mes_doorbell_free(adev); error: - amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs); - amdgpu_device_wb_free(adev, adev->mes.query_status_fence_offs); - amdgpu_device_wb_free(adev, adev->mes.read_val_offs); -error_ids: + for (i = 0; i < AMDGPU_MAX_MES_PIPES; i++) { + if (adev->mes.sch_ctx_ptr[i]) + amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs[i]); + if (adev->mes.query_status_fence_ptr[i]) + amdgpu_device_wb_free(adev, + adev->mes.query_status_fence_offs[i]); + } + if (adev->mes.read_val_ptr) + amdgpu_device_wb_free(adev, adev->mes.read_val_offs); + idr_destroy(&adev->mes.pasid_idr); idr_destroy(&adev->mes.gang_id_idr); idr_destroy(&adev->mes.queue_id_idr); @@ -228,13 +236,22 @@ error_ids: void amdgpu_mes_fini(struct amdgpu_device *adev) { + int i; + amdgpu_bo_free_kernel(&adev->mes.event_log_gpu_obj, &adev->mes.event_log_gpu_addr, &adev->mes.event_log_cpu_addr); - amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs); - amdgpu_device_wb_free(adev, adev->mes.query_status_fence_offs); - amdgpu_device_wb_free(adev, adev->mes.read_val_offs); + for (i = 0; i < AMDGPU_MAX_MES_PIPES; i++) { + if (adev->mes.sch_ctx_ptr[i]) + amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs[i]); + if (adev->mes.query_status_fence_ptr[i]) + amdgpu_device_wb_free(adev, + adev->mes.query_status_fence_offs[i]); + } + if (adev->mes.read_val_ptr) + amdgpu_device_wb_free(adev, adev->mes.read_val_offs); + amdgpu_mes_doorbell_free(adev); idr_destroy(&adev->mes.pasid_idr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h index f89e3f61fe46..0bc837dab578 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h @@ -112,12 +112,12 @@ struct amdgpu_mes { uint32_t gfx_hqd_mask[AMDGPU_MES_MAX_GFX_PIPES]; uint32_t sdma_hqd_mask[AMDGPU_MES_MAX_SDMA_PIPES]; uint32_t aggregated_doorbells[AMDGPU_MES_PRIORITY_NUM_LEVELS]; - uint32_t sch_ctx_offs; - uint64_t sch_ctx_gpu_addr; - uint64_t *sch_ctx_ptr; - uint32_t query_status_fence_offs; - uint64_t query_status_fence_gpu_addr; - uint64_t *query_status_fence_ptr; + uint32_t sch_ctx_offs[AMDGPU_MAX_MES_PIPES]; + uint64_t sch_ctx_gpu_addr[AMDGPU_MAX_MES_PIPES]; + uint64_t *sch_ctx_ptr[AMDGPU_MAX_MES_PIPES]; + uint32_t query_status_fence_offs[AMDGPU_MAX_MES_PIPES]; + uint64_t query_status_fence_gpu_addr[AMDGPU_MAX_MES_PIPES]; + uint64_t *query_status_fence_ptr[AMDGPU_MAX_MES_PIPES]; uint32_t read_val_offs; uint64_t read_val_gpu_addr; uint32_t *read_val_ptr; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 44bdfa0b263a..2ea8223eb969 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -522,9 +522,9 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes) mes_set_hw_res_pkt.vmid_mask_gfxhub = mes->vmid_mask_gfxhub; mes_set_hw_res_pkt.gds_size = adev->gds.gds_size; mes_set_hw_res_pkt.paging_vmid = 0; - mes_set_hw_res_pkt.g_sch_ctx_gpu_mc_ptr = mes->sch_ctx_gpu_addr; + mes_set_hw_res_pkt.g_sch_ctx_gpu_mc_ptr = mes->sch_ctx_gpu_addr[0]; mes_set_hw_res_pkt.query_status_fence_gpu_mc_ptr = - mes->query_status_fence_gpu_addr; + mes->query_status_fence_gpu_addr[0]; for (i = 0; i < MAX_COMPUTE_PIPES; i++) mes_set_hw_res_pkt.compute_hqd_mask[i] = @@ -1210,9 +1210,6 @@ static int mes_v11_0_sw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int pipe; - amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs); - amdgpu_device_wb_free(adev, adev->mes.query_status_fence_offs); - for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) { kfree(adev->mes.mqd_backup[pipe]); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index d18ec5855193..ed77d70441cf 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -542,27 +542,33 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe) mes_set_hw_res_pkt.header.opcode = MES_SCH_API_SET_HW_RSRC; mes_set_hw_res_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS; - mes_set_hw_res_pkt.vmid_mask_mmhub = mes->vmid_mask_mmhub; - mes_set_hw_res_pkt.vmid_mask_gfxhub = mes->vmid_mask_gfxhub; - mes_set_hw_res_pkt.gds_size = adev->gds.gds_size; - mes_set_hw_res_pkt.paging_vmid = 0; - mes_set_hw_res_pkt.g_sch_ctx_gpu_mc_ptr = mes->sch_ctx_gpu_addr; + if (pipe == AMDGPU_MES_SCHED_PIPE) { + mes_set_hw_res_pkt.vmid_mask_mmhub = mes->vmid_mask_mmhub; + mes_set_hw_res_pkt.vmid_mask_gfxhub = mes->vmid_mask_gfxhub; + mes_set_hw_res_pkt.gds_size = adev->gds.gds_size; + mes_set_hw_res_pkt.paging_vmid = 0; + + for (i = 0; i < MAX_COMPUTE_PIPES; i++) + mes_set_hw_res_pkt.compute_hqd_mask[i] = + mes->compute_hqd_mask[i]; + + for (i = 0; i < MAX_GFX_PIPES; i++) + mes_set_hw_res_pkt.gfx_hqd_mask[i] = + mes->gfx_hqd_mask[i]; + + for (i = 0; i < MAX_SDMA_PIPES; i++) + mes_set_hw_res_pkt.sdma_hqd_mask[i] = + mes->sdma_hqd_mask[i]; + + for (i = 0; i < AMD_PRIORITY_NUM_LEVELS; i++) + mes_set_hw_res_pkt.aggregated_doorbells[i] = + mes->aggregated_doorbells[i]; + } + + mes_set_hw_res_pkt.g_sch_ctx_gpu_mc_ptr = + mes->sch_ctx_gpu_addr[pipe]; mes_set_hw_res_pkt.query_status_fence_gpu_mc_ptr = - mes->query_status_fence_gpu_addr; - - for (i = 0; i < MAX_COMPUTE_PIPES; i++) - mes_set_hw_res_pkt.compute_hqd_mask[i] = - mes->compute_hqd_mask[i]; - - for (i = 0; i < MAX_GFX_PIPES; i++) - mes_set_hw_res_pkt.gfx_hqd_mask[i] = mes->gfx_hqd_mask[i]; - - for (i = 0; i < MAX_SDMA_PIPES; i++) - mes_set_hw_res_pkt.sdma_hqd_mask[i] = mes->sdma_hqd_mask[i]; - - for (i = 0; i < AMD_PRIORITY_NUM_LEVELS; i++) - mes_set_hw_res_pkt.aggregated_doorbells[i] = - mes->aggregated_doorbells[i]; + mes->query_status_fence_gpu_addr[pipe]; for (i = 0; i < 5; i++) { mes_set_hw_res_pkt.gc_base[i] = adev->reg_offset[GC_HWIP][0][i]; @@ -1292,9 +1298,6 @@ static int mes_v12_0_sw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int pipe; - amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs); - amdgpu_device_wb_free(adev, adev->mes.query_status_fence_offs); - for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) { kfree(adev->mes.mqd_backup[pipe]); From af401543df510a73f7beb13f80cf4c541be94786 Mon Sep 17 00:00:00 2001 From: Jack Xiao Date: Wed, 7 Aug 2024 15:23:16 +0800 Subject: [PATCH 228/562] drm/amdgpu/mes12: sw/hw fini for unified mes Free memory for two pipes and unmap pipe0 via pipe1. Signed-off-by: Jack Xiao Acked-by: Alex Deucher Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher (cherry picked from commit 98cae695a8ae0e4291b1fa7feef9b54fabefe885) --- drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 31 +++++++++++++++++--------- 1 file changed, 20 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index ed77d70441cf..e39a58d262c9 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -1305,18 +1305,21 @@ static int mes_v12_0_sw_fini(void *handle) &adev->mes.eop_gpu_addr[pipe], NULL); amdgpu_ucode_release(&adev->mes.fw[pipe]); + + if (adev->enable_uni_mes || pipe == AMDGPU_MES_SCHED_PIPE) { + amdgpu_bo_free_kernel(&adev->mes.ring[pipe].mqd_obj, + &adev->mes.ring[pipe].mqd_gpu_addr, + &adev->mes.ring[pipe].mqd_ptr); + amdgpu_ring_fini(&adev->mes.ring[pipe]); + } } - amdgpu_bo_free_kernel(&adev->gfx.kiq[0].ring.mqd_obj, - &adev->gfx.kiq[0].ring.mqd_gpu_addr, - &adev->gfx.kiq[0].ring.mqd_ptr); - - amdgpu_bo_free_kernel(&adev->mes.ring[0].mqd_obj, - &adev->mes.ring[0].mqd_gpu_addr, - &adev->mes.ring[0].mqd_ptr); - - amdgpu_ring_fini(&adev->gfx.kiq[0].ring); - amdgpu_ring_fini(&adev->mes.ring[0]); + if (!adev->enable_uni_mes) { + amdgpu_bo_free_kernel(&adev->gfx.kiq[0].ring.mqd_obj, + &adev->gfx.kiq[0].ring.mqd_gpu_addr, + &adev->gfx.kiq[0].ring.mqd_ptr); + amdgpu_ring_fini(&adev->gfx.kiq[0].ring); + } if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) { mes_v12_0_free_ucode_buffers(adev, AMDGPU_MES_KIQ_PIPE); @@ -1433,7 +1436,13 @@ failure: static int mes_v12_0_kiq_hw_fini(struct amdgpu_device *adev) { if (adev->mes.ring[0].sched.ready) { - mes_v12_0_kiq_dequeue_sched(adev); + if (adev->enable_uni_mes) + amdgpu_mes_unmap_legacy_queue(adev, + &adev->mes.ring[AMDGPU_MES_SCHED_PIPE], + RESET_QUEUES, 0, 0); + else + mes_v12_0_kiq_dequeue_sched(adev); + adev->mes.ring[0].sched.ready = false; } From 4246b1077ffcc37926868581bb818fdb49d0d065 Mon Sep 17 00:00:00 2001 From: Jack Xiao Date: Wed, 7 Aug 2024 12:03:11 +0800 Subject: [PATCH 229/562] drm/amdgpu/mes12: fix suspend issue Use mes pipe to unmap kcq and kgq. Signed-off-by: Jack Xiao Acked-by: Alex Deucher Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher (cherry picked from commit f7fb9d677faf0460131bc2af15afd766d48a1f47) --- drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 22 ++++++++++++++++++++ drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 27 +------------------------ 2 files changed, 23 insertions(+), 26 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index f165b9d49e29..c770cb201e64 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -509,6 +509,16 @@ int amdgpu_gfx_disable_kcq(struct amdgpu_device *adev, int xcc_id) int i, r = 0; int j; + if (adev->enable_mes) { + for (i = 0; i < adev->gfx.num_compute_rings; i++) { + j = i + xcc_id * adev->gfx.num_compute_rings; + amdgpu_mes_unmap_legacy_queue(adev, + &adev->gfx.compute_ring[j], + RESET_QUEUES, 0, 0); + } + return 0; + } + if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues) return -EINVAL; @@ -551,6 +561,18 @@ int amdgpu_gfx_disable_kgq(struct amdgpu_device *adev, int xcc_id) int i, r = 0; int j; + if (adev->enable_mes) { + if (amdgpu_gfx_is_master_xcc(adev, xcc_id)) { + for (i = 0; i < adev->gfx.num_gfx_rings; i++) { + j = i + xcc_id * adev->gfx.num_gfx_rings; + amdgpu_mes_unmap_legacy_queue(adev, + &adev->gfx.gfx_ring[j], + PREEMPT_QUEUES, 0, 0); + } + } + return 0; + } + if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index 506fa8003388..2c611b8577a7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -3546,33 +3546,9 @@ static int gfx_v12_0_hw_init(void *handle) return r; } -static int gfx_v12_0_kiq_disable_kgq(struct amdgpu_device *adev) -{ - struct amdgpu_kiq *kiq = &adev->gfx.kiq[0]; - struct amdgpu_ring *kiq_ring = &kiq->ring; - int i, r = 0; - - if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues) - return -EINVAL; - - if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size * - adev->gfx.num_gfx_rings)) - return -ENOMEM; - - for (i = 0; i < adev->gfx.num_gfx_rings; i++) - kiq->pmf->kiq_unmap_queues(kiq_ring, &adev->gfx.gfx_ring[i], - PREEMPT_QUEUES, 0, 0); - - if (adev->gfx.kiq[0].ring.sched.ready) - r = amdgpu_ring_test_helper(kiq_ring); - - return r; -} - static int gfx_v12_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - int r; uint32_t tmp; amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0); @@ -3580,8 +3556,7 @@ static int gfx_v12_0_hw_fini(void *handle) if (!adev->no_hw_access) { if (amdgpu_async_gfx_ring) { - r = gfx_v12_0_kiq_disable_kgq(adev); - if (r) + if (amdgpu_gfx_disable_kgq(adev, 0)) DRM_ERROR("KGQ disable failed\n"); } From 470516c2925493594a690bc4d05b1f4471d9f996 Mon Sep 17 00:00:00 2001 From: "David (Ming Qiang) Wu" Date: Thu, 8 Aug 2024 12:19:50 -0400 Subject: [PATCH 230/562] drm/amd/amdgpu: command submission parser for JPEG Add JPEG IB command parser to ensure registers in the command are within the JPEG IP block. Reviewed-by: Alex Deucher Signed-off-by: David (Ming Qiang) Wu Signed-off-by: Alex Deucher (cherry picked from commit a7f670d5d8e77b092404ca8a35bb0f8f89ed3117) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 3 ++ drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c | 61 +++++++++++++++++++++++- drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h | 7 ++- drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c | 1 + drivers/gpu/drm/amd/amdgpu/soc15d.h | 6 +++ 5 files changed, 76 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 9aa952f258cf..6dfdff58bffd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1057,6 +1057,9 @@ static int amdgpu_cs_patch_ibs(struct amdgpu_cs_parser *p, r = amdgpu_ring_parse_cs(ring, p, job, ib); if (r) return r; + + if (ib->sa_bo) + ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo); } else { ib->ptr = (uint32_t *)kptr; r = amdgpu_ring_patch_cs_in_place(ring, p, job, ib); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c index f4662920c653..6ae5a784e187 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c @@ -23,6 +23,7 @@ #include "amdgpu.h" #include "amdgpu_jpeg.h" +#include "amdgpu_cs.h" #include "soc15.h" #include "soc15d.h" #include "jpeg_v4_0_3.h" @@ -782,7 +783,11 @@ void jpeg_v4_0_3_dec_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8))); + + if (ring->funcs->parse_cs) + amdgpu_ring_write(ring, 0); + else + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8))); amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JPEG_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); @@ -1084,6 +1089,7 @@ static const struct amdgpu_ring_funcs jpeg_v4_0_3_dec_ring_vm_funcs = { .get_rptr = jpeg_v4_0_3_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_3_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_3_dec_ring_set_wptr, + .parse_cs = jpeg_v4_0_3_dec_ring_parse_cs, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + @@ -1248,3 +1254,56 @@ static void jpeg_v4_0_3_set_ras_funcs(struct amdgpu_device *adev) { adev->jpeg.ras = &jpeg_v4_0_3_ras; } + +/** + * jpeg_v4_0_3_dec_ring_parse_cs - command submission parser + * + * @parser: Command submission parser context + * @job: the job to parse + * @ib: the IB to parse + * + * Parse the command stream, return -EINVAL for invalid packet, + * 0 otherwise + */ +int jpeg_v4_0_3_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + uint32_t i, reg, res, cond, type; + struct amdgpu_device *adev = parser->adev; + + for (i = 0; i < ib->length_dw ; i += 2) { + reg = CP_PACKETJ_GET_REG(ib->ptr[i]); + res = CP_PACKETJ_GET_RES(ib->ptr[i]); + cond = CP_PACKETJ_GET_COND(ib->ptr[i]); + type = CP_PACKETJ_GET_TYPE(ib->ptr[i]); + + if (res) /* only support 0 at the moment */ + return -EINVAL; + + switch (type) { + case PACKETJ_TYPE0: + if (cond != PACKETJ_CONDITION_CHECK0 || reg < JPEG_REG_RANGE_START || reg > JPEG_REG_RANGE_END) { + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + return -EINVAL; + } + break; + case PACKETJ_TYPE3: + if (cond != PACKETJ_CONDITION_CHECK3 || reg < JPEG_REG_RANGE_START || reg > JPEG_REG_RANGE_END) { + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + return -EINVAL; + } + break; + case PACKETJ_TYPE6: + if (ib->ptr[i] == CP_PACKETJ_NOP) + continue; + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + return -EINVAL; + default: + dev_err(adev->dev, "Unknown packet type %d !\n", type); + return -EINVAL; + } + } + + return 0; +} diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h index 747a3e5f6856..71c54b294e15 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h @@ -46,6 +46,9 @@ #define JRBC_DEC_EXTERNAL_REG_WRITE_ADDR 0x18000 +#define JPEG_REG_RANGE_START 0x4000 +#define JPEG_REG_RANGE_END 0x41c2 + extern const struct amdgpu_ip_block_version jpeg_v4_0_3_ip_block; void jpeg_v4_0_3_dec_ring_emit_ib(struct amdgpu_ring *ring, @@ -62,5 +65,7 @@ void jpeg_v4_0_3_dec_ring_insert_end(struct amdgpu_ring *ring); void jpeg_v4_0_3_dec_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val); void jpeg_v4_0_3_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, uint32_t val, uint32_t mask); - +int jpeg_v4_0_3_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib); #endif /* __JPEG_V4_0_3_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c index d694a276498a..f4daff90c770 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c @@ -646,6 +646,7 @@ static const struct amdgpu_ring_funcs jpeg_v5_0_0_dec_ring_vm_funcs = { .get_rptr = jpeg_v5_0_0_dec_ring_get_rptr, .get_wptr = jpeg_v5_0_0_dec_ring_get_wptr, .set_wptr = jpeg_v5_0_0_dec_ring_set_wptr, + .parse_cs = jpeg_v4_0_3_dec_ring_parse_cs, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + diff --git a/drivers/gpu/drm/amd/amdgpu/soc15d.h b/drivers/gpu/drm/amd/amdgpu/soc15d.h index 2357ff39323f..e74e1983da53 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15d.h +++ b/drivers/gpu/drm/amd/amdgpu/soc15d.h @@ -76,6 +76,12 @@ ((cond & 0xF) << 24) | \ ((type & 0xF) << 28)) +#define CP_PACKETJ_NOP 0x60000000 +#define CP_PACKETJ_GET_REG(x) ((x) & 0x3FFFF) +#define CP_PACKETJ_GET_RES(x) (((x) >> 18) & 0x3F) +#define CP_PACKETJ_GET_COND(x) (((x) >> 24) & 0xF) +#define CP_PACKETJ_GET_TYPE(x) (((x) >> 28) & 0xF) + /* Packet 3 types */ #define PACKET3_NOP 0x10 #define PACKET3_SET_BASE 0x11 From 507a2286c052919fe416b3daa0f0061d0fc702b9 Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Fri, 9 Aug 2024 17:20:26 -0400 Subject: [PATCH 231/562] drm/amdgpu: Update kmd_fw_shared for VCN5 kmd_fw_shared changed in VCN5 Signed-off-by: Yinjie Yao Reviewed-by: Ruijing Dong Acked-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit aa02486fb18cecbaca0c4fd393d1a03f1d4c3f9a) --- drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index 1a5439abd1a0..c87d68d4be53 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -461,8 +461,11 @@ struct amdgpu_vcn5_fw_shared { struct amdgpu_fw_shared_unified_queue_struct sq; uint8_t pad1[8]; struct amdgpu_fw_shared_fw_logging fw_log; + uint8_t pad2[20]; struct amdgpu_fw_shared_rb_setup rb_setup; - uint8_t pad2[4]; + struct amdgpu_fw_shared_smu_interface_info smu_dpm_interface; + struct amdgpu_fw_shared_drm_key_wa drm_key_wa; + uint8_t pad3[9]; }; #define VCN_BLOCK_ENCODE_DISABLE_MASK 0x80 From 23acd1f344e8102f803119d0c8fc4df4628d694f Mon Sep 17 00:00:00 2001 From: Kenneth Feng Date: Thu, 8 Aug 2024 12:19:22 +0800 Subject: [PATCH 232/562] drm/amd/amdgpu: add HDP_SD support on gc 12.0.0/1 add HDP_SD support on gc 12.0.0/1 Signed-off-by: Kenneth Feng Reviewed-by: Yang Wang Signed-off-by: Alex Deucher (cherry picked from commit 61cffacb3a1c590b15c0e9ff987de02d293e0dd8) --- drivers/gpu/drm/amd/amdgpu/soc24.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/soc24.c b/drivers/gpu/drm/amd/amdgpu/soc24.c index 7d641d0dadba..b0c3678cfb31 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc24.c +++ b/drivers/gpu/drm/amd/amdgpu/soc24.c @@ -406,6 +406,7 @@ static int soc24_common_early_init(void *handle) AMD_CG_SUPPORT_ATHUB_MGCG | AMD_CG_SUPPORT_ATHUB_LS | AMD_CG_SUPPORT_MC_MGCG | + AMD_CG_SUPPORT_HDP_SD | AMD_CG_SUPPORT_MC_LS; adev->pg_flags = AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_JPEG | @@ -424,6 +425,7 @@ static int soc24_common_early_init(void *handle) AMD_CG_SUPPORT_ATHUB_MGCG | AMD_CG_SUPPORT_ATHUB_LS | AMD_CG_SUPPORT_MC_MGCG | + AMD_CG_SUPPORT_HDP_SD | AMD_CG_SUPPORT_MC_LS; adev->pg_flags = AMD_PG_SUPPORT_VCN | From 100bff23818eb61751ed05d64a7df36ce9728a4d Mon Sep 17 00:00:00 2001 From: Kyle Huey Date: Tue, 13 Aug 2024 15:17:27 +0000 Subject: [PATCH 233/562] perf/bpf: Don't call bpf_overflow_handler() for tracing events The regressing commit is new in 6.10. It assumed that anytime event->prog is set bpf_overflow_handler() should be invoked to execute the attached bpf program. This assumption is false for tracing events, and as a result the regressing commit broke bpftrace by invoking the bpf handler with garbage inputs on overflow. Prior to the regression the overflow handlers formed a chain (of length 0, 1, or 2) and perf_event_set_bpf_handler() (the !tracing case) added bpf_overflow_handler() to that chain, while perf_event_attach_bpf_prog() (the tracing case) did not. Both set event->prog. The chain of overflow handlers was replaced by a single overflow handler slot and a fixed call to bpf_overflow_handler() when appropriate. This modifies the condition there to check event->prog->type == BPF_PROG_TYPE_PERF_EVENT, restoring the previous behavior and fixing bpftrace. Signed-off-by: Kyle Huey Suggested-by: Andrii Nakryiko Reported-by: Joe Damato Closes: https://lore.kernel.org/lkml/ZpFfocvyF3KHaSzF@LQ3V64L9R2/ Fixes: f11f10bfa1ca ("perf/bpf: Call BPF handler directly, not through overflow machinery") Cc: stable@vger.kernel.org Tested-by: Joe Damato # bpftrace Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20240813151727.28797-1-jdamato@fastly.com Signed-off-by: Alexei Starovoitov --- kernel/events/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index aa3450bdc227..c973e3c11e03 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9706,7 +9706,8 @@ static int __perf_event_overflow(struct perf_event *event, ret = __perf_event_account_interrupt(event, throttle); - if (event->prog && !bpf_overflow_handler(event, data, regs)) + if (event->prog && event->prog->type == BPF_PROG_TYPE_PERF_EVENT && + !bpf_overflow_handler(event, data, regs)) return ret; /* From faada2174c08662ae98b439c69efe3e79382c538 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 13 Aug 2024 16:35:14 +0200 Subject: [PATCH 234/562] dm persistent data: fix memory allocation failure kmalloc is unreliable when allocating more than 8 pages of memory. It may fail when there is plenty of free memory but the memory is fragmented. Zdenek Kabelac observed such failure in his tests. This commit changes kmalloc to kvmalloc - kvmalloc will fall back to vmalloc if the large allocation fails. Signed-off-by: Mikulas Patocka Reported-by: Zdenek Kabelac Reviewed-by: Mike Snitzer Cc: stable@vger.kernel.org --- drivers/md/persistent-data/dm-space-map-metadata.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index 04698fd03e60..d48c4fafc779 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -277,7 +277,7 @@ static void sm_metadata_destroy(struct dm_space_map *sm) { struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); - kfree(smm); + kvfree(smm); } static int sm_metadata_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count) @@ -772,7 +772,7 @@ struct dm_space_map *dm_sm_metadata_init(void) { struct sm_metadata *smm; - smm = kmalloc(sizeof(*smm), GFP_KERNEL); + smm = kvmalloc(sizeof(*smm), GFP_KERNEL); if (!smm) return ERR_PTR(-ENOMEM); From 3e30296b374af33cb4c12ff93df0b1e5b2d0f80b Mon Sep 17 00:00:00 2001 From: Abhinav Kumar Date: Thu, 8 Aug 2024 16:52:27 -0700 Subject: [PATCH 235/562] drm/msm: fix the highest_bank_bit for sc7180 sc7180 programs the ubwc settings as 0x1e as that would mean a highest bank bit of 14 which matches what the GPU sets as well. However, the highest_bank_bit field of the msm_mdss_data which is being used to program the SSPP's fetch configuration is programmed to a highest bank bit of 16 as 0x3 translates to 16 and not 14. Fix the highest bank bit field used for the SSPP to match the mdss and gpu settings. Fixes: 6f410b246209 ("drm/msm/mdss: populate missing data") Reviewed-by: Rob Clark Tested-by: Stephen Boyd # Trogdor.Lazor Patchwork: https://patchwork.freedesktop.org/patch/607625/ Link: https://lore.kernel.org/r/20240808235227.2701479-1-quic_abhinavk@quicinc.com Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/msm_mdss.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index d90b9471ba6f..faa88fd6eb4d 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -577,7 +577,7 @@ static const struct msm_mdss_data sc7180_data = { .ubwc_enc_version = UBWC_2_0, .ubwc_dec_version = UBWC_2_0, .ubwc_static = 0x1e, - .highest_bank_bit = 0x3, + .highest_bank_bit = 0x1, .reg_bus_bw = 76800, }; From f50733b45d865f91db90919f8311e2127ce5a0cb Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 8 Aug 2024 11:39:08 -0700 Subject: [PATCH 236/562] exec: Fix ToCToU between perm check and set-uid/gid usage When opening a file for exec via do_filp_open(), permission checking is done against the file's metadata at that moment, and on success, a file pointer is passed back. Much later in the execve() code path, the file metadata (specifically mode, uid, and gid) is used to determine if/how to set the uid and gid. However, those values may have changed since the permissions check, meaning the execution may gain unintended privileges. For example, if a file could change permissions from executable and not set-id: ---------x 1 root root 16048 Aug 7 13:16 target to set-id and non-executable: ---S------ 1 root root 16048 Aug 7 13:16 target it is possible to gain root privileges when execution should have been disallowed. While this race condition is rare in real-world scenarios, it has been observed (and proven exploitable) when package managers are updating the setuid bits of installed programs. Such files start with being world-executable but then are adjusted to be group-exec with a set-uid bit. For example, "chmod o-x,u+s target" makes "target" executable only by uid "root" and gid "cdrom", while also becoming setuid-root: -rwxr-xr-x 1 root cdrom 16048 Aug 7 13:16 target becomes: -rwsr-xr-- 1 root cdrom 16048 Aug 7 13:16 target But racing the chmod means users without group "cdrom" membership can get the permission to execute "target" just before the chmod, and when the chmod finishes, the exec reaches brpm_fill_uid(), and performs the setuid to root, violating the expressed authorization of "only cdrom group members can setuid to root". Re-check that we still have execute permissions in case the metadata has changed. It would be better to keep a copy from the perm-check time, but until we can do that refactoring, the least-bad option is to do a full inode_permission() call (under inode lock). It is understood that this is safe against dead-locks, but hardly optimal. Reported-by: Marco Vanotti Tested-by: Marco Vanotti Suggested-by: Linus Torvalds Cc: stable@vger.kernel.org Cc: Eric Biederman Cc: Alexander Viro Cc: Christian Brauner Signed-off-by: Kees Cook --- fs/exec.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/exec.c b/fs/exec.c index a126e3d1cacb..50e76cc633c4 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1692,6 +1692,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) unsigned int mode; vfsuid_t vfsuid; vfsgid_t vfsgid; + int err; if (!mnt_may_suid(file->f_path.mnt)) return; @@ -1708,12 +1709,17 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) /* Be careful if suid/sgid is set */ inode_lock(inode); - /* reload atomically mode/uid/gid now that lock held */ + /* Atomically reload and check mode/uid/gid now that lock held. */ mode = inode->i_mode; vfsuid = i_uid_into_vfsuid(idmap, inode); vfsgid = i_gid_into_vfsgid(idmap, inode); + err = inode_permission(idmap, inode, MAY_EXEC); inode_unlock(inode); + /* Did the exec bit vanish out from under us? Give up. */ + if (err) + return; + /* We ignore suid/sgid if there are no mappings for them in the ns */ if (!vfsuid_has_mapping(bprm->cred->user_ns, vfsuid) || !vfsgid_has_mapping(bprm->cred->user_ns, vfsgid)) From b739dffa5d570b411d4bdf4bb9b8dfd6b7d72305 Mon Sep 17 00:00:00 2001 From: Stefan Wiehler Date: Mon, 12 Aug 2024 12:06:51 +0200 Subject: [PATCH 237/562] of/irq: Prevent device address out-of-bounds read in interrupt map walk When of_irq_parse_raw() is invoked with a device address smaller than the interrupt parent node (from #address-cells property), KASAN detects the following out-of-bounds read when populating the initial match table (dyndbg="func of_irq_parse_* +p"): OF: of_irq_parse_one: dev=/soc@0/picasso/watchdog, index=0 OF: parent=/soc@0/pci@878000000000/gpio0@17,0, intsize=2 OF: intspec=4 OF: of_irq_parse_raw: ipar=/soc@0/pci@878000000000/gpio0@17,0, size=2 OF: -> addrsize=3 ================================================================== BUG: KASAN: slab-out-of-bounds in of_irq_parse_raw+0x2b8/0x8d0 Read of size 4 at addr ffffff81beca5608 by task bash/764 CPU: 1 PID: 764 Comm: bash Tainted: G O 6.1.67-484c613561-nokia_sm_arm64 #1 Hardware name: Unknown Unknown Product/Unknown Product, BIOS 2023.01-12.24.03-dirty 01/01/2023 Call trace: dump_backtrace+0xdc/0x130 show_stack+0x1c/0x30 dump_stack_lvl+0x6c/0x84 print_report+0x150/0x448 kasan_report+0x98/0x140 __asan_load4+0x78/0xa0 of_irq_parse_raw+0x2b8/0x8d0 of_irq_parse_one+0x24c/0x270 parse_interrupts+0xc0/0x120 of_fwnode_add_links+0x100/0x2d0 fw_devlink_parse_fwtree+0x64/0xc0 device_add+0xb38/0xc30 of_device_add+0x64/0x90 of_platform_device_create_pdata+0xd0/0x170 of_platform_bus_create+0x244/0x600 of_platform_notify+0x1b0/0x254 blocking_notifier_call_chain+0x9c/0xd0 __of_changeset_entry_notify+0x1b8/0x230 __of_changeset_apply_notify+0x54/0xe4 of_overlay_fdt_apply+0xc04/0xd94 ... The buggy address belongs to the object at ffffff81beca5600 which belongs to the cache kmalloc-128 of size 128 The buggy address is located 8 bytes inside of 128-byte region [ffffff81beca5600, ffffff81beca5680) The buggy address belongs to the physical page: page:00000000230d3d03 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1beca4 head:00000000230d3d03 order:1 compound_mapcount:0 compound_pincount:0 flags: 0x8000000000010200(slab|head|zone=2) raw: 8000000000010200 0000000000000000 dead000000000122 ffffff810000c300 raw: 0000000000000000 0000000000200020 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffffff81beca5500: 04 fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffffff81beca5580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffffff81beca5600: 00 fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffffff81beca5680: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffffff81beca5700: 00 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc ================================================================== OF: -> got it ! Prevent the out-of-bounds read by copying the device address into a buffer of sufficient size. Signed-off-by: Stefan Wiehler Link: https://lore.kernel.org/r/20240812100652.3800963-1-stefan.wiehler@nokia.com Signed-off-by: Rob Herring (Arm) --- drivers/of/irq.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/of/irq.c b/drivers/of/irq.c index c94203ce65bb..8fd63100ba8f 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -344,7 +344,8 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar struct device_node *p; const __be32 *addr; u32 intsize; - int i, res; + int i, res, addr_len; + __be32 addr_buf[3] = { 0 }; pr_debug("of_irq_parse_one: dev=%pOF, index=%d\n", device, index); @@ -353,13 +354,19 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar return of_irq_parse_oldworld(device, index, out_irq); /* Get the reg property (if any) */ - addr = of_get_property(device, "reg", NULL); + addr = of_get_property(device, "reg", &addr_len); + + /* Prevent out-of-bounds read in case of longer interrupt parent address size */ + if (addr_len > (3 * sizeof(__be32))) + addr_len = 3 * sizeof(__be32); + if (addr) + memcpy(addr_buf, addr, addr_len); /* Try the new-style interrupts-extended first */ res = of_parse_phandle_with_args(device, "interrupts-extended", "#interrupt-cells", index, out_irq); if (!res) - return of_irq_parse_raw(addr, out_irq); + return of_irq_parse_raw(addr_buf, out_irq); /* Look for the interrupt parent. */ p = of_irq_find_parent(device); @@ -389,7 +396,7 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar /* Check if there are any interrupt-map translations to process */ - res = of_irq_parse_raw(addr, out_irq); + res = of_irq_parse_raw(addr_buf, out_irq); out: of_node_put(p); return res; From 4e91fa1ef3ce6290b4c598e54b5eb6cf134fbec8 Mon Sep 17 00:00:00 2001 From: Andi Shyti Date: Mon, 12 Aug 2024 21:40:28 +0200 Subject: [PATCH 238/562] i2c: qcom-geni: Add missing geni_icc_disable in geni_i2c_runtime_resume Add the missing geni_icc_disable() call before returning in the geni_i2c_runtime_resume() function. Commit 9ba48db9f77c ("i2c: qcom-geni: Add missing geni_icc_disable in geni_i2c_runtime_resume") by Gaosheng missed disabling the interconnect in one case. Fixes: bf225ed357c6 ("i2c: i2c-qcom-geni: Add interconnect support") Cc: Gaosheng Cui Cc: stable@vger.kernel.org # v5.9+ Signed-off-by: Andi Shyti --- drivers/i2c/busses/i2c-qcom-geni.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 365e37bba0f3..06e836e3e877 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -986,8 +986,10 @@ static int __maybe_unused geni_i2c_runtime_resume(struct device *dev) return ret; ret = clk_prepare_enable(gi2c->core_clk); - if (ret) + if (ret) { + geni_icc_disable(&gi2c->se); return ret; + } ret = geni_se_resources_on(&gi2c->se); if (ret) { From 655111b838cdabdb604f3625a9ff08c5eedb11da Mon Sep 17 00:00:00 2001 From: Eugene Syromiatnikov Date: Mon, 12 Aug 2024 08:51:23 +0200 Subject: [PATCH 239/562] mptcp: correct MPTCP_SUBFLOW_ATTR_SSN_OFFSET reserved size ssn_offset field is u32 and is placed into the netlink response with nla_put_u32(), but only 2 bytes are reserved for the attribute payload in subflow_get_info_size() (even though it makes no difference in the end, as it is aligned up to 4 bytes). Supply the correct argument to the relevant nla_total_size() call to make it less confusing. Fixes: 5147dfb50832 ("mptcp: allow dumping subflow context to userspace") Signed-off-by: Eugene Syromiatnikov Reviewed-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240812065024.GA19719@asgard.redhat.com Signed-off-by: Jakub Kicinski --- net/mptcp/diag.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index 3ae46b545d2c..2d3efb405437 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -94,7 +94,7 @@ static size_t subflow_get_info_size(const struct sock *sk) nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */ nla_total_size_64bit(8) + /* MPTCP_SUBFLOW_ATTR_MAP_SEQ */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */ - nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ + nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_FLAGS */ nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_REM */ From a24e6e7146e361aa0855cf8ee3b2e80b8eb692e3 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 13 Aug 2024 22:40:39 -0400 Subject: [PATCH 240/562] bcachefs: delete faulty fastpath in bch2_btree_path_traverse_cached() bch2_btree_path_traverse_cached() was previously checking if it could just relock the path, which is a common idiom in path traversal. However, it was using btree_node_relock(), not btree_path_relock(); btree_path_relock() only succeeds if the path was in state BTREE_ITER_NEED_RELOCK. If the path was in state BTREE_ITER_NEED_TRAVERSE a full traversal is needed; this led to a null ptr deref in bch2_btree_path_traverse_cached(). And the short circuit check here isn't needed, since it was already done in the main bch2_btree_path_traverse_one(). Signed-off-by: Kent Overstreet --- fs/bcachefs/btree_key_cache.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index f2f2e525460b..79954490627c 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -497,11 +497,6 @@ int bch2_btree_path_traverse_cached(struct btree_trans *trans, struct btree_path path->l[1].b = NULL; - if (bch2_btree_node_relock_notrace(trans, path, 0)) { - path->uptodate = BTREE_ITER_UPTODATE; - return 0; - } - int ret; do { ret = btree_path_traverse_cached_fast(trans, path); From bd864bc2d90790e00b02b17c75fb951cb4b0bb8b Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 12 Aug 2024 23:24:03 -0400 Subject: [PATCH 241/562] bcachefs: Fix bch2_trigger_alloc when upgrading from old versions bch2_trigger_alloc was assuming that the new key would always be newly created and thus always an alloc_v4 key, but - not when called from btree_gc. Signed-off-by: Kent Overstreet --- fs/bcachefs/alloc_background.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index d9c5a92fa708..0a8a1bc9a4ac 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -829,7 +829,19 @@ int bch2_trigger_alloc(struct btree_trans *trans, struct bch_alloc_v4 old_a_convert; const struct bch_alloc_v4 *old_a = bch2_alloc_to_v4(old, &old_a_convert); - struct bch_alloc_v4 *new_a = bkey_s_to_alloc_v4(new).v; + + struct bch_alloc_v4 *new_a; + if (likely(new.k->type == KEY_TYPE_alloc_v4)) { + new_a = bkey_s_to_alloc_v4(new).v; + } else { + BUG_ON(!(flags & BTREE_TRIGGER_gc)); + + struct bkey_i_alloc_v4 *new_ka = bch2_alloc_to_v4_mut_inlined(trans, new.s_c); + ret = PTR_ERR_OR_ZERO(new_ka); + if (unlikely(ret)) + goto err; + new_a = &new_ka->v; + } if (flags & BTREE_TRIGGER_transactional) { alloc_data_type_set(new_a, new_a->data_type); From d9e615762bf2eb7459fb0f270525f8b186bce6b7 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 13 Aug 2024 04:53:12 -0400 Subject: [PATCH 242/562] bcachefs: bch2_accounting_invalid() fixup Signed-off-by: Kent Overstreet --- fs/bcachefs/disk_accounting.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c index 046ac92b6639..212f53927111 100644 --- a/fs/bcachefs/disk_accounting.c +++ b/fs/bcachefs/disk_accounting.c @@ -154,7 +154,7 @@ int bch2_accounting_invalid(struct bch_fs *c, struct bkey_s_c k, "accounting key replicas entry with bad nr_required"); for (unsigned i = 0; i + 1 < acc_k.replicas.nr_devs; i++) - bkey_fsck_err_on(acc_k.replicas.devs[i] > acc_k.replicas.devs[i + 1], + bkey_fsck_err_on(acc_k.replicas.devs[i] >= acc_k.replicas.devs[i + 1], c, err, accounting_key_replicas_devs_unsorted, "accounting key replicas entry with unsorted devs"); From 486d920735325e507d965c2639ba2775b81fd329 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 13 Aug 2024 22:47:55 -0400 Subject: [PATCH 243/562] bcachefs: disk accounting: ignore unknown types forward compat fix Signed-off-by: Kent Overstreet --- fs/bcachefs/disk_accounting.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c index 212f53927111..03a9de6c2e0a 100644 --- a/fs/bcachefs/disk_accounting.c +++ b/fs/bcachefs/disk_accounting.c @@ -528,6 +528,9 @@ int bch2_gc_accounting_done(struct bch_fs *c) struct disk_accounting_pos acc_k; bpos_to_disk_accounting_pos(&acc_k, e->pos); + if (acc_k.type >= BCH_DISK_ACCOUNTING_TYPE_NR) + continue; + u64 src_v[BCH_ACCOUNTING_MAX_COUNTERS]; u64 dst_v[BCH_ACCOUNTING_MAX_COUNTERS]; @@ -760,6 +763,12 @@ void bch2_verify_accounting_clean(struct bch_fs *c) struct bkey_s_c_accounting a = bkey_s_c_to_accounting(k); unsigned nr = bch2_accounting_counters(k.k); + struct disk_accounting_pos acc_k; + bpos_to_disk_accounting_pos(&acc_k, k.k->p); + + if (acc_k.type >= BCH_DISK_ACCOUNTING_TYPE_NR) + continue; + bch2_accounting_mem_read(c, k.k->p, v, nr); if (memcmp(a.v->d, v, nr * sizeof(u64))) { @@ -775,9 +784,6 @@ void bch2_verify_accounting_clean(struct bch_fs *c) mismatch = true; } - struct disk_accounting_pos acc_k; - bpos_to_disk_accounting_pos(&acc_k, a.k->p); - switch (acc_k.type) { case BCH_DISK_ACCOUNTING_persistent_reserved: base.reserved += acc_k.persistent_reserved.nr_replicas * a.v->d[0]; From 48d6cc1b4895ada0781da11a0a483332a236ec14 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 13 Aug 2024 01:01:35 -0400 Subject: [PATCH 244/562] bcachefs: Add missing downgrade table entry Signed-off-by: Kent Overstreet --- fs/bcachefs/sb-downgrade.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index 6c4469f53313..9f82d497d9e0 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -104,6 +104,7 @@ BCH_FSCK_ERR_fs_usage_nr_inodes_wrong, \ BCH_FSCK_ERR_fs_usage_persistent_reserved_wrong, \ BCH_FSCK_ERR_fs_usage_replicas_wrong, \ + BCH_FSCK_ERR_accounting_replicas_not_marked, \ BCH_FSCK_ERR_bkey_version_in_future) struct upgrade_downgrade_entry { From 968feb854a86b59cc4bc72af3105989706ca2c7d Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 7 Aug 2024 16:34:28 -0400 Subject: [PATCH 245/562] bcachefs: Convert for_each_btree_node() to lockrestart_do() for_each_btree_node() now works similarly to for_each_btree_key(), where the loop body is passed as an argument to be passed to lockrestart_do(). This now calls trans_begin() on every loop iteration - which fixes an SRCU warning in backpointers fsck. Signed-off-by: Kent Overstreet --- fs/bcachefs/backpointers.c | 15 +++++--------- fs/bcachefs/btree_iter.c | 1 + fs/bcachefs/btree_iter.h | 42 ++++++++++++++++++++++++-------------- fs/bcachefs/debug.c | 38 ++++++++-------------------------- 4 files changed, 42 insertions(+), 54 deletions(-) diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index 3cc02479a982..9edc4c5f735c 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -763,27 +763,22 @@ static int bch2_get_btree_in_memory_pos(struct btree_trans *trans, btree < BTREE_ID_NR && !ret; btree++) { unsigned depth = (BIT_ULL(btree) & btree_leaf_mask) ? 0 : 1; - struct btree_iter iter; - struct btree *b; if (!(BIT_ULL(btree) & btree_leaf_mask) && !(BIT_ULL(btree) & btree_interior_mask)) continue; - bch2_trans_begin(trans); - - __for_each_btree_node(trans, iter, btree, + ret = __for_each_btree_node(trans, iter, btree, btree == start.btree ? start.pos : POS_MIN, - 0, depth, BTREE_ITER_prefetch, b, ret) { + 0, depth, BTREE_ITER_prefetch, b, ({ mem_may_pin -= btree_buf_bytes(b); if (mem_may_pin <= 0) { c->btree_cache.pinned_nodes_end = *end = BBPOS(btree, b->key.k.p); - bch2_trans_iter_exit(trans, &iter); - return 0; + break; } - } - bch2_trans_iter_exit(trans, &iter); + 0; + })); } return ret; diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index aa8a049071f4..2e84d22e17bd 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -1900,6 +1900,7 @@ err: goto out; } +/* Only kept for -tools */ struct btree *bch2_btree_iter_peek_node_and_restart(struct btree_iter *iter) { struct btree *b; diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h index c7725865309c..dca62375d7d3 100644 --- a/fs/bcachefs/btree_iter.h +++ b/fs/bcachefs/btree_iter.h @@ -600,23 +600,35 @@ void bch2_trans_srcu_unlock(struct btree_trans *); u32 bch2_trans_begin(struct btree_trans *); -/* - * XXX - * this does not handle transaction restarts from bch2_btree_iter_next_node() - * correctly - */ -#define __for_each_btree_node(_trans, _iter, _btree_id, _start, \ - _locks_want, _depth, _flags, _b, _ret) \ - for (bch2_trans_node_iter_init((_trans), &(_iter), (_btree_id), \ - _start, _locks_want, _depth, _flags); \ - (_b) = bch2_btree_iter_peek_node_and_restart(&(_iter)), \ - !((_ret) = PTR_ERR_OR_ZERO(_b)) && (_b); \ - (_b) = bch2_btree_iter_next_node(&(_iter))) +#define __for_each_btree_node(_trans, _iter, _btree_id, _start, \ + _locks_want, _depth, _flags, _b, _do) \ +({ \ + bch2_trans_begin((_trans)); \ + \ + struct btree_iter _iter; \ + bch2_trans_node_iter_init((_trans), &_iter, (_btree_id), \ + _start, _locks_want, _depth, _flags); \ + int _ret3 = 0; \ + do { \ + _ret3 = lockrestart_do((_trans), ({ \ + struct btree *_b = bch2_btree_iter_peek_node(&_iter); \ + if (!_b) \ + break; \ + \ + PTR_ERR_OR_ZERO(_b) ?: (_do); \ + })) ?: \ + lockrestart_do((_trans), \ + PTR_ERR_OR_ZERO(bch2_btree_iter_next_node(&_iter))); \ + } while (!_ret3); \ + \ + bch2_trans_iter_exit((_trans), &(_iter)); \ + _ret3; \ +}) #define for_each_btree_node(_trans, _iter, _btree_id, _start, \ - _flags, _b, _ret) \ - __for_each_btree_node(_trans, _iter, _btree_id, _start, \ - 0, 0, _flags, _b, _ret) + _flags, _b, _do) \ + __for_each_btree_node(_trans, _iter, _btree_id, _start, \ + 0, 0, _flags, _b, _do) static inline struct bkey_s_c bch2_btree_iter_peek_prev_type(struct btree_iter *iter, unsigned flags) diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c index ebabab171fe5..45aec1afdb0e 100644 --- a/fs/bcachefs/debug.c +++ b/fs/bcachefs/debug.c @@ -397,47 +397,27 @@ static ssize_t bch2_read_btree_formats(struct file *file, char __user *buf, size_t size, loff_t *ppos) { struct dump_iter *i = file->private_data; - struct btree_trans *trans; - struct btree_iter iter; - struct btree *b; - ssize_t ret; i->ubuf = buf; i->size = size; i->ret = 0; - ret = flush_buf(i); + ssize_t ret = flush_buf(i); if (ret) return ret; if (bpos_eq(SPOS_MAX, i->from)) return i->ret; - trans = bch2_trans_get(i->c); -retry: - bch2_trans_begin(trans); + return bch2_trans_run(i->c, + for_each_btree_node(trans, iter, i->id, i->from, 0, b, ({ + bch2_btree_node_to_text(&i->buf, i->c, b); + i->from = !bpos_eq(SPOS_MAX, b->key.k.p) + ? bpos_successor(b->key.k.p) + : b->key.k.p; - for_each_btree_node(trans, iter, i->id, i->from, 0, b, ret) { - bch2_btree_node_to_text(&i->buf, i->c, b); - i->from = !bpos_eq(SPOS_MAX, b->key.k.p) - ? bpos_successor(b->key.k.p) - : b->key.k.p; - - ret = drop_locks_do(trans, flush_buf(i)); - if (ret) - break; - } - bch2_trans_iter_exit(trans, &iter); - - if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) - goto retry; - - bch2_trans_put(trans); - - if (!ret) - ret = flush_buf(i); - - return ret ?: i->ret; + drop_locks_do(trans, flush_buf(i)); + }))) ?: i->ret; } static const struct file_operations btree_format_debug_ops = { From b2f11c6f3e1fc60742673b8675c95b78447f3dae Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 10 Aug 2024 21:04:35 -0400 Subject: [PATCH 246/562] lib/generic-radix-tree.c: Fix rare race in __genradix_ptr_alloc() If we need to increase the tree depth, allocate a new node, and then race with another thread that increased the tree depth before us, we'll still have a preallocated node that might be used later. If we then use that node for a new non-root node, it'll still have a pointer to the old root instead of being zeroed - fix this by zeroing it in the cmpxchg failure path. Signed-off-by: Kent Overstreet --- lib/generic-radix-tree.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/generic-radix-tree.c b/lib/generic-radix-tree.c index aaefb9b678c8..fa692c86f069 100644 --- a/lib/generic-radix-tree.c +++ b/lib/generic-radix-tree.c @@ -121,6 +121,8 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset, if ((v = cmpxchg_release(&radix->root, r, new_root)) == r) { v = new_root; new_node = NULL; + } else { + new_node->children[0] = NULL; } } From 7254555c440ff6b136aa97fb3c33fd5e0bb4fb9f Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 10 Aug 2024 14:40:09 -0400 Subject: [PATCH 247/562] bcachefs: Add hysteresis to waiting on btree key cache flush This helps ensure key cache reclaim isn't contending with threads waiting for the key cache to be helped, and fixes a severe performance bug. Signed-off-by: Kent Overstreet --- fs/bcachefs/btree_key_cache.h | 9 +++++++++ fs/bcachefs/btree_trans_commit.c | 2 +- 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/bcachefs/btree_key_cache.h b/fs/bcachefs/btree_key_cache.h index e6b2cd0dd2c1..113309f62918 100644 --- a/fs/bcachefs/btree_key_cache.h +++ b/fs/bcachefs/btree_key_cache.h @@ -20,6 +20,15 @@ static inline bool bch2_btree_key_cache_must_wait(struct bch_fs *c) return nr_dirty > max_dirty; } +static inline bool bch2_btree_key_cache_wait_done(struct bch_fs *c) +{ + size_t nr_dirty = atomic_long_read(&c->btree_key_cache.nr_dirty); + size_t nr_keys = atomic_long_read(&c->btree_key_cache.nr_keys); + size_t max_dirty = 2048 + (nr_keys * 5) / 8; + + return nr_dirty <= max_dirty; +} + int bch2_btree_key_cache_journal_flush(struct journal *, struct journal_entry_pin *, u64); diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index cca336fe46e9..f567bfb82850 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -927,7 +927,7 @@ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags static int journal_reclaim_wait_done(struct bch_fs *c) { int ret = bch2_journal_error(&c->journal) ?: - !bch2_btree_key_cache_must_wait(c); + bch2_btree_key_cache_wait_done(c); if (!ret) journal_reclaim_kick(&c->journal); From 790666c8ac6427ddaa00f502dc44073c1e039355 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 10 Aug 2024 14:31:17 -0400 Subject: [PATCH 248/562] bcachefs: Improve trans_blocked_journal_reclaim tracepoint include information about the state of the btree key cache Signed-off-by: Kent Overstreet --- fs/bcachefs/btree_key_cache.h | 9 +++++++-- fs/bcachefs/trace.c | 1 + fs/bcachefs/trace.h | 27 +++++++++++++++++++++++++-- 3 files changed, 33 insertions(+), 4 deletions(-) diff --git a/fs/bcachefs/btree_key_cache.h b/fs/bcachefs/btree_key_cache.h index 113309f62918..51d6289b8dee 100644 --- a/fs/bcachefs/btree_key_cache.h +++ b/fs/bcachefs/btree_key_cache.h @@ -11,13 +11,18 @@ static inline size_t bch2_nr_btree_keys_need_flush(struct bch_fs *c) return max_t(ssize_t, 0, nr_dirty - max_dirty); } -static inline bool bch2_btree_key_cache_must_wait(struct bch_fs *c) +static inline ssize_t __bch2_btree_key_cache_must_wait(struct bch_fs *c) { size_t nr_dirty = atomic_long_read(&c->btree_key_cache.nr_dirty); size_t nr_keys = atomic_long_read(&c->btree_key_cache.nr_keys); size_t max_dirty = 4096 + (nr_keys * 3) / 4; - return nr_dirty > max_dirty; + return nr_dirty - max_dirty; +} + +static inline bool bch2_btree_key_cache_must_wait(struct bch_fs *c) +{ + return __bch2_btree_key_cache_must_wait(c) > 0; } static inline bool bch2_btree_key_cache_wait_done(struct bch_fs *c) diff --git a/fs/bcachefs/trace.c b/fs/bcachefs/trace.c index dc48b52b01b4..dfad1d06633d 100644 --- a/fs/bcachefs/trace.c +++ b/fs/bcachefs/trace.c @@ -4,6 +4,7 @@ #include "buckets.h" #include "btree_cache.h" #include "btree_iter.h" +#include "btree_key_cache.h" #include "btree_locking.h" #include "btree_update_interior.h" #include "keylist.h" diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h index d0e6b9deb6cb..c62f00322d1e 100644 --- a/fs/bcachefs/trace.h +++ b/fs/bcachefs/trace.h @@ -988,10 +988,33 @@ TRACE_EVENT(trans_restart_split_race, __entry->u64s_remaining) ); -DEFINE_EVENT(transaction_event, trans_blocked_journal_reclaim, +TRACE_EVENT(trans_blocked_journal_reclaim, TP_PROTO(struct btree_trans *trans, unsigned long caller_ip), - TP_ARGS(trans, caller_ip) + TP_ARGS(trans, caller_ip), + + TP_STRUCT__entry( + __array(char, trans_fn, 32 ) + __field(unsigned long, caller_ip ) + + __field(unsigned long, key_cache_nr_keys ) + __field(unsigned long, key_cache_nr_dirty ) + __field(long, must_wait ) + ), + + TP_fast_assign( + strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn)); + __entry->caller_ip = caller_ip; + __entry->key_cache_nr_keys = atomic_long_read(&trans->c->btree_key_cache.nr_keys); + __entry->key_cache_nr_dirty = atomic_long_read(&trans->c->btree_key_cache.nr_dirty); + __entry->must_wait = __bch2_btree_key_cache_must_wait(trans->c); + ), + + TP_printk("%s %pS key cache keys %lu dirty %lu must_wait %li", + __entry->trans_fn, (void *) __entry->caller_ip, + __entry->key_cache_nr_keys, + __entry->key_cache_nr_dirty, + __entry->must_wait) ); TRACE_EVENT(trans_restart_journal_preres_get, From 06a8693b890c0cf7d94bf7c6f0e2adf3a3aaa346 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 10 Aug 2024 15:48:18 -0400 Subject: [PATCH 249/562] bcachefs: Add a time_stat for blocked on key cache flush Signed-off-by: Kent Overstreet --- fs/bcachefs/bcachefs.h | 1 + fs/bcachefs/btree_trans_commit.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index eedf2d6045e7..0c7086e00d18 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -447,6 +447,7 @@ BCH_DEBUG_PARAMS_DEBUG() x(blocked_journal_low_on_space) \ x(blocked_journal_low_on_pin) \ x(blocked_journal_max_in_flight) \ + x(blocked_key_cache_flush) \ x(blocked_allocate) \ x(blocked_allocate_open_bucket) \ x(blocked_write_buffer_full) \ diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index f567bfb82850..ac0c92683aad 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -973,9 +973,13 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags, bch2_trans_unlock(trans); trace_and_count(c, trans_blocked_journal_reclaim, trans, trace_ip); + track_event_change(&c->times[BCH_TIME_blocked_key_cache_flush], true); wait_event_freezable(c->journal.reclaim_wait, (ret = journal_reclaim_wait_done(c))); + + track_event_change(&c->times[BCH_TIME_blocked_key_cache_flush], false); + if (ret < 0) break; From c99471024f24b3cbafc02bf5b112ecf34b0dbd40 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 12 Aug 2024 23:29:46 -0400 Subject: [PATCH 250/562] bcachefs: Fix warning in __bch2_fsck_err() for trans not passed in Signed-off-by: Kent Overstreet --- fs/bcachefs/btree_io.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index 2c424435ca4a..70ebcca08ba2 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -1767,6 +1767,8 @@ static int __bch2_btree_root_read(struct btree_trans *trans, enum btree_id id, set_btree_node_read_in_flight(b); + /* we can't pass the trans to read_done() for fsck errors, so it must be unlocked */ + bch2_trans_unlock(trans); bch2_btree_node_read(trans, b, true); if (btree_node_read_error(b)) { From d97de0d017cde0d442c3d144b4f969f43064cc0f Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 12 Aug 2024 21:31:25 -0400 Subject: [PATCH 251/562] bcachefs: Make bkey_fsck_err() a wrapper around fsck_err() bkey_fsck_err() was added as an interface that looks like fsck_err(), but previously all it did was ensure that the appropriate error counter was incremented in the superblock. This is a cleanup and bugfix patch that converts it to a wrapper around fsck_err(). This is needed to fix an issue with the upgrade path to disk_accounting_v3, where the "silent fix" error list now includes bkey_fsck errors; fsck_err() handles this in a unified way, and since we need to change printing of bkey fsck errors from the caller to the inner bkey_fsck_err() calls, this ends up being a pretty big change. Als,, rename .invalid() methods to .validate(), for clarity, while we're changing the function signature anyways (to drop the printbuf argument). Signed-off-by: Kent Overstreet --- fs/bcachefs/alloc_background.c | 63 ++++++------ fs/bcachefs/alloc_background.h | 26 +++-- fs/bcachefs/backpointers.c | 8 +- fs/bcachefs/backpointers.h | 5 +- fs/bcachefs/bkey.h | 7 +- fs/bcachefs/bkey_methods.c | 109 ++++++++++----------- fs/bcachefs/bkey_methods.h | 21 ++-- fs/bcachefs/btree_io.c | 67 ++++--------- fs/bcachefs/btree_node_scan.c | 2 +- fs/bcachefs/btree_trans_commit.c | 72 +++----------- fs/bcachefs/btree_update_interior.c | 16 +--- fs/bcachefs/data_update.c | 6 +- fs/bcachefs/dirent.c | 33 ++++--- fs/bcachefs/dirent.h | 5 +- fs/bcachefs/disk_accounting.c | 13 ++- fs/bcachefs/disk_accounting.h | 5 +- fs/bcachefs/ec.c | 15 ++- fs/bcachefs/ec.h | 5 +- fs/bcachefs/errcode.h | 1 + fs/bcachefs/error.c | 22 +++++ fs/bcachefs/error.h | 39 ++++---- fs/bcachefs/extents.c | 144 ++++++++++++++-------------- fs/bcachefs/extents.h | 24 ++--- fs/bcachefs/inode.c | 77 +++++++-------- fs/bcachefs/inode.h | 24 ++--- fs/bcachefs/journal_io.c | 24 +---- fs/bcachefs/lru.c | 9 +- fs/bcachefs/lru.h | 5 +- fs/bcachefs/quota.c | 8 +- fs/bcachefs/quota.h | 5 +- fs/bcachefs/reflink.c | 19 ++-- fs/bcachefs/reflink.h | 22 ++--- fs/bcachefs/snapshot.c | 42 ++++---- fs/bcachefs/snapshot.h | 11 +-- fs/bcachefs/subvolume.c | 16 ++-- fs/bcachefs/subvolume.h | 5 +- fs/bcachefs/xattr.c | 21 ++-- fs/bcachefs/xattr.h | 5 +- 38 files changed, 448 insertions(+), 553 deletions(-) diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index 0a8a1bc9a4ac..fd3a2522bc3e 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -196,75 +196,71 @@ static unsigned bch_alloc_v1_val_u64s(const struct bch_alloc *a) return DIV_ROUND_UP(bytes, sizeof(u64)); } -int bch2_alloc_v1_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_alloc_v1_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_s_c_alloc a = bkey_s_c_to_alloc(k); int ret = 0; /* allow for unknown fields */ - bkey_fsck_err_on(bkey_val_u64s(a.k) < bch_alloc_v1_val_u64s(a.v), c, err, - alloc_v1_val_size_bad, + bkey_fsck_err_on(bkey_val_u64s(a.k) < bch_alloc_v1_val_u64s(a.v), + c, alloc_v1_val_size_bad, "incorrect value size (%zu < %u)", bkey_val_u64s(a.k), bch_alloc_v1_val_u64s(a.v)); fsck_err: return ret; } -int bch2_alloc_v2_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_alloc_v2_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_alloc_unpacked u; int ret = 0; - bkey_fsck_err_on(bch2_alloc_unpack_v2(&u, k), c, err, - alloc_v2_unpack_error, + bkey_fsck_err_on(bch2_alloc_unpack_v2(&u, k), + c, alloc_v2_unpack_error, "unpack error"); fsck_err: return ret; } -int bch2_alloc_v3_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_alloc_v3_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_alloc_unpacked u; int ret = 0; - bkey_fsck_err_on(bch2_alloc_unpack_v3(&u, k), c, err, - alloc_v2_unpack_error, + bkey_fsck_err_on(bch2_alloc_unpack_v3(&u, k), + c, alloc_v2_unpack_error, "unpack error"); fsck_err: return ret; } -int bch2_alloc_v4_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, struct printbuf *err) +int bch2_alloc_v4_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_s_c_alloc_v4 a = bkey_s_c_to_alloc_v4(k); int ret = 0; - bkey_fsck_err_on(alloc_v4_u64s_noerror(a.v) > bkey_val_u64s(k.k), c, err, - alloc_v4_val_size_bad, + bkey_fsck_err_on(alloc_v4_u64s_noerror(a.v) > bkey_val_u64s(k.k), + c, alloc_v4_val_size_bad, "bad val size (%u > %zu)", alloc_v4_u64s_noerror(a.v), bkey_val_u64s(k.k)); bkey_fsck_err_on(!BCH_ALLOC_V4_BACKPOINTERS_START(a.v) && - BCH_ALLOC_V4_NR_BACKPOINTERS(a.v), c, err, - alloc_v4_backpointers_start_bad, + BCH_ALLOC_V4_NR_BACKPOINTERS(a.v), + c, alloc_v4_backpointers_start_bad, "invalid backpointers_start"); - bkey_fsck_err_on(alloc_data_type(*a.v, a.v->data_type) != a.v->data_type, c, err, - alloc_key_data_type_bad, + bkey_fsck_err_on(alloc_data_type(*a.v, a.v->data_type) != a.v->data_type, + c, alloc_key_data_type_bad, "invalid data type (got %u should be %u)", a.v->data_type, alloc_data_type(*a.v, a.v->data_type)); for (unsigned i = 0; i < 2; i++) bkey_fsck_err_on(a.v->io_time[i] > LRU_TIME_MAX, - c, err, - alloc_key_io_time_bad, + c, alloc_key_io_time_bad, "invalid io_time[%s]: %llu, max %llu", i == READ ? "read" : "write", a.v->io_time[i], LRU_TIME_MAX); @@ -282,7 +278,7 @@ int bch2_alloc_v4_invalid(struct bch_fs *c, struct bkey_s_c k, a.v->dirty_sectors || a.v->cached_sectors || a.v->stripe, - c, err, alloc_key_empty_but_have_data, + c, alloc_key_empty_but_have_data, "empty data type free but have data %u.%u.%u %u", stripe_sectors, a.v->dirty_sectors, @@ -296,7 +292,7 @@ int bch2_alloc_v4_invalid(struct bch_fs *c, struct bkey_s_c k, case BCH_DATA_parity: bkey_fsck_err_on(!a.v->dirty_sectors && !stripe_sectors, - c, err, alloc_key_dirty_sectors_0, + c, alloc_key_dirty_sectors_0, "data_type %s but dirty_sectors==0", bch2_data_type_str(a.v->data_type)); break; @@ -305,12 +301,12 @@ int bch2_alloc_v4_invalid(struct bch_fs *c, struct bkey_s_c k, a.v->dirty_sectors || stripe_sectors || a.v->stripe, - c, err, alloc_key_cached_inconsistency, + c, alloc_key_cached_inconsistency, "data type inconsistency"); bkey_fsck_err_on(!a.v->io_time[READ] && c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_to_lru_refs, - c, err, alloc_key_cached_but_read_time_zero, + c, alloc_key_cached_but_read_time_zero, "cached bucket with read_time == 0"); break; case BCH_DATA_stripe: @@ -513,14 +509,13 @@ static unsigned alloc_gen(struct bkey_s_c k, unsigned offset) : 0; } -int bch2_bucket_gens_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_bucket_gens_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { int ret = 0; - bkey_fsck_err_on(bkey_val_bytes(k.k) != sizeof(struct bch_bucket_gens), c, err, - bucket_gens_val_size_bad, + bkey_fsck_err_on(bkey_val_bytes(k.k) != sizeof(struct bch_bucket_gens), + c, bucket_gens_val_size_bad, "bad val size (%zu != %zu)", bkey_val_bytes(k.k), sizeof(struct bch_bucket_gens)); fsck_err: diff --git a/fs/bcachefs/alloc_background.h b/fs/bcachefs/alloc_background.h index 96a0444ea78f..260e7fa83d05 100644 --- a/fs/bcachefs/alloc_background.h +++ b/fs/bcachefs/alloc_background.h @@ -240,52 +240,48 @@ struct bkey_i_alloc_v4 *bch2_alloc_to_v4_mut(struct btree_trans *, struct bkey_s int bch2_bucket_io_time_reset(struct btree_trans *, unsigned, size_t, int); -int bch2_alloc_v1_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); -int bch2_alloc_v2_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); -int bch2_alloc_v3_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); -int bch2_alloc_v4_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_alloc_v1_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_alloc_v2_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_alloc_v3_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_alloc_v4_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); void bch2_alloc_v4_swab(struct bkey_s); void bch2_alloc_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_alloc ((struct bkey_ops) { \ - .key_invalid = bch2_alloc_v1_invalid, \ + .key_validate = bch2_alloc_v1_validate, \ .val_to_text = bch2_alloc_to_text, \ .trigger = bch2_trigger_alloc, \ .min_val_size = 8, \ }) #define bch2_bkey_ops_alloc_v2 ((struct bkey_ops) { \ - .key_invalid = bch2_alloc_v2_invalid, \ + .key_validate = bch2_alloc_v2_validate, \ .val_to_text = bch2_alloc_to_text, \ .trigger = bch2_trigger_alloc, \ .min_val_size = 8, \ }) #define bch2_bkey_ops_alloc_v3 ((struct bkey_ops) { \ - .key_invalid = bch2_alloc_v3_invalid, \ + .key_validate = bch2_alloc_v3_validate, \ .val_to_text = bch2_alloc_to_text, \ .trigger = bch2_trigger_alloc, \ .min_val_size = 16, \ }) #define bch2_bkey_ops_alloc_v4 ((struct bkey_ops) { \ - .key_invalid = bch2_alloc_v4_invalid, \ + .key_validate = bch2_alloc_v4_validate, \ .val_to_text = bch2_alloc_to_text, \ .swab = bch2_alloc_v4_swab, \ .trigger = bch2_trigger_alloc, \ .min_val_size = 48, \ }) -int bch2_bucket_gens_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_bucket_gens_validate(struct bch_fs *, struct bkey_s_c, + enum bch_validate_flags); void bch2_bucket_gens_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_bucket_gens ((struct bkey_ops) { \ - .key_invalid = bch2_bucket_gens_invalid, \ + .key_validate = bch2_bucket_gens_validate, \ .val_to_text = bch2_bucket_gens_to_text, \ }) diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index 9edc4c5f735c..d4da6343efa9 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -47,9 +47,8 @@ static bool extent_matches_bp(struct bch_fs *c, return false; } -int bch2_backpointer_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_backpointer_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(k); @@ -68,8 +67,7 @@ int bch2_backpointer_invalid(struct bch_fs *c, struct bkey_s_c k, bkey_fsck_err_on((bp.v->bucket_offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT) >= ca->mi.bucket_size || !bpos_eq(bp.k->p, bp_pos), - c, err, - backpointer_bucket_offset_wrong, + c, backpointer_bucket_offset_wrong, "backpointer bucket_offset wrong"); fsck_err: return ret; diff --git a/fs/bcachefs/backpointers.h b/fs/bcachefs/backpointers.h index 6021de1c5e98..7daecadb764e 100644 --- a/fs/bcachefs/backpointers.h +++ b/fs/bcachefs/backpointers.h @@ -18,14 +18,13 @@ static inline u64 swab40(u64 x) ((x & 0xff00000000ULL) >> 32)); } -int bch2_backpointer_invalid(struct bch_fs *, struct bkey_s_c k, - enum bch_validate_flags, struct printbuf *); +int bch2_backpointer_validate(struct bch_fs *, struct bkey_s_c k, enum bch_validate_flags); void bch2_backpointer_to_text(struct printbuf *, const struct bch_backpointer *); void bch2_backpointer_k_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_backpointer_swab(struct bkey_s); #define bch2_bkey_ops_backpointer ((struct bkey_ops) { \ - .key_invalid = bch2_backpointer_invalid, \ + .key_validate = bch2_backpointer_validate, \ .val_to_text = bch2_backpointer_k_to_text, \ .swab = bch2_backpointer_swab, \ .min_val_size = 32, \ diff --git a/fs/bcachefs/bkey.h b/fs/bcachefs/bkey.h index 936357149cf0..e34cb2bf329c 100644 --- a/fs/bcachefs/bkey.h +++ b/fs/bcachefs/bkey.h @@ -10,9 +10,10 @@ #include "vstructs.h" enum bch_validate_flags { - BCH_VALIDATE_write = (1U << 0), - BCH_VALIDATE_commit = (1U << 1), - BCH_VALIDATE_journal = (1U << 2), + BCH_VALIDATE_write = BIT(0), + BCH_VALIDATE_commit = BIT(1), + BCH_VALIDATE_journal = BIT(2), + BCH_VALIDATE_silent = BIT(3), }; #if 0 diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c index 5f07cf853d0c..88d8958281e8 100644 --- a/fs/bcachefs/bkey_methods.c +++ b/fs/bcachefs/bkey_methods.c @@ -27,27 +27,27 @@ const char * const bch2_bkey_types[] = { NULL }; -static int deleted_key_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, struct printbuf *err) +static int deleted_key_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { return 0; } #define bch2_bkey_ops_deleted ((struct bkey_ops) { \ - .key_invalid = deleted_key_invalid, \ + .key_validate = deleted_key_validate, \ }) #define bch2_bkey_ops_whiteout ((struct bkey_ops) { \ - .key_invalid = deleted_key_invalid, \ + .key_validate = deleted_key_validate, \ }) -static int empty_val_key_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, struct printbuf *err) +static int empty_val_key_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { int ret = 0; - bkey_fsck_err_on(bkey_val_bytes(k.k), c, err, - bkey_val_size_nonzero, + bkey_fsck_err_on(bkey_val_bytes(k.k), + c, bkey_val_size_nonzero, "incorrect value size (%zu != 0)", bkey_val_bytes(k.k)); fsck_err: @@ -55,11 +55,11 @@ fsck_err: } #define bch2_bkey_ops_error ((struct bkey_ops) { \ - .key_invalid = empty_val_key_invalid, \ + .key_validate = empty_val_key_validate, \ }) -static int key_type_cookie_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, struct printbuf *err) +static int key_type_cookie_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { return 0; } @@ -73,17 +73,17 @@ static void key_type_cookie_to_text(struct printbuf *out, struct bch_fs *c, } #define bch2_bkey_ops_cookie ((struct bkey_ops) { \ - .key_invalid = key_type_cookie_invalid, \ + .key_validate = key_type_cookie_validate, \ .val_to_text = key_type_cookie_to_text, \ .min_val_size = 8, \ }) #define bch2_bkey_ops_hash_whiteout ((struct bkey_ops) {\ - .key_invalid = empty_val_key_invalid, \ + .key_validate = empty_val_key_validate, \ }) -static int key_type_inline_data_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, struct printbuf *err) +static int key_type_inline_data_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { return 0; } @@ -98,9 +98,9 @@ static void key_type_inline_data_to_text(struct printbuf *out, struct bch_fs *c, datalen, min(datalen, 32U), d.v->data); } -#define bch2_bkey_ops_inline_data ((struct bkey_ops) { \ - .key_invalid = key_type_inline_data_invalid, \ - .val_to_text = key_type_inline_data_to_text, \ +#define bch2_bkey_ops_inline_data ((struct bkey_ops) { \ + .key_validate = key_type_inline_data_validate, \ + .val_to_text = key_type_inline_data_to_text, \ }) static bool key_type_set_merge(struct bch_fs *c, struct bkey_s l, struct bkey_s_c r) @@ -110,7 +110,7 @@ static bool key_type_set_merge(struct bch_fs *c, struct bkey_s l, struct bkey_s_ } #define bch2_bkey_ops_set ((struct bkey_ops) { \ - .key_invalid = empty_val_key_invalid, \ + .key_validate = empty_val_key_validate, \ .key_merge = key_type_set_merge, \ }) @@ -123,9 +123,8 @@ const struct bkey_ops bch2_bkey_ops[] = { const struct bkey_ops bch2_bkey_null_ops = { }; -int bch2_bkey_val_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_bkey_val_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { if (test_bit(BCH_FS_no_invalid_checks, &c->flags)) return 0; @@ -133,15 +132,15 @@ int bch2_bkey_val_invalid(struct bch_fs *c, struct bkey_s_c k, const struct bkey_ops *ops = bch2_bkey_type_ops(k.k->type); int ret = 0; - bkey_fsck_err_on(bkey_val_bytes(k.k) < ops->min_val_size, c, err, - bkey_val_size_too_small, + bkey_fsck_err_on(bkey_val_bytes(k.k) < ops->min_val_size, + c, bkey_val_size_too_small, "bad val size (%zu < %u)", bkey_val_bytes(k.k), ops->min_val_size); - if (!ops->key_invalid) + if (!ops->key_validate) return 0; - ret = ops->key_invalid(c, k, flags, err); + ret = ops->key_validate(c, k, flags); fsck_err: return ret; } @@ -161,18 +160,17 @@ const char *bch2_btree_node_type_str(enum btree_node_type type) return type == BKEY_TYPE_btree ? "internal btree node" : bch2_btree_id_str(type - 1); } -int __bch2_bkey_invalid(struct bch_fs *c, struct bkey_s_c k, - enum btree_node_type type, - enum bch_validate_flags flags, - struct printbuf *err) +int __bch2_bkey_validate(struct bch_fs *c, struct bkey_s_c k, + enum btree_node_type type, + enum bch_validate_flags flags) { if (test_bit(BCH_FS_no_invalid_checks, &c->flags)) return 0; int ret = 0; - bkey_fsck_err_on(k.k->u64s < BKEY_U64s, c, err, - bkey_u64s_too_small, + bkey_fsck_err_on(k.k->u64s < BKEY_U64s, + c, bkey_u64s_too_small, "u64s too small (%u < %zu)", k.k->u64s, BKEY_U64s); if (type >= BKEY_TYPE_NR) @@ -180,8 +178,8 @@ int __bch2_bkey_invalid(struct bch_fs *c, struct bkey_s_c k, bkey_fsck_err_on(k.k->type < KEY_TYPE_MAX && (type == BKEY_TYPE_btree || (flags & BCH_VALIDATE_commit)) && - !(bch2_key_types_allowed[type] & BIT_ULL(k.k->type)), c, err, - bkey_invalid_type_for_btree, + !(bch2_key_types_allowed[type] & BIT_ULL(k.k->type)), + c, bkey_invalid_type_for_btree, "invalid key type for btree %s (%s)", bch2_btree_node_type_str(type), k.k->type < KEY_TYPE_MAX @@ -189,17 +187,17 @@ int __bch2_bkey_invalid(struct bch_fs *c, struct bkey_s_c k, : "(unknown)"); if (btree_node_type_is_extents(type) && !bkey_whiteout(k.k)) { - bkey_fsck_err_on(k.k->size == 0, c, err, - bkey_extent_size_zero, + bkey_fsck_err_on(k.k->size == 0, + c, bkey_extent_size_zero, "size == 0"); - bkey_fsck_err_on(k.k->size > k.k->p.offset, c, err, - bkey_extent_size_greater_than_offset, + bkey_fsck_err_on(k.k->size > k.k->p.offset, + c, bkey_extent_size_greater_than_offset, "size greater than offset (%u > %llu)", k.k->size, k.k->p.offset); } else { - bkey_fsck_err_on(k.k->size, c, err, - bkey_size_nonzero, + bkey_fsck_err_on(k.k->size, + c, bkey_size_nonzero, "size != 0"); } @@ -207,12 +205,12 @@ int __bch2_bkey_invalid(struct bch_fs *c, struct bkey_s_c k, enum btree_id btree = type - 1; if (btree_type_has_snapshots(btree)) { - bkey_fsck_err_on(!k.k->p.snapshot, c, err, - bkey_snapshot_zero, + bkey_fsck_err_on(!k.k->p.snapshot, + c, bkey_snapshot_zero, "snapshot == 0"); } else if (!btree_type_has_snapshot_field(btree)) { - bkey_fsck_err_on(k.k->p.snapshot, c, err, - bkey_snapshot_nonzero, + bkey_fsck_err_on(k.k->p.snapshot, + c, bkey_snapshot_nonzero, "nonzero snapshot"); } else { /* @@ -221,34 +219,33 @@ int __bch2_bkey_invalid(struct bch_fs *c, struct bkey_s_c k, */ } - bkey_fsck_err_on(bkey_eq(k.k->p, POS_MAX), c, err, - bkey_at_pos_max, + bkey_fsck_err_on(bkey_eq(k.k->p, POS_MAX), + c, bkey_at_pos_max, "key at POS_MAX"); } fsck_err: return ret; } -int bch2_bkey_invalid(struct bch_fs *c, struct bkey_s_c k, +int bch2_bkey_validate(struct bch_fs *c, struct bkey_s_c k, enum btree_node_type type, - enum bch_validate_flags flags, - struct printbuf *err) + enum bch_validate_flags flags) { - return __bch2_bkey_invalid(c, k, type, flags, err) ?: - bch2_bkey_val_invalid(c, k, flags, err); + return __bch2_bkey_validate(c, k, type, flags) ?: + bch2_bkey_val_validate(c, k, flags); } int bch2_bkey_in_btree_node(struct bch_fs *c, struct btree *b, - struct bkey_s_c k, struct printbuf *err) + struct bkey_s_c k, enum bch_validate_flags flags) { int ret = 0; - bkey_fsck_err_on(bpos_lt(k.k->p, b->data->min_key), c, err, - bkey_before_start_of_btree_node, + bkey_fsck_err_on(bpos_lt(k.k->p, b->data->min_key), + c, bkey_before_start_of_btree_node, "key before start of btree node"); - bkey_fsck_err_on(bpos_gt(k.k->p, b->data->max_key), c, err, - bkey_after_end_of_btree_node, + bkey_fsck_err_on(bpos_gt(k.k->p, b->data->max_key), + c, bkey_after_end_of_btree_node, "key past end of btree node"); fsck_err: return ret; diff --git a/fs/bcachefs/bkey_methods.h b/fs/bcachefs/bkey_methods.h index baef0722f5fb..3df3dd2723a1 100644 --- a/fs/bcachefs/bkey_methods.h +++ b/fs/bcachefs/bkey_methods.h @@ -14,15 +14,15 @@ extern const char * const bch2_bkey_types[]; extern const struct bkey_ops bch2_bkey_null_ops; /* - * key_invalid: checks validity of @k, returns 0 if good or -EINVAL if bad. If + * key_validate: checks validity of @k, returns 0 if good or -EINVAL if bad. If * invalid, entire key will be deleted. * * When invalid, error string is returned via @err. @rw indicates whether key is * being read or written; more aggressive checks can be enabled when rw == WRITE. */ struct bkey_ops { - int (*key_invalid)(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, struct printbuf *err); + int (*key_validate)(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags); void (*val_to_text)(struct printbuf *, struct bch_fs *, struct bkey_s_c); void (*swab)(struct bkey_s); @@ -48,14 +48,13 @@ static inline const struct bkey_ops *bch2_bkey_type_ops(enum bch_bkey_type type) : &bch2_bkey_null_ops; } -int bch2_bkey_val_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); -int __bch2_bkey_invalid(struct bch_fs *, struct bkey_s_c, enum btree_node_type, - enum bch_validate_flags, struct printbuf *); -int bch2_bkey_invalid(struct bch_fs *, struct bkey_s_c, enum btree_node_type, - enum bch_validate_flags, struct printbuf *); -int bch2_bkey_in_btree_node(struct bch_fs *, struct btree *, - struct bkey_s_c, struct printbuf *); +int bch2_bkey_val_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int __bch2_bkey_validate(struct bch_fs *, struct bkey_s_c, enum btree_node_type, + enum bch_validate_flags); +int bch2_bkey_validate(struct bch_fs *, struct bkey_s_c, enum btree_node_type, + enum bch_validate_flags); +int bch2_bkey_in_btree_node(struct bch_fs *, struct btree *, struct bkey_s_c, + enum bch_validate_flags); void bch2_bpos_to_text(struct printbuf *, struct bpos); void bch2_bkey_to_text(struct printbuf *, const struct bkey *); diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index 70ebcca08ba2..56ea9a77cd4a 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -836,14 +836,13 @@ fsck_err: return ret; } -static int bset_key_invalid(struct bch_fs *c, struct btree *b, - struct bkey_s_c k, - bool updated_range, int rw, - struct printbuf *err) +static int bset_key_validate(struct bch_fs *c, struct btree *b, + struct bkey_s_c k, + bool updated_range, int rw) { - return __bch2_bkey_invalid(c, k, btree_node_type(b), READ, err) ?: - (!updated_range ? bch2_bkey_in_btree_node(c, b, k, err) : 0) ?: - (rw == WRITE ? bch2_bkey_val_invalid(c, k, READ, err) : 0); + return __bch2_bkey_validate(c, k, btree_node_type(b), 0) ?: + (!updated_range ? bch2_bkey_in_btree_node(c, b, k, 0) : 0) ?: + (rw == WRITE ? bch2_bkey_val_validate(c, k, 0) : 0); } static bool bkey_packed_valid(struct bch_fs *c, struct btree *b, @@ -858,12 +857,9 @@ static bool bkey_packed_valid(struct bch_fs *c, struct btree *b, if (!bkeyp_u64s_valid(&b->format, k)) return false; - struct printbuf buf = PRINTBUF; struct bkey tmp; struct bkey_s u = __bkey_disassemble(b, k, &tmp); - bool ret = __bch2_bkey_invalid(c, u.s_c, btree_node_type(b), READ, &buf); - printbuf_exit(&buf); - return ret; + return !__bch2_bkey_validate(c, u.s_c, btree_node_type(b), BCH_VALIDATE_silent); } static int validate_bset_keys(struct bch_fs *c, struct btree *b, @@ -915,19 +911,11 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b, u = __bkey_disassemble(b, k, &tmp); - printbuf_reset(&buf); - if (bset_key_invalid(c, b, u.s_c, updated_range, write, &buf)) { - printbuf_reset(&buf); - bset_key_invalid(c, b, u.s_c, updated_range, write, &buf); - prt_printf(&buf, "\n "); - bch2_bkey_val_to_text(&buf, c, u.s_c); - - btree_err(-BCH_ERR_btree_node_read_err_fixable, - c, NULL, b, i, k, - btree_node_bad_bkey, - "invalid bkey: %s", buf.buf); + ret = bset_key_validate(c, b, u.s_c, updated_range, write); + if (ret == -BCH_ERR_fsck_delete_bkey) goto drop_this_key; - } + if (ret) + goto fsck_err; if (write) bch2_bkey_compat(b->c.level, b->c.btree_id, version, @@ -1228,23 +1216,10 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, struct bkey tmp; struct bkey_s u = __bkey_disassemble(b, k, &tmp); - printbuf_reset(&buf); - - if (bch2_bkey_val_invalid(c, u.s_c, READ, &buf) || + ret = bch2_bkey_val_validate(c, u.s_c, READ); + if (ret == -BCH_ERR_fsck_delete_bkey || (bch2_inject_invalid_keys && !bversion_cmp(u.k->version, MAX_VERSION))) { - printbuf_reset(&buf); - - prt_printf(&buf, "invalid bkey: "); - bch2_bkey_val_invalid(c, u.s_c, READ, &buf); - prt_printf(&buf, "\n "); - bch2_bkey_val_to_text(&buf, c, u.s_c); - - btree_err(-BCH_ERR_btree_node_read_err_fixable, - c, NULL, b, i, k, - btree_node_bad_bkey, - "%s", buf.buf); - btree_keys_account_key_drop(&b->nr, 0, k); i->u64s = cpu_to_le16(le16_to_cpu(i->u64s) - k->u64s); @@ -1253,6 +1228,8 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, set_btree_bset_end(b, b->set); continue; } + if (ret) + goto fsck_err; if (u.k->type == KEY_TYPE_btree_ptr_v2) { struct bkey_s_btree_ptr_v2 bp = bkey_s_to_btree_ptr_v2(u); @@ -1954,18 +1931,14 @@ static void btree_node_write_endio(struct bio *bio) static int validate_bset_for_write(struct bch_fs *c, struct btree *b, struct bset *i, unsigned sectors) { - struct printbuf buf = PRINTBUF; bool saw_error; - int ret; - ret = bch2_bkey_invalid(c, bkey_i_to_s_c(&b->key), - BKEY_TYPE_btree, WRITE, &buf); - - if (ret) - bch2_fs_inconsistent(c, "invalid btree node key before write: %s", buf.buf); - printbuf_exit(&buf); - if (ret) + int ret = bch2_bkey_validate(c, bkey_i_to_s_c(&b->key), + BKEY_TYPE_btree, WRITE); + if (ret) { + bch2_fs_inconsistent(c, "invalid btree node key before write"); return ret; + } ret = validate_bset_keys(c, b, i, WRITE, false, &saw_error) ?: validate_bset(c, NULL, b, i, b->written, sectors, WRITE, false, &saw_error); diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c index 001107226377..b28c649c6838 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -530,7 +530,7 @@ int bch2_get_scanned_nodes(struct bch_fs *c, enum btree_id btree, bch_verbose(c, "%s(): recovering %s", __func__, buf.buf); printbuf_exit(&buf); - BUG_ON(bch2_bkey_invalid(c, bkey_i_to_s_c(&tmp.k), BKEY_TYPE_btree, 0, NULL)); + BUG_ON(bch2_bkey_validate(c, bkey_i_to_s_c(&tmp.k), BKEY_TYPE_btree, 0)); ret = bch2_journal_key_insert(c, btree, level + 1, &tmp.k); if (ret) diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index ac0c92683aad..1a1e9d2036da 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -818,50 +818,6 @@ static noinline void bch2_drop_overwrites_from_journal(struct btree_trans *trans bch2_journal_key_overwritten(trans->c, i->btree_id, i->level, i->k->k.p); } -static noinline int bch2_trans_commit_bkey_invalid(struct btree_trans *trans, - enum bch_validate_flags flags, - struct btree_insert_entry *i, - struct printbuf *err) -{ - struct bch_fs *c = trans->c; - - printbuf_reset(err); - prt_printf(err, "invalid bkey on insert from %s -> %ps\n", - trans->fn, (void *) i->ip_allocated); - printbuf_indent_add(err, 2); - - bch2_bkey_val_to_text(err, c, bkey_i_to_s_c(i->k)); - prt_newline(err); - - bch2_bkey_invalid(c, bkey_i_to_s_c(i->k), i->bkey_type, flags, err); - bch2_print_string_as_lines(KERN_ERR, err->buf); - - bch2_inconsistent_error(c); - bch2_dump_trans_updates(trans); - - return -EINVAL; -} - -static noinline int bch2_trans_commit_journal_entry_invalid(struct btree_trans *trans, - struct jset_entry *i) -{ - struct bch_fs *c = trans->c; - struct printbuf buf = PRINTBUF; - - prt_printf(&buf, "invalid bkey on insert from %s\n", trans->fn); - printbuf_indent_add(&buf, 2); - - bch2_journal_entry_to_text(&buf, c, i); - prt_newline(&buf); - - bch2_print_string_as_lines(KERN_ERR, buf.buf); - - bch2_inconsistent_error(c); - bch2_dump_trans_updates(trans); - - return -EINVAL; -} - static int bch2_trans_commit_journal_pin_flush(struct journal *j, struct journal_entry_pin *_pin, u64 seq) { @@ -1064,20 +1020,19 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) goto out_reset; trans_for_each_update(trans, i) { - struct printbuf buf = PRINTBUF; enum bch_validate_flags invalid_flags = 0; if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit; - if (unlikely(bch2_bkey_invalid(c, bkey_i_to_s_c(i->k), - i->bkey_type, invalid_flags, &buf))) - ret = bch2_trans_commit_bkey_invalid(trans, invalid_flags, i, &buf); - btree_insert_entry_checks(trans, i); - printbuf_exit(&buf); - - if (ret) + ret = bch2_bkey_validate(c, bkey_i_to_s_c(i->k), + i->bkey_type, invalid_flags); + if (unlikely(ret)){ + bch2_trans_inconsistent(trans, "invalid bkey on insert from %s -> %ps\n", + trans->fn, (void *) i->ip_allocated); return ret; + } + btree_insert_entry_checks(trans, i); } for (struct jset_entry *i = trans->journal_entries; @@ -1088,13 +1043,14 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit; - if (unlikely(bch2_journal_entry_validate(c, NULL, i, - bcachefs_metadata_version_current, - CPU_BIG_ENDIAN, invalid_flags))) - ret = bch2_trans_commit_journal_entry_invalid(trans, i); - - if (ret) + ret = bch2_journal_entry_validate(c, NULL, i, + bcachefs_metadata_version_current, + CPU_BIG_ENDIAN, invalid_flags); + if (unlikely(ret)) { + bch2_trans_inconsistent(trans, "invalid journal entry on insert from %s\n", + trans->fn); return ret; + } } if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags))) { diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index e61f9695771e..b3454d4619e8 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -1364,18 +1364,10 @@ static void bch2_insert_fixup_btree_ptr(struct btree_update *as, if (unlikely(!test_bit(JOURNAL_replay_done, &c->journal.flags))) bch2_journal_key_overwritten(c, b->c.btree_id, b->c.level, insert->k.p); - if (bch2_bkey_invalid(c, bkey_i_to_s_c(insert), - btree_node_type(b), WRITE, &buf) ?: - bch2_bkey_in_btree_node(c, b, bkey_i_to_s_c(insert), &buf)) { - printbuf_reset(&buf); - prt_printf(&buf, "inserting invalid bkey\n "); - bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(insert)); - prt_printf(&buf, "\n "); - bch2_bkey_invalid(c, bkey_i_to_s_c(insert), - btree_node_type(b), WRITE, &buf); - bch2_bkey_in_btree_node(c, b, bkey_i_to_s_c(insert), &buf); - - bch2_fs_inconsistent(c, "%s", buf.buf); + if (bch2_bkey_validate(c, bkey_i_to_s_c(insert), + btree_node_type(b), BCH_VALIDATE_write) ?: + bch2_bkey_in_btree_node(c, b, bkey_i_to_s_c(insert), BCH_VALIDATE_write)) { + bch2_fs_inconsistent(c, "%s: inserting invalid bkey", __func__); dump_stack(); } diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 0087b8555ead..6a854c918496 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -250,10 +250,8 @@ restart_drop_extra_replicas: * it's been hard to reproduce, so this should give us some more * information when it does occur: */ - struct printbuf err = PRINTBUF; - int invalid = bch2_bkey_invalid(c, bkey_i_to_s_c(insert), __btree_node_type(0, m->btree_id), 0, &err); - printbuf_exit(&err); - + int invalid = bch2_bkey_validate(c, bkey_i_to_s_c(insert), __btree_node_type(0, m->btree_id), + BCH_VALIDATE_commit); if (invalid) { struct printbuf buf = PRINTBUF; diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c index d743da89308e..32bfdf19289a 100644 --- a/fs/bcachefs/dirent.c +++ b/fs/bcachefs/dirent.c @@ -100,20 +100,19 @@ const struct bch_hash_desc bch2_dirent_hash_desc = { .is_visible = dirent_is_visible, }; -int bch2_dirent_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_dirent_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k); struct qstr d_name = bch2_dirent_get_name(d); int ret = 0; - bkey_fsck_err_on(!d_name.len, c, err, - dirent_empty_name, + bkey_fsck_err_on(!d_name.len, + c, dirent_empty_name, "empty name"); - bkey_fsck_err_on(bkey_val_u64s(k.k) > dirent_val_u64s(d_name.len), c, err, - dirent_val_too_big, + bkey_fsck_err_on(bkey_val_u64s(k.k) > dirent_val_u64s(d_name.len), + c, dirent_val_too_big, "value too big (%zu > %u)", bkey_val_u64s(k.k), dirent_val_u64s(d_name.len)); @@ -121,27 +120,27 @@ int bch2_dirent_invalid(struct bch_fs *c, struct bkey_s_c k, * Check new keys don't exceed the max length * (older keys may be larger.) */ - bkey_fsck_err_on((flags & BCH_VALIDATE_commit) && d_name.len > BCH_NAME_MAX, c, err, - dirent_name_too_long, + bkey_fsck_err_on((flags & BCH_VALIDATE_commit) && d_name.len > BCH_NAME_MAX, + c, dirent_name_too_long, "dirent name too big (%u > %u)", d_name.len, BCH_NAME_MAX); - bkey_fsck_err_on(d_name.len != strnlen(d_name.name, d_name.len), c, err, - dirent_name_embedded_nul, + bkey_fsck_err_on(d_name.len != strnlen(d_name.name, d_name.len), + c, dirent_name_embedded_nul, "dirent has stray data after name's NUL"); bkey_fsck_err_on((d_name.len == 1 && !memcmp(d_name.name, ".", 1)) || - (d_name.len == 2 && !memcmp(d_name.name, "..", 2)), c, err, - dirent_name_dot_or_dotdot, + (d_name.len == 2 && !memcmp(d_name.name, "..", 2)), + c, dirent_name_dot_or_dotdot, "invalid name"); - bkey_fsck_err_on(memchr(d_name.name, '/', d_name.len), c, err, - dirent_name_has_slash, + bkey_fsck_err_on(memchr(d_name.name, '/', d_name.len), + c, dirent_name_has_slash, "name with /"); bkey_fsck_err_on(d.v->d_type != DT_SUBVOL && - le64_to_cpu(d.v->d_inum) == d.k->p.inode, c, err, - dirent_to_itself, + le64_to_cpu(d.v->d_inum) == d.k->p.inode, + c, dirent_to_itself, "dirent points to own directory"); fsck_err: return ret; diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h index 24037e6e0a09..8945145865c5 100644 --- a/fs/bcachefs/dirent.h +++ b/fs/bcachefs/dirent.h @@ -7,12 +7,11 @@ enum bch_validate_flags; extern const struct bch_hash_desc bch2_dirent_hash_desc; -int bch2_dirent_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_dirent_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); void bch2_dirent_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_dirent ((struct bkey_ops) { \ - .key_invalid = bch2_dirent_invalid, \ + .key_validate = bch2_dirent_validate, \ .val_to_text = bch2_dirent_to_text, \ .min_val_size = 16, \ }) diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c index 03a9de6c2e0a..f059cbffdf23 100644 --- a/fs/bcachefs/disk_accounting.c +++ b/fs/bcachefs/disk_accounting.c @@ -126,9 +126,8 @@ static inline bool is_zero(char *start, char *end) #define field_end(p, member) (((void *) (&p.member)) + sizeof(p.member)) -int bch2_accounting_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_accounting_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct disk_accounting_pos acc_k; bpos_to_disk_accounting_pos(&acc_k, k.k->p); @@ -144,18 +143,18 @@ int bch2_accounting_invalid(struct bch_fs *c, struct bkey_s_c k, break; case BCH_DISK_ACCOUNTING_replicas: bkey_fsck_err_on(!acc_k.replicas.nr_devs, - c, err, accounting_key_replicas_nr_devs_0, + c, accounting_key_replicas_nr_devs_0, "accounting key replicas entry with nr_devs=0"); bkey_fsck_err_on(acc_k.replicas.nr_required > acc_k.replicas.nr_devs || (acc_k.replicas.nr_required > 1 && acc_k.replicas.nr_required == acc_k.replicas.nr_devs), - c, err, accounting_key_replicas_nr_required_bad, + c, accounting_key_replicas_nr_required_bad, "accounting key replicas entry with bad nr_required"); for (unsigned i = 0; i + 1 < acc_k.replicas.nr_devs; i++) bkey_fsck_err_on(acc_k.replicas.devs[i] >= acc_k.replicas.devs[i + 1], - c, err, accounting_key_replicas_devs_unsorted, + c, accounting_key_replicas_devs_unsorted, "accounting key replicas entry with unsorted devs"); end = (void *) &acc_k.replicas + replicas_entry_bytes(&acc_k.replicas); @@ -178,7 +177,7 @@ int bch2_accounting_invalid(struct bch_fs *c, struct bkey_s_c k, } bkey_fsck_err_on(!is_zero(end, (void *) (&acc_k + 1)), - c, err, accounting_key_junk_at_end, + c, accounting_key_junk_at_end, "junk at end of accounting key"); fsck_err: return ret; diff --git a/fs/bcachefs/disk_accounting.h b/fs/bcachefs/disk_accounting.h index 3d3f25e08b69..b92f8c2e3054 100644 --- a/fs/bcachefs/disk_accounting.h +++ b/fs/bcachefs/disk_accounting.h @@ -82,14 +82,13 @@ int bch2_disk_accounting_mod(struct btree_trans *, struct disk_accounting_pos *, s64 *, unsigned, bool); int bch2_mod_dev_cached_sectors(struct btree_trans *, unsigned, s64, bool); -int bch2_accounting_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_accounting_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); void bch2_accounting_key_to_text(struct printbuf *, struct disk_accounting_pos *); void bch2_accounting_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_accounting_swab(struct bkey_s); #define bch2_bkey_ops_accounting ((struct bkey_ops) { \ - .key_invalid = bch2_accounting_invalid, \ + .key_validate = bch2_accounting_validate, \ .val_to_text = bch2_accounting_to_text, \ .swab = bch2_accounting_swab, \ .min_val_size = 8, \ diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c index 84f1cbf6497f..141a4c63142f 100644 --- a/fs/bcachefs/ec.c +++ b/fs/bcachefs/ec.c @@ -107,24 +107,23 @@ struct ec_bio { /* Stripes btree keys: */ -int bch2_stripe_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_stripe_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { const struct bch_stripe *s = bkey_s_c_to_stripe(k).v; int ret = 0; bkey_fsck_err_on(bkey_eq(k.k->p, POS_MIN) || - bpos_gt(k.k->p, POS(0, U32_MAX)), c, err, - stripe_pos_bad, + bpos_gt(k.k->p, POS(0, U32_MAX)), + c, stripe_pos_bad, "stripe at bad pos"); - bkey_fsck_err_on(bkey_val_u64s(k.k) < stripe_val_u64s(s), c, err, - stripe_val_size_bad, + bkey_fsck_err_on(bkey_val_u64s(k.k) < stripe_val_u64s(s), + c, stripe_val_size_bad, "incorrect value size (%zu < %u)", bkey_val_u64s(k.k), stripe_val_u64s(s)); - ret = bch2_bkey_ptrs_invalid(c, k, flags, err); + ret = bch2_bkey_ptrs_validate(c, k, flags); fsck_err: return ret; } diff --git a/fs/bcachefs/ec.h b/fs/bcachefs/ec.h index 84a23eeb6249..90962b3c0130 100644 --- a/fs/bcachefs/ec.h +++ b/fs/bcachefs/ec.h @@ -8,8 +8,7 @@ enum bch_validate_flags; -int bch2_stripe_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_stripe_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); void bch2_stripe_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_trigger_stripe(struct btree_trans *, enum btree_id, unsigned, @@ -17,7 +16,7 @@ int bch2_trigger_stripe(struct btree_trans *, enum btree_id, unsigned, enum btree_iter_update_trigger_flags); #define bch2_bkey_ops_stripe ((struct bkey_ops) { \ - .key_invalid = bch2_stripe_invalid, \ + .key_validate = bch2_stripe_validate, \ .val_to_text = bch2_stripe_to_text, \ .swab = bch2_ptr_swab, \ .trigger = bch2_trigger_stripe, \ diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index a268af3e52bf..ab5a7adece10 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -166,6 +166,7 @@ x(0, journal_reclaim_would_deadlock) \ x(EINVAL, fsck) \ x(BCH_ERR_fsck, fsck_fix) \ + x(BCH_ERR_fsck, fsck_delete_bkey) \ x(BCH_ERR_fsck, fsck_ignore) \ x(BCH_ERR_fsck, fsck_errors_not_fixed) \ x(BCH_ERR_fsck, fsck_repair_unimplemented) \ diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c index a62b63108820..95afa7bf2020 100644 --- a/fs/bcachefs/error.c +++ b/fs/bcachefs/error.c @@ -416,6 +416,28 @@ err: return ret; } +int __bch2_bkey_fsck_err(struct bch_fs *c, + struct bkey_s_c k, + enum bch_fsck_flags flags, + enum bch_sb_error_id err, + const char *fmt, ...) +{ + struct printbuf buf = PRINTBUF; + va_list args; + + prt_str(&buf, "invalid bkey "); + bch2_bkey_val_to_text(&buf, c, k); + prt_str(&buf, "\n "); + va_start(args, fmt); + prt_vprintf(&buf, fmt, args); + va_end(args); + prt_str(&buf, ": delete?"); + + int ret = __bch2_fsck_err(c, NULL, flags, err, "%s", buf.buf); + printbuf_exit(&buf); + return ret; +} + void bch2_flush_fsck_errs(struct bch_fs *c) { struct fsck_err_state *s, *n; diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h index 995e6bba9bad..2f1b86978f36 100644 --- a/fs/bcachefs/error.h +++ b/fs/bcachefs/error.h @@ -4,6 +4,7 @@ #include #include +#include "bkey_types.h" #include "sb-errors.h" struct bch_dev; @@ -166,24 +167,30 @@ void bch2_flush_fsck_errs(struct bch_fs *); #define fsck_err_on(cond, c, _err_type, ...) \ __fsck_err_on(cond, c, FSCK_CAN_FIX|FSCK_CAN_IGNORE, _err_type, __VA_ARGS__) -__printf(4, 0) -static inline void bch2_bkey_fsck_err(struct bch_fs *c, - struct printbuf *err_msg, - enum bch_sb_error_id err_type, - const char *fmt, ...) -{ - va_list args; +__printf(5, 6) +int __bch2_bkey_fsck_err(struct bch_fs *, + struct bkey_s_c, + enum bch_fsck_flags, + enum bch_sb_error_id, + const char *, ...); - va_start(args, fmt); - prt_vprintf(err_msg, fmt, args); - va_end(args); -} - -#define bkey_fsck_err(c, _err_msg, _err_type, ...) \ +/* + * for now, bkey fsck errors are always handled by deleting the entire key - + * this will change at some point + */ +#define bkey_fsck_err(c, _err_type, _err_msg, ...) \ do { \ - prt_printf(_err_msg, __VA_ARGS__); \ - bch2_sb_error_count(c, BCH_FSCK_ERR_##_err_type); \ - ret = -BCH_ERR_invalid_bkey; \ + if ((flags & BCH_VALIDATE_silent)) { \ + ret = -BCH_ERR_fsck_delete_bkey; \ + goto fsck_err; \ + } \ + int _ret = __bch2_bkey_fsck_err(c, k, FSCK_CAN_FIX, \ + BCH_FSCK_ERR_##_err_type, \ + _err_msg, ##__VA_ARGS__); \ + if (_ret != -BCH_ERR_fsck_fix && \ + _ret != -BCH_ERR_fsck_ignore) \ + ret = _ret; \ + ret = -BCH_ERR_fsck_delete_bkey; \ goto fsck_err; \ } while (0) diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index 07973198e35f..4419ad3e454e 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -171,17 +171,16 @@ int bch2_bkey_pick_read_device(struct bch_fs *c, struct bkey_s_c k, /* KEY_TYPE_btree_ptr: */ -int bch2_btree_ptr_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_btree_ptr_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { int ret = 0; - bkey_fsck_err_on(bkey_val_u64s(k.k) > BCH_REPLICAS_MAX, c, err, - btree_ptr_val_too_big, + bkey_fsck_err_on(bkey_val_u64s(k.k) > BCH_REPLICAS_MAX, + c, btree_ptr_val_too_big, "value too big (%zu > %u)", bkey_val_u64s(k.k), BCH_REPLICAS_MAX); - ret = bch2_bkey_ptrs_invalid(c, k, flags, err); + ret = bch2_bkey_ptrs_validate(c, k, flags); fsck_err: return ret; } @@ -192,28 +191,27 @@ void bch2_btree_ptr_to_text(struct printbuf *out, struct bch_fs *c, bch2_bkey_ptrs_to_text(out, c, k); } -int bch2_btree_ptr_v2_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_btree_ptr_v2_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_s_c_btree_ptr_v2 bp = bkey_s_c_to_btree_ptr_v2(k); int ret = 0; bkey_fsck_err_on(bkey_val_u64s(k.k) > BKEY_BTREE_PTR_VAL_U64s_MAX, - c, err, btree_ptr_v2_val_too_big, + c, btree_ptr_v2_val_too_big, "value too big (%zu > %zu)", bkey_val_u64s(k.k), BKEY_BTREE_PTR_VAL_U64s_MAX); bkey_fsck_err_on(bpos_ge(bp.v->min_key, bp.k->p), - c, err, btree_ptr_v2_min_key_bad, + c, btree_ptr_v2_min_key_bad, "min_key > key"); if (flags & BCH_VALIDATE_write) bkey_fsck_err_on(!bp.v->sectors_written, - c, err, btree_ptr_v2_written_0, + c, btree_ptr_v2_written_0, "sectors_written == 0"); - ret = bch2_bkey_ptrs_invalid(c, k, flags, err); + ret = bch2_bkey_ptrs_validate(c, k, flags); fsck_err: return ret; } @@ -399,15 +397,14 @@ bool bch2_extent_merge(struct bch_fs *c, struct bkey_s l, struct bkey_s_c r) /* KEY_TYPE_reservation: */ -int bch2_reservation_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_reservation_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_s_c_reservation r = bkey_s_c_to_reservation(k); int ret = 0; - bkey_fsck_err_on(!r.v->nr_replicas || r.v->nr_replicas > BCH_REPLICAS_MAX, c, err, - reservation_key_nr_replicas_invalid, + bkey_fsck_err_on(!r.v->nr_replicas || r.v->nr_replicas > BCH_REPLICAS_MAX, + c, reservation_key_nr_replicas_invalid, "invalid nr_replicas (%u)", r.v->nr_replicas); fsck_err: return ret; @@ -1102,14 +1099,12 @@ void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c, } } - -static int extent_ptr_invalid(struct bch_fs *c, - struct bkey_s_c k, - enum bch_validate_flags flags, - const struct bch_extent_ptr *ptr, - unsigned size_ondisk, - bool metadata, - struct printbuf *err) +static int extent_ptr_validate(struct bch_fs *c, + struct bkey_s_c k, + enum bch_validate_flags flags, + const struct bch_extent_ptr *ptr, + unsigned size_ondisk, + bool metadata) { int ret = 0; @@ -1128,28 +1123,27 @@ static int extent_ptr_invalid(struct bch_fs *c, struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); bkey_for_each_ptr(ptrs, ptr2) - bkey_fsck_err_on(ptr != ptr2 && ptr->dev == ptr2->dev, c, err, - ptr_to_duplicate_device, + bkey_fsck_err_on(ptr != ptr2 && ptr->dev == ptr2->dev, + c, ptr_to_duplicate_device, "multiple pointers to same device (%u)", ptr->dev); - bkey_fsck_err_on(bucket >= nbuckets, c, err, - ptr_after_last_bucket, + bkey_fsck_err_on(bucket >= nbuckets, + c, ptr_after_last_bucket, "pointer past last bucket (%llu > %llu)", bucket, nbuckets); - bkey_fsck_err_on(bucket < first_bucket, c, err, - ptr_before_first_bucket, + bkey_fsck_err_on(bucket < first_bucket, + c, ptr_before_first_bucket, "pointer before first bucket (%llu < %u)", bucket, first_bucket); - bkey_fsck_err_on(bucket_offset + size_ondisk > bucket_size, c, err, - ptr_spans_multiple_buckets, + bkey_fsck_err_on(bucket_offset + size_ondisk > bucket_size, + c, ptr_spans_multiple_buckets, "pointer spans multiple buckets (%u + %u > %u)", bucket_offset, size_ondisk, bucket_size); fsck_err: return ret; } -int bch2_bkey_ptrs_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_bkey_ptrs_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); const union bch_extent_entry *entry; @@ -1164,25 +1158,24 @@ int bch2_bkey_ptrs_invalid(struct bch_fs *c, struct bkey_s_c k, size_ondisk = btree_sectors(c); bkey_extent_entry_for_each(ptrs, entry) { - bkey_fsck_err_on(__extent_entry_type(entry) >= BCH_EXTENT_ENTRY_MAX, c, err, - extent_ptrs_invalid_entry, - "invalid extent entry type (got %u, max %u)", - __extent_entry_type(entry), BCH_EXTENT_ENTRY_MAX); + bkey_fsck_err_on(__extent_entry_type(entry) >= BCH_EXTENT_ENTRY_MAX, + c, extent_ptrs_invalid_entry, + "invalid extent entry type (got %u, max %u)", + __extent_entry_type(entry), BCH_EXTENT_ENTRY_MAX); bkey_fsck_err_on(bkey_is_btree_ptr(k.k) && - !extent_entry_is_ptr(entry), c, err, - btree_ptr_has_non_ptr, + !extent_entry_is_ptr(entry), + c, btree_ptr_has_non_ptr, "has non ptr field"); switch (extent_entry_type(entry)) { case BCH_EXTENT_ENTRY_ptr: - ret = extent_ptr_invalid(c, k, flags, &entry->ptr, - size_ondisk, false, err); + ret = extent_ptr_validate(c, k, flags, &entry->ptr, size_ondisk, false); if (ret) return ret; - bkey_fsck_err_on(entry->ptr.cached && have_ec, c, err, - ptr_cached_and_erasure_coded, + bkey_fsck_err_on(entry->ptr.cached && have_ec, + c, ptr_cached_and_erasure_coded, "cached, erasure coded ptr"); if (!entry->ptr.unwritten) @@ -1199,44 +1192,50 @@ int bch2_bkey_ptrs_invalid(struct bch_fs *c, struct bkey_s_c k, case BCH_EXTENT_ENTRY_crc128: crc = bch2_extent_crc_unpack(k.k, entry_to_crc(entry)); - bkey_fsck_err_on(crc.offset + crc.live_size > crc.uncompressed_size, c, err, - ptr_crc_uncompressed_size_too_small, + bkey_fsck_err_on(crc.offset + crc.live_size > crc.uncompressed_size, + c, ptr_crc_uncompressed_size_too_small, "checksum offset + key size > uncompressed size"); - bkey_fsck_err_on(!bch2_checksum_type_valid(c, crc.csum_type), c, err, - ptr_crc_csum_type_unknown, + bkey_fsck_err_on(!bch2_checksum_type_valid(c, crc.csum_type), + c, ptr_crc_csum_type_unknown, "invalid checksum type"); - bkey_fsck_err_on(crc.compression_type >= BCH_COMPRESSION_TYPE_NR, c, err, - ptr_crc_compression_type_unknown, + bkey_fsck_err_on(crc.compression_type >= BCH_COMPRESSION_TYPE_NR, + c, ptr_crc_compression_type_unknown, "invalid compression type"); if (bch2_csum_type_is_encryption(crc.csum_type)) { if (nonce == UINT_MAX) nonce = crc.offset + crc.nonce; else if (nonce != crc.offset + crc.nonce) - bkey_fsck_err(c, err, ptr_crc_nonce_mismatch, + bkey_fsck_err(c, ptr_crc_nonce_mismatch, "incorrect nonce"); } - bkey_fsck_err_on(crc_since_last_ptr, c, err, - ptr_crc_redundant, + bkey_fsck_err_on(crc_since_last_ptr, + c, ptr_crc_redundant, "redundant crc entry"); crc_since_last_ptr = true; bkey_fsck_err_on(crc_is_encoded(crc) && (crc.uncompressed_size > c->opts.encoded_extent_max >> 9) && - (flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit)), c, err, - ptr_crc_uncompressed_size_too_big, + (flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit)), + c, ptr_crc_uncompressed_size_too_big, "too large encoded extent"); size_ondisk = crc.compressed_size; break; case BCH_EXTENT_ENTRY_stripe_ptr: - bkey_fsck_err_on(have_ec, c, err, - ptr_stripe_redundant, + bkey_fsck_err_on(have_ec, + c, ptr_stripe_redundant, "redundant stripe entry"); have_ec = true; break; case BCH_EXTENT_ENTRY_rebalance: { + /* + * this shouldn't be a fsck error, for forward + * compatibility; the rebalance code should just refetch + * the compression opt if it's unknown + */ +#if 0 const struct bch_extent_rebalance *r = &entry->rebalance; if (!bch2_compression_opt_valid(r->compression)) { @@ -1245,28 +1244,29 @@ int bch2_bkey_ptrs_invalid(struct bch_fs *c, struct bkey_s_c k, opt.type, opt.level); return -BCH_ERR_invalid_bkey; } +#endif break; } } } - bkey_fsck_err_on(!nr_ptrs, c, err, - extent_ptrs_no_ptrs, + bkey_fsck_err_on(!nr_ptrs, + c, extent_ptrs_no_ptrs, "no ptrs"); - bkey_fsck_err_on(nr_ptrs > BCH_BKEY_PTRS_MAX, c, err, - extent_ptrs_too_many_ptrs, + bkey_fsck_err_on(nr_ptrs > BCH_BKEY_PTRS_MAX, + c, extent_ptrs_too_many_ptrs, "too many ptrs: %u > %u", nr_ptrs, BCH_BKEY_PTRS_MAX); - bkey_fsck_err_on(have_written && have_unwritten, c, err, - extent_ptrs_written_and_unwritten, + bkey_fsck_err_on(have_written && have_unwritten, + c, extent_ptrs_written_and_unwritten, "extent with unwritten and written ptrs"); - bkey_fsck_err_on(k.k->type != KEY_TYPE_extent && have_unwritten, c, err, - extent_ptrs_unwritten, + bkey_fsck_err_on(k.k->type != KEY_TYPE_extent && have_unwritten, + c, extent_ptrs_unwritten, "has unwritten ptrs"); - bkey_fsck_err_on(crc_since_last_ptr, c, err, - extent_ptrs_redundant_crc, + bkey_fsck_err_on(crc_since_last_ptr, + c, extent_ptrs_redundant_crc, "redundant crc entry"); - bkey_fsck_err_on(have_ec, c, err, - extent_ptrs_redundant_stripe, + bkey_fsck_err_on(have_ec, + c, extent_ptrs_redundant_stripe, "redundant stripe entry"); fsck_err: return ret; diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h index facdb8a86eec..1a6ddee48041 100644 --- a/fs/bcachefs/extents.h +++ b/fs/bcachefs/extents.h @@ -409,26 +409,26 @@ int bch2_bkey_pick_read_device(struct bch_fs *, struct bkey_s_c, /* KEY_TYPE_btree_ptr: */ -int bch2_btree_ptr_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_btree_ptr_validate(struct bch_fs *, struct bkey_s_c, + enum bch_validate_flags); void bch2_btree_ptr_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); -int bch2_btree_ptr_v2_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_btree_ptr_v2_validate(struct bch_fs *, struct bkey_s_c, + enum bch_validate_flags); void bch2_btree_ptr_v2_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_btree_ptr_v2_compat(enum btree_id, unsigned, unsigned, int, struct bkey_s); #define bch2_bkey_ops_btree_ptr ((struct bkey_ops) { \ - .key_invalid = bch2_btree_ptr_invalid, \ + .key_validate = bch2_btree_ptr_validate, \ .val_to_text = bch2_btree_ptr_to_text, \ .swab = bch2_ptr_swab, \ .trigger = bch2_trigger_extent, \ }) #define bch2_bkey_ops_btree_ptr_v2 ((struct bkey_ops) { \ - .key_invalid = bch2_btree_ptr_v2_invalid, \ + .key_validate = bch2_btree_ptr_v2_validate, \ .val_to_text = bch2_btree_ptr_v2_to_text, \ .swab = bch2_ptr_swab, \ .compat = bch2_btree_ptr_v2_compat, \ @@ -441,7 +441,7 @@ void bch2_btree_ptr_v2_compat(enum btree_id, unsigned, unsigned, bool bch2_extent_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); #define bch2_bkey_ops_extent ((struct bkey_ops) { \ - .key_invalid = bch2_bkey_ptrs_invalid, \ + .key_validate = bch2_bkey_ptrs_validate, \ .val_to_text = bch2_bkey_ptrs_to_text, \ .swab = bch2_ptr_swab, \ .key_normalize = bch2_extent_normalize, \ @@ -451,13 +451,13 @@ bool bch2_extent_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); /* KEY_TYPE_reservation: */ -int bch2_reservation_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_reservation_validate(struct bch_fs *, struct bkey_s_c, + enum bch_validate_flags); void bch2_reservation_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); bool bch2_reservation_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); #define bch2_bkey_ops_reservation ((struct bkey_ops) { \ - .key_invalid = bch2_reservation_invalid, \ + .key_validate = bch2_reservation_validate, \ .val_to_text = bch2_reservation_to_text, \ .key_merge = bch2_reservation_merge, \ .trigger = bch2_trigger_reservation, \ @@ -683,8 +683,8 @@ bool bch2_extent_normalize(struct bch_fs *, struct bkey_s); void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *, const struct bch_extent_ptr *); void bch2_bkey_ptrs_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); -int bch2_bkey_ptrs_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_bkey_ptrs_validate(struct bch_fs *, struct bkey_s_c, + enum bch_validate_flags); void bch2_ptr_swab(struct bkey_s); diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c index 1e20020eadd1..2be6be33afa3 100644 --- a/fs/bcachefs/inode.c +++ b/fs/bcachefs/inode.c @@ -434,100 +434,98 @@ struct bkey_i *bch2_inode_to_v3(struct btree_trans *trans, struct bkey_i *k) return &inode_p->inode.k_i; } -static int __bch2_inode_invalid(struct bch_fs *c, struct bkey_s_c k, struct printbuf *err) +static int __bch2_inode_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bch_inode_unpacked unpacked; int ret = 0; - bkey_fsck_err_on(k.k->p.inode, c, err, - inode_pos_inode_nonzero, + bkey_fsck_err_on(k.k->p.inode, + c, inode_pos_inode_nonzero, "nonzero k.p.inode"); - bkey_fsck_err_on(k.k->p.offset < BLOCKDEV_INODE_MAX, c, err, - inode_pos_blockdev_range, + bkey_fsck_err_on(k.k->p.offset < BLOCKDEV_INODE_MAX, + c, inode_pos_blockdev_range, "fs inode in blockdev range"); - bkey_fsck_err_on(bch2_inode_unpack(k, &unpacked), c, err, - inode_unpack_error, + bkey_fsck_err_on(bch2_inode_unpack(k, &unpacked), + c, inode_unpack_error, "invalid variable length fields"); - bkey_fsck_err_on(unpacked.bi_data_checksum >= BCH_CSUM_OPT_NR + 1, c, err, - inode_checksum_type_invalid, + bkey_fsck_err_on(unpacked.bi_data_checksum >= BCH_CSUM_OPT_NR + 1, + c, inode_checksum_type_invalid, "invalid data checksum type (%u >= %u", unpacked.bi_data_checksum, BCH_CSUM_OPT_NR + 1); bkey_fsck_err_on(unpacked.bi_compression && - !bch2_compression_opt_valid(unpacked.bi_compression - 1), c, err, - inode_compression_type_invalid, + !bch2_compression_opt_valid(unpacked.bi_compression - 1), + c, inode_compression_type_invalid, "invalid compression opt %u", unpacked.bi_compression - 1); bkey_fsck_err_on((unpacked.bi_flags & BCH_INODE_unlinked) && - unpacked.bi_nlink != 0, c, err, - inode_unlinked_but_nlink_nonzero, + unpacked.bi_nlink != 0, + c, inode_unlinked_but_nlink_nonzero, "flagged as unlinked but bi_nlink != 0"); - bkey_fsck_err_on(unpacked.bi_subvol && !S_ISDIR(unpacked.bi_mode), c, err, - inode_subvol_root_but_not_dir, + bkey_fsck_err_on(unpacked.bi_subvol && !S_ISDIR(unpacked.bi_mode), + c, inode_subvol_root_but_not_dir, "subvolume root but not a directory"); fsck_err: return ret; } -int bch2_inode_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_inode_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_s_c_inode inode = bkey_s_c_to_inode(k); int ret = 0; - bkey_fsck_err_on(INODE_STR_HASH(inode.v) >= BCH_STR_HASH_NR, c, err, - inode_str_hash_invalid, + bkey_fsck_err_on(INODE_STR_HASH(inode.v) >= BCH_STR_HASH_NR, + c, inode_str_hash_invalid, "invalid str hash type (%llu >= %u)", INODE_STR_HASH(inode.v), BCH_STR_HASH_NR); - ret = __bch2_inode_invalid(c, k, err); + ret = __bch2_inode_validate(c, k, flags); fsck_err: return ret; } -int bch2_inode_v2_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_inode_v2_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_s_c_inode_v2 inode = bkey_s_c_to_inode_v2(k); int ret = 0; - bkey_fsck_err_on(INODEv2_STR_HASH(inode.v) >= BCH_STR_HASH_NR, c, err, - inode_str_hash_invalid, + bkey_fsck_err_on(INODEv2_STR_HASH(inode.v) >= BCH_STR_HASH_NR, + c, inode_str_hash_invalid, "invalid str hash type (%llu >= %u)", INODEv2_STR_HASH(inode.v), BCH_STR_HASH_NR); - ret = __bch2_inode_invalid(c, k, err); + ret = __bch2_inode_validate(c, k, flags); fsck_err: return ret; } -int bch2_inode_v3_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_inode_v3_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_s_c_inode_v3 inode = bkey_s_c_to_inode_v3(k); int ret = 0; bkey_fsck_err_on(INODEv3_FIELDS_START(inode.v) < INODEv3_FIELDS_START_INITIAL || - INODEv3_FIELDS_START(inode.v) > bkey_val_u64s(inode.k), c, err, - inode_v3_fields_start_bad, + INODEv3_FIELDS_START(inode.v) > bkey_val_u64s(inode.k), + c, inode_v3_fields_start_bad, "invalid fields_start (got %llu, min %u max %zu)", INODEv3_FIELDS_START(inode.v), INODEv3_FIELDS_START_INITIAL, bkey_val_u64s(inode.k)); - bkey_fsck_err_on(INODEv3_STR_HASH(inode.v) >= BCH_STR_HASH_NR, c, err, - inode_str_hash_invalid, + bkey_fsck_err_on(INODEv3_STR_HASH(inode.v) >= BCH_STR_HASH_NR, + c, inode_str_hash_invalid, "invalid str hash type (%llu >= %u)", INODEv3_STR_HASH(inode.v), BCH_STR_HASH_NR); - ret = __bch2_inode_invalid(c, k, err); + ret = __bch2_inode_validate(c, k, flags); fsck_err: return ret; } @@ -625,14 +623,13 @@ int bch2_trigger_inode(struct btree_trans *trans, return 0; } -int bch2_inode_generation_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_inode_generation_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { int ret = 0; - bkey_fsck_err_on(k.k->p.inode, c, err, - inode_pos_inode_nonzero, + bkey_fsck_err_on(k.k->p.inode, + c, inode_pos_inode_nonzero, "nonzero k.p.inode"); fsck_err: return ret; diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h index da0e4a745099..f1fcb4c58039 100644 --- a/fs/bcachefs/inode.h +++ b/fs/bcachefs/inode.h @@ -9,12 +9,12 @@ enum bch_validate_flags; extern const char * const bch2_inode_opts[]; -int bch2_inode_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); -int bch2_inode_v2_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); -int bch2_inode_v3_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_inode_validate(struct bch_fs *, struct bkey_s_c, + enum bch_validate_flags); +int bch2_inode_v2_validate(struct bch_fs *, struct bkey_s_c, + enum bch_validate_flags); +int bch2_inode_v3_validate(struct bch_fs *, struct bkey_s_c, + enum bch_validate_flags); void bch2_inode_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_trigger_inode(struct btree_trans *, enum btree_id, unsigned, @@ -22,21 +22,21 @@ int bch2_trigger_inode(struct btree_trans *, enum btree_id, unsigned, enum btree_iter_update_trigger_flags); #define bch2_bkey_ops_inode ((struct bkey_ops) { \ - .key_invalid = bch2_inode_invalid, \ + .key_validate = bch2_inode_validate, \ .val_to_text = bch2_inode_to_text, \ .trigger = bch2_trigger_inode, \ .min_val_size = 16, \ }) #define bch2_bkey_ops_inode_v2 ((struct bkey_ops) { \ - .key_invalid = bch2_inode_v2_invalid, \ + .key_validate = bch2_inode_v2_validate, \ .val_to_text = bch2_inode_to_text, \ .trigger = bch2_trigger_inode, \ .min_val_size = 32, \ }) #define bch2_bkey_ops_inode_v3 ((struct bkey_ops) { \ - .key_invalid = bch2_inode_v3_invalid, \ + .key_validate = bch2_inode_v3_validate, \ .val_to_text = bch2_inode_to_text, \ .trigger = bch2_trigger_inode, \ .min_val_size = 48, \ @@ -49,12 +49,12 @@ static inline bool bkey_is_inode(const struct bkey *k) k->type == KEY_TYPE_inode_v3; } -int bch2_inode_generation_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_inode_generation_validate(struct bch_fs *, struct bkey_s_c, + enum bch_validate_flags); void bch2_inode_generation_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_inode_generation ((struct bkey_ops) { \ - .key_invalid = bch2_inode_generation_invalid, \ + .key_validate = bch2_inode_generation_validate, \ .val_to_text = bch2_inode_generation_to_text, \ .min_val_size = 8, \ }) diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index 7a833a3f1c63..7664b68e6a15 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -332,7 +332,6 @@ static int journal_validate_key(struct bch_fs *c, { int write = flags & BCH_VALIDATE_write; void *next = vstruct_next(entry); - struct printbuf buf = PRINTBUF; int ret = 0; if (journal_entry_err_on(!k->k.u64s, @@ -368,34 +367,21 @@ static int journal_validate_key(struct bch_fs *c, bch2_bkey_compat(level, btree_id, version, big_endian, write, NULL, bkey_to_packed(k)); - if (bch2_bkey_invalid(c, bkey_i_to_s_c(k), - __btree_node_type(level, btree_id), write, &buf)) { - printbuf_reset(&buf); - journal_entry_err_msg(&buf, version, jset, entry); - prt_newline(&buf); - printbuf_indent_add(&buf, 2); - - bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(k)); - prt_newline(&buf); - bch2_bkey_invalid(c, bkey_i_to_s_c(k), - __btree_node_type(level, btree_id), write, &buf); - - mustfix_fsck_err(c, journal_entry_bkey_invalid, - "%s", buf.buf); - + ret = bch2_bkey_validate(c, bkey_i_to_s_c(k), + __btree_node_type(level, btree_id), write); + if (ret == -BCH_ERR_fsck_delete_bkey) { le16_add_cpu(&entry->u64s, -((u16) k->k.u64s)); memmove(k, bkey_next(k), next - (void *) bkey_next(k)); journal_entry_null_range(vstruct_next(entry), next); - - printbuf_exit(&buf); return FSCK_DELETED_KEY; } + if (ret) + goto fsck_err; if (write) bch2_bkey_compat(level, btree_id, version, big_endian, write, NULL, bkey_to_packed(k)); fsck_err: - printbuf_exit(&buf); return ret; } diff --git a/fs/bcachefs/lru.c b/fs/bcachefs/lru.c index 83b1586cb371..96f2f4f8c397 100644 --- a/fs/bcachefs/lru.c +++ b/fs/bcachefs/lru.c @@ -10,14 +10,13 @@ #include "recovery.h" /* KEY_TYPE_lru is obsolete: */ -int bch2_lru_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_lru_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { int ret = 0; - bkey_fsck_err_on(!lru_pos_time(k.k->p), c, err, - lru_entry_at_time_0, + bkey_fsck_err_on(!lru_pos_time(k.k->p), + c, lru_entry_at_time_0, "lru entry at time=0"); fsck_err: return ret; diff --git a/fs/bcachefs/lru.h b/fs/bcachefs/lru.h index 5bd8974a7f11..e6a7d8241bb8 100644 --- a/fs/bcachefs/lru.h +++ b/fs/bcachefs/lru.h @@ -33,14 +33,13 @@ static inline enum bch_lru_type lru_type(struct bkey_s_c l) return BCH_LRU_read; } -int bch2_lru_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_lru_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); void bch2_lru_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_lru_pos_to_text(struct printbuf *, struct bpos); #define bch2_bkey_ops_lru ((struct bkey_ops) { \ - .key_invalid = bch2_lru_invalid, \ + .key_validate = bch2_lru_validate, \ .val_to_text = bch2_lru_to_text, \ .min_val_size = 8, \ }) diff --git a/fs/bcachefs/quota.c b/fs/bcachefs/quota.c index a0cca8b70e0a..c32a05e252e2 100644 --- a/fs/bcachefs/quota.c +++ b/fs/bcachefs/quota.c @@ -59,13 +59,13 @@ const struct bch_sb_field_ops bch_sb_field_ops_quota = { .to_text = bch2_sb_quota_to_text, }; -int bch2_quota_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, struct printbuf *err) +int bch2_quota_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { int ret = 0; - bkey_fsck_err_on(k.k->p.inode >= QTYP_NR, c, err, - quota_type_invalid, + bkey_fsck_err_on(k.k->p.inode >= QTYP_NR, + c, quota_type_invalid, "invalid quota type (%llu >= %u)", k.k->p.inode, QTYP_NR); fsck_err: diff --git a/fs/bcachefs/quota.h b/fs/bcachefs/quota.h index 02d37a332218..a62abcc5332a 100644 --- a/fs/bcachefs/quota.h +++ b/fs/bcachefs/quota.h @@ -8,12 +8,11 @@ enum bch_validate_flags; extern const struct bch_sb_field_ops bch_sb_field_ops_quota; -int bch2_quota_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_quota_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); void bch2_quota_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_quota ((struct bkey_ops) { \ - .key_invalid = bch2_quota_invalid, \ + .key_validate = bch2_quota_validate, \ .val_to_text = bch2_quota_to_text, \ .min_val_size = 32, \ }) diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c index 5f92715e1525..e59c0abb4772 100644 --- a/fs/bcachefs/reflink.c +++ b/fs/bcachefs/reflink.c @@ -29,15 +29,14 @@ static inline unsigned bkey_type_to_indirect(const struct bkey *k) /* reflink pointers */ -int bch2_reflink_p_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_reflink_p_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k); int ret = 0; bkey_fsck_err_on(le64_to_cpu(p.v->idx) < le32_to_cpu(p.v->front_pad), - c, err, reflink_p_front_pad_bad, + c, reflink_p_front_pad_bad, "idx < front_pad (%llu < %u)", le64_to_cpu(p.v->idx), le32_to_cpu(p.v->front_pad)); fsck_err: @@ -256,11 +255,10 @@ int bch2_trigger_reflink_p(struct btree_trans *trans, /* indirect extents */ -int bch2_reflink_v_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_reflink_v_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { - return bch2_bkey_ptrs_invalid(c, k, flags, err); + return bch2_bkey_ptrs_validate(c, k, flags); } void bch2_reflink_v_to_text(struct printbuf *out, struct bch_fs *c, @@ -311,9 +309,8 @@ int bch2_trigger_reflink_v(struct btree_trans *trans, /* indirect inline data */ -int bch2_indirect_inline_data_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_indirect_inline_data_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { return 0; } diff --git a/fs/bcachefs/reflink.h b/fs/bcachefs/reflink.h index e894f3a2c67a..51afe11d8ed6 100644 --- a/fs/bcachefs/reflink.h +++ b/fs/bcachefs/reflink.h @@ -4,41 +4,37 @@ enum bch_validate_flags; -int bch2_reflink_p_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); -void bch2_reflink_p_to_text(struct printbuf *, struct bch_fs *, - struct bkey_s_c); +int bch2_reflink_p_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +void bch2_reflink_p_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); bool bch2_reflink_p_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); int bch2_trigger_reflink_p(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, enum btree_iter_update_trigger_flags); #define bch2_bkey_ops_reflink_p ((struct bkey_ops) { \ - .key_invalid = bch2_reflink_p_invalid, \ + .key_validate = bch2_reflink_p_validate, \ .val_to_text = bch2_reflink_p_to_text, \ .key_merge = bch2_reflink_p_merge, \ .trigger = bch2_trigger_reflink_p, \ .min_val_size = 16, \ }) -int bch2_reflink_v_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); -void bch2_reflink_v_to_text(struct printbuf *, struct bch_fs *, - struct bkey_s_c); +int bch2_reflink_v_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +void bch2_reflink_v_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_trigger_reflink_v(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, enum btree_iter_update_trigger_flags); #define bch2_bkey_ops_reflink_v ((struct bkey_ops) { \ - .key_invalid = bch2_reflink_v_invalid, \ + .key_validate = bch2_reflink_v_validate, \ .val_to_text = bch2_reflink_v_to_text, \ .swab = bch2_ptr_swab, \ .trigger = bch2_trigger_reflink_v, \ .min_val_size = 8, \ }) -int bch2_indirect_inline_data_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_indirect_inline_data_validate(struct bch_fs *, struct bkey_s_c, + enum bch_validate_flags); void bch2_indirect_inline_data_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_trigger_indirect_inline_data(struct btree_trans *, @@ -47,7 +43,7 @@ int bch2_trigger_indirect_inline_data(struct btree_trans *, enum btree_iter_update_trigger_flags); #define bch2_bkey_ops_indirect_inline_data ((struct bkey_ops) { \ - .key_invalid = bch2_indirect_inline_data_invalid, \ + .key_validate = bch2_indirect_inline_data_validate, \ .val_to_text = bch2_indirect_inline_data_to_text, \ .trigger = bch2_trigger_indirect_inline_data, \ .min_val_size = 8, \ diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c index 96744b1a76f5..8b18a9b483a4 100644 --- a/fs/bcachefs/snapshot.c +++ b/fs/bcachefs/snapshot.c @@ -31,15 +31,14 @@ void bch2_snapshot_tree_to_text(struct printbuf *out, struct bch_fs *c, le32_to_cpu(t.v->root_snapshot)); } -int bch2_snapshot_tree_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_snapshot_tree_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { int ret = 0; bkey_fsck_err_on(bkey_gt(k.k->p, POS(0, U32_MAX)) || - bkey_lt(k.k->p, POS(0, 1)), c, err, - snapshot_tree_pos_bad, + bkey_lt(k.k->p, POS(0, 1)), + c, snapshot_tree_pos_bad, "bad pos"); fsck_err: return ret; @@ -225,55 +224,54 @@ void bch2_snapshot_to_text(struct printbuf *out, struct bch_fs *c, le32_to_cpu(s.v->skip[2])); } -int bch2_snapshot_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_snapshot_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_s_c_snapshot s; u32 i, id; int ret = 0; bkey_fsck_err_on(bkey_gt(k.k->p, POS(0, U32_MAX)) || - bkey_lt(k.k->p, POS(0, 1)), c, err, - snapshot_pos_bad, + bkey_lt(k.k->p, POS(0, 1)), + c, snapshot_pos_bad, "bad pos"); s = bkey_s_c_to_snapshot(k); id = le32_to_cpu(s.v->parent); - bkey_fsck_err_on(id && id <= k.k->p.offset, c, err, - snapshot_parent_bad, + bkey_fsck_err_on(id && id <= k.k->p.offset, + c, snapshot_parent_bad, "bad parent node (%u <= %llu)", id, k.k->p.offset); - bkey_fsck_err_on(le32_to_cpu(s.v->children[0]) < le32_to_cpu(s.v->children[1]), c, err, - snapshot_children_not_normalized, + bkey_fsck_err_on(le32_to_cpu(s.v->children[0]) < le32_to_cpu(s.v->children[1]), + c, snapshot_children_not_normalized, "children not normalized"); - bkey_fsck_err_on(s.v->children[0] && s.v->children[0] == s.v->children[1], c, err, - snapshot_child_duplicate, + bkey_fsck_err_on(s.v->children[0] && s.v->children[0] == s.v->children[1], + c, snapshot_child_duplicate, "duplicate child nodes"); for (i = 0; i < 2; i++) { id = le32_to_cpu(s.v->children[i]); - bkey_fsck_err_on(id >= k.k->p.offset, c, err, - snapshot_child_bad, + bkey_fsck_err_on(id >= k.k->p.offset, + c, snapshot_child_bad, "bad child node (%u >= %llu)", id, k.k->p.offset); } if (bkey_val_bytes(k.k) > offsetof(struct bch_snapshot, skip)) { bkey_fsck_err_on(le32_to_cpu(s.v->skip[0]) > le32_to_cpu(s.v->skip[1]) || - le32_to_cpu(s.v->skip[1]) > le32_to_cpu(s.v->skip[2]), c, err, - snapshot_skiplist_not_normalized, + le32_to_cpu(s.v->skip[1]) > le32_to_cpu(s.v->skip[2]), + c, snapshot_skiplist_not_normalized, "skiplist not normalized"); for (i = 0; i < ARRAY_SIZE(s.v->skip); i++) { id = le32_to_cpu(s.v->skip[i]); - bkey_fsck_err_on(id && id < le32_to_cpu(s.v->parent), c, err, - snapshot_skiplist_bad, + bkey_fsck_err_on(id && id < le32_to_cpu(s.v->parent), + c, snapshot_skiplist_bad, "bad skiplist node %u", id); } } diff --git a/fs/bcachefs/snapshot.h b/fs/bcachefs/snapshot.h index 31b0ee03e962..eb5ef64221d6 100644 --- a/fs/bcachefs/snapshot.h +++ b/fs/bcachefs/snapshot.h @@ -5,11 +5,11 @@ enum bch_validate_flags; void bch2_snapshot_tree_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); -int bch2_snapshot_tree_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_snapshot_tree_validate(struct bch_fs *, struct bkey_s_c, + enum bch_validate_flags); #define bch2_bkey_ops_snapshot_tree ((struct bkey_ops) { \ - .key_invalid = bch2_snapshot_tree_invalid, \ + .key_validate = bch2_snapshot_tree_validate, \ .val_to_text = bch2_snapshot_tree_to_text, \ .min_val_size = 8, \ }) @@ -19,14 +19,13 @@ struct bkey_i_snapshot_tree *__bch2_snapshot_tree_create(struct btree_trans *); int bch2_snapshot_tree_lookup(struct btree_trans *, u32, struct bch_snapshot_tree *); void bch2_snapshot_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); -int bch2_snapshot_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_snapshot_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); int bch2_mark_snapshot(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, enum btree_iter_update_trigger_flags); #define bch2_bkey_ops_snapshot ((struct bkey_ops) { \ - .key_invalid = bch2_snapshot_invalid, \ + .key_validate = bch2_snapshot_validate, \ .val_to_text = bch2_snapshot_to_text, \ .trigger = bch2_mark_snapshot, \ .min_val_size = 24, \ diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c index f56720b55862..dbe834cb349f 100644 --- a/fs/bcachefs/subvolume.c +++ b/fs/bcachefs/subvolume.c @@ -207,23 +207,23 @@ int bch2_check_subvol_children(struct bch_fs *c) /* Subvolumes: */ -int bch2_subvolume_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, struct printbuf *err) +int bch2_subvolume_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_s_c_subvolume subvol = bkey_s_c_to_subvolume(k); int ret = 0; bkey_fsck_err_on(bkey_lt(k.k->p, SUBVOL_POS_MIN) || - bkey_gt(k.k->p, SUBVOL_POS_MAX), c, err, - subvol_pos_bad, + bkey_gt(k.k->p, SUBVOL_POS_MAX), + c, subvol_pos_bad, "invalid pos"); - bkey_fsck_err_on(!subvol.v->snapshot, c, err, - subvol_snapshot_bad, + bkey_fsck_err_on(!subvol.v->snapshot, + c, subvol_snapshot_bad, "invalid snapshot"); - bkey_fsck_err_on(!subvol.v->inode, c, err, - subvol_inode_bad, + bkey_fsck_err_on(!subvol.v->inode, + c, subvol_inode_bad, "invalid inode"); fsck_err: return ret; diff --git a/fs/bcachefs/subvolume.h b/fs/bcachefs/subvolume.h index afa5e871efb2..a8299ba2cab2 100644 --- a/fs/bcachefs/subvolume.h +++ b/fs/bcachefs/subvolume.h @@ -10,15 +10,14 @@ enum bch_validate_flags; int bch2_check_subvols(struct bch_fs *); int bch2_check_subvol_children(struct bch_fs *); -int bch2_subvolume_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_subvolume_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); void bch2_subvolume_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_subvolume_trigger(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, enum btree_iter_update_trigger_flags); #define bch2_bkey_ops_subvolume ((struct bkey_ops) { \ - .key_invalid = bch2_subvolume_invalid, \ + .key_validate = bch2_subvolume_validate, \ .val_to_text = bch2_subvolume_to_text, \ .trigger = bch2_subvolume_trigger, \ .min_val_size = 16, \ diff --git a/fs/bcachefs/xattr.c b/fs/bcachefs/xattr.c index c11bf6dacc2c..f2b4c17a0307 100644 --- a/fs/bcachefs/xattr.c +++ b/fs/bcachefs/xattr.c @@ -70,17 +70,16 @@ const struct bch_hash_desc bch2_xattr_hash_desc = { .cmp_bkey = xattr_cmp_bkey, }; -int bch2_xattr_invalid(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, - struct printbuf *err) +int bch2_xattr_validate(struct bch_fs *c, struct bkey_s_c k, + enum bch_validate_flags flags) { struct bkey_s_c_xattr xattr = bkey_s_c_to_xattr(k); unsigned val_u64s = xattr_val_u64s(xattr.v->x_name_len, le16_to_cpu(xattr.v->x_val_len)); int ret = 0; - bkey_fsck_err_on(bkey_val_u64s(k.k) < val_u64s, c, err, - xattr_val_size_too_small, + bkey_fsck_err_on(bkey_val_u64s(k.k) < val_u64s, + c, xattr_val_size_too_small, "value too small (%zu < %u)", bkey_val_u64s(k.k), val_u64s); @@ -88,17 +87,17 @@ int bch2_xattr_invalid(struct bch_fs *c, struct bkey_s_c k, val_u64s = xattr_val_u64s(xattr.v->x_name_len, le16_to_cpu(xattr.v->x_val_len) + 4); - bkey_fsck_err_on(bkey_val_u64s(k.k) > val_u64s, c, err, - xattr_val_size_too_big, + bkey_fsck_err_on(bkey_val_u64s(k.k) > val_u64s, + c, xattr_val_size_too_big, "value too big (%zu > %u)", bkey_val_u64s(k.k), val_u64s); - bkey_fsck_err_on(!bch2_xattr_type_to_handler(xattr.v->x_type), c, err, - xattr_invalid_type, + bkey_fsck_err_on(!bch2_xattr_type_to_handler(xattr.v->x_type), + c, xattr_invalid_type, "invalid type (%u)", xattr.v->x_type); - bkey_fsck_err_on(memchr(xattr.v->x_name, '\0', xattr.v->x_name_len), c, err, - xattr_name_invalid_chars, + bkey_fsck_err_on(memchr(xattr.v->x_name, '\0', xattr.v->x_name_len), + c, xattr_name_invalid_chars, "xattr name has invalid characters"); fsck_err: return ret; diff --git a/fs/bcachefs/xattr.h b/fs/bcachefs/xattr.h index 1574b9eb4c85..c188a5ad64ce 100644 --- a/fs/bcachefs/xattr.h +++ b/fs/bcachefs/xattr.h @@ -6,12 +6,11 @@ extern const struct bch_hash_desc bch2_xattr_hash_desc; -int bch2_xattr_invalid(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, struct printbuf *); +int bch2_xattr_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); void bch2_xattr_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_xattr ((struct bkey_ops) { \ - .key_invalid = bch2_xattr_invalid, \ + .key_validate = bch2_xattr_validate, \ .val_to_text = bch2_xattr_to_text, \ .min_val_size = 8, \ }) From 5132b99bb62664c02bd6c0dd62ad3fedc75294d8 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 12 Aug 2024 02:35:10 -0400 Subject: [PATCH 252/562] bcachefs: Kill __bch2_accounting_mem_mod() The next patch will be adding a disk accounting counter type which is not kept in the in-memory eytzinger tree. As prep, fold __bch2_accounting_mem_mod() into bch2_accounting_mem_mod_locked() so that we can check for that counter type and bail out without calling bpos_to_disk_accounting_pos() twice. Signed-off-by: Kent Overstreet --- fs/bcachefs/btree_trans_commit.c | 4 +- fs/bcachefs/disk_accounting.c | 4 +- fs/bcachefs/disk_accounting.h | 68 +++++++++++++++----------------- 3 files changed, 35 insertions(+), 41 deletions(-) diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index 1a1e9d2036da..a0101d9c5d83 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -712,7 +712,7 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, a->k.version = journal_pos_to_bversion(&trans->journal_res, (u64 *) entry - (u64 *) trans->journal_entries); BUG_ON(bversion_zero(a->k.version)); - ret = bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), false); + ret = bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), false, false); if (ret) goto revert_fs_usage; } @@ -798,7 +798,7 @@ revert_fs_usage: struct bkey_s_accounting a = bkey_i_to_s_accounting(entry2->start); bch2_accounting_neg(a); - bch2_accounting_mem_mod_locked(trans, a.c, false); + bch2_accounting_mem_mod_locked(trans, a.c, false, false); bch2_accounting_neg(a); } percpu_up_read(&c->mark_lock); diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c index f059cbffdf23..e57b40623cd9 100644 --- a/fs/bcachefs/disk_accounting.c +++ b/fs/bcachefs/disk_accounting.c @@ -566,7 +566,7 @@ int bch2_gc_accounting_done(struct bch_fs *c) struct { __BKEY_PADDED(k, BCH_ACCOUNTING_MAX_COUNTERS); } k_i; accounting_key_init(&k_i.k, &acc_k, src_v, nr); - bch2_accounting_mem_mod_locked(trans, bkey_i_to_s_c_accounting(&k_i.k), false); + bch2_accounting_mem_mod_locked(trans, bkey_i_to_s_c_accounting(&k_i.k), false, false); preempt_disable(); struct bch_fs_usage_base *dst = this_cpu_ptr(c->usage); @@ -595,7 +595,7 @@ static int accounting_read_key(struct btree_trans *trans, struct bkey_s_c k) return 0; percpu_down_read(&c->mark_lock); - int ret = __bch2_accounting_mem_mod(c, bkey_s_c_to_accounting(k), false); + int ret = bch2_accounting_mem_mod_locked(trans, bkey_s_c_to_accounting(k), false, true); percpu_up_read(&c->mark_lock); if (bch2_accounting_key_is_zero(bkey_s_c_to_accounting(k)) && diff --git a/fs/bcachefs/disk_accounting.h b/fs/bcachefs/disk_accounting.h index b92f8c2e3054..653090667aaa 100644 --- a/fs/bcachefs/disk_accounting.h +++ b/fs/bcachefs/disk_accounting.h @@ -106,8 +106,37 @@ static inline int accounting_pos_cmp(const void *_l, const void *_r) int bch2_accounting_mem_insert(struct bch_fs *, struct bkey_s_c_accounting, bool); void bch2_accounting_mem_gc(struct bch_fs *); -static inline int __bch2_accounting_mem_mod(struct bch_fs *c, struct bkey_s_c_accounting a, bool gc) +/* + * Update in memory counters so they match the btree update we're doing; called + * from transaction commit path + */ +static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, struct bkey_s_c_accounting a, bool gc, bool read) { + struct bch_fs *c = trans->c; + struct disk_accounting_pos acc_k; + bpos_to_disk_accounting_pos(&acc_k, a.k->p); + + if (!gc && !read) { + switch (acc_k.type) { + case BCH_DISK_ACCOUNTING_persistent_reserved: + trans->fs_usage_delta.reserved += acc_k.persistent_reserved.nr_replicas * a.v->d[0]; + break; + case BCH_DISK_ACCOUNTING_replicas: + fs_usage_data_type_to_base(&trans->fs_usage_delta, acc_k.replicas.data_type, a.v->d[0]); + break; + case BCH_DISK_ACCOUNTING_dev_data_type: + rcu_read_lock(); + struct bch_dev *ca = bch2_dev_rcu(c, acc_k.dev_data_type.dev); + if (ca) { + this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].buckets, a.v->d[0]); + this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].sectors, a.v->d[1]); + this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].fragmented, a.v->d[2]); + } + rcu_read_unlock(); + break; + } + } + struct bch_accounting_mem *acc = &c->accounting; unsigned idx; @@ -129,45 +158,10 @@ static inline int __bch2_accounting_mem_mod(struct bch_fs *c, struct bkey_s_c_ac return 0; } -/* - * Update in memory counters so they match the btree update we're doing; called - * from transaction commit path - */ -static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, struct bkey_s_c_accounting a, bool gc) -{ - struct bch_fs *c = trans->c; - - if (!gc) { - struct disk_accounting_pos acc_k; - bpos_to_disk_accounting_pos(&acc_k, a.k->p); - - switch (acc_k.type) { - case BCH_DISK_ACCOUNTING_persistent_reserved: - trans->fs_usage_delta.reserved += acc_k.persistent_reserved.nr_replicas * a.v->d[0]; - break; - case BCH_DISK_ACCOUNTING_replicas: - fs_usage_data_type_to_base(&trans->fs_usage_delta, acc_k.replicas.data_type, a.v->d[0]); - break; - case BCH_DISK_ACCOUNTING_dev_data_type: - rcu_read_lock(); - struct bch_dev *ca = bch2_dev_rcu(c, acc_k.dev_data_type.dev); - if (ca) { - this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].buckets, a.v->d[0]); - this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].sectors, a.v->d[1]); - this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].fragmented, a.v->d[2]); - } - rcu_read_unlock(); - break; - } - } - - return __bch2_accounting_mem_mod(c, a, gc); -} - static inline int bch2_accounting_mem_add(struct btree_trans *trans, struct bkey_s_c_accounting a, bool gc) { percpu_down_read(&trans->c->mark_lock); - int ret = bch2_accounting_mem_mod_locked(trans, a, gc); + int ret = bch2_accounting_mem_mod_locked(trans, a, gc, false); percpu_up_read(&trans->c->mark_lock); return ret; } From 58474f76a770bcc79d4b2d7232e4d6650e732b50 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 12 Aug 2024 02:27:36 -0400 Subject: [PATCH 253/562] bcachefs: bcachefs_metadata_version_disk_accounting_inum This adds another disk accounting counter to track usage per inode number (any snapshot ID). This will be used for a couple things: - It'll give us a way to tell the user how much space a given file ista consuming in all snapshots; i.e. how much extra space it's consuming due to snapshot versioning. - It counts number of extents and total size of extents (both in btree keyspace sectors and actual disk usage), meaning it gives us average extent size: that is, it'll let us cheaply find fragmented files that should be defragmented. Signed-off-by: Kent Overstreet --- fs/bcachefs/bcachefs_format.h | 3 ++- fs/bcachefs/buckets.c | 14 ++++++++++++++ fs/bcachefs/disk_accounting.c | 3 +++ fs/bcachefs/disk_accounting.h | 3 +++ fs/bcachefs/disk_accounting_format.h | 8 +++++++- fs/bcachefs/sb-downgrade.c | 5 ++++- 6 files changed, 33 insertions(+), 3 deletions(-) diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index b25f86356728..c75f2e0f32bb 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -676,7 +676,8 @@ struct bch_sb_field_ext { x(mi_btree_bitmap, BCH_VERSION(1, 7)) \ x(bucket_stripe_sectors, BCH_VERSION(1, 8)) \ x(disk_accounting_v2, BCH_VERSION(1, 9)) \ - x(disk_accounting_v3, BCH_VERSION(1, 10)) + x(disk_accounting_v3, BCH_VERSION(1, 10)) \ + x(disk_accounting_inum, BCH_VERSION(1, 11)) enum bcachefs_metadata_version { bcachefs_metadata_version_min = 9, diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index 9f7004e941ce..b69ef4b3de6e 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -810,6 +810,20 @@ static int __trigger_extent(struct btree_trans *trans, ret = bch2_disk_accounting_mod(trans, &acc_btree_key, &replicas_sectors, 1, gc); if (ret) return ret; + } else { + bool insert = !(flags & BTREE_TRIGGER_overwrite); + struct disk_accounting_pos acc_inum_key = { + .type = BCH_DISK_ACCOUNTING_inum, + .inum.inum = k.k->p.inode, + }; + s64 v[3] = { + insert ? 1 : -1, + insert ? k.k->size : -((s64) k.k->size), + replicas_sectors, + }; + ret = bch2_disk_accounting_mod(trans, &acc_inum_key, v, ARRAY_SIZE(v), gc); + if (ret) + return ret; } if (bch2_bkey_rebalance_opts(k)) { diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c index e57b40623cd9..e972e2bca546 100644 --- a/fs/bcachefs/disk_accounting.c +++ b/fs/bcachefs/disk_accounting.c @@ -768,6 +768,9 @@ void bch2_verify_accounting_clean(struct bch_fs *c) if (acc_k.type >= BCH_DISK_ACCOUNTING_TYPE_NR) continue; + if (acc_k.type == BCH_DISK_ACCOUNTING_inum) + continue; + bch2_accounting_mem_read(c, k.k->p, v, nr); if (memcmp(a.v->d, v, nr * sizeof(u64))) { diff --git a/fs/bcachefs/disk_accounting.h b/fs/bcachefs/disk_accounting.h index 653090667aaa..f29fd0dd9581 100644 --- a/fs/bcachefs/disk_accounting.h +++ b/fs/bcachefs/disk_accounting.h @@ -116,6 +116,9 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, stru struct disk_accounting_pos acc_k; bpos_to_disk_accounting_pos(&acc_k, a.k->p); + if (acc_k.type == BCH_DISK_ACCOUNTING_inum) + return 0; + if (!gc && !read) { switch (acc_k.type) { case BCH_DISK_ACCOUNTING_persistent_reserved: diff --git a/fs/bcachefs/disk_accounting_format.h b/fs/bcachefs/disk_accounting_format.h index a93cf26ff4a9..7b6e6c97e6aa 100644 --- a/fs/bcachefs/disk_accounting_format.h +++ b/fs/bcachefs/disk_accounting_format.h @@ -103,7 +103,8 @@ static inline bool data_type_is_hidden(enum bch_data_type type) x(compression, 4) \ x(snapshot, 5) \ x(btree, 6) \ - x(rebalance_work, 7) + x(rebalance_work, 7) \ + x(inum, 8) enum disk_accounting_type { #define x(f, nr) BCH_DISK_ACCOUNTING_##f = nr, @@ -136,6 +137,10 @@ struct bch_acct_btree { __u32 id; } __packed; +struct bch_acct_inum { + __u64 inum; +} __packed; + struct bch_acct_rebalance_work { }; @@ -152,6 +157,7 @@ struct disk_accounting_pos { struct bch_acct_snapshot snapshot; struct bch_acct_btree btree; struct bch_acct_rebalance_work rebalance_work; + struct bch_acct_inum inum; } __packed; } __packed; struct bpos _pad; diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index 9f82d497d9e0..650a1f77ca40 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -72,7 +72,10 @@ BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \ BCH_FSCK_ERR_accounting_key_replicas_nr_required_bad, \ BCH_FSCK_ERR_accounting_key_replicas_devs_unsorted, \ - BCH_FSCK_ERR_accounting_key_junk_at_end) + BCH_FSCK_ERR_accounting_key_junk_at_end) \ + x(disk_accounting_inum, \ + BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ + BCH_FSCK_ERR_accounting_mismatch) #define DOWNGRADE_TABLE() \ x(bucket_stripe_sectors, \ From 63de936b513f7a9ce559194d3269ac291f4f4662 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 21 Jul 2024 17:38:40 +0200 Subject: [PATCH 254/562] media: atomisp: Fix streaming no longer working on BYT / ISP2400 devices Commit a0821ca14bb8 ("media: atomisp: Remove test pattern generator (TPG) support") broke BYT support because it removed a seemingly unused field from struct sh_css_sp_config and a seemingly unused value from enum ia_css_input_mode. But these are part of the ABI between the kernel and firmware on ISP2400 and this part of the TPG support removal changes broke ISP2400 support. ISP2401 support was not affected because on ISP2401 only a part of struct sh_css_sp_config is used. Restore the removed field and enum value to fix this. Fixes: a0821ca14bb8 ("media: atomisp: Remove test pattern generator (TPG) support") Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede Signed-off-by: Hans Verkuil --- .../media/atomisp/pci/ia_css_stream_public.h | 8 ++++++-- .../media/atomisp/pci/sh_css_internal.h | 19 ++++++++++++++++--- 2 files changed, 22 insertions(+), 5 deletions(-) diff --git a/drivers/staging/media/atomisp/pci/ia_css_stream_public.h b/drivers/staging/media/atomisp/pci/ia_css_stream_public.h index 961c61288083..aad860e54d3a 100644 --- a/drivers/staging/media/atomisp/pci/ia_css_stream_public.h +++ b/drivers/staging/media/atomisp/pci/ia_css_stream_public.h @@ -27,12 +27,16 @@ #include "ia_css_prbs.h" #include "ia_css_input_port.h" -/* Input modes, these enumerate all supported input modes. - * Note that not all ISP modes support all input modes. +/* + * Input modes, these enumerate all supported input modes. + * This enum is part of the atomisp firmware ABI and must + * NOT be changed! + * Note that not all ISP modes support all input modes. */ enum ia_css_input_mode { IA_CSS_INPUT_MODE_SENSOR, /** data from sensor */ IA_CSS_INPUT_MODE_FIFO, /** data from input-fifo */ + IA_CSS_INPUT_MODE_TPG, /** data from test-pattern generator */ IA_CSS_INPUT_MODE_PRBS, /** data from pseudo-random bit stream */ IA_CSS_INPUT_MODE_MEMORY, /** data from a frame in memory */ IA_CSS_INPUT_MODE_BUFFERED_SENSOR /** data is sent through mipi buffer */ diff --git a/drivers/staging/media/atomisp/pci/sh_css_internal.h b/drivers/staging/media/atomisp/pci/sh_css_internal.h index a2d972ea3fa0..959e7f549641 100644 --- a/drivers/staging/media/atomisp/pci/sh_css_internal.h +++ b/drivers/staging/media/atomisp/pci/sh_css_internal.h @@ -344,7 +344,14 @@ struct sh_css_sp_input_formatter_set { #define IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT (3) -/* SP configuration information */ +/* + * SP configuration information + * + * This struct is part of the atomisp firmware ABI and is directly copied + * to ISP DRAM by sh_css_store_sp_group_to_ddr() + * + * Do NOT change this struct's layout or remove seemingly unused fields! + */ struct sh_css_sp_config { u8 no_isp_sync; /* Signal host immediately after start */ u8 enable_raw_pool_locking; /** Enable Raw Buffer Locking for HALv3 Support */ @@ -354,6 +361,10 @@ struct sh_css_sp_config { host (true) or when they are passed to the preview/video pipe (false). */ + /* + * Note the fields below are only used on the ISP2400 not on the ISP2401, + * sh_css_store_sp_group_to_ddr() skip copying these when run on the ISP2401. + */ struct { u8 a_changed; u8 b_changed; @@ -363,11 +374,13 @@ struct sh_css_sp_config { } input_formatter; sync_generator_cfg_t sync_gen; + tpg_cfg_t tpg; prbs_cfg_t prbs; input_system_cfg_t input_circuit; u8 input_circuit_cfg_changed; - u32 mipi_sizes_for_check[N_CSI_PORTS][IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT]; - u8 enable_isys_event_queue; + u32 mipi_sizes_for_check[N_CSI_PORTS][IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT]; + /* These last 2 fields are used on both the ISP2400 and the ISP2401 */ + u8 enable_isys_event_queue; u8 disable_cont_vf; }; From a2cbb1603943281a604f5adc48079a148db5cb0d Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Thu, 8 Aug 2024 16:06:40 -0700 Subject: [PATCH 255/562] tcp: Update window clamping condition This patch is based on the discussions between Neal Cardwell and Eric Dumazet in the link https://lore.kernel.org/netdev/20240726204105.1466841-1-quic_subashab@quicinc.com/ It was correctly pointed out that tp->window_clamp would not be updated in cases where net.ipv4.tcp_moderate_rcvbuf=0 or if (copied <= tp->rcvq_space.space). While it is expected for most setups to leave the sysctl enabled, the latter condition may not end up hitting depending on the TCP receive queue size and the pattern of arriving data. The updated check should be hit only on initial MSS update from TCP_MIN_MSS to measured MSS value and subsequently if there was an update to a larger value. Fixes: 05f76b2d634e ("tcp: Adjust clamping window for applications specifying SO_RCVBUF") Signed-off-by: Sean Tranchetti Signed-off-by: Subash Abhinov Kasiviswanathan Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e2b9583ed96a..e37488d3453f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -238,9 +238,14 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) */ if (unlikely(len != icsk->icsk_ack.rcv_mss)) { u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE; + u8 old_ratio = tcp_sk(sk)->scaling_ratio; do_div(val, skb->truesize); tcp_sk(sk)->scaling_ratio = val ? val : 1; + + if (old_ratio != tcp_sk(sk)->scaling_ratio) + WRITE_ONCE(tcp_sk(sk)->window_clamp, + tcp_win_from_space(sk, sk->sk_rcvbuf)); } icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); @@ -754,7 +759,8 @@ void tcp_rcv_space_adjust(struct sock *sk) * */ - if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)) { + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && + !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { u64 rcvwin, grow; int rcvbuf; @@ -770,22 +776,12 @@ void tcp_rcv_space_adjust(struct sock *sk) rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin), READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); - if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { - if (rcvbuf > sk->sk_rcvbuf) { - WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); + if (rcvbuf > sk->sk_rcvbuf) { + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); - /* Make the window clamp follow along. */ - WRITE_ONCE(tp->window_clamp, - tcp_win_from_space(sk, rcvbuf)); - } - } else { - /* Make the window clamp follow along while being bounded - * by SO_RCVBUF. - */ - int clamp = tcp_win_from_space(sk, min(rcvbuf, sk->sk_rcvbuf)); - - if (clamp > tp->window_clamp) - WRITE_ONCE(tp->window_clamp, clamp); + /* Make the window clamp follow along. */ + WRITE_ONCE(tp->window_clamp, + tcp_win_from_space(sk, rcvbuf)); } } tp->rcvq_space.space = copied; From c286f204ce6ba7b48e3dcba53eda7df8eaa64dd9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Juan=20Jos=C3=A9=20Arboleda?= Date: Tue, 13 Aug 2024 11:10:53 -0500 Subject: [PATCH 256/562] ALSA: usb-audio: Support Yamaha P-125 quirk entry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds a USB quirk for the Yamaha P-125 digital piano. Signed-off-by: Juan José Arboleda Cc: Link: https://patch.msgid.link/20240813161053.70256-1-soyjuanarbol@gmail.com Signed-off-by: Takashi Iwai --- sound/usb/quirks-table.h | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index f13a8d63a019..aaa6a515d0f8 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -273,6 +273,7 @@ YAMAHA_DEVICE(0x105a, NULL), YAMAHA_DEVICE(0x105b, NULL), YAMAHA_DEVICE(0x105c, NULL), YAMAHA_DEVICE(0x105d, NULL), +YAMAHA_DEVICE(0x1718, "P-125"), { USB_DEVICE(0x0499, 0x1503), .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { From fa0db8e568787c665384430eaf2221b299b85367 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Tue, 13 Aug 2024 15:19:01 +0200 Subject: [PATCH 257/562] Revert "ata: libata-scsi: Honor the D_SENSE bit for CK_COND=1 and no error" This reverts commit 28ab9769117ca944cb6eb537af5599aa436287a4. Sense data can be in either fixed format or descriptor format. SAT-6 revision 1, "10.4.6 Control mode page", defines the D_SENSE bit: "The SATL shall support this bit as defined in SPC-5 with the following exception: if the D_ SENSE bit is set to zero (i.e., fixed format sense data), then the SATL should return fixed format sense data for ATA PASS-THROUGH commands." The libata SATL has always kept D_SENSE set to zero by default. (It is however possible to change the value using a MODE SELECT SG_IO command.) Failed ATA PASS-THROUGH commands correctly respected the D_SENSE bit, however, successful ATA PASS-THROUGH commands incorrectly returned the sense data in descriptor format (regardless of the D_SENSE bit). Commit 28ab9769117c ("ata: libata-scsi: Honor the D_SENSE bit for CK_COND=1 and no error") fixed this bug for successful ATA PASS-THROUGH commands. However, after commit 28ab9769117c ("ata: libata-scsi: Honor the D_SENSE bit for CK_COND=1 and no error"), there were bug reports that hdparm, hddtemp, and udisks were no longer working as expected. These applications incorrectly assume the returned sense data is in descriptor format, without even looking at the RESPONSE CODE field in the returned sense data (to see which format the returned sense data is in). Considering that there will be broken versions of these applications around roughly forever, we are stuck with being bug compatible with older kernels. Cc: stable@vger.kernel.org # 4.19+ Reported-by: Stephan Eisvogel Reported-by: Christian Heusel Closes: https://lore.kernel.org/linux-ide/0bf3f2f0-0fc6-4ba5-a420-c0874ef82d64@heusel.eu/ Fixes: 28ab9769117c ("ata: libata-scsi: Honor the D_SENSE bit for CK_COND=1 and no error") Reviewed-by: Hannes Reinecke Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20240813131900.1285842-2-cassel@kernel.org Signed-off-by: Niklas Cassel --- drivers/ata/libata-scsi.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index d6f5e25e1ed8..473e00a58a8b 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -951,8 +951,19 @@ static void ata_gen_passthru_sense(struct ata_queued_cmd *qc) &sense_key, &asc, &ascq); ata_scsi_set_sense(qc->dev, cmd, sense_key, asc, ascq); } else { - /* ATA PASS-THROUGH INFORMATION AVAILABLE */ - ata_scsi_set_sense(qc->dev, cmd, RECOVERED_ERROR, 0, 0x1D); + /* + * ATA PASS-THROUGH INFORMATION AVAILABLE + * + * Note: we are supposed to call ata_scsi_set_sense(), which + * respects the D_SENSE bit, instead of unconditionally + * generating the sense data in descriptor format. However, + * because hdparm, hddtemp, and udisks incorrectly assume sense + * data in descriptor format, without even looking at the + * RESPONSE CODE field in the returned sense data (to see which + * format the returned sense data is in), we are stuck with + * being bug compatible with older kernels. + */ + scsi_build_sense(cmd, 1, RECOVERED_ERROR, 0, 0x1D); } } From 829e2a23121fb36ee30ea5145c2a85199f68e2c8 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 14 Aug 2024 12:04:59 +0200 Subject: [PATCH 258/562] ALSA: hda/tas2781: Use correct endian conversion The data conversion is done rather by a wrong function. We convert to BE32, not from BE32. Although the end result must be same, this was complained by the compiler. Fix the code again and align with another similar function tas2563_apply_calib() that does already right. Fixes: 3beddef84d90 ("ALSA: hda/tas2781: fix wrong calibrated data order") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202408141630.DiDUB8Z4-lkp@intel.com/ Link: https://patch.msgid.link/20240814100500.1944-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/pci/hda/tas2781_hda_i2c.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index 7dbfc92d9d55..89d8235537cd 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -527,8 +527,8 @@ static void tas2781_apply_calib(struct tasdevice_priv *tas_priv) for (i = 0; i < tas_priv->ndev; i++) { for (j = 0; j < CALIB_MAX; j++) { - data = get_unaligned_be32( - &tas_priv->cali_data.data[offset]); + data = cpu_to_be32( + *(uint32_t *)&tas_priv->cali_data.data[offset]); rc = tasdevice_dev_bulk_write(tas_priv, i, TASDEVICE_REG(0, page_array[j], rgno_array[j]), (unsigned char *)&data, 4); From 73c34b0b85d46bf9c2c0b367aeaffa1e2481b136 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 29 Jul 2024 13:44:33 -0700 Subject: [PATCH 259/562] xfs: attr forks require attr, not attr2 It turns out that I misunderstood the difference between the attr and attr2 feature bits. "attr" means that at some point an attr fork was created somewhere in the filesystem. "attr2" means that inodes have variable-sized forks, but says nothing about whether or not there actually /are/ attr forks in the system. If we have an attr fork, we only need to check that attr is set. Fixes: 99d9d8d05da26 ("xfs: scrub inode block mappings") Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Chandan Babu R --- fs/xfs/scrub/bmap.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 24a15bf784f1..5ab2ac53c920 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -938,7 +938,13 @@ xchk_bmap( } break; case XFS_ATTR_FORK: - if (!xfs_has_attr(mp) && !xfs_has_attr2(mp)) + /* + * "attr" means that an attr fork was created at some point in + * the life of this filesystem. "attr2" means that inodes have + * variable-sized data/attr fork areas. Hence we only check + * attr here. + */ + if (!xfs_has_attr(mp)) xchk_ino_set_corrupt(sc, sc->ip->i_ino); break; default: From 04d6dbb55301a29aeb9a197e6b0012cdc265f1e4 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sun, 4 Aug 2024 14:39:34 -0700 Subject: [PATCH 260/562] xfs: revert AIL TASK_KILLABLE threshold In commit 9adf40249e6c, we changed the behavior of the AIL thread to set its own task state to KILLABLE whenever the timeout value is nonzero. Unfortunately, this missed the fact that xfsaild_push will return 50ms (aka a longish sleep) when we reach the push target or the AIL becomes empty, so xfsaild goes to sleep for a long period of time in uninterruptible D state. This results in artificially high load averages because KILLABLE processes are UNINTERRUPTIBLE, which contributes to load average even though the AIL is asleep waiting for someone to interrupt it. It's not blocked on IOs or anything, but people scrap ps for processes that look like they're stuck in D state, so restore the previous threshold. Fixes: 9adf40249e6c ("xfs: AIL doesn't need manual pushing") Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Chandan Babu R --- fs/xfs/xfs_trans_ail.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 0fafcc9f3dbe..8ede9d099d1f 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -644,7 +644,12 @@ xfsaild( set_freezable(); while (1) { - if (tout) + /* + * Long waits of 50ms or more occur when we've run out of items + * to push, so we only want uninterruptible state if we're + * actually blocked on something. + */ + if (tout && tout <= 20) set_current_state(TASK_KILLABLE|TASK_FREEZABLE); else set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); From 8d16762047c627073955b7ed171a36addaf7b1ff Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sun, 4 Aug 2024 14:39:57 -0700 Subject: [PATCH 261/562] xfs: conditionally allow FS_XFLAG_REALTIME changes if S_DAX is set If a file has the S_DAX flag (aka fsdax access mode) set, we cannot allow users to change the realtime flag unless the datadev and rtdev both support fsdax access modes. Even if there are no extents allocated to the file, the setattr thread could be racing with another thread that has already started down the write code paths. Fixes: ba23cba9b3bdc ("fs: allow per-device dax status checking for filesystems") Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Chandan Babu R --- fs/xfs/xfs_ioctl.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 4e933db75b12..6b13666d4e96 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -483,6 +483,17 @@ xfs_ioctl_setattr_xflags( /* Can't change realtime flag if any extents are allocated. */ if (ip->i_df.if_nextents || ip->i_delayed_blks) return -EINVAL; + + /* + * If S_DAX is enabled on this file, we can only switch the + * device if both support fsdax. We can't update S_DAX because + * there might be other threads walking down the access paths. + */ + if (IS_DAX(VFS_I(ip)) && + (mp->m_ddev_targp->bt_daxdev == NULL || + (mp->m_rtdev_targp && + mp->m_rtdev_targp->bt_daxdev == NULL))) + return -EINVAL; } if (rtflag) { From 66155de93bcf4f2967e602a4b3bf7ebe58f34b11 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 9 Aug 2024 12:02:58 -0700 Subject: [PATCH 262/562] KVM: x86: Disallow read-only memslots for SEV-ES and SEV-SNP (and TDX) Disallow read-only memslots for SEV-{ES,SNP} VM types, as KVM can't directly emulate instructions for ES/SNP, and instead the guest must explicitly request emulation. Unless the guest explicitly requests emulation without accessing memory, ES/SNP relies on KVM creating an MMIO SPTE, with the subsequent #NPF being reflected into the guest as a #VC. But for read-only memslots, KVM deliberately doesn't create MMIO SPTEs, because except for ES/SNP, doing so requires setting reserved bits in the SPTE, i.e. the SPTE can't be readable while also generating a #VC on writes. Because KVM never creates MMIO SPTEs and jumps directly to emulation, the guest never gets a #VC. And since KVM simply resumes the guest if ES/SNP guests trigger emulation, KVM effectively puts the vCPU into an infinite #NPF loop if the vCPU attempts to write read-only memory. Disallow read-only memory for all VMs with protected state, i.e. for upcoming TDX VMs as well as ES/SNP VMs. For TDX, it's actually possible to support read-only memory, as TDX uses EPT Violation #VE to reflect the fault into the guest, e.g. KVM could configure read-only SPTEs with RX protections and SUPPRESS_VE=0. But there is no strong use case for supporting read-only memslots on TDX, e.g. the main historical usage is to emulate option ROMs, but TDX disallows executing from shared memory. And if someone comes along with a legitimate, strong use case, the restriction can always be lifted for TDX. Don't bother trying to retroactively apply the restriction to SEV-ES VMs that are created as type KVM_X86_DEFAULT_VM. Read-only memslots can't possibly work for SEV-ES, i.e. disallowing such memslots is really just means reporting an error to userspace instead of silently hanging vCPUs. Trying to deal with the ordering between KVM_SEV_INIT and memslot creation isn't worth the marginal benefit it would provide userspace. Fixes: 26c44aa9e076 ("KVM: SEV: define VM types for SEV and SEV-ES") Fixes: 1dfe571c12cf ("KVM: SEV: Add initial SEV-SNP support") Cc: Peter Gonda Cc: Michael Roth Cc: Vishal Annapurve Cc: Ackerly Tng Signed-off-by: Sean Christopherson Message-ID: <20240809190319.1710470-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 ++ include/linux/kvm_host.h | 7 +++++++ virt/kvm/kvm_main.c | 5 ++--- 3 files changed, 11 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 94e7b5a4fafe..4a68cb3eba78 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -2192,6 +2192,8 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, #define kvm_arch_has_private_mem(kvm) false #endif +#define kvm_arch_has_readonly_mem(kvm) (!(kvm)->arch.has_protected_state) + static inline u16 kvm_read_ldt(void) { u16 ldt; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 79a6b1a63027..b23c6d48392f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -715,6 +715,13 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm) } #endif +#ifndef kvm_arch_has_readonly_mem +static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm) +{ + return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM); +} +#endif + struct kvm_memslots { u64 generation; atomic_long_t last_used_slot; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 92901656a0d4..cb2b78e92910 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1578,15 +1578,14 @@ static int check_memory_region_flags(struct kvm *kvm, if (mem->flags & KVM_MEM_GUEST_MEMFD) valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES; -#ifdef CONFIG_HAVE_KVM_READONLY_MEM /* * GUEST_MEMFD is incompatible with read-only memslots, as writes to * read-only memslots have emulated MMIO, not page fault, semantics, * and KVM doesn't allow emulated MMIO for private memory. */ - if (!(mem->flags & KVM_MEM_GUEST_MEMFD)) + if (kvm_arch_has_readonly_mem(kvm) && + !(mem->flags & KVM_MEM_GUEST_MEMFD)) valid_flags |= KVM_MEM_READONLY; -#endif if (mem->flags & ~valid_flags) return -EINVAL; From f94511df53bb792e505c98662971434c7995388a Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 7 Aug 2024 11:37:31 +0100 Subject: [PATCH 263/562] arm64: uaccess: correct thinko in __get_mem_asm() In the CONFIG_CC_HAS_ASM_GOTO_OUTPUT=y version of __get_mem_asm(), we incorrectly use _ASM_EXTABLE_##type##ACCESS_ERR() such that upon a fault the extable fixup handler writes -EFAULT into "%w0", which is the register containing 'x' (the result of the load). This was a thinko in commit: 86a6a68febfcf57b ("arm64: start using 'asm goto' for get_user() when available") Prior to that commit _ASM_EXTABLE_##type##ACCESS_ERR_ZERO() was used such that the extable fixup handler wrote -EFAULT into "%w0" (the register containing 'err'), and zero into "%w1" (the register containing 'x'). When the 'err' variable was removed, the extable entry was updated incorrectly. Writing -EFAULT to the value register is unnecessary but benign: * We never want -EFAULT in the value register, and previously this would have been zeroed in the extable fixup handler. * In __get_user_error() the value is overwritten with zero explicitly in the error path. * The asm goto outputs cannot be used when the goto label is taken, as older compilers (e.g. clang < 16.0.0) do not guarantee that asm goto outputs are usable in this path and may use a stale value rather than the value in an output register. Consequently, zeroing in the extable fixup handler is insufficient to ensure callers see zero in the error path. * The expected usage of unsafe_get_user() and get_kernel_nofault() requires that the value is not consumed in the error path. Some versions of GCC would mis-compile asm goto with outputs, and erroneously omit subsequent assignments, breaking the error path handling in __get_user_error(). This was discussed at: https://lore.kernel.org/lkml/ZpfxLrJAOF2YNqCk@J2N7QTR9R3.cambridge.arm.com/ ... and was fixed by removing support for asm goto with outputs on those broken compilers in commit: f2f6a8e887172503 ("init/Kconfig: remove CONFIG_GCC_ASM_GOTO_OUTPUT_WORKAROUND") With that out of the way, we can safely replace the usage of _ASM_EXTABLE_##type##ACCESS_ERR() with _ASM_EXTABLE_##type##ACCESS(), leaving the value register unchanged in the case a fault is taken, as was originally intended. This matches other architectures and matches our __put_mem_asm(). Signed-off-by: Mark Rutland Cc: Will Deacon Link: https://lore.kernel.org/r/20240807103731.2498893-1-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 28f665e0975a..1aa4ecb73429 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -188,7 +188,7 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr) #define __get_mem_asm(load, reg, x, addr, label, type) \ asm_goto_output( \ "1: " load " " reg "0, [%1]\n" \ - _ASM_EXTABLE_##type##ACCESS_ERR(1b, %l2, %w0) \ + _ASM_EXTABLE_##type##ACCESS(1b, %l2) \ : "=r" (x) \ : "r" (addr) : : label) #else From a21dcf0ea8566ebbe011c79d6ed08cdfea771de3 Mon Sep 17 00:00:00 2001 From: Haibo Xu Date: Mon, 5 Aug 2024 11:30:24 +0800 Subject: [PATCH 264/562] arm64: ACPI: NUMA: initialize all values of acpi_early_node_map to NUMA_NO_NODE Currently, only acpi_early_node_map[0] was initialized to NUMA_NO_NODE. To ensure all the values were properly initialized, switch to initialize all of them to NUMA_NO_NODE. Fixes: e18962491696 ("arm64: numa: rework ACPI NUMA initialization") Cc: # 4.19.x Reported-by: Andrew Jones Suggested-by: Andrew Jones Signed-off-by: Haibo Xu Reviewed-by: Anshuman Khandual Reviewed-by: Sunil V L Reviewed-by: Andrew Jones Acked-by: Catalin Marinas Acked-by: Lorenzo Pieralisi Reviewed-by: Hanjun Guo Link: https://lore.kernel.org/r/853d7f74aa243f6f5999e203246f0d1ae92d2b61.1722828421.git.haibo1.xu@intel.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/acpi_numa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c index 0c036a9a3c33..2465f291c7e1 100644 --- a/arch/arm64/kernel/acpi_numa.c +++ b/arch/arm64/kernel/acpi_numa.c @@ -27,7 +27,7 @@ #include -static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE }; +static int acpi_early_node_map[NR_CPUS] __initdata = { [0 ... NR_CPUS - 1] = NUMA_NO_NODE }; int __init acpi_numa_get_nid(unsigned int cpu) { From 1c0e5881691a787a9399a99bff4d56ead6e75e91 Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Wed, 14 Aug 2024 10:31:13 +0200 Subject: [PATCH 265/562] KVM: SEV: uapi: fix typo in SEV_RET_INVALID_CONFIG "INVALID" is misspelt in "SEV_RET_INAVLID_CONFIG". Since this is part of the UAPI, keep the current definition and add a new one with the fix. Fix-suggested-by: Marc Zyngier Signed-off-by: Amit Shah Message-ID: <20240814083113.21622-1-amit@kernel.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/psp-sev.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index 2289b7c76c59..832c15d9155b 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -51,6 +51,7 @@ typedef enum { SEV_RET_INVALID_PLATFORM_STATE, SEV_RET_INVALID_GUEST_STATE, SEV_RET_INAVLID_CONFIG, + SEV_RET_INVALID_CONFIG = SEV_RET_INAVLID_CONFIG, SEV_RET_INVALID_LEN, SEV_RET_ALREADY_OWNED, SEV_RET_INVALID_CERTIFICATE, From 57d5af2660e9443b081eeaf1c373b3ce48477828 Mon Sep 17 00:00:00 2001 From: Vignesh Raghavendra Date: Wed, 14 Aug 2024 20:42:37 +0530 Subject: [PATCH 266/562] spi: spi-cadence-quadspi: Fix OSPI NOR failures during system resume Its necessary to call pm_runtime_force_*() hooks as part of system suspend/resume calls so that the runtime_pm hooks get called. This ensures latest state of the IP is cached and restored during system sleep. This is especially true if runtime autosuspend is enabled as runtime suspend hooks may not be called at all before system sleeps. Without this patch, OSPI NOR enumeration (READ_ID) fails during resume as context saved during suspend path is inconsistent. Fixes: 078d62de433b ("spi: cadence-qspi: add system-wide suspend and resume callbacks") Signed-off-by: Vignesh Raghavendra Link: https://patch.msgid.link/20240814151237.3856184-1-vigneshr@ti.com Signed-off-by: Mark Brown --- drivers/spi/spi-cadence-quadspi.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 05ebb03d319f..d4607cb89c48 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -2000,13 +2000,25 @@ static int cqspi_runtime_resume(struct device *dev) static int cqspi_suspend(struct device *dev) { struct cqspi_st *cqspi = dev_get_drvdata(dev); + int ret; - return spi_controller_suspend(cqspi->host); + ret = spi_controller_suspend(cqspi->host); + if (ret) + return ret; + + return pm_runtime_force_suspend(dev); } static int cqspi_resume(struct device *dev) { struct cqspi_st *cqspi = dev_get_drvdata(dev); + int ret; + + ret = pm_runtime_force_resume(dev); + if (ret) { + dev_err(dev, "pm_runtime_force_resume failed on resume\n"); + return ret; + } return spi_controller_resume(cqspi->host); } From 71833e79a42178d8a50b5081c98c78ace9325628 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Wed, 14 Aug 2024 13:16:49 +0100 Subject: [PATCH 267/562] i2c: Use IS_REACHABLE() for substituting empty ACPI functions Replace IS_ENABLED() with IS_REACHABLE() to substitute empty stubs for: i2c_acpi_get_i2c_resource() i2c_acpi_client_count() i2c_acpi_find_bus_speed() i2c_acpi_new_device_by_fwnode() i2c_adapter *i2c_acpi_find_adapter_by_handle() i2c_acpi_waive_d0_probe() commit f17c06c6608a ("i2c: Fix conditional for substituting empty ACPI functions") partially fixed this conditional to depend on CONFIG_I2C, but used IS_ENABLED(), which is wrong since CONFIG_I2C is tristate. CONFIG_ACPI is boolean but let's also change it to use IS_REACHABLE() to future-proof it against becoming tristate. Somehow despite testing various combinations of CONFIG_I2C and CONFIG_ACPI we missed the combination CONFIG_I2C=m, CONFIG_ACPI=y. Signed-off-by: Richard Fitzgerald Fixes: f17c06c6608a ("i2c: Fix conditional for substituting empty ACPI functions") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202408141333.gYnaitcV-lkp@intel.com/ Reviewed-by: Takashi Iwai Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 7eedd0c662da..377def497298 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -1066,7 +1066,7 @@ static inline int of_i2c_get_board_info(struct device *dev, struct acpi_resource; struct acpi_resource_i2c_serialbus; -#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_I2C) +#if IS_REACHABLE(CONFIG_ACPI) && IS_REACHABLE(CONFIG_I2C) bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c); int i2c_acpi_client_count(struct acpi_device *adev); From 3cd740b985963f874a1a094f1969e998b9d05554 Mon Sep 17 00:00:00 2001 From: Tom Hughes Date: Tue, 6 Aug 2024 12:40:52 +0100 Subject: [PATCH 268/562] netfilter: allow ipv6 fragments to arrive on different devices Commit 264640fc2c5f4 ("ipv6: distinguish frag queues by device for multicast and link-local packets") modified the ipv6 fragment reassembly logic to distinguish frag queues by device for multicast and link-local packets but in fact only the main reassembly code limits the use of the device to those address types and the netfilter reassembly code uses the device for all packets. This means that if fragments of a packet arrive on different interfaces then netfilter will fail to reassemble them and the fragments will be expired without going any further through the filters. Fixes: 648700f76b03 ("inet: frags: use rhashtables for reassembly units") Signed-off-by: Tom Hughes Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/nf_conntrack_reasm.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 6f0844c9315d..4120e67a8ce6 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -154,6 +154,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, }; struct inet_frag_queue *q; + if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST | + IPV6_ADDR_LINKLOCAL))) + key.iif = 0; + q = inet_frag_find(nf_frag->fqdir, &key); if (!q) return NULL; From 61119394631f219e23ce98bcc3eb993a64a8ea64 Mon Sep 17 00:00:00 2001 From: Celeste Liu Date: Thu, 27 Jun 2024 22:23:39 +0800 Subject: [PATCH 269/562] riscv: entry: always initialize regs->a0 to -ENOSYS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Otherwise when the tracer changes syscall number to -1, the kernel fails to initialize a0 with -ENOSYS and subsequently fails to return the error code of the failed syscall to userspace. For example, it will break strace syscall tampering. Fixes: 52449c17bdd1 ("riscv: entry: set a0 = -ENOSYS only when syscall != -1") Reported-by: "Dmitry V. Levin" Reviewed-by: Björn Töpel Cc: stable@vger.kernel.org Signed-off-by: Celeste Liu Link: https://lore.kernel.org/r/20240627142338.5114-2-CoelacanthusHex@gmail.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/traps.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 05a16b1f0aee..51ebfd23e007 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -319,6 +319,7 @@ void do_trap_ecall_u(struct pt_regs *regs) regs->epc += 4; regs->orig_a0 = regs->a0; + regs->a0 = -ENOSYS; riscv_v_vstate_discard(regs); @@ -328,8 +329,7 @@ void do_trap_ecall_u(struct pt_regs *regs) if (syscall >= 0 && syscall < NR_syscalls) syscall_handler(regs, syscall); - else if (syscall != -1) - regs->a0 = -ENOSYS; + /* * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), * so the maximum stack offset is 1k bytes (10 bits). From 57d76bc51fd80824bcc0c84a5b5ec944f1b51edd Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Wed, 8 May 2024 21:19:17 +0200 Subject: [PATCH 270/562] riscv: change XIP's kernel_map.size to be size of the entire kernel With XIP kernel, kernel_map.size is set to be only the size of data part of the kernel. This is inconsistent with "normal" kernel, who sets it to be the size of the entire kernel. More importantly, XIP kernel fails to boot if CONFIG_DEBUG_VIRTUAL is enabled, because there are checks on virtual addresses with the assumption that kernel_map.size is the size of the entire kernel (these checks are in arch/riscv/mm/physaddr.c). Change XIP's kernel_map.size to be the size of the entire kernel. Signed-off-by: Nam Cao Cc: # v6.1+ Reviewed-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20240508191917.2892064-1-namcao@linutronix.de Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 8b698d9609e7..eb0649a61b4c 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -927,7 +927,7 @@ static void __init create_kernel_page_table(pgd_t *pgdir, PMD_SIZE, PAGE_KERNEL_EXEC); /* Map the data in RAM */ - end_va = kernel_map.virt_addr + XIP_OFFSET + kernel_map.size; + end_va = kernel_map.virt_addr + kernel_map.size; for (va = kernel_map.virt_addr + XIP_OFFSET; va < end_va; va += PMD_SIZE) create_pgd_mapping(pgdir, va, kernel_map.phys_addr + (va - (kernel_map.virt_addr + XIP_OFFSET)), @@ -1096,7 +1096,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) phys_ram_base = CONFIG_PHYS_RAM_BASE; kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE; - kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_sdata); + kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start); kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom; #else From a445699879f989f6700df81f497b70bf94cc6163 Mon Sep 17 00:00:00 2001 From: Haibo Xu Date: Mon, 5 Aug 2024 11:30:23 +0800 Subject: [PATCH 271/562] RISC-V: ACPI: NUMA: initialize all values of acpi_early_node_map to NUMA_NO_NODE Currently, only acpi_early_node_map[0] was initialized to NUMA_NO_NODE. To ensure all the values were properly initialized, switch to initialize all of them to NUMA_NO_NODE. Fixes: eabd9db64ea8 ("ACPI: RISCV: Add NUMA support based on SRAT and SLIT") Reported-by: Andrew Jones Suggested-by: Andrew Jones Signed-off-by: Haibo Xu Reviewed-by: Sunil V L Reviewed-by: Andrew Jones Reviewed-by: Hanjun Guo Link: https://lore.kernel.org/r/0d362a8ae50558b95685da4c821b2ae9e8cf78be.1722828421.git.haibo1.xu@intel.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/acpi_numa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kernel/acpi_numa.c b/arch/riscv/kernel/acpi_numa.c index 0231482d6946..ff95aeebee3e 100644 --- a/arch/riscv/kernel/acpi_numa.c +++ b/arch/riscv/kernel/acpi_numa.c @@ -28,7 +28,7 @@ #include -static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE }; +static int acpi_early_node_map[NR_CPUS] __initdata = { [0 ... NR_CPUS - 1] = NUMA_NO_NODE }; int __init acpi_numa_get_nid(unsigned int cpu) { From c42e2f076769c9c1bc5f3f0aa1c2032558e76647 Mon Sep 17 00:00:00 2001 From: Evan Green Date: Fri, 9 Aug 2024 14:44:43 -0700 Subject: [PATCH 272/562] RISC-V: hwprobe: Add MISALIGNED_PERF key RISCV_HWPROBE_KEY_CPUPERF_0 was mistakenly flagged as a bitmask in hwprobe_key_is_bitmask(), when in reality it was an enum value. This causes problems when used in conjunction with RISCV_HWPROBE_WHICH_CPUS, since SLOW, FAST, and EMULATED have values whose bits overlap with each other. If the caller asked for the set of CPUs that was SLOW or EMULATED, the returned set would also include CPUs that were FAST. Introduce a new hwprobe key, RISCV_HWPROBE_KEY_MISALIGNED_PERF, which returns the same values in response to a direct query (with no flags), but is properly handled as an enumerated value. As a result, SLOW, FAST, and EMULATED are all correctly treated as distinct values under the new key when queried with the WHICH_CPUS flag. Leave the old key in place to avoid disturbing applications which may have already come to rely on the key, with or without its broken behavior with respect to the WHICH_CPUS flag. Fixes: e178bf146e4b ("RISC-V: hwprobe: Introduce which-cpus flag") Signed-off-by: Evan Green Reviewed-by: Charlie Jenkins Reviewed-by: Andrew Jones Link: https://lore.kernel.org/r/20240809214444.3257596-2-evan@rivosinc.com Signed-off-by: Palmer Dabbelt --- Documentation/arch/riscv/hwprobe.rst | 20 +++++++++++++------- arch/riscv/include/asm/hwprobe.h | 2 +- arch/riscv/include/uapi/asm/hwprobe.h | 1 + arch/riscv/kernel/sys_hwprobe.c | 1 + 4 files changed, 16 insertions(+), 8 deletions(-) diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst index 3db60a0911df..a994eed75bde 100644 --- a/Documentation/arch/riscv/hwprobe.rst +++ b/Documentation/arch/riscv/hwprobe.rst @@ -239,8 +239,13 @@ The following keys are defined: ratified in commit 98918c844281 ("Merge pull request #1217 from riscv/zawrs") of riscv-isa-manual. -* :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance - information about the selected set of processors. +* :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: Deprecated. Returns similar values to + :c:macro:`RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF`, but the key was + mistakenly classified as a bitmask rather than a value. + +* :c:macro:`RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF`: An enum value describing + the performance of misaligned scalar native word accesses on the selected set + of processors. * :c:macro:`RISCV_HWPROBE_MISALIGNED_UNKNOWN`: The performance of misaligned accesses is unknown. @@ -249,12 +254,13 @@ The following keys are defined: emulated via software, either in or below the kernel. These accesses are always extremely slow. - * :c:macro:`RISCV_HWPROBE_MISALIGNED_SLOW`: Misaligned accesses are slower - than equivalent byte accesses. Misaligned accesses may be supported - directly in hardware, or trapped and emulated by software. + * :c:macro:`RISCV_HWPROBE_MISALIGNED_SLOW`: Misaligned native word + sized accesses are slower than the equivalent quantity of byte accesses. + Misaligned accesses may be supported directly in hardware, or trapped and + emulated by software. - * :c:macro:`RISCV_HWPROBE_MISALIGNED_FAST`: Misaligned accesses are faster - than equivalent byte accesses. + * :c:macro:`RISCV_HWPROBE_MISALIGNED_FAST`: Misaligned native word + sized accesses are faster than the equivalent quantity of byte accesses. * :c:macro:`RISCV_HWPROBE_MISALIGNED_UNSUPPORTED`: Misaligned accesses are not supported at all and will generate a misaligned address fault. diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h index ef01c182af2b..ffb9484531af 100644 --- a/arch/riscv/include/asm/hwprobe.h +++ b/arch/riscv/include/asm/hwprobe.h @@ -8,7 +8,7 @@ #include -#define RISCV_HWPROBE_MAX_KEY 8 +#define RISCV_HWPROBE_MAX_KEY 9 static inline bool riscv_hwprobe_key_is_valid(__s64 key) { diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h index b706c8e47b02..635753084275 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -82,6 +82,7 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE 6 #define RISCV_HWPROBE_KEY_HIGHEST_VIRT_ADDRESS 7 #define RISCV_HWPROBE_KEY_TIME_CSR_FREQ 8 +#define RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF 9 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */ /* Flags */ diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index 8d1b5c35d2a7..2d0f4f6a32c3 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -225,6 +225,7 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair, break; case RISCV_HWPROBE_KEY_CPUPERF_0: + case RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF: pair->value = hwprobe_misaligned(cpus); break; From 1f5288874de776412041022607513ffac74ae1a6 Mon Sep 17 00:00:00 2001 From: Evan Green Date: Fri, 9 Aug 2024 14:44:44 -0700 Subject: [PATCH 273/562] RISC-V: hwprobe: Add SCALAR to misaligned perf defines In preparation for misaligned vector performance hwprobe keys, rename the hwprobe key values associated with misaligned scalar accesses to include the term SCALAR. Leave the old defines in place to maintain source compatibility. This change is intended to be a functional no-op. Signed-off-by: Evan Green Reviewed-by: Charlie Jenkins Link: https://lore.kernel.org/r/20240809214444.3257596-3-evan@rivosinc.com Signed-off-by: Palmer Dabbelt --- Documentation/arch/riscv/hwprobe.rst | 28 ++++++++++++---------- arch/riscv/include/uapi/asm/hwprobe.h | 5 ++++ arch/riscv/kernel/sys_hwprobe.c | 10 ++++---- arch/riscv/kernel/traps_misaligned.c | 6 ++--- arch/riscv/kernel/unaligned_access_speed.c | 12 +++++----- 5 files changed, 34 insertions(+), 27 deletions(-) diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst index a994eed75bde..85b709257918 100644 --- a/Documentation/arch/riscv/hwprobe.rst +++ b/Documentation/arch/riscv/hwprobe.rst @@ -247,23 +247,25 @@ The following keys are defined: the performance of misaligned scalar native word accesses on the selected set of processors. - * :c:macro:`RISCV_HWPROBE_MISALIGNED_UNKNOWN`: The performance of misaligned - accesses is unknown. + * :c:macro:`RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN`: The performance of + misaligned scalar accesses is unknown. - * :c:macro:`RISCV_HWPROBE_MISALIGNED_EMULATED`: Misaligned accesses are - emulated via software, either in or below the kernel. These accesses are - always extremely slow. + * :c:macro:`RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED`: Misaligned scalar + accesses are emulated via software, either in or below the kernel. These + accesses are always extremely slow. - * :c:macro:`RISCV_HWPROBE_MISALIGNED_SLOW`: Misaligned native word - sized accesses are slower than the equivalent quantity of byte accesses. - Misaligned accesses may be supported directly in hardware, or trapped and - emulated by software. + * :c:macro:`RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW`: Misaligned scalar native + word sized accesses are slower than the equivalent quantity of byte + accesses. Misaligned accesses may be supported directly in hardware, or + trapped and emulated by software. - * :c:macro:`RISCV_HWPROBE_MISALIGNED_FAST`: Misaligned native word - sized accesses are faster than the equivalent quantity of byte accesses. + * :c:macro:`RISCV_HWPROBE_MISALIGNED_SCALAR_FAST`: Misaligned scalar native + word sized accesses are faster than the equivalent quantity of byte + accesses. - * :c:macro:`RISCV_HWPROBE_MISALIGNED_UNSUPPORTED`: Misaligned accesses are - not supported at all and will generate a misaligned address fault. + * :c:macro:`RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED`: Misaligned scalar + accesses are not supported at all and will generate a misaligned address + fault. * :c:macro:`RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE`: An unsigned int which represents the size of the Zicboz block in bytes. diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h index 635753084275..1e153cda57db 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -83,6 +83,11 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_KEY_HIGHEST_VIRT_ADDRESS 7 #define RISCV_HWPROBE_KEY_TIME_CSR_FREQ 8 #define RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF 9 +#define RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN 0 +#define RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED 1 +#define RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW 2 +#define RISCV_HWPROBE_MISALIGNED_SCALAR_FAST 3 +#define RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED 4 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */ /* Flags */ diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index 2d0f4f6a32c3..cea0ca2bf2a2 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -178,13 +178,13 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus) perf = this_perf; if (perf != this_perf) { - perf = RISCV_HWPROBE_MISALIGNED_UNKNOWN; + perf = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN; break; } } if (perf == -1ULL) - return RISCV_HWPROBE_MISALIGNED_UNKNOWN; + return RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN; return perf; } @@ -192,12 +192,12 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus) static u64 hwprobe_misaligned(const struct cpumask *cpus) { if (IS_ENABLED(CONFIG_RISCV_EFFICIENT_UNALIGNED_ACCESS)) - return RISCV_HWPROBE_MISALIGNED_FAST; + return RISCV_HWPROBE_MISALIGNED_SCALAR_FAST; if (IS_ENABLED(CONFIG_RISCV_EMULATED_UNALIGNED_ACCESS) && unaligned_ctl_available()) - return RISCV_HWPROBE_MISALIGNED_EMULATED; + return RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED; - return RISCV_HWPROBE_MISALIGNED_SLOW; + return RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW; } #endif diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index b62d5a2f4541..192cd5603e95 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -338,7 +338,7 @@ int handle_misaligned_load(struct pt_regs *regs) perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr); #ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS - *this_cpu_ptr(&misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_EMULATED; + *this_cpu_ptr(&misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED; #endif if (!unaligned_enabled) @@ -532,13 +532,13 @@ static bool check_unaligned_access_emulated(int cpu) unsigned long tmp_var, tmp_val; bool misaligned_emu_detected; - *mas_ptr = RISCV_HWPROBE_MISALIGNED_UNKNOWN; + *mas_ptr = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN; __asm__ __volatile__ ( " "REG_L" %[tmp], 1(%[ptr])\n" : [tmp] "=r" (tmp_val) : [ptr] "r" (&tmp_var) : "memory"); - misaligned_emu_detected = (*mas_ptr == RISCV_HWPROBE_MISALIGNED_EMULATED); + misaligned_emu_detected = (*mas_ptr == RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED); /* * If unaligned_ctl is already set, this means that we detected that all * CPUS uses emulated misaligned access at boot time. If that changed diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c index a9a6bcb02acf..160628a2116d 100644 --- a/arch/riscv/kernel/unaligned_access_speed.c +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -34,9 +34,9 @@ static int check_unaligned_access(void *param) struct page *page = param; void *dst; void *src; - long speed = RISCV_HWPROBE_MISALIGNED_SLOW; + long speed = RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW; - if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN) + if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) return 0; /* Make an unaligned destination buffer. */ @@ -95,14 +95,14 @@ static int check_unaligned_access(void *param) } if (word_cycles < byte_cycles) - speed = RISCV_HWPROBE_MISALIGNED_FAST; + speed = RISCV_HWPROBE_MISALIGNED_SCALAR_FAST; ratio = div_u64((byte_cycles * 100), word_cycles); pr_info("cpu%d: Ratio of byte access time to unaligned word access is %d.%02d, unaligned accesses are %s\n", cpu, ratio / 100, ratio % 100, - (speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow"); + (speed == RISCV_HWPROBE_MISALIGNED_SCALAR_FAST) ? "fast" : "slow"); per_cpu(misaligned_access_speed, cpu) = speed; @@ -110,7 +110,7 @@ static int check_unaligned_access(void *param) * Set the value of fast_misaligned_access of a CPU. These operations * are atomic to avoid race conditions. */ - if (speed == RISCV_HWPROBE_MISALIGNED_FAST) + if (speed == RISCV_HWPROBE_MISALIGNED_SCALAR_FAST) cpumask_set_cpu(cpu, &fast_misaligned_access); else cpumask_clear_cpu(cpu, &fast_misaligned_access); @@ -188,7 +188,7 @@ static int riscv_online_cpu(unsigned int cpu) static struct page *buf; /* We are already set since the last check */ - if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN) + if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) goto exit; buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); From d1a7b382a9d3f0f3e5a80e0be2991c075fa4f618 Mon Sep 17 00:00:00 2001 From: Donald Hunter Date: Tue, 6 Aug 2024 16:43:24 +0100 Subject: [PATCH 274/562] netfilter: nfnetlink: Initialise extack before use in ACKs Add missing extack initialisation when ACKing BATCH_BEGIN and BATCH_END. Fixes: bf2ac490d28c ("netfilter: nfnetlink: Handle ACK flags for batch messages") Signed-off-by: Donald Hunter Reviewed-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 4abf660c7baf..932b3ddb34f1 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -427,8 +427,10 @@ replay_abort: nfnl_unlock(subsys_id); - if (nlh->nlmsg_flags & NLM_F_ACK) + if (nlh->nlmsg_flags & NLM_F_ACK) { + memset(&extack, 0, sizeof(extack)); nfnl_err_add(&err_list, nlh, 0, &extack); + } while (skb->len >= nlmsg_total_size(0)) { int msglen, type; @@ -577,6 +579,7 @@ done: ss->abort(net, oskb, NFNL_ABORT_NONE); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); } else if (nlh->nlmsg_flags & NLM_F_ACK) { + memset(&extack, 0, sizeof(extack)); nfnl_err_add(&err_list, nlh, 0, &extack); } } else { From e9767137308daf906496613fd879808a07f006a2 Mon Sep 17 00:00:00 2001 From: Donald Hunter Date: Tue, 6 Aug 2024 17:16:37 +0100 Subject: [PATCH 275/562] netfilter: flowtable: initialise extack before use Fix missing initialisation of extack in flow offload. Fixes: c29f74e0df7a ("netfilter: nf_flow_table: hardware offload support") Signed-off-by: Donald Hunter Reviewed-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_flow_table_offload.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index ff1a4e36c2b5..e06bc36f49fe 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -841,8 +841,8 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable, struct list_head *block_cb_list) { struct flow_cls_offload cls_flow = {}; + struct netlink_ext_ack extack = {}; struct flow_block_cb *block_cb; - struct netlink_ext_ack extack; __be16 proto = ETH_P_ALL; int err, i = 0; From 7d8dc1c7be8d3509e8f5164dd5df64c8e34d7eeb Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 7 Aug 2024 21:28:41 +0200 Subject: [PATCH 276/562] netfilter: nf_queue: drop packets with cloned unconfirmed conntracks Conntrack assumes an unconfirmed entry (not yet committed to global hash table) has a refcount of 1 and is not visible to other cores. With multicast forwarding this assumption breaks down because such skbs get cloned after being picked up, i.e. ct->use refcount is > 1. Likewise, bridge netfilter will clone broad/mutlicast frames and all frames in case they need to be flood-forwarded during learning phase. For ip multicast forwarding or plain bridge flood-forward this will "work" because packets don't leave softirq and are implicitly serialized. With nfqueue this no longer holds true, the packets get queued and can be reinjected in arbitrary ways. Disable this feature, I see no other solution. After this patch, nfqueue cannot queue packets except the last multicast/broadcast packet. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/bridge/br_netfilter_hooks.c | 6 +++++- net/netfilter/nfnetlink_queue.c | 35 +++++++++++++++++++++++++++++++-- 2 files changed, 38 insertions(+), 3 deletions(-) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 09f6a773a708..8f9c19d992ac 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -622,8 +622,12 @@ static unsigned int br_nf_local_in(void *priv, if (likely(nf_ct_is_confirmed(ct))) return NF_ACCEPT; + if (WARN_ON_ONCE(refcount_read(&nfct->use) != 1)) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + WARN_ON_ONCE(skb_shared(skb)); - WARN_ON_ONCE(refcount_read(&nfct->use) != 1); /* We can't call nf_confirm here, it would create a dependency * on nf_conntrack module. diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 55e28e1da66e..e0716da256bf 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -820,10 +820,41 @@ static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) static const unsigned long flags = IPS_CONFIRMED | IPS_DYING; - const struct nf_conn *ct = (void *)skb_nfct(entry->skb); + struct nf_conn *ct = (void *)skb_nfct(entry->skb); + unsigned long status; + unsigned int use; - if (ct && ((ct->status & flags) == IPS_DYING)) + if (!ct) + return false; + + status = READ_ONCE(ct->status); + if ((status & flags) == IPS_DYING) return true; + + if (status & IPS_CONFIRMED) + return false; + + /* in some cases skb_clone() can occur after initial conntrack + * pickup, but conntrack assumes exclusive skb->_nfct ownership for + * unconfirmed entries. + * + * This happens for br_netfilter and with ip multicast routing. + * We can't be solved with serialization here because one clone could + * have been queued for local delivery. + */ + use = refcount_read(&ct->ct_general.use); + if (likely(use == 1)) + return false; + + /* Can't decrement further? Exclusive ownership. */ + if (!refcount_dec_not_one(&ct->ct_general.use)) + return false; + + skb_set_nfct(entry->skb, 0); + /* No nf_ct_put(): we already decremented .use and it cannot + * drop down to 0. + */ + return true; #endif return false; } From ea2306f0330c59ac8cd6ba13193497f0a6a02684 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 8 Aug 2024 23:14:43 +0200 Subject: [PATCH 277/562] selftests: netfilter: add test for br_netfilter+conntrack+queue combination Trigger cloned skbs leaving softirq protection. This triggers splat without the preceeding change ("netfilter: nf_queue: drop packets with cloned unconfirmed conntracks"): WARNING: at net/netfilter/nf_conntrack_core.c:1198 __nf_conntrack_confirm.. because local delivery and forwarding will race for confirmation. Based on a reproducer script from Yi Chen. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- .../testing/selftests/net/netfilter/Makefile | 1 + .../net/netfilter/br_netfilter_queue.sh | 78 +++++++++++++++++++ 2 files changed, 79 insertions(+) create mode 100755 tools/testing/selftests/net/netfilter/br_netfilter_queue.sh diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile index 47945b2b3f92..d13fb5ea3e89 100644 --- a/tools/testing/selftests/net/netfilter/Makefile +++ b/tools/testing/selftests/net/netfilter/Makefile @@ -7,6 +7,7 @@ MNL_CFLAGS := $(shell $(HOSTPKG_CONFIG) --cflags libmnl 2>/dev/null) MNL_LDLIBS := $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl) TEST_PROGS := br_netfilter.sh bridge_brouter.sh +TEST_PROGS += br_netfilter_queue.sh TEST_PROGS += conntrack_icmp_related.sh TEST_PROGS += conntrack_ipip_mtu.sh TEST_PROGS += conntrack_tcp_unreplied.sh diff --git a/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh b/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh new file mode 100755 index 000000000000..6a764d70ab06 --- /dev/null +++ b/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh @@ -0,0 +1,78 @@ +#!/bin/bash + +source lib.sh + +checktool "nft --version" "run test without nft tool" + +cleanup() { + cleanup_all_ns +} + +setup_ns c1 c2 c3 sender + +trap cleanup EXIT + +nf_queue_wait() +{ + grep -q "^ *$1 " "/proc/self/net/netfilter/nfnetlink_queue" +} + +port_add() { + ns="$1" + dev="$2" + a="$3" + + ip link add name "$dev" type veth peer name "$dev" netns "$ns" + + ip -net "$ns" addr add 192.168.1."$a"/24 dev "$dev" + ip -net "$ns" link set "$dev" up + + ip link set "$dev" master br0 + ip link set "$dev" up +} + +[ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; } + +ip link add br0 type bridge +ip addr add 192.168.1.254/24 dev br0 + +port_add "$c1" "c1" 1 +port_add "$c2" "c2" 2 +port_add "$c3" "c3" 3 +port_add "$sender" "sender" 253 + +ip link set br0 up + +modprobe -q br_netfilter + +sysctl net.bridge.bridge-nf-call-iptables=1 || exit 1 + +ip netns exec "$sender" ping -I sender -c1 192.168.1.1 || exit 1 +ip netns exec "$sender" ping -I sender -c1 192.168.1.2 || exit 2 +ip netns exec "$sender" ping -I sender -c1 192.168.1.3 || exit 3 + +nft -f /dev/stdin < /dev/null & + +busywait 5000 nf_queue_wait + +for i in $(seq 1 5); do conntrack -F > /dev/null 2> /dev/null; sleep 0.1 ; done & +ip netns exec "$sender" ping -I sender -f -c 50 -b 192.168.1.255 + +read t < /proc/sys/kernel/tainted +if [ "$t" -eq 0 ];then + echo PASS: kernel not tainted +else + echo ERROR: kernel is tainted + exit 1 +fi + +exit 0 From e0b6648b0446e59522819c75ba1dcb09e68d3e94 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Fri, 9 Aug 2024 15:07:30 +0200 Subject: [PATCH 278/562] netfilter: nf_tables: Audit log dump reset after the fact In theory, dumpreset may fail and invalidate the preceeding log message. Fix this and use the occasion to prepare for object reset locking, which benefits from a few unrelated changes: * Add an early call to nfnetlink_unicast if not resetting which effectively skips the audit logging but also unindents it. * Extract the table's name from the netlink attribute (which is verified via earlier table lookup) to not rely upon validity of the looked up table pointer. * Do not use local variable family, it will vanish. Fixes: 8e6cf365e1d5 ("audit: log nftables configuration change events") Signed-off-by: Phil Sutter Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 481ee78e77bc..4fa132715fcc 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8055,6 +8055,7 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { + const struct nftables_pernet *nft_net = nft_pernet(info->net); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; @@ -8064,6 +8065,7 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, struct sk_buff *skb2; bool reset = false; u32 objtype; + char *buf; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { @@ -8102,27 +8104,23 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) reset = true; - if (reset) { - const struct nftables_pernet *nft_net; - char *buf; - - nft_net = nft_pernet(net); - buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq); - - audit_log_nfcfg(buf, - family, - 1, - AUDIT_NFT_OP_OBJ_RESET, - GFP_ATOMIC); - kfree(buf); - } - err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, family, table, obj, reset); if (err < 0) goto err_fill_obj_info; + if (!reset) + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + + buf = kasprintf(GFP_ATOMIC, "%.*s:%u", + nla_len(nla[NFTA_OBJ_TABLE]), + (char *)nla_data(nla[NFTA_OBJ_TABLE]), + nft_net->base_seq); + audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, + AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); + kfree(buf); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); err_fill_obj_info: From 69fc3e9e90f1afc11f4015e6b75d18ab9acee348 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Fri, 9 Aug 2024 15:07:31 +0200 Subject: [PATCH 279/562] netfilter: nf_tables: Introduce nf_tables_getobj_single Outsource the reply skb preparation for non-dump getrule requests into a distinct function. Prep work for object reset locking. Signed-off-by: Phil Sutter Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 85 ++++++++++++++++++++--------------- 1 file changed, 49 insertions(+), 36 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4fa132715fcc..c12c9cae784d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8052,10 +8052,10 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, - const struct nlattr * const nla[]) +static struct sk_buff * +nf_tables_getobj_single(u32 portid, const struct nfnl_info *info, + const struct nlattr * const nla[], bool reset) { - const struct nftables_pernet *nft_net = nft_pernet(info->net); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; @@ -8063,11 +8063,51 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, struct net *net = info->net; struct nft_object *obj; struct sk_buff *skb2; - bool reset = false; u32 objtype; - char *buf; int err; + if (!nla[NFTA_OBJ_NAME] || + !nla[NFTA_OBJ_TYPE]) + return ERR_PTR(-EINVAL); + + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); + return ERR_CAST(table); + } + + objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); + obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); + if (IS_ERR(obj)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); + return ERR_CAST(obj); + } + + skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); + if (!skb2) + return ERR_PTR(-ENOMEM); + + err = nf_tables_fill_obj_info(skb2, net, portid, + info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, + family, table, obj, reset); + if (err < 0) { + kfree_skb(skb2); + return ERR_PTR(err); + } + + return skb2; +} + +static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct nftables_pernet *nft_net = nft_pernet(info->net); + u32 portid = NETLINK_CB(skb).portid; + struct net *net = info->net; + struct sk_buff *skb2; + bool reset = false; + char *buf; + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_obj_start, @@ -8080,35 +8120,12 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } - if (!nla[NFTA_OBJ_NAME] || - !nla[NFTA_OBJ_TYPE]) - return -EINVAL; - - table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0); - if (IS_ERR(table)) { - NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); - return PTR_ERR(table); - } - - objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); - if (IS_ERR(obj)) { - NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); - return PTR_ERR(obj); - } - - skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); - if (!skb2) - return -ENOMEM; - if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) reset = true; - err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid, - info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, - family, table, obj, reset); - if (err < 0) - goto err_fill_obj_info; + skb2 = nf_tables_getobj_single(portid, info, nla, reset); + if (IS_ERR(skb2)) + return PTR_ERR(skb2); if (!reset) return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); @@ -8121,11 +8138,7 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); kfree(buf); - return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); - -err_fill_obj_info: - kfree_skb(skb2); - return err; + return nfnetlink_unicast(skb2, net, portid); } static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) From bd662c4218f9648e888bebde9468146965f3f8a0 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Fri, 9 Aug 2024 15:07:32 +0200 Subject: [PATCH 280/562] netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests Objects' dump callbacks are not concurrency-safe per-se with reset bit set. If two CPUs perform a reset at the same time, at least counter and quota objects suffer from value underrun. Prevent this by introducing dedicated locking callbacks for nfnetlink and the asynchronous dump handling to serialize access. Fixes: 43da04a593d8 ("netfilter: nf_tables: atomic dump and reset for stateful objects") Signed-off-by: Phil Sutter Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 74 ++++++++++++++++++++++++++++------- 1 file changed, 60 insertions(+), 14 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c12c9cae784d..0a2f79346958 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8020,6 +8020,19 @@ cont: return skb->len; } +static int nf_tables_dumpreset_obj(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk)); + int ret; + + mutex_lock(&nft_net->commit_mutex); + ret = nf_tables_dump_obj(skb, cb); + mutex_unlock(&nft_net->commit_mutex); + + return ret; +} + static int nf_tables_dump_obj_start(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; @@ -8036,12 +8049,18 @@ static int nf_tables_dump_obj_start(struct netlink_callback *cb) if (nla[NFTA_OBJ_TYPE]) ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) - ctx->reset = true; - return 0; } +static int nf_tables_dumpreset_obj_start(struct netlink_callback *cb) +{ + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; + + ctx->reset = true; + + return nf_tables_dump_obj_start(cb); +} + static int nf_tables_dump_obj_done(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; @@ -8101,12 +8120,8 @@ nf_tables_getobj_single(u32 portid, const struct nfnl_info *info, static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - struct nftables_pernet *nft_net = nft_pernet(info->net); u32 portid = NETLINK_CB(skb).portid; - struct net *net = info->net; struct sk_buff *skb2; - bool reset = false; - char *buf; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { @@ -8120,15 +8135,46 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } - if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) - reset = true; - - skb2 = nf_tables_getobj_single(portid, info, nla, reset); + skb2 = nf_tables_getobj_single(portid, info, nla, false); if (IS_ERR(skb2)) return PTR_ERR(skb2); - if (!reset) - return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, info->net, portid); +} + +static int nf_tables_getobj_reset(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct nftables_pernet *nft_net = nft_pernet(info->net); + u32 portid = NETLINK_CB(skb).portid; + struct net *net = info->net; + struct sk_buff *skb2; + char *buf; + + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start = nf_tables_dumpreset_obj_start, + .dump = nf_tables_dumpreset_obj, + .done = nf_tables_dump_obj_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); + } + + if (!try_module_get(THIS_MODULE)) + return -EINVAL; + rcu_read_unlock(); + mutex_lock(&nft_net->commit_mutex); + skb2 = nf_tables_getobj_single(portid, info, nla, true); + mutex_unlock(&nft_net->commit_mutex); + rcu_read_lock(); + module_put(THIS_MODULE); + + if (IS_ERR(skb2)) + return PTR_ERR(skb2); buf = kasprintf(GFP_ATOMIC, "%.*s:%u", nla_len(nla[NFTA_OBJ_TABLE]), @@ -9421,7 +9467,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ_RESET] = { - .call = nf_tables_getobj, + .call = nf_tables_getobj_reset, .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, From 14d069d92951a3e150c0a81f2ca3b93e54da913b Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Tue, 13 Aug 2024 09:12:53 -0700 Subject: [PATCH 281/562] i2c: tegra: Do not mark ACPI devices as irq safe On ACPI machines, the tegra i2c module encounters an issue due to a mutex being called inside a spinlock. This leads to the following bug: BUG: sleeping function called from invalid context at kernel/locking/mutex.c:585 ... Call trace: __might_sleep __mutex_lock_common mutex_lock_nested acpi_subsys_runtime_resume rpm_resume tegra_i2c_xfer The problem arises because during __pm_runtime_resume(), the spinlock &dev->power.lock is acquired before rpm_resume() is called. Later, rpm_resume() invokes acpi_subsys_runtime_resume(), which relies on mutexes, triggering the error. To address this issue, devices on ACPI are now marked as not IRQ-safe, considering the dependency of acpi_subsys_runtime_resume() on mutexes. Fixes: bd2fdedbf2ba ("i2c: tegra: Add the ACPI support") Cc: # v5.17+ Co-developed-by: Michael van der Westhuizen Signed-off-by: Michael van der Westhuizen Signed-off-by: Breno Leitao Reviewed-by: Dmitry Osipenko Reviewed-by: Andy Shevchenko Signed-off-by: Andi Shyti --- drivers/i2c/busses/i2c-tegra.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 85b31edc558d..1df5b4204142 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -1802,9 +1802,9 @@ static int tegra_i2c_probe(struct platform_device *pdev) * domain. * * VI I2C device shouldn't be marked as IRQ-safe because VI I2C won't - * be used for atomic transfers. + * be used for atomic transfers. ACPI device is not IRQ safe also. */ - if (!IS_VI(i2c_dev)) + if (!IS_VI(i2c_dev) && !has_acpi_companion(i2c_dev->dev)) pm_runtime_irq_safe(i2c_dev->dev); pm_runtime_enable(i2c_dev->dev); From 6c569b77f0300f8a9960277c7094fa0f128eb811 Mon Sep 17 00:00:00 2001 From: Abhinav Jain Date: Wed, 14 Aug 2024 13:37:43 +0530 Subject: [PATCH 282/562] selftest: af_unix: Fix kselftest compilation warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Change expected_buf from (const void *) to (const char *) in function __recvpair(). This change fixes the below warnings during test compilation: ``` In file included from msg_oob.c:14: msg_oob.c: In function ‘__recvpair’: ../../kselftest_harness.h:106:40: warning: format ‘%s’ expects argument of type ‘char *’,but argument 6 has type ‘const void *’ [-Wformat=] ../../kselftest_harness.h:101:17: note: in expansion of macro ‘__TH_LOG’ msg_oob.c:235:17: note: in expansion of macro ‘TH_LOG’ ../../kselftest_harness.h:106:40: warning: format ‘%s’ expects argument of type ‘char *’,but argument 6 has type ‘const void *’ [-Wformat=] ../../kselftest_harness.h:101:17: note: in expansion of macro ‘__TH_LOG’ msg_oob.c:259:25: note: in expansion of macro ‘TH_LOG’ ``` Fixes: d098d77232c3 ("selftest: af_unix: Add msg_oob.c.") Signed-off-by: Abhinav Jain Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20240814080743.1156166-1-jain.abhinav177@gmail.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/af_unix/msg_oob.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c index 16d0c172eaeb..535eb2c3d7d1 100644 --- a/tools/testing/selftests/net/af_unix/msg_oob.c +++ b/tools/testing/selftests/net/af_unix/msg_oob.c @@ -209,7 +209,7 @@ static void __sendpair(struct __test_metadata *_metadata, static void __recvpair(struct __test_metadata *_metadata, FIXTURE_DATA(msg_oob) *self, - const void *expected_buf, int expected_len, + const char *expected_buf, int expected_len, int buf_len, int flags) { int i, ret[2], recv_errno[2], expected_errno = 0; From 0863bffda1131fd2fa9c05b653ad9ee3d8db127e Mon Sep 17 00:00:00 2001 From: Griffin Kroah-Hartman Date: Wed, 14 Aug 2024 13:17:47 +0200 Subject: [PATCH 283/562] Revert "serial: 8250_omap: Set the console genpd always on if no console suspend" This reverts commit 68e6939ea9ec3d6579eadeab16060339cdeaf940. Kevin reported that this causes a crash during suspend on platforms that dont use PM domains. Link: https://lore.kernel.org/r/7ha5hgpchq.fsf@baylibre.com Cc: Thomas Richard Fixes: 68e6939ea9ec ("serial: 8250_omap: Set the console genpd always on if no console suspend") Cc: stable Reported-by: Kevin Hilman Signed-off-by: Griffin Kroah-Hartman Link: https://lore.kernel.org/r/20240814111747.82371-1-griffin@kroah.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_omap.c | 33 +++++------------------------ 1 file changed, 5 insertions(+), 28 deletions(-) diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 1af9aed99c65..afef1dd4ddf4 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -27,7 +27,6 @@ #include #include #include -#include #include "8250.h" @@ -119,12 +118,6 @@ #define UART_OMAP_TO_L 0x26 #define UART_OMAP_TO_H 0x27 -/* - * Copy of the genpd flags for the console. - * Only used if console suspend is disabled - */ -static unsigned int genpd_flags_console; - struct omap8250_priv { void __iomem *membase; int line; @@ -1655,7 +1648,6 @@ static int omap8250_suspend(struct device *dev) { struct omap8250_priv *priv = dev_get_drvdata(dev); struct uart_8250_port *up = serial8250_get_port(priv->line); - struct generic_pm_domain *genpd = pd_to_genpd(dev->pm_domain); int err = 0; serial8250_suspend_port(priv->line); @@ -1666,19 +1658,8 @@ static int omap8250_suspend(struct device *dev) if (!device_may_wakeup(dev)) priv->wer = 0; serial_out(up, UART_OMAP_WER, priv->wer); - if (uart_console(&up->port)) { - if (console_suspend_enabled) - err = pm_runtime_force_suspend(dev); - else { - /* - * The pd shall not be powered-off (no console suspend). - * Make copy of genpd flags before to set it always on. - * The original value is restored during the resume. - */ - genpd_flags_console = genpd->flags; - genpd->flags |= GENPD_FLAG_ALWAYS_ON; - } - } + if (uart_console(&up->port) && console_suspend_enabled) + err = pm_runtime_force_suspend(dev); flush_work(&priv->qos_work); return err; @@ -1688,16 +1669,12 @@ static int omap8250_resume(struct device *dev) { struct omap8250_priv *priv = dev_get_drvdata(dev); struct uart_8250_port *up = serial8250_get_port(priv->line); - struct generic_pm_domain *genpd = pd_to_genpd(dev->pm_domain); int err; if (uart_console(&up->port) && console_suspend_enabled) { - if (console_suspend_enabled) { - err = pm_runtime_force_resume(dev); - if (err) - return err; - } else - genpd->flags = genpd_flags_console; + err = pm_runtime_force_resume(dev); + if (err) + return err; } serial8250_resume_port(priv->line); From f75c235565f90c4a17b125e47f1c68ef6b8c2bce Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Wed, 14 Aug 2024 02:09:53 -0700 Subject: [PATCH 284/562] arm64: Fix KASAN random tag seed initialization Currently, kasan_init_sw_tags() is called before setup_per_cpu_areas(), so per_cpu(prng_state, cpu) accesses the same address regardless of the value of "cpu", and the same seed value gets copied to the percpu area for every CPU. Fix this by moving the call to smp_prepare_boot_cpu(), which is the first architecture hook after setup_per_cpu_areas(). Fixes: 3c9e3aa11094 ("kasan: add tag related helper functions") Fixes: 3f41b6093823 ("kasan: fix random seed generation for tag-based mode") Signed-off-by: Samuel Holland Reviewed-by: Andrey Konovalov Link: https://lore.kernel.org/r/20240814091005.969756-1-samuel.holland@sifive.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/setup.c | 3 --- arch/arm64/kernel/smp.c | 2 ++ 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index a096e2451044..b22d28ec8028 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -355,9 +355,6 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) smp_init_cpus(); smp_build_mpidr_hash(); - /* Init percpu seeds for random tags after cpus are set up. */ - kasan_init_sw_tags(); - #ifdef CONFIG_ARM64_SW_TTBR0_PAN /* * Make sure init_thread_info.ttbr0 always generates translation diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 5e18fbcee9a2..f01f0fd7b7fe 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -467,6 +467,8 @@ void __init smp_prepare_boot_cpu(void) init_gic_priority_masking(); kasan_init_hw_tags(); + /* Init percpu seeds for random tags after cpus are set up. */ + kasan_init_sw_tags(); } /* From 69139d2919dd4aa9a553c8245e7c63e82613e3fc Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sun, 11 Aug 2024 19:21:53 -0700 Subject: [PATCH 285/562] vsock: fix recursive ->recvmsg calls After a vsock socket has been added to a BPF sockmap, its prot->recvmsg has been replaced with vsock_bpf_recvmsg(). Thus the following recursiion could happen: vsock_bpf_recvmsg() -> __vsock_recvmsg() -> vsock_connectible_recvmsg() -> prot->recvmsg() -> vsock_bpf_recvmsg() again We need to fix it by calling the original ->recvmsg() without any BPF sockmap logic in __vsock_recvmsg(). Fixes: 634f1a7110b4 ("vsock: support sockmap") Reported-by: syzbot+bdb4bd87b5e22058e2a4@syzkaller.appspotmail.com Tested-by: syzbot+bdb4bd87b5e22058e2a4@syzkaller.appspotmail.com Cc: Bobby Eshleman Cc: Michael S. Tsirkin Cc: Stefano Garzarella Signed-off-by: Cong Wang Acked-by: Michael S. Tsirkin Link: https://patch.msgid.link/20240812022153.86512-1-xiyou.wangcong@gmail.com Signed-off-by: Paolo Abeni --- include/net/af_vsock.h | 4 ++++ net/vmw_vsock/af_vsock.c | 50 +++++++++++++++++++++++---------------- net/vmw_vsock/vsock_bpf.c | 4 ++-- 3 files changed, 35 insertions(+), 23 deletions(-) diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 535701efc1e5..24d970f7a4fa 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -230,8 +230,12 @@ struct vsock_tap { int vsock_add_tap(struct vsock_tap *vt); int vsock_remove_tap(struct vsock_tap *vt); void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque); +int __vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags); int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags); int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 4b040285aa78..0ff9b2dd86ba 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1270,25 +1270,28 @@ out: return err; } +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) +{ + struct sock *sk = sock->sk; + struct vsock_sock *vsk = vsock_sk(sk); + + return vsk->transport->dgram_dequeue(vsk, msg, len, flags); +} + int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { #ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; const struct proto *prot; -#endif - struct vsock_sock *vsk; - struct sock *sk; - sk = sock->sk; - vsk = vsock_sk(sk); - -#ifdef CONFIG_BPF_SYSCALL prot = READ_ONCE(sk->sk_prot); if (prot != &vsock_proto) return prot->recvmsg(sk, msg, len, flags, NULL); #endif - return vsk->transport->dgram_dequeue(vsk, msg, len, flags); + return __vsock_dgram_recvmsg(sock, msg, len, flags); } EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg); @@ -2174,15 +2177,12 @@ out: } int -vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +__vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; -#ifdef CONFIG_BPF_SYSCALL - const struct proto *prot; -#endif int err; sk = sock->sk; @@ -2233,14 +2233,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto out; } -#ifdef CONFIG_BPF_SYSCALL - prot = READ_ONCE(sk->sk_prot); - if (prot != &vsock_proto) { - release_sock(sk); - return prot->recvmsg(sk, msg, len, flags, NULL); - } -#endif - if (sk->sk_type == SOCK_STREAM) err = __vsock_stream_recvmsg(sk, msg, len, flags); else @@ -2250,6 +2242,22 @@ out: release_sock(sk); return err; } + +int +vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ +#ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; + const struct proto *prot; + + prot = READ_ONCE(sk->sk_prot); + if (prot != &vsock_proto) + return prot->recvmsg(sk, msg, len, flags, NULL); +#endif + + return __vsock_connectible_recvmsg(sock, msg, len, flags); +} EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg); static int vsock_set_rcvlowat(struct sock *sk, int val) diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index a3c97546ab84..c42c5cc18f32 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -64,9 +64,9 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int int err; if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) - err = vsock_connectible_recvmsg(sock, msg, len, flags); + err = __vsock_connectible_recvmsg(sock, msg, len, flags); else if (sk->sk_type == SOCK_DGRAM) - err = vsock_dgram_recvmsg(sock, msg, len, flags); + err = __vsock_dgram_recvmsg(sock, msg, len, flags); else err = -EPROTOTYPE; From fde25c20f51807db340b875953cfd1cedaa392fc Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Mon, 12 Aug 2024 17:08:24 +0300 Subject: [PATCH 286/562] net: ethtool: Allow write mechanism of LPL and both LPL and EPL CMIS 5.2 standard section 9.4.2 defines four types of firmware update supported mechanism: None, only LPL, only EPL, both LPL and EPL. Currently, only LPL (Local Payload) type of write firmware block is supported. However, if the module supports both LPL and EPL the flashing process wrongly fails for no supporting LPL. Fix that, by allowing the write mechanism to be LPL or both LPL and EPL. Fixes: c4f78134d45c ("ethtool: cmis_fw_update: add a layer for supporting firmware update using CDB") Reported-by: Vladyslav Mykhaliuk Signed-off-by: Danielle Ratson Reviewed-by: Petr Machata Link: https://patch.msgid.link/20240812140824.3718826-1-danieller@nvidia.com Signed-off-by: Paolo Abeni --- net/ethtool/cmis_fw_update.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/ethtool/cmis_fw_update.c b/net/ethtool/cmis_fw_update.c index ae4b4b28a601..655ff5224ffa 100644 --- a/net/ethtool/cmis_fw_update.c +++ b/net/ethtool/cmis_fw_update.c @@ -35,7 +35,10 @@ struct cmis_cdb_fw_mng_features_rpl { __be16 resv7; }; -#define CMIS_CDB_FW_WRITE_MECHANISM_LPL 0x01 +enum cmis_cdb_fw_write_mechanism { + CMIS_CDB_FW_WRITE_MECHANISM_LPL = 0x01, + CMIS_CDB_FW_WRITE_MECHANISM_BOTH = 0x11, +}; static int cmis_fw_update_fw_mng_features_get(struct ethtool_cmis_cdb *cdb, @@ -64,7 +67,8 @@ cmis_fw_update_fw_mng_features_get(struct ethtool_cmis_cdb *cdb, } rpl = (struct cmis_cdb_fw_mng_features_rpl *)args.req.payload; - if (!(rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_LPL)) { + if (!(rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_LPL || + rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_BOTH)) { ethnl_module_fw_flash_ntf_err(dev, ntf_params, "Write LPL is not supported", NULL); From 1f1b194284093d619c9fbc7e9e38b2c68d0408e8 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 12 Aug 2024 15:13:22 +0100 Subject: [PATCH 287/562] net: thunder_bgx: Fix netdev structure allocation Commit 94833addfaba ("net: thunderx: Unembed netdev structure") had a go at dynamically allocating the netdev structures for the thunderx_bgx driver. This change results in my ThunderX box catching fire (to be fair, it is what it does best). The issues with this change are that: - bgx_lmac_enable() is called *after* bgx_acpi_register_phy() and bgx_init_of_phy(), both expecting netdev to be a valid pointer. - bgx_init_of_phy() populates the MAC addresses for *all* LMACs attached to a given BGX instance, and thus needs netdev for each of them to have been allocated. There is a few things to be said about how the driver mixes LMAC and BGX states which leads to this sorry state, but that's beside the point. To address this, go back to a situation where all netdev structures are allocated before the driver starts relying on them, and move the freeing of these structures to driver removal. Someone brave enough can always go and restructure the driver if they want. Fixes: 94833addfaba ("net: thunderx: Unembed netdev structure") Signed-off-by: Marc Zyngier Cc: Breno Leitao Cc: Sunil Goutham Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Reviewed-by: Simon Horman Reviewed-by: Breno Leitao Link: https://patch.msgid.link/20240812141322.1742918-1-maz@kernel.org Signed-off-by: Paolo Abeni --- .../net/ethernet/cavium/thunder/thunder_bgx.c | 30 +++++++++++++------ 1 file changed, 21 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index a40c266c37f2..608cc6af5af1 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1054,18 +1054,12 @@ static int phy_interface_mode(u8 lmac_type) static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid) { - struct lmac *lmac, **priv; + struct lmac *lmac; u64 cfg; lmac = &bgx->lmac[lmacid]; lmac->bgx = bgx; - lmac->netdev = alloc_netdev_dummy(sizeof(struct lmac *)); - if (!lmac->netdev) - return -ENOMEM; - priv = netdev_priv(lmac->netdev); - *priv = lmac; - if ((lmac->lmac_type == BGX_MODE_SGMII) || (lmac->lmac_type == BGX_MODE_QSGMII) || (lmac->lmac_type == BGX_MODE_RGMII)) { @@ -1191,7 +1185,6 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid) (lmac->lmac_type != BGX_MODE_10G_KR) && lmac->phydev) phy_disconnect(lmac->phydev); - free_netdev(lmac->netdev); lmac->phydev = NULL; } @@ -1653,6 +1646,23 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) bgx_get_qlm_mode(bgx); + for (lmac = 0; lmac < bgx->lmac_count; lmac++) { + struct lmac *lmacp, **priv; + + lmacp = &bgx->lmac[lmac]; + lmacp->netdev = alloc_netdev_dummy(sizeof(struct lmac *)); + + if (!lmacp->netdev) { + for (int i = 0; i < lmac; i++) + free_netdev(bgx->lmac[i].netdev); + err = -ENOMEM; + goto err_enable; + } + + priv = netdev_priv(lmacp->netdev); + *priv = lmacp; + } + err = bgx_init_phy(bgx); if (err) goto err_enable; @@ -1692,8 +1702,10 @@ static void bgx_remove(struct pci_dev *pdev) u8 lmac; /* Disable all LMACs */ - for (lmac = 0; lmac < bgx->lmac_count; lmac++) + for (lmac = 0; lmac < bgx->lmac_count; lmac++) { bgx_lmac_disable(bgx, lmac); + free_netdev(bgx->lmac[lmac].netdev); + } pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx); From fd45cc614b8acca5bb435ba37fe9b3f9a17fab84 Mon Sep 17 00:00:00 2001 From: Alex Bee Date: Mon, 5 Aug 2024 13:08:56 +0200 Subject: [PATCH 288/562] drm/rockchip: inno-hdmi: Fix infoframe upload HDMI analyser shows that the AVI infoframe is no being longer send. The switch to the HDMI connector api should have used the frame content which is now given in the buffer parameter, but instead still uses the (now) empty and superfluous packed_frame variable. Fix it. Fixes: 65548c8ff0ab ("drm/rockchip: inno_hdmi: Switch to HDMI connector") Signed-off-by: Alex Bee Acked-by: Maxime Ripard Signed-off-by: Heiko Stuebner Link: https://patchwork.freedesktop.org/patch/msgid/20240805110855.274140-2-knaerzche@gmail.com --- drivers/gpu/drm/rockchip/inno_hdmi.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c index 2241e53a2946..dec6913cec5b 100644 --- a/drivers/gpu/drm/rockchip/inno_hdmi.c +++ b/drivers/gpu/drm/rockchip/inno_hdmi.c @@ -279,7 +279,6 @@ static int inno_hdmi_upload_frame(struct drm_connector *connector, const u8 *buffer, size_t len) { struct inno_hdmi *hdmi = connector_to_inno_hdmi(connector); - u8 packed_frame[HDMI_MAXIMUM_INFO_FRAME_SIZE]; ssize_t i; if (type != HDMI_INFOFRAME_TYPE_AVI) { @@ -291,8 +290,7 @@ static int inno_hdmi_upload_frame(struct drm_connector *connector, inno_hdmi_disable_frame(connector, type); for (i = 0; i < len; i++) - hdmi_writeb(hdmi, HDMI_CONTROL_PACKET_ADDR + i, - packed_frame[i]); + hdmi_writeb(hdmi, HDMI_CONTROL_PACKET_ADDR + i, buffer[i]); return 0; } From 52dd070c62e4ae2b5e7411b920e3f7a64235ecfb Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Wed, 14 Aug 2024 20:47:40 +0800 Subject: [PATCH 289/562] pmdomain: imx: wait SSAR when i.MX93 power domain on With "quiet" set in bootargs, there is power domain failure: "imx93_power_domain 44462400.power-domain: pd_off timeout: name: 44462400.power-domain, stat: 4" The current power on opertation takes ISO state as power on finished flag, but it is wrong. Before powering on operation really finishes, powering off comes and powering off will never finish because the last powering on still not finishes, so the following powering off actually not trigger hardware state machine to run. SSAR is the last step when powering on a domain, so need to wait SSAR done when powering on. Since EdgeLock Enclave(ELE) handshake is involved in the flow, enlarge the waiting time to 10ms for both on and off to avoid timeout. Cc: stable@vger.kernel.org Fixes: 0a0f7cc25d4a ("soc: imx: add i.MX93 SRC power domain driver") Reviewed-by: Jacky Bai Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/20240814124740.2778952-1-peng.fan@oss.nxp.com Signed-off-by: Ulf Hansson --- drivers/pmdomain/imx/imx93-pd.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/pmdomain/imx/imx93-pd.c b/drivers/pmdomain/imx/imx93-pd.c index 1e94b499c19b..d750a7dc58d2 100644 --- a/drivers/pmdomain/imx/imx93-pd.c +++ b/drivers/pmdomain/imx/imx93-pd.c @@ -20,6 +20,7 @@ #define FUNC_STAT_PSW_STAT_MASK BIT(0) #define FUNC_STAT_RST_STAT_MASK BIT(2) #define FUNC_STAT_ISO_STAT_MASK BIT(4) +#define FUNC_STAT_SSAR_STAT_MASK BIT(8) struct imx93_power_domain { struct generic_pm_domain genpd; @@ -50,7 +51,7 @@ static int imx93_pd_on(struct generic_pm_domain *genpd) writel(val, addr + MIX_SLICE_SW_CTRL_OFF); ret = readl_poll_timeout(addr + MIX_FUNC_STAT_OFF, val, - !(val & FUNC_STAT_ISO_STAT_MASK), 1, 10000); + !(val & FUNC_STAT_SSAR_STAT_MASK), 1, 10000); if (ret) { dev_err(domain->dev, "pd_on timeout: name: %s, stat: %x\n", genpd->name, val); return ret; @@ -72,7 +73,7 @@ static int imx93_pd_off(struct generic_pm_domain *genpd) writel(val, addr + MIX_SLICE_SW_CTRL_OFF); ret = readl_poll_timeout(addr + MIX_FUNC_STAT_OFF, val, - val & FUNC_STAT_PSW_STAT_MASK, 1, 1000); + val & FUNC_STAT_PSW_STAT_MASK, 1, 10000); if (ret) { dev_err(domain->dev, "pd_off timeout: name: %s, stat: %x\n", genpd->name, val); return ret; From cdc90f75387c42d64a0ed1ba03550ea9447249d4 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 13 Aug 2024 09:37:19 +0200 Subject: [PATCH 290/562] pse-core: Conditionally set current limit during PI regulator registration Fix an issue where `devm_regulator_register()` would fail for PSE controllers that do not support current limit control, such as simple GPIO-based controllers like the podl-pse-regulator. The `REGULATOR_CHANGE_CURRENT` flag and `max_uA` constraint are now conditionally set only if the `pi_set_current_limit` operation is supported. This change prevents the regulator registration routine from attempting to call `pse_pi_set_current_limit()`, which would return `-EOPNOTSUPP` and cause the registration to fail. Fixes: 4a83abcef5f4f ("net: pse-pd: Add new power limit get and set c33 features") Signed-off-by: Oleksij Rempel Reviewed-by: Kory Maincent Tested-by: Kyle Swenson Link: https://patch.msgid.link/20240813073719.2304633-1-o.rempel@pengutronix.de Signed-off-by: Paolo Abeni --- drivers/net/pse-pd/pse_core.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c index ec20953e0f82..4f032b16a8a0 100644 --- a/drivers/net/pse-pd/pse_core.c +++ b/drivers/net/pse-pd/pse_core.c @@ -401,9 +401,14 @@ devm_pse_pi_regulator_register(struct pse_controller_dev *pcdev, rdesc->ops = &pse_pi_ops; rdesc->owner = pcdev->owner; - rinit_data->constraints.valid_ops_mask = REGULATOR_CHANGE_STATUS | - REGULATOR_CHANGE_CURRENT; - rinit_data->constraints.max_uA = MAX_PI_CURRENT; + rinit_data->constraints.valid_ops_mask = REGULATOR_CHANGE_STATUS; + + if (pcdev->ops->pi_set_current_limit) { + rinit_data->constraints.valid_ops_mask |= + REGULATOR_CHANGE_CURRENT; + rinit_data->constraints.max_uA = MAX_PI_CURRENT; + } + rinit_data->supply_regulator = "vpwr"; rconfig.dev = pcdev->dev; From 7965a7f32a53d9ad807ce2c53bdda69ba104974f Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 13 Aug 2024 15:39:34 +0200 Subject: [PATCH 291/562] selftests: net: lib: kill PIDs before del netns When deleting netns, it is possible to still have some tasks running, e.g. background tasks like tcpdump running in the background, not stopped because the test has been interrupted. Before deleting the netns, it is then safer to kill all attached PIDs, if any. That should reduce some noises after the end of some tests, and help with the debugging of some issues. That's why this modification is seen as a "fix". Fixes: 25ae948b4478 ("selftests/net: add lib.sh") Acked-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Acked-by: Florian Westphal Reviewed-by: Hangbin Liu Link: https://patch.msgid.link/20240813-upstream-net-20240813-selftests-net-lib-kill-v1-1-27b689b248b8@kernel.org Signed-off-by: Paolo Abeni --- tools/testing/selftests/net/lib.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index d0219032f773..8ee4489238ca 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -146,6 +146,7 @@ cleanup_ns() for ns in "$@"; do [ -z "${ns}" ] && continue + ip netns pids "${ns}" 2> /dev/null | xargs -r kill || true ip netns delete "${ns}" &> /dev/null || true if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then echo "Warn: Failed to remove namespace $ns" From 8445d9d3c03101859663d34fda747f6a50947556 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Tue, 13 Aug 2024 22:10:20 +0800 Subject: [PATCH 292/562] net: hns3: fix wrong use of semaphore up Currently, if hns3 PF or VF FLR reset failed after five times retry, the reset done process will directly release the semaphore which has already released in hclge_reset_prepare_general. This will cause down operation fail. So this patch fixes it by adding reset state judgement. The up operation is only called after successful PF FLR reset. Fixes: 8627bdedc435 ("net: hns3: refactor the precedure of PF FLR") Fixes: f28368bb4542 ("net: hns3: refactor the procedure of VF FLR") Signed-off-by: Jie Wang Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 ++-- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 82574ce0194f..125e04434611 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -11516,8 +11516,8 @@ static void hclge_reset_done(struct hnae3_ae_dev *ae_dev) dev_err(&hdev->pdev->dev, "fail to rebuild, ret=%d\n", ret); hdev->reset_type = HNAE3_NONE_RESET; - clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state); - up(&hdev->reset_sem); + if (test_and_clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + up(&hdev->reset_sem); } static void hclge_clear_resetting_state(struct hclge_dev *hdev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 3735d2fed11f..094a7c7b5592 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1747,8 +1747,8 @@ static void hclgevf_reset_done(struct hnae3_ae_dev *ae_dev) ret); hdev->reset_type = HNAE3_NONE_RESET; - clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state); - up(&hdev->reset_sem); + if (test_and_clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) + up(&hdev->reset_sem); } static u32 hclgevf_get_fw_version(struct hnae3_handle *handle) From 30545e17eac1f50c5ef49644daf6af205100a965 Mon Sep 17 00:00:00 2001 From: Peiyang Wang Date: Tue, 13 Aug 2024 22:10:21 +0800 Subject: [PATCH 293/562] net: hns3: use the user's cfg after reset Consider the followed case that the user change speed and reset the net interface. Before the hw change speed successfully, the driver get old old speed from hw by timer task. After reset, the previous speed is config to hw. As a result, the new speed is configed successfully but lost after PF reset. The followed pictured shows more dirrectly. +------+ +----+ +----+ | USER | | PF | | HW | +---+--+ +-+--+ +-+--+ | ethtool -s 100G | | +------------------>| set speed 100G | | +--------------------->| | | set successfully | | |<---------------------+---+ | |query cfg (timer task)| | | +--------------------->| | handle speed | | return 200G | | changing event | ethtool --reset |<---------------------+ | (100G) +------------------>| cfg previous speed |<--+ | | after reset (200G) | | +--------------------->| | | +---+ | |query cfg (timer task)| | | +--------------------->| | handle speed | | return 100G | | changing event | |<---------------------+ | (200G) | | |<--+ | |query cfg (timer task)| | +--------------------->| | | return 200G | | |<---------------------+ | | | v v v This patch save new speed if hw change speed successfully, which will be used after reset successfully. Fixes: 2d03eacc0b7e ("net: hns3: Only update mac configuation when necessary") Signed-off-by: Peiyang Wang Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni --- .../hisilicon/hns3/hns3pf/hclge_main.c | 24 ++++++++++++++----- .../hisilicon/hns3/hns3pf/hclge_mdio.c | 3 +++ 2 files changed, 21 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 125e04434611..465f0d582283 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2653,8 +2653,17 @@ static int hclge_cfg_mac_speed_dup_h(struct hnae3_handle *handle, int speed, { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; + int ret; - return hclge_cfg_mac_speed_dup(hdev, speed, duplex, lane_num); + ret = hclge_cfg_mac_speed_dup(hdev, speed, duplex, lane_num); + + if (ret) + return ret; + + hdev->hw.mac.req_speed = speed; + hdev->hw.mac.req_duplex = duplex; + + return 0; } static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable) @@ -2956,17 +2965,20 @@ static int hclge_mac_init(struct hclge_dev *hdev) if (!test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) hdev->hw.mac.duplex = HCLGE_MAC_FULL; - ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed, - hdev->hw.mac.duplex, hdev->hw.mac.lane_num); - if (ret) - return ret; - if (hdev->hw.mac.support_autoneg) { ret = hclge_set_autoneg_en(hdev, hdev->hw.mac.autoneg); if (ret) return ret; } + if (!hdev->hw.mac.autoneg) { + ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.req_speed, + hdev->hw.mac.req_duplex, + hdev->hw.mac.lane_num); + if (ret) + return ret; + } + mac->link = 0; if (mac->user_fec_mode & BIT(HNAE3_FEC_USER_DEF)) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index 85fb11de43a1..80079657afeb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -191,6 +191,9 @@ static void hclge_mac_adjust_link(struct net_device *netdev) if (ret) netdev_err(netdev, "failed to adjust link.\n"); + hdev->hw.mac.req_speed = (u32)speed; + hdev->hw.mac.req_duplex = (u8)duplex; + ret = hclge_cfg_flowctrl(hdev); if (ret) netdev_err(netdev, "failed to configure flow control.\n"); From be5e816d00a506719e9dbb1a9c861c5ced30a109 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Tue, 13 Aug 2024 22:10:22 +0800 Subject: [PATCH 294/562] net: hns3: fix a deadlock problem when config TC during resetting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When config TC during the reset process, may cause a deadlock, the flow is as below: pf reset start │ ▼ ...... setup tc │ │ ▼ ▼ DOWN: napi_disable() napi_disable()(skip) │ │ │ ▼ ▼ ...... ...... │ │ ▼ │ napi_enable() │ ▼ UINIT: netif_napi_del() │ ▼ ...... │ ▼ INIT: netif_napi_add() │ ▼ ...... global reset start │ │ ▼ ▼ UP: napi_enable()(skip) ...... │ │ ▼ ▼ ...... napi_disable() In reset process, the driver will DOWN the port and then UINIT, in this case, the setup tc process will UP the port before UINIT, so cause the problem. Adds a DOWN process in UINIT to fix it. Fixes: bb6b94a896d4 ("net: hns3: Add reset interface implementation in client") Signed-off-by: Jie Wang Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index a5fc0209d628..4cbc4d069a1f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5724,6 +5724,9 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle) struct net_device *netdev = handle->kinfo.netdev; struct hns3_nic_priv *priv = netdev_priv(netdev); + if (!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) + hns3_nic_net_stop(netdev); + if (!test_and_clear_bit(HNS3_NIC_STATE_INITED, &priv->state)) { netdev_warn(netdev, "already uninitialized\n"); return 0; From 86db7bfb06704ef17340eeae71c832f21cfce35c Mon Sep 17 00:00:00 2001 From: Peiyang Wang Date: Tue, 13 Aug 2024 22:10:23 +0800 Subject: [PATCH 295/562] net: hns3: void array out of bound when loop tnl_num When query reg inf of SSU, it loops tnl_num times. However, tnl_num comes from hardware and the length of array is a fixed value. To void array out of bound, make sure the loop time is not greater than the length of array Signed-off-by: Peiyang Wang Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index e132c2f09560..cc7f46c0b35f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -1598,8 +1598,7 @@ static void hclge_query_reg_info_of_ssu(struct hclge_dev *hdev) { u32 loop_para[HCLGE_MOD_MSG_PARA_ARRAY_MAX_SIZE] = {0}; struct hclge_mod_reg_common_msg msg; - u8 i, j, num; - u32 loop_time; + u8 i, j, num, loop_time; num = ARRAY_SIZE(hclge_ssu_reg_common_msg); for (i = 0; i < num; i++) { @@ -1609,7 +1608,8 @@ static void hclge_query_reg_info_of_ssu(struct hclge_dev *hdev) loop_time = 1; loop_para[0] = 0; if (msg.need_para) { - loop_time = hdev->ae_dev->dev_specs.tnl_num; + loop_time = min(hdev->ae_dev->dev_specs.tnl_num, + HCLGE_MOD_MSG_PARA_ARRAY_MAX_SIZE); for (j = 0; j < loop_time; j++) loop_para[j] = j + 1; } From 7660833d217528c8f2385528951ab820a031e4e3 Mon Sep 17 00:00:00 2001 From: Peiyang Wang Date: Tue, 13 Aug 2024 22:10:24 +0800 Subject: [PATCH 296/562] net: hns3: use correct release function during uninitialization pci_request_regions is called to apply for PCI I/O and memory resources when the driver is initialized, Therefore, when the driver is uninstalled, pci_release_regions should be used to release PCI I/O and memory resources instead of pci_release_mem_regions is used to release memory reasouces only. Signed-off-by: Peiyang Wang Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 465f0d582283..6c33195a1168 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -11456,7 +11456,7 @@ static void hclge_pci_uninit(struct hclge_dev *hdev) pcim_iounmap(pdev, hdev->hw.hw.io_base); pci_free_irq_vectors(pdev); - pci_release_mem_regions(pdev); + pci_release_regions(pdev); pci_disable_device(pdev); } From ddeb7989a98faf8da67ac613731a0eee32667b7d Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Wed, 17 Jul 2024 07:04:28 -0700 Subject: [PATCH 297/562] drm/xe: Validate user fence during creation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fail invalid addresses during user fence creation. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Matthew Brost Reviewed-by: Thomas Hellström Reviewed-by: Nirmoy Das Link: https://patchwork.freedesktop.org/patch/msgid/20240717140429.1396820-1-matthew.brost@intel.com (cherry picked from commit 0fde907da2d5fd4da68845e96c6842497159c858) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_sync.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c index c4e018aa2982..e8d31e010860 100644 --- a/drivers/gpu/drm/xe/xe_sync.c +++ b/drivers/gpu/drm/xe/xe_sync.c @@ -53,14 +53,18 @@ static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr, u64 value) { struct xe_user_fence *ufence; + u64 __user *ptr = u64_to_user_ptr(addr); + + if (!access_ok(ptr, sizeof(ptr))) + return ERR_PTR(-EFAULT); ufence = kmalloc(sizeof(*ufence), GFP_KERNEL); if (!ufence) - return NULL; + return ERR_PTR(-ENOMEM); ufence->xe = xe; kref_init(&ufence->refcount); - ufence->addr = u64_to_user_ptr(addr); + ufence->addr = ptr; ufence->value = value; ufence->mm = current->mm; mmgrab(ufence->mm); @@ -183,8 +187,8 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef, } else { sync->ufence = user_fence_create(xe, sync_in.addr, sync_in.timeline_value); - if (XE_IOCTL_DBG(xe, !sync->ufence)) - return -ENOMEM; + if (XE_IOCTL_DBG(xe, IS_ERR(sync->ufence))) + return PTR_ERR(sync->ufence); } break; From e98a032c0340d45c199f4eb536359f5762a8748f Mon Sep 17 00:00:00 2001 From: Umesh Nerlige Ramappa Date: Thu, 18 Jul 2024 14:05:45 -0700 Subject: [PATCH 298/562] drm/xe: Move part of xe_file cleanup to a helper In order to make xe_file ref counted, move destruction of xe_file members to a helper. v2: Move xe_vm_close_and_put back into xe_file_close (Matt) Signed-off-by: Umesh Nerlige Ramappa Reviewed-by: Matthew Brost Reviewed-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20240718210548.3580382-2-umesh.nerlige.ramappa@intel.com Signed-off-by: Lucas De Marchi (cherry picked from commit 3d0c4a62cc553c6ffde4cb11620eba991e770665) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_device.c | 29 ++++++++++++++++++----------- 1 file changed, 18 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 76109415eba6..452dbc1b495b 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -90,9 +90,25 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file) return 0; } +static void xe_file_destroy(struct xe_file *xef) +{ + struct xe_device *xe = xef->xe; + + xa_destroy(&xef->exec_queue.xa); + mutex_destroy(&xef->exec_queue.lock); + xa_destroy(&xef->vm.xa); + mutex_destroy(&xef->vm.lock); + + spin_lock(&xe->clients.lock); + xe->clients.count--; + spin_unlock(&xe->clients.lock); + + xe_drm_client_put(xef->client); + kfree(xef); +} + static void xe_file_close(struct drm_device *dev, struct drm_file *file) { - struct xe_device *xe = to_xe_device(dev); struct xe_file *xef = file->driver_priv; struct xe_vm *vm; struct xe_exec_queue *q; @@ -108,21 +124,12 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file) xe_exec_queue_kill(q); xe_exec_queue_put(q); } - xa_destroy(&xef->exec_queue.xa); - mutex_destroy(&xef->exec_queue.lock); mutex_lock(&xef->vm.lock); xa_for_each(&xef->vm.xa, idx, vm) xe_vm_close_and_put(vm); mutex_unlock(&xef->vm.lock); - xa_destroy(&xef->vm.xa); - mutex_destroy(&xef->vm.lock); - spin_lock(&xe->clients.lock); - xe->clients.count--; - spin_unlock(&xe->clients.lock); - - xe_drm_client_put(xef->client); - kfree(xef); + xe_file_destroy(xef); } static const struct drm_ioctl_desc xe_ioctls[] = { From d28bb0120f360e772458a7cf295d6d0ae3dc18a4 Mon Sep 17 00:00:00 2001 From: Umesh Nerlige Ramappa Date: Thu, 18 Jul 2024 14:05:46 -0700 Subject: [PATCH 299/562] drm/xe: Add ref counting for xe_file Add ref counting for xe_file. v2: - Add kernel doc for exported functions (Matt) - Instead of xe_file_destroy, export the get/put helpers (Lucas) v3: Fixup the kernel-doc format and description (Matt, Lucas) Signed-off-by: Umesh Nerlige Ramappa Reviewed-by: Matthew Brost Link: https://patchwork.freedesktop.org/patch/msgid/20240718210548.3580382-3-umesh.nerlige.ramappa@intel.com Signed-off-by: Lucas De Marchi (cherry picked from commit ce8c161cbad43f4056451e541f7ae3471d0cca12) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_device.c | 33 ++++++++++++++++++++++++++-- drivers/gpu/drm/xe/xe_device.h | 3 +++ drivers/gpu/drm/xe/xe_device_types.h | 3 +++ 3 files changed, 37 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 452dbc1b495b..4178bd05701e 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -87,11 +87,14 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file) spin_unlock(&xe->clients.lock); file->driver_priv = xef; + kref_init(&xef->refcount); + return 0; } -static void xe_file_destroy(struct xe_file *xef) +static void xe_file_destroy(struct kref *ref) { + struct xe_file *xef = container_of(ref, struct xe_file, refcount); struct xe_device *xe = xef->xe; xa_destroy(&xef->exec_queue.xa); @@ -107,6 +110,32 @@ static void xe_file_destroy(struct xe_file *xef) kfree(xef); } +/** + * xe_file_get() - Take a reference to the xe file object + * @xef: Pointer to the xe file + * + * Anyone with a pointer to xef must take a reference to the xe file + * object using this call. + * + * Return: xe file pointer + */ +struct xe_file *xe_file_get(struct xe_file *xef) +{ + kref_get(&xef->refcount); + return xef; +} + +/** + * xe_file_put() - Drop a reference to the xe file object + * @xef: Pointer to the xe file + * + * Used to drop reference to the xef object + */ +void xe_file_put(struct xe_file *xef) +{ + kref_put(&xef->refcount, xe_file_destroy); +} + static void xe_file_close(struct drm_device *dev, struct drm_file *file) { struct xe_file *xef = file->driver_priv; @@ -129,7 +158,7 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file) xe_vm_close_and_put(vm); mutex_unlock(&xef->vm.lock); - xe_file_destroy(xef); + xe_file_put(xef); } static const struct drm_ioctl_desc xe_ioctls[] = { diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h index bb07f5669dbb..b3952718b3c1 100644 --- a/drivers/gpu/drm/xe/xe_device.h +++ b/drivers/gpu/drm/xe/xe_device.h @@ -170,4 +170,7 @@ static inline bool xe_device_wedged(struct xe_device *xe) void xe_device_declare_wedged(struct xe_device *xe); +struct xe_file *xe_file_get(struct xe_file *xef); +void xe_file_put(struct xe_file *xef); + #endif diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 3bca6d344744..cbc582bcc90a 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -566,6 +566,9 @@ struct xe_file { /** @client: drm client */ struct xe_drm_client *client; + + /** @refcount: ref count of this xe file */ + struct kref refcount; }; #endif From 6309f9b1fc4de2daa1293fe12a488d765e60507d Mon Sep 17 00:00:00 2001 From: Umesh Nerlige Ramappa Date: Thu, 18 Jul 2024 14:05:47 -0700 Subject: [PATCH 300/562] drm/xe: Take a ref to xe file when user creates a VM Take a reference to xef when user creates the VM and put the reference when user destroys the VM. Signed-off-by: Umesh Nerlige Ramappa Reviewed-by: Matthew Brost Reviewed-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20240718210548.3580382-4-umesh.nerlige.ramappa@intel.com Signed-off-by: Lucas De Marchi (cherry picked from commit a2387e69493df3de706f14e4573ee123d23d5d34) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_vm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 5b166fa03684..6bfcbd4e778a 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -1601,6 +1601,10 @@ static void vm_destroy_work_func(struct work_struct *w) XE_WARN_ON(vm->pt_root[id]); trace_xe_vm_free(vm); + + if (vm->xef) + xe_file_put(vm->xef); + kfree(vm); } @@ -1916,7 +1920,7 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data, } args->vm_id = id; - vm->xef = xef; + vm->xef = xe_file_get(xef); /* Record BO memory for VM pagetable created against client */ for_each_tile(tile, xe, id) From 817c70e2ba278e9d5360833b1137ef8855ac1728 Mon Sep 17 00:00:00 2001 From: Umesh Nerlige Ramappa Date: Thu, 18 Jul 2024 14:05:48 -0700 Subject: [PATCH 301/562] drm/xe: Fix use after free when client stats are captured xe_file_close triggers an asynchronous queue cleanup and then frees up the xef object. Since queue cleanup flushes all pending jobs and the KMD stores client usage stats into the xef object after jobs are flushed, we see a use-after-free for the xef object. Resolve this by taking a reference to xef from xe_exec_queue. While at it, revert an earlier change that contained a partial work around for this issue. v2: - Take a ref to xef even for the VM bind queue (Matt) - Squash patches relevant to that fix and work around (Lucas) v3: Fix typo (Lucas) Fixes: ce62827bc294 ("drm/xe: Do not access xe file when updating exec queue run_ticks") Fixes: 6109f24f87d7 ("drm/xe: Add helper to accumulate exec queue runtime") Closes: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1908 Signed-off-by: Umesh Nerlige Ramappa Reviewed-by: Matthew Brost Reviewed-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20240718210548.3580382-5-umesh.nerlige.ramappa@intel.com Signed-off-by: Lucas De Marchi (cherry picked from commit 2149ded63079449b8dddf9da38392632f155e6b5) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_drm_client.c | 5 +---- drivers/gpu/drm/xe/xe_exec_queue.c | 10 +++++++++- drivers/gpu/drm/xe/xe_exec_queue_types.h | 7 +++---- 3 files changed, 13 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c index 6a26923fa10e..7ddd59908334 100644 --- a/drivers/gpu/drm/xe/xe_drm_client.c +++ b/drivers/gpu/drm/xe/xe_drm_client.c @@ -251,11 +251,8 @@ static void show_run_ticks(struct drm_printer *p, struct drm_file *file) /* Accumulate all the exec queues from this client */ mutex_lock(&xef->exec_queue.lock); - xa_for_each(&xef->exec_queue.xa, i, q) { + xa_for_each(&xef->exec_queue.xa, i, q) xe_exec_queue_update_run_ticks(q); - xef->run_ticks[q->class] += q->run_ticks - q->old_run_ticks; - q->old_run_ticks = q->run_ticks; - } mutex_unlock(&xef->exec_queue.lock); /* Get the total GPU cycles */ diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 0ba37835849b..a39384bb9553 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -37,6 +37,10 @@ static void __xe_exec_queue_free(struct xe_exec_queue *q) { if (q->vm) xe_vm_put(q->vm); + + if (q->xef) + xe_file_put(q->xef); + kfree(q); } @@ -649,6 +653,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, goto kill_exec_queue; args->exec_queue_id = id; + q->xef = xe_file_get(xef); return 0; @@ -762,6 +767,7 @@ bool xe_exec_queue_is_idle(struct xe_exec_queue *q) */ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q) { + struct xe_file *xef; struct xe_lrc *lrc; u32 old_ts, new_ts; @@ -773,6 +779,8 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q) if (!q->vm || !q->vm->xef) return; + xef = q->vm->xef; + /* * Only sample the first LRC. For parallel submission, all of them are * scheduled together and we compensate that below by multiplying by @@ -783,7 +791,7 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q) */ lrc = q->lrc[0]; new_ts = xe_lrc_update_timestamp(lrc, &old_ts); - q->run_ticks += (new_ts - old_ts) * q->width; + xef->run_ticks[q->class] += (new_ts - old_ts) * q->width; } void xe_exec_queue_kill(struct xe_exec_queue *q) diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index 201588ec33c3..a35ce24c9798 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -38,6 +38,9 @@ enum xe_exec_queue_priority { * a kernel object. */ struct xe_exec_queue { + /** @xef: Back pointer to xe file if this is user created exec queue */ + struct xe_file *xef; + /** @gt: graphics tile this exec queue can submit to */ struct xe_gt *gt; /** @@ -139,10 +142,6 @@ struct xe_exec_queue { * Protected by @vm's resv. Unused if @vm == NULL. */ u64 tlb_flush_seqno; - /** @old_run_ticks: prior hw engine class run time in ticks for this exec queue */ - u64 old_run_ticks; - /** @run_ticks: hw engine class run time in ticks for this exec queue */ - u64 run_ticks; /** @lrc: logical ring context for this exec queue */ struct xe_lrc *lrc[]; }; From 64da63cd3f7d771bf8f240e72203da1f72aa3728 Mon Sep 17 00:00:00 2001 From: Michal Wajdeczko Date: Thu, 18 Jul 2024 22:31:55 +0200 Subject: [PATCH 302/562] drm/xe/vf: Fix register value lookup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We should use the number of actual entries stored in the runtime register buffer, not the maximum number of entries that this buffer can hold, otherwise bsearch() may fail and we may miss the data and wrongly report unexpected access to some registers. Fixes: 4edadc41a3a4 ("drm/xe/vf: Use register values obtained from the PF") Signed-off-by: Michal Wajdeczko Cc: Piotr Piórkowski Cc: Matt Roper Reviewed-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20240718203155.486-1-michal.wajdeczko@intel.com (cherry picked from commit ad16682db18f4414e53bba1ce0db75b08bdc4dff) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c index 41e46a00c01e..8892d6c2291e 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c @@ -850,7 +850,7 @@ static struct vf_runtime_reg *vf_lookup_reg(struct xe_gt *gt, u32 addr) xe_gt_assert(gt, IS_SRIOV_VF(gt_to_xe(gt))); - return bsearch(&key, runtime->regs, runtime->regs_size, sizeof(key), + return bsearch(&key, runtime->regs, runtime->num_regs, sizeof(key), vf_runtime_reg_cmp); } From 55ea73aacfb9a92def840a7110a468c5a76caeb5 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Fri, 19 Jul 2024 10:29:05 -0700 Subject: [PATCH 303/562] drm/xe: Build PM into GuC CT layer Take PM ref when any G2H are outstanding, drop when none are outstanding. To safely ensure we have PM ref when in the GuC CT layer, a PM ref needs to be held when scheduler messages are pending too. v2: - Add outer PM protections to xe_file_close (CI) v3: - Only take PM ref 0->1 and drop on 1->0 (Matthew Auld) v4: - Add assert to G2H increment function v5: - Rebase v6: - Declare xe as local variable in xe_file_close (CI) Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: Matthew Auld Cc: Rodrigo Vivi Cc: Nirmoy Das Signed-off-by: Matthew Brost Reviewed-by: Matthew Auld Reviewed-by: Nirmoy Das Link: https://patchwork.freedesktop.org/patch/msgid/20240719172905.1527927-5-matthew.brost@intel.com (cherry picked from commit d930c19fdff3109e97b610fa10943b7602efcabd) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_device.c | 5 +++++ drivers/gpu/drm/xe/xe_guc_ct.c | 10 +++++++++- drivers/gpu/drm/xe/xe_guc_submit.c | 4 ++++ 3 files changed, 18 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 4178bd05701e..f2f1d8ddb221 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -138,11 +138,14 @@ void xe_file_put(struct xe_file *xef) static void xe_file_close(struct drm_device *dev, struct drm_file *file) { + struct xe_device *xe = to_xe_device(dev); struct xe_file *xef = file->driver_priv; struct xe_vm *vm; struct xe_exec_queue *q; unsigned long idx; + xe_pm_runtime_get(xe); + /* * No need for exec_queue.lock here as there is no contention for it * when FD is closing as IOCTLs presumably can't be modifying the @@ -159,6 +162,8 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file) mutex_unlock(&xef->vm.lock); xe_file_put(xef); + + xe_pm_runtime_put(xe); } static const struct drm_ioctl_desc xe_ioctls[] = { diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index 7d2e937da1d8..64afc90ad2c5 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -327,6 +327,8 @@ static void xe_guc_ct_set_state(struct xe_guc_ct *ct, xe_gt_assert(ct_to_gt(ct), ct->g2h_outstanding == 0 || state == XE_GUC_CT_STATE_STOPPED); + if (ct->g2h_outstanding) + xe_pm_runtime_put(ct_to_xe(ct)); ct->g2h_outstanding = 0; ct->state = state; @@ -495,10 +497,15 @@ static void h2g_reserve_space(struct xe_guc_ct *ct, u32 cmd_len) static void __g2h_reserve_space(struct xe_guc_ct *ct, u32 g2h_len, u32 num_g2h) { xe_gt_assert(ct_to_gt(ct), g2h_len <= ct->ctbs.g2h.info.space); + xe_gt_assert(ct_to_gt(ct), (!g2h_len && !num_g2h) || + (g2h_len && num_g2h)); if (g2h_len) { lockdep_assert_held(&ct->fast_lock); + if (!ct->g2h_outstanding) + xe_pm_runtime_get_noresume(ct_to_xe(ct)); + ct->ctbs.g2h.info.space -= g2h_len; ct->g2h_outstanding += num_g2h; } @@ -511,7 +518,8 @@ static void __g2h_release_space(struct xe_guc_ct *ct, u32 g2h_len) ct->ctbs.g2h.info.size - ct->ctbs.g2h.info.resv_space); ct->ctbs.g2h.info.space += g2h_len; - --ct->g2h_outstanding; + if (!--ct->g2h_outstanding) + xe_pm_runtime_put(ct_to_xe(ct)); } static void g2h_release_space(struct xe_guc_ct *ct, u32 g2h_len) diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 8d7e7f4bbff7..6398629e6b4e 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -1393,6 +1393,8 @@ static void guc_exec_queue_process_msg(struct xe_sched_msg *msg) default: XE_WARN_ON("Unknown message type"); } + + xe_pm_runtime_put(guc_to_xe(exec_queue_to_guc(msg->private_data))); } static const struct drm_sched_backend_ops drm_sched_ops = { @@ -1482,6 +1484,8 @@ static void guc_exec_queue_kill(struct xe_exec_queue *q) static void guc_exec_queue_add_msg(struct xe_exec_queue *q, struct xe_sched_msg *msg, u32 opcode) { + xe_pm_runtime_get_noresume(guc_to_xe(exec_queue_to_guc(q))); + INIT_LIST_HEAD(&msg->link); msg->opcode = opcode; msg->private_data = q; From 4f7652dcd339aca6678084d42fda999ecb19b624 Mon Sep 17 00:00:00 2001 From: Michal Wajdeczko Date: Tue, 6 Aug 2024 20:05:16 +0200 Subject: [PATCH 304/562] drm/xe/pf: Fix VF config validation on multi-GT platforms MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When validating VF config on the media GT, we may wrongly report that VF is already partially configured on it, as we consider GGTT and LMEM provisioning done on the primary GT (since both GGTT and LMEM are tile-level resources, not a GT-level). This will cause skipping a VF auto-provisioning on the media-GT and in result will block a VF from successfully initialize that GT. Fix that by considering GGTT and LMEM configurations only when checking if a VF provisioning is complete, and omit GGTT and LMEM when reporting empty/partial provisioning. Fixes: 234670cea9a2 ("drm/xe/pf: Skip fair VFs provisioning if already provisioned") Signed-off-by: Michal Wajdeczko Cc: Piotr Piórkowski Reviewed-by: Jonathan Cavitt Link: https://patchwork.freedesktop.org/patch/msgid/20240806180516.618-1-michal.wajdeczko@intel.com (cherry picked from commit 5bdacb0907c1f531995b6ba47b832ac3a0182ae9) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c index 4699b7836001..b6f0a7299c03 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c @@ -1927,6 +1927,7 @@ static int pf_validate_vf_config(struct xe_gt *gt, unsigned int vfid) { struct xe_gt *primary_gt = gt_to_tile(gt)->primary_gt; struct xe_device *xe = gt_to_xe(gt); + bool is_primary = !xe_gt_is_media_type(gt); bool valid_ggtt, valid_ctxs, valid_dbs; bool valid_any, valid_all; @@ -1935,13 +1936,17 @@ static int pf_validate_vf_config(struct xe_gt *gt, unsigned int vfid) valid_dbs = pf_get_vf_config_dbs(gt, vfid); /* note that GuC doorbells are optional */ - valid_any = valid_ggtt || valid_ctxs || valid_dbs; - valid_all = valid_ggtt && valid_ctxs; + valid_any = valid_ctxs || valid_dbs; + valid_all = valid_ctxs; + + /* and GGTT/LMEM is configured on primary GT only */ + valid_all = valid_all && valid_ggtt; + valid_any = valid_any || (valid_ggtt && is_primary); if (IS_DGFX(xe)) { bool valid_lmem = pf_get_vf_config_ggtt(primary_gt, vfid); - valid_any = valid_any || valid_lmem; + valid_any = valid_any || (valid_lmem && is_primary); valid_all = valid_all && valid_lmem; } From 90be4cc6f7674a1478c4c750beeee3edd14aee38 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Fri, 19 Jul 2024 10:29:02 -0700 Subject: [PATCH 305/562] drm/xe: Add xe_gt_tlb_invalidation_fence_init helper Other layers should not be touching struct xe_gt_tlb_invalidation_fence directly, add helper for initialization. v2: - Add dma_fence_get and list init to xe_gt_tlb_invalidation_fence_init Signed-off-by: Matthew Brost Reviewed-by: Nirmoy Das Link: https://patchwork.freedesktop.org/patch/msgid/20240719172905.1527927-2-matthew.brost@intel.com (cherry picked from commit a522b285c6b4b611406d59612a8d7241714d2e31) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 36 +++++++++++++++++++++ drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h | 3 ++ drivers/gpu/drm/xe/xe_pt.c | 26 +-------------- 3 files changed, 40 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index d9359976ab8b..92a18a0e4acd 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -508,3 +508,39 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len) return 0; } + +static const char * +invalidation_fence_get_driver_name(struct dma_fence *dma_fence) +{ + return "xe"; +} + +static const char * +invalidation_fence_get_timeline_name(struct dma_fence *dma_fence) +{ + return "invalidation_fence"; +} + +static const struct dma_fence_ops invalidation_fence_ops = { + .get_driver_name = invalidation_fence_get_driver_name, + .get_timeline_name = invalidation_fence_get_timeline_name, +}; + +/** + * xe_gt_tlb_invalidation_fence_init - Initialize TLB invalidation fence + * @gt: GT + * @fence: TLB invalidation fence to initialize + * + * Initialize TLB invalidation fence for use + */ +void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt, + struct xe_gt_tlb_invalidation_fence *fence) +{ + spin_lock_irq(>->tlb_invalidation.lock); + dma_fence_init(&fence->base, &invalidation_fence_ops, + >->tlb_invalidation.lock, + dma_fence_context_alloc(1), 1); + spin_unlock_irq(>->tlb_invalidation.lock); + INIT_LIST_HEAD(&fence->link); + dma_fence_get(&fence->base); +} diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h index bf3bebd9f985..948f4a2f5214 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h @@ -26,4 +26,7 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt, int xe_gt_tlb_invalidation_wait(struct xe_gt *gt, int seqno); int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len); +void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt, + struct xe_gt_tlb_invalidation_fence *fence); + #endif /* _XE_GT_TLB_INVALIDATION_ */ diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index ade9e7a3a0ad..4c17a1ec8f8b 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -1115,23 +1115,6 @@ struct invalidation_fence { u32 asid; }; -static const char * -invalidation_fence_get_driver_name(struct dma_fence *dma_fence) -{ - return "xe"; -} - -static const char * -invalidation_fence_get_timeline_name(struct dma_fence *dma_fence) -{ - return "invalidation_fence"; -} - -static const struct dma_fence_ops invalidation_fence_ops = { - .get_driver_name = invalidation_fence_get_driver_name, - .get_timeline_name = invalidation_fence_get_timeline_name, -}; - static void invalidation_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb) { @@ -1170,15 +1153,8 @@ static int invalidation_fence_init(struct xe_gt *gt, trace_xe_gt_tlb_invalidation_fence_create(gt_to_xe(gt), &ifence->base); - spin_lock_irq(>->tlb_invalidation.lock); - dma_fence_init(&ifence->base.base, &invalidation_fence_ops, - >->tlb_invalidation.lock, - dma_fence_context_alloc(1), 1); - spin_unlock_irq(>->tlb_invalidation.lock); + xe_gt_tlb_invalidation_fence_init(gt, &ifence->base); - INIT_LIST_HEAD(&ifence->base.link); - - dma_fence_get(&ifence->base.base); /* Ref for caller */ ifence->fence = fence; ifence->gt = gt; ifence->start = start; From 58bfe6674467f4c037e89111e6007f25b34d8bb3 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Fri, 19 Jul 2024 10:29:03 -0700 Subject: [PATCH 306/562] drm/xe: Drop xe_gt_tlb_invalidation_wait Having two methods to wait on GT TLB invalidations is not ideal. Remove xe_gt_tlb_invalidation_wait and only use GT TLB invalidation fences. In addition to two methods being less than ideal, once GT TLB invalidations are coalesced the seqno cannot be assigned during xe_gt_tlb_invalidation_ggtt/range. Thus xe_gt_tlb_invalidation_wait would not have a seqno to wait one. A fence however can be armed and later signaled. v3: - Add explaination about coalescing to commit message v4: - Don't put dma fence if defined on stack (CI) v5: - Initialize ret to zero (CI) v6: - Use invalidation_fence_signal helper in tlb timeout (Matthew Auld) Signed-off-by: Matthew Brost Reviewed-by: Nirmoy Das Link: https://patchwork.freedesktop.org/patch/msgid/20240719172905.1527927-3-matthew.brost@intel.com (cherry picked from commit 61ac035361ae555ee5a17a7667fe96afdde3d59a) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 148 ++++++++------------ drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h | 10 +- drivers/gpu/drm/xe/xe_pt.c | 2 +- drivers/gpu/drm/xe/xe_vm.c | 30 ++-- 4 files changed, 80 insertions(+), 110 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index 92a18a0e4acd..c3419d4412ce 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -17,6 +17,8 @@ #include "xe_trace.h" #include "regs/xe_guc_regs.h" +#define FENCE_STACK_BIT DMA_FENCE_FLAG_USER_BITS + /* * TLB inval depends on pending commands in the CT queue and then the real * invalidation time. Double up the time to process full CT queue @@ -33,6 +35,23 @@ static long tlb_timeout_jiffies(struct xe_gt *gt) return hw_tlb_timeout + 2 * delay; } +static void +__invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence) +{ + bool stack = test_bit(FENCE_STACK_BIT, &fence->base.flags); + + trace_xe_gt_tlb_invalidation_fence_signal(xe, fence); + dma_fence_signal(&fence->base); + if (!stack) + dma_fence_put(&fence->base); +} + +static void +invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence) +{ + list_del(&fence->link); + __invalidation_fence_signal(xe, fence); +} static void xe_gt_tlb_fence_timeout(struct work_struct *work) { @@ -54,10 +73,8 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work) xe_gt_err(gt, "TLB invalidation fence timeout, seqno=%d recv=%d", fence->seqno, gt->tlb_invalidation.seqno_recv); - list_del(&fence->link); fence->base.error = -ETIME; - dma_fence_signal(&fence->base); - dma_fence_put(&fence->base); + invalidation_fence_signal(xe, fence); } if (!list_empty(>->tlb_invalidation.pending_fences)) queue_delayed_work(system_wq, @@ -87,21 +104,6 @@ int xe_gt_tlb_invalidation_init(struct xe_gt *gt) return 0; } -static void -__invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence) -{ - trace_xe_gt_tlb_invalidation_fence_signal(xe, fence); - dma_fence_signal(&fence->base); - dma_fence_put(&fence->base); -} - -static void -invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence) -{ - list_del(&fence->link); - __invalidation_fence_signal(xe, fence); -} - /** * xe_gt_tlb_invalidation_reset - Initialize GT TLB invalidation reset * @gt: graphics tile @@ -111,7 +113,6 @@ invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fe void xe_gt_tlb_invalidation_reset(struct xe_gt *gt) { struct xe_gt_tlb_invalidation_fence *fence, *next; - struct xe_guc *guc = >->uc.guc; int pending_seqno; /* @@ -134,7 +135,6 @@ void xe_gt_tlb_invalidation_reset(struct xe_gt *gt) else pending_seqno = gt->tlb_invalidation.seqno - 1; WRITE_ONCE(gt->tlb_invalidation.seqno_recv, pending_seqno); - wake_up_all(&guc->ct.wq); list_for_each_entry_safe(fence, next, >->tlb_invalidation.pending_fences, link) @@ -165,6 +165,8 @@ static int send_tlb_invalidation(struct xe_guc *guc, int seqno; int ret; + xe_gt_assert(gt, fence); + /* * XXX: The seqno algorithm relies on TLB invalidation being processed * in order which they currently are, if that changes the algorithm will @@ -173,10 +175,8 @@ static int send_tlb_invalidation(struct xe_guc *guc, mutex_lock(&guc->ct.lock); seqno = gt->tlb_invalidation.seqno; - if (fence) { - fence->seqno = seqno; - trace_xe_gt_tlb_invalidation_fence_send(xe, fence); - } + fence->seqno = seqno; + trace_xe_gt_tlb_invalidation_fence_send(xe, fence); action[1] = seqno; ret = xe_guc_ct_send_locked(&guc->ct, action, len, G2H_LEN_DW_TLB_INVALIDATE, 1); @@ -209,7 +209,6 @@ static int send_tlb_invalidation(struct xe_guc *guc, TLB_INVALIDATION_SEQNO_MAX; if (!gt->tlb_invalidation.seqno) gt->tlb_invalidation.seqno = 1; - ret = seqno; } mutex_unlock(&guc->ct.lock); @@ -223,14 +222,16 @@ static int send_tlb_invalidation(struct xe_guc *guc, /** * xe_gt_tlb_invalidation_guc - Issue a TLB invalidation on this GT for the GuC * @gt: graphics tile + * @fence: invalidation fence which will be signal on TLB invalidation + * completion * * Issue a TLB invalidation for the GuC. Completion of TLB is asynchronous and - * caller can use seqno + xe_gt_tlb_invalidation_wait to wait for completion. + * caller can use the invalidation fence to wait for completion. * - * Return: Seqno which can be passed to xe_gt_tlb_invalidation_wait on success, - * negative error code on error. + * Return: 0 on success, negative error code on error */ -static int xe_gt_tlb_invalidation_guc(struct xe_gt *gt) +static int xe_gt_tlb_invalidation_guc(struct xe_gt *gt, + struct xe_gt_tlb_invalidation_fence *fence) { u32 action[] = { XE_GUC_ACTION_TLB_INVALIDATION, @@ -238,7 +239,7 @@ static int xe_gt_tlb_invalidation_guc(struct xe_gt *gt) MAKE_INVAL_OP(XE_GUC_TLB_INVAL_GUC), }; - return send_tlb_invalidation(>->uc.guc, NULL, action, + return send_tlb_invalidation(>->uc.guc, fence, action, ARRAY_SIZE(action)); } @@ -257,13 +258,15 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt) if (xe_guc_ct_enabled(>->uc.guc.ct) && gt->uc.guc.submission_state.enabled) { - int seqno; + struct xe_gt_tlb_invalidation_fence fence; + int ret; - seqno = xe_gt_tlb_invalidation_guc(gt); - if (seqno <= 0) - return seqno; + xe_gt_tlb_invalidation_fence_init(gt, &fence, true); + ret = xe_gt_tlb_invalidation_guc(gt, &fence); + if (ret < 0) + return ret; - xe_gt_tlb_invalidation_wait(gt, seqno); + xe_gt_tlb_invalidation_fence_wait(&fence); } else if (xe_device_uc_enabled(xe) && !xe_device_wedged(xe)) { if (IS_SRIOV_VF(xe)) return 0; @@ -290,18 +293,16 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt) * * @gt: graphics tile * @fence: invalidation fence which will be signal on TLB invalidation - * completion, can be NULL + * completion * @start: start address * @end: end address * @asid: address space id * * Issue a range based TLB invalidation if supported, if not fallback to a full - * TLB invalidation. Completion of TLB is asynchronous and caller can either use - * the invalidation fence or seqno + xe_gt_tlb_invalidation_wait to wait for - * completion. + * TLB invalidation. Completion of TLB is asynchronous and caller can use + * the invalidation fence to wait for completion. * - * Return: Seqno which can be passed to xe_gt_tlb_invalidation_wait on success, - * negative error code on error. + * Return: Negative error code on error, 0 on success */ int xe_gt_tlb_invalidation_range(struct xe_gt *gt, struct xe_gt_tlb_invalidation_fence *fence, @@ -312,11 +313,11 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt, u32 action[MAX_TLB_INVALIDATION_LEN]; int len = 0; + xe_gt_assert(gt, fence); + /* Execlists not supported */ if (gt_to_xe(gt)->info.force_execlist) { - if (fence) - __invalidation_fence_signal(xe, fence); - + __invalidation_fence_signal(xe, fence); return 0; } @@ -382,12 +383,10 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt, * @vma: VMA to invalidate * * Issue a range based TLB invalidation if supported, if not fallback to a full - * TLB invalidation. Completion of TLB is asynchronous and caller can either use - * the invalidation fence or seqno + xe_gt_tlb_invalidation_wait to wait for - * completion. + * TLB invalidation. Completion of TLB is asynchronous and caller can use + * the invalidation fence to wait for completion. * - * Return: Seqno which can be passed to xe_gt_tlb_invalidation_wait on success, - * negative error code on error. + * Return: Negative error code on error, 0 on success */ int xe_gt_tlb_invalidation_vma(struct xe_gt *gt, struct xe_gt_tlb_invalidation_fence *fence, @@ -400,43 +399,6 @@ int xe_gt_tlb_invalidation_vma(struct xe_gt *gt, xe_vma_vm(vma)->usm.asid); } -/** - * xe_gt_tlb_invalidation_wait - Wait for TLB to complete - * @gt: graphics tile - * @seqno: seqno to wait which was returned from xe_gt_tlb_invalidation - * - * Wait for tlb_timeout_jiffies() for a TLB invalidation to complete. - * - * Return: 0 on success, -ETIME on TLB invalidation timeout - */ -int xe_gt_tlb_invalidation_wait(struct xe_gt *gt, int seqno) -{ - struct xe_guc *guc = >->uc.guc; - int ret; - - /* Execlists not supported */ - if (gt_to_xe(gt)->info.force_execlist) - return 0; - - /* - * XXX: See above, this algorithm only works if seqno are always in - * order - */ - ret = wait_event_timeout(guc->ct.wq, - tlb_invalidation_seqno_past(gt, seqno), - tlb_timeout_jiffies(gt)); - if (!ret) { - struct drm_printer p = xe_gt_err_printer(gt); - - xe_gt_err(gt, "TLB invalidation time'd out, seqno=%d, recv=%d\n", - seqno, gt->tlb_invalidation.seqno_recv); - xe_guc_ct_print(&guc->ct, &p, true); - return -ETIME; - } - - return 0; -} - /** * xe_guc_tlb_invalidation_done_handler - TLB invalidation done handler * @guc: guc @@ -480,12 +442,7 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len) return 0; } - /* - * wake_up_all() and wait_event_timeout() already have the correct - * barriers. - */ WRITE_ONCE(gt->tlb_invalidation.seqno_recv, msg[0]); - wake_up_all(&guc->ct.wq); list_for_each_entry_safe(fence, next, >->tlb_invalidation.pending_fences, link) { @@ -530,11 +487,13 @@ static const struct dma_fence_ops invalidation_fence_ops = { * xe_gt_tlb_invalidation_fence_init - Initialize TLB invalidation fence * @gt: GT * @fence: TLB invalidation fence to initialize + * @stack: fence is stack variable * * Initialize TLB invalidation fence for use */ void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt, - struct xe_gt_tlb_invalidation_fence *fence) + struct xe_gt_tlb_invalidation_fence *fence, + bool stack) { spin_lock_irq(>->tlb_invalidation.lock); dma_fence_init(&fence->base, &invalidation_fence_ops, @@ -542,5 +501,8 @@ void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt, dma_fence_context_alloc(1), 1); spin_unlock_irq(>->tlb_invalidation.lock); INIT_LIST_HEAD(&fence->link); - dma_fence_get(&fence->base); + if (stack) + set_bit(FENCE_STACK_BIT, &fence->base.flags); + else + dma_fence_get(&fence->base); } diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h index 948f4a2f5214..f430d5797af7 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h @@ -23,10 +23,16 @@ int xe_gt_tlb_invalidation_vma(struct xe_gt *gt, int xe_gt_tlb_invalidation_range(struct xe_gt *gt, struct xe_gt_tlb_invalidation_fence *fence, u64 start, u64 end, u32 asid); -int xe_gt_tlb_invalidation_wait(struct xe_gt *gt, int seqno); int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len); void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt, - struct xe_gt_tlb_invalidation_fence *fence); + struct xe_gt_tlb_invalidation_fence *fence, + bool stack); + +static inline void +xe_gt_tlb_invalidation_fence_wait(struct xe_gt_tlb_invalidation_fence *fence) +{ + dma_fence_wait(&fence->base, false); +} #endif /* _XE_GT_TLB_INVALIDATION_ */ diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index 4c17a1ec8f8b..31a751a5de3f 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -1153,7 +1153,7 @@ static int invalidation_fence_init(struct xe_gt *gt, trace_xe_gt_tlb_invalidation_fence_create(gt_to_xe(gt), &ifence->base); - xe_gt_tlb_invalidation_fence_init(gt, &ifence->base); + xe_gt_tlb_invalidation_fence_init(gt, &ifence->base, false); ifence->fence = fence; ifence->gt = gt; diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 6bfcbd4e778a..931935ec33db 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -3341,10 +3341,10 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) { struct xe_device *xe = xe_vma_vm(vma)->xe; struct xe_tile *tile; + struct xe_gt_tlb_invalidation_fence fence[XE_MAX_TILES_PER_DEVICE]; u32 tile_needs_invalidate = 0; - int seqno[XE_MAX_TILES_PER_DEVICE]; u8 id; - int ret; + int ret = 0; xe_assert(xe, !xe_vma_is_null(vma)); trace_xe_vma_invalidate(vma); @@ -3369,29 +3369,31 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) for_each_tile(tile, xe, id) { if (xe_pt_zap_ptes(tile, vma)) { - tile_needs_invalidate |= BIT(id); xe_device_wmb(xe); + xe_gt_tlb_invalidation_fence_init(tile->primary_gt, + &fence[id], true); + /* * FIXME: We potentially need to invalidate multiple * GTs within the tile */ - seqno[id] = xe_gt_tlb_invalidation_vma(tile->primary_gt, NULL, vma); - if (seqno[id] < 0) - return seqno[id]; + ret = xe_gt_tlb_invalidation_vma(tile->primary_gt, + &fence[id], vma); + if (ret < 0) + goto wait; + + tile_needs_invalidate |= BIT(id); } } - for_each_tile(tile, xe, id) { - if (tile_needs_invalidate & BIT(id)) { - ret = xe_gt_tlb_invalidation_wait(tile->primary_gt, seqno[id]); - if (ret < 0) - return ret; - } - } +wait: + for_each_tile(tile, xe, id) + if (tile_needs_invalidate & BIT(id)) + xe_gt_tlb_invalidation_fence_wait(&fence[id]); vma->tile_invalidated = vma->tile_mask; - return 0; + return ret; } struct xe_vm_snapshot { From f002702290fccbd473f5bb94e52f25c96917fff2 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Fri, 19 Jul 2024 10:29:04 -0700 Subject: [PATCH 307/562] drm/xe: Hold a PM ref when GT TLB invalidations are inflight Avoid GT TLB invalidation timeouts by holding a PM ref when invalidations are inflight. v2: - Drop PM ref before signaling fence (CI) v3: - Move invalidation_fence_signal helper in tlb timeout to previous patch (Matthew Auld) Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: Rodrigo Vivi Cc: Nirmoy Das Signed-off-by: Matthew Brost Reviewed-by: Nirmoy Das Link: https://patchwork.freedesktop.org/patch/msgid/20240719172905.1527927-4-matthew.brost@intel.com (cherry picked from commit 0a382f9bc5dc4744a33970a5ed4df8f9c702ee9e) Requires: 46209ce5287b ("drm/xe: Add xe_gt_tlb_invalidation_fence_init helper") Requires: 0e414ab036e0 ("drm/xe: Drop xe_gt_tlb_invalidation_wait") Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 23 +++++++++++++++++-- drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h | 1 + .../gpu/drm/xe/xe_gt_tlb_invalidation_types.h | 4 ++++ drivers/gpu/drm/xe/xe_vm.c | 4 +++- 4 files changed, 29 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index c3419d4412ce..481d83d07367 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -13,6 +13,7 @@ #include "xe_guc.h" #include "xe_guc_ct.h" #include "xe_mmio.h" +#include "xe_pm.h" #include "xe_sriov.h" #include "xe_trace.h" #include "regs/xe_guc_regs.h" @@ -41,6 +42,7 @@ __invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_ bool stack = test_bit(FENCE_STACK_BIT, &fence->base.flags); trace_xe_gt_tlb_invalidation_fence_signal(xe, fence); + xe_gt_tlb_invalidation_fence_fini(fence); dma_fence_signal(&fence->base); if (!stack) dma_fence_put(&fence->base); @@ -263,8 +265,10 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt) xe_gt_tlb_invalidation_fence_init(gt, &fence, true); ret = xe_gt_tlb_invalidation_guc(gt, &fence); - if (ret < 0) + if (ret < 0) { + xe_gt_tlb_invalidation_fence_fini(&fence); return ret; + } xe_gt_tlb_invalidation_fence_wait(&fence); } else if (xe_device_uc_enabled(xe) && !xe_device_wedged(xe)) { @@ -489,12 +493,15 @@ static const struct dma_fence_ops invalidation_fence_ops = { * @fence: TLB invalidation fence to initialize * @stack: fence is stack variable * - * Initialize TLB invalidation fence for use + * Initialize TLB invalidation fence for use. xe_gt_tlb_invalidation_fence_fini + * must be called if fence is not signaled. */ void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt, struct xe_gt_tlb_invalidation_fence *fence, bool stack) { + xe_pm_runtime_get_noresume(gt_to_xe(gt)); + spin_lock_irq(>->tlb_invalidation.lock); dma_fence_init(&fence->base, &invalidation_fence_ops, >->tlb_invalidation.lock, @@ -505,4 +512,16 @@ void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt, set_bit(FENCE_STACK_BIT, &fence->base.flags); else dma_fence_get(&fence->base); + fence->gt = gt; +} + +/** + * xe_gt_tlb_invalidation_fence_fini - Finalize TLB invalidation fence + * @fence: TLB invalidation fence to finalize + * + * Drop PM ref which fence took durinig init. + */ +void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence) +{ + xe_pm_runtime_put(gt_to_xe(fence->gt)); } diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h index f430d5797af7..a84065fa324c 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h @@ -28,6 +28,7 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len); void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt, struct xe_gt_tlb_invalidation_fence *fence, bool stack); +void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence); static inline void xe_gt_tlb_invalidation_fence_wait(struct xe_gt_tlb_invalidation_fence *fence) diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h index 934c828efe31..de6e825e0851 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h @@ -8,6 +8,8 @@ #include +struct xe_gt; + /** * struct xe_gt_tlb_invalidation_fence - XE GT TLB invalidation fence * @@ -17,6 +19,8 @@ struct xe_gt_tlb_invalidation_fence { /** @base: dma fence base */ struct dma_fence base; + /** @gt: GT which fence belong to */ + struct xe_gt *gt; /** @link: link into list of pending tlb fences */ struct list_head link; /** @seqno: seqno of TLB invalidation to signal fence one */ diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 931935ec33db..c7561a56abaf 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -3379,8 +3379,10 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) */ ret = xe_gt_tlb_invalidation_vma(tile->primary_gt, &fence[id], vma); - if (ret < 0) + if (ret < 0) { + xe_gt_tlb_invalidation_fence_fini(&fence[id]); goto wait; + } tile_needs_invalidate |= BIT(id); } From af8e119f52e9c13e556be9e03f27957554a84656 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Thu, 15 Aug 2024 17:11:17 +0300 Subject: [PATCH 308/562] xhci: Fix Panther point NULL pointer deref at full-speed re-enumeration re-enumerating full-speed devices after a failed address device command can trigger a NULL pointer dereference. Full-speed devices may need to reconfigure the endpoint 0 Max Packet Size value during enumeration. Usb core calls usb_ep0_reinit() in this case, which ends up calling xhci_configure_endpoint(). On Panther point xHC the xhci_configure_endpoint() function will additionally check and reserve bandwidth in software. Other hosts do this in hardware If xHC address device command fails then a new xhci_virt_device structure is allocated as part of re-enabling the slot, but the bandwidth table pointers are not set up properly here. This triggers the NULL pointer dereference the next time usb_ep0_reinit() is called and xhci_configure_endpoint() tries to check and reserve bandwidth [46710.713538] usb 3-1: new full-speed USB device number 5 using xhci_hcd [46710.713699] usb 3-1: Device not responding to setup address. [46710.917684] usb 3-1: Device not responding to setup address. [46711.125536] usb 3-1: device not accepting address 5, error -71 [46711.125594] BUG: kernel NULL pointer dereference, address: 0000000000000008 [46711.125600] #PF: supervisor read access in kernel mode [46711.125603] #PF: error_code(0x0000) - not-present page [46711.125606] PGD 0 P4D 0 [46711.125610] Oops: Oops: 0000 [#1] PREEMPT SMP PTI [46711.125615] CPU: 1 PID: 25760 Comm: kworker/1:2 Not tainted 6.10.3_2 #1 [46711.125620] Hardware name: Gigabyte Technology Co., Ltd. [46711.125623] Workqueue: usb_hub_wq hub_event [usbcore] [46711.125668] RIP: 0010:xhci_reserve_bandwidth (drivers/usb/host/xhci.c Fix this by making sure bandwidth table pointers are set up correctly after a failed address device command, and additionally by avoiding checking for bandwidth in cases like this where no actual endpoints are added or removed, i.e. only context for default control endpoint 0 is evaluated. Reported-by: Karel Balej Closes: https://lore.kernel.org/linux-usb/D3CKQQAETH47.1MUO22RTCH2O3@matfyz.cz/ Cc: stable@vger.kernel.org Fixes: 651aaf36a7d7 ("usb: xhci: Handle USB transaction error on address command") Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20240815141117.2702314-2-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 0a8cf6c17f82..efdf4c228b8c 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -2837,7 +2837,7 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci, xhci->num_active_eps); return -ENOMEM; } - if ((xhci->quirks & XHCI_SW_BW_CHECKING) && + if ((xhci->quirks & XHCI_SW_BW_CHECKING) && !ctx_change && xhci_reserve_bandwidth(xhci, virt_dev, command->in_ctx)) { if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK)) xhci_free_host_resources(xhci, ctrl_ctx); @@ -4200,8 +4200,10 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev, mutex_unlock(&xhci->mutex); ret = xhci_disable_slot(xhci, udev->slot_id); xhci_free_virt_device(xhci, udev->slot_id); - if (!ret) - xhci_alloc_dev(hcd, udev); + if (!ret) { + if (xhci_alloc_dev(hcd, udev) == 1) + xhci_setup_addressable_virt_dev(xhci, udev); + } kfree(command->completion); kfree(command); return -EPROTO; From 9bb5e74b2bf88fbb024bb15ded3b011e02c673be Mon Sep 17 00:00:00 2001 From: Griffin Kroah-Hartman Date: Thu, 15 Aug 2024 11:49:20 +0200 Subject: [PATCH 309/562] Revert "misc: fastrpc: Restrict untrusted app to attach to privileged PD" This reverts commit bab2f5e8fd5d2f759db26b78d9db57412888f187. Joel reported that this commit breaks userspace and stops sensors in SDM845 from working. Also breaks other qcom SoC devices running postmarketOS. Cc: stable Cc: Ekansh Gupta Cc: Dmitry Baryshkov Reported-by: Joel Selvaraj Link: https://lore.kernel.org/r/9a9f5646-a554-4b65-8122-d212bb665c81@umsystem.edu Signed-off-by: Griffin Kroah-Hartman Acked-by: Srinivas Kandagatla Fixes: bab2f5e8fd5d ("misc: fastrpc: Restrict untrusted app to attach to privileged PD") Link: https://lore.kernel.org/r/20240815094920.8242-1-griffin@kroah.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 22 +++------------------- include/uapi/misc/fastrpc.h | 3 --- 2 files changed, 3 insertions(+), 22 deletions(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 5204fda51da3..339d126414d4 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -2085,16 +2085,6 @@ err_invoke: return err; } -static int is_attach_rejected(struct fastrpc_user *fl) -{ - /* Check if the device node is non-secure */ - if (!fl->is_secure_dev) { - dev_dbg(&fl->cctx->rpdev->dev, "untrusted app trying to attach to privileged DSP PD\n"); - return -EACCES; - } - return 0; -} - static long fastrpc_device_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -2107,19 +2097,13 @@ static long fastrpc_device_ioctl(struct file *file, unsigned int cmd, err = fastrpc_invoke(fl, argp); break; case FASTRPC_IOCTL_INIT_ATTACH: - err = is_attach_rejected(fl); - if (!err) - err = fastrpc_init_attach(fl, ROOT_PD); + err = fastrpc_init_attach(fl, ROOT_PD); break; case FASTRPC_IOCTL_INIT_ATTACH_SNS: - err = is_attach_rejected(fl); - if (!err) - err = fastrpc_init_attach(fl, SENSORS_PD); + err = fastrpc_init_attach(fl, SENSORS_PD); break; case FASTRPC_IOCTL_INIT_CREATE_STATIC: - err = is_attach_rejected(fl); - if (!err) - err = fastrpc_init_create_static_process(fl, argp); + err = fastrpc_init_create_static_process(fl, argp); break; case FASTRPC_IOCTL_INIT_CREATE: err = fastrpc_init_create_process(fl, argp); diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h index 91583690bddc..f33d914d8f46 100644 --- a/include/uapi/misc/fastrpc.h +++ b/include/uapi/misc/fastrpc.h @@ -8,14 +8,11 @@ #define FASTRPC_IOCTL_ALLOC_DMA_BUFF _IOWR('R', 1, struct fastrpc_alloc_dma_buf) #define FASTRPC_IOCTL_FREE_DMA_BUFF _IOWR('R', 2, __u32) #define FASTRPC_IOCTL_INVOKE _IOWR('R', 3, struct fastrpc_invoke) -/* This ioctl is only supported with secure device nodes */ #define FASTRPC_IOCTL_INIT_ATTACH _IO('R', 4) #define FASTRPC_IOCTL_INIT_CREATE _IOWR('R', 5, struct fastrpc_init_create) #define FASTRPC_IOCTL_MMAP _IOWR('R', 6, struct fastrpc_req_mmap) #define FASTRPC_IOCTL_MUNMAP _IOWR('R', 7, struct fastrpc_req_munmap) -/* This ioctl is only supported with secure device nodes */ #define FASTRPC_IOCTL_INIT_ATTACH_SNS _IO('R', 8) -/* This ioctl is only supported with secure device nodes */ #define FASTRPC_IOCTL_INIT_CREATE_STATIC _IOWR('R', 9, struct fastrpc_init_create_static) #define FASTRPC_IOCTL_MEM_MAP _IOWR('R', 10, struct fastrpc_mem_map) #define FASTRPC_IOCTL_MEM_UNMAP _IOWR('R', 11, struct fastrpc_mem_unmap) From 92e9bac18124682c4b99ede9ee3bcdd68f121e92 Mon Sep 17 00:00:00 2001 From: Ivan Orlov Date: Thu, 15 Aug 2024 01:04:31 +0100 Subject: [PATCH 310/562] kunit/overflow: Fix UB in overflow_allocation_test The 'device_name' array doesn't exist out of the 'overflow_allocation_test' function scope. However, it is being used as a driver name when calling 'kunit_driver_create' from 'kunit_device_register'. It produces the kernel panic with KASAN enabled. Since this variable is used in one place only, remove it and pass the device name into kunit_device_register directly as an ascii string. Signed-off-by: Ivan Orlov Reviewed-by: David Gow Link: https://lore.kernel.org/r/20240815000431.401869-1-ivan.orlov0322@gmail.com Signed-off-by: Kees Cook --- lib/overflow_kunit.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c index f314a0c15a6d..2abc78367dd1 100644 --- a/lib/overflow_kunit.c +++ b/lib/overflow_kunit.c @@ -668,7 +668,6 @@ DEFINE_TEST_ALLOC(devm_kzalloc, devm_kfree, 1, 1, 0); static void overflow_allocation_test(struct kunit *test) { - const char device_name[] = "overflow-test"; struct device *dev; int count = 0; @@ -678,7 +677,7 @@ static void overflow_allocation_test(struct kunit *test) } while (0) /* Create dummy device for devm_kmalloc()-family tests. */ - dev = kunit_device_register(test, device_name); + dev = kunit_device_register(test, "overflow-test"); KUNIT_ASSERT_FALSE_MSG(test, IS_ERR(dev), "Cannot register test device\n"); From 020925ce92990c3bf59ab2cde386ac6d9ec734ff Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 7 Aug 2024 15:05:12 -0700 Subject: [PATCH 311/562] kallsyms: Do not cleanup .llvm. suffix before sorting symbols Cleaning up the symbols causes various issues afterwards. Let's sort the list based on original name. Signed-off-by: Song Liu Fixes: 8cc32a9bbf29 ("kallsyms: strip LTO-only suffixes from promoted global functions") Reviewed-by: Masami Hiramatsu (Google) Tested-by: Masami Hiramatsu (Google) Acked-by: Petr Mladek Reviewed-by: Sami Tolvanen Reviewed-by: Luis Chamberlain Link: https://lore.kernel.org/r/20240807220513.3100483-2-song@kernel.org Signed-off-by: Kees Cook --- scripts/kallsyms.c | 31 ++----------------------------- scripts/link-vmlinux.sh | 4 ---- 2 files changed, 2 insertions(+), 33 deletions(-) diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 0ed873491bf5..123dab0572f8 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -5,8 +5,7 @@ * This software may be used and distributed according to the terms * of the GNU General Public License, incorporated herein by reference. * - * Usage: kallsyms [--all-symbols] [--absolute-percpu] - * [--lto-clang] in.map > out.S + * Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S * * Table compression uses all the unused char codes on the symbols and * maps these to the most used substrings (tokens). For instance, it might @@ -62,7 +61,6 @@ static struct sym_entry **table; static unsigned int table_size, table_cnt; static int all_symbols; static int absolute_percpu; -static int lto_clang; static int token_profit[0x10000]; @@ -73,8 +71,7 @@ static unsigned char best_table_len[256]; static void usage(void) { - fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] " - "[--lto-clang] in.map > out.S\n"); + fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S\n"); exit(1); } @@ -344,25 +341,6 @@ static bool symbol_absolute(const struct sym_entry *s) return s->percpu_absolute; } -static void cleanup_symbol_name(char *s) -{ - char *p; - - /* - * ASCII[.] = 2e - * ASCII[0-9] = 30,39 - * ASCII[A-Z] = 41,5a - * ASCII[_] = 5f - * ASCII[a-z] = 61,7a - * - * As above, replacing the first '.' in ".llvm." with '\0' does not - * affect the main sorting, but it helps us with subsorting. - */ - p = strstr(s, ".llvm."); - if (p) - *p = '\0'; -} - static int compare_names(const void *a, const void *b) { int ret; @@ -526,10 +504,6 @@ static void write_src(void) output_address(relative_base); printf("\n"); - if (lto_clang) - for (i = 0; i < table_cnt; i++) - cleanup_symbol_name((char *)table[i]->sym); - sort_symbols_by_name(); output_label("kallsyms_seqs_of_names"); for (i = 0; i < table_cnt; i++) @@ -807,7 +781,6 @@ int main(int argc, char **argv) static const struct option long_options[] = { {"all-symbols", no_argument, &all_symbols, 1}, {"absolute-percpu", no_argument, &absolute_percpu, 1}, - {"lto-clang", no_argument, <o_clang, 1}, {}, }; diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index f7b2503cdba9..22d0bc843986 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -156,10 +156,6 @@ kallsyms() kallsymopt="${kallsymopt} --absolute-percpu" fi - if is_enabled CONFIG_LTO_CLANG; then - kallsymopt="${kallsymopt} --lto-clang" - fi - info KSYMS "${2}.S" scripts/kallsyms ${kallsymopt} "${1}" > "${2}.S" From fb6a421fb6153d97cf3058f9bd550b377b76a490 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 7 Aug 2024 15:05:13 -0700 Subject: [PATCH 312/562] kallsyms: Match symbols exactly with CONFIG_LTO_CLANG With CONFIG_LTO_CLANG=y, the compiler may add .llvm. suffix to function names to avoid duplication. APIs like kallsyms_lookup_name() and kallsyms_on_each_match_symbol() tries to match these symbol names without the .llvm. suffix, e.g., match "c_stop" with symbol c_stop.llvm.17132674095431275852. This turned out to be problematic for use cases that require exact match, for example, livepatch. Fix this by making the APIs to match symbols exactly. Also cleanup kallsyms_selftests accordingly. Signed-off-by: Song Liu Fixes: 8cc32a9bbf29 ("kallsyms: strip LTO-only suffixes from promoted global functions") Tested-by: Masami Hiramatsu (Google) Reviewed-by: Masami Hiramatsu (Google) Acked-by: Petr Mladek Reviewed-by: Sami Tolvanen Reviewed-by: Luis Chamberlain Link: https://lore.kernel.org/r/20240807220513.3100483-3-song@kernel.org Signed-off-by: Kees Cook --- kernel/kallsyms.c | 55 +++++--------------------------------- kernel/kallsyms_selftest.c | 22 +-------------- 2 files changed, 7 insertions(+), 70 deletions(-) diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index fb2c77368d18..a9a0ca605d4a 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -160,38 +160,6 @@ unsigned long kallsyms_sym_address(int idx) return kallsyms_relative_base - 1 - kallsyms_offsets[idx]; } -static void cleanup_symbol_name(char *s) -{ - char *res; - - if (!IS_ENABLED(CONFIG_LTO_CLANG)) - return; - - /* - * LLVM appends various suffixes for local functions and variables that - * must be promoted to global scope as part of LTO. This can break - * hooking of static functions with kprobes. '.' is not a valid - * character in an identifier in C. Suffixes only in LLVM LTO observed: - * - foo.llvm.[0-9a-f]+ - */ - res = strstr(s, ".llvm."); - if (res) - *res = '\0'; - - return; -} - -static int compare_symbol_name(const char *name, char *namebuf) -{ - /* The kallsyms_seqs_of_names is sorted based on names after - * cleanup_symbol_name() (see scripts/kallsyms.c) if clang lto is enabled. - * To ensure correct bisection in kallsyms_lookup_names(), do - * cleanup_symbol_name(namebuf) before comparing name and namebuf. - */ - cleanup_symbol_name(namebuf); - return strcmp(name, namebuf); -} - static unsigned int get_symbol_seq(int index) { unsigned int i, seq = 0; @@ -219,7 +187,7 @@ static int kallsyms_lookup_names(const char *name, seq = get_symbol_seq(mid); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); - ret = compare_symbol_name(name, namebuf); + ret = strcmp(name, namebuf); if (ret > 0) low = mid + 1; else if (ret < 0) @@ -236,7 +204,7 @@ static int kallsyms_lookup_names(const char *name, seq = get_symbol_seq(low - 1); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); - if (compare_symbol_name(name, namebuf)) + if (strcmp(name, namebuf)) break; low--; } @@ -248,7 +216,7 @@ static int kallsyms_lookup_names(const char *name, seq = get_symbol_seq(high + 1); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); - if (compare_symbol_name(name, namebuf)) + if (strcmp(name, namebuf)) break; high++; } @@ -407,8 +375,7 @@ static int kallsyms_lookup_buildid(unsigned long addr, if (modbuildid) *modbuildid = NULL; - ret = strlen(namebuf); - goto found; + return strlen(namebuf); } /* See if it's in a module or a BPF JITed image. */ @@ -422,8 +389,6 @@ static int kallsyms_lookup_buildid(unsigned long addr, ret = ftrace_mod_address_lookup(addr, symbolsize, offset, modname, namebuf); -found: - cleanup_symbol_name(namebuf); return ret; } @@ -450,8 +415,6 @@ const char *kallsyms_lookup(unsigned long addr, int lookup_symbol_name(unsigned long addr, char *symname) { - int res; - symname[0] = '\0'; symname[KSYM_NAME_LEN - 1] = '\0'; @@ -462,16 +425,10 @@ int lookup_symbol_name(unsigned long addr, char *symname) /* Grab name */ kallsyms_expand_symbol(get_symbol_offset(pos), symname, KSYM_NAME_LEN); - goto found; + return 0; } /* See if it's in a module. */ - res = lookup_module_symbol_name(addr, symname); - if (res) - return res; - -found: - cleanup_symbol_name(symname); - return 0; + return lookup_module_symbol_name(addr, symname); } /* Look up a kernel symbol and return it in a text buffer. */ diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c index 2f84896a7bcb..873f7c445488 100644 --- a/kernel/kallsyms_selftest.c +++ b/kernel/kallsyms_selftest.c @@ -187,31 +187,11 @@ static void test_perf_kallsyms_lookup_name(void) stat.min, stat.max, div_u64(stat.sum, stat.real_cnt)); } -static bool match_cleanup_name(const char *s, const char *name) -{ - char *p; - int len; - - if (!IS_ENABLED(CONFIG_LTO_CLANG)) - return false; - - p = strstr(s, ".llvm."); - if (!p) - return false; - - len = strlen(name); - if (p - s != len) - return false; - - return !strncmp(s, name, len); -} - static int find_symbol(void *data, const char *name, unsigned long addr) { struct test_stat *stat = (struct test_stat *)data; - if (strcmp(name, stat->name) == 0 || - (!stat->perf && match_cleanup_name(name, stat->name))) { + if (!strcmp(name, stat->name)) { stat->real_cnt++; stat->addr = addr; From aae6b81260fd9a7224f7eb4fc440d625852245bb Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 12 Aug 2024 10:43:48 -0400 Subject: [PATCH 313/562] Bluetooth: HCI: Invert LE State quirk to be opt-out rather then opt-in This inverts the LE State quirk so by default we assume the controllers would report valid states rather than invalid which is how quirks normally behave, also this would result in HCI command failing it the LE States are really broken thus exposing the controllers that are really broken in this respect. Link: https://github.com/bluez/bluez/issues/584 Fixes: 220915857e29 ("Bluetooth: Adding driver and quirk defs for multi-role LE") Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btintel.c | 10 ---------- drivers/bluetooth/btintel_pcie.c | 3 --- drivers/bluetooth/btmtksdio.c | 3 --- drivers/bluetooth/btrtl.c | 1 - drivers/bluetooth/btusb.c | 4 ++-- drivers/bluetooth/hci_qca.c | 4 ++-- drivers/bluetooth/hci_vhci.c | 2 -- include/net/bluetooth/hci.h | 17 ++++++++++------- include/net/bluetooth/hci_core.h | 2 +- net/bluetooth/hci_event.c | 2 +- 10 files changed, 16 insertions(+), 32 deletions(-) diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 2ebc970e6573..7d5e4de64e3c 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -2945,9 +2945,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) INTEL_ROM_LEGACY_NO_WBS_SUPPORT)) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - if (ver.hw_variant == 0x08 && ver.fw_variant == 0x22) - set_bit(HCI_QUIRK_VALID_LE_STATES, - &hdev->quirks); err = btintel_legacy_rom_setup(hdev, &ver); break; @@ -2956,7 +2953,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) case 0x12: /* ThP */ case 0x13: /* HrP */ case 0x14: /* CcP */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); fallthrough; case 0x0c: /* WsP */ /* Apply the device specific HCI quirks @@ -3048,9 +3044,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) /* These variants don't seem to support LE Coded PHY */ set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks); - /* Set Valid LE States quirk */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, ver.hw_variant); @@ -3076,9 +3069,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) */ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - /* Apply LE States quirk from solar onwards */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, INTEL_HW_VARIANT(ver_tlv.cnvi_bt)); diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index 0d1a0415557b..1c7631f22c52 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -1180,9 +1180,6 @@ static int btintel_pcie_setup(struct hci_dev *hdev) */ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - /* Apply LE States quirk from solar onwards */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, INTEL_HW_VARIANT(ver_tlv.cnvi_bt)); diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c index 39d6898497a4..497e4c87f5be 100644 --- a/drivers/bluetooth/btmtksdio.c +++ b/drivers/bluetooth/btmtksdio.c @@ -1148,9 +1148,6 @@ static int btmtksdio_setup(struct hci_dev *hdev) } } - /* Valid LE States quirk for MediaTek 7921 */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - break; case 0x7663: case 0x7668: diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index f2f37143c454..fd7991ea7672 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -1287,7 +1287,6 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) case CHIP_ID_8852C: case CHIP_ID_8851B: case CHIP_ID_8852BT: - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); /* RTL8852C needs to transmit mSBC data continuously without diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index acdba5d77694..51d9d4532dda 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -3956,8 +3956,8 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_WIDEBAND_SPEECH) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - if (id->driver_info & BTUSB_VALID_LE_STATES) - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); + if (!(id->driver_info & BTUSB_VALID_LE_STATES)) + set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks); if (id->driver_info & BTUSB_DIGIANSWER) { data->cmdreq_type = USB_TYPE_VENDOR; diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 45adc1560d94..4b1ad7ea5b95 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -2474,8 +2474,8 @@ static int qca_serdev_probe(struct serdev_device *serdev) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - if (data->capabilities & QCA_CAP_VALID_LE_STATES) - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); + if (!(data->capabilities & QCA_CAP_VALID_LE_STATES)) + set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks); } return 0; diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index c4046f8f1985..43e9ac5a3324 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -425,8 +425,6 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) if (opcode & 0x80) set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks); - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - if (hci_register_dev(hdev) < 0) { BT_ERR("Can't register HCI device"); hci_free_dev(hdev); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index e372a88e8c3f..d1d073089f38 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -206,14 +206,17 @@ enum { */ HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, - /* When this quirk is set, the controller has validated that - * LE states reported through the HCI_LE_READ_SUPPORTED_STATES are - * valid. This mechanism is necessary as many controllers have - * been seen has having trouble initiating a connectable - * advertisement despite the state combination being reported as - * supported. + /* When this quirk is set, the LE states reported through the + * HCI_LE_READ_SUPPORTED_STATES are invalid/broken. + * + * This mechanism is necessary as many controllers have been seen has + * having trouble initiating a connectable advertisement despite the + * state combination being reported as supported. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. */ - HCI_QUIRK_VALID_LE_STATES, + HCI_QUIRK_BROKEN_LE_STATES, /* When this quirk is set, then erroneous data reporting * is ignored. This is mainly due to the fact that the HCI diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 31020891fc68..e449dba698f3 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -825,7 +825,7 @@ extern struct mutex hci_cb_list_lock; } while (0) #define hci_dev_le_state_simultaneous(hdev) \ - (test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) && \ + (!test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) && \ (hdev->le_states[4] & 0x08) && /* Central */ \ (hdev->le_states[4] & 0x40) && /* Peripheral */ \ (hdev->le_states[3] & 0x10)) /* Simultaneous */ diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index d0c118c47f6c..1c82dcdf6e8f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5920,7 +5920,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, * while we have an existing one in peripheral role. */ if (hdev->conn_hash.le_num_peripheral > 0 && - (!test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) || + (test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) || !(hdev->le_states[3] & 0x10))) return NULL; From 932021a11805b9da4bd6abf66fe233cccd59fe0e Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 12 Aug 2024 11:22:08 -0400 Subject: [PATCH 314/562] Bluetooth: hci_core: Fix LE quote calculation Function hci_sched_le needs to update the respective counter variable inplace other the likes of hci_quote_sent would attempt to use the possible outdated value of conn->{le_cnt,acl_cnt}. Link: https://github.com/bluez/bluez/issues/915 Fixes: 73d80deb7bdf ("Bluetooth: prioritizing data over HCI") Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/hci_core.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 06da8ac13dca..f25a21f532aa 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -3664,19 +3664,19 @@ static void hci_sched_le(struct hci_dev *hdev) { struct hci_chan *chan; struct sk_buff *skb; - int quote, cnt, tmp; + int quote, *cnt, tmp; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, LE_LINK)) return; - cnt = hdev->le_pkts ? hdev->le_cnt : hdev->acl_cnt; + cnt = hdev->le_pkts ? &hdev->le_cnt : &hdev->acl_cnt; - __check_timeout(hdev, cnt, LE_LINK); + __check_timeout(hdev, *cnt, LE_LINK); - tmp = cnt; - while (cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { + tmp = *cnt; + while (*cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote-- && (skb = skb_peek(&chan->data_q))) { BT_DBG("chan %p skb %p len %d priority %u", chan, skb, @@ -3691,7 +3691,7 @@ static void hci_sched_le(struct hci_dev *hdev) hci_send_frame(hdev, skb); hdev->le_last_tx = jiffies; - cnt--; + (*cnt)--; chan->sent++; chan->conn->sent++; @@ -3701,12 +3701,7 @@ static void hci_sched_le(struct hci_dev *hdev) } } - if (hdev->le_pkts) - hdev->le_cnt = cnt; - else - hdev->acl_cnt = cnt; - - if (cnt != tmp) + if (*cnt != tmp) hci_prio_recalculate(hdev, LE_LINK); } From 28cd47f75185c4818b0fb1b46f2f02faaba96376 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Wed, 30 Aug 2023 15:08:06 -0700 Subject: [PATCH 315/562] Bluetooth: SMP: Fix assumption of Central always being Initiator SMP initiator role shall be considered the one that initiates the pairing procedure with SMP_CMD_PAIRING_REQ: BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 3, Part H page 1557: Figure 2.1: LE pairing phases Note that by sending SMP_CMD_SECURITY_REQ it doesn't change the role to be Initiator. Link: https://github.com/bluez/bluez/issues/567 Fixes: b28b4943660f ("Bluetooth: Add strict checks for allowed SMP PDUs") Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/smp.c | 146 ++++++++++++++++++++++---------------------- 1 file changed, 73 insertions(+), 73 deletions(-) diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 1e7ea3a4b7ef..4f9fdf400584 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -914,7 +914,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, * Confirms and the responder Enters the passkey. */ if (smp->method == OVERLAP) { - if (hcon->role == HCI_ROLE_MASTER) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp->method = CFM_PASSKEY; else smp->method = REQ_PASSKEY; @@ -964,7 +964,7 @@ static u8 smp_confirm(struct smp_chan *smp) smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp); - if (conn->hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM); else SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -980,7 +980,8 @@ static u8 smp_random(struct smp_chan *smp) int ret; bt_dev_dbg(conn->hcon->hdev, "conn %p %s", conn, - conn->hcon->out ? "initiator" : "responder"); + test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" : + "responder"); ret = smp_c1(smp->tk, smp->rrnd, smp->preq, smp->prsp, hcon->init_addr_type, &hcon->init_addr, @@ -994,7 +995,7 @@ static u8 smp_random(struct smp_chan *smp) return SMP_CONFIRM_FAILED; } - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { u8 stk[16]; __le64 rand = 0; __le16 ediv = 0; @@ -1256,14 +1257,15 @@ static void smp_distribute_keys(struct smp_chan *smp) rsp = (void *) &smp->prsp[1]; /* The responder sends its keys first */ - if (hcon->out && (smp->remote_key_dist & KEY_DIST_MASK)) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags) && + (smp->remote_key_dist & KEY_DIST_MASK)) { smp_allow_key_dist(smp); return; } req = (void *) &smp->preq[1]; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { keydist = &rsp->init_key_dist; *keydist &= req->init_key_dist; } else { @@ -1432,7 +1434,7 @@ static int sc_mackey_and_ltk(struct smp_chan *smp, u8 mackey[16], u8 ltk[16]) struct hci_conn *hcon = smp->conn->hcon; u8 *na, *nb, a[7], b[7]; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { na = smp->prnd; nb = smp->rrnd; } else { @@ -1460,7 +1462,7 @@ static void sc_dhkey_check(struct smp_chan *smp) a[6] = hcon->init_addr_type; b[6] = hcon->resp_addr_type; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local_addr = a; remote_addr = b; memcpy(io_cap, &smp->preq[1], 3); @@ -1539,7 +1541,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) /* The round is only complete when the initiator * receives pairing random. */ - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); if (smp->passkey_round == 20) @@ -1567,7 +1569,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); return 0; @@ -1578,7 +1580,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) case SMP_CMD_PUBLIC_KEY: default: /* Initiating device starts the round */ - if (!hcon->out) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return 0; bt_dev_dbg(hdev, "Starting passkey round %u", @@ -1623,7 +1625,7 @@ static int sc_user_reply(struct smp_chan *smp, u16 mgmt_op, __le32 passkey) } /* Initiator sends DHKey check first */ - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { sc_dhkey_check(smp); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); } else if (test_and_clear_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags)) { @@ -1746,7 +1748,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) struct smp_cmd_pairing rsp, *req = (void *) skb->data; struct l2cap_chan *chan = conn->smp; struct hci_dev *hdev = conn->hcon->hdev; - struct smp_chan *smp; + struct smp_chan *smp = chan->data; u8 key_size, auth, sec_level; int ret; @@ -1755,16 +1757,14 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*req)) return SMP_INVALID_PARAMS; - if (conn->hcon->role != HCI_ROLE_SLAVE) + if (smp && test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_CMD_NOTSUPP; - if (!chan->data) + if (!smp) { smp = smp_chan_create(conn); - else - smp = chan->data; - - if (!smp) - return SMP_UNSPECIFIED; + if (!smp) + return SMP_UNSPECIFIED; + } /* We didn't start the pairing, so match remote */ auth = req->auth_req & AUTH_REQ_MASK(hdev); @@ -1946,7 +1946,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*rsp)) return SMP_INVALID_PARAMS; - if (conn->hcon->role != HCI_ROLE_MASTER) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_CMD_NOTSUPP; skb_pull(skb, sizeof(*rsp)); @@ -2041,7 +2041,7 @@ static u8 sc_check_confirm(struct smp_chan *smp) if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY) return sc_passkey_round(smp, SMP_CMD_PAIRING_CONFIRM); - if (conn->hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -2063,7 +2063,7 @@ static int fixup_sc_false_positive(struct smp_chan *smp) u8 auth; /* The issue is only observed when we're in responder role */ - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_UNSPECIFIED; if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) { @@ -2099,7 +2099,8 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) struct hci_dev *hdev = hcon->hdev; bt_dev_dbg(hdev, "conn %p %s", conn, - hcon->out ? "initiator" : "responder"); + test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" : + "responder"); if (skb->len < sizeof(smp->pcnf)) return SMP_INVALID_PARAMS; @@ -2121,7 +2122,7 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) return ret; } - if (conn->hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -2156,7 +2157,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) if (!test_bit(SMP_FLAG_SC, &smp->flags)) return smp_random(smp); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { pkax = smp->local_pk; pkbx = smp->remote_pk; na = smp->prnd; @@ -2169,7 +2170,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) } if (smp->method == REQ_OOB) { - if (!hcon->out) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); @@ -2180,7 +2181,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY) return sc_passkey_round(smp, SMP_CMD_PAIRING_RANDOM); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { u8 cfm[16]; err = smp_f4(smp->tfm_cmac, smp->remote_pk, smp->local_pk, @@ -2221,7 +2222,7 @@ mackey_and_ltk: return SMP_UNSPECIFIED; if (smp->method == REQ_OOB) { - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { sc_dhkey_check(smp); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); } @@ -2295,10 +2296,27 @@ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level, return false; } +static void smp_send_pairing_req(struct smp_chan *smp, __u8 auth) +{ + struct smp_cmd_pairing cp; + + if (smp->conn->hcon->type == ACL_LINK) + build_bredr_pairing_cmd(smp, &cp, NULL); + else + build_pairing_cmd(smp->conn, &cp, NULL, auth); + + smp->preq[0] = SMP_CMD_PAIRING_REQ; + memcpy(&smp->preq[1], &cp, sizeof(cp)); + + smp_send_cmd(smp->conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); + SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); + + set_bit(SMP_FLAG_INITIATOR, &smp->flags); +} + static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_cmd_security_req *rp = (void *) skb->data; - struct smp_cmd_pairing cp; struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; struct smp_chan *smp; @@ -2347,18 +2365,22 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) skb_pull(skb, sizeof(*rp)); - memset(&cp, 0, sizeof(cp)); - build_pairing_cmd(conn, &cp, NULL, auth); - - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &cp, sizeof(cp)); - - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); + smp_send_pairing_req(smp, auth); return 0; } +static void smp_send_security_req(struct smp_chan *smp, __u8 auth) +{ + struct smp_cmd_security_req cp; + + cp.auth_req = auth; + smp_send_cmd(smp->conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); + SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ); + + clear_bit(SMP_FLAG_INITIATOR, &smp->flags); +} + int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) { struct l2cap_conn *conn = hcon->l2cap_data; @@ -2427,23 +2449,11 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) authreq |= SMP_AUTH_MITM; } - if (hcon->role == HCI_ROLE_MASTER) { - struct smp_cmd_pairing cp; + if (hcon->role == HCI_ROLE_MASTER) + smp_send_pairing_req(smp, authreq); + else + smp_send_security_req(smp, authreq); - build_pairing_cmd(conn, &cp, NULL, authreq); - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &cp, sizeof(cp)); - - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); - } else { - struct smp_cmd_security_req cp; - cp.auth_req = authreq; - smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ); - } - - set_bit(SMP_FLAG_INITIATOR, &smp->flags); ret = 0; unlock: @@ -2694,8 +2704,6 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb) static u8 sc_select_method(struct smp_chan *smp) { - struct l2cap_conn *conn = smp->conn; - struct hci_conn *hcon = conn->hcon; struct smp_cmd_pairing *local, *remote; u8 local_mitm, remote_mitm, local_io, remote_io, method; @@ -2708,7 +2716,7 @@ static u8 sc_select_method(struct smp_chan *smp) * the "struct smp_cmd_pairing" from them we need to skip the * first byte which contains the opcode. */ - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local = (void *) &smp->preq[1]; remote = (void *) &smp->prsp[1]; } else { @@ -2777,7 +2785,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) /* Non-initiating device sends its public key after receiving * the key from the initiating device. */ - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { err = sc_send_public_key(smp); if (err) return err; @@ -2839,7 +2847,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) } if (smp->method == REQ_OOB) { - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); @@ -2848,7 +2856,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) return 0; } - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM); if (smp->method == REQ_PASSKEY) { @@ -2863,7 +2871,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) /* The Initiating device waits for the non-initiating device to * send the confirm value. */ - if (conn->hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return 0; err = smp_f4(smp->tfm_cmac, smp->local_pk, smp->remote_pk, smp->prnd, @@ -2897,7 +2905,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) a[6] = hcon->init_addr_type; b[6] = hcon->resp_addr_type; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local_addr = a; remote_addr = b; memcpy(io_cap, &smp->prsp[1], 3); @@ -2922,7 +2930,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) if (crypto_memneq(check->e, e, 16)) return SMP_DHKEY_CHECK_FAILED; - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { if (test_bit(SMP_FLAG_WAIT_USER, &smp->flags)) { set_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags); return 0; @@ -2934,7 +2942,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) sc_add_ltk(smp); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { hci_le_start_enc(hcon, 0, 0, smp->tk, smp->enc_key_size); hcon->enc_key_size = smp->enc_key_size; } @@ -3083,7 +3091,6 @@ static void bredr_pairing(struct l2cap_chan *chan) struct l2cap_conn *conn = chan->conn; struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; - struct smp_cmd_pairing req; struct smp_chan *smp; bt_dev_dbg(hdev, "chan %p", chan); @@ -3135,14 +3142,7 @@ static void bredr_pairing(struct l2cap_chan *chan) bt_dev_dbg(hdev, "starting SMP over BR/EDR"); - /* Prepare and send the BR/EDR SMP Pairing Request */ - build_bredr_pairing_cmd(smp, &req, NULL); - - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &req, sizeof(req)); - - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(req), &req); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); + smp_send_pairing_req(smp, 0x00); } static void smp_resume_cb(struct l2cap_chan *chan) From 538fd3921afac97158d4177139a0ad39f056dbb2 Mon Sep 17 00:00:00 2001 From: Griffin Kroah-Hartman Date: Thu, 15 Aug 2024 13:51:00 +0200 Subject: [PATCH 316/562] Bluetooth: MGMT: Add error handling to pair_device() hci_conn_params_add() never checks for a NULL value and could lead to a NULL pointer dereference causing a crash. Fixed by adding error handling in the function. Cc: Stable Fixes: 5157b8a503fa ("Bluetooth: Fix initializing conn_params in scan phase") Signed-off-by: Griffin Kroah-Hartman Reported-by: Yiwei Zhang Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/mgmt.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 40d4887c7f79..25979f4283a6 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -3456,6 +3456,10 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, * will be kept and this function does nothing. */ p = hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type); + if (!p) { + err = -EIO; + goto unlock; + } if (p->auto_connect == HCI_AUTO_CONN_EXPLICIT) p->auto_connect = HCI_AUTO_CONN_DISABLED; From 624ab9cde26a9f150b4fd268b0f3dae3184dc40c Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Tue, 16 Jul 2024 09:06:30 -0700 Subject: [PATCH 317/562] drm/msm/adreno: Fix error return if missing firmware-name -ENODEV is used to signify that there is no zap shader for the platform, and the CPU can directly take the GPU out of secure mode. We want to use this return code when there is no zap-shader node. But not when there is, but without a firmware-name property. This case we want to treat as-if the needed fw is not found. Signed-off-by: Rob Clark Reviewed-by: Dmitry Baryshkov Reviewed-by: Akhil P Oommen Patchwork: https://patchwork.freedesktop.org/patch/604564/ --- drivers/gpu/drm/msm/adreno/adreno_gpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 1c6626747b98..ecc3fc5cec22 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -99,7 +99,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname, * was a bad idea, and is only provided for backwards * compatibility for older targets. */ - return -ENODEV; + return -ENOENT; } if (IS_ERR(fw)) { From c0247d289e73e18f6ddb0895de30c09770fbed95 Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Tue, 13 Aug 2024 12:53:15 +0200 Subject: [PATCH 318/562] btrfs: send: annotate struct name_cache_entry with __counted_by() Add the __counted_by compiler attribute to the flexible array member name to improve access bounds-checking via CONFIG_UBSAN_BOUNDS and CONFIG_FORTIFY_SOURCE. Signed-off-by: Thorsten Blum Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/send.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 7fc692fc76e1..619fa0b8b3f6 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -347,7 +347,7 @@ struct name_cache_entry { int ret; int need_later_update; int name_len; - char name[]; + char name[] __counted_by(name_len); }; /* See the comment at lru_cache.h about struct btrfs_lru_cache_entry. */ From 3bc2ac2f8f0b78a13140fc72022771efe0c9b778 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 12 Aug 2024 12:30:52 -0400 Subject: [PATCH 319/562] btrfs: update target inode's ctime on unlink Unlink changes the link count on the target inode. POSIX mandates that the ctime must also change when this occurs. According to https://pubs.opengroup.org/onlinepubs/9699919799/functions/unlink.html: "Upon successful completion, unlink() shall mark for update the last data modification and last file status change timestamps of the parent directory. Also, if the file's link count is not 0, the last file status change timestamp of the file shall be marked for update." Signed-off-by: Jeff Layton Reviewed-by: David Sterba [ add link to the opengroup docs ] Signed-off-by: David Sterba --- fs/btrfs/inode.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 333b0e8587a2..b1b6564ab68f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4195,6 +4195,7 @@ err: btrfs_i_size_write(dir, dir->vfs_inode.i_size - name->len * 2); inode_inc_iversion(&inode->vfs_inode); + inode_set_ctime_current(&inode->vfs_inode); inode_inc_iversion(&dir->vfs_inode); inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode)); ret = btrfs_update_inode(trans, dir); From 008e2512dc5696ab2dc5bf264e98a9fe9ceb830e Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Sun, 11 Aug 2024 15:00:22 +0930 Subject: [PATCH 320/562] btrfs: tree-checker: add dev extent item checks [REPORT] There is a corruption report that btrfs refused to mount a fs that has overlapping dev extents: BTRFS error (device sdc): dev extent devid 4 physical offset 14263979671552 overlap with previous dev extent end 14263980982272 BTRFS error (device sdc): failed to verify dev extents against chunks: -117 BTRFS error (device sdc): open_ctree failed [CAUSE] The direct cause is very obvious, there is a bad dev extent item with incorrect length. With btrfs check reporting two overlapping extents, the second one shows some clue on the cause: ERROR: dev extent devid 4 offset 14263979671552 len 6488064 overlap with previous dev extent end 14263980982272 ERROR: dev extent devid 13 offset 2257707008000 len 6488064 overlap with previous dev extent end 2257707270144 ERROR: errors found in extent allocation tree or chunk allocation The second one looks like a bitflip happened during new chunk allocation: hex(2257707008000) = 0x20da9d30000 hex(2257707270144) = 0x20da9d70000 diff = 0x00000040000 So it looks like a bitflip happened during new dev extent allocation, resulting the second overlap. Currently we only do the dev-extent verification at mount time, but if the corruption is caused by memory bitflip, we really want to catch it before writing the corruption to the storage. Furthermore the dev extent items has the following key definition: ( DEV_EXTENT ) Thus we can not just rely on the generic key order check to make sure there is no overlapping. [ENHANCEMENT] Introduce dedicated dev extent checks, including: - Fixed member checks * chunk_tree should always be BTRFS_CHUNK_TREE_OBJECTID (3) * chunk_objectid should always be BTRFS_FIRST_CHUNK_CHUNK_TREE_OBJECTID (256) - Alignment checks * chunk_offset should be aligned to sectorsize * length should be aligned to sectorsize * key.offset should be aligned to sectorsize - Overlap checks If the previous key is also a dev-extent item, with the same device id, make sure we do not overlap with the previous dev extent. Reported: Stefan N Link: https://lore.kernel.org/linux-btrfs/CA+W5K0rSO3koYTo=nzxxTm1-Pdu1HYgVxEpgJ=aGc7d=E8mGEg@mail.gmail.com/ CC: stable@vger.kernel.org # 5.10+ Reviewed-by: Anand Jain Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/tree-checker.c | 69 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 6f1e2f2215d9..634d69964fe4 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1764,6 +1764,72 @@ static int check_raid_stripe_extent(const struct extent_buffer *leaf, return 0; } +static int check_dev_extent_item(const struct extent_buffer *leaf, + const struct btrfs_key *key, + int slot, + struct btrfs_key *prev_key) +{ + struct btrfs_dev_extent *de; + const u32 sectorsize = leaf->fs_info->sectorsize; + + de = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent); + /* Basic fixed member checks. */ + if (unlikely(btrfs_dev_extent_chunk_tree(leaf, de) != + BTRFS_CHUNK_TREE_OBJECTID)) { + generic_err(leaf, slot, + "invalid dev extent chunk tree id, has %llu expect %llu", + btrfs_dev_extent_chunk_tree(leaf, de), + BTRFS_CHUNK_TREE_OBJECTID); + return -EUCLEAN; + } + if (unlikely(btrfs_dev_extent_chunk_objectid(leaf, de) != + BTRFS_FIRST_CHUNK_TREE_OBJECTID)) { + generic_err(leaf, slot, + "invalid dev extent chunk objectid, has %llu expect %llu", + btrfs_dev_extent_chunk_objectid(leaf, de), + BTRFS_FIRST_CHUNK_TREE_OBJECTID); + return -EUCLEAN; + } + /* Alignment check. */ + if (unlikely(!IS_ALIGNED(key->offset, sectorsize))) { + generic_err(leaf, slot, + "invalid dev extent key.offset, has %llu not aligned to %u", + key->offset, sectorsize); + return -EUCLEAN; + } + if (unlikely(!IS_ALIGNED(btrfs_dev_extent_chunk_offset(leaf, de), + sectorsize))) { + generic_err(leaf, slot, + "invalid dev extent chunk offset, has %llu not aligned to %u", + btrfs_dev_extent_chunk_objectid(leaf, de), + sectorsize); + return -EUCLEAN; + } + if (unlikely(!IS_ALIGNED(btrfs_dev_extent_length(leaf, de), + sectorsize))) { + generic_err(leaf, slot, + "invalid dev extent length, has %llu not aligned to %u", + btrfs_dev_extent_length(leaf, de), sectorsize); + return -EUCLEAN; + } + /* Overlap check with previous dev extent. */ + if (slot && prev_key->objectid == key->objectid && + prev_key->type == key->type) { + struct btrfs_dev_extent *prev_de; + u64 prev_len; + + prev_de = btrfs_item_ptr(leaf, slot - 1, struct btrfs_dev_extent); + prev_len = btrfs_dev_extent_length(leaf, prev_de); + if (unlikely(prev_key->offset + prev_len > key->offset)) { + generic_err(leaf, slot, + "dev extent overlap, prev offset %llu len %llu current offset %llu", + prev_key->objectid, prev_len, key->offset); + return -EUCLEAN; + } + } + return 0; +} + /* * Common point to switch the item-specific validation. */ @@ -1800,6 +1866,9 @@ static enum btrfs_tree_block_status check_leaf_item(struct extent_buffer *leaf, case BTRFS_DEV_ITEM_KEY: ret = check_dev_item(leaf, key, slot); break; + case BTRFS_DEV_EXTENT_KEY: + ret = check_dev_extent_item(leaf, key, slot, prev_key); + break; case BTRFS_INODE_ITEM_KEY: ret = check_inode_item(leaf, key, slot); break; From e30729d4bd4001881be4d1ad4332a5d4985398f8 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Thu, 1 Aug 2024 16:47:52 +0900 Subject: [PATCH 321/562] btrfs: zoned: properly take lock to read/update block group's zoned variables __btrfs_add_free_space_zoned() references and modifies bg's alloc_offset, ro, and zone_unusable, but without taking the lock. It is mostly safe because they monotonically increase (at least for now) and this function is mostly called by a transaction commit, which is serialized by itself. Still, taking the lock is a safer and correct option and I'm going to add a change to reset zone_unusable while a block group is still alive. So, add locking around the operations. Fixes: 169e0da91a21 ("btrfs: zoned: track unusable bytes for zones") CC: stable@vger.kernel.org # 5.15+ Reviewed-by: Johannes Thumshirn Signed-off-by: Naohiro Aota Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/free-space-cache.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index f5996a43db24..eaa1dbd31352 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2697,15 +2697,16 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, u64 offset = bytenr - block_group->start; u64 to_free, to_unusable; int bg_reclaim_threshold = 0; - bool initial = ((size == block_group->length) && (block_group->alloc_offset == 0)); + bool initial; u64 reclaimable_unusable; - WARN_ON(!initial && offset + size > block_group->zone_capacity); + spin_lock(&block_group->lock); + initial = ((size == block_group->length) && (block_group->alloc_offset == 0)); + WARN_ON(!initial && offset + size > block_group->zone_capacity); if (!initial) bg_reclaim_threshold = READ_ONCE(sinfo->bg_reclaim_threshold); - spin_lock(&ctl->tree_lock); if (!used) to_free = size; else if (initial) @@ -2718,7 +2719,9 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, to_free = offset + size - block_group->alloc_offset; to_unusable = size - to_free; + spin_lock(&ctl->tree_lock); ctl->free_space += to_free; + spin_unlock(&ctl->tree_lock); /* * If the block group is read-only, we should account freed space into * bytes_readonly. @@ -2727,11 +2730,8 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, block_group->zone_unusable += to_unusable; WARN_ON(block_group->zone_unusable > block_group->length); } - spin_unlock(&ctl->tree_lock); if (!used) { - spin_lock(&block_group->lock); block_group->alloc_offset -= size; - spin_unlock(&block_group->lock); } reclaimable_unusable = block_group->zone_unusable - @@ -2745,6 +2745,8 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, btrfs_mark_bg_to_reclaim(block_group); } + spin_unlock(&block_group->lock); + return 0; } From 6486cad00a8b7f8585983408c152bbe33dda529b Mon Sep 17 00:00:00 2001 From: David Gstir Date: Wed, 17 Jul 2024 13:28:44 +0200 Subject: [PATCH 322/562] KEYS: trusted: fix DCP blob payload length assignment The DCP trusted key type uses the wrong helper function to store the blob's payload length which can lead to the wrong byte order being used in case this would ever run on big endian architectures. Fix by using correct helper function. Cc: stable@vger.kernel.org # v6.10+ Fixes: 2e8a0f40a39c ("KEYS: trusted: Introduce NXP DCP-backed trusted keys") Suggested-by: Richard Weinberger Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202405240610.fj53EK0q-lkp@intel.com/ Signed-off-by: David Gstir Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- security/keys/trusted-keys/trusted_dcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/keys/trusted-keys/trusted_dcp.c b/security/keys/trusted-keys/trusted_dcp.c index b5f81a05be36..b0947f072a98 100644 --- a/security/keys/trusted-keys/trusted_dcp.c +++ b/security/keys/trusted-keys/trusted_dcp.c @@ -222,7 +222,7 @@ static int trusted_dcp_seal(struct trusted_key_payload *p, char *datablob) return ret; } - b->payload_len = get_unaligned_le32(&p->key_len); + put_unaligned_le32(p->key_len, &b->payload_len); p->blob_len = blen; return 0; } From 0e28bf61a5f9ab30be3f3b4eafb8d097e39446bb Mon Sep 17 00:00:00 2001 From: David Gstir Date: Wed, 17 Jul 2024 13:28:45 +0200 Subject: [PATCH 323/562] KEYS: trusted: dcp: fix leak of blob encryption key Trusted keys unseal the key blob on load, but keep the sealed payload in the blob field so that every subsequent read (export) will simply convert this field to hex and send it to userspace. With DCP-based trusted keys, we decrypt the blob encryption key (BEK) in the Kernel due hardware limitations and then decrypt the blob payload. BEK decryption is done in-place which means that the trusted key blob field is modified and it consequently holds the BEK in plain text. Every subsequent read of that key thus send the plain text BEK instead of the encrypted BEK to userspace. This issue only occurs when importing a trusted DCP-based key and then exporting it again. This should rarely happen as the common use cases are to either create a new trusted key and export it, or import a key blob and then just use it without exporting it again. Fix this by performing BEK decryption and encryption in a dedicated buffer. Further always wipe the plain text BEK buffer to prevent leaking the key via uninitialized memory. Cc: stable@vger.kernel.org # v6.10+ Fixes: 2e8a0f40a39c ("KEYS: trusted: Introduce NXP DCP-backed trusted keys") Signed-off-by: David Gstir Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- security/keys/trusted-keys/trusted_dcp.c | 33 +++++++++++++++--------- 1 file changed, 21 insertions(+), 12 deletions(-) diff --git a/security/keys/trusted-keys/trusted_dcp.c b/security/keys/trusted-keys/trusted_dcp.c index b0947f072a98..4edc5bbbcda3 100644 --- a/security/keys/trusted-keys/trusted_dcp.c +++ b/security/keys/trusted-keys/trusted_dcp.c @@ -186,20 +186,21 @@ out: return ret; } -static int decrypt_blob_key(u8 *key) +static int decrypt_blob_key(u8 *encrypted_key, u8 *plain_key) { - return do_dcp_crypto(key, key, false); + return do_dcp_crypto(encrypted_key, plain_key, false); } -static int encrypt_blob_key(u8 *key) +static int encrypt_blob_key(u8 *plain_key, u8 *encrypted_key) { - return do_dcp_crypto(key, key, true); + return do_dcp_crypto(plain_key, encrypted_key, true); } static int trusted_dcp_seal(struct trusted_key_payload *p, char *datablob) { struct dcp_blob_fmt *b = (struct dcp_blob_fmt *)p->blob; int blen, ret; + u8 plain_blob_key[AES_KEYSIZE_128]; blen = calc_blob_len(p->key_len); if (blen > MAX_BLOB_SIZE) @@ -207,30 +208,36 @@ static int trusted_dcp_seal(struct trusted_key_payload *p, char *datablob) b->fmt_version = DCP_BLOB_VERSION; get_random_bytes(b->nonce, AES_KEYSIZE_128); - get_random_bytes(b->blob_key, AES_KEYSIZE_128); + get_random_bytes(plain_blob_key, AES_KEYSIZE_128); - ret = do_aead_crypto(p->key, b->payload, p->key_len, b->blob_key, + ret = do_aead_crypto(p->key, b->payload, p->key_len, plain_blob_key, b->nonce, true); if (ret) { pr_err("Unable to encrypt blob payload: %i\n", ret); - return ret; + goto out; } - ret = encrypt_blob_key(b->blob_key); + ret = encrypt_blob_key(plain_blob_key, b->blob_key); if (ret) { pr_err("Unable to encrypt blob key: %i\n", ret); - return ret; + goto out; } put_unaligned_le32(p->key_len, &b->payload_len); p->blob_len = blen; - return 0; + ret = 0; + +out: + memzero_explicit(plain_blob_key, sizeof(plain_blob_key)); + + return ret; } static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob) { struct dcp_blob_fmt *b = (struct dcp_blob_fmt *)p->blob; int blen, ret; + u8 plain_blob_key[AES_KEYSIZE_128]; if (b->fmt_version != DCP_BLOB_VERSION) { pr_err("DCP blob has bad version: %i, expected %i\n", @@ -248,14 +255,14 @@ static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob) goto out; } - ret = decrypt_blob_key(b->blob_key); + ret = decrypt_blob_key(b->blob_key, plain_blob_key); if (ret) { pr_err("Unable to decrypt blob key: %i\n", ret); goto out; } ret = do_aead_crypto(b->payload, p->key, p->key_len + DCP_BLOB_AUTHLEN, - b->blob_key, b->nonce, false); + plain_blob_key, b->nonce, false); if (ret) { pr_err("Unwrap of DCP payload failed: %i\n", ret); goto out; @@ -263,6 +270,8 @@ static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob) ret = 0; out: + memzero_explicit(plain_blob_key, sizeof(plain_blob_key)); + return ret; } From e01d48c699bbe015d887cb598e4047f08f3998a8 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Wed, 14 Aug 2024 21:26:19 +0200 Subject: [PATCH 324/562] riscv: Fix out-of-bounds when accessing Andes per hart vendor extension array The out-of-bounds access is reported by UBSAN: [ 0.000000] UBSAN: array-index-out-of-bounds in ../arch/riscv/kernel/vendor_extensions.c:41:66 [ 0.000000] index -1 is out of range for type 'riscv_isavendorinfo [32]' [ 0.000000] CPU: 0 UID: 0 PID: 0 Comm: swapper Not tainted 6.11.0-rc2ubuntu-defconfig #2 [ 0.000000] Hardware name: riscv-virtio,qemu (DT) [ 0.000000] Call Trace: [ 0.000000] [] dump_backtrace+0x32/0x40 [ 0.000000] [] show_stack+0x38/0x44 [ 0.000000] [] dump_stack_lvl+0x70/0x9c [ 0.000000] [] dump_stack+0x18/0x20 [ 0.000000] [] ubsan_epilogue+0x10/0x46 [ 0.000000] [] __ubsan_handle_out_of_bounds+0x94/0x9c [ 0.000000] [] __riscv_isa_vendor_extension_available+0x90/0x92 [ 0.000000] [] riscv_cpufeature_patch_func+0xc4/0x148 [ 0.000000] [] _apply_alternatives+0x42/0x50 [ 0.000000] [] apply_boot_alternatives+0x3c/0x100 [ 0.000000] [] setup_arch+0x85a/0x8bc [ 0.000000] [] start_kernel+0xa4/0xfb6 The dereferencing using cpu should actually not happen, so remove it. Fixes: 23c996fc2bc1 ("riscv: Extend cpufeature.c to detect vendor extensions") Signed-off-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20240814192619.276794-1-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/vendor_extensions.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kernel/vendor_extensions.c b/arch/riscv/kernel/vendor_extensions.c index b6c1e7b5d34b..a8126d118341 100644 --- a/arch/riscv/kernel/vendor_extensions.c +++ b/arch/riscv/kernel/vendor_extensions.c @@ -38,7 +38,7 @@ bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsig #ifdef CONFIG_RISCV_ISA_VENDOR_EXT_ANDES case ANDES_VENDOR_ID: bmap = &riscv_isa_vendor_ext_list_andes.all_harts_isa_bitmap; - cpu_bmap = &riscv_isa_vendor_ext_list_andes.per_hart_isa_bitmap[cpu]; + cpu_bmap = riscv_isa_vendor_ext_list_andes.per_hart_isa_bitmap; break; #endif default: From 74c2ab6d653b4c2354df65a7f7f2df1925a40a51 Mon Sep 17 00:00:00 2001 From: Su Hui Date: Thu, 8 Aug 2024 20:23:32 +0800 Subject: [PATCH 325/562] smb/client: avoid possible NULL dereference in cifs_free_subrequest() Clang static checker (scan-build) warning: cifsglob.h:line 890, column 3 Access to field 'ops' results in a dereference of a null pointer. Commit 519be989717c ("cifs: Add a tracepoint to track credits involved in R/W requests") adds a check for 'rdata->server', and let clang throw this warning about NULL dereference. When 'rdata->credits.value != 0 && rdata->server == NULL' happens, add_credits_and_wake_if() will call rdata->server->ops->add_credits(). This will cause NULL dereference problem. Add a check for 'rdata->server' to avoid NULL dereference. Cc: stable@vger.kernel.org Fixes: 69c3c023af25 ("cifs: Implement netfslib hooks") Reviewed-by: David Howells Signed-off-by: Su Hui Signed-off-by: Steve French --- fs/smb/client/file.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index b2405dd4d4d4..45459af5044d 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -315,7 +315,7 @@ static void cifs_free_subrequest(struct netfs_io_subrequest *subreq) #endif } - if (rdata->credits.value != 0) + if (rdata->credits.value != 0) { trace_smb3_rw_credits(rdata->rreq->debug_id, rdata->subreq.debug_index, rdata->credits.value, @@ -323,8 +323,12 @@ static void cifs_free_subrequest(struct netfs_io_subrequest *subreq) rdata->server ? rdata->server->in_flight : 0, -rdata->credits.value, cifs_trace_rw_credits_free_subreq); + if (rdata->server) + add_credits_and_wake_if(rdata->server, &rdata->credits, 0); + else + rdata->credits.value = 0; + } - add_credits_and_wake_if(rdata->server, &rdata->credits, 0); if (rdata->have_xid) free_xid(rdata->xid); } From c916ca35308d3187c9928664f9be249b22a3a701 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Sat, 3 Aug 2024 17:11:37 +0800 Subject: [PATCH 326/562] md/raid1: Fix data corruption for degraded array with slow disk MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit read_balance() will avoid reading from slow disks as much as possible, however, if valid data only lands in slow disks, and a new normal disk is still in recovery, unrecovered data can be read: raid1_read_request read_balance raid1_should_read_first -> return false choose_best_rdev -> normal disk is not recovered, return -1 choose_bb_rdev -> missing the checking of recovery, return the normal disk -> read unrecovered data Root cause is that the checking of recovery is missing in choose_bb_rdev(). Hence add such checking to fix the problem. Also fix similar problem in choose_slow_rdev(). Cc: stable@vger.kernel.org Fixes: 9f3ced792203 ("md/raid1: factor out choose_bb_rdev() from read_balance()") Fixes: dfa8ecd167c1 ("md/raid1: factor out choose_slow_rdev() from read_balance()") Reported-and-tested-by: Mateusz Jończyk Closes: https://lore.kernel.org/all/9952f532-2554-44bf-b906-4880b2e88e3a@o2.pl/ Signed-off-by: Yu Kuai Link: https://lore.kernel.org/r/20240803091137.3197008-1-yukuai1@huaweicloud.com Signed-off-by: Song Liu --- drivers/md/raid1.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 7acfe7c9dc8d..761989d67906 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -617,6 +617,12 @@ static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio, return -1; } +static bool rdev_in_recovery(struct md_rdev *rdev, struct r1bio *r1_bio) +{ + return !test_bit(In_sync, &rdev->flags) && + rdev->recovery_offset < r1_bio->sector + r1_bio->sectors; +} + static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio, int *max_sectors) { @@ -635,6 +641,7 @@ static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio, rdev = conf->mirrors[disk].rdev; if (!rdev || test_bit(Faulty, &rdev->flags) || + rdev_in_recovery(rdev, r1_bio) || test_bit(WriteMostly, &rdev->flags)) continue; @@ -673,7 +680,8 @@ static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio, rdev = conf->mirrors[disk].rdev; if (!rdev || test_bit(Faulty, &rdev->flags) || - !test_bit(WriteMostly, &rdev->flags)) + !test_bit(WriteMostly, &rdev->flags) || + rdev_in_recovery(rdev, r1_bio)) continue; /* there are no bad blocks, we can use this disk */ @@ -733,9 +741,7 @@ static bool rdev_readable(struct md_rdev *rdev, struct r1bio *r1_bio) if (!rdev || test_bit(Faulty, &rdev->flags)) return false; - /* still in recovery */ - if (!test_bit(In_sync, &rdev->flags) && - rdev->recovery_offset < r1_bio->sector + r1_bio->sectors) + if (rdev_in_recovery(rdev, r1_bio)) return false; /* don't read from slow disk unless have to */ From 836bb3268db405cf9021496ac4dbc26d3e4758fe Mon Sep 17 00:00:00 2001 From: Steve French Date: Thu, 15 Aug 2024 14:03:43 -0500 Subject: [PATCH 327/562] smb3: fix lock breakage for cached writes Mandatory locking is enforced for cached writes, which violates default posix semantics, and also it is enforced inconsistently. This apparently breaks recent versions of libreoffice, but can also be demonstrated by opening a file twice from the same client, locking it from handle one and writing to it from handle two (which fails, returning EACCES). Since there was already a mount option "forcemandatorylock" (which defaults to off), with this change only when the user intentionally specifies "forcemandatorylock" on mount will we break posix semantics on write to a locked range (ie we will only fail the write in this case, if the user mounts with "forcemandatorylock"). Fixes: 85160e03a79e ("CIFS: Implement caching mechanism for mandatory brlocks") Cc: stable@vger.kernel.org Cc: Pavel Shilovsky Reported-by: abartlet@samba.org Reported-by: Kevin Ottens Reviewed-by: David Howells Signed-off-by: Steve French --- fs/smb/client/file.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 45459af5044d..06a0667f8ff2 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -2753,6 +2753,7 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file->f_mapping->host; struct cifsInodeInfo *cinode = CIFS_I(inode); struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server; + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); ssize_t rc; rc = netfs_start_io_write(inode); @@ -2769,12 +2770,16 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) if (rc <= 0) goto out; - if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from), + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) && + (cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from), server->vals->exclusive_lock_type, 0, - NULL, CIFS_WRITE_OP)) - rc = netfs_buffered_write_iter_locked(iocb, from, NULL); - else + NULL, CIFS_WRITE_OP))) { rc = -EACCES; + goto out; + } + + rc = netfs_buffered_write_iter_locked(iocb, from, NULL); + out: up_read(&cinode->lock_sem); netfs_end_io_write(inode); From 5b4f3af39b6588e8de4444d8e1ccf759b40f9414 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 8 Aug 2024 16:04:04 -0600 Subject: [PATCH 328/562] smb: smb2pdu.h: Use static_assert() to check struct sizes Commit 9f9bef9bc5c6 ("smb: smb2pdu.h: Avoid -Wflex-array-member-not-at-end warnings") introduced tagged `struct create_context_hdr`. We want to ensure that when new members need to be added to the flexible structure, they are always included within this tagged struct. So, we use `static_assert()` to ensure that the memory layout for both the flexible structure and the tagged struct is the same after any changes. Acked-by: Namjae Jeon Signed-off-by: Gustavo A. R. Silva Signed-off-by: Steve French --- fs/smb/common/smb2pdu.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index c3ee42188d25..c769f9dbc0b4 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -1216,6 +1216,8 @@ struct create_context { ); __u8 Buffer[]; } __packed; +static_assert(offsetof(struct create_context, Buffer) == sizeof(struct create_context_hdr), + "struct member likely outside of __struct_group()"); struct smb2_create_req { struct smb2_hdr hdr; From b313a8c835516bdda85025500be866ac8a74e022 Mon Sep 17 00:00:00 2001 From: Li Lingfeng Date: Thu, 15 Aug 2024 10:47:36 +0800 Subject: [PATCH 329/562] block: Fix lockdep warning in blk_mq_mark_tag_wait Lockdep reported a warning in Linux version 6.6: [ 414.344659] ================================ [ 414.345155] WARNING: inconsistent lock state [ 414.345658] 6.6.0-07439-gba2303cacfda #6 Not tainted [ 414.346221] -------------------------------- [ 414.346712] inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage. [ 414.347545] kworker/u10:3/1152 [HC0[0]:SC0[0]:HE0:SE1] takes: [ 414.349245] ffff88810edd1098 (&sbq->ws[i].wait){+.?.}-{2:2}, at: blk_mq_dispatch_rq_list+0x131c/0x1ee0 [ 414.351204] {IN-SOFTIRQ-W} state was registered at: [ 414.351751] lock_acquire+0x18d/0x460 [ 414.352218] _raw_spin_lock_irqsave+0x39/0x60 [ 414.352769] __wake_up_common_lock+0x22/0x60 [ 414.353289] sbitmap_queue_wake_up+0x375/0x4f0 [ 414.353829] sbitmap_queue_clear+0xdd/0x270 [ 414.354338] blk_mq_put_tag+0xdf/0x170 [ 414.354807] __blk_mq_free_request+0x381/0x4d0 [ 414.355335] blk_mq_free_request+0x28b/0x3e0 [ 414.355847] __blk_mq_end_request+0x242/0xc30 [ 414.356367] scsi_end_request+0x2c1/0x830 [ 414.345155] WARNING: inconsistent lock state [ 414.345658] 6.6.0-07439-gba2303cacfda #6 Not tainted [ 414.346221] -------------------------------- [ 414.346712] inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage. [ 414.347545] kworker/u10:3/1152 [HC0[0]:SC0[0]:HE0:SE1] takes: [ 414.349245] ffff88810edd1098 (&sbq->ws[i].wait){+.?.}-{2:2}, at: blk_mq_dispatch_rq_list+0x131c/0x1ee0 [ 414.351204] {IN-SOFTIRQ-W} state was registered at: [ 414.351751] lock_acquire+0x18d/0x460 [ 414.352218] _raw_spin_lock_irqsave+0x39/0x60 [ 414.352769] __wake_up_common_lock+0x22/0x60 [ 414.353289] sbitmap_queue_wake_up+0x375/0x4f0 [ 414.353829] sbitmap_queue_clear+0xdd/0x270 [ 414.354338] blk_mq_put_tag+0xdf/0x170 [ 414.354807] __blk_mq_free_request+0x381/0x4d0 [ 414.355335] blk_mq_free_request+0x28b/0x3e0 [ 414.355847] __blk_mq_end_request+0x242/0xc30 [ 414.356367] scsi_end_request+0x2c1/0x830 [ 414.356863] scsi_io_completion+0x177/0x1610 [ 414.357379] scsi_complete+0x12f/0x260 [ 414.357856] blk_complete_reqs+0xba/0xf0 [ 414.358338] __do_softirq+0x1b0/0x7a2 [ 414.358796] irq_exit_rcu+0x14b/0x1a0 [ 414.359262] sysvec_call_function_single+0xaf/0xc0 [ 414.359828] asm_sysvec_call_function_single+0x1a/0x20 [ 414.360426] default_idle+0x1e/0x30 [ 414.360873] default_idle_call+0x9b/0x1f0 [ 414.361390] do_idle+0x2d2/0x3e0 [ 414.361819] cpu_startup_entry+0x55/0x60 [ 414.362314] start_secondary+0x235/0x2b0 [ 414.362809] secondary_startup_64_no_verify+0x18f/0x19b [ 414.363413] irq event stamp: 428794 [ 414.363825] hardirqs last enabled at (428793): [] ktime_get+0x1dc/0x200 [ 414.364694] hardirqs last disabled at (428794): [] _raw_spin_lock_irq+0x47/0x50 [ 414.365629] softirqs last enabled at (428444): [] __do_softirq+0x540/0x7a2 [ 414.366522] softirqs last disabled at (428419): [] irq_exit_rcu+0x14b/0x1a0 [ 414.367425] other info that might help us debug this: [ 414.368194] Possible unsafe locking scenario: [ 414.368900] CPU0 [ 414.369225] ---- [ 414.369548] lock(&sbq->ws[i].wait); [ 414.370000] [ 414.370342] lock(&sbq->ws[i].wait); [ 414.370802] *** DEADLOCK *** [ 414.371569] 5 locks held by kworker/u10:3/1152: [ 414.372088] #0: ffff88810130e938 ((wq_completion)writeback){+.+.}-{0:0}, at: process_scheduled_works+0x357/0x13f0 [ 414.373180] #1: ffff88810201fdb8 ((work_completion)(&(&wb->dwork)->work)){+.+.}-{0:0}, at: process_scheduled_works+0x3a3/0x13f0 [ 414.374384] #2: ffffffff86ffbdc0 (rcu_read_lock){....}-{1:2}, at: blk_mq_run_hw_queue+0x637/0xa00 [ 414.375342] #3: ffff88810edd1098 (&sbq->ws[i].wait){+.?.}-{2:2}, at: blk_mq_dispatch_rq_list+0x131c/0x1ee0 [ 414.376377] #4: ffff888106205a08 (&hctx->dispatch_wait_lock){+.-.}-{2:2}, at: blk_mq_dispatch_rq_list+0x1337/0x1ee0 [ 414.378607] stack backtrace: [ 414.379177] CPU: 0 PID: 1152 Comm: kworker/u10:3 Not tainted 6.6.0-07439-gba2303cacfda #6 [ 414.380032] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 414.381177] Workqueue: writeback wb_workfn (flush-253:0) [ 414.381805] Call Trace: [ 414.382136] [ 414.382429] dump_stack_lvl+0x91/0xf0 [ 414.382884] mark_lock_irq+0xb3b/0x1260 [ 414.383367] ? __pfx_mark_lock_irq+0x10/0x10 [ 414.383889] ? stack_trace_save+0x8e/0xc0 [ 414.384373] ? __pfx_stack_trace_save+0x10/0x10 [ 414.384903] ? graph_lock+0xcf/0x410 [ 414.385350] ? save_trace+0x3d/0xc70 [ 414.385808] mark_lock.part.20+0x56d/0xa90 [ 414.386317] mark_held_locks+0xb0/0x110 [ 414.386791] ? __pfx_do_raw_spin_lock+0x10/0x10 [ 414.387320] lockdep_hardirqs_on_prepare+0x297/0x3f0 [ 414.387901] ? _raw_spin_unlock_irq+0x28/0x50 [ 414.388422] trace_hardirqs_on+0x58/0x100 [ 414.388917] _raw_spin_unlock_irq+0x28/0x50 [ 414.389422] __blk_mq_tag_busy+0x1d6/0x2a0 [ 414.389920] __blk_mq_get_driver_tag+0x761/0x9f0 [ 414.390899] blk_mq_dispatch_rq_list+0x1780/0x1ee0 [ 414.391473] ? __pfx_blk_mq_dispatch_rq_list+0x10/0x10 [ 414.392070] ? sbitmap_get+0x2b8/0x450 [ 414.392533] ? __blk_mq_get_driver_tag+0x210/0x9f0 [ 414.393095] __blk_mq_sched_dispatch_requests+0xd99/0x1690 [ 414.393730] ? elv_attempt_insert_merge+0x1b1/0x420 [ 414.394302] ? __pfx___blk_mq_sched_dispatch_requests+0x10/0x10 [ 414.394970] ? lock_acquire+0x18d/0x460 [ 414.395456] ? blk_mq_run_hw_queue+0x637/0xa00 [ 414.395986] ? __pfx_lock_acquire+0x10/0x10 [ 414.396499] blk_mq_sched_dispatch_requests+0x109/0x190 [ 414.397100] blk_mq_run_hw_queue+0x66e/0xa00 [ 414.397616] blk_mq_flush_plug_list.part.17+0x614/0x2030 [ 414.398244] ? __pfx_blk_mq_flush_plug_list.part.17+0x10/0x10 [ 414.398897] ? writeback_sb_inodes+0x241/0xcc0 [ 414.399429] blk_mq_flush_plug_list+0x65/0x80 [ 414.399957] __blk_flush_plug+0x2f1/0x530 [ 414.400458] ? __pfx___blk_flush_plug+0x10/0x10 [ 414.400999] blk_finish_plug+0x59/0xa0 [ 414.401467] wb_writeback+0x7cc/0x920 [ 414.401935] ? __pfx_wb_writeback+0x10/0x10 [ 414.402442] ? mark_held_locks+0xb0/0x110 [ 414.402931] ? __pfx_do_raw_spin_lock+0x10/0x10 [ 414.403462] ? lockdep_hardirqs_on_prepare+0x297/0x3f0 [ 414.404062] wb_workfn+0x2b3/0xcf0 [ 414.404500] ? __pfx_wb_workfn+0x10/0x10 [ 414.404989] process_scheduled_works+0x432/0x13f0 [ 414.405546] ? __pfx_process_scheduled_works+0x10/0x10 [ 414.406139] ? do_raw_spin_lock+0x101/0x2a0 [ 414.406641] ? assign_work+0x19b/0x240 [ 414.407106] ? lock_is_held_type+0x9d/0x110 [ 414.407604] worker_thread+0x6f2/0x1160 [ 414.408075] ? __kthread_parkme+0x62/0x210 [ 414.408572] ? lockdep_hardirqs_on_prepare+0x297/0x3f0 [ 414.409168] ? __kthread_parkme+0x13c/0x210 [ 414.409678] ? __pfx_worker_thread+0x10/0x10 [ 414.410191] kthread+0x33c/0x440 [ 414.410602] ? __pfx_kthread+0x10/0x10 [ 414.411068] ret_from_fork+0x4d/0x80 [ 414.411526] ? __pfx_kthread+0x10/0x10 [ 414.411993] ret_from_fork_asm+0x1b/0x30 [ 414.412489] When interrupt is turned on while a lock holding by spin_lock_irq it throws a warning because of potential deadlock. blk_mq_prep_dispatch_rq blk_mq_get_driver_tag __blk_mq_get_driver_tag __blk_mq_alloc_driver_tag blk_mq_tag_busy -> tag is already busy // failed to get driver tag blk_mq_mark_tag_wait spin_lock_irq(&wq->lock) -> lock A (&sbq->ws[i].wait) __add_wait_queue(wq, wait) -> wait queue active blk_mq_get_driver_tag __blk_mq_tag_busy -> 1) tag must be idle, which means there can't be inflight IO spin_lock_irq(&tags->lock) -> lock B (hctx->tags) spin_unlock_irq(&tags->lock) -> unlock B, turn on interrupt accidentally -> 2) context must be preempt by IO interrupt to trigger deadlock. As shown above, the deadlock is not possible in theory, but the warning still need to be fixed. Fix it by using spin_lock_irqsave to get lockB instead of spin_lock_irq. Fixes: 4f1731df60f9 ("blk-mq: fix potential io hang by wrong 'wake_batch'") Signed-off-by: Li Lingfeng Reviewed-by: Ming Lei Reviewed-by: Yu Kuai Reviewed-by: Bart Van Assche Link: https://lore.kernel.org/r/20240815024736.2040971-1-lilingfeng@huaweicloud.com Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index cc57e2dd9a0b..2cafcf11ee8b 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -38,6 +38,7 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags, void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { unsigned int users; + unsigned long flags; struct blk_mq_tags *tags = hctx->tags; /* @@ -56,11 +57,11 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) return; } - spin_lock_irq(&tags->lock); + spin_lock_irqsave(&tags->lock, flags); users = tags->active_queues + 1; WRITE_ONCE(tags->active_queues, users); blk_mq_update_wake_batch(tags, users); - spin_unlock_irq(&tags->lock); + spin_unlock_irqrestore(&tags->lock, flags); } /* From 9b340aeb26d50e9a9ec99599e2a39b035fac978e Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Fri, 16 Aug 2024 06:19:23 +1000 Subject: [PATCH 330/562] nouveau/firmware: use dma non-coherent allocator Currently, enabling SG_DEBUG in the kernel will cause nouveau to hit a BUG() on startup, when the iommu is enabled: kernel BUG at include/linux/scatterlist.h:187! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 7 PID: 930 Comm: (udev-worker) Not tainted 6.9.0-rc3Lyude-Test+ #30 Hardware name: MSI MS-7A39/A320M GAMING PRO (MS-7A39), BIOS 1.I0 01/22/2019 RIP: 0010:sg_init_one+0x85/0xa0 Code: 69 88 32 01 83 e1 03 f6 c3 03 75 20 a8 01 75 1e 48 09 cb 41 89 54 24 08 49 89 1c 24 41 89 6c 24 0c 5b 5d 41 5c e9 7b b9 88 00 <0f> 0b 0f 0b 0f 0b 48 8b 05 5e 46 9a 01 eb b2 66 66 2e 0f 1f 84 00 RSP: 0018:ffffa776017bf6a0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffffa77600d87000 RCX: 000000000000002b RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffffa77680d87000 RBP: 000000000000e000 R08: 0000000000000000 R09: 0000000000000000 R10: ffff98f4c46aa508 R11: 0000000000000000 R12: ffff98f4c46aa508 R13: ffff98f4c46aa008 R14: ffffa77600d4a000 R15: ffffa77600d4a018 FS: 00007feeb5aae980(0000) GS:ffff98f5c4dc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f22cb9a4520 CR3: 00000001043ba000 CR4: 00000000003506f0 Call Trace: ? die+0x36/0x90 ? do_trap+0xdd/0x100 ? sg_init_one+0x85/0xa0 ? do_error_trap+0x65/0x80 ? sg_init_one+0x85/0xa0 ? exc_invalid_op+0x50/0x70 ? sg_init_one+0x85/0xa0 ? asm_exc_invalid_op+0x1a/0x20 ? sg_init_one+0x85/0xa0 nvkm_firmware_ctor+0x14a/0x250 [nouveau] nvkm_falcon_fw_ctor+0x42/0x70 [nouveau] ga102_gsp_booter_ctor+0xb4/0x1a0 [nouveau] r535_gsp_oneinit+0xb3/0x15f0 [nouveau] ? srso_return_thunk+0x5/0x5f ? srso_return_thunk+0x5/0x5f ? nvkm_udevice_new+0x95/0x140 [nouveau] ? srso_return_thunk+0x5/0x5f ? srso_return_thunk+0x5/0x5f ? ktime_get+0x47/0xb0 Fix this by using the non-coherent allocator instead, I think there might be a better answer to this, but it involve ripping up some of APIs using sg lists. Cc: stable@vger.kernel.org Fixes: 2541626cfb79 ("drm/nouveau/acr: use common falcon HS FW code for ACR FWs") Signed-off-by: Dave Airlie Signed-off-by: Danilo Krummrich Link: https://patchwork.freedesktop.org/patch/msgid/20240815201923.632803-1-airlied@gmail.com --- drivers/gpu/drm/nouveau/nvkm/core/firmware.c | 9 ++++++--- drivers/gpu/drm/nouveau/nvkm/falcon/fw.c | 6 ++++++ 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c index adc60b25f8e6..0af01a0ec601 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c @@ -205,7 +205,8 @@ nvkm_firmware_dtor(struct nvkm_firmware *fw) break; case NVKM_FIRMWARE_IMG_DMA: nvkm_memory_unref(&memory); - dma_free_coherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), fw->img, fw->phys); + dma_free_noncoherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), + fw->img, fw->phys, DMA_TO_DEVICE); break; case NVKM_FIRMWARE_IMG_SGT: nvkm_memory_unref(&memory); @@ -236,10 +237,12 @@ nvkm_firmware_ctor(const struct nvkm_firmware_func *func, const char *name, break; case NVKM_FIRMWARE_IMG_DMA: { dma_addr_t addr; - len = ALIGN(fw->len, PAGE_SIZE); - fw->img = dma_alloc_coherent(fw->device->dev, len, &addr, GFP_KERNEL); + fw->img = dma_alloc_noncoherent(fw->device->dev, + len, &addr, + DMA_TO_DEVICE, + GFP_KERNEL); if (fw->img) { memcpy(fw->img, src, fw->len); fw->phys = addr; diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c index 80a480b12174..a1c8545f1249 100644 --- a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c @@ -89,6 +89,12 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user, nvkm_falcon_fw_dtor_sigs(fw); } + /* after last write to the img, sync dma mappings */ + dma_sync_single_for_device(fw->fw.device->dev, + fw->fw.phys, + sg_dma_len(&fw->fw.mem.sgl), + DMA_TO_DEVICE); + FLCNFW_DBG(fw, "resetting"); fw->func->reset(fw); From b96ed2c97c791954abc881ef384e773010945aec Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 14 Aug 2024 14:25:00 +0200 Subject: [PATCH 331/562] virtio_net: move netdev_tx_reset_queue() call before RX napi enable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit During suspend/resume the following BUG was hit: ------------[ cut here ]------------ kernel BUG at lib/dynamic_queue_limits.c:99! Internal error: Oops - BUG: 0 [#1] SMP ARM Modules linked in: bluetooth ecdh_generic ecc libaes CPU: 1 PID: 1282 Comm: rtcwake Not tainted 6.10.0-rc3-00732-gc8bd1f7f3e61 #15240 Hardware name: Generic DT based system PC is at dql_completed+0x270/0x2cc LR is at __free_old_xmit+0x120/0x198 pc : []    lr : []    psr: 80000013 ... Flags: Nzcv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none Control: 10c5387d  Table: 43a4406a  DAC: 00000051 ... Process rtcwake (pid: 1282, stack limit = 0xfbc21278) Stack: (0xe0805e80 to 0xe0806000) ... Call trace:  dql_completed from __free_old_xmit+0x120/0x198  __free_old_xmit from free_old_xmit+0x44/0xe4  free_old_xmit from virtnet_poll_tx+0x88/0x1b4  virtnet_poll_tx from __napi_poll+0x2c/0x1d4  __napi_poll from net_rx_action+0x140/0x2b4  net_rx_action from handle_softirqs+0x11c/0x350  handle_softirqs from call_with_stack+0x18/0x20  call_with_stack from do_softirq+0x48/0x50  do_softirq from __local_bh_enable_ip+0xa0/0xa4  __local_bh_enable_ip from virtnet_open+0xd4/0x21c  virtnet_open from virtnet_restore+0x94/0x120  virtnet_restore from virtio_device_restore+0x110/0x1f4  virtio_device_restore from dpm_run_callback+0x3c/0x100  dpm_run_callback from device_resume+0x12c/0x2a8  device_resume from dpm_resume+0x12c/0x1e0  dpm_resume from dpm_resume_end+0xc/0x18  dpm_resume_end from suspend_devices_and_enter+0x1f0/0x72c  suspend_devices_and_enter from pm_suspend+0x270/0x2a0  pm_suspend from state_store+0x68/0xc8  state_store from kernfs_fop_write_iter+0x10c/0x1cc  kernfs_fop_write_iter from vfs_write+0x2b0/0x3dc  vfs_write from ksys_write+0x5c/0xd4  ksys_write from ret_fast_syscall+0x0/0x54 Exception stack(0xe8bf1fa8 to 0xe8bf1ff0) ... ---[ end trace 0000000000000000 ]--- After virtnet_napi_enable() is called, the following path is hit: __napi_poll() -> virtnet_poll() -> virtnet_poll_cleantx() -> netif_tx_wake_queue() That wakes the TX queue and allows skbs to be submitted and accounted by BQL counters. Then netdev_tx_reset_queue() is called that resets BQL counters and eventually leads to the BUG in dql_completed(). Move virtnet_napi_tx_enable() what does BQL counters reset before RX napi enable to avoid the issue. Reported-by: Marek Szyprowski Closes: https://lore.kernel.org/netdev/e632e378-d019-4de7-8f13-07c572ab37a9@samsung.com/ Fixes: c8bd1f7f3e61 ("virtio_net: add support for Byte Queue Limits") Tested-by: Marek Szyprowski Signed-off-by: Jiri Pirko Acked-by: Michael S. Tsirkin Acked-by: Jason Wang Link: https://patch.msgid.link/20240814122500.1710279-1-jiri@resnulli.us Signed-off-by: Jakub Kicinski --- drivers/net/virtio_net.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 3f10c72743e9..c6af18948092 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2867,8 +2867,8 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) if (err < 0) goto err_xdp_reg_mem_model; - virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, qp_index)); + virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); return 0; From c948c0973df5db9314459da621342e1170bd9e8e Mon Sep 17 00:00:00 2001 From: Pavan Chebbi Date: Wed, 14 Aug 2024 15:54:29 -0700 Subject: [PATCH 332/562] bnxt_en: Don't clear ntuple filters and rss contexts during ethtool ops The driver currently blindly deletes its cache of RSS cotexts and ntuple filters when the ethtool channel count is changing. It also deletes the ntuple filters cache when the default indirection table is changing. The core will not allow ethtool channels to drop below any that have been configured as ntuple destinations since this commit from 2022: 47f3ecf4763d ("ethtool: Fail number of channels change when it conflicts with rxnfc") So there is absolutely no need to delete the ntuple filters and RSS contexts when changing ethtool channels. It is also unnecessary to delete ntuple filters when the default RSS indirection table is changing. Remove bnxt_clear_usr_fltrs() and bnxt_clear_rss_ctxis() from the ethtool ops and change them to static functions. This bug will cause confusion to the end user and causes failure when running the rss_ctx.py selftest. Fixes: 1018319f949c ("bnxt_en: Invalidate user filters when needed") Reported-by: Jakub Kicinski Closes: https://lore.kernel.org/netdev/20240725111912.7bc17cf6@kernel.org/ Reviewed-by: Andy Gospodarek Signed-off-by: Pavan Chebbi Signed-off-by: Michael Chan Link: https://patch.msgid.link/20240814225429.199280-1-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++-- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 2 -- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 4 ---- 3 files changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index e27e1082ee33..04a623b3eee2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -5056,7 +5056,7 @@ void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr) list_del_init(&fltr->list); } -void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all) +static void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all) { struct bnxt_filter_base *usr_fltr, *tmp; @@ -10248,7 +10248,7 @@ static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp) } } -void bnxt_clear_rss_ctxs(struct bnxt *bp) +static void bnxt_clear_rss_ctxs(struct bnxt *bp) { struct ethtool_rxfh_context *ctx; unsigned long context; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 6bbdc718c3a7..059a6f81c1a8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2790,7 +2790,6 @@ void bnxt_set_ring_params(struct bnxt *); int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode); void bnxt_insert_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr); void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr); -void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all); int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size, bool async_only); int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp); @@ -2842,7 +2841,6 @@ int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic); int __bnxt_setup_vnic_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic); void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx, bool all); -void bnxt_clear_rss_ctxs(struct bnxt *bp); int bnxt_open_nic(struct bnxt *, bool, bool); int bnxt_half_open_nic(struct bnxt *bp); void bnxt_half_close_nic(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 9dadc89378f0..4cf9bf8b01b0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -968,9 +968,6 @@ static int bnxt_set_channels(struct net_device *dev, return -EINVAL; } - bnxt_clear_usr_fltrs(bp, true); - if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp)) - bnxt_clear_rss_ctxs(bp); if (netif_running(dev)) { if (BNXT_PF(bp)) { /* TODO CHIMP_FW: Send message to all VF's @@ -2000,7 +1997,6 @@ static int bnxt_set_rxfh(struct net_device *dev, bnxt_modify_rss(bp, NULL, NULL, rxfh); - bnxt_clear_usr_fltrs(bp, false); if (netif_running(bp->dev)) { bnxt_close_nic(bp, false, false); rc = bnxt_open_nic(bp, false, false); From b153b3c747003e1ce312ba205e552db4bd9e8df7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 14 Aug 2024 07:28:32 -0700 Subject: [PATCH 333/562] MAINTAINERS: add selftests to network drivers tools/testing/selftests/drivers/net/ is not listed under networking entries. Add it to NETWORKING DRIVERS. Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240814142832.3473685-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index f328373463b0..a964a34651f5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15886,6 +15886,7 @@ F: include/linux/netdevice.h F: include/uapi/linux/cn_proc.h F: include/uapi/linux/if_* F: include/uapi/linux/netdevice.h +F: tools/testing/selftests/drivers/net/ X: drivers/net/wireless/ NETWORKING DRIVERS (WIRELESS) From e46bc2e7eb90a370bc27fa2fd98cb8251e7da1ec Mon Sep 17 00:00:00 2001 From: Pedro Falcato Date: Wed, 7 Aug 2024 18:33:35 +0100 Subject: [PATCH 334/562] mseal: fix is_madv_discard() is_madv_discard did its check wrong. MADV_ flags are not bitwise, they're normal sequential numbers. So, for instance: behavior & (/* ... */ | MADV_REMOVE) tagged both MADV_REMOVE and MADV_RANDOM (bit 0 set) as discard operations. As a result the kernel could erroneously block certain madvises (e.g MADV_RANDOM or MADV_HUGEPAGE) on sealed VMAs due to them sharing bits with blocked MADV operations (e.g REMOVE or WIPEONFORK). This is obviously incorrect, so use a switch statement instead. Link: https://lkml.kernel.org/r/20240807173336.2523757-1-pedro.falcato@gmail.com Link: https://lkml.kernel.org/r/20240807173336.2523757-2-pedro.falcato@gmail.com Fixes: 8be7258aad44 ("mseal: add mseal syscall") Signed-off-by: Pedro Falcato Tested-by: Jeff Xu Reviewed-by: Jeff Xu Cc: Kees Cook Cc: Liam R. Howlett Cc: Shuah Khan Cc: Signed-off-by: Andrew Morton --- mm/mseal.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/mm/mseal.c b/mm/mseal.c index bf783bba8ed0..15bba28acc00 100644 --- a/mm/mseal.c +++ b/mm/mseal.c @@ -40,9 +40,17 @@ static bool can_modify_vma(struct vm_area_struct *vma) static bool is_madv_discard(int behavior) { - return behavior & - (MADV_FREE | MADV_DONTNEED | MADV_DONTNEED_LOCKED | - MADV_REMOVE | MADV_DONTFORK | MADV_WIPEONFORK); + switch (behavior) { + case MADV_FREE: + case MADV_DONTNEED: + case MADV_DONTNEED_LOCKED: + case MADV_REMOVE: + case MADV_DONTFORK: + case MADV_WIPEONFORK: + return true; + } + + return false; } static bool is_ro_anon(struct vm_area_struct *vma) From 5f75cfbd6bb02295ddaed48adf667b6c828ce07b Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 1 Aug 2024 22:47:48 +0200 Subject: [PATCH 335/562] mm/hugetlb: fix hugetlb vs. core-mm PT locking We recently made GUP's common page table walking code to also walk hugetlb VMAs without most hugetlb special-casing, preparing for the future of having less hugetlb-specific page table walking code in the codebase. Turns out that we missed one page table locking detail: page table locking for hugetlb folios that are not mapped using a single PMD/PUD. Assume we have hugetlb folio that spans multiple PTEs (e.g., 64 KiB hugetlb folios on arm64 with 4 KiB base page size). GUP, as it walks the page tables, will perform a pte_offset_map_lock() to grab the PTE table lock. However, hugetlb that concurrently modifies these page tables would actually grab the mm->page_table_lock: with USE_SPLIT_PTE_PTLOCKS, the locks would differ. Something similar can happen right now with hugetlb folios that span multiple PMDs when USE_SPLIT_PMD_PTLOCKS. This issue can be reproduced [1], for example triggering: [ 3105.936100] ------------[ cut here ]------------ [ 3105.939323] WARNING: CPU: 31 PID: 2732 at mm/gup.c:142 try_grab_folio+0x11c/0x188 [ 3105.944634] Modules linked in: [...] [ 3105.974841] CPU: 31 PID: 2732 Comm: reproducer Not tainted 6.10.0-64.eln141.aarch64 #1 [ 3105.980406] Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-4.fc40 05/24/2024 [ 3105.986185] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 3105.991108] pc : try_grab_folio+0x11c/0x188 [ 3105.994013] lr : follow_page_pte+0xd8/0x430 [ 3105.996986] sp : ffff80008eafb8f0 [ 3105.999346] x29: ffff80008eafb900 x28: ffffffe8d481f380 x27: 00f80001207cff43 [ 3106.004414] x26: 0000000000000001 x25: 0000000000000000 x24: ffff80008eafba48 [ 3106.009520] x23: 0000ffff9372f000 x22: ffff7a54459e2000 x21: ffff7a546c1aa978 [ 3106.014529] x20: ffffffe8d481f3c0 x19: 0000000000610041 x18: 0000000000000001 [ 3106.019506] x17: 0000000000000001 x16: ffffffffffffffff x15: 0000000000000000 [ 3106.024494] x14: ffffb85477fdfe08 x13: 0000ffff9372ffff x12: 0000000000000000 [ 3106.029469] x11: 1fffef4a88a96be1 x10: ffff7a54454b5f0c x9 : ffffb854771b12f0 [ 3106.034324] x8 : 0008000000000000 x7 : ffff7a546c1aa980 x6 : 0008000000000080 [ 3106.038902] x5 : 00000000001207cf x4 : 0000ffff9372f000 x3 : ffffffe8d481f000 [ 3106.043420] x2 : 0000000000610041 x1 : 0000000000000001 x0 : 0000000000000000 [ 3106.047957] Call trace: [ 3106.049522] try_grab_folio+0x11c/0x188 [ 3106.051996] follow_pmd_mask.constprop.0.isra.0+0x150/0x2e0 [ 3106.055527] follow_page_mask+0x1a0/0x2b8 [ 3106.058118] __get_user_pages+0xf0/0x348 [ 3106.060647] faultin_page_range+0xb0/0x360 [ 3106.063651] do_madvise+0x340/0x598 Let's make huge_pte_lockptr() effectively use the same PT locks as any core-mm page table walker would. Add ptep_lockptr() to obtain the PTE page table lock using a pte pointer -- unfortunately we cannot convert pte_lockptr() because virt_to_page() doesn't work with kmap'ed page tables we can have with CONFIG_HIGHPTE. Handle CONFIG_PGTABLE_LEVELS correctly by checking in reverse order, such that when e.g., CONFIG_PGTABLE_LEVELS==2 with PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE will work as expected. Document why that works. There is one ugly case: powerpc 8xx, whereby we have an 8 MiB hugetlb folio being mapped using two PTE page tables. While hugetlb wants to take the PMD table lock, core-mm would grab the PTE table lock of one of both PTE page tables. In such corner cases, we have to make sure that both locks match, which is (fortunately!) currently guaranteed for 8xx as it does not support SMP and consequently doesn't use split PT locks. [1] https://lore.kernel.org/all/1bbfcc7f-f222-45a5-ac44-c5a1381c596d@redhat.com/ Link: https://lkml.kernel.org/r/20240801204748.99107-1-david@redhat.com Fixes: 9cb28da54643 ("mm/gup: handle hugetlb in the generic follow_page_mask code") Signed-off-by: David Hildenbrand Acked-by: Peter Xu Reviewed-by: Baolin Wang Tested-by: Baolin Wang Cc: Peter Xu Cc: Oscar Salvador Cc: Muchun Song Cc: Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 33 ++++++++++++++++++++++++++++++--- include/linux/mm.h | 11 +++++++++++ 2 files changed, 41 insertions(+), 3 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c9bf68c239a0..45bf05ad5c53 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -944,10 +944,37 @@ static inline bool htlb_allow_alloc_fallback(int reason) static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { - if (huge_page_size(h) == PMD_SIZE) + const unsigned long size = huge_page_size(h); + + VM_WARN_ON(size == PAGE_SIZE); + + /* + * hugetlb must use the exact same PT locks as core-mm page table + * walkers would. When modifying a PTE table, hugetlb must take the + * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD + * PT lock etc. + * + * The expectation is that any hugetlb folio smaller than a PMD is + * always mapped into a single PTE table and that any hugetlb folio + * smaller than a PUD (but at least as big as a PMD) is always mapped + * into a single PMD table. + * + * If that does not hold for an architecture, then that architecture + * must disable split PT locks such that all *_lockptr() functions + * will give us the same result: the per-MM PT lock. + * + * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where + * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr() + * and core-mm would use pmd_lockptr(). However, in such configurations + * split PMD locks are disabled -- they don't make sense on a single + * PGDIR page table -- and the end result is the same. + */ + if (size >= PUD_SIZE) + return pud_lockptr(mm, (pud_t *) pte); + else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE)) return pmd_lockptr(mm, (pmd_t *) pte); - VM_BUG_ON(huge_page_size(h) == PAGE_SIZE); - return &mm->page_table_lock; + /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */ + return ptep_lockptr(mm, pte); } #ifndef hugepages_supported diff --git a/include/linux/mm.h b/include/linux/mm.h index c4b238a20b76..6549d0979b28 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2920,6 +2920,13 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) return ptlock_ptr(page_ptdesc(pmd_page(*pmd))); } +static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) +{ + BUILD_BUG_ON(IS_ENABLED(CONFIG_HIGHPTE)); + BUILD_BUG_ON(MAX_PTRS_PER_PTE * sizeof(pte_t) > PAGE_SIZE); + return ptlock_ptr(virt_to_ptdesc(pte)); +} + static inline bool ptlock_init(struct ptdesc *ptdesc) { /* @@ -2944,6 +2951,10 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } +static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) +{ + return &mm->page_table_lock; +} static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} From ace0741a55e453c265cbf3d965eea7f687cd6d45 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Thu, 8 Aug 2024 21:34:34 +0000 Subject: [PATCH 336/562] mm: don't account memmap on failure Patch series "Fixes for memmap accounting", v4. Memmap accounting provides us with observability of how much memory is used for per-page metadata: i.e. "struct page"'s and "struct page_ext". It also provides with information of how much was allocated using boot allocator (i.e. not part of MemTotal), and how much was allocated using buddy allocated (i.e. part of MemTotal). This small series fixes a few problems that were discovered with the original patch. This patch (of 3): When we fail to allocate the mmemmap in alloc_vmemmap_page_list(), do not account any already-allocated pages: we're going to free all them before we return from the function. Link: https://lkml.kernel.org/r/20240809191020.1142142-1-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20240808213437.682006-1-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20240808213437.682006-2-pasha.tatashin@soleen.com Fixes: 15995a352474 ("mm: report per-page metadata information") Signed-off-by: Pasha Tatashin Reviewed-by: Fan Ni Reviewed-by: Yosry Ahmed Acked-by: David Hildenbrand Tested-by: Alison Schofield Reviewed-by: Muchun Song Acked-by: David Rientjes Cc: Dan Williams Cc: Domenico Cerasuolo Cc: Joel Granados Cc: Johannes Weiner Cc: Li Zhijian Cc: Matthew Wilcox (Oracle) Cc: Mike Rapoport Cc: Nhat Pham Cc: Sourav Panda Cc: Vlastimil Babka Cc: Yi Zhang Signed-off-by: Andrew Morton --- mm/hugetlb_vmemmap.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 829112b0a914..4f51e0596197 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -392,13 +392,10 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end, for (i = 0; i < nr_pages; i++) { page = alloc_pages_node(nid, gfp_mask, 0); - if (!page) { - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, i); + if (!page) goto out; - } list_add(&page->lru, list); } - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, nr_pages); return 0; From f4cb78af91e3b2b7aa76dbf8213b898fa8811b12 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Thu, 8 Aug 2024 21:34:35 +0000 Subject: [PATCH 337/562] mm: add system wide stats items category /proc/vmstat contains events and stats, events can only grow, but stats can grow and shrink. vmstat has the following: ------------------------- NR_VM_ZONE_STAT_ITEMS: per-zone stats NR_VM_NUMA_EVENT_ITEMS: per-numa events NR_VM_NODE_STAT_ITEMS: per-numa stats NR_VM_WRITEBACK_STAT_ITEMS: system-wide background-writeback and dirty-throttling tresholds. NR_VM_EVENT_ITEMS: system-wide events ------------------------- Rename NR_VM_WRITEBACK_STAT_ITEMS to NR_VM_STAT_ITEMS, to track the system-wide stats, we are going to add per-page metadata stats to this category in the next patch. Also delete unused writeback_stat_name(). Link: https://lkml.kernel.org/r/20240809191020.1142142-2-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20240808213437.682006-3-pasha.tatashin@soleen.com Fixes: 15995a352474 ("mm: report per-page metadata information") Signed-off-by: Pasha Tatashin Suggested-by: Yosry Ahmed Tested-by: Alison Schofield Acked-by: David Hildenbrand Acked-by: David Rientjes Cc: Dan Williams Cc: Domenico Cerasuolo Cc: Joel Granados Cc: Johannes Weiner Cc: Li Zhijian Cc: Matthew Wilcox (Oracle) Cc: Mike Rapoport Cc: Muchun Song Cc: Nhat Pham Cc: Sourav Panda Cc: Vlastimil Babka Cc: Yi Zhang Cc: Fan Ni Signed-off-by: Andrew Morton --- include/linux/vmstat.h | 15 ++++----------- mm/vmstat.c | 6 +++--- 2 files changed, 7 insertions(+), 14 deletions(-) diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 23cd17942036..9ab4fa5e09b5 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -34,10 +34,11 @@ struct reclaim_stat { unsigned nr_lazyfree_fail; }; -enum writeback_stat_item { +/* Stat data for system wide items */ +enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, - NR_VM_WRITEBACK_STAT_ITEMS, + NR_VM_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS @@ -514,21 +515,13 @@ static inline const char *lru_list_name(enum lru_list lru) return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" } -static inline const char *writeback_stat_name(enum writeback_stat_item item) -{ - return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_EVENT_ITEMS + - NR_VM_NODE_STAT_ITEMS + - item]; -} - #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + - NR_VM_WRITEBACK_STAT_ITEMS + + NR_VM_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ diff --git a/mm/vmstat.c b/mm/vmstat.c index 04a1cb6cc636..6f8aa4766f16 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1257,7 +1257,7 @@ const char * const vmstat_text[] = { "pgdemote_khugepaged", "nr_memmap", "nr_memmap_boot", - /* enum writeback_stat_item counters */ + /* system-wide enum vm_stat_item counters */ "nr_dirty_threshold", "nr_dirty_background_threshold", @@ -1790,7 +1790,7 @@ static const struct seq_operations zoneinfo_op = { #define NR_VMSTAT_ITEMS (NR_VM_ZONE_STAT_ITEMS + \ NR_VM_NUMA_EVENT_ITEMS + \ NR_VM_NODE_STAT_ITEMS + \ - NR_VM_WRITEBACK_STAT_ITEMS + \ + NR_VM_STAT_ITEMS + \ (IS_ENABLED(CONFIG_VM_EVENT_COUNTERS) ? \ NR_VM_EVENT_ITEMS : 0)) @@ -1827,7 +1827,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD, v + NR_DIRTY_THRESHOLD); - v += NR_VM_WRITEBACK_STAT_ITEMS; + v += NR_VM_STAT_ITEMS; #ifdef CONFIG_VM_EVENT_COUNTERS all_vm_events(v); From 9d85731110241fb8ca9445ea4177d816041a8825 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Thu, 8 Aug 2024 21:34:36 +0000 Subject: [PATCH 338/562] mm: don't account memmap per-node Fix invalid access to pgdat during hot-remove operation: ndctl users reported a GPF when trying to destroy a namespace: $ ndctl destroy-namespace all -r all -f Segmentation fault dmesg: Oops: general protection fault, probably for non-canonical address 0xdffffc0000005650: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: probably user-memory-access in range [0x000000000002b280-0x000000000002b287] CPU: 26 UID: 0 PID: 1868 Comm: ndctl Not tainted 6.11.0-rc1 #1 Hardware name: Dell Inc. PowerEdge R640/08HT8T, BIOS 2.20.1 09/13/2023 RIP: 0010:mod_node_page_state+0x2a/0x110 cxl-test users report a GPF when trying to unload the test module: $ modrpobe -r cxl-test dmesg BUG: unable to handle page fault for address: 0000000000004200 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] PREEMPT SMP PTI CPU: 0 UID: 0 PID: 1076 Comm: modprobe Tainted: G O N 6.11.0-rc1 #197 Tainted: [O]=OOT_MODULE, [N]=TEST Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/15 RIP: 0010:mod_node_page_state+0x6/0x90 Currently, when memory is hot-plugged or hot-removed the accounting is done based on the assumption that memmap is allocated from the same node as the hot-plugged/hot-removed memory, which is not always the case. In addition, there are challenges with keeping the node id of the memory that is being remove to the time when memmap accounting is actually performed: since this is done after remove_pfn_range_from_zone(), and also after remove_memory_block_devices(). Meaning that we cannot use pgdat nor walking though memblocks to get the nid. Given all of that, account the memmap overhead system wide instead. For this we are going to be using global atomic counters, but given that memmap size is rarely modified, and normally is only modified either during early boot when there is only one CPU, or under a hotplug global mutex lock, therefore there is no need for per-cpu optimizations. Also, while we are here rename nr_memmap to nr_memmap_pages, and nr_memmap_boot to nr_memmap_boot_pages to be self explanatory that the units are in page count. [pasha.tatashin@soleen.com: address a few nits from David Hildenbrand] Link: https://lkml.kernel.org/r/20240809191020.1142142-4-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20240809191020.1142142-4-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20240808213437.682006-4-pasha.tatashin@soleen.com Fixes: 15995a352474 ("mm: report per-page metadata information") Signed-off-by: Pasha Tatashin Reported-by: Yi Zhang Closes: https://lore.kernel.org/linux-cxl/CAHj4cs9Ax1=CoJkgBGP_+sNu6-6=6v=_L-ZBZY0bVLD3wUWZQg@mail.gmail.com Reported-by: Alison Schofield Closes: https://lore.kernel.org/linux-mm/Zq0tPd2h6alFz8XF@aschofie-mobl2/#t Tested-by: Dan Williams Tested-by: Alison Schofield Acked-by: David Hildenbrand Acked-by: David Rientjes Tested-by: Yi Zhang Cc: Domenico Cerasuolo Cc: Fan Ni Cc: Joel Granados Cc: Johannes Weiner Cc: Li Zhijian Cc: Matthew Wilcox (Oracle) Cc: Mike Rapoport Cc: Muchun Song Cc: Nhat Pham Cc: Sourav Panda Cc: Vlastimil Babka Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 2 -- include/linux/vmstat.h | 7 ++++--- mm/hugetlb_vmemmap.c | 8 ++++---- mm/mm_init.c | 3 +-- mm/page_alloc.c | 1 - mm/page_ext.c | 18 ++++------------- mm/sparse-vmemmap.c | 11 ++++------ mm/sparse.c | 5 ++--- mm/vmstat.c | 46 ++++++++++++++++++++---------------------- 9 files changed, 41 insertions(+), 60 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 41458892bc8a..1dc6248feb83 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -220,8 +220,6 @@ enum node_stat_item { PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, - NR_MEMMAP, /* page metadata allocated through buddy allocator */ - NR_MEMMAP_BOOT, /* page metadata allocated through boot allocator */ NR_VM_NODE_STAT_ITEMS }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 9ab4fa5e09b5..9eb77c9007e6 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -38,6 +38,8 @@ struct reclaim_stat { enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, + NR_MEMMAP_PAGES, /* page metadata allocated through buddy allocator */ + NR_MEMMAP_BOOT_PAGES, /* page metadata allocated through boot allocator */ NR_VM_STAT_ITEMS, }; @@ -618,7 +620,6 @@ static inline void lruvec_stat_sub_folio(struct folio *folio, lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } -void __meminit mod_node_early_perpage_metadata(int nid, long delta); -void __meminit store_early_perpage_metadata(void); - +void memmap_boot_pages_add(long delta); +void memmap_pages_add(long delta); #endif /* _LINUX_VMSTAT_H */ diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 4f51e0596197..0c3f56b3578e 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -185,11 +185,11 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end, static inline void free_vmemmap_page(struct page *page) { if (PageReserved(page)) { + memmap_boot_pages_add(-1); free_bootmem_page(page); - mod_node_page_state(page_pgdat(page), NR_MEMMAP_BOOT, -1); } else { + memmap_pages_add(-1); __free_page(page); - mod_node_page_state(page_pgdat(page), NR_MEMMAP, -1); } } @@ -341,7 +341,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end, copy_page(page_to_virt(walk.reuse_page), (void *)walk.reuse_addr); list_add(&walk.reuse_page->lru, vmemmap_pages); - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, 1); + memmap_pages_add(1); } /* @@ -396,7 +396,7 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end, goto out; list_add(&page->lru, list); } - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, nr_pages); + memmap_pages_add(nr_pages); return 0; out: diff --git a/mm/mm_init.c b/mm/mm_init.c index 75c3bd42799b..f9a60ffc5532 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1623,8 +1623,7 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat) panic("Failed to allocate %ld bytes for node %d memory map\n", size, pgdat->node_id); pgdat->node_mem_map = map + offset; - mod_node_early_perpage_metadata(pgdat->node_id, - DIV_ROUND_UP(size, PAGE_SIZE)); + memmap_boot_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", __func__, pgdat->node_id, (unsigned long)pgdat, (unsigned long)pgdat->node_mem_map); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 28f80daf5c04..875d76e8684a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5755,7 +5755,6 @@ void __init setup_per_cpu_pageset(void) for_each_online_pgdat(pgdat) pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat); - store_early_perpage_metadata(); } __meminit void zone_pcp_init(struct zone *zone) diff --git a/mm/page_ext.c b/mm/page_ext.c index c191e490c401..641d93f6af4c 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -214,8 +214,7 @@ static int __init alloc_node_page_ext(int nid) return -ENOMEM; NODE_DATA(nid)->node_page_ext = base; total_usage += table_size; - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP_BOOT, - DIV_ROUND_UP(table_size, PAGE_SIZE)); + memmap_boot_pages_add(DIV_ROUND_UP(table_size, PAGE_SIZE)); return 0; } @@ -275,10 +274,8 @@ static void *__meminit alloc_page_ext(size_t size, int nid) else addr = vzalloc_node(size, nid); - if (addr) { - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, - DIV_ROUND_UP(size, PAGE_SIZE)); - } + if (addr) + memmap_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); return addr; } @@ -323,25 +320,18 @@ static void free_page_ext(void *addr) { size_t table_size; struct page *page; - struct pglist_data *pgdat; table_size = page_ext_size * PAGES_PER_SECTION; + memmap_pages_add(-1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); if (is_vmalloc_addr(addr)) { - page = vmalloc_to_page(addr); - pgdat = page_pgdat(page); vfree(addr); } else { page = virt_to_page(addr); - pgdat = page_pgdat(page); BUG_ON(PageReserved(page)); kmemleak_free(addr); free_pages_exact(addr, table_size); } - - mod_node_page_state(pgdat, NR_MEMMAP, - -1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); - } static void __free_page_ext(unsigned long pfn) diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 1dda6c53370b..edcc7a6b0f6f 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -469,13 +469,10 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn, if (r < 0) return NULL; - if (system_state == SYSTEM_BOOTING) { - mod_node_early_perpage_metadata(nid, DIV_ROUND_UP(end - start, - PAGE_SIZE)); - } else { - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, - DIV_ROUND_UP(end - start, PAGE_SIZE)); - } + if (system_state == SYSTEM_BOOTING) + memmap_boot_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE)); + else + memmap_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE)); return pfn_to_page(pfn); } diff --git a/mm/sparse.c b/mm/sparse.c index e4b830091d13..0f018c6f9ec5 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -463,7 +463,7 @@ static void __init sparse_buffer_init(unsigned long size, int nid) sparsemap_buf = memmap_alloc(size, section_map_size(), addr, nid, true); sparsemap_buf_end = sparsemap_buf + size; #ifndef CONFIG_SPARSEMEM_VMEMMAP - mod_node_early_perpage_metadata(nid, DIV_ROUND_UP(size, PAGE_SIZE)); + memmap_boot_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); #endif } @@ -643,8 +643,7 @@ static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages, unsigned long start = (unsigned long) pfn_to_page(pfn); unsigned long end = start + nr_pages * sizeof(struct page); - mod_node_page_state(page_pgdat(pfn_to_page(pfn)), NR_MEMMAP, - -1L * (DIV_ROUND_UP(end - start, PAGE_SIZE))); + memmap_pages_add(-1L * (DIV_ROUND_UP(end - start, PAGE_SIZE))); vmemmap_free(start, end, altmap); } static void free_map_bootmem(struct page *memmap) diff --git a/mm/vmstat.c b/mm/vmstat.c index 6f8aa4766f16..e875f2a4915f 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1033,6 +1033,24 @@ unsigned long node_page_state(struct pglist_data *pgdat, } #endif +/* + * Count number of pages "struct page" and "struct page_ext" consume. + * nr_memmap_boot_pages: # of pages allocated by boot allocator + * nr_memmap_pages: # of pages that were allocated by buddy allocator + */ +static atomic_long_t nr_memmap_boot_pages = ATOMIC_LONG_INIT(0); +static atomic_long_t nr_memmap_pages = ATOMIC_LONG_INIT(0); + +void memmap_boot_pages_add(long delta) +{ + atomic_long_add(delta, &nr_memmap_boot_pages); +} + +void memmap_pages_add(long delta) +{ + atomic_long_add(delta, &nr_memmap_pages); +} + #ifdef CONFIG_COMPACTION struct contig_page_info { @@ -1255,11 +1273,11 @@ const char * const vmstat_text[] = { "pgdemote_kswapd", "pgdemote_direct", "pgdemote_khugepaged", - "nr_memmap", - "nr_memmap_boot", /* system-wide enum vm_stat_item counters */ "nr_dirty_threshold", "nr_dirty_background_threshold", + "nr_memmap_pages", + "nr_memmap_boot_pages", #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) /* enum vm_event_item counters */ @@ -1827,6 +1845,8 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD, v + NR_DIRTY_THRESHOLD); + v[NR_MEMMAP_PAGES] = atomic_long_read(&nr_memmap_pages); + v[NR_MEMMAP_BOOT_PAGES] = atomic_long_read(&nr_memmap_boot_pages); v += NR_VM_STAT_ITEMS; #ifdef CONFIG_VM_EVENT_COUNTERS @@ -2285,25 +2305,3 @@ static int __init extfrag_debug_init(void) module_init(extfrag_debug_init); #endif - -/* - * Page metadata size (struct page and page_ext) in pages - */ -static unsigned long early_perpage_metadata[MAX_NUMNODES] __meminitdata; - -void __meminit mod_node_early_perpage_metadata(int nid, long delta) -{ - early_perpage_metadata[nid] += delta; -} - -void __meminit store_early_perpage_metadata(void) -{ - int nid; - struct pglist_data *pgdat; - - for_each_online_pgdat(pgdat) { - nid = pgdat->node_id; - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP_BOOT, - early_perpage_metadata[nid]); - } -} From d75abd0d0bc29e6ebfebbf76d11b4067b35844af Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 6 Aug 2024 12:41:07 -0400 Subject: [PATCH 339/562] mm/memory-failure: use raw_spinlock_t in struct memory_failure_cpu The memory_failure_cpu structure is a per-cpu structure. Access to its content requires the use of get_cpu_var() to lock in the current CPU and disable preemption. The use of a regular spinlock_t for locking purpose is fine for a non-RT kernel. Since the integration of RT spinlock support into the v5.15 kernel, a spinlock_t in a RT kernel becomes a sleeping lock and taking a sleeping lock in a preemption disabled context is illegal resulting in the following kind of warning. [12135.732244] BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48 [12135.732248] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 270076, name: kworker/0:0 [12135.732252] preempt_count: 1, expected: 0 [12135.732255] RCU nest depth: 2, expected: 2 : [12135.732420] Hardware name: Dell Inc. PowerEdge R640/0HG0J8, BIOS 2.10.2 02/24/2021 [12135.732423] Workqueue: kacpi_notify acpi_os_execute_deferred [12135.732433] Call Trace: [12135.732436] [12135.732450] dump_stack_lvl+0x57/0x81 [12135.732461] __might_resched.cold+0xf4/0x12f [12135.732479] rt_spin_lock+0x4c/0x100 [12135.732491] memory_failure_queue+0x40/0xe0 [12135.732503] ghes_do_memory_failure+0x53/0x390 [12135.732516] ghes_do_proc.constprop.0+0x229/0x3e0 [12135.732575] ghes_proc+0xf9/0x1a0 [12135.732591] ghes_notify_hed+0x6a/0x150 [12135.732602] notifier_call_chain+0x43/0xb0 [12135.732626] blocking_notifier_call_chain+0x43/0x60 [12135.732637] acpi_ev_notify_dispatch+0x47/0x70 [12135.732648] acpi_os_execute_deferred+0x13/0x20 [12135.732654] process_one_work+0x41f/0x500 [12135.732695] worker_thread+0x192/0x360 [12135.732715] kthread+0x111/0x140 [12135.732733] ret_from_fork+0x29/0x50 [12135.732779] Fix it by using a raw_spinlock_t for locking instead. Also move the pr_err() out of the lock critical section and after put_cpu_ptr() to avoid indeterminate latency and the possibility of sleep with this call. [longman@redhat.com: don't hold percpu ref across pr_err(), per Miaohe] Link: https://lkml.kernel.org/r/20240807181130.1122660-1-longman@redhat.com Link: https://lkml.kernel.org/r/20240806164107.1044956-1-longman@redhat.com Fixes: 0f383b6dc96e ("locking/spinlock: Provide RT variant") Signed-off-by: Waiman Long Acked-by: Miaohe Lin Cc: "Huang, Ying" Cc: Juri Lelli Cc: Len Brown Cc: Naoya Horiguchi Cc: Signed-off-by: Andrew Morton --- mm/memory-failure.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 581d3e5c9117..7066fc84f351 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2417,7 +2417,7 @@ struct memory_failure_entry { struct memory_failure_cpu { DECLARE_KFIFO(fifo, struct memory_failure_entry, MEMORY_FAILURE_FIFO_SIZE); - spinlock_t lock; + raw_spinlock_t lock; struct work_struct work; }; @@ -2443,20 +2443,22 @@ void memory_failure_queue(unsigned long pfn, int flags) { struct memory_failure_cpu *mf_cpu; unsigned long proc_flags; + bool buffer_overflow; struct memory_failure_entry entry = { .pfn = pfn, .flags = flags, }; mf_cpu = &get_cpu_var(memory_failure_cpu); - spin_lock_irqsave(&mf_cpu->lock, proc_flags); - if (kfifo_put(&mf_cpu->fifo, entry)) + raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags); + buffer_overflow = !kfifo_put(&mf_cpu->fifo, entry); + if (!buffer_overflow) schedule_work_on(smp_processor_id(), &mf_cpu->work); - else + raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + put_cpu_var(memory_failure_cpu); + if (buffer_overflow) pr_err("buffer overflow when queuing memory failure at %#lx\n", pfn); - spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); - put_cpu_var(memory_failure_cpu); } EXPORT_SYMBOL_GPL(memory_failure_queue); @@ -2469,9 +2471,9 @@ static void memory_failure_work_func(struct work_struct *work) mf_cpu = container_of(work, struct memory_failure_cpu, work); for (;;) { - spin_lock_irqsave(&mf_cpu->lock, proc_flags); + raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags); gotten = kfifo_get(&mf_cpu->fifo, &entry); - spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); if (!gotten) break; if (entry.flags & MF_SOFT_OFFLINE) @@ -2501,7 +2503,7 @@ static int __init memory_failure_init(void) for_each_possible_cpu(cpu) { mf_cpu = &per_cpu(memory_failure_cpu, cpu); - spin_lock_init(&mf_cpu->lock); + raw_spin_lock_init(&mf_cpu->lock); INIT_KFIFO(mf_cpu->fifo); INIT_WORK(&mf_cpu->work, memory_failure_work_func); } From 61ebe5a747da649057c37be1c37eb934b4af79ca Mon Sep 17 00:00:00 2001 From: Hailong Liu Date: Thu, 8 Aug 2024 20:19:56 +0800 Subject: [PATCH 340/562] mm/vmalloc: fix page mapping if vm_area_alloc_pages() with high order fallback to order 0 The __vmap_pages_range_noflush() assumes its argument pages** contains pages with the same page shift. However, since commit e9c3cda4d86e ("mm, vmalloc: fix high order __GFP_NOFAIL allocations"), if gfp_flags includes __GFP_NOFAIL with high order in vm_area_alloc_pages() and page allocation failed for high order, the pages** may contain two different page shifts (high order and order-0). This could lead __vmap_pages_range_noflush() to perform incorrect mappings, potentially resulting in memory corruption. Users might encounter this as follows (vmap_allow_huge = true, 2M is for PMD_SIZE): kvmalloc(2M, __GFP_NOFAIL|GFP_X) __vmalloc_node_range_noprof(vm_flags=VM_ALLOW_HUGE_VMAP) vm_area_alloc_pages(order=9) ---> order-9 allocation failed and fallback to order-0 vmap_pages_range() vmap_pages_range_noflush() __vmap_pages_range_noflush(page_shift = 21) ----> wrong mapping happens We can remove the fallback code because if a high-order allocation fails, __vmalloc_node_range_noprof() will retry with order-0. Therefore, it is unnecessary to fallback to order-0 here. Therefore, fix this by removing the fallback code. Link: https://lkml.kernel.org/r/20240808122019.3361-1-hailong.liu@oppo.com Fixes: e9c3cda4d86e ("mm, vmalloc: fix high order __GFP_NOFAIL allocations") Signed-off-by: Hailong Liu Reported-by: Tangquan Zheng Reviewed-by: Baoquan He Reviewed-by: Uladzislau Rezki (Sony) Acked-by: Barry Song Acked-by: Michal Hocko Cc: Matthew Wilcox Cc: Signed-off-by: Andrew Morton --- mm/vmalloc.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 6b783baf12a1..af2de36549d6 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3584,15 +3584,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid, page = alloc_pages_noprof(alloc_gfp, order); else page = alloc_pages_node_noprof(nid, alloc_gfp, order); - if (unlikely(!page)) { - if (!nofail) - break; - - /* fall back to the zero order allocations */ - alloc_gfp |= __GFP_NOFAIL; - order = 0; - continue; - } + if (unlikely(!page)) + break; /* * Higher order allocations must be able to be treated as From 40b760cfd44566bca791c80e0720d70d75382b84 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Fri, 9 Aug 2024 10:59:04 -0400 Subject: [PATCH 341/562] mm/numa: no task_numa_fault() call if PTE is changed When handling a numa page fault, task_numa_fault() should be called by a process that restores the page table of the faulted folio to avoid duplicated stats counting. Commit b99a342d4f11 ("NUMA balancing: reduce TLB flush via delaying mapping on hint page fault") restructured do_numa_page() and did not avoid task_numa_fault() call in the second page table check after a numa migration failure. Fix it by making all !pte_same() return immediately. This issue can cause task_numa_fault() being called more than necessary and lead to unexpected numa balancing results (It is hard to tell whether the issue will cause positive or negative performance impact due to duplicated numa fault counting). Link: https://lkml.kernel.org/r/20240809145906.1513458-2-ziy@nvidia.com Fixes: b99a342d4f11 ("NUMA balancing: reduce TLB flush via delaying mapping on hint page fault") Signed-off-by: Zi Yan Reported-by: "Huang, Ying" Closes: https://lore.kernel.org/linux-mm/87zfqfw0yw.fsf@yhuang6-desk2.ccr.corp.intel.com/ Acked-by: David Hildenbrand Cc: Baolin Wang Cc: Kefeng Wang Cc: Mel Gorman Cc: Yang Shi Cc: Signed-off-by: Andrew Morton --- mm/memory.c | 33 ++++++++++++++++----------------- 1 file changed, 16 insertions(+), 17 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 34f8402d2046..3c01d68065be 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5295,7 +5295,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) if (unlikely(!pte_same(old_pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; + return 0; } pte = pte_modify(old_pte, vma->vm_page_prot); @@ -5358,23 +5358,19 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) if (!migrate_misplaced_folio(folio, vma, target_nid)) { nid = target_nid; flags |= TNF_MIGRATED; - } else { - flags |= TNF_MIGRATE_FAIL; - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); - if (unlikely(!vmf->pte)) - goto out; - if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { - pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; - } - goto out_map; + task_numa_fault(last_cpupid, nid, nr_pages, flags); + return 0; } -out: - if (nid != NUMA_NO_NODE) - task_numa_fault(last_cpupid, nid, nr_pages, flags); - return 0; + flags |= TNF_MIGRATE_FAIL; + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (unlikely(!vmf->pte)) + return 0; + if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; + } out_map: /* * Make it present again, depending on how arch implements @@ -5387,7 +5383,10 @@ out_map: numa_rebuild_single_mapping(vmf, vma, vmf->address, vmf->pte, writable); pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; + + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, nr_pages, flags); + return 0; } static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) From fd8c35a92910f4829b7c99841f39b1b952c259d5 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Fri, 9 Aug 2024 10:59:05 -0400 Subject: [PATCH 342/562] mm/numa: no task_numa_fault() call if PMD is changed When handling a numa page fault, task_numa_fault() should be called by a process that restores the page table of the faulted folio to avoid duplicated stats counting. Commit c5b5a3dd2c1f ("mm: thp: refactor NUMA fault handling") restructured do_huge_pmd_numa_page() and did not avoid task_numa_fault() call in the second page table check after a numa migration failure. Fix it by making all !pmd_same() return immediately. This issue can cause task_numa_fault() being called more than necessary and lead to unexpected numa balancing results (It is hard to tell whether the issue will cause positive or negative performance impact due to duplicated numa fault counting). Link: https://lkml.kernel.org/r/20240809145906.1513458-3-ziy@nvidia.com Fixes: c5b5a3dd2c1f ("mm: thp: refactor NUMA fault handling") Reported-by: "Huang, Ying" Closes: https://lore.kernel.org/linux-mm/87zfqfw0yw.fsf@yhuang6-desk2.ccr.corp.intel.com/ Signed-off-by: Zi Yan Acked-by: David Hildenbrand Cc: Baolin Wang Cc: "Huang, Ying" Cc: Kefeng Wang Cc: Mel Gorman Cc: Yang Shi Cc: Signed-off-by: Andrew Morton --- mm/huge_memory.c | 29 +++++++++++++---------------- 1 file changed, 13 insertions(+), 16 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f4be468e06a4..67c86a5d64a6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1685,7 +1685,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { spin_unlock(vmf->ptl); - goto out; + return 0; } pmd = pmd_modify(oldpmd, vma->vm_page_prot); @@ -1728,22 +1728,16 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) if (!migrate_misplaced_folio(folio, vma, target_nid)) { flags |= TNF_MIGRATED; nid = target_nid; - } else { - flags |= TNF_MIGRATE_FAIL; - vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); - if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { - spin_unlock(vmf->ptl); - goto out; - } - goto out_map; + task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; } -out: - if (nid != NUMA_NO_NODE) - task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); - - return 0; - + flags |= TNF_MIGRATE_FAIL; + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { + spin_unlock(vmf->ptl); + return 0; + } out_map: /* Restore the PMD */ pmd = pmd_modify(oldpmd, vma->vm_page_prot); @@ -1753,7 +1747,10 @@ out_map: set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); - goto out; + + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; } /* From af3b7d09a9934220a8136065a0e6985fe0b67a1b Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 9 Aug 2024 15:32:30 +0300 Subject: [PATCH 343/562] selftests/mm: compaction_test: fix off by one in check_compaction() The "initial_nr_hugepages" variable is unsigned long so it takes up to 20 characters to print, plus 1 more character for the NUL terminator. Unfortunately, this buffer is not quite large enough for the terminator to fit. Also use snprintf() for a belt and suspenders approach. Link: https://lkml.kernel.org/r/87470c06-b45a-4e83-92ff-aac2e7b9c6ba@stanley.mountain Fixes: fb9293b6b015 ("selftests/mm: compaction_test: fix bogus test success and reduce probability of OOM-killer invocation") Signed-off-by: Dan Carpenter Cc: Shuah Khan Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/compaction_test.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index e140558e6f53..2c3a0eb6b22d 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -89,9 +89,10 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, int fd, ret = -1; int compaction_index = 0; char nr_hugepages[20] = {0}; - char init_nr_hugepages[20] = {0}; + char init_nr_hugepages[24] = {0}; - sprintf(init_nr_hugepages, "%lu", initial_nr_hugepages); + snprintf(init_nr_hugepages, sizeof(init_nr_hugepages), + "%lu", initial_nr_hugepages); /* We want to test with 80% of available memory. Else, OOM killer comes in to play */ From 807174a93d24c456503692dc3f5af322ee0b640a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 9 Aug 2024 14:48:47 +0300 Subject: [PATCH 344/562] mm: fix endless reclaim on machines with unaccepted memory Unaccepted memory is considered unusable free memory, which is not counted as free on the zone watermark check. This causes get_page_from_freelist() to accept more memory to hit the high watermark, but it creates problems in the reclaim path. The reclaim path encounters a failed zone watermark check and attempts to reclaim memory. This is usually successful, but if there is little or no reclaimable memory, it can result in endless reclaim with little to no progress. This can occur early in the boot process, just after start of the init process when the only reclaimable memory is the page cache of the init executable and its libraries. Make unaccepted memory free from watermark check point of view. This way unaccepted memory will never be the trigger of memory reclaim. Accept more memory in the get_page_from_freelist() if needed. Link: https://lkml.kernel.org/r/20240809114854.3745464-2-kirill.shutemov@linux.intel.com Fixes: dcdfdd40fa82 ("mm: Add support for unaccepted memory") Signed-off-by: Kirill A. Shutemov Reported-by: Jianxiong Gao Acked-by: David Hildenbrand Tested-by: Jianxiong Gao Cc: Borislav Petkov Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Matthew Wilcox Cc: Mel Gorman Cc: Mike Rapoport (Microsoft) Cc: Tom Lendacky Cc: Vlastimil Babka Cc: [6.5+] Signed-off-by: Andrew Morton --- mm/page_alloc.c | 42 ++++++++++++++++++++---------------------- 1 file changed, 20 insertions(+), 22 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 875d76e8684a..8747087acee3 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -287,7 +287,7 @@ EXPORT_SYMBOL(nr_online_nodes); static bool page_contains_unaccepted(struct page *page, unsigned int order); static void accept_page(struct page *page, unsigned int order); -static bool try_to_accept_memory(struct zone *zone, unsigned int order); +static bool cond_accept_memory(struct zone *zone, unsigned int order); static inline bool has_unaccepted_memory(void); static bool __free_unaccepted(struct page *page); @@ -3072,9 +3072,6 @@ static inline long __zone_watermark_unusable_free(struct zone *z, if (!(alloc_flags & ALLOC_CMA)) unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES); #endif -#ifdef CONFIG_UNACCEPTED_MEMORY - unusable_free += zone_page_state(z, NR_UNACCEPTED); -#endif return unusable_free; } @@ -3368,6 +3365,8 @@ retry: } } + cond_accept_memory(zone, order); + /* * Detect whether the number of free pages is below high * watermark. If so, we will decrease pcp->high and free @@ -3393,10 +3392,8 @@ check_alloc_wmark: gfp_mask)) { int ret; - if (has_unaccepted_memory()) { - if (try_to_accept_memory(zone, order)) - goto try_this_zone; - } + if (cond_accept_memory(zone, order)) + goto try_this_zone; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* @@ -3450,10 +3447,8 @@ try_this_zone: return page; } else { - if (has_unaccepted_memory()) { - if (try_to_accept_memory(zone, order)) - goto try_this_zone; - } + if (cond_accept_memory(zone, order)) + goto try_this_zone; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* Try again if zone has deferred pages */ @@ -6950,9 +6945,6 @@ static bool try_to_accept_memory_one(struct zone *zone) struct page *page; bool last; - if (list_empty(&zone->unaccepted_pages)) - return false; - spin_lock_irqsave(&zone->lock, flags); page = list_first_entry_or_null(&zone->unaccepted_pages, struct page, lru); @@ -6978,23 +6970,29 @@ static bool try_to_accept_memory_one(struct zone *zone) return true; } -static bool try_to_accept_memory(struct zone *zone, unsigned int order) +static bool cond_accept_memory(struct zone *zone, unsigned int order) { long to_accept; - int ret = false; + bool ret = false; + + if (!has_unaccepted_memory()) + return false; + + if (list_empty(&zone->unaccepted_pages)) + return false; /* How much to accept to get to high watermark? */ to_accept = high_wmark_pages(zone) - (zone_page_state(zone, NR_FREE_PAGES) - - __zone_watermark_unusable_free(zone, order, 0)); + __zone_watermark_unusable_free(zone, order, 0) - + zone_page_state(zone, NR_UNACCEPTED)); - /* Accept at least one page */ - do { + while (to_accept > 0) { if (!try_to_accept_memory_one(zone)) break; ret = true; to_accept -= MAX_ORDER_NR_PAGES; - } while (to_accept > 0); + } return ret; } @@ -7037,7 +7035,7 @@ static void accept_page(struct page *page, unsigned int order) { } -static bool try_to_accept_memory(struct zone *zone, unsigned int order) +static bool cond_accept_memory(struct zone *zone, unsigned int order) { return false; } From 7c5e8d212d7d81991a580e7de3904ea213d9a852 Mon Sep 17 00:00:00 2001 From: Muhammad Usama Anjum Date: Fri, 9 Aug 2024 12:56:42 +0500 Subject: [PATCH 345/562] selftests: memfd_secret: don't build memfd_secret test on unsupported arches [1] mentions that memfd_secret is only supported on arm64, riscv, x86 and x86_64 for now. It doesn't support other architectures. I found the build error on arm and decided to send the fix as it was creating noise on KernelCI: memfd_secret.c: In function 'memfd_secret': memfd_secret.c:42:24: error: '__NR_memfd_secret' undeclared (first use in this function); did you mean 'memfd_secret'? 42 | return syscall(__NR_memfd_secret, flags); | ^~~~~~~~~~~~~~~~~ | memfd_secret Hence I'm adding condition that memfd_secret should only be compiled on supported architectures. Also check in run_vmtests script if memfd_secret binary is present before executing it. Link: https://lkml.kernel.org/r/20240812061522.1933054-1-usama.anjum@collabora.com Link: https://lore.kernel.org/all/20210518072034.31572-7-rppt@kernel.org/ [1] Link: https://lkml.kernel.org/r/20240809075642.403247-1-usama.anjum@collabora.com Fixes: 76fe17ef588a ("secretmem: test: add basic selftest for memfd_secret(2)") Signed-off-by: Muhammad Usama Anjum Reviewed-by: Shuah Khan Acked-by: Mike Rapoport (Microsoft) Cc: Albert Ou Cc: James Bottomley Cc: Mike Rapoport (Microsoft) Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/Makefile | 2 ++ tools/testing/selftests/mm/run_vmtests.sh | 3 +++ 2 files changed, 5 insertions(+) diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 7b8a5def54a1..cfad627e8d94 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -53,7 +53,9 @@ TEST_GEN_FILES += madv_populate TEST_GEN_FILES += map_fixed_noreplace TEST_GEN_FILES += map_hugetlb TEST_GEN_FILES += map_populate +ifneq (,$(filter $(ARCH),arm64 riscv riscv64 x86 x86_64)) TEST_GEN_FILES += memfd_secret +endif TEST_GEN_FILES += migration TEST_GEN_FILES += mkdirty TEST_GEN_FILES += mlock-random-test diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 03ac4f2e1cce..36045edb10de 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -374,8 +374,11 @@ CATEGORY="hmm" run_test bash ./test_hmm.sh smoke # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate +if [ -x ./memfd_secret ] +then (echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope 2>&1) | tap_prefix CATEGORY="memfd_secret" run_test ./memfd_secret +fi # KSM KSM_MERGE_TIME_HUGE_PAGES test with size of 100 CATEGORY="ksm" run_test ./ksm_tests -H -s 100 From edb907a6133323e19311901a39dee68b1c6a2ef8 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Mon, 12 Aug 2024 14:20:17 +0800 Subject: [PATCH 346/562] crash: fix riscv64 crash memory reserve dead loop On RISCV64 Qemu machine with 512MB memory, cmdline "crashkernel=500M,high" will cause system stall as below: Zone ranges: DMA32 [mem 0x0000000080000000-0x000000009fffffff] Normal empty Movable zone start for each node Early memory node ranges node 0: [mem 0x0000000080000000-0x000000008005ffff] node 0: [mem 0x0000000080060000-0x000000009fffffff] Initmem setup node 0 [mem 0x0000000080000000-0x000000009fffffff] (stall here) commit 5d99cadf1568 ("crash: fix x86_32 crash memory reserve dead loop bug") fix this on 32-bit architecture. However, the problem is not completely solved. If `CRASH_ADDR_LOW_MAX = CRASH_ADDR_HIGH_MAX` on 64-bit architecture, for example, when system memory is equal to CRASH_ADDR_LOW_MAX on RISCV64, the following infinite loop will also occur: -> reserve_crashkernel_generic() and high is true -> alloc at [CRASH_ADDR_LOW_MAX, CRASH_ADDR_HIGH_MAX] fail -> alloc at [0, CRASH_ADDR_LOW_MAX] fail and repeatedly (because CRASH_ADDR_LOW_MAX = CRASH_ADDR_HIGH_MAX). As Catalin suggested, do not remove the ",high" reservation fallback to ",low" logic which will change arm64's kdump behavior, but fix it by skipping the above situation similar to commit d2f32f23190b ("crash: fix x86_32 crash memory reserve dead loop"). After this patch, it print: cannot allocate crashkernel (size:0x1f400000) Link: https://lkml.kernel.org/r/20240812062017.2674441-1-ruanjinjie@huawei.com Signed-off-by: Jinjie Ruan Suggested-by: Catalin Marinas Reviewed-by: Catalin Marinas Acked-by: Baoquan He Cc: Albert Ou Cc: Dave Young Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Vivek Goyal Signed-off-by: Andrew Morton --- kernel/crash_reserve.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c index d3b4cd12bdd1..64d44a52c011 100644 --- a/kernel/crash_reserve.c +++ b/kernel/crash_reserve.c @@ -423,7 +423,8 @@ retry: if (high && search_end == CRASH_ADDR_HIGH_MAX) { search_end = CRASH_ADDR_LOW_MAX; search_base = 0; - goto retry; + if (search_end != CRASH_ADDR_HIGH_MAX) + goto retry; } pr_warn("cannot allocate crashkernel (size:0x%llx)\n", crash_size); From a8fc28dad6d574582cdf2f7e78c73c59c623df30 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Tue, 13 Aug 2024 08:07:56 -0700 Subject: [PATCH 347/562] alloc_tag: introduce clear_page_tag_ref() helper function In several cases we are freeing pages which were not allocated using common page allocators. For such cases, in order to keep allocation accounting correct, we should clear the page tag to indicate that the page being freed is expected to not have a valid allocation tag. Introduce clear_page_tag_ref() helper function to be used for this. Link: https://lkml.kernel.org/r/20240813150758.855881-1-surenb@google.com Fixes: d224eb0287fb ("codetag: debug: mark codetags for reserved pages as empty") Signed-off-by: Suren Baghdasaryan Suggested-by: David Hildenbrand Acked-by: David Hildenbrand Reviewed-by: Pasha Tatashin Cc: Kees Cook Cc: Kent Overstreet Cc: Sourav Panda Cc: Vlastimil Babka Cc: [6.10] Signed-off-by: Andrew Morton --- include/linux/pgalloc_tag.h | 13 +++++++++++++ mm/mm_init.c | 10 +--------- mm/page_alloc.c | 9 +-------- 3 files changed, 15 insertions(+), 17 deletions(-) diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index 18cd0c0c73d9..207f0c83c8e9 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -43,6 +43,18 @@ static inline void put_page_tag_ref(union codetag_ref *ref) page_ext_put(page_ext_from_codetag_ref(ref)); } +static inline void clear_page_tag_ref(struct page *page) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + set_codetag_empty(ref); + put_page_tag_ref(ref); + } + } +} + static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) { @@ -126,6 +138,7 @@ static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) static inline union codetag_ref *get_page_tag_ref(struct page *page) { return NULL; } static inline void put_page_tag_ref(union codetag_ref *ref) {} +static inline void clear_page_tag_ref(struct page *page) {} static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) {} static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} diff --git a/mm/mm_init.c b/mm/mm_init.c index f9a60ffc5532..adc3127573cd 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2459,15 +2459,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn, } /* pages were reserved and not allocated */ - if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); - - if (ref) { - set_codetag_empty(ref); - put_page_tag_ref(ref); - } - } - + clear_page_tag_ref(page); __free_pages_core(page, order, MEMINIT_EARLY); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8747087acee3..c565de8f48e9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5815,14 +5815,7 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char void free_reserved_page(struct page *page) { - if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); - - if (ref) { - set_codetag_empty(ref); - put_page_tag_ref(ref); - } - } + clear_page_tag_ref(page); ClearPageReserved(page); init_page_count(page); __free_page(page); From 766c163c2068b45330664fb67df67268e588a22d Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Tue, 13 Aug 2024 08:07:57 -0700 Subject: [PATCH 348/562] alloc_tag: mark pages reserved during CMA activation as not tagged During CMA activation, pages in CMA area are prepared and then freed without being allocated. This triggers warnings when memory allocation debug config (CONFIG_MEM_ALLOC_PROFILING_DEBUG) is enabled. Fix this by marking these pages not tagged before freeing them. Link: https://lkml.kernel.org/r/20240813150758.855881-2-surenb@google.com Fixes: d224eb0287fb ("codetag: debug: mark codetags for reserved pages as empty") Signed-off-by: Suren Baghdasaryan Acked-by: David Hildenbrand Cc: Kees Cook Cc: Kent Overstreet Cc: Pasha Tatashin Cc: Sourav Panda Cc: Vlastimil Babka Cc: [6.10] Signed-off-by: Andrew Morton --- mm/mm_init.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/mm_init.c b/mm/mm_init.c index adc3127573cd..51960079875b 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2244,6 +2244,8 @@ void __init init_cma_reserved_pageblock(struct page *page) set_pageblock_migratetype(page, MIGRATE_CMA); set_page_refcounted(page); + /* pages were reserved and not allocated */ + clear_page_tag_ref(page); __free_pages(page, pageblock_order); adjust_managed_page_count(page, pageblock_nr_pages); From 2e6506e1c4eed2676a8412231046f31e10e240da Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Mon, 29 Jul 2024 10:13:06 +0800 Subject: [PATCH 349/562] mm/migrate: fix deadlock in migrate_pages_batch() on large folios Currently, migrate_pages_batch() can lock multiple locked folios with an arbitrary order. Although folio_trylock() is used to avoid deadlock as commit 2ef7dbb26990 ("migrate_pages: try migrate in batch asynchronously firstly") mentioned, it seems try_split_folio() is still missing. It was found by compaction stress test when I explicitly enable EROFS compressed files to use large folios, which case I cannot reproduce with the same workload if large folio support is off (current mainline). Typically, filesystem reads (with locked file-backed folios) could use another bdev/meta inode to load some other I/Os (e.g. inode extent metadata or caching compressed data), so the locking order will be: file-backed folios (A) bdev/meta folios (B) The following calltrace shows the deadlock: Thread 1 takes (B) lock and tries to take folio (A) lock Thread 2 takes (A) lock and tries to take folio (B) lock [Thread 1] INFO: task stress:1824 blocked for more than 30 seconds. Tainted: G OE 6.10.0-rc7+ #6 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:stress state:D stack:0 pid:1824 tgid:1824 ppid:1822 flags:0x0000000c Call trace: __switch_to+0xec/0x138 __schedule+0x43c/0xcb0 schedule+0x54/0x198 io_schedule+0x44/0x70 folio_wait_bit_common+0x184/0x3f8 <-- folio mapping ffff00036d69cb18 index 996 (**) __folio_lock+0x24/0x38 migrate_pages_batch+0x77c/0xea0 // try_split_folio (mm/migrate.c:1486:2) // migrate_pages_batch (mm/migrate.c:1734:16) <--- LIST_HEAD(unmap_folios) has .. folio mapping 0xffff0000d184f1d8 index 1711; (*) folio mapping 0xffff0000d184f1d8 index 1712; .. migrate_pages+0xb28/0xe90 compact_zone+0xa08/0x10f0 compact_node+0x9c/0x180 sysctl_compaction_handler+0x8c/0x118 proc_sys_call_handler+0x1a8/0x280 proc_sys_write+0x1c/0x30 vfs_write+0x240/0x380 ksys_write+0x78/0x118 __arm64_sys_write+0x24/0x38 invoke_syscall+0x78/0x108 el0_svc_common.constprop.0+0x48/0xf0 do_el0_svc+0x24/0x38 el0_svc+0x3c/0x148 el0t_64_sync_handler+0x100/0x130 el0t_64_sync+0x190/0x198 [Thread 2] INFO: task stress:1825 blocked for more than 30 seconds. Tainted: G OE 6.10.0-rc7+ #6 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:stress state:D stack:0 pid:1825 tgid:1825 ppid:1822 flags:0x0000000c Call trace: __switch_to+0xec/0x138 __schedule+0x43c/0xcb0 schedule+0x54/0x198 io_schedule+0x44/0x70 folio_wait_bit_common+0x184/0x3f8 <-- folio = 0xfffffdffc6b503c0 (mapping == 0xffff0000d184f1d8 index == 1711) (*) __folio_lock+0x24/0x38 z_erofs_runqueue+0x384/0x9c0 [erofs] z_erofs_readahead+0x21c/0x350 [erofs] <-- folio mapping 0xffff00036d69cb18 range from [992, 1024] (**) read_pages+0x74/0x328 page_cache_ra_order+0x26c/0x348 ondemand_readahead+0x1c0/0x3a0 page_cache_sync_ra+0x9c/0xc0 filemap_get_pages+0xc4/0x708 filemap_read+0x104/0x3a8 generic_file_read_iter+0x4c/0x150 vfs_read+0x27c/0x330 ksys_pread64+0x84/0xd0 __arm64_sys_pread64+0x28/0x40 invoke_syscall+0x78/0x108 el0_svc_common.constprop.0+0x48/0xf0 do_el0_svc+0x24/0x38 el0_svc+0x3c/0x148 el0t_64_sync_handler+0x100/0x130 el0t_64_sync+0x190/0x198 Link: https://lkml.kernel.org/r/20240729021306.398286-1-hsiangkao@linux.alibaba.com Fixes: 5dfab109d519 ("migrate_pages: batch _unmap and _move") Signed-off-by: Gao Xiang Reviewed-by: "Huang, Ying" Acked-by: David Hildenbrand Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- mm/migrate.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/mm/migrate.c b/mm/migrate.c index e7296c0fb5d5..923ea80ba744 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1479,11 +1479,17 @@ out: return rc; } -static inline int try_split_folio(struct folio *folio, struct list_head *split_folios) +static inline int try_split_folio(struct folio *folio, struct list_head *split_folios, + enum migrate_mode mode) { int rc; - folio_lock(folio); + if (mode == MIGRATE_ASYNC) { + if (!folio_trylock(folio)) + return -EAGAIN; + } else { + folio_lock(folio); + } rc = split_folio_to_list(folio, split_folios); folio_unlock(folio); if (!rc) @@ -1677,7 +1683,7 @@ static int migrate_pages_batch(struct list_head *from, */ if (nr_pages > 2 && !list_empty(&folio->_deferred_list)) { - if (try_split_folio(folio, split_folios) == 0) { + if (!try_split_folio(folio, split_folios, mode)) { nr_failed++; stats->nr_thp_failed += is_thp; stats->nr_thp_split += is_thp; @@ -1699,7 +1705,7 @@ static int migrate_pages_batch(struct list_head *from, if (!thp_migration_supported() && is_thp) { nr_failed++; stats->nr_thp_failed++; - if (!try_split_folio(folio, split_folios)) { + if (!try_split_folio(folio, split_folios, mode)) { stats->nr_thp_split++; stats->nr_split++; continue; @@ -1731,7 +1737,7 @@ static int migrate_pages_batch(struct list_head *from, stats->nr_thp_failed += is_thp; /* Large folio NUMA faulting doesn't split to retry. */ if (is_large && !nosplit) { - int ret = try_split_folio(folio, split_folios); + int ret = try_split_folio(folio, split_folios, mode); if (!ret) { stats->nr_thp_split += is_thp; From ad899c301c880766cc709aad277991b3ab671b66 Mon Sep 17 00:00:00 2001 From: Eli Billauer Date: Fri, 16 Aug 2024 10:01:59 +0300 Subject: [PATCH 350/562] char: xillybus: Refine workqueue handling As the wakeup work item now runs on a separate workqueue, it needs to be flushed separately along with flushing the device's workqueue. Also, move the destroy_workqueue() call to the end of the exit method, so that deinitialization is done in the opposite order of initialization. Fixes: ccbde4b128ef ("char: xillybus: Don't destroy workqueue from work item running on it") Cc: stable Signed-off-by: Eli Billauer Link: https://lore.kernel.org/r/20240816070200.50695-1-eli.billauer@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/char/xillybus/xillyusb.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/char/xillybus/xillyusb.c b/drivers/char/xillybus/xillyusb.c index 33ca0f4af390..e12d359194f8 100644 --- a/drivers/char/xillybus/xillyusb.c +++ b/drivers/char/xillybus/xillyusb.c @@ -2093,9 +2093,11 @@ static int xillyusb_discovery(struct usb_interface *interface) * just after responding with the IDT, there is no reason for any * work item to be running now. To be sure that xdev->channels * is updated on anything that might run in parallel, flush the - * workqueue, which rarely does anything. + * device's workqueue and the wakeup work item. This rarely + * does anything. */ flush_workqueue(xdev->workq); + flush_work(&xdev->wakeup_workitem); xdev->num_channels = num_channels; @@ -2274,9 +2276,9 @@ static int __init xillyusb_init(void) static void __exit xillyusb_exit(void) { - destroy_workqueue(wakeup_wq); - usb_deregister(&xillyusb_driver); + + destroy_workqueue(wakeup_wq); } module_init(xillyusb_init); From 2374bf7558de915edc6ec8cb10ec3291dfab9594 Mon Sep 17 00:00:00 2001 From: Eli Billauer Date: Fri, 16 Aug 2024 10:02:00 +0300 Subject: [PATCH 351/562] char: xillybus: Check USB endpoints when probing device Ensure, as the driver probes the device, that all endpoints that the driver may attempt to access exist and are of the correct type. All XillyUSB devices must have a Bulk IN and Bulk OUT endpoint at address 1. This is verified in xillyusb_setup_base_eps(). On top of that, a XillyUSB device may have additional Bulk OUT endpoints. The information about these endpoints' addresses is deduced from a data structure (the IDT) that the driver fetches from the device while probing it. These endpoints are checked in setup_channels(). A XillyUSB device never has more than one IN endpoint, as all data towards the host is multiplexed in this single Bulk IN endpoint. This is why setup_channels() only checks OUT endpoints. Reported-by: syzbot+eac39cba052f2e750dbe@syzkaller.appspotmail.com Cc: stable Closes: https://lore.kernel.org/all/0000000000001d44a6061f7a54ee@google.com/T/ Fixes: a53d1202aef1 ("char: xillybus: Add driver for XillyUSB (Xillybus variant for USB)"). Signed-off-by: Eli Billauer Link: https://lore.kernel.org/r/20240816070200.50695-2-eli.billauer@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/char/xillybus/xillyusb.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/drivers/char/xillybus/xillyusb.c b/drivers/char/xillybus/xillyusb.c index e12d359194f8..45771b1a3716 100644 --- a/drivers/char/xillybus/xillyusb.c +++ b/drivers/char/xillybus/xillyusb.c @@ -1903,6 +1903,13 @@ static const struct file_operations xillyusb_fops = { static int xillyusb_setup_base_eps(struct xillyusb_dev *xdev) { + struct usb_device *udev = xdev->udev; + + /* Verify that device has the two fundamental bulk in/out endpoints */ + if (usb_pipe_type_check(udev, usb_sndbulkpipe(udev, MSG_EP_NUM)) || + usb_pipe_type_check(udev, usb_rcvbulkpipe(udev, IN_EP_NUM))) + return -ENODEV; + xdev->msg_ep = endpoint_alloc(xdev, MSG_EP_NUM | USB_DIR_OUT, bulk_out_work, 1, 2); if (!xdev->msg_ep) @@ -1932,14 +1939,15 @@ static int setup_channels(struct xillyusb_dev *xdev, __le16 *chandesc, int num_channels) { - struct xillyusb_channel *chan; + struct usb_device *udev = xdev->udev; + struct xillyusb_channel *chan, *new_channels; int i; chan = kcalloc(num_channels, sizeof(*chan), GFP_KERNEL); if (!chan) return -ENOMEM; - xdev->channels = chan; + new_channels = chan; for (i = 0; i < num_channels; i++, chan++) { unsigned int in_desc = le16_to_cpu(*chandesc++); @@ -1968,6 +1976,15 @@ static int setup_channels(struct xillyusb_dev *xdev, */ if ((out_desc & 0x80) && i < 14) { /* Entry is valid */ + if (usb_pipe_type_check(udev, + usb_sndbulkpipe(udev, i + 2))) { + dev_err(xdev->dev, + "Missing BULK OUT endpoint %d\n", + i + 2); + kfree(new_channels); + return -ENODEV; + } + chan->writable = 1; chan->out_synchronous = !!(out_desc & 0x40); chan->out_seekable = !!(out_desc & 0x20); @@ -1977,6 +1994,7 @@ static int setup_channels(struct xillyusb_dev *xdev, } } + xdev->channels = new_channels; return 0; } From 8d019b15ddd55d6dc5685b1f51902c4aa8e01939 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:06:54 +0300 Subject: [PATCH 352/562] selftests: net: local_termination: refactor macvlan creation/deletion This will be used in other subtests as well; make new macvlan_create() and macvlan_destroy() functions. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- .../net/forwarding/local_termination.sh | 30 +++++++++++-------- 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 4b364cdf3ef0..36f3d577d0be 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -247,19 +247,29 @@ bridge_destroy() ip link del br0 } +macvlan_create() +{ + local lower=$1 + + ip link add link $lower name macvlan0 type macvlan mode private + ip link set macvlan0 address $MACVLAN_ADDR + ip link set macvlan0 up +} + +macvlan_destroy() +{ + ip link del macvlan0 +} + standalone() { h1_create h2_create - - ip link add link $h2 name macvlan0 type macvlan mode private - ip link set macvlan0 address $MACVLAN_ADDR - ip link set macvlan0 up + macvlan_create $h2 run_test $h2 - ip link del macvlan0 - + macvlan_destroy h2_destroy h1_destroy } @@ -268,15 +278,11 @@ bridge() { h1_create bridge_create - - ip link add link br0 name macvlan0 type macvlan mode private - ip link set macvlan0 address $MACVLAN_ADDR - ip link set macvlan0 up + macvlan_create br0 run_test br0 - ip link del macvlan0 - + macvlan_destroy bridge_destroy h1_destroy } From 4261fa35185c0112acca0496d3732c8fcfe1dcf2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:06:55 +0300 Subject: [PATCH 353/562] selftests: net: local_termination: parameterize sending interface In future changes we will want to subject the DUT, $h2, to additional VLAN-tagged traffic. For that, we need to run the tests using $h1.100 as a sending interface, rather than the currently hardcoded $h1. Add a parameter to run_test() and modify its 2 callers to explicitly pass $h1, as was implicit before. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- .../net/forwarding/local_termination.sh | 39 ++++++++++--------- 1 file changed, 20 insertions(+), 19 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 36f3d577d0be..92f0e242d119 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -104,44 +104,45 @@ mc_route_destroy() run_test() { - local rcv_if_name=$1 - local smac=$(mac_get $h1) + local send_if_name=$1; shift + local rcv_if_name=$1; shift + local smac=$(mac_get $send_if_name) local rcv_dmac=$(mac_get $rcv_if_name) tcpdump_start $rcv_if_name - mc_route_prepare $h1 + mc_route_prepare $send_if_name mc_route_prepare $rcv_if_name - send_uc_ipv4 $h1 $rcv_dmac - send_uc_ipv4 $h1 $MACVLAN_ADDR - send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR1 + send_uc_ipv4 $send_if_name $rcv_dmac + send_uc_ipv4 $send_if_name $MACVLAN_ADDR + send_uc_ipv4 $send_if_name $UNKNOWN_UC_ADDR1 ip link set dev $rcv_if_name promisc on - send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR2 - mc_send $h1 $UNKNOWN_IPV4_MC_ADDR2 - mc_send $h1 $UNKNOWN_IPV6_MC_ADDR2 + send_uc_ipv4 $send_if_name $UNKNOWN_UC_ADDR2 + mc_send $send_if_name $UNKNOWN_IPV4_MC_ADDR2 + mc_send $send_if_name $UNKNOWN_IPV6_MC_ADDR2 ip link set dev $rcv_if_name promisc off mc_join $rcv_if_name $JOINED_IPV4_MC_ADDR - mc_send $h1 $JOINED_IPV4_MC_ADDR + mc_send $send_if_name $JOINED_IPV4_MC_ADDR mc_leave mc_join $rcv_if_name $JOINED_IPV6_MC_ADDR - mc_send $h1 $JOINED_IPV6_MC_ADDR + mc_send $send_if_name $JOINED_IPV6_MC_ADDR mc_leave - mc_send $h1 $UNKNOWN_IPV4_MC_ADDR1 - mc_send $h1 $UNKNOWN_IPV6_MC_ADDR1 + mc_send $send_if_name $UNKNOWN_IPV4_MC_ADDR1 + mc_send $send_if_name $UNKNOWN_IPV6_MC_ADDR1 ip link set dev $rcv_if_name allmulticast on - send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR3 - mc_send $h1 $UNKNOWN_IPV4_MC_ADDR3 - mc_send $h1 $UNKNOWN_IPV6_MC_ADDR3 + send_uc_ipv4 $send_if_name $UNKNOWN_UC_ADDR3 + mc_send $send_if_name $UNKNOWN_IPV4_MC_ADDR3 + mc_send $send_if_name $UNKNOWN_IPV6_MC_ADDR3 ip link set dev $rcv_if_name allmulticast off mc_route_destroy $rcv_if_name - mc_route_destroy $h1 + mc_route_destroy $send_if_name sleep 1 @@ -267,7 +268,7 @@ standalone() h2_create macvlan_create $h2 - run_test $h2 + run_test $h1 $h2 macvlan_destroy h2_destroy @@ -280,7 +281,7 @@ bridge() bridge_create macvlan_create br0 - run_test br0 + run_test $h1 br0 macvlan_destroy bridge_destroy From df7cf5cc551c7c0a92520e91e1184993784c6386 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:06:56 +0300 Subject: [PATCH 354/562] selftests: net: local_termination: parameterize test name There are upcoming tests which verify the RX filtering of a bridge (or bridge port), but under differing vlan_filtering conditions. Since we currently print $h2 (the DUT) in the log_test() output, it becomes necessary to make a further distinction between tests, to not give the user the impression that the exact same thing is run twice. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- .../net/forwarding/local_termination.sh | 38 ++++++++++--------- 1 file changed, 20 insertions(+), 18 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 92f0e242d119..af284edaf401 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -68,10 +68,11 @@ send_uc_ipv4() check_rcv() { - local if_name=$1 - local type=$2 - local pattern=$3 - local should_receive=$4 + local if_name=$1; shift + local type=$1; shift + local pattern=$1; shift + local should_receive=$1; shift + local test_name="$1"; shift local should_fail= [ $should_receive = true ] && should_fail=0 || should_fail=1 @@ -81,7 +82,7 @@ check_rcv() check_err_fail "$should_fail" "$?" "reception" - log_test "$if_name: $type" + log_test "$test_name: $type" } mc_route_prepare() @@ -106,6 +107,7 @@ run_test() { local send_if_name=$1; shift local rcv_if_name=$1; shift + local test_name="$1"; shift local smac=$(mac_get $send_if_name) local rcv_dmac=$(mac_get $rcv_if_name) @@ -150,61 +152,61 @@ run_test() check_rcv $rcv_if_name "Unicast IPv4 to primary MAC address" \ "$smac > $rcv_dmac, ethertype IPv4 (0x0800)" \ - true + true "$test_name" check_rcv $rcv_if_name "Unicast IPv4 to macvlan MAC address" \ "$smac > $MACVLAN_ADDR, ethertype IPv4 (0x0800)" \ - true + true "$test_name" xfail_on_veth $h1 \ check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address" \ "$smac > $UNKNOWN_UC_ADDR1, ethertype IPv4 (0x0800)" \ - false + false "$test_name" check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address, promisc" \ "$smac > $UNKNOWN_UC_ADDR2, ethertype IPv4 (0x0800)" \ - true + true "$test_name" xfail_on_veth $h1 \ check_rcv $rcv_if_name \ "Unicast IPv4 to unknown MAC address, allmulti" \ "$smac > $UNKNOWN_UC_ADDR3, ethertype IPv4 (0x0800)" \ - false + false "$test_name" check_rcv $rcv_if_name "Multicast IPv4 to joined group" \ "$smac > $JOINED_MACV4_MC_ADDR, ethertype IPv4 (0x0800)" \ - true + true "$test_name" xfail_on_veth $h1 \ check_rcv $rcv_if_name \ "Multicast IPv4 to unknown group" \ "$smac > $UNKNOWN_MACV4_MC_ADDR1, ethertype IPv4 (0x0800)" \ - false + false "$test_name" check_rcv $rcv_if_name "Multicast IPv4 to unknown group, promisc" \ "$smac > $UNKNOWN_MACV4_MC_ADDR2, ethertype IPv4 (0x0800)" \ - true + true "$test_name" check_rcv $rcv_if_name "Multicast IPv4 to unknown group, allmulti" \ "$smac > $UNKNOWN_MACV4_MC_ADDR3, ethertype IPv4 (0x0800)" \ - true + true "$test_name" check_rcv $rcv_if_name "Multicast IPv6 to joined group" \ "$smac > $JOINED_MACV6_MC_ADDR, ethertype IPv6 (0x86dd)" \ - true + true "$test_name" xfail_on_veth $h1 \ check_rcv $rcv_if_name "Multicast IPv6 to unknown group" \ "$smac > $UNKNOWN_MACV6_MC_ADDR1, ethertype IPv6 (0x86dd)" \ - false + false "$test_name" check_rcv $rcv_if_name "Multicast IPv6 to unknown group, promisc" \ "$smac > $UNKNOWN_MACV6_MC_ADDR2, ethertype IPv6 (0x86dd)" \ - true + true "$test_name" check_rcv $rcv_if_name "Multicast IPv6 to unknown group, allmulti" \ "$smac > $UNKNOWN_MACV6_MC_ADDR3, ethertype IPv6 (0x86dd)" \ - true + true "$test_name" tcpdump_cleanup $rcv_if_name } From 5b8e74182ed3d4f1c38c626e6120275ca9d92bee Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:06:57 +0300 Subject: [PATCH 355/562] selftests: net: local_termination: add one more test for VLAN-aware bridges The current bridge() test is for packet reception on a VLAN-unaware bridge. Some things are different enough with VLAN-aware bridges that it's worth renaming this test into vlan_unaware_bridge(), and add a new vlan_aware_bridge() test. The two will share the same implementation: bridge() becomes a common function, which receives $vlan_filtering as an argument. Rename it to test_bridge() at the same time, because just bridge() pollutes the global namespace and we cannot invoke the binary with the same name from the iproute2 package currently. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- .../net/forwarding/local_termination.sh | 22 +++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index af284edaf401..5aa364b40e33 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -1,7 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="standalone bridge" +ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge" NUM_NETIFS=2 PING_COUNT=1 REQUIRE_MTOOLS=yes @@ -233,7 +233,9 @@ h2_destroy() bridge_create() { - ip link add br0 type bridge + local vlan_filtering=$1 + + ip link add br0 type bridge vlan_filtering $vlan_filtering ip link set br0 address $BRIDGE_ADDR ip link set br0 up @@ -277,10 +279,12 @@ standalone() h1_destroy } -bridge() +test_bridge() { + local vlan_filtering=$1 + h1_create - bridge_create + bridge_create $vlan_filtering macvlan_create br0 run_test $h1 br0 @@ -290,6 +294,16 @@ bridge() h1_destroy } +vlan_unaware_bridge() +{ + test_bridge 0 +} + +vlan_aware_bridge() +{ + test_bridge 1 +} + cleanup() { pre_cleanup From 5fea8bb009744bbb90b3f6ca41c558429ee4c849 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:06:58 +0300 Subject: [PATCH 356/562] selftests: net: local_termination: introduce new tests which capture VLAN behavior Add more coverage to the local termination selftest as follows: - 8021q upper of $h2 - 8021q upper of $h2, where $h2 is a port of a VLAN-unaware bridge - 8021q upper of $h2, where $h2 is a port of a VLAN-aware bridge - 8021q upper of VLAN-unaware br0, which is the upper of $h2 - 8021q upper of VLAN-aware br0, which is the upper of $h2 Especially the cases with traffic sent through the VLAN upper of a VLAN-aware bridge port will be immediately relevant when we will start transmitting PTP packets as an additional kind of traffic. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- .../net/forwarding/local_termination.sh | 117 ++++++++++++++++-- 1 file changed, 110 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 5aa364b40e33..e22c6a693bef 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -1,7 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge" +ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge test_vlan \ + vlan_over_vlan_unaware_bridged_port vlan_over_vlan_aware_bridged_port \ + vlan_over_vlan_unaware_bridge vlan_over_vlan_aware_bridge" NUM_NETIFS=2 PING_COUNT=1 REQUIRE_MTOOLS=yes @@ -231,6 +233,30 @@ h2_destroy() simple_if_fini $h2 $H2_IPV4/24 $H2_IPV6/64 } +h1_vlan_create() +{ + simple_if_init $h1 + vlan_create $h1 100 v$h1 $H1_IPV4/24 $H1_IPV6/64 +} + +h1_vlan_destroy() +{ + vlan_destroy $h1 100 + simple_if_fini $h1 +} + +h2_vlan_create() +{ + simple_if_init $h2 + vlan_create $h2 100 v$h2 $H2_IPV4/24 $H2_IPV6/64 +} + +h2_vlan_destroy() +{ + vlan_destroy $h2 100 + simple_if_fini $h2 +} + bridge_create() { local vlan_filtering=$1 @@ -241,14 +267,10 @@ bridge_create() ip link set $h2 master br0 ip link set $h2 up - - simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64 } bridge_destroy() { - simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64 - ip link del br0 } @@ -272,7 +294,7 @@ standalone() h2_create macvlan_create $h2 - run_test $h1 $h2 + run_test $h1 $h2 "$h2" macvlan_destroy h2_destroy @@ -285,11 +307,13 @@ test_bridge() h1_create bridge_create $vlan_filtering + simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64 macvlan_create br0 - run_test $h1 br0 + run_test $h1 br0 "vlan_filtering=$vlan_filtering bridge" macvlan_destroy + simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64 bridge_destroy h1_destroy } @@ -304,6 +328,85 @@ vlan_aware_bridge() test_bridge 1 } +test_vlan() +{ + h1_vlan_create + h2_vlan_create + macvlan_create $h2.100 + + run_test $h1.100 $h2.100 "VLAN upper" + + macvlan_destroy + h2_vlan_destroy + h1_vlan_destroy +} + +vlan_over_bridged_port() +{ + local vlan_filtering=$1 + + h1_vlan_create + h2_vlan_create + bridge_create $vlan_filtering + macvlan_create $h2.100 + + run_test $h1.100 $h2.100 "VLAN over vlan_filtering=$vlan_filtering bridged port" + + macvlan_destroy + bridge_destroy + h2_vlan_destroy + h1_vlan_destroy +} + +vlan_over_vlan_unaware_bridged_port() +{ + vlan_over_bridged_port 0 +} + +vlan_over_vlan_aware_bridged_port() +{ + vlan_over_bridged_port 1 +} + +vlan_over_bridge() +{ + local vlan_filtering=$1 + + h1_vlan_create + bridge_create $vlan_filtering + simple_if_init br0 + vlan_create br0 100 vbr0 $H2_IPV4/24 $H2_IPV6/64 + macvlan_create br0.100 + + if [ $vlan_filtering = 1 ]; then + bridge vlan add dev $h2 vid 100 master + bridge vlan add dev br0 vid 100 self + fi + + run_test $h1.100 br0.100 "VLAN over vlan_filtering=$vlan_filtering bridge" + + if [ $vlan_filtering = 1 ]; then + bridge vlan del dev br0 vid 100 self + bridge vlan del dev $h2 vid 100 master + fi + + macvlan_destroy + vlan_destroy br0 100 + simple_if_fini br0 + bridge_destroy + h1_vlan_destroy +} + +vlan_over_vlan_unaware_bridge() +{ + vlan_over_bridge 0 +} + +vlan_over_vlan_aware_bridge() +{ + vlan_over_bridge 1 +} + cleanup() { pre_cleanup From 9aa3749ca4a880c1a59720aab3eacf344ed8d68d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:06:59 +0300 Subject: [PATCH 357/562] selftests: net: local_termination: don't use xfail_on_veth() xfail_on_veth() for this test is an incorrect approximation which gives false positives and false negatives. When local_termination fails with "reception succeeded, but should have failed", it is because the DUT ($h2) accepts packets even when not configured as promiscuous. This is not something specific to veth; even the bridge behaves that way, but this is not captured by the xfail_on_veth test. The IFF_UNICAST_FLT flag is not explicitly exported to user space, but it can somewhat be determined from the interface's behavior. We have to create a macvlan upper with a different MAC address. This forces a dev_uc_add() call in the kernel. When the unicast filtering list is not empty, but the device doesn't support IFF_UNICAST_FLT, __dev_set_rx_mode() force-enables promiscuity on the interface, to ensure correct behavior (that the requested address is received). We can monitor the change in the promiscuity flag and infer from it whether the device supports unicast filtering. There is no equivalent thing for allmulti, unfortunately. We never know what's hiding behind a device which has allmulti=off. Whether it will actually perform RX multicast filtering of unknown traffic is a strong "maybe". The bridge driver, for example, completely ignores the flag. We'll have to keep the xfail behavior, but instead of XFAIL on just veth, always XFAIL. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- tools/testing/selftests/net/forwarding/lib.sh | 57 ++++++++++++++++++ .../net/forwarding/local_termination.sh | 58 ++++++++++++++----- 2 files changed, 99 insertions(+), 16 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index ff96bb7535ff..718d04a4f72d 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -500,6 +500,11 @@ check_err_fail() fi } +xfail() +{ + FAIL_TO_XFAIL=yes "$@" +} + xfail_on_slow() { if [[ $KSFT_MACHINE_SLOW = yes ]]; then @@ -1113,6 +1118,39 @@ mac_get() ip -j link show dev $if_name | jq -r '.[]["address"]' } +ether_addr_to_u64() +{ + local addr="$1" + local order="$((1 << 40))" + local val=0 + local byte + + addr="${addr//:/ }" + + for byte in $addr; do + byte="0x$byte" + val=$((val + order * byte)) + order=$((order >> 8)) + done + + printf "0x%x" $val +} + +u64_to_ether_addr() +{ + local val=$1 + local byte + local i + + for ((i = 40; i >= 0; i -= 8)); do + byte=$(((val & (0xff << i)) >> i)) + printf "%02x" $byte + if [ $i -ne 0 ]; then + printf ":" + fi + done +} + ipv6_lladdr_get() { local if_name=$1 @@ -2229,3 +2267,22 @@ absval() echo $((v > 0 ? v : -v)) } + +has_unicast_flt() +{ + local dev=$1; shift + local mac_addr=$(mac_get $dev) + local tmp=$(ether_addr_to_u64 $mac_addr) + local promisc + + ip link set $dev up + ip link add link $dev name macvlan-tmp type macvlan mode private + ip link set macvlan-tmp address $(u64_to_ether_addr $((tmp + 1))) + ip link set macvlan-tmp up + + promisc=$(ip -j -d link show dev $dev | jq -r '.[].promiscuity') + + ip link del macvlan-tmp + + [[ $promisc == 1 ]] && echo "no" || echo "yes" +} diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index e22c6a693bef..80ea4c10d764 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -109,9 +109,11 @@ run_test() { local send_if_name=$1; shift local rcv_if_name=$1; shift + local no_unicast_flt=$1; shift local test_name="$1"; shift local smac=$(mac_get $send_if_name) local rcv_dmac=$(mac_get $rcv_if_name) + local should_receive tcpdump_start $rcv_if_name @@ -160,26 +162,26 @@ run_test() "$smac > $MACVLAN_ADDR, ethertype IPv4 (0x0800)" \ true "$test_name" - xfail_on_veth $h1 \ - check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address" \ - "$smac > $UNKNOWN_UC_ADDR1, ethertype IPv4 (0x0800)" \ - false "$test_name" + [ $no_unicast_flt = true ] && should_receive=true || should_receive=false + check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address" \ + "$smac > $UNKNOWN_UC_ADDR1, ethertype IPv4 (0x0800)" \ + $should_receive "$test_name" check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address, promisc" \ "$smac > $UNKNOWN_UC_ADDR2, ethertype IPv4 (0x0800)" \ true "$test_name" - xfail_on_veth $h1 \ - check_rcv $rcv_if_name \ - "Unicast IPv4 to unknown MAC address, allmulti" \ - "$smac > $UNKNOWN_UC_ADDR3, ethertype IPv4 (0x0800)" \ - false "$test_name" + [ $no_unicast_flt = true ] && should_receive=true || should_receive=false + check_rcv $rcv_if_name \ + "Unicast IPv4 to unknown MAC address, allmulti" \ + "$smac > $UNKNOWN_UC_ADDR3, ethertype IPv4 (0x0800)" \ + $should_receive "$test_name" check_rcv $rcv_if_name "Multicast IPv4 to joined group" \ "$smac > $JOINED_MACV4_MC_ADDR, ethertype IPv4 (0x0800)" \ true "$test_name" - xfail_on_veth $h1 \ + xfail \ check_rcv $rcv_if_name \ "Multicast IPv4 to unknown group" \ "$smac > $UNKNOWN_MACV4_MC_ADDR1, ethertype IPv4 (0x0800)" \ @@ -197,7 +199,7 @@ run_test() "$smac > $JOINED_MACV6_MC_ADDR, ethertype IPv6 (0x86dd)" \ true "$test_name" - xfail_on_veth $h1 \ + xfail \ check_rcv $rcv_if_name "Multicast IPv6 to unknown group" \ "$smac > $UNKNOWN_MACV6_MC_ADDR1, ethertype IPv6 (0x86dd)" \ false "$test_name" @@ -290,11 +292,17 @@ macvlan_destroy() standalone() { + local no_unicast_flt=true + + if [ $(has_unicast_flt $h2) = yes ]; then + no_unicast_flt=false + fi + h1_create h2_create macvlan_create $h2 - run_test $h1 $h2 "$h2" + run_test $h1 $h2 $no_unicast_flt "$h2" macvlan_destroy h2_destroy @@ -303,6 +311,7 @@ standalone() test_bridge() { + local no_unicast_flt=true local vlan_filtering=$1 h1_create @@ -310,7 +319,7 @@ test_bridge() simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64 macvlan_create br0 - run_test $h1 br0 "vlan_filtering=$vlan_filtering bridge" + run_test $h1 br0 $no_unicast_flt "vlan_filtering=$vlan_filtering bridge" macvlan_destroy simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64 @@ -330,11 +339,17 @@ vlan_aware_bridge() test_vlan() { + local no_unicast_flt=true + + if [ $(has_unicast_flt $h2) = yes ]; then + no_unicast_flt=false + fi + h1_vlan_create h2_vlan_create macvlan_create $h2.100 - run_test $h1.100 $h2.100 "VLAN upper" + run_test $h1.100 $h2.100 $no_unicast_flt "VLAN upper" macvlan_destroy h2_vlan_destroy @@ -343,14 +358,23 @@ test_vlan() vlan_over_bridged_port() { + local no_unicast_flt=true local vlan_filtering=$1 + # br_manage_promisc() will not force a single vlan_filtering port to + # promiscuous mode, so we should still expect unicast filtering to take + # place if the device can do it. + if [ $(has_unicast_flt $h2) = yes ] && [ $vlan_filtering = 1 ]; then + no_unicast_flt=false + fi + h1_vlan_create h2_vlan_create bridge_create $vlan_filtering macvlan_create $h2.100 - run_test $h1.100 $h2.100 "VLAN over vlan_filtering=$vlan_filtering bridged port" + run_test $h1.100 $h2.100 $no_unicast_flt \ + "VLAN over vlan_filtering=$vlan_filtering bridged port" macvlan_destroy bridge_destroy @@ -370,6 +394,7 @@ vlan_over_vlan_aware_bridged_port() vlan_over_bridge() { + local no_unicast_flt=true local vlan_filtering=$1 h1_vlan_create @@ -383,7 +408,8 @@ vlan_over_bridge() bridge vlan add dev br0 vid 100 self fi - run_test $h1.100 br0.100 "VLAN over vlan_filtering=$vlan_filtering bridge" + run_test $h1.100 br0.100 $no_unicast_flt \ + "VLAN over vlan_filtering=$vlan_filtering bridge" if [ $vlan_filtering = 1 ]; then bridge vlan del dev br0 vid 100 self From 237979504264912a9797dabc0db35126e705fe0d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:00 +0300 Subject: [PATCH 358/562] selftests: net: local_termination: add PTP frames to the mix A breakage in the felix DSA driver shows we do not have enough test coverage. More generally, it is sufficiently special that it is likely drivers will treat it differently. This is not meant to be a full PTP test, it just makes sure that PTP packets sent to the different addresses corresponding to their profiles are received correctly. The local_termination selftest seemed like the most appropriate place for this addition. PTP RX/TX in some cases makes no sense (over a bridge) and this is why $skip_ptp exists. And in others - PTP over a bridge port - the IP stack needs convincing through the available bridge netfilter hooks to leave the PTP packets alone and not stolen by the bridge rx_handler. It is safe to assume that users have that figured out already. This is a driver level test, and by using tcpdump, all that extra setup is out of scope here. send_non_ip() was an unfinished idea; written but never used. Replace it with a more generic send_raw(), and send 3 PTP packet types times 3 transports. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- .../net/forwarding/local_termination.sh | 161 ++++++++++++++++-- 1 file changed, 148 insertions(+), 13 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 80ea4c10d764..648868f74604 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -39,9 +39,68 @@ UNKNOWN_MACV6_MC_ADDR1="33:33:01:02:03:05" UNKNOWN_MACV6_MC_ADDR2="33:33:01:02:03:06" UNKNOWN_MACV6_MC_ADDR3="33:33:01:02:03:07" -NON_IP_MC="01:02:03:04:05:06" -NON_IP_PKT="00:04 48:45:4c:4f" -BC="ff:ff:ff:ff:ff:ff" +PTP_1588_L2_SYNC=" \ +01:1b:19:00:00:00 00:00:de:ad:be:ef 88:f7 00 02 \ +00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 00 00 \ +00 00 00 00 00 00 00 00 00 00" +PTP_1588_L2_FOLLOW_UP=" \ +01:1b:19:00:00:00 00:00:de:ad:be:ef 88:f7 08 02 \ +00 2c 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 02 00 \ +00 00 66 83 c5 f1 17 97 ed f0" +PTP_1588_L2_PDELAY_REQ=" \ +01:80:c2:00:00:0e 00:00:de:ad:be:ef 88:f7 02 02 \ +00 36 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 06 05 7f \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 00 00" +PTP_1588_IPV4_SYNC=" \ +01:00:5e:00:01:81 00:00:de:ad:be:ef 08:00 45 00 \ +00 48 0a 9a 40 00 01 11 cb 88 c0 00 02 01 e0 00 \ +01 81 01 3f 01 3f 00 34 a3 c8 00 02 00 2c 00 00 \ +02 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \ +63 ff fe cf 17 0e 00 01 00 00 00 00 00 00 00 00 \ +00 00 00 00 00 00" +PTP_1588_IPV4_FOLLOW_UP=" +01:00:5e:00:01:81 00:00:de:ad:be:ef 08:00 45 00 \ +00 48 0a 9b 40 00 01 11 cb 87 c0 00 02 01 e0 00 \ +01 81 01 40 01 40 00 34 a3 c8 08 02 00 2c 00 00 \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \ +63 ff fe cf 17 0e 00 01 00 00 02 00 00 00 66 83 \ +c6 0f 1d 9a 61 87" +PTP_1588_IPV4_PDELAY_REQ=" \ +01:00:5e:00:00:6b 00:00:de:ad:be:ef 08:00 45 00 \ +00 52 35 a9 40 00 01 11 a1 85 c0 00 02 01 e0 00 \ +00 6b 01 3f 01 3f 00 3e a2 bc 02 02 00 36 00 00 \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \ +63 ff fe cf 17 0e 00 01 00 01 05 7f 00 00 00 00 \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00" +PTP_1588_IPV6_SYNC=" \ +33:33:00:00:01:81 00:00:de:ad:be:ef 86:dd 60 06 \ +7c 2f 00 36 11 01 20 01 0d b8 00 01 00 00 00 00 \ +00 00 00 00 00 01 ff 0e 00 00 00 00 00 00 00 00 \ +00 00 00 00 01 81 01 3f 01 3f 00 36 2e 92 00 02 \ +00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 00 00 \ +00 00 00 00 00 00 00 00 00 00 00 00" +PTP_1588_IPV6_FOLLOW_UP=" \ +33:33:00:00:01:81 00:00:de:ad:be:ef 86:dd 60 0a \ +00 bc 00 36 11 01 20 01 0d b8 00 01 00 00 00 00 \ +00 00 00 00 00 01 ff 0e 00 00 00 00 00 00 00 00 \ +00 00 00 00 01 81 01 40 01 40 00 36 2e 92 08 02 \ +00 2c 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 02 00 \ +00 00 66 83 c6 2a 32 09 bd 74 00 00" +PTP_1588_IPV6_PDELAY_REQ=" \ +33:33:00:00:00:6b 00:00:de:ad:be:ef 86:dd 60 0c \ +5c fd 00 40 11 01 fe 80 00 00 00 00 00 00 3c 37 \ +63 ff fe cf 17 0e ff 02 00 00 00 00 00 00 00 00 \ +00 00 00 00 00 6b 01 3f 01 3f 00 40 b4 54 02 02 \ +00 36 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 01 05 7f \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 00 00 00 00" # Disable promisc to ensure we don't receive unknown MAC DA packets export TCPDUMP_EXTRA_FLAGS="-pl" @@ -49,13 +108,15 @@ export TCPDUMP_EXTRA_FLAGS="-pl" h1=${NETIFS[p1]} h2=${NETIFS[p2]} -send_non_ip() +send_raw() { - local if_name=$1 - local smac=$2 - local dmac=$3 + local if_name=$1; shift + local pkt="$1"; shift + local smac=$(mac_get $if_name) - $MZ -q $if_name "$dmac $smac $NON_IP_PKT" + pkt="${pkt/00:00:de:ad:be:ef/$smac}" + + $MZ -q $if_name "$pkt" } send_uc_ipv4() @@ -109,6 +170,7 @@ run_test() { local send_if_name=$1; shift local rcv_if_name=$1; shift + local skip_ptp=$1; shift local no_unicast_flt=$1; shift local test_name="$1"; shift local smac=$(mac_get $send_if_name) @@ -150,6 +212,35 @@ run_test() mc_route_destroy $rcv_if_name mc_route_destroy $send_if_name + if [ $skip_ptp = false ]; then + ip maddress add 01:1b:19:00:00:00 dev $rcv_if_name + send_raw $send_if_name "$PTP_1588_L2_SYNC" + send_raw $send_if_name "$PTP_1588_L2_FOLLOW_UP" + ip maddress del 01:1b:19:00:00:00 dev $rcv_if_name + + ip maddress add 01:80:c2:00:00:0e dev $rcv_if_name + send_raw $send_if_name "$PTP_1588_L2_PDELAY_REQ" + ip maddress del 01:80:c2:00:00:0e dev $rcv_if_name + + mc_join $rcv_if_name 224.0.1.129 + send_raw $send_if_name "$PTP_1588_IPV4_SYNC" + send_raw $send_if_name "$PTP_1588_IPV4_FOLLOW_UP" + mc_leave + + mc_join $rcv_if_name 224.0.0.107 + send_raw $send_if_name "$PTP_1588_IPV4_PDELAY_REQ" + mc_leave + + mc_join $rcv_if_name ff0e::181 + send_raw $send_if_name "$PTP_1588_IPV6_SYNC" + send_raw $send_if_name "$PTP_1588_IPV6_FOLLOW_UP" + mc_leave + + mc_join $rcv_if_name ff02::6b + send_raw $send_if_name "$PTP_1588_IPV6_PDELAY_REQ" + mc_leave + fi + sleep 1 tcpdump_stop $rcv_if_name @@ -212,6 +303,44 @@ run_test() "$smac > $UNKNOWN_MACV6_MC_ADDR3, ethertype IPv6 (0x86dd)" \ true "$test_name" + if [ $skip_ptp = false ]; then + check_rcv $rcv_if_name "1588v2 over L2 transport, Sync" \ + "ethertype PTP (0x88f7).* PTPv2.* msg type : sync msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over L2 transport, Follow-Up" \ + "ethertype PTP (0x88f7).* PTPv2.* msg type : follow up msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over L2 transport, Peer Delay Request" \ + "ethertype PTP (0x88f7).* PTPv2.* msg type : peer delay req msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv4, Sync" \ + "ethertype IPv4 (0x0800).* PTPv2.* msg type : sync msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv4, Follow-Up" \ + "ethertype IPv4 (0x0800).* PTPv2.* msg type : follow up msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv4, Peer Delay Request" \ + "ethertype IPv4 (0x0800).* PTPv2.* msg type : peer delay req msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv6, Sync" \ + "ethertype IPv6 (0x86dd).* PTPv2.* msg type : sync msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv6, Follow-Up" \ + "ethertype IPv6 (0x86dd).* PTPv2.* msg type : follow up msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv6, Peer Delay Request" \ + "ethertype IPv6 (0x86dd).* PTPv2.* msg type : peer delay req msg" \ + true "$test_name" + fi + tcpdump_cleanup $rcv_if_name } @@ -293,6 +422,7 @@ macvlan_destroy() standalone() { local no_unicast_flt=true + local skip_ptp=false if [ $(has_unicast_flt $h2) = yes ]; then no_unicast_flt=false @@ -302,7 +432,7 @@ standalone() h2_create macvlan_create $h2 - run_test $h1 $h2 $no_unicast_flt "$h2" + run_test $h1 $h2 $skip_ptp $no_unicast_flt "$h2" macvlan_destroy h2_destroy @@ -313,13 +443,15 @@ test_bridge() { local no_unicast_flt=true local vlan_filtering=$1 + local skip_ptp=true h1_create bridge_create $vlan_filtering simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64 macvlan_create br0 - run_test $h1 br0 $no_unicast_flt "vlan_filtering=$vlan_filtering bridge" + run_test $h1 br0 $skip_ptp $no_unicast_flt \ + "vlan_filtering=$vlan_filtering bridge" macvlan_destroy simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64 @@ -340,6 +472,7 @@ vlan_aware_bridge() test_vlan() { local no_unicast_flt=true + local skip_ptp=false if [ $(has_unicast_flt $h2) = yes ]; then no_unicast_flt=false @@ -349,7 +482,7 @@ test_vlan() h2_vlan_create macvlan_create $h2.100 - run_test $h1.100 $h2.100 $no_unicast_flt "VLAN upper" + run_test $h1.100 $h2.100 $skip_ptp $no_unicast_flt "VLAN upper" macvlan_destroy h2_vlan_destroy @@ -360,6 +493,7 @@ vlan_over_bridged_port() { local no_unicast_flt=true local vlan_filtering=$1 + local skip_ptp=false # br_manage_promisc() will not force a single vlan_filtering port to # promiscuous mode, so we should still expect unicast filtering to take @@ -373,7 +507,7 @@ vlan_over_bridged_port() bridge_create $vlan_filtering macvlan_create $h2.100 - run_test $h1.100 $h2.100 $no_unicast_flt \ + run_test $h1.100 $h2.100 $skip_ptp $no_unicast_flt \ "VLAN over vlan_filtering=$vlan_filtering bridged port" macvlan_destroy @@ -396,6 +530,7 @@ vlan_over_bridge() { local no_unicast_flt=true local vlan_filtering=$1 + local skip_ptp=true h1_vlan_create bridge_create $vlan_filtering @@ -408,7 +543,7 @@ vlan_over_bridge() bridge vlan add dev br0 vid 100 self fi - run_test $h1.100 br0.100 $no_unicast_flt \ + run_test $h1.100 br0.100 $skip_ptp $no_unicast_flt \ "VLAN over vlan_filtering=$vlan_filtering bridge" if [ $vlan_filtering = 1 ]; then From e29b82ef27616777e21c07dc263a8769cbdaa358 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:01 +0300 Subject: [PATCH 359/562] selftests: net: bridge_vlan_aware: test that other TPIDs are seen as untagged The bridge VLAN implementation w.r.t. VLAN protocol is described in merge commit 1a0b20b25732 ("Merge branch 'bridge-next'"). We are only sensitive to those VLAN tags whose TPID is equal to the bridge's vlan_protocol. Thus, an 802.1ad VLAN should be treated as 802.1Q-untagged. Add 3 tests which validate that: - 802.1ad-tagged traffic is learned into the PVID of an 802.1Q-aware bridge - Double-tagged traffic is forwarded when just the PVID of the port is present in the VLAN group of the ports - Double-tagged traffic is not forwarded when the PVID of the port is absent from the VLAN group of the ports The test passes with both veth and ocelot. Signed-off-by: Vladimir Oltean Reviewed-by: Ido Schimmel Tested-by: Ido Schimmel Signed-off-by: David S. Miller --- .../net/forwarding/bridge_vlan_aware.sh | 54 ++++++++++++++++++- 1 file changed, 53 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh index 64bd00fe9a4f..90f8a244ea90 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh @@ -1,7 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn" +ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid" NUM_NETIFS=4 CHECK_TC="yes" source lib.sh @@ -142,6 +142,58 @@ extern_learn() bridge fdb del de:ad:be:ef:13:37 dev $swp1 master vlan 1 &> /dev/null } +other_tpid() +{ + local mac=de:ad:be:ef:13:37 + + # Test that packets with TPID 802.1ad VID 3 + TPID 802.1Q VID 5 are + # classified as untagged by a bridge with vlan_protocol 802.1Q, and + # are processed in the PVID of the ingress port (here 1). Not VID 3, + # and not VID 5. + RET=0 + + tc qdisc add dev $h2 clsact + tc filter add dev $h2 ingress protocol all pref 1 handle 101 \ + flower dst_mac $mac action drop + ip link set $h2 promisc on + ethtool -K $h2 rx-vlan-filter off rx-vlan-stag-filter off + + $MZ -q $h1 -c 1 -b $mac -a own "88:a8 00:03 81:00 00:05 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa" + sleep 1 + + # Match on 'self' addresses as well, for those drivers which + # do not push their learned addresses to the bridge software + # database + bridge -j fdb show $swp1 | \ + jq -e ".[] | select(.mac == \"$(mac_get $h1)\") | select(.vlan == 1)" &> /dev/null + check_err $? "FDB entry was not learned when it should" + + log_test "FDB entry in PVID for VLAN-tagged with other TPID" + + RET=0 + tc -j -s filter show dev $h2 ingress \ + | jq -e ".[] | select(.options.handle == 101) \ + | select(.options.actions[0].stats.packets == 1)" &> /dev/null + check_err $? "Packet was not forwarded when it should" + log_test "Reception of VLAN with other TPID as untagged" + + bridge vlan del dev $swp1 vid 1 + + $MZ -q $h1 -c 1 -b $mac -a own "88:a8 00:03 81:00 00:05 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa" + sleep 1 + + RET=0 + tc -j -s filter show dev $h2 ingress \ + | jq -e ".[] | select(.options.handle == 101) \ + | select(.options.actions[0].stats.packets == 1)" &> /dev/null + check_err $? "Packet was forwarded when should not" + log_test "Reception of VLAN with other TPID as untagged (no PVID)" + + bridge vlan add dev $swp1 vid 1 pvid untagged + ip link set $h2 promisc off + tc qdisc del dev $h2 clsact +} + trap cleanup EXIT setup_prepare From 67c3ca2c5cfe6a50772514e3349b5e7b3b0fac03 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:02 +0300 Subject: [PATCH 360/562] net: mscc: ocelot: use ocelot_xmit_get_vlan_info() also for FDMA and register injection Problem description ------------------- On an NXP LS1028A (felix DSA driver) with the following configuration: - ocelot-8021q tagging protocol - VLAN-aware bridge (with STP) spanning at least swp0 and swp1 - 8021q VLAN upper interfaces on swp0 and swp1: swp0.700, swp1.700 - ptp4l on swp0.700 and swp1.700 we see that the ptp4l instances do not see each other's traffic, and they all go to the grand master state due to the ANNOUNCE_RECEIPT_TIMEOUT_EXPIRES condition. Jumping to the conclusion for the impatient ------------------------------------------- There is a zero-day bug in the ocelot switchdev driver in the way it handles VLAN-tagged packet injection. The correct logic already exists in the source code, in function ocelot_xmit_get_vlan_info() added by commit 5ca721c54d86 ("net: dsa: tag_ocelot: set the classified VLAN during xmit"). But it is used only for normal NPI-based injection with the DSA "ocelot" tagging protocol. The other injection code paths (register-based and FDMA-based) roll their own wrong logic. This affects and was noticed on the DSA "ocelot-8021q" protocol because it uses register-based injection. By moving ocelot_xmit_get_vlan_info() to a place that's common for both the DSA tagger and the ocelot switch library, it can also be called from ocelot_port_inject_frame() in ocelot.c. We need to touch the lines with ocelot_ifh_port_set()'s prototype anyway, so let's rename it to something clearer regarding what it does, and add a kernel-doc. ocelot_ifh_set_basic() should do. Investigation notes ------------------- Debugging reveals that PTP event (aka those carrying timestamps, like Sync) frames injected into swp0.700 (but also swp1.700) hit the wire with two VLAN tags: 00000000: 01 1b 19 00 00 00 00 01 02 03 04 05 81 00 02 bc ~~~~~~~~~~~ 00000010: 81 00 02 bc 88 f7 00 12 00 2c 00 00 02 00 00 00 ~~~~~~~~~~~ 00000020: 00 00 00 00 00 00 00 00 00 00 00 01 02 ff fe 03 00000030: 04 05 00 01 00 04 00 00 00 00 00 00 00 00 00 00 00000040: 00 00 The second (unexpected) VLAN tag makes felix_check_xtr_pkt() -> ptp_classify_raw() fail to see these as PTP packets at the link partner's receiving end, and return PTP_CLASS_NONE (because the BPF classifier is not written to expect 2 VLAN tags). The reason why packets have 2 VLAN tags is because the transmission code treats VLAN incorrectly. Neither ocelot switchdev, nor felix DSA, declare the NETIF_F_HW_VLAN_CTAG_TX feature. Therefore, at xmit time, all VLANs should be in the skb head, and none should be in the hwaccel area. This is done by: static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tag_present(skb) && !vlan_hw_offload_capable(features, skb->vlan_proto)) skb = __vlan_hwaccel_push_inside(skb); return skb; } But ocelot_port_inject_frame() handles things incorrectly: ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); void ocelot_ifh_port_set(struct sk_buff *skb, void *ifh, int port, u32 rew_op) { (...) if (vlan_tag) ocelot_ifh_set_vlan_tci(ifh, vlan_tag); (...) } The way __vlan_hwaccel_push_inside() pushes the tag inside the skb head is by calling: static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) { skb->vlan_present = 0; } which does _not_ zero out skb->vlan_tci as seen by skb_vlan_tag_get(). This means that ocelot, when it calls skb_vlan_tag_get(), sees (and uses) a residual skb->vlan_tci, while the same VLAN tag is _already_ in the skb head. The trivial fix for double VLAN headers is to replace the content of ocelot_ifh_port_set() with: if (skb_vlan_tag_present(skb)) ocelot_ifh_set_vlan_tci(ifh, skb_vlan_tag_get(skb)); but this would not be correct either, because, as mentioned, vlan_hw_offload_capable() is false for us, so we'd be inserting dead code and we'd always transmit packets with VID=0 in the injection frame header. I can't actually test the ocelot switchdev driver and rely exclusively on code inspection, but I don't think traffic from 8021q uppers has ever been injected properly, and not double-tagged. Thus I'm blaming the introduction of VLAN fields in the injection header - early driver code. As hinted at in the early conclusion, what we _want_ to happen for VLAN transmission was already described once in commit 5ca721c54d86 ("net: dsa: tag_ocelot: set the classified VLAN during xmit"). ocelot_xmit_get_vlan_info() intends to ensure that if the port through which we're transmitting is under a VLAN-aware bridge, the outer VLAN tag from the skb head is stripped from there and inserted into the injection frame header (so that the packet is processed in hardware through that actual VLAN). And in all other cases, the packet is sent with VID=0 in the injection frame header, since the port is VLAN-unaware and has logic to strip this VID on egress (making it invisible to the wire). Fixes: 08d02364b12f ("net: mscc: fix the injection header") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 29 +++++++++++---- drivers/net/ethernet/mscc/ocelot_fdma.c | 2 +- include/linux/dsa/ocelot.h | 47 +++++++++++++++++++++++++ include/soc/mscc/ocelot.h | 3 +- net/dsa/tag_ocelot.c | 37 ++----------------- 5 files changed, 75 insertions(+), 43 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index ed2fb44500b0..69a4e5a90475 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1193,17 +1193,34 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp) } EXPORT_SYMBOL(ocelot_can_inject); -void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag) +/** + * ocelot_ifh_set_basic - Set basic information in Injection Frame Header + * @ifh: Pointer to Injection Frame Header memory + * @ocelot: Switch private data structure + * @port: Egress port number + * @rew_op: Egress rewriter operation for PTP + * @skb: Pointer to socket buffer (packet) + * + * Populate the Injection Frame Header with basic information for this skb: the + * analyzer bypass bit, destination port, VLAN info, egress rewriter info. + */ +void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, + u32 rew_op, struct sk_buff *skb) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + u64 vlan_tci, tag_type; + + ocelot_xmit_get_vlan_info(skb, ocelot_port->bridge, &vlan_tci, + &tag_type); + ocelot_ifh_set_bypass(ifh, 1); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); - ocelot_ifh_set_tag_type(ifh, IFH_TAG_TYPE_C); - if (vlan_tag) - ocelot_ifh_set_vlan_tci(ifh, vlan_tag); + ocelot_ifh_set_tag_type(ifh, tag_type); + ocelot_ifh_set_vlan_tci(ifh, vlan_tci); if (rew_op) ocelot_ifh_set_rew_op(ifh, rew_op); } -EXPORT_SYMBOL(ocelot_ifh_port_set); +EXPORT_SYMBOL(ocelot_ifh_set_basic); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb) @@ -1214,7 +1231,7 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) | QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp); - ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb); for (i = 0; i < OCELOT_TAG_LEN / 4; i++) ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp); diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c index 312a46832154..87b59cc5e441 100644 --- a/drivers/net/ethernet/mscc/ocelot_fdma.c +++ b/drivers/net/ethernet/mscc/ocelot_fdma.c @@ -666,7 +666,7 @@ static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op, ifh = skb_push(skb, OCELOT_TAG_LEN); skb_put(skb, ETH_FCS_LEN); memset(ifh, 0, OCELOT_TAG_LEN); - ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb); return 0; } diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index dca2969015d8..6fbfbde68a37 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -5,6 +5,8 @@ #ifndef _NET_DSA_TAG_OCELOT_H #define _NET_DSA_TAG_OCELOT_H +#include +#include #include #include #include @@ -273,4 +275,49 @@ static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb) return rew_op; } +/** + * ocelot_xmit_get_vlan_info: Determine VLAN_TCI and TAG_TYPE for injected frame + * @skb: Pointer to socket buffer + * @br: Pointer to bridge device that the port is under, if any + * @vlan_tci: + * @tag_type: + * + * If the port is under a VLAN-aware bridge, remove the VLAN header from the + * payload and move it into the DSA tag, which will make the switch classify + * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, + * which is the pvid of standalone ports (OCELOT_STANDALONE_PVID), although not + * of VLAN-unaware bridge ports (that would be ocelot_vlan_unaware_pvid()). + * Anyway, VID 0 is fine because it is stripped on egress for these port modes, + * and source address learning is not performed for packets injected from the + * CPU anyway, so it doesn't matter that the VID is "wrong". + */ +static inline void ocelot_xmit_get_vlan_info(struct sk_buff *skb, + struct net_device *br, + u64 *vlan_tci, u64 *tag_type) +{ + struct vlan_ethhdr *hdr; + u16 proto, tci; + + if (!br || !br_vlan_enabled(br)) { + *vlan_tci = 0; + *tag_type = IFH_TAG_TYPE_C; + return; + } + + hdr = (struct vlan_ethhdr *)skb_mac_header(skb); + br_vlan_get_proto(br, &proto); + + if (ntohs(hdr->h_vlan_proto) == proto) { + vlan_remove_tag(skb, &tci); + *vlan_tci = tci; + } else { + rcu_read_lock(); + br_vlan_get_pvid_rcu(br, &tci); + rcu_read_unlock(); + *vlan_tci = tci; + } + + *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; +} + #endif diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 6a37b29f4b4c..ed18e6bafc8d 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -969,7 +969,8 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb); -void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag); +void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, + u32 rew_op, struct sk_buff *skb); int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb); void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp); void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index e0e4300bfbd3..bf6608fc6be7 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -8,40 +8,6 @@ #define OCELOT_NAME "ocelot" #define SEVILLE_NAME "seville" -/* If the port is under a VLAN-aware bridge, remove the VLAN header from the - * payload and move it into the DSA tag, which will make the switch classify - * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, - * which is the pvid of standalone and VLAN-unaware bridge ports. - */ -static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp, - u64 *vlan_tci, u64 *tag_type) -{ - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct vlan_ethhdr *hdr; - u16 proto, tci; - - if (!br || !br_vlan_enabled(br)) { - *vlan_tci = 0; - *tag_type = IFH_TAG_TYPE_C; - return; - } - - hdr = skb_vlan_eth_hdr(skb); - br_vlan_get_proto(br, &proto); - - if (ntohs(hdr->h_vlan_proto) == proto) { - vlan_remove_tag(skb, &tci); - *vlan_tci = tci; - } else { - rcu_read_lock(); - br_vlan_get_pvid_rcu(br, &tci); - rcu_read_unlock(); - *vlan_tci = tci; - } - - *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; -} - static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, __be32 ifh_prefix, void **ifh) { @@ -53,7 +19,8 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, u32 rew_op = 0; u64 qos_class; - ocelot_xmit_get_vlan_info(skb, dp, &vlan_tci, &tag_type); + ocelot_xmit_get_vlan_info(skb, dsa_port_bridge_dev_get(dp), &vlan_tci, + &tag_type); qos_class = netdev_get_num_tc(netdev) ? netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority; From e1b9e80236c540fa85d76e2d510d1b38e1968c5d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:03 +0300 Subject: [PATCH 361/562] net: mscc: ocelot: fix QoS class for injected packets with "ocelot-8021q" There are 2 distinct code paths (listed below) in the source code which set up an injection header for Ocelot(-like) switches. Code path (2) lacks the QoS class and source port being set correctly. Especially the improper QoS classification is a problem for the "ocelot-8021q" alternative DSA tagging protocol, because we support tc-taprio and each packet needs to be scheduled precisely through its time slot. This includes PTP, which is normally assigned to a traffic class other than 0, but would be sent through TC 0 nonetheless. The code paths are: (1) ocelot_xmit_common() from net/dsa/tag_ocelot.c - called only by the standard "ocelot" DSA tagging protocol which uses NPI-based injection - sets up bit fields in the tag manually to account for a small difference (destination port offset) between Ocelot and Seville. Namely, ocelot_ifh_set_dest() is omitted out of ocelot_xmit_common(), because there's also seville_ifh_set_dest(). (2) ocelot_ifh_set_basic(), called by: - ocelot_fdma_prepare_skb() for FDMA transmission of the ocelot switchdev driver - ocelot_port_xmit() -> ocelot_port_inject_frame() for register-based transmission of the ocelot switchdev driver - felix_port_deferred_xmit() -> ocelot_port_inject_frame() for the DSA tagger ocelot-8021q when it must transmit PTP frames (also through register-based injection). sets the bit fields according to its own logic. The problem is that (2) doesn't call ocelot_ifh_set_qos_class(). Copying that logic from ocelot_xmit_common() fixes that. Unfortunately, although desirable, it is not easily possible to de-duplicate code paths (1) and (2), and make net/dsa/tag_ocelot.c directly call ocelot_ifh_set_basic()), because of the ocelot/seville difference. This is the "minimal" fix with some logic duplicated (but at least more consolidated). Fixes: 0a6f17c6ae21 ("net: dsa: tag_ocelot_8021q: add support for PTP timestamping") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 10 +++++++++- drivers/net/ethernet/mscc/ocelot_fdma.c | 1 - 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 69a4e5a90475..9301716e21d5 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1208,13 +1208,21 @@ void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, u32 rew_op, struct sk_buff *skb) { struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct net_device *dev = skb->dev; u64 vlan_tci, tag_type; + int qos_class; ocelot_xmit_get_vlan_info(skb, ocelot_port->bridge, &vlan_tci, &tag_type); + qos_class = netdev_get_num_tc(dev) ? + netdev_get_prio_tc_map(dev, skb->priority) : skb->priority; + + memset(ifh, 0, OCELOT_TAG_LEN); ocelot_ifh_set_bypass(ifh, 1); + ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports)); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); + ocelot_ifh_set_qos_class(ifh, qos_class); ocelot_ifh_set_tag_type(ifh, tag_type); ocelot_ifh_set_vlan_tci(ifh, vlan_tci); if (rew_op) @@ -1225,7 +1233,7 @@ EXPORT_SYMBOL(ocelot_ifh_set_basic); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb) { - u32 ifh[OCELOT_TAG_LEN / 4] = {0}; + u32 ifh[OCELOT_TAG_LEN / 4]; unsigned int i, count, last; ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) | diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c index 87b59cc5e441..00326ae8c708 100644 --- a/drivers/net/ethernet/mscc/ocelot_fdma.c +++ b/drivers/net/ethernet/mscc/ocelot_fdma.c @@ -665,7 +665,6 @@ static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op, ifh = skb_push(skb, OCELOT_TAG_LEN); skb_put(skb, ETH_FCS_LEN); - memset(ifh, 0, OCELOT_TAG_LEN); ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb); return 0; From c5e12ac3beb0dd3a718296b2d8af5528e9ab728e Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:04 +0300 Subject: [PATCH 362/562] net: mscc: ocelot: serialize access to the injection/extraction groups As explained by Horatiu Vultur in commit 603ead96582d ("net: sparx5: Add spinlock for frame transmission from CPU") which is for a similar hardware design, multiple CPUs can simultaneously perform injection or extraction. There are only 2 register groups for injection and 2 for extraction, and the driver only uses one of each. So we'd better serialize access using spin locks, otherwise frame corruption is possible. Note that unlike in sparx5, FDMA in ocelot does not have this issue because struct ocelot_fdma_tx_ring already contains an xmit_lock. I guess this is mostly a problem for NXP LS1028A, as that is dual core. I don't think VSC7514 is. So I'm blaming the commit where LS1028A (aka the felix DSA driver) started using register-based packet injection and extraction. Fixes: 0a6f17c6ae21 ("net: dsa: tag_ocelot_8021q: add support for PTP timestamping") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 11 +++++ drivers/net/ethernet/mscc/ocelot.c | 52 ++++++++++++++++++++++ drivers/net/ethernet/mscc/ocelot_vsc7514.c | 4 ++ include/soc/mscc/ocelot.h | 9 ++++ 4 files changed, 76 insertions(+) diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index e554699f06d4..8d31ff18c5c7 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -528,7 +528,9 @@ static int felix_tag_8021q_setup(struct dsa_switch *ds) * so we need to be careful that there are no extra frames to be * dequeued over MMIO, since we would never know to discard them. */ + ocelot_lock_xtr_grp_bh(ocelot, 0); ocelot_drain_cpu_queue(ocelot, 0); + ocelot_unlock_xtr_grp_bh(ocelot, 0); return 0; } @@ -1518,6 +1520,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work) int port = xmit_work->dp->index; int retries = 10; + ocelot_lock_inj_grp(ocelot, 0); + do { if (ocelot_can_inject(ocelot, 0)) break; @@ -1526,6 +1530,7 @@ static void felix_port_deferred_xmit(struct kthread_work *work) } while (--retries); if (!retries) { + ocelot_unlock_inj_grp(ocelot, 0); dev_err(ocelot->dev, "port %d failed to inject skb\n", port); ocelot_port_purge_txtstamp_skb(ocelot, port, skb); @@ -1535,6 +1540,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work) ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); + ocelot_unlock_inj_grp(ocelot, 0); + consume_skb(skb); kfree(xmit_work); } @@ -1694,6 +1701,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot) if (!felix->info->quirk_no_xtr_irq) return false; + ocelot_lock_xtr_grp(ocelot, grp); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) { struct sk_buff *skb; unsigned int type; @@ -1730,6 +1739,8 @@ out: ocelot_drain_cpu_queue(ocelot, 0); } + ocelot_unlock_xtr_grp(ocelot, grp); + return true; } diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 9301716e21d5..f4e027a6fe95 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1099,6 +1099,48 @@ void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, } EXPORT_SYMBOL(ocelot_ptp_rx_timestamp); +void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp) + __acquires(&ocelot->inj_lock) +{ + spin_lock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_inj_grp); + +void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp) + __releases(&ocelot->inj_lock) +{ + spin_unlock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_inj_grp); + +void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp) + __acquires(&ocelot->inj_lock) +{ + spin_lock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp); + +void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp) + __releases(&ocelot->inj_lock) +{ + spin_unlock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp); + +void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp) + __acquires(&ocelot->xtr_lock) +{ + spin_lock_bh(&ocelot->xtr_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp_bh); + +void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp) + __releases(&ocelot->xtr_lock) +{ + spin_unlock_bh(&ocelot->xtr_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp_bh); + int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) { u64 timestamp, src_port, len; @@ -1109,6 +1151,8 @@ int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) u32 val, *buf; int err; + lockdep_assert_held(&ocelot->xtr_lock); + err = ocelot_xtr_poll_xfh(ocelot, grp, xfh); if (err) return err; @@ -1184,6 +1228,8 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp) { u32 val = ocelot_read(ocelot, QS_INJ_STATUS); + lockdep_assert_held(&ocelot->inj_lock); + if (!(val & QS_INJ_STATUS_FIFO_RDY(BIT(grp)))) return false; if (val & QS_INJ_STATUS_WMARK_REACHED(BIT(grp))) @@ -1236,6 +1282,8 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 ifh[OCELOT_TAG_LEN / 4]; unsigned int i, count, last; + lockdep_assert_held(&ocelot->inj_lock); + ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) | QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp); @@ -1272,6 +1320,8 @@ EXPORT_SYMBOL(ocelot_port_inject_frame); void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp) { + lockdep_assert_held(&ocelot->xtr_lock); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) ocelot_read_rix(ocelot, QS_XTR_RD, grp); } @@ -2954,6 +3004,8 @@ int ocelot_init(struct ocelot *ocelot) mutex_init(&ocelot->fwd_domain_lock); spin_lock_init(&ocelot->ptp_clock_lock); spin_lock_init(&ocelot->ts_id_lock); + spin_lock_init(&ocelot->inj_lock); + spin_lock_init(&ocelot->xtr_lock); ocelot->owq = alloc_ordered_workqueue("ocelot-owq", 0); if (!ocelot->owq) diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 993212c3a7da..c09dd2e3343c 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -51,6 +51,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) struct ocelot *ocelot = arg; int grp = 0, err; + ocelot_lock_xtr_grp(ocelot, grp); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) { struct sk_buff *skb; @@ -69,6 +71,8 @@ out: if (err < 0) ocelot_drain_cpu_queue(ocelot, 0); + ocelot_unlock_xtr_grp(ocelot, grp); + return IRQ_HANDLED; } diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index ed18e6bafc8d..462c653e1017 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -813,6 +813,9 @@ struct ocelot { const u32 *const *map; struct list_head stats_regions; + spinlock_t inj_lock; + spinlock_t xtr_lock; + u32 pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM]; int packet_buffer_size; int num_frame_refs; @@ -966,6 +969,12 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, u32 val, u32 reg, u32 offset); /* Packet I/O */ +void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp); +void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp); +void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp); +void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp); +void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp); +void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp); bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb); From 93e4649efa964201c73b0a03c35c04a0d6fc809f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:05 +0300 Subject: [PATCH 363/562] net: dsa: provide a software untagging function on RX for VLAN-aware bridges Through code analysis, I realized that the ds->untag_bridge_pvid logic is contradictory - see the newly added FIXME above the kernel-doc for dsa_software_untag_vlan_unaware_bridge(). Moreover, for the Felix driver, I need something very similar, but which is actually _not_ contradictory: untag the bridge PVID on RX, but for VLAN-aware bridges. The existing logic does it for VLAN-unaware bridges. Since I don't want to change the functionality of drivers which were supposedly properly tested with the ds->untag_bridge_pvid flag, I have introduced a new one: ds->untag_vlan_aware_bridge_pvid, and I have refactored the DSA reception code into a common path for both flags. TODO: both flags should be unified under a single ds->software_vlan_untag, which users of both current flags should set. This is not something that can be carried out right away. It needs very careful examination of all drivers which make use of this functionality, since some of them actually get this wrong in the first place. For example, commit 9130c2d30c17 ("net: dsa: microchip: ksz8795: Use software untagging on CPU port") uses this in a driver which has ds->configure_vlan_while_not_filtering = true. The latter mechanism has been known for many years to be broken by design: https://lore.kernel.org/netdev/CABumfLzJmXDN_W-8Z=p9KyKUVi_HhS7o_poBkeKHS2BkAiyYpw@mail.gmail.com/ and we have the situation of 2 bugs canceling each other. There is no private VLAN, and the port follows the PVID of the VLAN-unaware bridge. So, it's kinda ok for that driver to use the ds->untag_bridge_pvid mechanism, in a broken way. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 16 ++++-- net/dsa/tag.c | 5 +- net/dsa/tag.h | 141 +++++++++++++++++++++++++++++++++++----------- 3 files changed, 121 insertions(+), 41 deletions(-) diff --git a/include/net/dsa.h b/include/net/dsa.h index b06f97ae3da1..d7a6c2930277 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -403,14 +403,18 @@ struct dsa_switch { */ u32 configure_vlan_while_not_filtering:1; - /* If the switch driver always programs the CPU port as egress tagged - * despite the VLAN configuration indicating otherwise, then setting - * @untag_bridge_pvid will force the DSA receive path to pop the - * bridge's default_pvid VLAN tagged frames to offer a consistent - * behavior between a vlan_filtering=0 and vlan_filtering=1 bridge - * device. + /* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames. + * DEPRECATED: Do NOT set this field in new drivers. Instead look at + * the dsa_software_vlan_untag() comments. */ u32 untag_bridge_pvid:1; + /* Pop the default_pvid of VLAN-aware bridge ports from tagged frames. + * Useful if the switch cannot preserve the VLAN tag as seen on the + * wire for user port ingress, and chooses to send all frames as + * VLAN-tagged to the CPU, including those which were originally + * untagged. + */ + u32 untag_vlan_aware_bridge_pvid:1; /* Let DSA manage the FDB entries towards the * CPU, based on the software bridge database. diff --git a/net/dsa/tag.c b/net/dsa/tag.c index 6e402d49afd3..79ad105902d9 100644 --- a/net/dsa/tag.c +++ b/net/dsa/tag.c @@ -105,8 +105,9 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, p = netdev_priv(skb->dev); - if (unlikely(cpu_dp->ds->untag_bridge_pvid)) { - nskb = dsa_untag_bridge_pvid(skb); + if (unlikely(cpu_dp->ds->untag_bridge_pvid || + cpu_dp->ds->untag_vlan_aware_bridge_pvid)) { + nskb = dsa_software_vlan_untag(skb); if (!nskb) { kfree_skb(skb); return 0; diff --git a/net/dsa/tag.h b/net/dsa/tag.h index f6b9c73718df..d5707870906b 100644 --- a/net/dsa/tag.h +++ b/net/dsa/tag.h @@ -44,46 +44,81 @@ static inline struct net_device *dsa_conduit_find_user(struct net_device *dev, return NULL; } -/* If under a bridge with vlan_filtering=0, make sure to send pvid-tagged - * frames as untagged, since the bridge will not untag them. +/** + * dsa_software_untag_vlan_aware_bridge: Software untagging for VLAN-aware bridge + * @skb: Pointer to received socket buffer (packet) + * @br: Pointer to bridge upper interface of ingress port + * @vid: Parsed VID from packet + * + * The bridge can process tagged packets. Software like STP/PTP may not. The + * bridge can also process untagged packets, to the same effect as if they were + * tagged with the PVID of the ingress port. So packets tagged with the PVID of + * the bridge port must be software-untagged, to support both use cases. */ -static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) +static inline void dsa_software_untag_vlan_aware_bridge(struct sk_buff *skb, + struct net_device *br, + u16 vid) { - struct dsa_port *dp = dsa_user_to_port(skb->dev); - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct net_device *dev = skb->dev; - struct net_device *upper_dev; - u16 vid, pvid, proto; + u16 pvid, proto; int err; - if (!br || br_vlan_enabled(br)) - return skb; - err = br_vlan_get_proto(br, &proto); if (err) - return skb; + return; - /* Move VLAN tag from data to hwaccel */ - if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) { - skb = skb_vlan_untag(skb); - if (!skb) - return NULL; - } - - if (!skb_vlan_tag_present(skb)) - return skb; - - vid = skb_vlan_tag_get_id(skb); - - /* We already run under an RCU read-side critical section since - * we are called from netif_receive_skb_list_internal(). - */ - err = br_vlan_get_pvid_rcu(dev, &pvid); + err = br_vlan_get_pvid_rcu(skb->dev, &pvid); if (err) - return skb; + return; - if (vid != pvid) - return skb; + if (vid == pvid && skb->vlan_proto == htons(proto)) + __vlan_hwaccel_clear_tag(skb); +} + +/** + * dsa_software_untag_vlan_unaware_bridge: Software untagging for VLAN-unaware bridge + * @skb: Pointer to received socket buffer (packet) + * @br: Pointer to bridge upper interface of ingress port + * @vid: Parsed VID from packet + * + * The bridge ignores all VLAN tags. Software like STP/PTP may not (it may run + * on the plain port, or on a VLAN upper interface). Maybe packets are coming + * to software as tagged with a driver-defined VID which is NOT equal to the + * PVID of the bridge port (since the bridge is VLAN-unaware, its configuration + * should NOT be committed to hardware). DSA needs a method for this private + * VID to be communicated by software to it, and if packets are tagged with it, + * software-untag them. Note: the private VID may be different per bridge, to + * support the FDB isolation use case. + * + * FIXME: this is currently implemented based on the broken assumption that + * the "private VID" used by the driver in VLAN-unaware mode is equal to the + * bridge PVID. It should not be, except for a coincidence; the bridge PVID is + * irrelevant to the data path in the VLAN-unaware mode. Thus, the VID that + * this function removes is wrong. + * + * All users of ds->untag_bridge_pvid should fix their drivers, if necessary, + * to make the two independent. Only then, if there still remains a need to + * strip the private VID from packets, then a new ds->ops->get_private_vid() + * API shall be introduced to communicate to DSA what this VID is, which needs + * to be stripped here. + */ +static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb, + struct net_device *br, + u16 vid) +{ + struct net_device *upper_dev; + u16 pvid, proto; + int err; + + err = br_vlan_get_proto(br, &proto); + if (err) + return; + + err = br_vlan_get_pvid_rcu(skb->dev, &pvid); + if (err) + return; + + if (vid != pvid || skb->vlan_proto != htons(proto)) + return; /* The sad part about attempting to untag from DSA is that we * don't know, unless we check, if the skb will end up in @@ -95,10 +130,50 @@ static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) * definitely keep the tag, to make sure it keeps working. */ upper_dev = __vlan_find_dev_deep_rcu(br, htons(proto), vid); - if (upper_dev) + if (!upper_dev) + __vlan_hwaccel_clear_tag(skb); +} + +/** + * dsa_software_vlan_untag: Software VLAN untagging in DSA receive path + * @skb: Pointer to socket buffer (packet) + * + * Receive path method for switches which cannot avoid tagging all packets + * towards the CPU port. Called when ds->untag_bridge_pvid (legacy) or + * ds->untag_vlan_aware_bridge_pvid is set to true. + * + * As a side effect of this method, any VLAN tag from the skb head is moved + * to hwaccel. + */ +static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb) +{ + struct dsa_port *dp = dsa_user_to_port(skb->dev); + struct net_device *br = dsa_port_bridge_dev_get(dp); + u16 vid; + + /* software untagging for standalone ports not yet necessary */ + if (!br) return skb; - __vlan_hwaccel_clear_tag(skb); + /* Move VLAN tag from data to hwaccel */ + if (!skb_vlan_tag_present(skb)) { + skb = skb_vlan_untag(skb); + if (!skb) + return NULL; + } + + if (!skb_vlan_tag_present(skb)) + return skb; + + vid = skb_vlan_tag_get_id(skb); + + if (br_vlan_enabled(br)) { + if (dp->ds->untag_vlan_aware_bridge_pvid) + dsa_software_untag_vlan_aware_bridge(skb, br, vid); + } else { + if (dp->ds->untag_bridge_pvid) + dsa_software_untag_vlan_unaware_bridge(skb, br, vid); + } return skb; } From f1288fd7293b91442ad7420394c252a252ecaa30 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:06 +0300 Subject: [PATCH 364/562] net: dsa: felix: fix VLAN tag loss on CPU reception with ocelot-8021q There is a major design bug with ocelot-8021q, which is that it expects more of the hardware than the hardware can actually do. The short summary of the issue is that when a port is under a VLAN-aware bridge and we use this tagging protocol, VLAN upper interfaces of this port do not see RX traffic. We use VCAP ES0 (egress rewriter) rules towards the tag_8021q CPU port to encapsulate packets with an outer tag, later stripped by software, that depends on the source user port. We do this so that packets can be identified in ocelot_rcv(). To be precise, we create rules with push_outer_tag = OCELOT_ES0_TAG and push_inner_tag = 0. With this configuration, we expect the switch to keep the inner tag configuration as found in the packet (if it was untagged on user port ingress, keep it untagged, otherwise preserve the VLAN tag unmodified as the inner tag towards the tag_8021q CPU port). But this is not what happens. Instead, table "Tagging Combinations" from the user manual suggests that when the ES0 action is "PUSH_OUTER_TAG=1 and PUSH_INNER_TAG=0", there will be "no inner tag". Experimentation further clarifies what this means. It appears that this "inner tag" which is not pushed into the packet on its egress towards the CPU is none other than the classified VLAN. When the ingress user port is standalone or under a VLAN-unaware bridge, the classified VLAN is a discardable quantity: it is a fixed value - the result of ocelot_vlan_unaware_pvid()'s configuration, and actually independent of the VID from any 802.1Q header that may be in the frame. It is actually preferable to discard the "inner tag" in this case. The problem is when the ingress port is under a VLAN-aware bridge. Then, the classified VLAN is taken from the frame's 802.1Q header, with a fallback on the bridge port's PVID. It would be very good to not discard the "inner tag" here, because if we do, we break communication with any 8021q VLAN uppers that the port might have. These have a processing path outside the bridge. There seems to be nothing else we can do except to change the configuration for VCAP ES0 rules, to actually push the inner VLAN into the frame. There are 2 options for that, first is to push a fixed value specified in the rule, and second is to push a fixed value, plus (aka arithmetic +) the classified VLAN. We choose the second option, and we select that fixed value as 0. Thus, what is pushed in the inner tag is just the classified VLAN. From there, we need to perform software untagging, in the receive path, of stuff that was untagged on the wire. Fixes: 7c83a7c539ab ("net: dsa: add a second tagger for Ocelot switches based on tag_8021q") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 115 +++++++++++++++++++++++++++++++-- 1 file changed, 109 insertions(+), 6 deletions(-) diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 8d31ff18c5c7..4a705f7333f4 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -61,11 +61,46 @@ static int felix_cpu_port_for_conduit(struct dsa_switch *ds, return cpu_dp->index; } +/** + * felix_update_tag_8021q_rx_rule - Update VCAP ES0 tag_8021q rule after + * vlan_filtering change + * @outer_tagging_rule: Pointer to VCAP filter on which the update is performed + * @vlan_filtering: Current bridge VLAN filtering setting + * + * Source port identification for tag_8021q is done using VCAP ES0 rules on the + * CPU port(s). The ES0 tag B (inner tag from the packet) can be configured as + * either: + * - push_inner_tag=0: the inner tag is never pushed into the frame + * (and we lose info about the classified VLAN). This is + * good when the classified VLAN is a discardable quantity + * for the software RX path: it is either set to + * OCELOT_STANDALONE_PVID, or to + * ocelot_vlan_unaware_pvid(bridge). + * - push_inner_tag=1: the inner tag is always pushed. This is good when the + * classified VLAN is not a discardable quantity (the port + * is under a VLAN-aware bridge, and software needs to + * continue processing the packet in the same VLAN as the + * hardware). + * The point is that what is good for a VLAN-unaware port is not good for a + * VLAN-aware port, and vice versa. Thus, the RX tagging rules must be kept in + * sync with the VLAN filtering state of the port. + */ +static void +felix_update_tag_8021q_rx_rule(struct ocelot_vcap_filter *outer_tagging_rule, + bool vlan_filtering) +{ + if (vlan_filtering) + outer_tagging_rule->action.push_inner_tag = OCELOT_ES0_TAG; + else + outer_tagging_rule->action.push_inner_tag = OCELOT_NO_ES0_TAG; +} + /* Set up VCAP ES0 rules for pushing a tag_8021q VLAN towards the CPU such that * the tagger can perform RX source port identification. */ static int felix_tag_8021q_vlan_add_rx(struct dsa_switch *ds, int port, - int upstream, u16 vid) + int upstream, u16 vid, + bool vlan_filtering) { struct ocelot_vcap_filter *outer_tagging_rule; struct ocelot *ocelot = ds->priv; @@ -96,6 +131,14 @@ static int felix_tag_8021q_vlan_add_rx(struct dsa_switch *ds, int port, outer_tagging_rule->action.tag_a_tpid_sel = OCELOT_TAG_TPID_SEL_8021AD; outer_tagging_rule->action.tag_a_vid_sel = 1; outer_tagging_rule->action.vid_a_val = vid; + felix_update_tag_8021q_rx_rule(outer_tagging_rule, vlan_filtering); + outer_tagging_rule->action.tag_b_tpid_sel = OCELOT_TAG_TPID_SEL_8021Q; + /* Leave TAG_B_VID_SEL at 0 (Classified VID + VID_B_VAL). Since we also + * leave VID_B_VAL at 0, this makes ES0 tag B (the inner tag) equal to + * the classified VID, which we need to see in the DSA tagger's receive + * path. Note: the inner tag is only visible in the packet when pushed + * (push_inner_tag == OCELOT_ES0_TAG). + */ err = ocelot_vcap_filter_add(ocelot, outer_tagging_rule, NULL); if (err) @@ -227,6 +270,7 @@ static int felix_tag_8021q_vlan_del_tx(struct dsa_switch *ds, int port, u16 vid) static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid, u16 flags) { + struct dsa_port *dp = dsa_to_port(ds, port); struct dsa_port *cpu_dp; int err; @@ -234,11 +278,12 @@ static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid, * membership, which we aren't. So we don't need to add any VCAP filter * for the CPU port. */ - if (!dsa_is_user_port(ds, port)) + if (!dsa_port_is_user(dp)) return 0; dsa_switch_for_each_cpu_port(cpu_dp, ds) { - err = felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid); + err = felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid, + dsa_port_is_vlan_filtering(dp)); if (err) return err; } @@ -258,10 +303,11 @@ add_tx_failed: static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid) { + struct dsa_port *dp = dsa_to_port(ds, port); struct dsa_port *cpu_dp; int err; - if (!dsa_is_user_port(ds, port)) + if (!dsa_port_is_user(dp)) return 0; dsa_switch_for_each_cpu_port(cpu_dp, ds) { @@ -278,11 +324,41 @@ static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid) del_tx_failed: dsa_switch_for_each_cpu_port(cpu_dp, ds) - felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid); + felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid, + dsa_port_is_vlan_filtering(dp)); return err; } +static int felix_update_tag_8021q_rx_rules(struct dsa_switch *ds, int port, + bool vlan_filtering) +{ + struct ocelot_vcap_filter *outer_tagging_rule; + struct ocelot_vcap_block *block_vcap_es0; + struct ocelot *ocelot = ds->priv; + struct dsa_port *cpu_dp; + unsigned long cookie; + int err; + + block_vcap_es0 = &ocelot->block[VCAP_ES0]; + + dsa_switch_for_each_cpu_port(cpu_dp, ds) { + cookie = OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port, + cpu_dp->index); + + outer_tagging_rule = ocelot_vcap_block_find_filter_by_id(block_vcap_es0, + cookie, false); + + felix_update_tag_8021q_rx_rule(outer_tagging_rule, vlan_filtering); + + err = ocelot_vcap_filter_replace(ocelot, outer_tagging_rule); + if (err) + return err; + } + + return 0; +} + static int felix_trap_get_cpu_port(struct dsa_switch *ds, const struct ocelot_vcap_filter *trap) { @@ -532,6 +608,16 @@ static int felix_tag_8021q_setup(struct dsa_switch *ds) ocelot_drain_cpu_queue(ocelot, 0); ocelot_unlock_xtr_grp_bh(ocelot, 0); + /* Problem: when using push_inner_tag=1 for ES0 tag B, we lose info + * about whether the received packets were VLAN-tagged on the wire, + * since they are always tagged on egress towards the CPU port. + * + * Since using push_inner_tag=1 is unavoidable for VLAN-aware bridges, + * we must work around the fallout by untagging in software to make + * untagged reception work more or less as expected. + */ + ds->untag_vlan_aware_bridge_pvid = true; + return 0; } @@ -556,6 +642,8 @@ static void felix_tag_8021q_teardown(struct dsa_switch *ds) ocelot_port_teardown_dsa_8021q_cpu(ocelot, dp->index); dsa_tag_8021q_unregister(ds); + + ds->untag_vlan_aware_bridge_pvid = false; } static unsigned long felix_tag_8021q_get_host_fwd_mask(struct dsa_switch *ds) @@ -1010,8 +1098,23 @@ static int felix_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, struct netlink_ext_ack *extack) { struct ocelot *ocelot = ds->priv; + bool using_tag_8021q; + struct felix *felix; + int err; - return ocelot_port_vlan_filtering(ocelot, port, enabled, extack); + err = ocelot_port_vlan_filtering(ocelot, port, enabled, extack); + if (err) + return err; + + felix = ocelot_to_felix(ocelot); + using_tag_8021q = felix->tag_proto == DSA_TAG_PROTO_OCELOT_8021Q; + if (using_tag_8021q) { + err = felix_update_tag_8021q_rx_rules(ds, port, enabled); + if (err) + return err; + } + + return 0; } static int felix_vlan_add(struct dsa_switch *ds, int port, From 36dd1141be70b5966906919714dc504a24c65ddf Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:07 +0300 Subject: [PATCH 365/562] net: mscc: ocelot: treat 802.1ad tagged traffic as 802.1Q-untagged I was revisiting the topic of 802.1ad treatment in the Ocelot switch [0] and realized that not only is its basic VLAN classification pipeline improper for offloading vlan_protocol 802.1ad bridges, but also improper for offloading regular 802.1Q bridges already. Namely, 802.1ad-tagged traffic should be treated as VLAN-untagged by bridged ports, but this switch treats it as if it was 802.1Q-tagged with the same VID as in the 802.1ad header. This is markedly different to what the Linux bridge expects; see the "other_tpid()" function in tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh. An idea came to me that the VCAP IS1 TCAM is more powerful than I'm giving it credit for, and that it actually overwrites the classified VID before the VLAN Table lookup takes place. In other words, it can be used even to save a packet from being dropped on ingress due to VLAN membership. Add a sophisticated TCAM rule hardcoded into the driver to force the switch to behave like a Linux bridge with vlan_filtering 1 vlan_protocol 802.1Q. Regarding the lifetime of the filter: eventually the bridge will disappear, and vlan_filtering on the port will be restored to 0 for standalone mode. Then the filter will be deleted. [0]: https://lore.kernel.org/netdev/20201009122947.nvhye4hvcha3tljh@skbuf/ Fixes: 7142529f1688 ("net: mscc: ocelot: add VLAN filtering") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 188 ++++++++++++++++++++++-- drivers/net/ethernet/mscc/ocelot_vcap.c | 1 + include/soc/mscc/ocelot_vcap.h | 2 + 3 files changed, 180 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index f4e027a6fe95..3d72aa7b1305 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -453,9 +453,158 @@ static u16 ocelot_vlan_unaware_pvid(struct ocelot *ocelot, return VLAN_N_VID - bridge_num - 1; } +/** + * ocelot_update_vlan_reclassify_rule() - Make switch aware only to bridge VLAN TPID + * + * @ocelot: Switch private data structure + * @port: Index of ingress port + * + * IEEE 802.1Q-2018 clauses "5.5 C-VLAN component conformance" and "5.6 S-VLAN + * component conformance" suggest that a C-VLAN component should only recognize + * and filter on C-Tags, and an S-VLAN component should only recognize and + * process based on C-Tags. + * + * In Linux, as per commit 1a0b20b25732 ("Merge branch 'bridge-next'"), C-VLAN + * components are largely represented by a bridge with vlan_protocol 802.1Q, + * and S-VLAN components by a bridge with vlan_protocol 802.1ad. + * + * Currently the driver only offloads vlan_protocol 802.1Q, but the hardware + * design is non-conformant, because the switch assigns each frame to a VLAN + * based on an entirely different question, as detailed in figure "Basic VLAN + * Classification Flow" from its manual and reproduced below. + * + * Set TAG_TYPE, PCP, DEI, VID to port-default values in VLAN_CFG register + * if VLAN_AWARE_ENA[port] and frame has outer tag then: + * if VLAN_INNER_TAG_ENA[port] and frame has inner tag then: + * TAG_TYPE = (Frame.InnerTPID <> 0x8100) + * Set PCP, DEI, VID to values from inner VLAN header + * else: + * TAG_TYPE = (Frame.OuterTPID <> 0x8100) + * Set PCP, DEI, VID to values from outer VLAN header + * if VID == 0 then: + * VID = VLAN_CFG.VLAN_VID + * + * Summarized, the switch will recognize both 802.1Q and 802.1ad TPIDs as VLAN + * "with equal rights", and just set the TAG_TYPE bit to 0 (if 802.1Q) or to 1 + * (if 802.1ad). It will classify based on whichever of the tags is "outer", no + * matter what TPID that may have (or "inner", if VLAN_INNER_TAG_ENA[port]). + * + * In the VLAN Table, the TAG_TYPE information is not accessible - just the + * classified VID is - so it is as if each VLAN Table entry is for 2 VLANs: + * C-VLAN X, and S-VLAN X. + * + * Whereas the Linux bridge behavior is to only filter on frames with a TPID + * equal to the vlan_protocol, and treat everything else as VLAN-untagged. + * + * Consider an ingress packet tagged with 802.1ad VID=3 and 802.1Q VID=5, + * received on a bridge vlan_filtering=1 vlan_protocol=802.1Q port. This frame + * should be treated as 802.1Q-untagged, and classified to the PVID of that + * bridge port. Not to VID=3, and not to VID=5. + * + * The VCAP IS1 TCAM has everything we need to overwrite the choices made in + * the basic VLAN classification pipeline: it can match on TAG_TYPE in the key, + * and it can modify the classified VID in the action. Thus, for each port + * under a vlan_filtering bridge, we can insert a rule in VCAP IS1 lookup 0 to + * match on 802.1ad tagged frames and modify their classified VID to the 802.1Q + * PVID of the port. This effectively makes it appear to the outside world as + * if those packets were processed as VLAN-untagged. + * + * The rule needs to be updated each time the bridge PVID changes, and needs + * to be deleted if the bridge PVID is deleted, or if the port becomes + * VLAN-unaware. + */ +static int ocelot_update_vlan_reclassify_rule(struct ocelot *ocelot, int port) +{ + unsigned long cookie = OCELOT_VCAP_IS1_VLAN_RECLASSIFY(ocelot, port); + struct ocelot_vcap_block *block_vcap_is1 = &ocelot->block[VCAP_IS1]; + struct ocelot_port *ocelot_port = ocelot->ports[port]; + const struct ocelot_bridge_vlan *pvid_vlan; + struct ocelot_vcap_filter *filter; + int err, val, pcp, dei; + bool vid_replace_ena; + u16 vid; + + pvid_vlan = ocelot_port->pvid_vlan; + vid_replace_ena = ocelot_port->vlan_aware && pvid_vlan; + + filter = ocelot_vcap_block_find_filter_by_id(block_vcap_is1, cookie, + false); + if (!vid_replace_ena) { + /* If the reclassification filter doesn't need to exist, delete + * it if it was previously installed, and exit doing nothing + * otherwise. + */ + if (filter) + return ocelot_vcap_filter_del(ocelot, filter); + + return 0; + } + + /* The reclassification rule must apply. See if it already exists + * or if it must be created. + */ + + /* Treating as VLAN-untagged means using as classified VID equal to + * the bridge PVID, and PCP/DEI set to the port default QoS values. + */ + vid = pvid_vlan->vid; + val = ocelot_read_gix(ocelot, ANA_PORT_QOS_CFG, port); + pcp = ANA_PORT_QOS_CFG_QOS_DEFAULT_VAL_X(val); + dei = !!(val & ANA_PORT_QOS_CFG_DP_DEFAULT_VAL); + + if (filter) { + bool changed = false; + + /* Filter exists, just update it */ + if (filter->action.vid != vid) { + filter->action.vid = vid; + changed = true; + } + if (filter->action.pcp != pcp) { + filter->action.pcp = pcp; + changed = true; + } + if (filter->action.dei != dei) { + filter->action.dei = dei; + changed = true; + } + + if (!changed) + return 0; + + return ocelot_vcap_filter_replace(ocelot, filter); + } + + /* Filter doesn't exist, create it */ + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) + return -ENOMEM; + + filter->key_type = OCELOT_VCAP_KEY_ANY; + filter->ingress_port_mask = BIT(port); + filter->vlan.tpid = OCELOT_VCAP_BIT_1; + filter->prio = 1; + filter->id.cookie = cookie; + filter->id.tc_offload = false; + filter->block_id = VCAP_IS1; + filter->type = OCELOT_VCAP_FILTER_OFFLOAD; + filter->lookup = 0; + filter->action.vid_replace_ena = true; + filter->action.pcp_dei_ena = true; + filter->action.vid = vid; + filter->action.pcp = pcp; + filter->action.dei = dei; + + err = ocelot_vcap_filter_add(ocelot, filter, NULL); + if (err) + kfree(filter); + + return err; +} + /* Default vlan to clasify for untagged frames (may be zero) */ -static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, - const struct ocelot_bridge_vlan *pvid_vlan) +static int ocelot_port_set_pvid(struct ocelot *ocelot, int port, + const struct ocelot_bridge_vlan *pvid_vlan) { struct ocelot_port *ocelot_port = ocelot->ports[port]; u16 pvid = ocelot_vlan_unaware_pvid(ocelot, ocelot_port->bridge); @@ -475,15 +624,23 @@ static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, * happens automatically), but also 802.1p traffic which gets * classified to VLAN 0, but that is always in our RX filter, so it * would get accepted were it not for this setting. + * + * Also, we only support the bridge 802.1Q VLAN protocol, so + * 802.1ad-tagged frames (carrying S-Tags) should be considered + * 802.1Q-untagged, and also dropped. */ if (!pvid_vlan && ocelot_port->vlan_aware) val = ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | - ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA; + ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA | + ANA_PORT_DROP_CFG_DROP_S_TAGGED_ENA; ocelot_rmw_gix(ocelot, val, ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | - ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA, + ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA | + ANA_PORT_DROP_CFG_DROP_S_TAGGED_ENA, ANA_PORT_DROP_CFG, port); + + return ocelot_update_vlan_reclassify_rule(ocelot, port); } static struct ocelot_bridge_vlan *ocelot_bridge_vlan_find(struct ocelot *ocelot, @@ -631,7 +788,10 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M, ANA_PORT_VLAN_CFG, port); - ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan); + err = ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan); + if (err) + return err; + ocelot_port_manage_port_tag(ocelot, port); return 0; @@ -684,9 +844,12 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, return err; /* Default ingress vlan classification */ - if (pvid) - ocelot_port_set_pvid(ocelot, port, - ocelot_bridge_vlan_find(ocelot, vid)); + if (pvid) { + err = ocelot_port_set_pvid(ocelot, port, + ocelot_bridge_vlan_find(ocelot, vid)); + if (err) + return err; + } /* Untagged egress vlan clasification */ ocelot_port_manage_port_tag(ocelot, port); @@ -712,8 +875,11 @@ int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid) return err; /* Ingress */ - if (del_pvid) - ocelot_port_set_pvid(ocelot, port, NULL); + if (del_pvid) { + err = ocelot_port_set_pvid(ocelot, port, NULL); + if (err) + return err; + } /* Egress */ ocelot_port_manage_port_tag(ocelot, port); @@ -2607,7 +2773,7 @@ int ocelot_port_set_default_prio(struct ocelot *ocelot, int port, u8 prio) ANA_PORT_QOS_CFG, port); - return 0; + return ocelot_update_vlan_reclassify_rule(ocelot, port); } EXPORT_SYMBOL_GPL(ocelot_port_set_default_prio); diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c index 73cdec5ca6a3..5734b86aed5b 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.c +++ b/drivers/net/ethernet/mscc/ocelot_vcap.c @@ -695,6 +695,7 @@ static void is1_entry_set(struct ocelot *ocelot, int ix, vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_MC, filter->dmac_mc); vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_BC, filter->dmac_bc); vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_VLAN_TAGGED, tag->tagged); + vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_TPID, tag->tpid); vcap_key_set(vcap, &data, VCAP_IS1_HK_VID, tag->vid.value, tag->vid.mask); vcap_key_set(vcap, &data, VCAP_IS1_HK_PCP, diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index c601a4598b0d..eb19668a06db 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -13,6 +13,7 @@ */ #define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port, upstream) ((upstream) << 16 | (port)) #define OCELOT_VCAP_IS1_TAG_8021Q_TXVLAN(ocelot, port) (port) +#define OCELOT_VCAP_IS1_VLAN_RECLASSIFY(ocelot, port) ((ocelot)->num_phys_ports + (port)) #define OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN(ocelot, port) (port) #define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port) ((ocelot)->num_phys_ports + (port)) #define OCELOT_VCAP_IS2_MRP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2) @@ -499,6 +500,7 @@ struct ocelot_vcap_key_vlan { struct ocelot_vcap_u8 pcp; /* PCP (3 bit) */ enum ocelot_vcap_bit dei; /* DEI */ enum ocelot_vcap_bit tagged; /* Tagged/untagged frame */ + enum ocelot_vcap_bit tpid; }; struct ocelot_vcap_key_etype { From b9b6ee6fe258ce4d89592593efcd3d798c418859 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 13 Aug 2024 16:25:19 +0200 Subject: [PATCH 366/562] thermal: gov_bang_bang: Call __thermal_cdev_update() directly MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of clearing the "updated" flag for each cooling device affected by the trip point crossing in bang_bang_control() and walking all thermal instances to run thermal_cdev_update() for all of the affected cooling devices, call __thermal_cdev_update() directly for each of them. No intentional functional impact. Signed-off-by: Rafael J. Wysocki Acked-by: Peter Kästle Reviewed-by: Zhang Rui Cc: 6.10+ # 6.10+ Link: https://patch.msgid.link/13583081.uLZWGnKmhe@rjwysocki.net --- drivers/thermal/gov_bang_bang.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c index 4a2e869b9538..b9474c6af72b 100644 --- a/drivers/thermal/gov_bang_bang.c +++ b/drivers/thermal/gov_bang_bang.c @@ -71,12 +71,9 @@ static void bang_bang_control(struct thermal_zone_device *tz, dev_dbg(&instance->cdev->device, "target=%ld\n", instance->target); mutex_lock(&instance->cdev->lock); - instance->cdev->updated = false; /* cdev needs update */ + __thermal_cdev_update(instance->cdev); mutex_unlock(&instance->cdev->lock); } - - list_for_each_entry(instance, &tz->thermal_instances, tz_node) - thermal_cdev_update(instance->cdev); } static struct thermal_governor thermal_gov_bang_bang = { From 84248e35d9b60e03df7276627e4e91fbaf80f73d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 13 Aug 2024 16:26:42 +0200 Subject: [PATCH 367/562] thermal: gov_bang_bang: Split bang_bang_control() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move the setting of the thermal instance target state from bang_bang_control() into a separate function that will be also called in a different place going forward. No intentional functional impact. Signed-off-by: Rafael J. Wysocki Acked-by: Peter Kästle Reviewed-by: Zhang Rui Cc: 6.10+ # 6.10+ Link: https://patch.msgid.link/3313587.aeNJFYEL58@rjwysocki.net --- drivers/thermal/gov_bang_bang.c | 42 ++++++++++++++++++--------------- 1 file changed, 23 insertions(+), 19 deletions(-) diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c index b9474c6af72b..87cff3ea77a9 100644 --- a/drivers/thermal/gov_bang_bang.c +++ b/drivers/thermal/gov_bang_bang.c @@ -13,6 +13,27 @@ #include "thermal_core.h" +static void bang_bang_set_instance_target(struct thermal_instance *instance, + unsigned int target) +{ + if (instance->target != 0 && instance->target != 1 && + instance->target != THERMAL_NO_TARGET) + pr_debug("Unexpected state %ld of thermal instance %s in bang-bang\n", + instance->target, instance->name); + + /* + * Enable the fan when the trip is crossed on the way up and disable it + * when the trip is crossed on the way down. + */ + instance->target = target; + + dev_dbg(&instance->cdev->device, "target=%ld\n", instance->target); + + mutex_lock(&instance->cdev->lock); + __thermal_cdev_update(instance->cdev); + mutex_unlock(&instance->cdev->lock); +} + /** * bang_bang_control - controls devices associated with the given zone * @tz: thermal_zone_device @@ -54,25 +75,8 @@ static void bang_bang_control(struct thermal_zone_device *tz, tz->temperature, trip->hysteresis); list_for_each_entry(instance, &tz->thermal_instances, tz_node) { - if (instance->trip != trip) - continue; - - if (instance->target != 0 && instance->target != 1 && - instance->target != THERMAL_NO_TARGET) - pr_debug("Unexpected state %ld of thermal instance %s in bang-bang\n", - instance->target, instance->name); - - /* - * Enable the fan when the trip is crossed on the way up and - * disable it when the trip is crossed on the way down. - */ - instance->target = crossed_up; - - dev_dbg(&instance->cdev->device, "target=%ld\n", instance->target); - - mutex_lock(&instance->cdev->lock); - __thermal_cdev_update(instance->cdev); - mutex_unlock(&instance->cdev->lock); + if (instance->trip == trip) + bang_bang_set_instance_target(instance, crossed_up); } } From 5f64b4a1ab1b0412446d42e1fc2964c2cdb60b27 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 13 Aug 2024 16:27:33 +0200 Subject: [PATCH 368/562] thermal: gov_bang_bang: Add .manage() callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After recent changes, the Bang-bang governor may not adjust the initial configuration of cooling devices to the actual situation. Namely, if a cooling device bound to a certain trip point starts in the "on" state and the thermal zone temperature is below the threshold of that trip point, the trip point may never be crossed on the way up in which case the state of the cooling device will never be adjusted because the thermal core will never invoke the governor's .trip_crossed() callback. [Note that there is no issue if the zone temperature is at the trip threshold or above it to start with because .trip_crossed() will be invoked then to indicate the start of thermal mitigation for the given trip.] To address this, add a .manage() callback to the Bang-bang governor and use it to ensure that all of the thermal instances managed by the governor have been initialized properly and the states of all of the cooling devices involved have been adjusted to the current zone temperature as appropriate. Fixes: 530c932bdf75 ("thermal: gov_bang_bang: Use .trip_crossed() instead of .throttle()") Link: https://lore.kernel.org/linux-pm/1bfbbae5-42b0-4c7d-9544-e98855715294@piie.net/ Cc: 6.10+ # 6.10+ Signed-off-by: Rafael J. Wysocki Acked-by: Peter Kästle Reviewed-by: Zhang Rui Link: https://patch.msgid.link/8419356.T7Z3S40VBb@rjwysocki.net --- drivers/thermal/gov_bang_bang.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c index 87cff3ea77a9..bc55e0698bfa 100644 --- a/drivers/thermal/gov_bang_bang.c +++ b/drivers/thermal/gov_bang_bang.c @@ -26,6 +26,7 @@ static void bang_bang_set_instance_target(struct thermal_instance *instance, * when the trip is crossed on the way down. */ instance->target = target; + instance->initialized = true; dev_dbg(&instance->cdev->device, "target=%ld\n", instance->target); @@ -80,8 +81,37 @@ static void bang_bang_control(struct thermal_zone_device *tz, } } +static void bang_bang_manage(struct thermal_zone_device *tz) +{ + const struct thermal_trip_desc *td; + struct thermal_instance *instance; + + for_each_trip_desc(tz, td) { + const struct thermal_trip *trip = &td->trip; + + if (tz->temperature >= td->threshold || + trip->temperature == THERMAL_TEMP_INVALID || + trip->type == THERMAL_TRIP_CRITICAL || + trip->type == THERMAL_TRIP_HOT) + continue; + + /* + * If the initial cooling device state is "on", but the zone + * temperature is not above the trip point, the core will not + * call bang_bang_control() until the zone temperature reaches + * the trip point temperature which may be never. In those + * cases, set the initial state of the cooling device to 0. + */ + list_for_each_entry(instance, &tz->thermal_instances, tz_node) { + if (!instance->initialized && instance->trip == trip) + bang_bang_set_instance_target(instance, 0); + } + } +} + static struct thermal_governor thermal_gov_bang_bang = { .name = "bang_bang", .trip_crossed = bang_bang_control, + .manage = bang_bang_manage, }; THERMAL_GOVERNOR_DECLARE(thermal_gov_bang_bang); From 6e6f58a170ea98e44075b761f2da42a5aec47dfb Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 13 Aug 2024 16:29:11 +0200 Subject: [PATCH 369/562] thermal: gov_bang_bang: Use governor_data to reduce overhead MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After running once, the for_each_trip_desc() loop in bang_bang_manage() is pure needless overhead because it is not going to make any changes unless a new cooling device has been bound to one of the trips in the thermal zone or the system is resuming from sleep. For this reason, make bang_bang_manage() set governor_data for the thermal zone and check it upfront to decide whether or not it needs to do anything. However, governor_data needs to be reset in some cases to let bang_bang_manage() know that it should walk the trips again, so add an .update_tz() callback to the governor and make the core additionally invoke it during system resume. To avoid affecting the other users of that callback unnecessarily, add a special notification reason for system resume, THERMAL_TZ_RESUME, and also pass it to __thermal_zone_device_update() called during system resume for consistency. Signed-off-by: Rafael J. Wysocki Acked-by: Peter Kästle Reviewed-by: Zhang Rui Cc: 6.10+ # 6.10+ Link: https://patch.msgid.link/2285575.iZASKD2KPV@rjwysocki.net --- drivers/thermal/gov_bang_bang.c | 18 ++++++++++++++++++ drivers/thermal/thermal_core.c | 3 ++- include/linux/thermal.h | 1 + 3 files changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c index bc55e0698bfa..daed67d19efb 100644 --- a/drivers/thermal/gov_bang_bang.c +++ b/drivers/thermal/gov_bang_bang.c @@ -86,6 +86,10 @@ static void bang_bang_manage(struct thermal_zone_device *tz) const struct thermal_trip_desc *td; struct thermal_instance *instance; + /* If the code below has run already, nothing needs to be done. */ + if (tz->governor_data) + return; + for_each_trip_desc(tz, td) { const struct thermal_trip *trip = &td->trip; @@ -107,11 +111,25 @@ static void bang_bang_manage(struct thermal_zone_device *tz) bang_bang_set_instance_target(instance, 0); } } + + tz->governor_data = (void *)true; +} + +static void bang_bang_update_tz(struct thermal_zone_device *tz, + enum thermal_notify_event reason) +{ + /* + * Let bang_bang_manage() know that it needs to walk trips after binding + * a new cdev and after system resume. + */ + if (reason == THERMAL_TZ_BIND_CDEV || reason == THERMAL_TZ_RESUME) + tz->governor_data = NULL; } static struct thermal_governor thermal_gov_bang_bang = { .name = "bang_bang", .trip_crossed = bang_bang_control, .manage = bang_bang_manage, + .update_tz = bang_bang_update_tz, }; THERMAL_GOVERNOR_DECLARE(thermal_gov_bang_bang); diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 95c399f94744..e6669aeda1ff 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1728,7 +1728,8 @@ static void thermal_zone_device_resume(struct work_struct *work) thermal_debug_tz_resume(tz); thermal_zone_device_init(tz); - __thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED); + thermal_governor_update_tz(tz, THERMAL_TZ_RESUME); + __thermal_zone_device_update(tz, THERMAL_TZ_RESUME); complete(&tz->resume); tz->resuming = false; diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 25fbf960b474..b86ddca46b9e 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -55,6 +55,7 @@ enum thermal_notify_event { THERMAL_TZ_BIND_CDEV, /* Cooling dev is bind to the thermal zone */ THERMAL_TZ_UNBIND_CDEV, /* Cooling dev is unbind from the thermal zone */ THERMAL_INSTANCE_WEIGHT_CHANGED, /* Thermal instance weight changed */ + THERMAL_TZ_RESUME, /* Thermal zone is resuming after system sleep */ }; /** From 145082ebfcf08f4fd254c467abf4aa58b4d38505 Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Mon, 12 Aug 2024 14:17:21 +0200 Subject: [PATCH 370/562] Documentation/llvm: turn make command for ccache into code block The command provided to use ccache with clang is not a literal code block. Once built, the documentation displays the '' symbols as a " character, which is wrong, and the command can not be applied as provided. Turn the command into a literal code block. Signed-off-by: Javier Carrasco Reviewed-by: Nathan Chancellor Signed-off-by: Masahiro Yamada --- Documentation/kbuild/llvm.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst index bb5c44f8bd1c..6dc66b4f31a7 100644 --- a/Documentation/kbuild/llvm.rst +++ b/Documentation/kbuild/llvm.rst @@ -126,7 +126,7 @@ Ccache ``ccache`` can be used with ``clang`` to improve subsequent builds, (though KBUILD_BUILD_TIMESTAMP_ should be set to a deterministic value between builds -in order to avoid 100% cache misses, see Reproducible_builds_ for more info): +in order to avoid 100% cache misses, see Reproducible_builds_ for more info):: KBUILD_BUILD_TIMESTAMP='' make LLVM=1 CC="ccache clang" From c2f6e16a6771eaefba6bb35f6803fe7217822d41 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Thu, 15 Aug 2024 13:02:55 -0400 Subject: [PATCH 371/562] bcachefs: Increase size of cuckoo hash table on too many rehashes Also, improve the calculation of the new table size, so that it can shrink when needed. Signed-off-by: Kent Overstreet --- fs/bcachefs/buckets_waiting_for_journal.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/bcachefs/buckets_waiting_for_journal.c b/fs/bcachefs/buckets_waiting_for_journal.c index ec1b636ef78d..f70eb2127d32 100644 --- a/fs/bcachefs/buckets_waiting_for_journal.c +++ b/fs/bcachefs/buckets_waiting_for_journal.c @@ -93,7 +93,7 @@ int bch2_set_bucket_needs_journal_commit(struct buckets_waiting_for_journal *b, .dev_bucket = (u64) dev << 56 | bucket, .journal_seq = journal_seq, }; - size_t i, size, new_bits, nr_elements = 1, nr_rehashes = 0; + size_t i, size, new_bits, nr_elements = 1, nr_rehashes = 0, nr_rehashes_this_size = 0; int ret = 0; mutex_lock(&b->lock); @@ -106,7 +106,7 @@ int bch2_set_bucket_needs_journal_commit(struct buckets_waiting_for_journal *b, for (i = 0; i < size; i++) nr_elements += t->d[i].journal_seq > flushed_seq; - new_bits = t->bits + (nr_elements * 3 > size); + new_bits = ilog2(roundup_pow_of_two(nr_elements * 3)); n = kvmalloc(sizeof(*n) + (sizeof(n->d[0]) << new_bits), GFP_KERNEL); if (!n) { @@ -115,7 +115,14 @@ int bch2_set_bucket_needs_journal_commit(struct buckets_waiting_for_journal *b, } retry_rehash: + if (nr_rehashes_this_size == 3) { + new_bits++; + nr_rehashes_this_size = 0; + } + nr_rehashes++; + nr_rehashes_this_size++; + bucket_table_init(n, new_bits); tmp = new; From 075cabf324c3fd790d6ba39ff9db33a30b954fe2 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 16 Aug 2024 12:31:29 -0400 Subject: [PATCH 372/562] bcachefs: Fix forgetting to pass trans to fsck_err() Reported-by: syzbot+e3938cd6d761b78750e6@syzkaller.appspotmail.com Signed-off-by: Kent Overstreet --- fs/bcachefs/buckets.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index b69ef4b3de6e..ad517ef744e5 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -925,7 +925,7 @@ static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans, return PTR_ERR(a); if (a->v.data_type && type && a->v.data_type != type) { - bch2_fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, + bch2_fsck_err(trans, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, bucket_metadata_type_mismatch, "bucket %llu:%llu gen %u different types of data in same bucket: %s, %s\n" "while marking %s", From 9482f3b05332a624508a91c2ab2cf3527328a6a4 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 16 Aug 2024 12:41:46 -0400 Subject: [PATCH 373/562] bcachefs: avoid overflowing LRU_TIME_BITS for cached data lru Reported-by: syzbot+510b0b28f8e6de64d307@syzkaller.appspotmail.com Signed-off-by: Kent Overstreet --- fs/bcachefs/alloc_background.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/bcachefs/alloc_background.h b/fs/bcachefs/alloc_background.h index 260e7fa83d05..fd790b03fbe1 100644 --- a/fs/bcachefs/alloc_background.h +++ b/fs/bcachefs/alloc_background.h @@ -150,7 +150,9 @@ static inline void alloc_data_type_set(struct bch_alloc_v4 *a, enum bch_data_typ static inline u64 alloc_lru_idx_read(struct bch_alloc_v4 a) { - return a.data_type == BCH_DATA_cached ? a.io_time[READ] : 0; + return a.data_type == BCH_DATA_cached + ? a.io_time[READ] & LRU_TIME_MAX + : 0; } #define DATA_TYPES_MOVABLE \ From 99c87fe0f584f8d778a323141504d1ba5c89a4a5 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 16 Aug 2024 12:44:49 -0400 Subject: [PATCH 374/562] bcachefs: fix incorrect i_state usage Reported-by: syzbot+95e40eae71609e40d851@syzkaller.appspotmail.com Signed-off-by: Kent Overstreet --- fs/bcachefs/fs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 15fc41e63b6c..94c392abef65 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -193,7 +193,7 @@ static struct bch_inode_info *bch2_inode_insert(struct bch_fs *c, struct bch_ino * only insert fully created inodes in the inode hash table. But * discard_new_inode() expects it to be set... */ - inode->v.i_flags |= I_NEW; + inode->v.i_state |= I_NEW; /* * We don't want bch2_evict_inode() to delete the inode on disk, * we just raced and had another inode in cache. Normally new From 1fc2ac428ef7d2ab9e8e19efe7ec3e58aea51bf3 Mon Sep 17 00:00:00 2001 From: Caleb Sander Mateos Date: Fri, 16 Aug 2024 12:15:23 -0600 Subject: [PATCH 375/562] io_uring: fix user_data field name in comment io_uring_cqe's user_data field refers to `sqe->data`, but io_uring_sqe does not have a data field. Fix the comment to say `sqe->user_data`. Signed-off-by: Caleb Sander Mateos Link: https://github.com/axboe/liburing/pull/1206 Link: https://lore.kernel.org/r/20240816181526.3642732-1-csander@purestorage.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 2aaf7ee256ac..adc2524fd8e3 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -421,7 +421,7 @@ enum io_uring_msg_ring_flags { * IO completion data structure (Completion Queue Entry) */ struct io_uring_cqe { - __u64 user_data; /* sqe->data submission passed back */ + __u64 user_data; /* sqe->user_data value passed back */ __s32 res; /* result code for this event */ __u32 flags; From 534f7eff9239c1b0af852fc33f5af2b62c00eddf Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Fri, 16 Aug 2024 10:40:38 +0930 Subject: [PATCH 376/562] btrfs: only enable extent map shrinker for DEBUG builds Although there are several patches improving the extent map shrinker, there are still reports of too frequent shrinker behavior, taking too much CPU for the kswapd process. So let's only enable extent shrinker for now, until we got more comprehensive understanding and a better solution. Link: https://lore.kernel.org/linux-btrfs/3df4acd616a07ef4d2dc6bad668701504b412ffc.camel@intelfx.name/ Link: https://lore.kernel.org/linux-btrfs/c30fd6b3-ca7a-4759-8a53-d42878bf84f7@gmail.com/ Fixes: 956a17d9d050 ("btrfs: add a shrinker for extent maps") CC: stable@vger.kernel.org # 6.10+ Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/super.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 11044e9e2cb1..98fa0f382480 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2402,7 +2402,13 @@ static long btrfs_nr_cached_objects(struct super_block *sb, struct shrink_contro trace_btrfs_extent_map_shrinker_count(fs_info, nr); - return nr; + /* + * Only report the real number for DEBUG builds, as there are reports of + * serious performance degradation caused by too frequent shrinks. + */ + if (IS_ENABLED(CONFIG_BTRFS_DEBUG)) + return nr; + return 0; } static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_control *sc) From f232de7cdb4b99adb2c7f2bc5e0b7e4e1292873b Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Thu, 15 Aug 2024 10:16:08 +0300 Subject: [PATCH 377/562] net/mlx5e: SHAMPO, Fix page leak When SHAMPO is used, a receive queue currently almost always leaks one page on shutdown. A page has MLX5E_SHAMPO_WQ_HEADER_PER_PAGE (8) headers. These headers are tracked in the SHAMPO bitmap. Each page is released when the last header index in the group is processed. During header allocation, there can be leftovers from a page that will be used in a subsequent allocation. This is normally fine, except for the following scenario (simplified a bit): 1) Allocate N new page fragments, showing only the relevant last 4 fragments: 0: new page 1: new page 2: new page 3: new page 4: page from previous allocation 5: page from previous allocation 6: page from previous allocation 7: page from previous allocation 2) NAPI processes header indices 4-7 because they are the oldest allocated. Bit 7 will be set to 0. 3) Receive queue shutdown occurs. All the remaining bits are being iterated on to release the pages. But the page assigned to header indices 0-3 will not be freed due to what happened in step 2. This patch fixes the issue by making sure that on allocation, header fragments are always allocated in groups of MLX5E_SHAMPO_WQ_HEADER_PER_PAGE so that there is never a partial page left over between allocations. A more appropriate fix would be a refactoring of mlx5e_alloc_rx_hd_mpwqe() and mlx5e_build_shampo_hd_umr(). But this refactoring is too big for net. It will be targeted for net-next. Fixes: e839ac9a89cb ("net/mlx5e: SHAMPO, Simplify header page release in teardown") Signed-off-by: Dragos Tatulea Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240815071611.2211873-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 225da8d691fc..23aa555ca0ae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -735,6 +735,7 @@ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq) ksm_entries = bitmap_find_window(shampo->bitmap, shampo->hd_per_wqe, shampo->hd_per_wq, shampo->pi); + ksm_entries = ALIGN_DOWN(ksm_entries, MLX5E_SHAMPO_WQ_HEADER_PER_PAGE); if (!ksm_entries) return 0; From 94e521937839475b83bac46e4d3ccba332e12064 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Thu, 15 Aug 2024 10:16:09 +0300 Subject: [PATCH 378/562] net/mlx5e: SHAMPO, Release in progress headers The change in the fixes tag cleaned up too much: it removed the part that was releasing header pages that were posted via UMR but haven't been acknowledged yet on the ICOSQ. This patch corrects this omission by setting the bits between pi and ci to on when shutting down a queue with SHAMPO. To be consistent with the Striding RQ code, this action is done in mlx5e_free_rx_missing_descs(). Fixes: e839ac9a89cb ("net/mlx5e: SHAMPO, Simplify header page release in teardown") Signed-off-by: Dragos Tatulea Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240815071611.2211873-3-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 + .../net/ethernet/mellanox/mlx5/core/en_main.c | 8 ++++++ .../net/ethernet/mellanox/mlx5/core/en_rx.c | 25 +++++++++++-------- 3 files changed, 24 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index bb5da42edc23..d9e241423bc5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -998,6 +998,7 @@ void mlx5e_build_ptys2ethtool_map(void); bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_shift, enum mlx5e_mpwrq_umr_mode umr_mode); +void mlx5e_shampo_fill_umr(struct mlx5e_rq *rq, int len); void mlx5e_shampo_dealloc_hd(struct mlx5e_rq *rq); void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats); void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5df904639b0c..583fa24a7ae9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1236,6 +1236,14 @@ void mlx5e_free_rx_missing_descs(struct mlx5e_rq *rq) rq->mpwqe.actual_wq_head = wq->head; rq->mpwqe.umr_in_progress = 0; rq->mpwqe.umr_completed = 0; + + if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) { + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; + u16 len; + + len = (shampo->pi - shampo->ci) & shampo->hd_per_wq; + mlx5e_shampo_fill_umr(rq, len); + } } void mlx5e_free_rx_descs(struct mlx5e_rq *rq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 23aa555ca0ae..de9d01036c28 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -963,26 +963,31 @@ void mlx5e_free_icosq_descs(struct mlx5e_icosq *sq) sq->cc = sqcc; } -static void mlx5e_handle_shampo_hd_umr(struct mlx5e_shampo_umr umr, - struct mlx5e_icosq *sq) +void mlx5e_shampo_fill_umr(struct mlx5e_rq *rq, int len) { - struct mlx5e_channel *c = container_of(sq, struct mlx5e_channel, icosq); - struct mlx5e_shampo_hd *shampo; - /* assume 1:1 relationship between RQ and icosq */ - struct mlx5e_rq *rq = &c->rq; - int end, from, len = umr.len; + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; + int end, from, full_len = len; - shampo = rq->mpwqe.shampo; end = shampo->hd_per_wq; from = shampo->ci; - if (from + len > shampo->hd_per_wq) { + if (from + len > end) { len -= end - from; bitmap_set(shampo->bitmap, from, end - from); from = 0; } bitmap_set(shampo->bitmap, from, len); - shampo->ci = (shampo->ci + umr.len) & (shampo->hd_per_wq - 1); + shampo->ci = (shampo->ci + full_len) & (shampo->hd_per_wq - 1); +} + +static void mlx5e_handle_shampo_hd_umr(struct mlx5e_shampo_umr umr, + struct mlx5e_icosq *sq) +{ + struct mlx5e_channel *c = container_of(sq, struct mlx5e_channel, icosq); + /* assume 1:1 relationship between RQ and icosq */ + struct mlx5e_rq *rq = &c->rq; + + mlx5e_shampo_fill_umr(rq, umr.len); } int mlx5e_poll_ico_cq(struct mlx5e_cq *cq) From a07e953dafe5ebd88942dc861dfb06eaf055fb07 Mon Sep 17 00:00:00 2001 From: Carolina Jubran Date: Thu, 15 Aug 2024 10:16:10 +0300 Subject: [PATCH 379/562] net/mlx5e: XPS, Fix oversight of Multi-PF Netdev changes The offending commit overlooked the Multi-PF Netdev changes. Revert mlx5e_set_default_xps_cpumasks to incorporate Multi-PF Netdev changes. Fixes: bcee093751f8 ("net/mlx5e: Modifying channels number and updating TX queues") Signed-off-by: Carolina Jubran Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240815071611.2211873-4-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 583fa24a7ae9..16b67c457b60 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3028,15 +3028,18 @@ int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv) static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv, struct mlx5e_params *params) { - struct mlx5_core_dev *mdev = priv->mdev; - int num_comp_vectors, ix, irq; - - num_comp_vectors = mlx5_comp_vectors_max(mdev); + int ix; for (ix = 0; ix < params->num_channels; ix++) { - cpumask_clear(priv->scratchpad.cpumask); + int num_comp_vectors, irq, vec_ix; + struct mlx5_core_dev *mdev; - for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) { + mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix); + num_comp_vectors = mlx5_comp_vectors_max(mdev); + cpumask_clear(priv->scratchpad.cpumask); + vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix); + + for (irq = vec_ix; irq < num_comp_vectors; irq += params->num_channels) { int cpu = mlx5_comp_vector_get_cpu(mdev, irq); cpumask_set_cpu(cpu, priv->scratchpad.cpumask); From 607e1df7bd47fe91cab85a97f57870a26d066137 Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 15 Aug 2024 10:16:11 +0300 Subject: [PATCH 380/562] net/mlx5: Fix IPsec RoCE MPV trace call Prevent the call trace below from happening, by not allowing IPsec creation over a slave, if master device doesn't support IPsec. WARNING: CPU: 44 PID: 16136 at kernel/locking/rwsem.c:240 down_read+0x75/0x94 Modules linked in: esp4_offload esp4 act_mirred act_vlan cls_flower sch_ingress mlx5_vdpa vringh vhost_iotlb vdpa mst_pciconf(OE) nfsv3 nfs_acl nfs lockd grace fscache netfs xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4 nft_compat nft_counter nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 rfkill cuse fuse rpcrdma sunrpc rdma_ucm ib_srpt ib_isert iscsi_target_mod target_core_mod ib_umad ib_iser libiscsi scsi_transport_iscsi rdma_cm ib_ipoib iw_cm ib_cm ipmi_ssif intel_rapl_msr intel_rapl_common amd64_edac edac_mce_amd kvm_amd kvm irqbypass crct10dif_pclmul crc32_pclmul mlx5_ib ghash_clmulni_intel sha1_ssse3 dell_smbios ib_uverbs aesni_intel crypto_simd dcdbas wmi_bmof dell_wmi_descriptor cryptd pcspkr ib_core acpi_ipmi sp5100_tco ccp i2c_piix4 ipmi_si ptdma k10temp ipmi_devintf ipmi_msghandler acpi_power_meter acpi_cpufreq ext4 mbcache jbd2 sd_mod t10_pi sg mgag200 drm_kms_helper syscopyarea sysfillrect mlx5_core sysimgblt fb_sys_fops cec ahci libahci mlxfw drm pci_hyperv_intf libata tg3 sha256_ssse3 tls megaraid_sas i2c_algo_bit psample wmi dm_mirror dm_region_hash dm_log dm_mod [last unloaded: mst_pci] CPU: 44 PID: 16136 Comm: kworker/44:3 Kdump: loaded Tainted: GOE 5.15.0-20240509.el8uek.uek7_u3_update_v6.6_ipsec_bf.x86_64 #2 Hardware name: Dell Inc. PowerEdge R7525/074H08, BIOS 2.0.3 01/15/2021 Workqueue: events xfrm_state_gc_task RIP: 0010:down_read+0x75/0x94 Code: 00 48 8b 45 08 65 48 8b 14 25 80 fc 01 00 83 e0 02 48 09 d0 48 83 c8 01 48 89 45 08 5d 31 c0 89 c2 89 c6 89 c7 e9 cb 88 3b 00 <0f> 0b 48 8b 45 08 a8 01 74 b2 a8 02 75 ae 48 89 c2 48 83 ca 02 f0 RSP: 0018:ffffb26387773da8 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffffa08b658af900 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ff886bc5e1366f2f RDI: 0000000000000000 RBP: ffffa08b658af940 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffa0a9bfb31540 R13: ffffa0a9bfb37900 R14: 0000000000000000 R15: ffffa0a9bfb37905 FS: 0000000000000000(0000) GS:ffffa0a9bfb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055a45ed814e8 CR3: 000000109038a000 CR4: 0000000000350ee0 Call Trace: ? show_trace_log_lvl+0x1d6/0x2f9 ? show_trace_log_lvl+0x1d6/0x2f9 ? mlx5_devcom_for_each_peer_begin+0x29/0x60 [mlx5_core] ? down_read+0x75/0x94 ? __warn+0x80/0x113 ? down_read+0x75/0x94 ? report_bug+0xa4/0x11d ? handle_bug+0x35/0x8b ? exc_invalid_op+0x14/0x75 ? asm_exc_invalid_op+0x16/0x1b ? down_read+0x75/0x94 ? down_read+0xe/0x94 mlx5_devcom_for_each_peer_begin+0x29/0x60 [mlx5_core] mlx5_ipsec_fs_roce_tx_destroy+0xb1/0x130 [mlx5_core] tx_destroy+0x1b/0xc0 [mlx5_core] tx_ft_put+0x53/0xc0 [mlx5_core] mlx5e_xfrm_free_state+0x45/0x90 [mlx5_core] ___xfrm_state_destroy+0x10f/0x1a2 xfrm_state_gc_task+0x81/0xa9 process_one_work+0x1f1/0x3c6 worker_thread+0x53/0x3e4 ? process_one_work.cold+0x46/0x3c kthread+0x127/0x144 ? set_kthread_struct+0x60/0x52 ret_from_fork+0x22/0x2d ---[ end trace 5ef7896144d398e1 ]--- Fixes: dfbd229abeee ("net/mlx5: Configure IPsec steering for egress RoCEv2 MPV traffic") Reviewed-by: Leon Romanovsky Signed-off-by: Patrisious Haddad Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240815071611.2211873-5-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c index 234cd00f71a1..b7d4b1a2baf2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c @@ -386,7 +386,8 @@ static int ipsec_fs_roce_tx_mpv_create(struct mlx5_core_dev *mdev, return -EOPNOTSUPP; peer_priv = mlx5_devcom_get_next_peer_data(*ipsec_roce->devcom, &tmp); - if (!peer_priv) { + if (!peer_priv || !peer_priv->ipsec) { + mlx5_core_err(mdev, "IPsec not supported on master device\n"); err = -EOPNOTSUPP; goto release_peer; } @@ -455,7 +456,8 @@ static int ipsec_fs_roce_rx_mpv_create(struct mlx5_core_dev *mdev, return -EOPNOTSUPP; peer_priv = mlx5_devcom_get_next_peer_data(*ipsec_roce->devcom, &tmp); - if (!peer_priv) { + if (!peer_priv || !peer_priv->ipsec) { + mlx5_core_err(mdev, "IPsec not supported on master device\n"); err = -EOPNOTSUPP; goto release_peer; } From 0e49d3ff12501adaafaf6fdb19699f021d1eda1c Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 4 May 2024 23:48:58 -0400 Subject: [PATCH 381/562] bcachefs: Fix locking in __bch2_trans_mark_dev_sb() We run this in full RW mode now, so we have to guard against the superblock buffer being reallocated. Signed-off-by: Kent Overstreet --- fs/bcachefs/btree_gc.c | 5 +---- fs/bcachefs/buckets.c | 14 +++++++++----- 2 files changed, 10 insertions(+), 9 deletions(-) diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c index 6cbf2aa6a947..eb3002c4eae7 100644 --- a/fs/bcachefs/btree_gc.c +++ b/fs/bcachefs/btree_gc.c @@ -741,12 +741,9 @@ fsck_err: static int bch2_mark_superblocks(struct bch_fs *c) { - mutex_lock(&c->sb_lock); gc_pos_set(c, gc_phase(GC_PHASE_sb)); - int ret = bch2_trans_mark_dev_sbs_flags(c, BTREE_TRIGGER_gc); - mutex_unlock(&c->sb_lock); - return ret; + return bch2_trans_mark_dev_sbs_flags(c, BTREE_TRIGGER_gc); } static void bch2_gc_free(struct bch_fs *c) diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index ad517ef744e5..be2bbd248631 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -915,7 +915,6 @@ static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans, enum bch_data_type type, unsigned sectors) { - struct bch_fs *c = trans->c; struct btree_iter iter; int ret = 0; @@ -1046,13 +1045,18 @@ static int bch2_trans_mark_metadata_sectors(struct btree_trans *trans, static int __bch2_trans_mark_dev_sb(struct btree_trans *trans, struct bch_dev *ca, enum btree_iter_update_trigger_flags flags) { - struct bch_sb_layout *layout = &ca->disk_sb.sb->layout; + struct bch_fs *c = trans->c; + + mutex_lock(&c->sb_lock); + struct bch_sb_layout layout = ca->disk_sb.sb->layout; + mutex_unlock(&c->sb_lock); + u64 bucket = 0; unsigned i, bucket_sectors = 0; int ret; - for (i = 0; i < layout->nr_superblocks; i++) { - u64 offset = le64_to_cpu(layout->sb_offset[i]); + for (i = 0; i < layout.nr_superblocks; i++) { + u64 offset = le64_to_cpu(layout.sb_offset[i]); if (offset == BCH_SB_SECTOR) { ret = bch2_trans_mark_metadata_sectors(trans, ca, @@ -1063,7 +1067,7 @@ static int __bch2_trans_mark_dev_sb(struct btree_trans *trans, struct bch_dev *c } ret = bch2_trans_mark_metadata_sectors(trans, ca, offset, - offset + (1 << layout->sb_max_size_bits), + offset + (1 << layout.sb_max_size_bits), BCH_DATA_sb, &bucket, &bucket_sectors, flags); if (ret) return ret; From 2fa62ce91a52e704716d08f9a8eb3f9e7e04710d Mon Sep 17 00:00:00 2001 From: Yihang Li Date: Wed, 14 Aug 2024 12:01:24 +0800 Subject: [PATCH 382/562] scsi: MAINTAINERS: Update HiSilicon SAS controller driver maintainer Add Yihang Li as the maintainer of the HiSilicon SAS controller driver, replacing Xiang Chen. Signed-off-by: Yihang Li Link: https://lore.kernel.org/r/20240814040124.1376195-1-liyihang9@huawei.com Signed-off-by: Martin K. Petersen --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 42decde38320..f96bc870a664 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10173,7 +10173,7 @@ F: Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt F: drivers/infiniband/hw/hns/ HISILICON SAS Controller -M: Xiang Chen +M: Yihang Li S: Supported W: http://www.hisilicon.com F: Documentation/devicetree/bindings/scsi/hisilicon-sas.txt From f03e94f23b04c2b71c0044c1534921b3975ef10c Mon Sep 17 00:00:00 2001 From: Chaotian Jing Date: Tue, 13 Aug 2024 13:34:10 +0800 Subject: [PATCH 383/562] scsi: core: Fix the return value of scsi_logical_block_count() scsi_logical_block_count() should return the block count of a given SCSI command. The original implementation ended up shifting twice, leading to an incorrect count being returned. Fix the conversion between bytes and logical blocks. Cc: stable@vger.kernel.org Fixes: 6a20e21ae1e2 ("scsi: core: Add helper to return number of logical blocks in a request") Signed-off-by: Chaotian Jing Link: https://lore.kernel.org/r/20240813053534.7720-1-chaotian.jing@mediatek.com Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/scsi/scsi_cmnd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 45c40d200154..8ecfb94049db 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -234,7 +234,7 @@ static inline sector_t scsi_get_lba(struct scsi_cmnd *scmd) static inline unsigned int scsi_logical_block_count(struct scsi_cmnd *scmd) { - unsigned int shift = ilog2(scmd->device->sector_size) - SECTOR_SHIFT; + unsigned int shift = ilog2(scmd->device->sector_size); return blk_rq_bytes(scsi_cmd_to_rq(scmd)) >> shift; } From a0c9fe5eecc97680323ee83780ea3eaf440ba1b7 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 15 Aug 2024 16:37:13 +0100 Subject: [PATCH 384/562] tc-testing: don't access non-existent variable on exception Since commit 255c1c7279ab ("tc-testing: Allow test cases to be skipped") the variable test_ordinal doesn't exist in call_pre_case(). So it should not be accessed when an exception occurs. This resolves the following splat: ... During handling of the above exception, another exception occurred: Traceback (most recent call last): File ".../tdc.py", line 1028, in main() File ".../tdc.py", line 1022, in main set_operation_mode(pm, parser, args, remaining) File ".../tdc.py", line 966, in set_operation_mode catresults = test_runner_serial(pm, args, alltests) File ".../tdc.py", line 642, in test_runner_serial (index, tsr) = test_runner(pm, args, alltests) File ".../tdc.py", line 536, in test_runner res = run_one_test(pm, args, index, tidx) File ".../tdc.py", line 419, in run_one_test pm.call_pre_case(tidx) File ".../tdc.py", line 146, in call_pre_case print('test_ordinal is {}'.format(test_ordinal)) NameError: name 'test_ordinal' is not defined Fixes: 255c1c7279ab ("tc-testing: Allow test cases to be skipped") Signed-off-by: Simon Horman Acked-by: Jamal Hadi Salim Link: https://patch.msgid.link/20240815-tdc-test-ordinal-v1-1-0255c122a427@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/tc-testing/tdc.py | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index ee349187636f..4f255cec0c22 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -143,7 +143,6 @@ class PluginMgr: except Exception as ee: print('exception {} in call to pre_case for {} plugin'. format(ee, pgn_inst.__class__)) - print('test_ordinal is {}'.format(test_ordinal)) print('testid is {}'.format(caseinfo['id'])) raise From cd06b713a6880997ca5aecac8e33d5f9c541749e Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Fri, 16 Aug 2024 11:55:10 +0530 Subject: [PATCH 385/562] scsi: ufs: core: Add a quirk for handling broken LSDBS field in controller capabilities register 'Legacy Queue & Single Doorbell Support (LSDBS)' field in the controller capabilities register is supposed to report whether the legacy single doorbell mode is supported in the controller or not. But some controllers report '1' in this field which corresponds to 'LSDB not supported', but they indeed support LSDB. So let's add a quirk to handle those controllers. If the quirk is enabled by the controller driver, then LSDBS register field will be ignored and legacy single doorbell mode is assumed to be enabled always. Tested-by: Amit Pundir Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20240816-ufs-bug-fix-v3-1-e6fe0e18e2a3@linaro.org Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufshcd.c | 6 +++++- include/ufs/ufshcd.h | 8 ++++++++ 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 0b3d0c8e0dda..a6f818cdef0e 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2426,7 +2426,11 @@ static inline int ufshcd_hba_capabilities(struct ufs_hba *hba) * 0h: legacy single doorbell support is available * 1h: indicate that legacy single doorbell support has been removed */ - hba->lsdb_sup = !FIELD_GET(MASK_LSDB_SUPPORT, hba->capabilities); + if (!(hba->quirks & UFSHCD_QUIRK_BROKEN_LSDBS_CAP)) + hba->lsdb_sup = !FIELD_GET(MASK_LSDB_SUPPORT, hba->capabilities); + else + hba->lsdb_sup = true; + if (!hba->mcq_sup) return 0; diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index cac0cdb9a916..0fd2aebac728 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -676,6 +676,14 @@ enum ufshcd_quirks { * the standard best practice for managing keys). */ UFSHCD_QUIRK_KEYS_IN_PRDT = 1 << 24, + + /* + * This quirk indicates that the controller reports the value 1 (not + * supported) in the Legacy Single DoorBell Support (LSDBS) bit of the + * Controller Capabilities register although it supports the legacy + * single doorbell mode. + */ + UFSHCD_QUIRK_BROKEN_LSDBS_CAP = 1 << 25, }; enum ufshcd_caps { From ea593e028a9cc523557b4084a61d87ae69e2f270 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Fri, 16 Aug 2024 11:55:11 +0530 Subject: [PATCH 386/562] scsi: ufs: qcom: Add UFSHCD_QUIRK_BROKEN_LSDBS_CAP for SM8550 SoC SM8550 SoC has the UFSHCI 4.0 compliant UFS controller and only supports legacy single doorbell mode without MCQ. But due to a hardware bug, it reports 1 in the 'Legacy Queue & Single Doorbell Support (LSDBS)' field of the Controller Capabilities register. This field is supposed to read as 0 if legacy single doorbell mode is supported and 1 otherwise. Starting with commit 0c60eb0cc320 ("scsi: ufs: core: Check LSDBS cap when !mcq"), ufshcd driver is now relying on the LSDBS field to decide when to use the legacy doorbell mode if MCQ is not supported. And this ends up breaking UFS on SM8550: ufshcd-qcom 1d84000.ufs: ufshcd_init: failed to initialize (legacy doorbell mode not supported) ufshcd-qcom 1d84000.ufs: error -EINVAL: Initialization failed with error -22 So use the UFSHCD_QUIRK_BROKEN_LSDBS_CAP quirk for SM8550 SoC so that the ufshcd driver could use legacy doorbell mode correctly. Fixes: 0c60eb0cc320 ("scsi: ufs: core: Check LSDBS cap when !mcq") Tested-by: Amit Pundir Reviewed-by: Bart Van Assche Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20240816-ufs-bug-fix-v3-2-e6fe0e18e2a3@linaro.org Signed-off-by: Martin K. Petersen --- drivers/ufs/host/ufs-qcom.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 810e637047d0..c87fdc849c62 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -857,6 +857,9 @@ static void ufs_qcom_advertise_quirks(struct ufs_hba *hba) if (host->hw_ver.major > 0x3) hba->quirks |= UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH; + + if (of_device_is_compatible(hba->dev->of_node, "qcom,sm8550-ufshc")) + hba->quirks |= UFSHCD_QUIRK_BROKEN_LSDBS_CAP; } static void ufs_qcom_set_phy_gear(struct ufs_qcom_host *host) @@ -1847,7 +1850,8 @@ static void ufs_qcom_remove(struct platform_device *pdev) } static const struct of_device_id ufs_qcom_of_match[] __maybe_unused = { - { .compatible = "qcom,ufshc"}, + { .compatible = "qcom,ufshc" }, + { .compatible = "qcom,sm8550-ufshc" }, {}, }; MODULE_DEVICE_TABLE(of, ufs_qcom_of_match); From cd612b57c3672487ae8565855eaf9e83862eccc5 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Fri, 16 Aug 2024 13:59:56 +0100 Subject: [PATCH 387/562] scsi: MAINTAINERS: Add header files to SCSI SUBSYSTEM This is part of an effort to assign a section in MAINTAINERS to header files that relate to Networking [1]. In this case the files with "net" in their name. [1] https://lore.kernel.org/netdev/20240816-net-mnt-v1-0-ef946b47ced4@kernel.org/ As part of that effort these files came up: * include/uapi/scsi/scsi_netlink_fc.h * include/uapi/scsi/scsi_netlink.h Unlike all the other matching files, these one seem to relate more closely to SCSI than Networking, so I have added them to the SCSI SUBSYSTEM section. In order to simplify things, and for consistency, I have added the entire include/uapi/scsi rather than the individual files. Signed-off-by: Simon Horman Link: https://lore.kernel.org/r/20240816-scsi-mnt-v1-1-439af8b1c28b@kernel.org Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index f96bc870a664..9a33ab69abab 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -20351,6 +20351,7 @@ F: Documentation/devicetree/bindings/scsi/ F: drivers/scsi/ F: drivers/ufs/ F: include/scsi/ +F: include/uapi/scsi/ SCSI TAPE DRIVER M: Kai Mäkisara From cbaac68987b8699397df29413b33bd51f5255255 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 16 Aug 2024 20:53:10 -0400 Subject: [PATCH 388/562] scsi: sd: Do not attempt to configure discard unless LBPME is set Commit f874d7210d88 ("scsi: sd: Keep the discard mode stable") attempted to address an issue where one mode of discard operation got configured prior to the device completing full discovery. Unfortunately this change assumed discard was always enabled on the device. Do not attempt to configure discard unless LBPME is enabled. Link: https://lore.kernel.org/r/20240817005325.3319384-1-martin.petersen@oracle.com Fixes: f874d7210d88 ("scsi: sd: Keep the discard mode stable") Reported-by: Chris Bainbridge Tested-by: Chris Bainbridge Tested-by: Shin'ichiro Kawasaki Tested-by: John Garry Signed-off-by: Martin K. Petersen --- drivers/scsi/sd.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 699f4f9674d9..dad3991397cf 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3308,6 +3308,9 @@ static void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer) static unsigned int sd_discard_mode(struct scsi_disk *sdkp) { + if (!sdkp->lbpme) + return SD_LBP_FULL; + if (!sdkp->lbpvpd) { /* LBP VPD page not provided */ if (sdkp->max_unmap_blocks) From 3c0da3d163eb32f1f91891efaade027fa9b245b9 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 6 Aug 2024 21:51:42 +0200 Subject: [PATCH 389/562] fuse: Initialize beyond-EOF page contents before setting uptodate fuse_notify_store(), unlike fuse_do_readpage(), does not enable page zeroing (because it can be used to change partial page contents). So fuse_notify_store() must be more careful to fully initialize page contents (including parts of the page that are beyond end-of-file) before marking the page uptodate. The current code can leave beyond-EOF page contents uninitialized, which makes these uninitialized page contents visible to userspace via mmap(). This is an information leak, but only affects systems which do not enable init-on-alloc (via CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y or the corresponding kernel command line parameter). Link: https://bugs.chromium.org/p/project-zero/issues/detail?id=2574 Cc: stable@kernel.org Fixes: a1d75f258230 ("fuse: add store request") Signed-off-by: Jann Horn Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 9eb191b5c4de..7146038b2fe7 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1618,9 +1618,11 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size, this_num = min_t(unsigned, num, PAGE_SIZE - offset); err = fuse_copy_page(cs, &page, offset, this_num, 0); - if (!err && offset == 0 && - (this_num == PAGE_SIZE || file_size == end)) + if (!PageUptodate(page) && !err && offset == 0 && + (this_num == PAGE_SIZE || file_size == end)) { + zero_user_segment(page, this_num, PAGE_SIZE); SetPageUptodate(page); + } unlock_page(page); put_page(page); From 47ac09b91befbb6a235ab620c32af719f8208399 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 18 Aug 2024 13:17:27 -0700 Subject: [PATCH 390/562] Linux 6.11-rc4 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 5f417808213f..68ebd6d6b444 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 11 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Baby Opossum Posse # *DOCUMENTATION* From e4be320eeca842a3d7648258ee3673f1755a5a59 Mon Sep 17 00:00:00 2001 From: Steve French Date: Thu, 15 Aug 2024 18:31:36 -0500 Subject: [PATCH 391/562] smb3: fix broken cached reads when posix locks Mandatory locking is enforced for cached reads, which violates default posix semantics, and also it is enforced inconsistently. This affected recent versions of libreoffice, and can be demonstrated by opening a file twice from the same client, locking it from handle one and trying to read from it from handle two (which fails, returning EACCES). There is already a mount option "forcemandatorylock" (which defaults to off), so with this change only when the user intentionally specifies "forcemandatorylock" on mount will we break posix semantics on read to a locked range (ie we will only fail in this case, if the user mounts with "forcemandatorylock"). An earlier patch fixed the write path. Fixes: 85160e03a79e ("CIFS: Implement caching mechanism for mandatory brlocks") Cc: stable@vger.kernel.org Cc: Pavel Shilovsky Reviewed-by: David Howells Reported-by: abartlet@samba.org Reported-by: Kevin Ottens Signed-off-by: Steve French --- fs/smb/client/file.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 1fc66bcf49eb..f9b302cb8233 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -2912,9 +2912,7 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to) if (!CIFS_CACHE_READ(cinode)) return netfs_unbuffered_read_iter(iocb, to); - if (cap_unix(tcon->ses) && - (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && - ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) { + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0) { if (iocb->ki_flags & IOCB_DIRECT) return netfs_unbuffered_read_iter(iocb, to); return netfs_buffered_read_iter(iocb, to); From dfd046d0ced19b6ff5f11ec4ceab0a83de924771 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 15 Aug 2024 08:56:35 +0900 Subject: [PATCH 392/562] ksmbd: Use unsafe_memcpy() for ntlm_negotiate rsp buffer is allocated larger than spnego_blob from smb2_allocate_rsp_buf(). Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 2df1354288e6..3f4c56a10a86 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1370,7 +1370,8 @@ static int ntlm_negotiate(struct ksmbd_work *work, } sz = le16_to_cpu(rsp->SecurityBufferOffset); - memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, spnego_blob_len); + unsafe_memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, spnego_blob_len, + /* alloc is larger than blob, see smb2_allocate_rsp_buf() */); rsp->SecurityBufferLength = cpu_to_le16(spnego_blob_len); out: @@ -1453,7 +1454,9 @@ static int ntlm_authenticate(struct ksmbd_work *work, return -ENOMEM; sz = le16_to_cpu(rsp->SecurityBufferOffset); - memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, spnego_blob_len); + unsafe_memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, + spnego_blob_len, + /* alloc is larger than blob, see smb2_allocate_rsp_buf() */); rsp->SecurityBufferLength = cpu_to_le16(spnego_blob_len); kfree(spnego_blob); } From 76e98a158b207771a6c9a0de0a60522a446a3447 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sat, 17 Aug 2024 14:03:49 +0900 Subject: [PATCH 393/562] ksmbd: fix race condition between destroy_previous_session() and smb2 operations() If there is ->PreviousSessionId field in the session setup request, The session of the previous connection should be destroyed. During this, if the smb2 operation requests in the previous session are being processed, a racy issue could happen with ksmbd_destroy_file_table(). This patch sets conn->status to KSMBD_SESS_NEED_RECONNECT to block incoming operations and waits until on-going operations are complete (i.e. idle) before desctorying the previous session. Fixes: c8efcc786146 ("ksmbd: add support for durable handles v1/v2") Cc: stable@vger.kernel.org # v6.6+ Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-25040 Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/connection.c | 34 ++++++++++++++++++++++++++++++- fs/smb/server/connection.h | 3 ++- fs/smb/server/mgmt/user_session.c | 9 ++++++++ fs/smb/server/smb2pdu.c | 2 +- 4 files changed, 45 insertions(+), 3 deletions(-) diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index 09e1e7771592..7889df8112b4 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -165,11 +165,43 @@ void ksmbd_all_conn_set_status(u64 sess_id, u32 status) up_read(&conn_list_lock); } -void ksmbd_conn_wait_idle(struct ksmbd_conn *conn, u64 sess_id) +void ksmbd_conn_wait_idle(struct ksmbd_conn *conn) { wait_event(conn->req_running_q, atomic_read(&conn->req_running) < 2); } +int ksmbd_conn_wait_idle_sess_id(struct ksmbd_conn *curr_conn, u64 sess_id) +{ + struct ksmbd_conn *conn; + int rc, retry_count = 0, max_timeout = 120; + int rcount = 1; + +retry_idle: + if (retry_count >= max_timeout) + return -EIO; + + down_read(&conn_list_lock); + list_for_each_entry(conn, &conn_list, conns_list) { + if (conn->binding || xa_load(&conn->sessions, sess_id)) { + if (conn == curr_conn) + rcount = 2; + if (atomic_read(&conn->req_running) >= rcount) { + rc = wait_event_timeout(conn->req_running_q, + atomic_read(&conn->req_running) < rcount, + HZ); + if (!rc) { + up_read(&conn_list_lock); + retry_count++; + goto retry_idle; + } + } + } + } + up_read(&conn_list_lock); + + return 0; +} + int ksmbd_conn_write(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 5c2845e47cf2..5b947175c048 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -145,7 +145,8 @@ extern struct list_head conn_list; extern struct rw_semaphore conn_list_lock; bool ksmbd_conn_alive(struct ksmbd_conn *conn); -void ksmbd_conn_wait_idle(struct ksmbd_conn *conn, u64 sess_id); +void ksmbd_conn_wait_idle(struct ksmbd_conn *conn); +int ksmbd_conn_wait_idle_sess_id(struct ksmbd_conn *curr_conn, u64 sess_id); struct ksmbd_conn *ksmbd_conn_alloc(void); void ksmbd_conn_free(struct ksmbd_conn *conn); bool ksmbd_conn_lookup_dialect(struct ksmbd_conn *c); diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index 162a12685d2c..99416ce9f501 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -311,6 +311,7 @@ void destroy_previous_session(struct ksmbd_conn *conn, { struct ksmbd_session *prev_sess; struct ksmbd_user *prev_user; + int err; down_write(&sessions_table_lock); down_write(&conn->session_lock); @@ -325,8 +326,16 @@ void destroy_previous_session(struct ksmbd_conn *conn, memcmp(user->passkey, prev_user->passkey, user->passkey_sz)) goto out; + ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_RECONNECT); + err = ksmbd_conn_wait_idle_sess_id(conn, id); + if (err) { + ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_NEGOTIATE); + goto out; + } + ksmbd_destroy_file_table(&prev_sess->file_table); prev_sess->state = SMB2_SESSION_EXPIRED; + ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_NEGOTIATE); ksmbd_launch_ksmbd_durable_scavenger(); out: up_write(&conn->session_lock); diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 3f4c56a10a86..cb7f487c96af 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2213,7 +2213,7 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_conn_unlock(conn); ksmbd_close_session_fds(work); - ksmbd_conn_wait_idle(conn, sess_id); + ksmbd_conn_wait_idle(conn); /* * Re-lookup session to validate if session is deleted From 4fdd8664c8a94411a01d11d5ed2f083f105f570a Mon Sep 17 00:00:00 2001 From: Victor Timofei Date: Fri, 16 Aug 2024 22:24:52 +0300 Subject: [PATCH 394/562] ksmbd: fix spelling mistakes in documentation There are a couple of spelling mistakes in the documentation. This patch fixes them. Signed-off-by: Victor Timofei Acked-by: Namjae Jeon Signed-off-by: Steve French --- Documentation/filesystems/smb/ksmbd.rst | 26 ++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/Documentation/filesystems/smb/ksmbd.rst b/Documentation/filesystems/smb/ksmbd.rst index 6b30e43a0d11..67cb68ea6e68 100644 --- a/Documentation/filesystems/smb/ksmbd.rst +++ b/Documentation/filesystems/smb/ksmbd.rst @@ -13,7 +13,7 @@ KSMBD architecture The subset of performance related operations belong in kernelspace and the other subset which belong to operations which are not really related with performance in userspace. So, DCE/RPC management that has historically resulted -into number of buffer overflow issues and dangerous security bugs and user +into a number of buffer overflow issues and dangerous security bugs and user account management are implemented in user space as ksmbd.mountd. File operations that are related with performance (open/read/write/close etc.) in kernel space (ksmbd). This also allows for easier integration with VFS @@ -24,8 +24,8 @@ ksmbd (kernel daemon) When the server daemon is started, It starts up a forker thread (ksmbd/interface name) at initialization time and open a dedicated port 445 -for listening to SMB requests. Whenever new clients make request, Forker -thread will accept the client connection and fork a new thread for dedicated +for listening to SMB requests. Whenever new clients make a request, the Forker +thread will accept the client connection and fork a new thread for a dedicated communication channel between the client and the server. It allows for parallel processing of SMB requests(commands) from clients as well as allowing for new clients to make new connections. Each instance is named ksmbd/1~n(port number) @@ -34,12 +34,12 @@ thread can decide to pass through the commands to the user space (ksmbd.mountd), currently DCE/RPC commands are identified to be handled through the user space. To further utilize the linux kernel, it has been chosen to process the commands as workitems and to be executed in the handlers of the ksmbd-io kworker threads. -It allows for multiplexing of the handlers as the kernel take care of initiating +It allows for multiplexing of the handlers as the kernel takes care of initiating extra worker threads if the load is increased and vice versa, if the load is -decreased it destroys the extra worker threads. So, after connection is -established with client. Dedicated ksmbd/1..n(port number) takes complete +decreased it destroys the extra worker threads. So, after the connection is +established with the client. Dedicated ksmbd/1..n(port number) takes complete ownership of receiving/parsing of SMB commands. Each received command is worked -in parallel i.e., There can be multiple clients commands which are worked in +in parallel i.e., there can be multiple client commands which are worked in parallel. After receiving each command a separated kernel workitem is prepared for each command which is further queued to be handled by ksmbd-io kworkers. So, each SMB workitem is queued to the kworkers. This allows the benefit of load @@ -49,9 +49,9 @@ performance by handling client commands in parallel. ksmbd.mountd (user space daemon) -------------------------------- -ksmbd.mountd is userspace process to, transfer user account and password that +ksmbd.mountd is a userspace process to, transfer the user account and password that are registered using ksmbd.adduser (part of utils for user space). Further it -allows sharing information parameters that parsed from smb.conf to ksmbd in +allows sharing information parameters that are parsed from smb.conf to ksmbd in kernel. For the execution part it has a daemon which is continuously running and connected to the kernel interface using netlink socket, it waits for the requests (dcerpc and share/user info). It handles RPC calls (at a minimum few @@ -124,7 +124,7 @@ How to run 1. Download ksmbd-tools(https://github.com/cifsd-team/ksmbd-tools/releases) and compile them. - - Refer README(https://github.com/cifsd-team/ksmbd-tools/blob/master/README.md) + - Refer to README(https://github.com/cifsd-team/ksmbd-tools/blob/master/README.md) to know how to use ksmbd.mountd/adduser/addshare/control utils $ ./autogen.sh @@ -133,7 +133,7 @@ How to run 2. Create /usr/local/etc/ksmbd/ksmbd.conf file, add SMB share in ksmbd.conf file. - - Refer ksmbd.conf.example in ksmbd-utils, See ksmbd.conf manpage + - Refer to ksmbd.conf.example in ksmbd-utils, See ksmbd.conf manpage for details to configure shares. $ man ksmbd.conf @@ -145,7 +145,7 @@ How to run $ man ksmbd.adduser $ sudo ksmbd.adduser -a -4. Insert ksmbd.ko module after build your kernel. No need to load module +4. Insert the ksmbd.ko module after you build your kernel. No need to load the module if ksmbd is built into the kernel. - Set ksmbd in menuconfig(e.g. $ make menuconfig) @@ -175,7 +175,7 @@ Each layer 1. Enable all component prints # sudo ksmbd.control -d "all" -2. Enable one of components (smb, auth, vfs, oplock, ipc, conn, rdma) +2. Enable one of the components (smb, auth, vfs, oplock, ipc, conn, rdma) # sudo ksmbd.control -d "smb" 3. Show what prints are enabled. From 7c525dddbee71880e654ad44f3917787a4f6042c Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Fri, 16 Aug 2024 19:33:39 +0200 Subject: [PATCH 395/562] ksmbd: Replace one-element arrays with flexible-array members Replace the deprecated one-element arrays with flexible-array members in the structs filesystem_attribute_info and filesystem_device_info. There are no binary differences after this conversion. Link: https://github.com/KSPP/linux/issues/79 Signed-off-by: Thorsten Blum Reviewed-by: Gustavo A. R. Silva Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 4 ++-- fs/smb/server/smb_common.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index cb7f487c96af..0bc9edf22ba4 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -5360,7 +5360,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, "NTFS", PATH_MAX, conn->local_nls, 0); len = len * 2; info->FileSystemNameLen = cpu_to_le32(len); - sz = sizeof(struct filesystem_attribute_info) - 2 + len; + sz = sizeof(struct filesystem_attribute_info) + len; rsp->OutputBufferLength = cpu_to_le32(sz); break; } @@ -5386,7 +5386,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, len = len * 2; info->VolumeLabelSize = cpu_to_le32(len); info->Reserved = 0; - sz = sizeof(struct filesystem_vol_info) - 2 + len; + sz = sizeof(struct filesystem_vol_info) + len; rsp->OutputBufferLength = cpu_to_le32(sz); break; } diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h index 4a3148b0167f..cc1d6dfe29d5 100644 --- a/fs/smb/server/smb_common.h +++ b/fs/smb/server/smb_common.h @@ -213,7 +213,7 @@ struct filesystem_attribute_info { __le32 Attributes; __le32 MaxPathNameComponentLength; __le32 FileSystemNameLen; - __le16 FileSystemName[1]; /* do not have to save this - get subset? */ + __le16 FileSystemName[]; /* do not have to save this - get subset? */ } __packed; struct filesystem_device_info { @@ -226,7 +226,7 @@ struct filesystem_vol_info { __le32 SerialNumber; __le32 VolumeLabelSize; __le16 Reserved; - __le16 VolumeLabel[1]; + __le16 VolumeLabel[]; } __packed; struct filesystem_info { From d6d539c9a7ad0655e5ad46b5e869f1b20bce8953 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 17 Aug 2024 19:51:13 -0400 Subject: [PATCH 396/562] bcachefs: Reallocate table when we're increasing size Fixes: c2f6e16a6771 ("bcachefs: Increase size of cuckoo hash table on too many rehashes") Signed-off-by: Kent Overstreet --- fs/bcachefs/buckets_waiting_for_journal.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/bcachefs/buckets_waiting_for_journal.c b/fs/bcachefs/buckets_waiting_for_journal.c index f70eb2127d32..f9fb150eda70 100644 --- a/fs/bcachefs/buckets_waiting_for_journal.c +++ b/fs/bcachefs/buckets_waiting_for_journal.c @@ -107,7 +107,7 @@ int bch2_set_bucket_needs_journal_commit(struct buckets_waiting_for_journal *b, nr_elements += t->d[i].journal_seq > flushed_seq; new_bits = ilog2(roundup_pow_of_two(nr_elements * 3)); - +realloc: n = kvmalloc(sizeof(*n) + (sizeof(n->d[0]) << new_bits), GFP_KERNEL); if (!n) { ret = -BCH_ERR_ENOMEM_buckets_waiting_for_journal_set; @@ -118,6 +118,8 @@ retry_rehash: if (nr_rehashes_this_size == 3) { new_bits++; nr_rehashes_this_size = 0; + kvfree(n); + goto realloc; } nr_rehashes++; From d9f49c3106e404776afcf6c5682357f4fe088beb Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 17 Aug 2024 16:41:39 -0400 Subject: [PATCH 397/562] bcachefs: fix field-spanning write warning attempts to retrofit memory safety onto C are increasingly annoying ------------[ cut here ]------------ memcpy: detected field-spanning write (size 4) of single field "&k.replicas" at fs/bcachefs/replicas.c:454 (size 3) WARNING: CPU: 5 PID: 6525 at fs/bcachefs/replicas.c:454 bch2_replicas_gc2+0x2cb/0x400 [bcachefs] bch2_replicas_gc2+0x2cb/0x400: bch2_replicas_gc2 at /home/ojab/src/bcachefs/fs/bcachefs/replicas.c:454 (discriminator 3) Modules linked in: dm_mod tun nf_conntrack_netlink nfnetlink xt_addrtype br_netfilter overlay msr sctp bcachefs lz4hc_compress lz4_compress libcrc32c xor raid6_pq lz4_decompress pps_ldisc pps_core wireguard libchacha20poly1305 chacha_x86_64 poly1305_x86_64 ip6_udp_tunnel udp_tunnel curve25519_x86_64 libcurve25519_generic libchacha sit tunnel4 ip_tunnel af_packet bridge stp llc ip6table_nat ip6table_filter ip6_tables xt_MASQUERADE xt_conntrack iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 iptable_filter ip_tables x_tables tcp_bbr sch_fq_codel efivarfs nls_iso8859_1 nls_cp437 vfat fat cdc_mbim cdc_wdm cdc_ncm cdc_ether usbnet r8152 input_leds joydev mii amdgpu mousedev hid_generic usbhid hid ath10k_pci amd_atl edac_mce_amd ath10k_core kvm_amd ath kvm mac80211 bfq crc32_pclmul crc32c_intel polyval_clmulni polyval_generic sha512_ssse3 sha256_ssse3 sha1_ssse3 snd_hda_codec_generic snd_hda_codec_hdmi snd_hda_intel snd_intel_dspcfg i2c_algo_bit drm_exec snd_hda_codec r8169 drm_suballoc_helper aesni_intel gf128mul crypto_simd amdxcp realtek mfd_core tpm_crb drm_buddy snd_hwdep mdio_devres libarc4 cryptd tpm_tis wmi_bmof cfg80211 evdev libphy snd_hda_core tpm_tis_core gpu_sched rapl xhci_pci xhci_hcd snd_pcm drm_display_helper snd_timer tpm sp5100_tco rfkill efi_pstore mpt3sas drm_ttm_helper ahci usbcore libaescfb ccp snd ttm 8250 libahci watchdog soundcore raid_class sha1_generic acpi_cpufreq k10temp 8250_base usb_common scsi_transport_sas i2c_piix4 hwmon video serial_mctrl_gpio serial_base ecdh_generic wmi rtc_cmos backlight ecc gpio_amdpt rng_core gpio_generic button CPU: 5 UID: 0 PID: 6525 Comm: bcachefs Tainted: G W 6.11.0-rc1-ojab-00058-g224bc118aec9 #6 6d5debde398d2a84851f42ab300dae32c2992027 Tainted: [W]=WARN RIP: 0010:bch2_replicas_gc2+0x2cb/0x400 [bcachefs] Code: c7 c2 60 91 d1 c1 48 89 c6 48 c7 c7 98 91 d1 c1 4c 89 14 24 44 89 5c 24 08 48 89 44 24 20 c6 05 fa 68 04 00 01 e8 05 a3 40 e4 <0f> 0b 4c 8b 14 24 44 8b 5c 24 08 48 8b 44 24 20 e9 55 fe ff ff 8b RSP: 0018:ffffb434c9263d60 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff9a8efa79cc00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffb434c9263de0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000005 R13: ffff9a8efa73c300 R14: ffff9a8d9e880000 R15: ffff9a8d9e8806f8 FS: 0000000000000000(0000) GS:ffff9a9410c80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000565423373090 CR3: 0000000164e30000 CR4: 00000000003506f0 Call Trace: ? __warn+0x97/0x150 ? bch2_replicas_gc2+0x2cb/0x400 [bcachefs 9803eca5e131ef28f26250ede34072d5b50d98b3] bch2_replicas_gc2+0x2cb/0x400: bch2_replicas_gc2 at /home/ojab/src/bcachefs/fs/bcachefs/replicas.c:454 (discriminator 3) ? report_bug+0x196/0x1c0 ? handle_bug+0x3c/0x70 ? exc_invalid_op+0x17/0x80 ? __wake_up_klogd.part.0+0x4c/0x80 ? asm_exc_invalid_op+0x16/0x20 ? bch2_replicas_gc2+0x2cb/0x400 [bcachefs 9803eca5e131ef28f26250ede34072d5b50d98b3] bch2_replicas_gc2+0x2cb/0x400: bch2_replicas_gc2 at /home/ojab/src/bcachefs/fs/bcachefs/replicas.c:454 (discriminator 3) ? bch2_dev_usage_read+0xa0/0xa0 [bcachefs 9803eca5e131ef28f26250ede34072d5b50d98b3] bch2_dev_usage_read+0xa0/0xa0: discard_in_flight_remove at /home/ojab/src/bcachefs/fs/bcachefs/alloc_background.c:1712 Signed-off-by: Kent Overstreet --- fs/bcachefs/replicas.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/bcachefs/replicas.c b/fs/bcachefs/replicas.c index 1223b710755d..12b1d28b7eb4 100644 --- a/fs/bcachefs/replicas.c +++ b/fs/bcachefs/replicas.c @@ -451,7 +451,8 @@ retry: .type = BCH_DISK_ACCOUNTING_replicas, }; - memcpy(&k.replicas, e, replicas_entry_bytes(e)); + unsafe_memcpy(&k.replicas, e, replicas_entry_bytes(e), + "embedded variable length struct"); struct bpos p = disk_accounting_pos_to_bpos(&k); From 47cdc7b14417a40af6a5d5909f1d28a5a23fc11d Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 17 Aug 2024 17:38:43 -0400 Subject: [PATCH 398/562] bcachefs: Fix incorrect gfp flags fixes: 00488 WARNING: CPU: 9 PID: 194 at mm/page_alloc.c:4410 __alloc_pages_noprof+0x1818/0x1888 00488 Modules linked in: 00488 CPU: 9 UID: 0 PID: 194 Comm: kworker/u66:1 Not tainted 6.11.0-rc1-ktest-g18fa10d6495f #2931 00488 Hardware name: linux,dummy-virt (DT) 00488 Workqueue: writeback wb_workfn (flush-bcachefs-2) 00488 pstate: 20001005 (nzCv daif -PAN -UAO -TCO -DIT +SSBS BTYPE=--) 00488 pc : __alloc_pages_noprof+0x1818/0x1888 00488 lr : __alloc_pages_noprof+0x5f4/0x1888 00488 sp : ffffff80ccd8ed00 00488 x29: ffffff80ccd8ed00 x28: 0000000000000000 x27: dfffffc000000000 00488 x26: 0000000000000010 x25: 0000000000000002 x24: 0000000000000000 00488 x23: 0000000000000000 x22: 1ffffff0199b1dbe x21: ffffff80cc680900 00488 x20: 0000000000000000 x19: ffffff80ccd8eed0 x18: 0000000000000000 00488 x17: ffffff80cc58a010 x16: dfffffc000000000 x15: 1ffffff00474e518 00488 x14: 1ffffff00474e518 x13: 1ffffff00474e518 x12: ffffffb8104701b9 00488 x11: 1ffffff8104701b8 x10: ffffffb8104701b8 x9 : ffffffc08043cde8 00488 x8 : 00000047efb8fe48 x7 : ffffff80ccd8ee20 x6 : 0000000000048000 00488 x5 : 1ffffff810470138 x4 : 0000000000000050 x3 : 1ffffff0199b1d94 00488 x2 : ffffffb0199b1d94 x1 : 0000000000000001 x0 : ffffffc082387448 00488 Call trace: 00488 __alloc_pages_noprof+0x1818/0x1888 00488 new_slab+0x284/0x2f0 00488 ___slab_alloc+0x208/0x8e0 00488 __kmalloc_noprof+0x328/0x340 00488 __bch2_writepage+0x106c/0x1830 00488 write_cache_pages+0xa0/0xe8 due to __GFP_NOFAIL without allowing reclaim Signed-off-by: Kent Overstreet --- fs/bcachefs/fs-io-buffered.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c index cc33d763f722..184d03851676 100644 --- a/fs/bcachefs/fs-io-buffered.c +++ b/fs/bcachefs/fs-io-buffered.c @@ -534,7 +534,7 @@ do_io: if (f_sectors > w->tmp_sectors) { kfree(w->tmp); - w->tmp = kcalloc(f_sectors, sizeof(struct bch_folio_sector), __GFP_NOFAIL); + w->tmp = kcalloc(f_sectors, sizeof(struct bch_folio_sector), GFP_NOFS|__GFP_NOFAIL); w->tmp_sectors = f_sectors; } From 5b5c96c63d5b6e91c622611e04b2b156bbae53f5 Mon Sep 17 00:00:00 2001 From: Hongzhen Luo Date: Thu, 1 Aug 2024 19:26:22 +0800 Subject: [PATCH 399/562] erofs: simplify readdir operation - Use i_size instead of i_size_read() due to immutable fses; - Get rid of an unneeded goto since erofs_fill_dentries() also works; - Remove unnecessary lines. Signed-off-by: Hongzhen Luo Link: https://lore.kernel.org/r/20240801112622.2164029-1-hongzhen@linux.alibaba.com Reviewed-by: Gao Xiang Signed-off-by: Gao Xiang --- fs/erofs/dir.c | 35 ++++++++++++----------------------- fs/erofs/internal.h | 2 +- 2 files changed, 13 insertions(+), 24 deletions(-) diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c index 2193a6710c8f..c3b90abdee37 100644 --- a/fs/erofs/dir.c +++ b/fs/erofs/dir.c @@ -8,19 +8,15 @@ static int erofs_fill_dentries(struct inode *dir, struct dir_context *ctx, void *dentry_blk, struct erofs_dirent *de, - unsigned int nameoff, unsigned int maxsize) + unsigned int nameoff0, unsigned int maxsize) { - const struct erofs_dirent *end = dentry_blk + nameoff; + const struct erofs_dirent *end = dentry_blk + nameoff0; while (de < end) { - const char *de_name; + unsigned char d_type = fs_ftype_to_dtype(de->file_type); + unsigned int nameoff = le16_to_cpu(de->nameoff); + const char *de_name = (char *)dentry_blk + nameoff; unsigned int de_namelen; - unsigned char d_type; - - d_type = fs_ftype_to_dtype(de->file_type); - - nameoff = le16_to_cpu(de->nameoff); - de_name = (char *)dentry_blk + nameoff; /* the last dirent in the block? */ if (de + 1 >= end) @@ -52,21 +48,20 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx) struct erofs_buf buf = __EROFS_BUF_INITIALIZER; struct super_block *sb = dir->i_sb; unsigned long bsz = sb->s_blocksize; - const size_t dirsize = i_size_read(dir); - unsigned int i = erofs_blknr(sb, ctx->pos); unsigned int ofs = erofs_blkoff(sb, ctx->pos); int err = 0; bool initial = true; buf.mapping = dir->i_mapping; - while (ctx->pos < dirsize) { + while (ctx->pos < dir->i_size) { + erofs_off_t dbstart = ctx->pos - ofs; struct erofs_dirent *de; unsigned int nameoff, maxsize; - de = erofs_bread(&buf, erofs_pos(sb, i), EROFS_KMAP); + de = erofs_bread(&buf, dbstart, EROFS_KMAP); if (IS_ERR(de)) { erofs_err(sb, "fail to readdir of logical block %u of nid %llu", - i, EROFS_I(dir)->nid); + erofs_blknr(sb, dbstart), EROFS_I(dir)->nid); err = PTR_ERR(de); break; } @@ -79,25 +74,19 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx) break; } - maxsize = min_t(unsigned int, dirsize - ctx->pos + ofs, bsz); - + maxsize = min_t(unsigned int, dir->i_size - dbstart, bsz); /* search dirents at the arbitrary position */ if (initial) { initial = false; - ofs = roundup(ofs, sizeof(struct erofs_dirent)); - ctx->pos = erofs_pos(sb, i) + ofs; - if (ofs >= nameoff) - goto skip_this; + ctx->pos = dbstart + ofs; } err = erofs_fill_dentries(dir, ctx, de, (void *)de + ofs, nameoff, maxsize); if (err) break; -skip_this: - ctx->pos = erofs_pos(sb, i) + maxsize; - ++i; + ctx->pos = dbstart + maxsize; ofs = 0; } erofs_put_metabuf(&buf); diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 736607675396..45dc15ebd870 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -220,7 +220,7 @@ struct erofs_buf { }; #define __EROFS_BUF_INITIALIZER ((struct erofs_buf){ .page = NULL }) -#define erofs_blknr(sb, addr) ((addr) >> (sb)->s_blocksize_bits) +#define erofs_blknr(sb, addr) ((erofs_blk_t)((addr) >> (sb)->s_blocksize_bits)) #define erofs_blkoff(sb, addr) ((addr) & ((sb)->s_blocksize - 1)) #define erofs_pos(sb, blk) ((erofs_off_t)(blk) << (sb)->s_blocksize_bits) #define erofs_iblks(i) (round_up((i)->i_size, i_blocksize(i)) >> (i)->i_blkbits) From 2c534624ae70100aeea0b5800b0f3768b2fd3cf0 Mon Sep 17 00:00:00 2001 From: Hongzhen Luo Date: Tue, 6 Aug 2024 19:22:08 +0800 Subject: [PATCH 400/562] erofs: get rid of check_layout_compatibility() Simple enough to just open-code it. Signed-off-by: Hongzhen Luo Reviewed-by: Sandeep Dhavale Reviewed-by: Gao Xiang Link: https://lore.kernel.org/r/20240806112208.150323-1-hongzhen@linux.alibaba.com Signed-off-by: Gao Xiang --- fs/erofs/super.c | 26 ++++++-------------------- 1 file changed, 6 insertions(+), 20 deletions(-) diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 32ce5b35e1df..6cb5c8916174 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -108,22 +108,6 @@ static void erofs_free_inode(struct inode *inode) kmem_cache_free(erofs_inode_cachep, vi); } -static bool check_layout_compatibility(struct super_block *sb, - struct erofs_super_block *dsb) -{ - const unsigned int feature = le32_to_cpu(dsb->feature_incompat); - - EROFS_SB(sb)->feature_incompat = feature; - - /* check if current kernel meets all mandatory requirements */ - if (feature & (~EROFS_ALL_FEATURE_INCOMPAT)) { - erofs_err(sb, "unidentified incompatible feature %x, please upgrade kernel", - feature & ~EROFS_ALL_FEATURE_INCOMPAT); - return false; - } - return true; -} - /* read variable-sized metadata, offset will be aligned by 4-byte */ void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, erofs_off_t *offset, int *lengthp) @@ -279,7 +263,7 @@ static int erofs_scan_devices(struct super_block *sb, static int erofs_read_superblock(struct super_block *sb) { - struct erofs_sb_info *sbi; + struct erofs_sb_info *sbi = EROFS_SB(sb); struct erofs_buf buf = __EROFS_BUF_INITIALIZER; struct erofs_super_block *dsb; void *data; @@ -291,9 +275,7 @@ static int erofs_read_superblock(struct super_block *sb) return PTR_ERR(data); } - sbi = EROFS_SB(sb); dsb = (struct erofs_super_block *)(data + EROFS_SUPER_OFFSET); - ret = -EINVAL; if (le32_to_cpu(dsb->magic) != EROFS_SUPER_MAGIC_V1) { erofs_err(sb, "cannot find valid erofs superblock"); @@ -318,8 +300,12 @@ static int erofs_read_superblock(struct super_block *sb) } ret = -EINVAL; - if (!check_layout_compatibility(sb, dsb)) + sbi->feature_incompat = le32_to_cpu(dsb->feature_incompat); + if (sbi->feature_incompat & ~EROFS_ALL_FEATURE_INCOMPAT) { + erofs_err(sb, "unidentified incompatible feature %x, please upgrade kernel", + sbi->feature_incompat & ~EROFS_ALL_FEATURE_INCOMPAT); goto out; + } sbi->sb_size = 128 + dsb->sb_extslots * EROFS_SB_EXTSLOT_SIZE; if (sbi->sb_size > PAGE_SIZE - EROFS_SUPER_OFFSET) { From 7ce7c2283fa6843ab3c2adfeb83dcc504a107858 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 14 Aug 2024 12:06:19 +0200 Subject: [PATCH 401/562] Input: i8042 - add Fujitsu Lifebook E756 to i8042 quirk table Yet another quirk entry for Fujitsu laptop. Lifebook E756 requires i8041.nomux for keeping the touchpad working after suspend/resume. Link: https://bugzilla.suse.com/show_bug.cgi?id=1229056 Signed-off-by: Takashi Iwai Link: https://lore.kernel.org/r/20240814100630.2048-1-tiwai@suse.de Signed-off-by: Dmitry Torokhov --- drivers/input/serio/i8042-acpipnpio.h | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 5b50475ec414..78e5c9c60b8b 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -626,6 +626,15 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { }, .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, + { + /* Fujitsu Lifebook E756 */ + /* https://bugzilla.suse.com/show_bug.cgi?id=1229056 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E756"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, { /* Fujitsu Lifebook E5411 */ .matches = { From 5d41eeb6725e3e24853629e5d7635e4bc45d736e Mon Sep 17 00:00:00 2001 From: Suraj Kandpal Date: Fri, 9 Aug 2024 17:11:28 +0530 Subject: [PATCH 402/562] drm/i915/hdcp: Use correct cp_irq_count We are checking cp_irq_count from the wrong hdcp structure which ends up giving timed out errors. We only increment the cp_irq_count of the primary connector's hdcp structure but here in case of multidisplay setup we end up checking the secondary connector's hdcp structure, which will not have its cp_irq_count incremented. This leads to a timed out at CP_IRQ error even though a CP_IRQ was raised. Extract it from the correct intel_hdcp structure. --v2 -Explain why it was the wrong hdcp structure [Jani] Fixes: 8c9e4f68b861 ("drm/i915/hdcp: Use per-device debugs") Signed-off-by: Suraj Kandpal Reviewed-by: Ankit Nautiyal Link: https://patchwork.freedesktop.org/patch/msgid/20240809114127.3940699-2-suraj.kandpal@intel.com (cherry picked from commit dd925902634def895690426bf10e0a8b3e56f56d) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/display/intel_dp_hdcp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c index 2edffe62f360..b0101d72b9c1 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c @@ -39,7 +39,9 @@ static u32 transcoder_to_stream_enc_status(enum transcoder cpu_transcoder) static void intel_dp_hdcp_wait_for_cp_irq(struct intel_connector *connector, int timeout) { - struct intel_hdcp *hdcp = &connector->hdcp; + struct intel_digital_port *dig_port = intel_attached_dig_port(connector); + struct intel_dp *dp = &dig_port->dp; + struct intel_hdcp *hdcp = &dp->attached_connector->hdcp; long ret; #define C (hdcp->cp_irq_count_cached != atomic_read(&hdcp->cp_irq_count)) From 3d765ae2daccc570b3f4fbcb57eb321b12cdded2 Mon Sep 17 00:00:00 2001 From: Werner Sembach Date: Thu, 4 Jan 2024 19:31:17 +0100 Subject: [PATCH 403/562] Input: i8042 - add forcenorestore quirk to leave controller untouched even on s3 On s3 resume the i8042 driver tries to restore the controller to a known state by reinitializing things, however this can confuse the controller with different effects. Mostly occasionally unresponsive keyboards after resume. These issues do not rise on s0ix resume as here the controller is assumed to preserved its state from before suspend. This patch adds a quirk for devices where the reinitialization on s3 resume is not needed and might be harmful as described above. It does this by using the s0ix resume code path at selected locations. This new quirk goes beyond what the preexisting reset=never quirk does, which only skips some reinitialization steps. Signed-off-by: Werner Sembach Cc: stable@vger.kernel.org Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20240104183118.779778-2-wse@tuxedocomputers.com Signed-off-by: Dmitry Torokhov --- drivers/input/serio/i8042-acpipnpio.h | 10 +++++++--- drivers/input/serio/i8042.c | 10 +++++++--- 2 files changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 78e5c9c60b8b..00e804301088 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -83,6 +83,7 @@ static inline void i8042_write_command(int val) #define SERIO_QUIRK_KBDRESET BIT(12) #define SERIO_QUIRK_DRITEK BIT(13) #define SERIO_QUIRK_NOPNP BIT(14) +#define SERIO_QUIRK_FORCENORESTORE BIT(15) /* Quirk table for different mainboards. Options similar or identical to i8042 * module parameters. @@ -1694,6 +1695,8 @@ static void __init i8042_check_quirks(void) if (quirks & SERIO_QUIRK_NOPNP) i8042_nopnp = true; #endif + if (quirks & SERIO_QUIRK_FORCENORESTORE) + i8042_forcenorestore = true; } #else static inline void i8042_check_quirks(void) {} @@ -1727,7 +1730,7 @@ static int __init i8042_platform_init(void) i8042_check_quirks(); - pr_debug("Active quirks (empty means none):%s%s%s%s%s%s%s%s%s%s%s%s%s\n", + pr_debug("Active quirks (empty means none):%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n", i8042_nokbd ? " nokbd" : "", i8042_noaux ? " noaux" : "", i8042_nomux ? " nomux" : "", @@ -1747,10 +1750,11 @@ static int __init i8042_platform_init(void) "", #endif #ifdef CONFIG_PNP - i8042_nopnp ? " nopnp" : ""); + i8042_nopnp ? " nopnp" : "", #else - ""); + "", #endif + i8042_forcenorestore ? " forcenorestore" : ""); retval = i8042_pnp_init(); if (retval) diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index e0fb1db653b7..8ec4872b4471 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -115,6 +115,10 @@ module_param_named(nopnp, i8042_nopnp, bool, 0); MODULE_PARM_DESC(nopnp, "Do not use PNP to detect controller settings"); #endif +static bool i8042_forcenorestore; +module_param_named(forcenorestore, i8042_forcenorestore, bool, 0); +MODULE_PARM_DESC(forcenorestore, "Force no restore on s3 resume, copying s2idle behaviour"); + #define DEBUG #ifdef DEBUG static bool i8042_debug; @@ -1232,7 +1236,7 @@ static int i8042_pm_suspend(struct device *dev) { int i; - if (pm_suspend_via_firmware()) + if (!i8042_forcenorestore && pm_suspend_via_firmware()) i8042_controller_reset(true); /* Set up serio interrupts for system wakeup. */ @@ -1248,7 +1252,7 @@ static int i8042_pm_suspend(struct device *dev) static int i8042_pm_resume_noirq(struct device *dev) { - if (!pm_resume_via_firmware()) + if (i8042_forcenorestore || !pm_resume_via_firmware()) i8042_interrupt(0, NULL); return 0; @@ -1271,7 +1275,7 @@ static int i8042_pm_resume(struct device *dev) * not restore the controller state to whatever it had been at boot * time, so we do not need to do anything. */ - if (!pm_suspend_via_firmware()) + if (i8042_forcenorestore || !pm_suspend_via_firmware()) return 0; /* From aaa4ca873d3da768896ffc909795359a01e853ef Mon Sep 17 00:00:00 2001 From: Werner Sembach Date: Thu, 4 Jan 2024 19:31:18 +0100 Subject: [PATCH 404/562] Input: i8042 - use new forcenorestore quirk to replace old buggy quirk combination The old quirk combination sometimes cause a laggy keyboard after boot. With the new quirk the initial issue of an unresponsive keyboard after s3 resume is also fixed, but it doesn't have the negative side effect of the sometimes laggy keyboard. Signed-off-by: Werner Sembach Cc: stable@vger.kernel.org Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20240104183118.779778-3-wse@tuxedocomputers.com Signed-off-by: Dmitry Torokhov --- drivers/input/serio/i8042-acpipnpio.h | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 00e804301088..bad238f69a7a 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -1159,18 +1159,10 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, { - /* - * Setting SERIO_QUIRK_NOMUX or SERIO_QUIRK_RESET_ALWAYS makes - * the keyboard very laggy for ~5 seconds after boot and - * sometimes also after resume. - * However both are required for the keyboard to not fail - * completely sometimes after boot or resume. - */ .matches = { DMI_MATCH(DMI_BOARD_NAME, "N150CU"), }, - .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | - SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + .driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE) }, { .matches = { From a9aaf1ff88a8cb99a1335c9eb76de637f0cf8c10 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 13 Aug 2024 21:07:50 +0200 Subject: [PATCH 405/562] power: sequencing: request the WLAN enable GPIO as-is If the WCN module is powered up before linux boots and the ath11k driver probes at the same time as the power sequencing driver, we may end up driving the wlan-enable GPIO low in the latter, breaking the start-up of the WLAN module. Request the wlan-enable GPIO as-is so that if the WLAN module is already starting/started, we leave it alone. Fixes: 2f1630f437df ("power: pwrseq: add a driver for the PMU module on the QCom WCN chipsets") Reported-by: Stephan Gerhold Link: https://lore.kernel.org/r/20240813190751.155035-1-brgl@bgdev.pl Signed-off-by: Bartosz Golaszewski --- drivers/power/sequencing/pwrseq-qcom-wcn.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/sequencing/pwrseq-qcom-wcn.c b/drivers/power/sequencing/pwrseq-qcom-wcn.c index 42dacfda745e..d786cbf1b2cd 100644 --- a/drivers/power/sequencing/pwrseq-qcom-wcn.c +++ b/drivers/power/sequencing/pwrseq-qcom-wcn.c @@ -283,7 +283,7 @@ static int pwrseq_qcom_wcn_probe(struct platform_device *pdev) "Failed to get the Bluetooth enable GPIO\n"); ctx->wlan_gpio = devm_gpiod_get_optional(dev, "wlan-enable", - GPIOD_OUT_LOW); + GPIOD_ASIS); if (IS_ERR(ctx->wlan_gpio)) return dev_err_probe(dev, PTR_ERR(ctx->wlan_gpio), "Failed to get the WLAN enable GPIO\n"); From e080a26725fb36f535f22ea42694c60ab005fb2e Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Mon, 19 Aug 2024 10:52:07 +0800 Subject: [PATCH 406/562] erofs: allow large folios for compressed files As commit 2e6506e1c4ee ("mm/migrate: fix deadlock in migrate_pages_batch() on large folios") has landed upstream, large folios can be safely enabled for compressed inodes since all prerequisites have already landed in 6.11-rc1. Stress tests has been running on my fleet for over 20 days without any regression. Additionally, users [1] have requested it for months. Let's allow large folios for EROFS full cases upstream now for wider testing. [1] https://lore.kernel.org/r/CAGsJ_4wtE8OcpinuqVwG4jtdx6Qh5f+TON6wz+4HMCq=A2qFcA@mail.gmail.com Cc: Barry Song <21cnbao@gmail.com> Cc: Matthew Wilcox (Oracle) [ Gao Xiang: minor commit typo fixes. ] Signed-off-by: Gao Xiang Link: https://lore.kernel.org/r/20240819025207.3808649-1-hsiangkao@linux.alibaba.com --- Documentation/filesystems/erofs.rst | 2 +- fs/erofs/inode.c | 20 +++++++++----------- 2 files changed, 10 insertions(+), 12 deletions(-) diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst index cc4626d6ee4f..c293f8e37468 100644 --- a/Documentation/filesystems/erofs.rst +++ b/Documentation/filesystems/erofs.rst @@ -75,7 +75,7 @@ Here are the main features of EROFS: - Support merging tail-end data into a special inode as fragments. - - Support large folios for uncompressed files. + - Support large folios to make use of THPs (Transparent Hugepages); - Support direct I/O on uncompressed files to avoid double caching for loop devices; diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index 43c09aae2afc..419432be3223 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -257,25 +257,23 @@ static int erofs_fill_inode(struct inode *inode) goto out_unlock; } + mapping_set_large_folios(inode->i_mapping); if (erofs_inode_is_data_compressed(vi->datalayout)) { #ifdef CONFIG_EROFS_FS_ZIP DO_ONCE_LITE_IF(inode->i_blkbits != PAGE_SHIFT, erofs_info, inode->i_sb, "EXPERIMENTAL EROFS subpage compressed block support in use. Use at your own risk!"); inode->i_mapping->a_ops = &z_erofs_aops; - err = 0; - goto out_unlock; -#endif +#else err = -EOPNOTSUPP; - goto out_unlock; - } - inode->i_mapping->a_ops = &erofs_raw_access_aops; - mapping_set_large_folios(inode->i_mapping); -#ifdef CONFIG_EROFS_FS_ONDEMAND - if (erofs_is_fscache_mode(inode->i_sb)) - inode->i_mapping->a_ops = &erofs_fscache_access_aops; #endif - + } else { + inode->i_mapping->a_ops = &erofs_raw_access_aops; +#ifdef CONFIG_EROFS_FS_ONDEMAND + if (erofs_is_fscache_mode(inode->i_sb)) + inode->i_mapping->a_ops = &erofs_fscache_access_aops; +#endif + } out_unlock: erofs_put_metabuf(&buf); return err; From 7167395a4be7930ecac6a33b4e54d7e3dd9ee209 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Thu, 15 Aug 2024 15:59:50 +0800 Subject: [PATCH 407/562] selftests: udpgro: report error when receive failed Currently, we only check the latest senders's exit code. If the receiver report failed, it is not recoreded. Fix it by checking the exit code of all the involved processes. Before: bad GRO lookup ok multiple GRO socks ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520 ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520 failed $ echo $? 0 After: bad GRO lookup ok multiple GRO socks ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520 ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520 failed $ echo $? 1 Fixes: 3327a9c46352 ("selftests: add functionals test for UDP GRO") Suggested-by: Paolo Abeni Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- tools/testing/selftests/net/udpgro.sh | 44 ++++++++++++++++----------- 1 file changed, 27 insertions(+), 17 deletions(-) diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index 11a1ebda564f..4659cf01e438 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -46,17 +46,19 @@ run_one() { local -r all="$@" local -r tx_args=${all%rx*} local -r rx_args=${all#*rx} + local ret=0 cfg_veth - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} && \ - echo "ok" || \ - echo "failed" & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} & + local PID1=$! wait_local_port_listen ${PEER_NS} 8000 udp ./udpgso_bench_tx ${tx_args} - ret=$? - wait $(jobs -p) + check_err $? + wait ${PID1} + check_err $? + [ "$ret" -eq 0 ] && echo "ok" || echo "failed" return $ret } @@ -73,6 +75,7 @@ run_one_nat() { local -r all="$@" local -r tx_args=${all%rx*} local -r rx_args=${all#*rx} + local ret=0 if [[ ${tx_args} = *-4* ]]; then ipt_cmd=iptables @@ -93,16 +96,17 @@ run_one_nat() { # ... so that GRO will match the UDP_GRO enabled socket, but packets # will land on the 'plain' one ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 & - pid=$! - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} && \ - echo "ok" || \ - echo "failed"& + local PID1=$! + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} & + local PID2=$! wait_local_port_listen "${PEER_NS}" 8000 udp ./udpgso_bench_tx ${tx_args} - ret=$? - kill -INT $pid - wait $(jobs -p) + check_err $? + kill -INT ${PID1} + wait ${PID2} + check_err $? + [ "$ret" -eq 0 ] && echo "ok" || echo "failed" return $ret } @@ -111,20 +115,26 @@ run_one_2sock() { local -r all="$@" local -r tx_args=${all%rx*} local -r rx_args=${all#*rx} + local ret=0 cfg_veth ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} -p 12345 & - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} && \ - echo "ok" || \ - echo "failed" & + local PID1=$! + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} & + local PID2=$! wait_local_port_listen "${PEER_NS}" 12345 udp ./udpgso_bench_tx ${tx_args} -p 12345 + check_err $? wait_local_port_listen "${PEER_NS}" 8000 udp ./udpgso_bench_tx ${tx_args} - ret=$? - wait $(jobs -p) + check_err $? + wait ${PID1} + check_err $? + wait ${PID2} + check_err $? + [ "$ret" -eq 0 ] && echo "ok" || echo "failed" return $ret } From d7818402b1d80347c764001583f6d63fa68c2e1a Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Thu, 15 Aug 2024 15:59:51 +0800 Subject: [PATCH 408/562] selftests: udpgro: no need to load xdp for gro MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After commit d7db7775ea2e ("net: veth: do not manipulate GRO when using XDP"), there is no need to load XDP program to enable GRO. On the other hand, the current test is failed due to loading the XDP program. e.g. # selftests: net: udpgro.sh # ipv4 # no GRO ok # no GRO chk cmsg ok # GRO ./udpgso_bench_rx: recv: bad packet len, got 1472, expected 14720 # # failed [...] # bad GRO lookup ok # multiple GRO socks ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520 # # ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520 # # failed ok 1 selftests: net: udpgro.sh After fix, all the test passed. # ./udpgro.sh ipv4 no GRO ok [...] multiple GRO socks ok Fixes: d7db7775ea2e ("net: veth: do not manipulate GRO when using XDP") Reported-by: Yi Chen Closes: https://issues.redhat.com/browse/RHEL-53858 Reviewed-by: Toke Høiland-Jørgensen Acked-by: Paolo Abeni Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- tools/testing/selftests/net/udpgro.sh | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index 4659cf01e438..d5ffd8c9172e 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -7,8 +7,6 @@ source net_helper.sh readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" -BPF_FILE="xdp_dummy.bpf.o" - # set global exit status, but never reset nonzero one. check_err() { @@ -38,7 +36,7 @@ cfg_veth() { ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24 ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad ip -netns "${PEER_NS}" link set dev veth1 up - ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp + ip netns exec "${PEER_NS}" ethtool -K veth1 gro on } run_one() { @@ -206,11 +204,6 @@ run_all() { return $ret } -if [ ! -f ${BPF_FILE} ]; then - echo "Missing ${BPF_FILE}. Run 'make' first" - exit -1 -fi - if [[ $# -eq 0 ]]; then run_all elif [[ $1 == "__subprocess" ]]; then From cf1e515c9a40caa8bddb920970d3257bb01c1421 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Mon, 19 Aug 2024 20:00:07 +0800 Subject: [PATCH 409/562] iommufd/selftest: Make dirty_ops static The sparse tool complains as follows: drivers/iommu/iommufd/selftest.c:277:30: warning: symbol 'dirty_ops' was not declared. Should it be static? This symbol is not used outside of selftest.c, so marks it static. Fixes: 266ce58989ba ("iommufd/selftest: Test IOMMU_HWPT_ALLOC_DIRTY_TRACKING") Link: https://patch.msgid.link/r/20240819120007.3884868-1-ruanjinjie@huawei.com Signed-off-by: Jinjie Ruan Reviewed-by: Yi Liu Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/selftest.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index f95e32e29133..222cfc11ebfd 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -273,7 +273,7 @@ static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain, return 0; } -const struct iommu_dirty_ops dirty_ops = { +static const struct iommu_dirty_ops dirty_ops = { .set_dirty_tracking = mock_domain_set_dirty_tracking, .read_and_clear_dirty = mock_domain_read_and_clear_dirty, }; From cd8e468efb4fb2742e06328a75b282c35c1abf8d Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 14 Aug 2024 21:01:57 +0200 Subject: [PATCH 410/562] ACPI: video: Add Dell UART backlight controller detection Dell All In One (AIO) models released after 2017 use a backlight controller board connected to an UART. In DSDT this uart port will be defined as: Name (_HID, "DELL0501") Name (_CID, EisaId ("PNP0501") Commit 484bae9e4d6a ("platform/x86: Add new Dell UART backlight driver") has added support for this, but I neglected to tie this into acpi_video_get_backlight_type(). Now the first AIO has turned up which has not only the DSDT bits for this, but also an actual controller attached to the UART, yet it is not using this controller for backlight control. Add support to acpi_video_get_backlight_type() for a new dell_uart backlight type. So that the existing infra to override the backlight control method on the commandline or with DMI quirks can be used. Fixes: 484bae9e4d6a ("platform/x86: Add new Dell UART backlight driver") Cc: All applicable Signed-off-by: Hans de Goede Reviewed-by: Andy Shevchenko Link: https://patch.msgid.link/20240814190159.15650-2-hdegoede@redhat.com Signed-off-by: Rafael J. Wysocki --- drivers/acpi/video_detect.c | 7 +++++++ include/acpi/video.h | 1 + 2 files changed, 8 insertions(+) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index c11cbe5b6eaa..e509dcbf3090 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -54,6 +54,8 @@ static void acpi_video_parse_cmdline(void) acpi_backlight_cmdline = acpi_backlight_nvidia_wmi_ec; if (!strcmp("apple_gmux", acpi_video_backlight_string)) acpi_backlight_cmdline = acpi_backlight_apple_gmux; + if (!strcmp("dell_uart", acpi_video_backlight_string)) + acpi_backlight_cmdline = acpi_backlight_dell_uart; if (!strcmp("none", acpi_video_backlight_string)) acpi_backlight_cmdline = acpi_backlight_none; } @@ -918,6 +920,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto static DEFINE_MUTEX(init_mutex); static bool nvidia_wmi_ec_present; static bool apple_gmux_present; + static bool dell_uart_present; static bool native_available; static bool init_done; static long video_caps; @@ -932,6 +935,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto &video_caps, NULL); nvidia_wmi_ec_present = nvidia_wmi_ec_supported(); apple_gmux_present = apple_gmux_detect(NULL, NULL); + dell_uart_present = acpi_dev_present("DELL0501", NULL, -1); init_done = true; } if (native) @@ -962,6 +966,9 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto if (apple_gmux_present) return acpi_backlight_apple_gmux; + if (dell_uart_present) + return acpi_backlight_dell_uart; + /* Use ACPI video if available, except when native should be preferred. */ if ((video_caps & ACPI_VIDEO_BACKLIGHT) && !(native_available && prefer_native_over_acpi_video())) diff --git a/include/acpi/video.h b/include/acpi/video.h index 3d538d4178ab..044c463138df 100644 --- a/include/acpi/video.h +++ b/include/acpi/video.h @@ -50,6 +50,7 @@ enum acpi_backlight_type { acpi_backlight_native, acpi_backlight_nvidia_wmi_ec, acpi_backlight_apple_gmux, + acpi_backlight_dell_uart, }; #if IS_ENABLED(CONFIG_ACPI_VIDEO) From b5f0943001339c4d324a1af10470ce0bdd79f966 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 14 Aug 2024 21:01:58 +0200 Subject: [PATCH 411/562] platform/x86: dell-uart-backlight: Use acpi_video_get_backlight_type() The dell-uart-backlight driver supports backlight control on Dell All In One (AIO) models using a backlight controller board connected to an UART. In DSDT this uart port will be defined as: Name (_HID, "DELL0501") Name (_CID, EisaId ("PNP0501") Now the first AIO has turned up which has not only the DSDT bits for this, but also an actual controller attached to the UART, yet it is not using this controller for backlight control. Use the acpi_video_get_backlight_type() function from the ACPI video-detect code to check if the dell-uart-backlight driver should actually be used. This allows reusing the existing ACPI video-detect infra to override the backlight control method on the commandline or with DMI quirks. Fixes: 484bae9e4d6a ("platform/x86: Add new Dell UART backlight driver") Cc: All applicable Signed-off-by: Hans de Goede Reviewed-by: Andy Shevchenko Link: https://patch.msgid.link/20240814190159.15650-3-hdegoede@redhat.com Signed-off-by: Rafael J. Wysocki --- drivers/platform/x86/dell/Kconfig | 1 + drivers/platform/x86/dell/dell-uart-backlight.c | 8 ++++++++ 2 files changed, 9 insertions(+) diff --git a/drivers/platform/x86/dell/Kconfig b/drivers/platform/x86/dell/Kconfig index 85a78ef91182..309236cecd5a 100644 --- a/drivers/platform/x86/dell/Kconfig +++ b/drivers/platform/x86/dell/Kconfig @@ -161,6 +161,7 @@ config DELL_SMO8800 config DELL_UART_BACKLIGHT tristate "Dell AIO UART Backlight driver" depends on ACPI + depends on ACPI_VIDEO depends on BACKLIGHT_CLASS_DEVICE depends on SERIAL_DEV_BUS help diff --git a/drivers/platform/x86/dell/dell-uart-backlight.c b/drivers/platform/x86/dell/dell-uart-backlight.c index 87d2a20b4cb3..3995f90add45 100644 --- a/drivers/platform/x86/dell/dell-uart-backlight.c +++ b/drivers/platform/x86/dell/dell-uart-backlight.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "../serdev_helpers.h" /* The backlight controller must respond within 1 second */ @@ -332,10 +333,17 @@ struct serdev_device_driver dell_uart_bl_serdev_driver = { static int dell_uart_bl_pdev_probe(struct platform_device *pdev) { + enum acpi_backlight_type bl_type; struct serdev_device *serdev; struct device *ctrl_dev; int ret; + bl_type = acpi_video_get_backlight_type(); + if (bl_type != acpi_backlight_dell_uart) { + dev_dbg(&pdev->dev, "Not loading (ACPI backlight type = %d)\n", bl_type); + return -ENODEV; + } + ctrl_dev = get_serdev_controller("DELL0501", NULL, 0, "serial0"); if (IS_ERR(ctrl_dev)) return PTR_ERR(ctrl_dev); From 5c7bb62cb8f53de71d8ab3d619be22740da0b837 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 14 Aug 2024 21:01:59 +0200 Subject: [PATCH 412/562] ACPI: video: Add backlight=native quirk for Dell OptiPlex 7760 AIO Dell All In One (AIO) models released after 2017 may use a backlight controller board connected to an UART. In DSDT this uart port will be defined as: Name (_HID, "DELL0501") Name (_CID, EisaId ("PNP0501") The Dell OptiPlex 7760 AIO has an ACPI device for one if its UARTs with the above _HID + _CID. Loading the dell-uart-backlight driver shows that there actually is a backlight controller board attached to the UART, which reports a firmware version of "G&MX01-V15". But the backlight controller board does not actually control the backlight brightness and the GPU's native backlight control method does work. Add a quirk to use the GPU's native backlight control method on this model. Fixes: 484bae9e4d6a ("platform/x86: Add new Dell UART backlight driver") Closes: https://bugzilla.redhat.com/show_bug.cgi?id=2303936 Cc: All applicable Signed-off-by: Hans de Goede Reviewed-by: Andy Shevchenko Link: https://patch.msgid.link/20240814190159.15650-4-hdegoede@redhat.com Signed-off-by: Rafael J. Wysocki --- drivers/acpi/video_detect.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index e509dcbf3090..674b9db7a1ef 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -823,6 +823,21 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, }, + /* + * Dell AIO (All in Ones) which advertise an UART attached backlight + * controller board in their ACPI tables (and may even have one), but + * which need native backlight control nevertheless. + */ + { + /* https://bugzilla.redhat.com/show_bug.cgi?id=2303936 */ + .callback = video_detect_force_native, + /* Dell OptiPlex 7760 AIO */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 7760 AIO"), + }, + }, + /* * Models which have nvidia-ec-wmi support, but should not use it. * Note this indicates a likely firmware bug on these models and should From f4b2a0ae1a31fd3d1b5ca18ee08319b479cf9b5f Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Wed, 24 Jul 2024 14:53:09 -0700 Subject: [PATCH 413/562] drm/xe: Fix opregion leak Being part o the display, ideally the setup and cleanup would be done by display itself. However this is a bigger refactor that needs to be done on both i915 and xe. For now, just fix the leak: unreferenced object 0xffff8881a0300008 (size 192): comm "modprobe", pid 4354, jiffies 4295647021 hex dump (first 32 bytes): 00 00 87 27 81 88 ff ff 18 80 9b 00 00 c9 ff ff ...'............ 18 81 9b 00 00 c9 ff ff 00 00 00 00 00 00 00 00 ................ backtrace (crc 99260e31): [] kmemleak_alloc+0x4b/0x80 [] kmalloc_trace_noprof+0x312/0x3d0 [] intel_opregion_setup+0x89/0x700 [xe] [] xe_display_init_noirq+0x2f/0x90 [xe] [] xe_device_probe+0x7a3/0xbf0 [xe] [] xe_pci_probe+0x333/0x5b0 [xe] [] local_pci_probe+0x48/0xb0 [] pci_device_probe+0xc8/0x280 [] really_probe+0xf8/0x390 [] __driver_probe_device+0x8a/0x170 [] driver_probe_device+0x23/0xb0 [] __driver_attach+0xc7/0x190 [] bus_for_each_dev+0x7d/0xd0 [] driver_attach+0x1e/0x30 [] bus_add_driver+0x117/0x250 Fixes: 44e694958b95 ("drm/xe/display: Implement display support") Reviewed-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20240724215309.644423-1-lucas.demarchi@intel.com Signed-off-by: Lucas De Marchi (cherry picked from commit 6f4e43a2f771b737d991142ec4f6d4b7ff31fbb4) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/display/xe_display.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c index 8b83dcff72e1..ca4468c82078 100644 --- a/drivers/gpu/drm/xe/display/xe_display.c +++ b/drivers/gpu/drm/xe/display/xe_display.c @@ -132,6 +132,7 @@ static void xe_display_fini_noirq(void *arg) return; intel_display_driver_remove_noirq(xe); + intel_opregion_cleanup(xe); } int xe_display_init_noirq(struct xe_device *xe) @@ -157,8 +158,10 @@ int xe_display_init_noirq(struct xe_device *xe) intel_display_device_info_runtime_init(xe); err = intel_display_driver_probe_noirq(xe); - if (err) + if (err) { + intel_opregion_cleanup(xe); return err; + } return devm_add_action_or_reset(xe->drm.dev, xe_display_fini_noirq, xe); } From c621f70539cae731d9749c1900cd00bb70ea5c72 Mon Sep 17 00:00:00 2001 From: Ashutosh Dixit Date: Sun, 4 Aug 2024 23:20:57 -0700 Subject: [PATCH 414/562] drm/xe/observation: Drop empty sysctl table entry An empty sysctl table entry was inadvertently left behind for observation sysctl. The breaks on 6.11 with the following errors: [ 219.654850] sysctl table check failed: dev/xe/(null) procname is null [ 219.654862] sysctl table check failed: dev/xe/(null) No proc_handler Drop the empty entry. Fixes: 63347fe031e3 ("drm/xe/uapi: Rename xe perf layer as xe observation layer") Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2419 Signed-off-by: Ashutosh Dixit Reviewed-by: Umesh Nerlige Ramappa Link: https://patchwork.freedesktop.org/patch/msgid/20240805062057.3547560-1-ashutosh.dixit@intel.com (cherry picked from commit be1dec570b6f5a29ce9c99334c52bea94c28914b) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_observation.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_observation.c b/drivers/gpu/drm/xe/xe_observation.c index fcb584b42a7d..a78c92a44ec2 100644 --- a/drivers/gpu/drm/xe/xe_observation.c +++ b/drivers/gpu/drm/xe/xe_observation.c @@ -66,7 +66,6 @@ static struct ctl_table observation_ctl_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - {} }; /** From 7090d7fc969fcc9985d7e538cfcd8a69a5f9c616 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Wed, 24 Jul 2024 08:28:31 -0700 Subject: [PATCH 415/562] drm/xe: Move VM dma-resv lock from xe_exec_queue_create to __xe_exec_queue_init The critical section which requires the VM dma-resv is the call xe_lrc_create in __xe_exec_queue_init. Move this lock to __xe_exec_queue_init holding it just around xe_lrc_create. Not only is good practice, this also fixes a locking double of the VM dma-resv in the error paths of __xe_exec_queue_init as xe_lrc_put tries to acquire this too resulting in a deadlock. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: Maarten Lankhorst Signed-off-by: Matthew Brost Reviewed-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20240724152831.1848325-1-matthew.brost@intel.com (cherry picked from commit 549dd786b61cd3db903f5d94d07fc5a89ccdbeb9) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_exec_queue.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index a39384bb9553..16f24f4a7062 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -105,22 +105,35 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe, static int __xe_exec_queue_init(struct xe_exec_queue *q) { + struct xe_vm *vm = q->vm; int i, err; + if (vm) { + err = xe_vm_lock(vm, true); + if (err) + return err; + } + for (i = 0; i < q->width; ++i) { q->lrc[i] = xe_lrc_create(q->hwe, q->vm, SZ_16K); if (IS_ERR(q->lrc[i])) { err = PTR_ERR(q->lrc[i]); - goto err_lrc; + goto err_unlock; } } + if (vm) + xe_vm_unlock(vm); + err = q->ops->init(q); if (err) goto err_lrc; return 0; +err_unlock: + if (vm) + xe_vm_unlock(vm); err_lrc: for (i = i - 1; i >= 0; --i) xe_lrc_put(q->lrc[i]); @@ -140,15 +153,7 @@ struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *v if (IS_ERR(q)) return q; - if (vm) { - err = xe_vm_lock(vm, true); - if (err) - goto err_post_alloc; - } - err = __xe_exec_queue_init(q); - if (vm) - xe_vm_unlock(vm); if (err) goto err_post_alloc; From 15939ca77d4424f736e1e4953b4da2351cc9689d Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Fri, 9 Aug 2024 16:28:30 -0700 Subject: [PATCH 416/562] drm/xe: Fix tile fini sequence Only set tile->mmio.regs to NULL if not the root tile in tile_fini. The root tile mmio regs is setup ealier in MMIO init thus it should be set to NULL in mmio_fini. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Matthew Brost Reviewed-by: Lucas De Marchi Reviewed-by: Himal Prasad Ghimiray Link: https://patchwork.freedesktop.org/patch/msgid/20240809232830.3302251-1-matthew.brost@intel.com (cherry picked from commit 3396900aa273903639a1792afa4d23dc09bec291) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_mmio.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c index f92faad4b96d..83122c77edd9 100644 --- a/drivers/gpu/drm/xe/xe_mmio.c +++ b/drivers/gpu/drm/xe/xe_mmio.c @@ -30,7 +30,8 @@ static void tiles_fini(void *arg) int id; for_each_tile(tile, xe, id) - tile->mmio.regs = NULL; + if (tile != xe_device_get_root_tile(xe)) + tile->mmio.regs = NULL; } int xe_mmio_probe_tiles(struct xe_device *xe) @@ -91,9 +92,11 @@ add_mmio_ext: static void mmio_fini(void *arg) { struct xe_device *xe = arg; + struct xe_tile *root_tile = xe_device_get_root_tile(xe); pci_iounmap(to_pci_dev(xe->drm.dev), xe->mmio.regs); xe->mmio.regs = NULL; + root_tile->mmio.regs = NULL; } int xe_mmio_init(struct xe_device *xe) From 730b72480e29f63fd644f5fa57c9d46109428953 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Wed, 14 Aug 2024 12:01:30 +0100 Subject: [PATCH 417/562] drm/xe: prevent UAF around preempt fence The fence lock is part of the queue, therefore in the current design anything locking the fence should then also hold a ref to the queue to prevent the queue from being freed. However, currently it looks like we signal the fence and then drop the queue ref, but if something is waiting on the fence, the waiter is kicked to wake up at some later point, where upon waking up it first grabs the lock before checking the fence state. But if we have already dropped the queue ref, then the lock might already be freed as part of the queue, leading to uaf. To prevent this, move the fence lock into the fence itself so we don't run into lifetime issues. Alternative might be to have device level lock, or only release the queue in the fence release callback, however that might require pushing to another worker to avoid locking issues. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") References: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2454 References: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2342 References: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2020 Signed-off-by: Matthew Auld Cc: Matthew Brost Cc: # v6.8+ Reviewed-by: Matthew Brost Link: https://patchwork.freedesktop.org/patch/msgid/20240814110129.825847-2-matthew.auld@intel.com (cherry picked from commit 7116c35aacedc38be6d15bd21b2fc936eed0008b) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_exec_queue.c | 1 - drivers/gpu/drm/xe/xe_exec_queue_types.h | 2 -- drivers/gpu/drm/xe/xe_preempt_fence.c | 3 ++- drivers/gpu/drm/xe/xe_preempt_fence_types.h | 2 ++ 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 16f24f4a7062..9731dcd0b1bd 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -643,7 +643,6 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, if (xe_vm_in_preempt_fence_mode(vm)) { q->lr.context = dma_fence_context_alloc(1); - spin_lock_init(&q->lr.lock); err = xe_vm_add_compute_exec_queue(vm, q); if (XE_IOCTL_DBG(xe, err)) diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index a35ce24c9798..f6ee0ae80fd6 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -126,8 +126,6 @@ struct xe_exec_queue { u32 seqno; /** @lr.link: link into VM's list of exec queues */ struct list_head link; - /** @lr.lock: preemption fences lock */ - spinlock_t lock; } lr; /** @ops: submission backend exec queue operations */ diff --git a/drivers/gpu/drm/xe/xe_preempt_fence.c b/drivers/gpu/drm/xe/xe_preempt_fence.c index e8b8ae5c6485..c453f45328b1 100644 --- a/drivers/gpu/drm/xe/xe_preempt_fence.c +++ b/drivers/gpu/drm/xe/xe_preempt_fence.c @@ -128,8 +128,9 @@ xe_preempt_fence_arm(struct xe_preempt_fence *pfence, struct xe_exec_queue *q, { list_del_init(&pfence->link); pfence->q = xe_exec_queue_get(q); + spin_lock_init(&pfence->lock); dma_fence_init(&pfence->base, &preempt_fence_ops, - &q->lr.lock, context, seqno); + &pfence->lock, context, seqno); return &pfence->base; } diff --git a/drivers/gpu/drm/xe/xe_preempt_fence_types.h b/drivers/gpu/drm/xe/xe_preempt_fence_types.h index b54b5c29b533..312c3372a49f 100644 --- a/drivers/gpu/drm/xe/xe_preempt_fence_types.h +++ b/drivers/gpu/drm/xe/xe_preempt_fence_types.h @@ -25,6 +25,8 @@ struct xe_preempt_fence { struct xe_exec_queue *q; /** @preempt_work: work struct which issues preemption */ struct work_struct preempt_work; + /** @lock: dma-fence fence lock */ + spinlock_t lock; /** @error: preempt fence is in error state */ int error; }; From ddf6492e0e508b7c2b42c8d5a4ac82bd38ef0dd5 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Tue, 6 Aug 2024 12:50:44 +0200 Subject: [PATCH 418/562] drm/xe/display: Make display suspend/resume work on discrete We should unpin before evicting all memory, and repin after GT resume. This way, we preserve the contents of the framebuffers, and won't hang on resume due to migration engine not being restored yet. Signed-off-by: Maarten Lankhorst Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: stable@vger.kernel.org # v6.8+ Reviewed-by: Uma Shankar Link: https://patchwork.freedesktop.org/patch/msgid/20240806105044.596842-3-maarten.lankhorst@linux.intel.com Signed-off-by: Maarten Lankhorst,,, (cherry picked from commit cb8f81c1753187995b7a43e79c12959f14eb32d3) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/display/xe_display.c | 23 +++++++++++++++++++++++ drivers/gpu/drm/xe/xe_pm.c | 11 ++++++----- 2 files changed, 29 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c index ca4468c82078..49de4e4f8a75 100644 --- a/drivers/gpu/drm/xe/display/xe_display.c +++ b/drivers/gpu/drm/xe/display/xe_display.c @@ -283,6 +283,27 @@ static bool suspend_to_idle(void) return false; } +static void xe_display_flush_cleanup_work(struct xe_device *xe) +{ + struct intel_crtc *crtc; + + for_each_intel_crtc(&xe->drm, crtc) { + struct drm_crtc_commit *commit; + + spin_lock(&crtc->base.commit_lock); + commit = list_first_entry_or_null(&crtc->base.commit_list, + struct drm_crtc_commit, commit_entry); + if (commit) + drm_crtc_commit_get(commit); + spin_unlock(&crtc->base.commit_lock); + + if (commit) { + wait_for_completion(&commit->cleanup_done); + drm_crtc_commit_put(commit); + } + } +} + void xe_display_pm_suspend(struct xe_device *xe, bool runtime) { bool s2idle = suspend_to_idle(); @@ -300,6 +321,8 @@ void xe_display_pm_suspend(struct xe_device *xe, bool runtime) if (!runtime) intel_display_driver_suspend(xe); + xe_display_flush_cleanup_work(xe); + intel_dp_mst_suspend(xe); intel_hpd_cancel_work(xe); diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index de3b5df65e48..9a3f618d22dc 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -91,13 +91,13 @@ int xe_pm_suspend(struct xe_device *xe) for_each_gt(gt, xe, id) xe_gt_suspend_prepare(gt); + xe_display_pm_suspend(xe, false); + /* FIXME: Super racey... */ err = xe_bo_evict_all(xe); if (err) goto err; - xe_display_pm_suspend(xe, false); - for_each_gt(gt, xe, id) { err = xe_gt_suspend(gt); if (err) { @@ -151,11 +151,11 @@ int xe_pm_resume(struct xe_device *xe) xe_irq_resume(xe); - xe_display_pm_resume(xe, false); - for_each_gt(gt, xe, id) xe_gt_resume(gt); + xe_display_pm_resume(xe, false); + err = xe_bo_restore_user(xe); if (err) goto err; @@ -363,10 +363,11 @@ int xe_pm_runtime_suspend(struct xe_device *xe) mutex_unlock(&xe->mem_access.vram_userfault.lock); if (xe->d3cold.allowed) { + xe_display_pm_suspend(xe, true); + err = xe_bo_evict_all(xe); if (err) goto out; - xe_display_pm_suspend(xe, true); } for_each_gt(gt, xe, id) { From ad614a706b1ac83b95b333f44b8f5e70bcb37dc5 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 29 Jul 2024 11:26:34 +0200 Subject: [PATCH 419/562] drm/xe/oa/uapi: Make bit masks unsigned MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When building with gcc-5: In function ‘decode_oa_format.isra.26’, inlined from ‘xe_oa_set_prop_oa_format’ at drivers/gpu/drm/xe/xe_oa.c:1664:6: ././include/linux/compiler_types.h:510:38: error: call to ‘__compiletime_assert_1336’ declared with attribute error: FIELD_GET: mask is not constant [...] ./include/linux/bitfield.h:155:3: note: in expansion of macro ‘__BF_FIELD_CHECK’ __BF_FIELD_CHECK(_mask, _reg, 0U, "FIELD_GET: "); \ ^ drivers/gpu/drm/xe/xe_oa.c:1573:18: note: in expansion of macro ‘FIELD_GET’ u32 bc_report = FIELD_GET(DRM_XE_OA_FORMAT_MASK_BC_REPORT, fmt); ^ Fixes: b6fd51c62119 ("drm/xe/oa/uapi: Define and parse OA stream properties") Signed-off-by: Geert Uytterhoeven Reviewed-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20240729092634.2227611-1-geert+renesas@glider.be Signed-off-by: Lucas De Marchi (cherry picked from commit f2881dfdaaa9ec873dbd383ef5512fc31e576cbb) Signed-off-by: Rodrigo Vivi --- include/uapi/drm/xe_drm.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 19619d4952a8..db232a25189e 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -1590,10 +1590,10 @@ enum drm_xe_oa_property_id { * b. Counter select c. Counter size and d. BC report. Also refer to the * oa_formats array in drivers/gpu/drm/xe/xe_oa.c. */ -#define DRM_XE_OA_FORMAT_MASK_FMT_TYPE (0xff << 0) -#define DRM_XE_OA_FORMAT_MASK_COUNTER_SEL (0xff << 8) -#define DRM_XE_OA_FORMAT_MASK_COUNTER_SIZE (0xff << 16) -#define DRM_XE_OA_FORMAT_MASK_BC_REPORT (0xff << 24) +#define DRM_XE_OA_FORMAT_MASK_FMT_TYPE (0xffu << 0) +#define DRM_XE_OA_FORMAT_MASK_COUNTER_SEL (0xffu << 8) +#define DRM_XE_OA_FORMAT_MASK_COUNTER_SIZE (0xffu << 16) +#define DRM_XE_OA_FORMAT_MASK_BC_REPORT (0xffu << 24) /** * @DRM_XE_OA_PROPERTY_OA_PERIOD_EXPONENT: Requests periodic OA unit From 565d121b69980637f040eb4d84289869cdaabedf Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 13 Aug 2024 00:28:25 +0200 Subject: [PATCH 420/562] tcp: prevent concurrent execution of tcp_sk_exit_batch Its possible that two threads call tcp_sk_exit_batch() concurrently, once from the cleanup_net workqueue, once from a task that failed to clone a new netns. In the latter case, error unwinding calls the exit handlers in reverse order for the 'failed' netns. tcp_sk_exit_batch() calls tcp_twsk_purge(). Problem is that since commit b099ce2602d8 ("net: Batch inet_twsk_purge"), this function picks up twsk in any dying netns, not just the one passed in via exit_batch list. This means that the error unwind of setup_net() can "steal" and destroy timewait sockets belonging to the exiting netns. This allows the netns exit worker to proceed to call WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount)); without the expected 1 -> 0 transition, which then splats. At same time, error unwind path that is also running inet_twsk_purge() will splat as well: WARNING: .. at lib/refcount.c:31 refcount_warn_saturate+0x1ed/0x210 ... refcount_dec include/linux/refcount.h:351 [inline] inet_twsk_kill+0x758/0x9c0 net/ipv4/inet_timewait_sock.c:70 inet_twsk_deschedule_put net/ipv4/inet_timewait_sock.c:221 inet_twsk_purge+0x725/0x890 net/ipv4/inet_timewait_sock.c:304 tcp_sk_exit_batch+0x1c/0x170 net/ipv4/tcp_ipv4.c:3522 ops_exit_list+0x128/0x180 net/core/net_namespace.c:178 setup_net+0x714/0xb40 net/core/net_namespace.c:375 copy_net_ns+0x2f0/0x670 net/core/net_namespace.c:508 create_new_namespaces+0x3ea/0xb10 kernel/nsproxy.c:110 ... because refcount_dec() of tw_refcount unexpectedly dropped to 0. This doesn't seem like an actual bug (no tw sockets got lost and I don't see a use-after-free) but as erroneous trigger of debug check. Add a mutex to force strict ordering: the task that calls tcp_twsk_purge() blocks other task from doing final _dec_and_test before mutex-owner has removed all tw sockets of dying netns. Fixes: e9bd0cca09d1 ("tcp: Don't allocate tcp_death_row outside of struct netns_ipv4.") Reported-by: syzbot+8ea26396ff85d23a8929@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/0000000000003a5292061f5e4e19@google.com/ Link: https://lore.kernel.org/netdev/20240812140104.GA21559@breakpoint.cc/ Signed-off-by: Florian Westphal Reviewed-by: Kuniyuki Iwashima Reviewed-by: Jason Xing Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240812222857.29837-1-fw@strlen.de Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_ipv4.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fd17f25ff288..a4e510846905 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -97,6 +97,8 @@ static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; +static DEFINE_MUTEX(tcp_exit_batch_mutex); + static u32 tcp_v4_init_seq(const struct sk_buff *skb) { return secure_tcp_seq(ip_hdr(skb)->daddr, @@ -3514,6 +3516,16 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; + /* make sure concurrent calls to tcp_sk_exit_batch from net_cleanup_work + * and failed setup_net error unwinding path are serialized. + * + * tcp_twsk_purge() handles twsk in any dead netns, not just those in + * net_exit_list, the thread that dismantles a particular twsk must + * do so without other thread progressing to refcount_dec_and_test() of + * tcp_death_row.tw_refcount. + */ + mutex_lock(&tcp_exit_batch_mutex); + tcp_twsk_purge(net_exit_list); list_for_each_entry(net, net_exit_list, exit_list) { @@ -3521,6 +3533,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount)); tcp_fastopen_ctx_destroy(net); } + + mutex_unlock(&tcp_exit_batch_mutex); } static struct pernet_operations __net_initdata tcp_sk_ops = { From 64b582ca88ca11400467b282d5fa3b870ded1c11 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 15 Aug 2024 16:32:27 +0000 Subject: [PATCH 421/562] block: Read max write zeroes once for __blkdev_issue_write_zeroes() As reported in [0], we may get a hang when formatting a XFS FS on a RAID0 drive. Commit 73a768d5f955 ("block: factor out a blk_write_zeroes_limit helper") changed __blkdev_issue_write_zeroes() to read the max write zeroes value in the loop. This is not safe as max write zeroes may change in value. Specifically for the case of [0], the value goes to 0, and we get an infinite loop. Lift the limit reading out of the loop. [0] https://lore.kernel.org/linux-xfs/4d31268f-310b-4220-88a2-e191c3932a82@oracle.com/T/#t Fixes: 73a768d5f955 ("block: factor out a blk_write_zeroes_limit helper") Reviewed-by: Christoph Hellwig Signed-off-by: John Garry Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20240815163228.216051-2-john.g.garry@oracle.com Signed-off-by: Jens Axboe --- block/blk-lib.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/block/blk-lib.c b/block/blk-lib.c index 9f735efa6c94..83eb7761c2bf 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -111,13 +111,20 @@ static sector_t bio_write_zeroes_limit(struct block_device *bdev) (UINT_MAX >> SECTOR_SHIFT) & ~bs_mask); } +/* + * There is no reliable way for the SCSI subsystem to determine whether a + * device supports a WRITE SAME operation without actually performing a write + * to media. As a result, write_zeroes is enabled by default and will be + * disabled if a zeroing operation subsequently fails. This means that this + * queue limit is likely to change at runtime. + */ static void __blkdev_issue_write_zeroes(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, - struct bio **biop, unsigned flags) + struct bio **biop, unsigned flags, sector_t limit) { + while (nr_sects) { - unsigned int len = min_t(sector_t, nr_sects, - bio_write_zeroes_limit(bdev)); + unsigned int len = min(nr_sects, limit); struct bio *bio; if ((flags & BLKDEV_ZERO_KILLABLE) && @@ -141,12 +148,14 @@ static void __blkdev_issue_write_zeroes(struct block_device *bdev, static int blkdev_issue_write_zeroes(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp, unsigned flags) { + sector_t limit = bio_write_zeroes_limit(bdev); struct bio *bio = NULL; struct blk_plug plug; int ret = 0; blk_start_plug(&plug); - __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp, &bio, flags); + __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp, &bio, + flags, limit); if (bio) { if ((flags & BLKDEV_ZERO_KILLABLE) && fatal_signal_pending(current)) { @@ -165,7 +174,7 @@ static int blkdev_issue_write_zeroes(struct block_device *bdev, sector_t sector, * on an I/O error, in which case we'll turn any error into * "not supported" here. */ - if (ret && !bdev_write_zeroes_sectors(bdev)) + if (ret && !limit) return -EOPNOTSUPP; return ret; } @@ -265,12 +274,14 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, unsigned flags) { + sector_t limit = bio_write_zeroes_limit(bdev); + if (bdev_read_only(bdev)) return -EPERM; - if (bdev_write_zeroes_sectors(bdev)) { + if (limit) { __blkdev_issue_write_zeroes(bdev, sector, nr_sects, - gfp_mask, biop, flags); + gfp_mask, biop, flags, limit); } else { if (flags & BLKDEV_ZERO_NOFALLBACK) return -EOPNOTSUPP; From 81475beb1b5996505a39cd1d9316ce1e668932a2 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 15 Aug 2024 16:32:28 +0000 Subject: [PATCH 422/562] block: Drop NULL check in bdev_write_zeroes_sectors() Function bdev_get_queue() must not return NULL, so drop the check in bdev_write_zeroes_sectors(). Reviewed-by: Christoph Hellwig Signed-off-by: John Garry Reviewed-by: Martin K. Petersen Reviewed-by: Nitesh Shetty Link: https://lore.kernel.org/r/20240815163228.216051-3-john.g.garry@oracle.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e85ec73a07d5..b7664d593486 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1296,12 +1296,7 @@ bdev_max_secure_erase_sectors(struct block_device *bdev) static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return q->limits.max_write_zeroes_sectors; - - return 0; + return bdev_get_queue(bdev)->limits.max_write_zeroes_sectors; } static inline bool bdev_nonrot(struct block_device *bdev) From de48aad2a8e80ba026ca91c383f590f0bf97b3c0 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 12 Aug 2024 11:47:57 -0400 Subject: [PATCH 423/562] rpcrdma: Device kref is over-incremented on error from xa_alloc If the device's reference count is too high, the device completion callback never fires. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/ib_client.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/xprtrdma/ib_client.c b/net/sunrpc/xprtrdma/ib_client.c index a938c19c3490..4d1e9fa89573 100644 --- a/net/sunrpc/xprtrdma/ib_client.c +++ b/net/sunrpc/xprtrdma/ib_client.c @@ -62,9 +62,9 @@ int rpcrdma_rn_register(struct ib_device *device, if (!rd || test_bit(RPCRDMA_RD_F_REMOVING, &rd->rd_flags)) return -ENETUNREACH; - kref_get(&rd->rd_kref); if (xa_alloc(&rd->rd_xa, &rn->rn_index, rn, xa_limit_32b, GFP_KERNEL) < 0) return -ENOMEM; + kref_get(&rd->rd_kref); rn->rn_done = done; return 0; } From 6b3b023e2d0c130235c0e494f77df2a9a64ab6a2 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 12 Aug 2024 11:47:58 -0400 Subject: [PATCH 424/562] rpcrdma: Use XA_FLAGS_ALLOC instead of XA_FLAGS_ALLOC1 Nit: The built-in xa_limit_32b range starts at 0, but XA_FLAGS_ALLOC1 configures the xarray's allocator to start at 1. Adopt the more conventional XA_FLAGS_ALLOC because there's no mechanical reason to skip 0. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/ib_client.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/xprtrdma/ib_client.c b/net/sunrpc/xprtrdma/ib_client.c index 4d1e9fa89573..7913d7bad23d 100644 --- a/net/sunrpc/xprtrdma/ib_client.c +++ b/net/sunrpc/xprtrdma/ib_client.c @@ -111,7 +111,7 @@ static int rpcrdma_add_one(struct ib_device *device) return -ENOMEM; kref_init(&rd->rd_kref); - xa_init_flags(&rd->rd_xa, XA_FLAGS_ALLOC1); + xa_init_flags(&rd->rd_xa, XA_FLAGS_ALLOC); rd->rd_device = device; init_completion(&rd->rd_done); ib_set_client_data(device, &rpcrdma_ib_client, rd); From dc0112e6d8b42b39f9d283bab489a757e9d284f0 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 12 Aug 2024 11:47:59 -0400 Subject: [PATCH 425/562] rpcrdma: Trace connection registration and unregistration These new trace points record xarray indices and the time of endpoint registration and unregistration, to co-ordinate with device removal events. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 36 +++++++++++++++++++++++++++++++++ net/sunrpc/xprtrdma/ib_client.c | 2 ++ 2 files changed, 38 insertions(+) diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index ba2d6a0e41cc..a96a985c49b3 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -2277,6 +2277,42 @@ DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_remove_one); DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_wait_on); DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_remove_one_done); +DECLARE_EVENT_CLASS(rpcrdma_client_register_class, + TP_PROTO( + const struct ib_device *device, + const struct rpcrdma_notification *rn + ), + + TP_ARGS(device, rn), + + TP_STRUCT__entry( + __string(name, device->name) + __field(void *, callback) + __field(u32, index) + ), + + TP_fast_assign( + __assign_str(name); + __entry->callback = rn->rn_done; + __entry->index = rn->rn_index; + ), + + TP_printk("device=%s index=%u done callback=%pS\n", + __get_str(name), __entry->index, __entry->callback + ) +); + +#define DEFINE_CLIENT_REGISTER_EVENT(name) \ + DEFINE_EVENT(rpcrdma_client_register_class, name, \ + TP_PROTO( \ + const struct ib_device *device, \ + const struct rpcrdma_notification *rn \ + ), \ + TP_ARGS(device, rn)) + +DEFINE_CLIENT_REGISTER_EVENT(rpcrdma_client_register); +DEFINE_CLIENT_REGISTER_EVENT(rpcrdma_client_unregister); + #endif /* _TRACE_RPCRDMA_H */ #include diff --git a/net/sunrpc/xprtrdma/ib_client.c b/net/sunrpc/xprtrdma/ib_client.c index 7913d7bad23d..8507cd4d8921 100644 --- a/net/sunrpc/xprtrdma/ib_client.c +++ b/net/sunrpc/xprtrdma/ib_client.c @@ -66,6 +66,7 @@ int rpcrdma_rn_register(struct ib_device *device, return -ENOMEM; kref_get(&rd->rd_kref); rn->rn_done = done; + trace_rpcrdma_client_register(device, rn); return 0; } @@ -91,6 +92,7 @@ void rpcrdma_rn_unregister(struct ib_device *device, if (!rd) return; + trace_rpcrdma_client_unregister(device, rn); xa_erase(&rd->rd_xa, rn->rn_index); kref_put(&rd->rd_kref, rpcrdma_rn_release); } From 2240a50e6294214de791729e9dcba6880fa7e44e Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Sat, 17 Aug 2024 18:15:41 +0800 Subject: [PATCH 426/562] KVM: arm64: vgic-debug: Don't put unmarked LPIs If there were LPIs being mapped behind our back (i.e., between .start() and .stop()), we would put them at iter_unmark_lpis() without checking if they were actually *marked*, which is obviously not good. Switch to use the xa_for_each_marked() iterator to fix it. Cc: stable@vger.kernel.org Fixes: 85d3ccc8b75b ("KVM: arm64: vgic-debug: Use an xarray mark for debug iterator") Signed-off-by: Zenghui Yu Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20240817101541.1664-1-yuzenghui@huawei.com Signed-off-by: Oliver Upton --- arch/arm64/kvm/vgic/vgic-debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c index bc74d06398ef..e1397ab2072a 100644 --- a/arch/arm64/kvm/vgic/vgic-debug.c +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -85,7 +85,7 @@ static void iter_unmark_lpis(struct kvm *kvm) struct vgic_irq *irq; unsigned long intid; - xa_for_each(&dist->lpi_xa, intid, irq) { + xa_for_each_marked(&dist->lpi_xa, intid, irq, LPI_XA_MARK_DEBUG_ITER) { xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); vgic_put_irq(kvm, irq); } From f616506754d34bcfdbfbc7508b562e5c98461e9a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 19 Aug 2024 13:50:45 +0100 Subject: [PATCH 427/562] KVM: arm64: vgic: Don't hold config_lock while unregistering redistributors We recently moved the teardown of the vgic part of a vcpu inside a critical section guarded by the config_lock. This teardown phase involves calling into kvm_io_bus_unregister_dev(), which takes the kvm->srcu lock. However, this violates the established order where kvm->srcu is taken on a memory fault (such as an MMIO access), possibly followed by taking the config_lock if the GIC emulation requires mutual exclusion from the other vcpus. It therefore results in a bad lockdep splat, as reported by Zenghui. Fix this by moving the call to kvm_io_bus_unregister_dev() outside of the config_lock critical section. At this stage, there shouln't be any need to hold the config_lock. As an additional bonus, document the ordering between kvm->slots_lock, kvm->srcu and kvm->arch.config_lock so that I cannot pretend I didn't know about those anymore. Fixes: 9eb18136af9f ("KVM: arm64: vgic: Hold config_lock while tearing down a CPU interface") Reported-by: Zenghui Yu Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Tested-by: Zenghui Yu Link: https://lore.kernel.org/r/20240819125045.3474845-1-maz@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/kvm/vgic/vgic-init.c | 9 ++++++--- arch/arm64/kvm/vgic/vgic.c | 5 +++++ 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 41feb858ff9a..e7c53e8af3d1 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -417,10 +417,8 @@ static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) kfree(vgic_cpu->private_irqs); vgic_cpu->private_irqs = NULL; - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { - vgic_unregister_redist_iodev(vcpu); + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; - } } void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) @@ -448,6 +446,11 @@ void kvm_vgic_destroy(struct kvm *kvm) kvm_vgic_dist_destroy(kvm); mutex_unlock(&kvm->arch.config_lock); + + if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) + kvm_for_each_vcpu(i, vcpu, kvm) + vgic_unregister_redist_iodev(vcpu); + mutex_unlock(&kvm->slots_lock); } diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index 974849ea7101..abe29c7d85d0 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -36,6 +36,11 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = { * we have to disable IRQs before taking this lock and everything lower * than it. * + * The config_lock has additional ordering requirements: + * kvm->slots_lock + * kvm->srcu + * kvm->arch.config_lock + * * If you need to take multiple locks, always take the upper lock first, * then the lower ones, e.g. first take the its_lock, then the irq_lock. * If you are already holding a lock and need to take a higher one, you From 27cb2b7fec2abf310e4128137979124ead920ccb Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Wed, 3 Jul 2024 13:43:38 +0100 Subject: [PATCH 428/562] drm/xe/bmg: implement Wa_16023588340 This involves enabling l2 caching of host side memory access to VRAM through the CPU BAR. The main fallout here is with display since VRAM writes from CPU can now be cached in GPU l2, and display is never coherent with caches, so needs various manual flushing. In the case of fbc we disable it due to complications in getting this to work correctly (in a later patch). Signed-off-by: Matthew Auld Cc: Jonathan Cavitt Cc: Matt Roper Cc: Lucas De Marchi Cc: Vinod Govindapillai Reviewed-by: Jonathan Cavitt Link: https://patchwork.freedesktop.org/patch/msgid/20240703124338.208220-3-matthew.auld@intel.com (cherry picked from commit 01570b446939c3538b1aa3d059837f49fa14a3ae) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/Makefile | 2 + drivers/gpu/drm/xe/display/xe_dsb_buffer.c | 8 ++++ drivers/gpu/drm/xe/display/xe_fb_pin.c | 3 ++ drivers/gpu/drm/xe/regs/xe_gt_regs.h | 8 ++++ drivers/gpu/drm/xe/xe_device.c | 30 ++++++++++++ drivers/gpu/drm/xe/xe_device.h | 1 + drivers/gpu/drm/xe/xe_gt.c | 54 ++++++++++++++++++++++ drivers/gpu/drm/xe/xe_pat.c | 11 ++++- drivers/gpu/drm/xe/xe_wa_oob.rules | 1 + 9 files changed, 117 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index 628c245c4822..e97c9da451b3 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -25,12 +25,14 @@ $(obj)/generated/%_wa_oob.c $(obj)/generated/%_wa_oob.h: $(obj)/xe_gen_wa_oob \ uses_generated_oob := \ $(obj)/xe_ggtt.o \ + $(obj)/xe_device.o \ $(obj)/xe_gsc.o \ $(obj)/xe_gt.o \ $(obj)/xe_guc.o \ $(obj)/xe_guc_ads.o \ $(obj)/xe_guc_pc.o \ $(obj)/xe_migrate.o \ + $(obj)/xe_pat.o \ $(obj)/xe_ring_ops.o \ $(obj)/xe_vm.o \ $(obj)/xe_wa.o \ diff --git a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c index 9e860c61f4b3..ccd0d87d438a 100644 --- a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c +++ b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c @@ -7,6 +7,8 @@ #include "intel_display_types.h" #include "intel_dsb_buffer.h" #include "xe_bo.h" +#include "xe_device.h" +#include "xe_device_types.h" #include "xe_gt.h" u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf) @@ -16,7 +18,10 @@ u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf) void intel_dsb_buffer_write(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val) { + struct xe_device *xe = dsb_buf->vma->bo->tile->xe; + iosys_map_wr(&dsb_buf->vma->bo->vmap, idx * 4, u32, val); + xe_device_l2_flush(xe); } u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx) @@ -26,9 +31,12 @@ u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx) void intel_dsb_buffer_memset(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val, size_t size) { + struct xe_device *xe = dsb_buf->vma->bo->tile->xe; + WARN_ON(idx > (dsb_buf->buf_size - size) / sizeof(*dsb_buf->cmd_buf)); iosys_map_memset(&dsb_buf->vma->bo->vmap, idx * 4, val, size); + xe_device_l2_flush(xe); } bool intel_dsb_buffer_create(struct intel_crtc *crtc, struct intel_dsb_buffer *dsb_buf, size_t size) diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c index 423f367c7065..d7db44e79eaf 100644 --- a/drivers/gpu/drm/xe/display/xe_fb_pin.c +++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c @@ -10,6 +10,7 @@ #include "intel_fb.h" #include "intel_fb_pin.h" #include "xe_bo.h" +#include "xe_device.h" #include "xe_ggtt.h" #include "xe_gt.h" #include "xe_pm.h" @@ -304,6 +305,8 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb, if (ret) goto err_unpin; + /* Ensure DPT writes are flushed */ + xe_device_l2_flush(xe); return vma; err_unpin: diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h index d44564bad009..fd9d94174efb 100644 --- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h @@ -80,6 +80,9 @@ #define LE_CACHEABILITY_MASK REG_GENMASK(1, 0) #define LE_CACHEABILITY(value) REG_FIELD_PREP(LE_CACHEABILITY_MASK, value) +#define XE2_GAMREQSTRM_CTRL XE_REG(0x4194) +#define CG_DIS_CNTLBUS REG_BIT(6) + #define CCS_AUX_INV XE_REG(0x4208) #define VD0_AUX_INV XE_REG(0x4218) @@ -372,6 +375,11 @@ #define XEHPC_L3CLOS_MASK(i) XE_REG_MCR(0xb194 + (i) * 8) +#define XE2_GLOBAL_INVAL XE_REG(0xb404) + +#define SCRATCH1LPFC XE_REG(0xb474) +#define EN_L3_RW_CCS_CACHE_FLUSH REG_BIT(0) + #define XE2LPM_L3SQCREG5 XE_REG_MCR(0xb658) #define XE2_TDF_CTRL XE_REG(0xb418) diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index f2f1d8ddb221..6ce44ca2524d 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -54,6 +54,9 @@ #include "xe_vm.h" #include "xe_vram.h" #include "xe_wait_user_fence.h" +#include "xe_wa.h" + +#include static int xe_file_open(struct drm_device *dev, struct drm_file *file) { @@ -820,6 +823,11 @@ void xe_device_td_flush(struct xe_device *xe) if (!IS_DGFX(xe) || GRAPHICS_VER(xe) < 20) return; + if (XE_WA(xe_root_mmio_gt(xe), 16023588340)) { + xe_device_l2_flush(xe); + return; + } + for_each_gt(gt, xe, id) { if (xe_gt_is_media_type(gt)) continue; @@ -843,6 +851,28 @@ void xe_device_td_flush(struct xe_device *xe) } } +void xe_device_l2_flush(struct xe_device *xe) +{ + struct xe_gt *gt; + int err; + + gt = xe_root_mmio_gt(xe); + + if (!XE_WA(gt, 16023588340)) + return; + + err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT); + if (err) + return; + + xe_mmio_write32(gt, XE2_GLOBAL_INVAL, 0x1); + + if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 150, NULL, true)) + xe_gt_err_once(gt, "Global invalidation timeout\n"); + + xe_force_wake_put(gt_to_fw(gt), XE_FW_GT); +} + u32 xe_device_ccs_bytes(struct xe_device *xe, u64 size) { return xe_device_has_flat_ccs(xe) ? diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h index b3952718b3c1..533ccfb2567a 100644 --- a/drivers/gpu/drm/xe/xe_device.h +++ b/drivers/gpu/drm/xe/xe_device.h @@ -162,6 +162,7 @@ u64 xe_device_canonicalize_addr(struct xe_device *xe, u64 address); u64 xe_device_uncanonicalize_addr(struct xe_device *xe, u64 address); void xe_device_td_flush(struct xe_device *xe); +void xe_device_l2_flush(struct xe_device *xe); static inline bool xe_device_wedged(struct xe_device *xe) { diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 31b2e64c70c6..816ecc9e294c 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -11,6 +11,8 @@ #include #include +#include + #include "instructions/xe_gfxpipe_commands.h" #include "instructions/xe_mi_commands.h" #include "regs/xe_gt_regs.h" @@ -95,6 +97,51 @@ void xe_gt_sanitize(struct xe_gt *gt) gt->uc.guc.submission_state.enabled = false; } +static void xe_gt_enable_host_l2_vram(struct xe_gt *gt) +{ + u32 reg; + int err; + + if (!XE_WA(gt, 16023588340)) + return; + + err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT); + if (WARN_ON(err)) + return; + + if (!xe_gt_is_media_type(gt)) { + xe_mmio_write32(gt, SCRATCH1LPFC, EN_L3_RW_CCS_CACHE_FLUSH); + reg = xe_mmio_read32(gt, XE2_GAMREQSTRM_CTRL); + reg |= CG_DIS_CNTLBUS; + xe_mmio_write32(gt, XE2_GAMREQSTRM_CTRL, reg); + } + + xe_gt_mcr_multicast_write(gt, XEHPC_L3CLOS_MASK(3), 0x3); + xe_force_wake_put(gt_to_fw(gt), XE_FW_GT); +} + +static void xe_gt_disable_host_l2_vram(struct xe_gt *gt) +{ + u32 reg; + int err; + + if (!XE_WA(gt, 16023588340)) + return; + + if (xe_gt_is_media_type(gt)) + return; + + err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT); + if (WARN_ON(err)) + return; + + reg = xe_mmio_read32(gt, XE2_GAMREQSTRM_CTRL); + reg &= ~CG_DIS_CNTLBUS; + xe_mmio_write32(gt, XE2_GAMREQSTRM_CTRL, reg); + + xe_force_wake_put(gt_to_fw(gt), XE_FW_GT); +} + /** * xe_gt_remove() - Clean up the GT structures before driver removal * @gt: the GT object @@ -111,6 +158,8 @@ void xe_gt_remove(struct xe_gt *gt) for (i = 0; i < XE_ENGINE_CLASS_MAX; ++i) xe_hw_fence_irq_finish(>->fence_irq[i]); + + xe_gt_disable_host_l2_vram(gt); } static void gt_reset_worker(struct work_struct *w); @@ -508,6 +557,7 @@ int xe_gt_init_hwconfig(struct xe_gt *gt) xe_gt_mcr_init_early(gt); xe_pat_init(gt); + xe_gt_enable_host_l2_vram(gt); err = xe_uc_init(>->uc); if (err) @@ -643,6 +693,8 @@ static int do_gt_restart(struct xe_gt *gt) xe_pat_init(gt); + xe_gt_enable_host_l2_vram(gt); + xe_gt_mcr_set_implicit_defaults(gt); xe_reg_sr_apply_mmio(>->reg_sr, gt); @@ -796,6 +848,8 @@ int xe_gt_suspend(struct xe_gt *gt) xe_gt_idle_disable_pg(gt); + xe_gt_disable_host_l2_vram(gt); + XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL)); xe_gt_dbg(gt, "suspended\n"); diff --git a/drivers/gpu/drm/xe/xe_pat.c b/drivers/gpu/drm/xe/xe_pat.c index 4ee32ee1cc88..722278cc23fc 100644 --- a/drivers/gpu/drm/xe/xe_pat.c +++ b/drivers/gpu/drm/xe/xe_pat.c @@ -7,6 +7,8 @@ #include +#include + #include "regs/xe_reg_defs.h" #include "xe_assert.h" #include "xe_device.h" @@ -15,6 +17,7 @@ #include "xe_gt_mcr.h" #include "xe_mmio.h" #include "xe_sriov.h" +#include "xe_wa.h" #define _PAT_ATS 0x47fc #define _PAT_INDEX(index) _PICK_EVEN_2RANGES(index, 8, \ @@ -382,7 +385,13 @@ void xe_pat_init_early(struct xe_device *xe) if (GRAPHICS_VER(xe) == 20) { xe->pat.ops = &xe2_pat_ops; xe->pat.table = xe2_pat_table; - xe->pat.n_entries = ARRAY_SIZE(xe2_pat_table); + + /* Wa_16023588340. XXX: Should use XE_WA */ + if (GRAPHICS_VERx100(xe) == 2001) + xe->pat.n_entries = 28; /* Disable CLOS3 */ + else + xe->pat.n_entries = ARRAY_SIZE(xe2_pat_table); + xe->pat.idx[XE_CACHE_NONE] = 3; xe->pat.idx[XE_CACHE_WT] = 15; xe->pat.idx[XE_CACHE_WB] = 2; diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules index 26066beb4f6f..08f7336881e3 100644 --- a/drivers/gpu/drm/xe/xe_wa_oob.rules +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules @@ -29,3 +29,4 @@ 13011645652 GRAPHICS_VERSION(2004) 22019338487 MEDIA_VERSION(2000) GRAPHICS_VERSION(2001) +16023588340 GRAPHICS_VERSION(2001) From 03a2dc84f5c4ef31ac0112b29d51ff103f7c8dd4 Mon Sep 17 00:00:00 2001 From: Ngai-Mint Kwan Date: Mon, 1 Jul 2024 11:46:37 -0700 Subject: [PATCH 429/562] drm/xe/xe2lpm: Extend Wa_16021639441 Wa_16021639441 applies to Xe2_LPM. Signed-off-by: Ngai-Mint Kwan Reviewed-by: Matt Roper Signed-off-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20240701184637.531794-1-ngai-mint.kwan@linux.intel.com (cherry picked from commit 74e3076800067c6dc0dcff5b75344cec064c20eb) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_wa.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c index c7bf0862b231..6c52d9d02b5f 100644 --- a/drivers/gpu/drm/xe/xe_wa.c +++ b/drivers/gpu/drm/xe/xe_wa.c @@ -539,6 +539,16 @@ static const struct xe_rtp_entry_sr engine_was[] = { XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE)) }, + /* Xe2_LPM */ + + { XE_RTP_NAME("16021639441"), + XE_RTP_RULES(MEDIA_VERSION(2000)), + XE_RTP_ACTIONS(SET(CSFE_CHICKEN1(0), + GHWSP_CSB_REPORT_DIS | + PPHWSP_CSB_AND_TIMESTAMP_REPORT_DIS, + XE_RTP_ACTION_FLAG(ENGINE_BASE))) + }, + /* Xe2_HPM */ { XE_RTP_NAME("16021639441"), From b196e6fcc71186134b4cfe756067d87ae41b1ed9 Mon Sep 17 00:00:00 2001 From: Bommu Krishnaiah Date: Wed, 3 Jul 2024 14:37:54 +0530 Subject: [PATCH 430/562] drm/xe/xe2lpg: Extend workaround 14021402888 workaround 14021402888 also applies to Xe2_LPG. Replicate the existing entry to one specific for Xe2_LPG. Signed-off-by: Bommu Krishnaiah Cc: Tejas Upadhyay Cc: Matt Roper Cc: Himal Prasad Ghimiray Reviewed-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20240703090754.1323647-1-krishnaiah.bommu@intel.com Signed-off-by: Lucas De Marchi (cherry picked from commit 56ab6986992ba143aee0bda33e15a764343e271d) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_wa.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c index 6c52d9d02b5f..fd009b2c68fa 100644 --- a/drivers/gpu/drm/xe/xe_wa.c +++ b/drivers/gpu/drm/xe/xe_wa.c @@ -486,6 +486,10 @@ static const struct xe_rtp_entry_sr engine_was[] = { XE_RTP_RULES(GRAPHICS_VERSION(2004), FUNC(xe_rtp_match_first_render_or_compute)), XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, SLM_WMTP_RESTORE)) }, + { XE_RTP_NAME("14021402888"), + XE_RTP_RULES(GRAPHICS_VERSION(2004), ENGINE_CLASS(RENDER)), + XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE)) + }, /* Xe2_HPG */ From 7e81285380743aa5759bb29a388f056c3d326a2c Mon Sep 17 00:00:00 2001 From: Tejas Upadhyay Date: Wed, 10 Jul 2024 10:57:50 +0530 Subject: [PATCH 431/562] drm/xe/xe2: Make subsequent L2 flush sequential Issuing the flush on top of an ongoing flush is not desirable. Lets use lock to make it sequential. Reviewed-by: Nirmoy Das Signed-off-by: Tejas Upadhyay Link: https://patchwork.freedesktop.org/patch/msgid/20240710052750.3031586-1-tejas.upadhyay@intel.com Signed-off-by: Nirmoy Das (cherry picked from commit 71733b8d7f50b61403f940c6c9745fb3a9b98dcb) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_device.c | 2 ++ drivers/gpu/drm/xe/xe_gt.c | 1 + drivers/gpu/drm/xe/xe_gt_types.h | 6 ++++++ 3 files changed, 9 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 6ce44ca2524d..c89deffffb6d 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -865,10 +865,12 @@ void xe_device_l2_flush(struct xe_device *xe) if (err) return; + spin_lock(>->global_invl_lock); xe_mmio_write32(gt, XE2_GLOBAL_INVAL, 0x1); if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 150, NULL, true)) xe_gt_err_once(gt, "Global invalidation timeout\n"); + spin_unlock(>->global_invl_lock); xe_force_wake_put(gt_to_fw(gt), XE_FW_GT); } diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 816ecc9e294c..b9bcbbe27705 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -388,6 +388,7 @@ int xe_gt_init_early(struct xe_gt *gt) xe_force_wake_init_gt(gt, gt_to_fw(gt)); xe_pcode_init(gt); + spin_lock_init(>->global_invl_lock); return 0; } diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h index 6b5e0b45efb0..38a0d0e178c8 100644 --- a/drivers/gpu/drm/xe/xe_gt_types.h +++ b/drivers/gpu/drm/xe/xe_gt_types.h @@ -362,6 +362,12 @@ struct xe_gt { */ spinlock_t mcr_lock; + /** + * @global_invl_lock: protects the register for the duration + * of a global invalidation of l2 cache + */ + spinlock_t global_invl_lock; + /** @wa_active: keep track of active workarounds */ struct { /** @wa_active.gt: bitmap with active GT workarounds */ From cbc6e98ab11bea52789d2835e45e8816c39407e1 Mon Sep 17 00:00:00 2001 From: Tejas Upadhyay Date: Tue, 9 Jul 2024 21:26:06 +0530 Subject: [PATCH 432/562] drm/xe/xe2: Add Wa_15015404425 Wa_15015404425 asks us to perform four "dummy" writes to a non-existent register offset before every real register read. Although the specific offset of the writes doesn't directly matter, the workaround suggests offset 0x130030 as a good target so that these writes will be easy to recognize and filter out in debugging traces. V5(MattR): - Avoid negating an equality comparison V4(MattR): - Use writel and remove xe_reg usage V3(MattR): - Define dummy reg local to function - Avoid tracing dummy writes - Update commit message V2: - Add WA to 8/16/32bit reads also - MattR - Corrected dummy reg address - MattR - Use for loop to avoid mental pause - JaniN Reviewed-by: Matt Roper Signed-off-by: Tejas Upadhyay Signed-off-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20240709155606.2998941-1-tejas.upadhyay@intel.com (cherry picked from commit 86c5b70a9c0c3f05f7002ef8b789460c96b54e27) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_mmio.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c index 83122c77edd9..aa68cac9fdf8 100644 --- a/drivers/gpu/drm/xe/xe_mmio.c +++ b/drivers/gpu/drm/xe/xe_mmio.c @@ -124,12 +124,29 @@ int xe_mmio_init(struct xe_device *xe) return devm_add_action_or_reset(xe->drm.dev, mmio_fini, xe); } +static void mmio_flush_pending_writes(struct xe_gt *gt) +{ +#define DUMMY_REG_OFFSET 0x130030 + struct xe_tile *tile = gt_to_tile(gt); + int i; + + if (tile->xe->info.platform != XE_LUNARLAKE) + return; + + /* 4 dummy writes */ + for (i = 0; i < 4; i++) + writel(0, tile->mmio.regs + DUMMY_REG_OFFSET); +} + u8 xe_mmio_read8(struct xe_gt *gt, struct xe_reg reg) { struct xe_tile *tile = gt_to_tile(gt); u32 addr = xe_mmio_adjusted_addr(gt, reg.addr); u8 val; + /* Wa_15015404425 */ + mmio_flush_pending_writes(gt); + val = readb((reg.ext ? tile->mmio_ext.regs : tile->mmio.regs) + addr); trace_xe_reg_rw(gt, false, addr, val, sizeof(val)); @@ -142,6 +159,9 @@ u16 xe_mmio_read16(struct xe_gt *gt, struct xe_reg reg) u32 addr = xe_mmio_adjusted_addr(gt, reg.addr); u16 val; + /* Wa_15015404425 */ + mmio_flush_pending_writes(gt); + val = readw((reg.ext ? tile->mmio_ext.regs : tile->mmio.regs) + addr); trace_xe_reg_rw(gt, false, addr, val, sizeof(val)); @@ -163,6 +183,9 @@ u32 xe_mmio_read32(struct xe_gt *gt, struct xe_reg reg) u32 addr = xe_mmio_adjusted_addr(gt, reg.addr); u32 val; + /* Wa_15015404425 */ + mmio_flush_pending_writes(gt); + if (!reg.vf && IS_SRIOV_VF(gt_to_xe(gt))) val = xe_gt_sriov_vf_read32(gt, reg); else From f5cb1275c8ce56c7583cb323cfa08a820a7ef6b4 Mon Sep 17 00:00:00 2001 From: Daniele Ceraolo Spurio Date: Wed, 7 Aug 2024 16:53:32 -0700 Subject: [PATCH 433/562] drm/xe: fix WA 14018094691 This WA is applied while initializing the media GT, but it a primary GT WA (because it modifies a register on the primary GT), so the XE_WA macro is returning false even when the WA should be applied. Fix this by using the primary GT in the macro. Note that this WA only applies to PXP and we don't yet support that in Xe, so there are no negative effects to this bug, which is why we didn't see any errors in testing. v2: use the primary GT in the macro instead of marking the WA as platform-wide (Lucas, Matt). Signed-off-by: Daniele Ceraolo Spurio Cc: Matt Roper Cc: Lucas De Marchi Reviewed-by: Matt Roper Reviewed-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20240807235333.1370915-1-daniele.ceraolospurio@intel.com (cherry picked from commit e422c0bfd9e47e399e86bcc483f49d8b54064fc2) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_gsc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c index f8239a13fa2b..77ce44e845c5 100644 --- a/drivers/gpu/drm/xe/xe_gsc.c +++ b/drivers/gpu/drm/xe/xe_gsc.c @@ -260,7 +260,7 @@ static int gsc_upload_and_init(struct xe_gsc *gsc) struct xe_tile *tile = gt_to_tile(gt); int ret; - if (XE_WA(gt, 14018094691)) { + if (XE_WA(tile->primary_gt, 14018094691)) { ret = xe_force_wake_get(gt_to_fw(tile->primary_gt), XE_FORCEWAKE_ALL); /* @@ -278,7 +278,7 @@ static int gsc_upload_and_init(struct xe_gsc *gsc) ret = gsc_upload(gsc); - if (XE_WA(gt, 14018094691)) + if (XE_WA(tile->primary_gt, 14018094691)) xe_force_wake_put(gt_to_fw(tile->primary_gt), XE_FORCEWAKE_ALL); if (ret) From 8776b0234e1d008d8f19b26f6c3af1cfa6187070 Mon Sep 17 00:00:00 2001 From: Tejas Upadhyay Date: Mon, 12 Aug 2024 19:11:17 +0530 Subject: [PATCH 434/562] drm/xe/xe2hpg: Add Wa_14021821874 Wa_14021821874 applies to xe2_hpg V2(Himal): - Use space after define Cc: Matt Roper Reviewed-by: Himal Prasad Ghimiray Signed-off-by: Tejas Upadhyay Reviewed-by: Matt Roper Signed-off-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20240812134117.813670-1-tejas.upadhyay@intel.com (cherry picked from commit 21ff3a16e92e2fa4f906a61d148aca1423c58298) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/regs/xe_gt_regs.h | 1 + drivers/gpu/drm/xe/xe_wa.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h index fd9d94174efb..3c2865040058 100644 --- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h @@ -437,6 +437,7 @@ #define DIS_FIX_EOT1_FLUSH REG_BIT(9) #define TDL_TSL_CHICKEN XE_REG_MCR(0xe4c4, XE_REG_OPTION_MASKED) +#define STK_ID_RESTRICT REG_BIT(12) #define SLM_WMTP_RESTORE REG_BIT(11) #define ROW_CHICKEN XE_REG_MCR(0xe4f0, XE_REG_OPTION_MASKED) diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c index fd009b2c68fa..e648265d081b 100644 --- a/drivers/gpu/drm/xe/xe_wa.c +++ b/drivers/gpu/drm/xe/xe_wa.c @@ -542,6 +542,10 @@ static const struct xe_rtp_entry_sr engine_was[] = { XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)), XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE)) }, + { XE_RTP_NAME("14021821874"), + XE_RTP_RULES(GRAPHICS_VERSION(2001), FUNC(xe_rtp_match_first_render_or_compute)), + XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, STK_ID_RESTRICT)) + }, /* Xe2_LPM */ From 8636a5c29be1f05b5162a5c82c874338b6717759 Mon Sep 17 00:00:00 2001 From: Daniele Ceraolo Spurio Date: Fri, 9 Aug 2024 16:12:35 -0700 Subject: [PATCH 435/562] drm/xe: use devm instead of drmm for managed bo The BO cleanup touches the GGTT and therefore requires the HW to be available, so we need to use devm instead of drmm. Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/1160 Signed-off-by: Daniele Ceraolo Spurio Cc: Lucas De Marchi Cc: Matthew Auld Reviewed-by: Matthew Auld Reviewed-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20240809231237.1503796-2-daniele.ceraolospurio@intel.com Signed-off-by: Lucas De Marchi (cherry picked from commit 8d3a2d3d766a823c7510cdc17e6ff7c042c63b61) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_bo.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 31192d983d9e..261d3d6c8a93 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -1575,7 +1575,7 @@ struct xe_bo *xe_bo_create_from_data(struct xe_device *xe, struct xe_tile *tile, return bo; } -static void __xe_bo_unpin_map_no_vm(struct drm_device *drm, void *arg) +static void __xe_bo_unpin_map_no_vm(void *arg) { xe_bo_unpin_map_no_vm(arg); } @@ -1590,7 +1590,7 @@ struct xe_bo *xe_managed_bo_create_pin_map(struct xe_device *xe, struct xe_tile if (IS_ERR(bo)) return bo; - ret = drmm_add_action_or_reset(&xe->drm, __xe_bo_unpin_map_no_vm, bo); + ret = devm_add_action_or_reset(xe->drm.dev, __xe_bo_unpin_map_no_vm, bo); if (ret) return ERR_PTR(ret); @@ -1638,7 +1638,7 @@ int xe_managed_bo_reinit_in_vram(struct xe_device *xe, struct xe_tile *tile, str if (IS_ERR(bo)) return PTR_ERR(bo); - drmm_release_action(&xe->drm, __xe_bo_unpin_map_no_vm, *src); + devm_release_action(xe->drm.dev, __xe_bo_unpin_map_no_vm, *src); *src = bo; return 0; From a06a7b3429e2548a28bb661f17347b8ffe4a8a15 Mon Sep 17 00:00:00 2001 From: Daniele Ceraolo Spurio Date: Thu, 15 Aug 2024 16:05:40 -0700 Subject: [PATCH 436/562] drm/xe/uc: Use devm to register cleanup that includes exec_queues Exec_queue cleanup requires HW access, so we need to use devm instead of drmm for it. Signed-off-by: Daniele Ceraolo Spurio Cc: John Harrison Cc: Alan Previn Reviewed-by: Matthew Brost Reviewed-by: Lucas De Marchi Reviewed-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20240815230541.3828206-2-lucas.demarchi@intel.com Signed-off-by: Lucas De Marchi (cherry picked from commit 5a891a0e69f134f53cc91b409f38e5ea1cafaf0a) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_gsc.c | 4 ++-- drivers/gpu/drm/xe/xe_guc_submit.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c index 77ce44e845c5..2a612652bb13 100644 --- a/drivers/gpu/drm/xe/xe_gsc.c +++ b/drivers/gpu/drm/xe/xe_gsc.c @@ -437,7 +437,7 @@ out: return ret; } -static void free_resources(struct drm_device *drm, void *arg) +static void free_resources(void *arg) { struct xe_gsc *gsc = arg; @@ -501,7 +501,7 @@ int xe_gsc_init_post_hwconfig(struct xe_gsc *gsc) gsc->q = q; gsc->wq = wq; - err = drmm_add_action_or_reset(&xe->drm, free_resources, gsc); + err = devm_add_action_or_reset(xe->drm.dev, free_resources, gsc); if (err) return err; diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 6398629e6b4e..77b0f0d8f729 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -284,7 +284,7 @@ static void guc_submit_fini(struct drm_device *drm, void *arg) free_submit_wq(guc); } -static void guc_submit_wedged_fini(struct drm_device *drm, void *arg) +static void guc_submit_wedged_fini(void *arg) { struct xe_guc *guc = arg; struct xe_exec_queue *q; @@ -877,7 +877,7 @@ void xe_guc_submit_wedge(struct xe_guc *guc) xe_gt_assert(guc_to_gt(guc), guc_to_xe(guc)->wedged.mode); - err = drmm_add_action_or_reset(&guc_to_xe(guc)->drm, + err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev, guc_submit_wedged_fini, guc); if (err) { drm_err(&xe->drm, "Failed to register xe_guc_submit clean-up on wedged.mode=2. Although device is wedged.\n"); From 4e870e6bbec5c41c0d8b253282dca9465fbf5044 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Mon, 19 Aug 2024 17:04:42 -0700 Subject: [PATCH 437/562] Input: himax_hx83112b - fix incorrect size when reading product ID We need to read a u32 value (4 bytes), not size of a pointer to that value. Also, himax_read_mcu() wrapper is an overkill, remove it and use himax_bus_read() directly. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202408200301.Ujpj7Vov-lkp@intel.com/ Fixes: 0944829d491e ("Input: himax_hx83112b - implement MCU register reading") Tested-by: Felix Kaechele Link: https://lore.kernel.org/r/ZsPdmtfC54R7JVxR@google.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/himax_hx83112b.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/drivers/input/touchscreen/himax_hx83112b.c b/drivers/input/touchscreen/himax_hx83112b.c index 9ed3bccde4ac..896a145ddb2b 100644 --- a/drivers/input/touchscreen/himax_hx83112b.c +++ b/drivers/input/touchscreen/himax_hx83112b.c @@ -130,17 +130,6 @@ static int himax_bus_read(struct himax_ts_data *ts, u32 address, void *dst, return 0; } -static int himax_read_mcu(struct himax_ts_data *ts, u32 address, u32 *dst) -{ - int error; - - error = himax_bus_read(ts, address, dst, sizeof(dst)); - if (error) - return error; - - return 0; -} - static void himax_reset(struct himax_ts_data *ts) { gpiod_set_value_cansleep(ts->gpiod_rst, 1); @@ -160,7 +149,8 @@ static int himax_read_product_id(struct himax_ts_data *ts, u32 *product_id) { int error; - error = himax_read_mcu(ts, HIMAX_REG_ADDR_ICID, product_id); + error = himax_bus_read(ts, HIMAX_REG_ADDR_ICID, product_id, + sizeof(*product_id)); if (error) return error; From ce335db0621648472f9bb4b7191eb2e13a5793cf Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Fri, 16 Aug 2024 18:29:17 +0800 Subject: [PATCH 438/562] net: mctp: test: Use correct skb for route input check In the MCTP route input test, we're routing one skb, then (when delivery is expected) checking the resulting routed skb. However, we're currently checking the original skb length, rather than the routed skb. Check the routed skb instead; the original will have been freed at this point. Fixes: 8892c0490779 ("mctp: Add route input to socket tests") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/kernel-janitors/4ad204f0-94cf-46c5-bdab-49592addf315@kili.mountain/ Signed-off-by: Jeremy Kerr Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240816-mctp-kunit-skb-fix-v1-1-3c367ac89c27@codeconstruct.com.au Signed-off-by: Jakub Kicinski --- net/mctp/test/route-test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index 77e5dd422258..8551dab1d1e6 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -366,7 +366,7 @@ static void mctp_test_route_input_sk(struct kunit *test) skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc); KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2); - KUNIT_EXPECT_EQ(test, skb->len, 1); + KUNIT_EXPECT_EQ(test, skb2->len, 1); skb_free_datagram(sock->sk, skb2); From 807067bf014d4a3ae2cc55bd3de16f22a01eb580 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 15 Aug 2024 15:04:37 -0700 Subject: [PATCH 439/562] kcm: Serialise kcm_sendmsg() for the same socket. syzkaller reported UAF in kcm_release(). [0] The scenario is 1. Thread A builds a skb with MSG_MORE and sets kcm->seq_skb. 2. Thread A resumes building skb from kcm->seq_skb but is blocked by sk_stream_wait_memory() 3. Thread B calls sendmsg() concurrently, finishes building kcm->seq_skb and puts the skb to the write queue 4. Thread A faces an error and finally frees skb that is already in the write queue 5. kcm_release() does double-free the skb in the write queue When a thread is building a MSG_MORE skb, another thread must not touch it. Let's add a per-sk mutex and serialise kcm_sendmsg(). [0]: BUG: KASAN: slab-use-after-free in __skb_unlink include/linux/skbuff.h:2366 [inline] BUG: KASAN: slab-use-after-free in __skb_dequeue include/linux/skbuff.h:2385 [inline] BUG: KASAN: slab-use-after-free in __skb_queue_purge_reason include/linux/skbuff.h:3175 [inline] BUG: KASAN: slab-use-after-free in __skb_queue_purge include/linux/skbuff.h:3181 [inline] BUG: KASAN: slab-use-after-free in kcm_release+0x170/0x4c8 net/kcm/kcmsock.c:1691 Read of size 8 at addr ffff0000ced0fc80 by task syz-executor329/6167 CPU: 1 PID: 6167 Comm: syz-executor329 Tainted: G B 6.8.0-rc5-syzkaller-g9abbc24128bc #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024 Call trace: dump_backtrace+0x1b8/0x1e4 arch/arm64/kernel/stacktrace.c:291 show_stack+0x2c/0x3c arch/arm64/kernel/stacktrace.c:298 __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd0/0x124 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:377 [inline] print_report+0x178/0x518 mm/kasan/report.c:488 kasan_report+0xd8/0x138 mm/kasan/report.c:601 __asan_report_load8_noabort+0x20/0x2c mm/kasan/report_generic.c:381 __skb_unlink include/linux/skbuff.h:2366 [inline] __skb_dequeue include/linux/skbuff.h:2385 [inline] __skb_queue_purge_reason include/linux/skbuff.h:3175 [inline] __skb_queue_purge include/linux/skbuff.h:3181 [inline] kcm_release+0x170/0x4c8 net/kcm/kcmsock.c:1691 __sock_release net/socket.c:659 [inline] sock_close+0xa4/0x1e8 net/socket.c:1421 __fput+0x30c/0x738 fs/file_table.c:376 ____fput+0x20/0x30 fs/file_table.c:404 task_work_run+0x230/0x2e0 kernel/task_work.c:180 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0x618/0x1f64 kernel/exit.c:871 do_group_exit+0x194/0x22c kernel/exit.c:1020 get_signal+0x1500/0x15ec kernel/signal.c:2893 do_signal+0x23c/0x3b44 arch/arm64/kernel/signal.c:1249 do_notify_resume+0x74/0x1f4 arch/arm64/kernel/entry-common.c:148 exit_to_user_mode_prepare arch/arm64/kernel/entry-common.c:169 [inline] exit_to_user_mode arch/arm64/kernel/entry-common.c:178 [inline] el0_svc+0xac/0x168 arch/arm64/kernel/entry-common.c:713 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Allocated by task 6166: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_alloc_info+0x70/0x84 mm/kasan/generic.c:626 unpoison_slab_object mm/kasan/common.c:314 [inline] __kasan_slab_alloc+0x74/0x8c mm/kasan/common.c:340 kasan_slab_alloc include/linux/kasan.h:201 [inline] slab_post_alloc_hook mm/slub.c:3813 [inline] slab_alloc_node mm/slub.c:3860 [inline] kmem_cache_alloc_node+0x204/0x4c0 mm/slub.c:3903 __alloc_skb+0x19c/0x3d8 net/core/skbuff.c:641 alloc_skb include/linux/skbuff.h:1296 [inline] kcm_sendmsg+0x1d3c/0x2124 net/kcm/kcmsock.c:783 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg net/socket.c:745 [inline] sock_sendmsg+0x220/0x2c0 net/socket.c:768 splice_to_socket+0x7cc/0xd58 fs/splice.c:889 do_splice_from fs/splice.c:941 [inline] direct_splice_actor+0xec/0x1d8 fs/splice.c:1164 splice_direct_to_actor+0x438/0xa0c fs/splice.c:1108 do_splice_direct_actor fs/splice.c:1207 [inline] do_splice_direct+0x1e4/0x304 fs/splice.c:1233 do_sendfile+0x460/0xb3c fs/read_write.c:1295 __do_sys_sendfile64 fs/read_write.c:1362 [inline] __se_sys_sendfile64 fs/read_write.c:1348 [inline] __arm64_sys_sendfile64+0x160/0x3b4 fs/read_write.c:1348 __invoke_syscall arch/arm64/kernel/syscall.c:37 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:51 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:136 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:155 el0_svc+0x54/0x168 arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Freed by task 6167: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_free_info+0x5c/0x74 mm/kasan/generic.c:640 poison_slab_object+0x124/0x18c mm/kasan/common.c:241 __kasan_slab_free+0x3c/0x78 mm/kasan/common.c:257 kasan_slab_free include/linux/kasan.h:184 [inline] slab_free_hook mm/slub.c:2121 [inline] slab_free mm/slub.c:4299 [inline] kmem_cache_free+0x15c/0x3d4 mm/slub.c:4363 kfree_skbmem+0x10c/0x19c __kfree_skb net/core/skbuff.c:1109 [inline] kfree_skb_reason+0x240/0x6f4 net/core/skbuff.c:1144 kfree_skb include/linux/skbuff.h:1244 [inline] kcm_release+0x104/0x4c8 net/kcm/kcmsock.c:1685 __sock_release net/socket.c:659 [inline] sock_close+0xa4/0x1e8 net/socket.c:1421 __fput+0x30c/0x738 fs/file_table.c:376 ____fput+0x20/0x30 fs/file_table.c:404 task_work_run+0x230/0x2e0 kernel/task_work.c:180 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0x618/0x1f64 kernel/exit.c:871 do_group_exit+0x194/0x22c kernel/exit.c:1020 get_signal+0x1500/0x15ec kernel/signal.c:2893 do_signal+0x23c/0x3b44 arch/arm64/kernel/signal.c:1249 do_notify_resume+0x74/0x1f4 arch/arm64/kernel/entry-common.c:148 exit_to_user_mode_prepare arch/arm64/kernel/entry-common.c:169 [inline] exit_to_user_mode arch/arm64/kernel/entry-common.c:178 [inline] el0_svc+0xac/0x168 arch/arm64/kernel/entry-common.c:713 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 The buggy address belongs to the object at ffff0000ced0fc80 which belongs to the cache skbuff_head_cache of size 240 The buggy address is located 0 bytes inside of freed 240-byte region [ffff0000ced0fc80, ffff0000ced0fd70) The buggy address belongs to the physical page: page:00000000d35f4ae4 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x10ed0f flags: 0x5ffc00000000800(slab|node=0|zone=2|lastcpupid=0x7ff) page_type: 0xffffffff() raw: 05ffc00000000800 ffff0000c1cbf640 fffffdffc3423100 dead000000000004 raw: 0000000000000000 00000000000c000c 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff0000ced0fb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff0000ced0fc00: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc >ffff0000ced0fc80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff0000ced0fd00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fc fc ffff0000ced0fd80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module") Reported-by: syzbot+b72d86aa5df17ce74c60@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=b72d86aa5df17ce74c60 Tested-by: syzbot+b72d86aa5df17ce74c60@syzkaller.appspotmail.com Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240815220437.69511-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/kcm.h | 1 + net/kcm/kcmsock.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/include/net/kcm.h b/include/net/kcm.h index 90279e5e09a5..441e993be634 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -70,6 +70,7 @@ struct kcm_sock { struct work_struct tx_work; struct list_head wait_psock_list; struct sk_buff *seq_skb; + struct mutex tx_mutex; u32 tx_stopped : 1; /* Don't use bit fields here, these are set under different locks */ diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 2f191e50d4fc..d4118c796290 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -755,6 +755,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); int err = -EPIPE; + mutex_lock(&kcm->tx_mutex); lock_sock(sk); /* Per tcp_sendmsg this should be in poll */ @@ -926,6 +927,7 @@ partial_message: KCM_STATS_ADD(kcm->stats.tx_bytes, copied); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return copied; out_error: @@ -951,6 +953,7 @@ out_error: sk->sk_write_space(sk); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return err; } @@ -1204,6 +1207,7 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) spin_unlock_bh(&mux->lock); INIT_WORK(&kcm->tx_work, kcm_tx_work); + mutex_init(&kcm->tx_mutex); spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); From 2102bdac67b55bf2d1df4ff757bced74e94a5f74 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 17 Aug 2024 21:03:07 -0400 Subject: [PATCH 440/562] bcachefs: Extra debug for data move path We don't have sufficient information to debug: https://github.com/koverstreet/bcachefs/issues/726 - print out durability of extent ptrs, when non default - print the number of replicas we need in data_update_to_text() Signed-off-by: Kent Overstreet --- fs/bcachefs/data_update.c | 3 +++ fs/bcachefs/extents.c | 2 ++ 2 files changed, 5 insertions(+) diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 6a854c918496..1ca628e93e87 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -475,6 +475,9 @@ void bch2_data_update_opts_to_text(struct printbuf *out, struct bch_fs *c, bch2_compression_opt_to_text(out, background_compression(*io_opts)); prt_newline(out); + prt_str(out, "opts.replicas:\t"); + prt_u64(out, io_opts->data_replicas); + prt_str(out, "extra replicas:\t"); prt_u64(out, data_opts->extra_replicas); } diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index 4419ad3e454e..9406f82fc255 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -1017,6 +1017,8 @@ void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *c, const struc prt_printf(out, "ptr: %u:%llu:%u gen %u", ptr->dev, b, offset, ptr->gen); + if (ca->mi.durability != 1) + prt_printf(out, " d=%u", ca->mi.durability); if (ptr->cached) prt_str(out, " cached"); if (ptr->unwritten) From 50f2b98dc83de7809a5c5bf0ccf9af2e75c37c13 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 13 Aug 2024 10:59:08 +0100 Subject: [PATCH 441/562] MIPS: cevt-r4k: Don't call get_c0_compare_int if timer irq is installed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This avoids warning: [ 0.118053] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:283 Caused by get_c0_compare_int on secondary CPU. We also skipped saving IRQ number to struct clock_event_device *cd as it's never used by clockevent core, as per comments it's only meant for "non CPU local devices". Reported-by: Serge Semin Closes: https://lore.kernel.org/linux-mips/6szkkqxpsw26zajwysdrwplpjvhl5abpnmxgu2xuj3dkzjnvsf@4daqrz4mf44k/ Signed-off-by: Jiaxun Yang Reviewed-by: Philippe Mathieu-Daudé Reviewed-by: Serge Semin Tested-by: Serge Semin Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/cevt-r4k.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c index 368e8475870f..5f6e9e2ebbdb 100644 --- a/arch/mips/kernel/cevt-r4k.c +++ b/arch/mips/kernel/cevt-r4k.c @@ -303,13 +303,6 @@ int r4k_clockevent_init(void) if (!c0_compare_int_usable()) return -ENXIO; - /* - * With vectored interrupts things are getting platform specific. - * get_c0_compare_int is a hook to allow a platform to return the - * interrupt number of its liking. - */ - irq = get_c0_compare_int(); - cd = &per_cpu(mips_clockevent_device, cpu); cd->name = "MIPS"; @@ -320,7 +313,6 @@ int r4k_clockevent_init(void) min_delta = calculate_min_delta(); cd->rating = 300; - cd->irq = irq; cd->cpumask = cpumask_of(cpu); cd->set_next_event = mips_next_event; cd->event_handler = mips_event_handler; @@ -332,6 +324,13 @@ int r4k_clockevent_init(void) cp0_timer_irq_installed = 1; + /* + * With vectored interrupts things are getting platform specific. + * get_c0_compare_int is a hook to allow a platform to return the + * interrupt number of its liking. + */ + irq = get_c0_compare_int(); + if (request_irq(irq, c0_compare_interrupt, flags, "timer", c0_compare_interrupt)) pr_err("Failed to request irq %d (timer)\n", irq); From 1eacdd71b3436b54d5fc8218c4bb0187d92a6892 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 20 Aug 2024 09:54:30 +0200 Subject: [PATCH 442/562] netfilter: nft_counter: Disable BH in nft_counter_offload_stats(). The sequence counter nft_counter_seq is a per-CPU counter. There is no lock associated with it. nft_counter_do_eval() is using the same counter and disables BH which suggest that it can be invoked from a softirq. This in turn means that nft_counter_offload_stats(), which disables only preemption, can be interrupted by nft_counter_do_eval() leading to two writer for one seqcount_t. This can lead to loosing stats or reading statistics while they are updated. Disable BH during stats update in nft_counter_offload_stats() to ensure one writer at a time. Fixes: b72920f6e4a9d ("netfilter: nftables: counter hardware offload support") Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_counter.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 291ed2026367..16f40b503d37 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -265,7 +265,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr, struct nft_counter *this_cpu; seqcount_t *myseq; - preempt_disable(); + local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); myseq = this_cpu_ptr(&nft_counter_seq); @@ -273,7 +273,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr, this_cpu->packets += stats->pkts; this_cpu->bytes += stats->bytes; write_seqcount_end(myseq); - preempt_enable(); + local_bh_enable(); } void nft_counter_init_seqcount(void) From a0b39e2dc7017ac667b70bdeee5293e410fab2fb Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 20 Aug 2024 09:54:31 +0200 Subject: [PATCH 443/562] netfilter: nft_counter: Synchronize nft_counter_reset() against reader. nft_counter_reset() resets the counter by subtracting the previously retrieved value from the counter. This is a write operation on the counter and as such it requires to be performed with a write sequence of nft_counter_seq to serialize against its possible reader. Update the packets/ bytes within write-sequence of nft_counter_seq. Fixes: d84701ecbcd6a ("netfilter: nft_counter: rework atomic dump and reset") Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_counter.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 16f40b503d37..eab0dc66bee6 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -107,11 +107,16 @@ static void nft_counter_reset(struct nft_counter_percpu_priv *priv, struct nft_counter *total) { struct nft_counter *this_cpu; + seqcount_t *myseq; local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); + myseq = this_cpu_ptr(&nft_counter_seq); + + write_seqcount_begin(myseq); this_cpu->packets -= total->packets; this_cpu->bytes -= total->bytes; + write_seqcount_end(myseq); local_bh_enable(); } From 46ee21e9f59205e54943dfe51b2dc8a9352ca37d Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Fri, 16 Aug 2024 09:36:26 -0700 Subject: [PATCH 444/562] platform/x86: ISST: Fix return value on last invalid resource MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When only the last resource is invalid, tpmi_sst_dev_add() is returing error even if there are other valid resources before. This function should return error when there are no valid resources. Here tpmi_sst_dev_add() is returning "ret" variable. But this "ret" variable contains the failure status of last call to sst_main(), which failed for the invalid resource. But there may be other valid resources before the last entry. To address this, do not update "ret" variable for sst_main() return status. If there are no valid resources, it is already checked for by !inst below the loop and -ENODEV is returned. Fixes: 9d1d36268f3d ("platform/x86: ISST: Support partitioned systems") Signed-off-by: Srinivas Pandruvada Cc: stable@vger.kernel.org # 6.10+ Link: https://lore.kernel.org/r/20240816163626.415762-1-srinivas.pandruvada@linux.intel.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c index 7fa360073f6e..404582307109 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c @@ -1549,8 +1549,7 @@ int tpmi_sst_dev_add(struct auxiliary_device *auxdev) goto unlock_free; } - ret = sst_main(auxdev, &pd_info[i]); - if (ret) { + if (sst_main(auxdev, &pd_info[i])) { /* * This entry is not valid, hardware can partially * populate dies. In this case MMIO will have 0xFFs. From 4b3e33fcc38f7750604b065c55a43e94c5bc3145 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Thu, 15 Aug 2024 17:14:16 +0200 Subject: [PATCH 445/562] ip6_tunnel: Fix broken GRO GRO code checks for matching layer 2 headers to see, if packet belongs to the same flow and because ip6 tunnel set dev->hard_header_len this check fails in cases, where it shouldn't. To fix this don't set hard_header_len, but use needed_headroom like ipv4/ip_tunnel.c does. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Thomas Bogendoerfer Link: https://patch.msgid.link/20240815151419.109864-1-tbogendoerfer@suse.de Signed-off-by: Paolo Abeni --- net/ipv6/ip6_tunnel.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 9dee0c127955..87dfb565a9f8 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1507,7 +1507,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) tdev = __dev_get_by_index(t->net, p->link); if (tdev) { - dev->hard_header_len = tdev->hard_header_len + t_hlen; + dev->needed_headroom = tdev->hard_header_len + + tdev->needed_headroom + t_hlen; mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU); mtu = mtu - t_hlen; @@ -1731,7 +1732,9 @@ ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr, int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { struct ip6_tnl *tnl = netdev_priv(dev); + int t_hlen; + t_hlen = tnl->hlen + sizeof(struct ipv6hdr); if (tnl->parms.proto == IPPROTO_IPV6) { if (new_mtu < IPV6_MIN_MTU) return -EINVAL; @@ -1740,10 +1743,10 @@ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; } if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) { - if (new_mtu > IP6_MAX_MTU - dev->hard_header_len) + if (new_mtu > IP6_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } else { - if (new_mtu > IP_MAX_MTU - dev->hard_header_len) + if (new_mtu > IP_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); @@ -1887,12 +1890,11 @@ ip6_tnl_dev_init_gen(struct net_device *dev) t_hlen = t->hlen + sizeof(struct ipv6hdr); dev->type = ARPHRD_TUNNEL6; - dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len; + dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len - t_hlen; netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); From 6275c7bc8dd07644ea8142a1773d826800f0f3f7 Mon Sep 17 00:00:00 2001 From: Ben Whitten Date: Sun, 11 Aug 2024 22:22:11 +0100 Subject: [PATCH 446/562] mmc: dw_mmc: allow biu and ciu clocks to defer Fix a race condition if the clock provider comes up after mmc is probed, this causes mmc to fail without retrying. When given the DEFER error from the clk source, pass it on up the chain. Fixes: f90a0612f0e1 ("mmc: dw_mmc: lookup for optional biu and ciu clocks") Signed-off-by: Ben Whitten Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240811212212.123255-1-ben.whitten@gmail.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/dw_mmc.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 2333ef4893ee..e9f6e4e62290 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -3299,6 +3299,10 @@ int dw_mci_probe(struct dw_mci *host) host->biu_clk = devm_clk_get(host->dev, "biu"); if (IS_ERR(host->biu_clk)) { dev_dbg(host->dev, "biu clock not available\n"); + ret = PTR_ERR(host->biu_clk); + if (ret == -EPROBE_DEFER) + return ret; + } else { ret = clk_prepare_enable(host->biu_clk); if (ret) { @@ -3310,6 +3314,10 @@ int dw_mci_probe(struct dw_mci *host) host->ciu_clk = devm_clk_get(host->dev, "ciu"); if (IS_ERR(host->ciu_clk)) { dev_dbg(host->dev, "ciu clock not available\n"); + ret = PTR_ERR(host->ciu_clk); + if (ret == -EPROBE_DEFER) + goto err_clk_biu; + host->bus_hz = host->pdata->bus_hz; } else { ret = clk_prepare_enable(host->ciu_clk); From a1e627af32ed60713941cbfc8075d44cad07f6dd Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 20 Aug 2024 11:44:08 +0300 Subject: [PATCH 447/562] mmc: mmc_test: Fix NULL dereference on allocation failure If the "test->highmem = alloc_pages()" allocation fails then calling __free_pages(test->highmem) will result in a NULL dereference. Also change the error code to -ENOMEM instead of returning success. Fixes: 2661081f5ab9 ("mmc_test: highmem tests") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/8c90be28-67b4-4b0d-a105-034dc72a0b31@stanley.mountain Signed-off-by: Ulf Hansson --- drivers/mmc/core/mmc_test.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c index 8f7f587a0025..b7f627a9fdea 100644 --- a/drivers/mmc/core/mmc_test.c +++ b/drivers/mmc/core/mmc_test.c @@ -3125,13 +3125,13 @@ static ssize_t mtf_test_write(struct file *file, const char __user *buf, test->buffer = kzalloc(BUFFER_SIZE, GFP_KERNEL); #ifdef CONFIG_HIGHMEM test->highmem = alloc_pages(GFP_KERNEL | __GFP_HIGHMEM, BUFFER_ORDER); + if (!test->highmem) { + count = -ENOMEM; + goto free_test_buffer; + } #endif -#ifdef CONFIG_HIGHMEM - if (test->buffer && test->highmem) { -#else if (test->buffer) { -#endif mutex_lock(&mmc_test_lock); mmc_test_run(test, testcase); mutex_unlock(&mmc_test_lock); @@ -3139,6 +3139,7 @@ static ssize_t mtf_test_write(struct file *file, const char __user *buf, #ifdef CONFIG_HIGHMEM __free_pages(test->highmem, BUFFER_ORDER); +free_test_buffer: #endif kfree(test->buffer); kfree(test); From 783bf5d09f86b9736605f3e01a3472e55ef98ff8 Mon Sep 17 00:00:00 2001 From: Carlos Song Date: Tue, 20 Aug 2024 15:06:58 +0800 Subject: [PATCH 448/562] spi: spi-fsl-lpspi: limit PRESCALE bit in TCR register Referring to the errata ERR051608 of I.MX93, LPSPI TCR[PRESCALE] can only be configured to be 0 or 1, other values are not valid and will cause LPSPI to not work. Add the prescale limitation for LPSPI in I.MX93. Other platforms are not affected. Signed-off-by: Carlos Song Link: https://patch.msgid.link/20240820070658.672127-1-carlos.song@nxp.com Signed-off-by: Mark Brown --- drivers/spi/spi-fsl-lpspi.c | 31 +++++++++++++++++++++++++++++-- 1 file changed, 29 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index be261ac09df8..350c5d91d869 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -82,6 +82,10 @@ #define TCR_RXMSK BIT(19) #define TCR_TXMSK BIT(18) +struct fsl_lpspi_devtype_data { + u8 prescale_max; +}; + struct lpspi_config { u8 bpw; u8 chip_select; @@ -119,10 +123,25 @@ struct fsl_lpspi_data { bool usedma; struct completion dma_rx_completion; struct completion dma_tx_completion; + + const struct fsl_lpspi_devtype_data *devtype_data; +}; + +/* + * ERR051608 fixed or not: + * https://www.nxp.com/docs/en/errata/i.MX93_1P87f.pdf + */ +static struct fsl_lpspi_devtype_data imx93_lpspi_devtype_data = { + .prescale_max = 1, +}; + +static struct fsl_lpspi_devtype_data imx7ulp_lpspi_devtype_data = { + .prescale_max = 8, }; static const struct of_device_id fsl_lpspi_dt_ids[] = { - { .compatible = "fsl,imx7ulp-spi", }, + { .compatible = "fsl,imx7ulp-spi", .data = &imx7ulp_lpspi_devtype_data,}, + { .compatible = "fsl,imx93-spi", .data = &imx93_lpspi_devtype_data,}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, fsl_lpspi_dt_ids); @@ -297,9 +316,11 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi) { struct lpspi_config config = fsl_lpspi->config; unsigned int perclk_rate, scldiv, div; + u8 prescale_max; u8 prescale; perclk_rate = clk_get_rate(fsl_lpspi->clk_per); + prescale_max = fsl_lpspi->devtype_data->prescale_max; if (!config.speed_hz) { dev_err(fsl_lpspi->dev, @@ -315,7 +336,7 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi) div = DIV_ROUND_UP(perclk_rate, config.speed_hz); - for (prescale = 0; prescale < 8; prescale++) { + for (prescale = 0; prescale < prescale_max; prescale++) { scldiv = div / (1 << prescale) - 2; if (scldiv < 256) { fsl_lpspi->config.prescale = prescale; @@ -822,6 +843,7 @@ static int fsl_lpspi_init_rpm(struct fsl_lpspi_data *fsl_lpspi) static int fsl_lpspi_probe(struct platform_device *pdev) { + const struct fsl_lpspi_devtype_data *devtype_data; struct fsl_lpspi_data *fsl_lpspi; struct spi_controller *controller; struct resource *res; @@ -830,6 +852,10 @@ static int fsl_lpspi_probe(struct platform_device *pdev) u32 temp; bool is_target; + devtype_data = of_device_get_match_data(&pdev->dev); + if (!devtype_data) + return -ENODEV; + is_target = of_property_read_bool((&pdev->dev)->of_node, "spi-slave"); if (is_target) controller = devm_spi_alloc_target(&pdev->dev, @@ -848,6 +874,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev) fsl_lpspi->is_target = is_target; fsl_lpspi->is_only_cs1 = of_property_read_bool((&pdev->dev)->of_node, "fsl,spi-only-use-cs1-sel"); + fsl_lpspi->devtype_data = devtype_data; init_completion(&fsl_lpspi->xfer_done); From fc59b9a5f7201b9f7272944596113a82cc7773d5 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 16 Aug 2024 14:48:10 +0300 Subject: [PATCH 449/562] bonding: fix bond_ipsec_offload_ok return type Fix the return type which should be bool. Fixes: 955b785ec6b3 ("bonding: fix suspicious RCU usage in bond_ipsec_offload_ok()") Signed-off-by: Nikolay Aleksandrov Reviewed-by: Hangbin Liu Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_main.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1cd92c12e782..85b5868deeea 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -599,34 +599,28 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) struct net_device *real_dev; struct slave *curr_active; struct bonding *bond; - int err; + bool ok = false; bond = netdev_priv(bond_dev); rcu_read_lock(); curr_active = rcu_dereference(bond->curr_active_slave); real_dev = curr_active->dev; - if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { - err = false; + if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) goto out; - } - if (!xs->xso.real_dev) { - err = false; + if (!xs->xso.real_dev) goto out; - } if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_offload_ok || - netif_is_bond_master(real_dev)) { - err = false; + netif_is_bond_master(real_dev)) goto out; - } - err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); + ok = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); out: rcu_read_unlock(); - return err; + return ok; } static const struct xfrmdev_ops bond_xfrmdev_ops = { From 95c90e4ad89d493a7a14fa200082e466e2548f9d Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 16 Aug 2024 14:48:11 +0300 Subject: [PATCH 450/562] bonding: fix null pointer deref in bond_ipsec_offload_ok We must check if there is an active slave before dereferencing the pointer. Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Nikolay Aleksandrov Reviewed-by: Hangbin Liu Reviewed-by: Eric Dumazet Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 85b5868deeea..65ddb71eebcd 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -604,6 +604,8 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) bond = netdev_priv(bond_dev); rcu_read_lock(); curr_active = rcu_dereference(bond->curr_active_slave); + if (!curr_active) + goto out; real_dev = curr_active->dev; if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) From f8cde9805981c50d0c029063dc7d82821806fc44 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 16 Aug 2024 14:48:12 +0300 Subject: [PATCH 451/562] bonding: fix xfrm real_dev null pointer dereference We shouldn't set real_dev to NULL because packets can be in transit and xfrm might call xdo_dev_offload_ok() in parallel. All callbacks assume real_dev is set. Example trace: kernel: BUG: unable to handle page fault for address: 0000000000001030 kernel: bond0: (slave eni0np1): making interface the new active one kernel: #PF: supervisor write access in kernel mode kernel: #PF: error_code(0x0002) - not-present page kernel: PGD 0 P4D 0 kernel: Oops: 0002 [#1] PREEMPT SMP kernel: CPU: 4 PID: 2237 Comm: ping Not tainted 6.7.7+ #12 kernel: Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-2.fc40 04/01/2014 kernel: RIP: 0010:nsim_ipsec_offload_ok+0xc/0x20 [netdevsim] kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA kernel: Code: e0 0f 0b 48 83 7f 38 00 74 de 0f 0b 48 8b 47 08 48 8b 37 48 8b 78 40 e9 b2 e5 9a d7 66 90 0f 1f 44 00 00 48 8b 86 80 02 00 00 <83> 80 30 10 00 00 01 b8 01 00 00 00 c3 0f 1f 80 00 00 00 00 0f 1f kernel: bond0: (slave eni0np1): making interface the new active one kernel: RSP: 0018:ffffabde81553b98 EFLAGS: 00010246 kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA kernel: kernel: RAX: 0000000000000000 RBX: ffff9eb404e74900 RCX: ffff9eb403d97c60 kernel: RDX: ffffffffc090de10 RSI: ffff9eb404e74900 RDI: ffff9eb3c5de9e00 kernel: RBP: ffff9eb3c0a42000 R08: 0000000000000010 R09: 0000000000000014 kernel: R10: 7974203030303030 R11: 3030303030303030 R12: 0000000000000000 kernel: R13: ffff9eb3c5de9e00 R14: ffffabde81553cc8 R15: ffff9eb404c53000 kernel: FS: 00007f2a77a3ad00(0000) GS:ffff9eb43bd00000(0000) knlGS:0000000000000000 kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 kernel: CR2: 0000000000001030 CR3: 00000001122ab000 CR4: 0000000000350ef0 kernel: bond0: (slave eni0np1): making interface the new active one kernel: Call Trace: kernel: kernel: ? __die+0x1f/0x60 kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA kernel: ? page_fault_oops+0x142/0x4c0 kernel: ? do_user_addr_fault+0x65/0x670 kernel: ? kvm_read_and_reset_apf_flags+0x3b/0x50 kernel: bond0: (slave eni0np1): making interface the new active one kernel: ? exc_page_fault+0x7b/0x180 kernel: ? asm_exc_page_fault+0x22/0x30 kernel: ? nsim_bpf_uninit+0x50/0x50 [netdevsim] kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA kernel: ? nsim_ipsec_offload_ok+0xc/0x20 [netdevsim] kernel: bond0: (slave eni0np1): making interface the new active one kernel: bond_ipsec_offload_ok+0x7b/0x90 [bonding] kernel: xfrm_output+0x61/0x3b0 kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA kernel: ip_push_pending_frames+0x56/0x80 Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Nikolay Aleksandrov Reviewed-by: Hangbin Liu Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_main.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 65ddb71eebcd..f74bacf071fc 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -582,7 +582,6 @@ static void bond_ipsec_del_sa_all(struct bonding *bond) } else { slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs); } - ipsec->xs->xso.real_dev = NULL; } spin_unlock_bh(&bond->ipsec_lock); rcu_read_unlock(); From c4c5c5d2ef40a9f67a9241dc5422eac9ffe19547 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 16 Aug 2024 14:48:13 +0300 Subject: [PATCH 452/562] bonding: fix xfrm state handling when clearing active slave If the active slave is cleared manually the xfrm state is not flushed. This leads to xfrm add/del imbalance and adding the same state multiple times. For example when the device cannot handle anymore states we get: [ 1169.884811] bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA because it's filled with the same state after multiple active slave clearings. This change also has a few nice side effects: user-space gets a notification for the change, the old device gets its mac address and promisc/mcast adjusted properly. Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Nikolay Aleksandrov Reviewed-by: Hangbin Liu Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_options.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index bc80fb6397dc..95d59a18c022 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -936,7 +936,7 @@ static int bond_option_active_slave_set(struct bonding *bond, /* check to see if we are clearing active */ if (!slave_dev) { netdev_dbg(bond->dev, "Clearing current active slave\n"); - RCU_INIT_POINTER(bond->curr_active_slave, NULL); + bond_change_active_slave(bond, NULL); bond_select_active_slave(bond); } else { struct slave *old_active = rtnl_dereference(bond->curr_active_slave); From 50b2143356e888777fc5bca023c39f34f404613a Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Wed, 7 Aug 2024 12:53:24 +0200 Subject: [PATCH 453/562] ice: fix page reuse when PAGE_SIZE is over 8k Architectures that have PAGE_SIZE >= 8192 such as arm64 should act the same as x86 currently, meaning reuse of a page should only take place when no one else is busy with it. Do two things independently of underlying PAGE_SIZE: - store the page count under ice_rx_buf::pgcnt - then act upon its value vs ice_rx_buf::pagecnt_bias when making the decision regarding page reuse Fixes: 2b245cb29421 ("ice: Implement transmit and NAPI support") Signed-off-by: Maciej Fijalkowski Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_txrx.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 8d25b6981269..50211188c1a7 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -837,16 +837,15 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) if (!dev_page_is_reusable(page)) return false; -#if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1)) return false; -#else +#if (PAGE_SIZE >= 8192) #define ICE_LAST_OFFSET \ (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_2048) if (rx_buf->page_offset > ICE_LAST_OFFSET) return false; -#endif /* PAGE_SIZE < 8192) */ +#endif /* PAGE_SIZE >= 8192) */ /* If we have drained the page fragment pool we need to update * the pagecnt_bias and page count so that we fully restock the @@ -949,12 +948,7 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, struct ice_rx_buf *rx_buf; rx_buf = &rx_ring->rx_buf[ntc]; - rx_buf->pgcnt = -#if (PAGE_SIZE < 8192) - page_count(rx_buf->page); -#else - 0; -#endif + rx_buf->pgcnt = page_count(rx_buf->page); prefetchw(rx_buf->page); if (!size) From b966ad832942b5a11e002f9b5ef102b08425b84a Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Wed, 7 Aug 2024 12:53:25 +0200 Subject: [PATCH 454/562] ice: fix ICE_LAST_OFFSET formula For bigger PAGE_SIZE archs, ice driver works on 3k Rx buffers. Therefore, ICE_LAST_OFFSET should take into account ICE_RXBUF_3072, not ICE_RXBUF_2048. Fixes: 7237f5b0dba4 ("ice: introduce legacy Rx flag") Suggested-by: Luiz Capitulino Signed-off-by: Maciej Fijalkowski Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 50211188c1a7..4b690952bb40 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -842,7 +842,7 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) return false; #if (PAGE_SIZE >= 8192) #define ICE_LAST_OFFSET \ - (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_2048) + (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_3072) if (rx_buf->page_offset > ICE_LAST_OFFSET) return false; #endif /* PAGE_SIZE >= 8192) */ From d53d4dcce69be5773e2d0878c9899ebfbf58c393 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Wed, 7 Aug 2024 12:53:26 +0200 Subject: [PATCH 455/562] ice: fix truesize operations for PAGE_SIZE >= 8192 When working on multi-buffer packet on arch that has PAGE_SIZE >= 8192, truesize is calculated and stored in xdp_buff::frame_sz per each processed Rx buffer. This means that frame_sz will contain the truesize based on last received buffer, but commit 1dc1a7e7f410 ("ice: Centrallize Rx buffer recycling") assumed this value will be constant for each buffer, which breaks the page recycling scheme and mess up the way we update the page::page_offset. To fix this, let us work on constant truesize when PAGE_SIZE >= 8192 instead of basing this on size of a packet read from Rx descriptor. This way we can simplify the code and avoid calculating truesize per each received frame and on top of that when using xdp_update_skb_shared_info(), current formula for truesize update will be valid. This means ice_rx_frame_truesize() can be removed altogether. Furthermore, first call to it within ice_clean_rx_irq() for 4k PAGE_SIZE was redundant as xdp_buff::frame_sz is initialized via xdp_init_buff() in ice_vsi_cfg_rxq(). This should have been removed at the point where xdp_buff struct started to be a member of ice_rx_ring and it was no longer a stack based variable. There are two fixes tags as my understanding is that the first one exposed us to broken truesize and page_offset handling and then second introduced broken skb_shared_info update in ice_{construct,build}_skb(). Reported-and-tested-by: Luiz Capitulino Closes: https://lore.kernel.org/netdev/8f9e2a5c-fd30-4206-9311-946a06d031bb@redhat.com/ Fixes: 1dc1a7e7f410 ("ice: Centrallize Rx buffer recycling") Fixes: 2fba7dc5157b ("ice: Add support for XDP multi-buffer on Rx side") Signed-off-by: Maciej Fijalkowski Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_base.c | 21 ++++++++++++++- drivers/net/ethernet/intel/ice/ice_txrx.c | 33 ----------------------- 2 files changed, 20 insertions(+), 34 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 1facf179a96f..f448d3a84564 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -512,6 +512,25 @@ static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring) xsk_pool_fill_cb(ring->xsk_pool, &desc); } +/** + * ice_get_frame_sz - calculate xdp_buff::frame_sz + * @rx_ring: the ring being configured + * + * Return frame size based on underlying PAGE_SIZE + */ +static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring) +{ + unsigned int frame_sz; + +#if (PAGE_SIZE >= 8192) + frame_sz = rx_ring->rx_buf_len; +#else + frame_sz = ice_rx_pg_size(rx_ring) / 2; +#endif + + return frame_sz; +} + /** * ice_vsi_cfg_rxq - Configure an Rx queue * @ring: the ring being configured @@ -576,7 +595,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) } } - xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq); + xdp_init_buff(&ring->xdp, ice_get_frame_sz(ring), &ring->xdp_rxq); ring->xdp.data = NULL; ring->xdp_ext.pkt_ctx = &ring->pkt_ctx; err = ice_setup_rx_ctx(ring); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 4b690952bb40..c9bc3f1add5d 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -521,30 +521,6 @@ err: return -ENOMEM; } -/** - * ice_rx_frame_truesize - * @rx_ring: ptr to Rx ring - * @size: size - * - * calculate the truesize with taking into the account PAGE_SIZE of - * underlying arch - */ -static unsigned int -ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size) -{ - unsigned int truesize; - -#if (PAGE_SIZE < 8192) - truesize = ice_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */ -#else - truesize = rx_ring->rx_offset ? - SKB_DATA_ALIGN(rx_ring->rx_offset + size) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) : - SKB_DATA_ALIGN(size); -#endif - return truesize; -} - /** * ice_run_xdp - Executes an XDP program on initialized xdp_buff * @rx_ring: Rx ring @@ -1154,11 +1130,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) bool failure; u32 first; - /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ -#if (PAGE_SIZE < 8192) - xdp->frame_sz = ice_rx_frame_truesize(rx_ring, 0); -#endif - xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (xdp_prog) { xdp_ring = rx_ring->xdp_ring; @@ -1217,10 +1188,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) hard_start = page_address(rx_buf->page) + rx_buf->page_offset - offset; xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); -#if (PAGE_SIZE > 4096) - /* At larger PAGE_SIZE, frame_sz depend on len size */ - xdp->frame_sz = ice_rx_frame_truesize(rx_ring, size); -#endif xdp_buff_clear_frags_flag(xdp); } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { break; From 503ab6ee40fc103ea55cc9e50bb879e571d65aac Mon Sep 17 00:00:00 2001 From: Michal Swiatkowski Date: Mon, 19 Aug 2024 09:17:42 +0200 Subject: [PATCH 456/562] ice: use internal pf id instead of function number Use always the same pf id in devlink port number. When doing pass-through the PF to VM bus info func number can be any value. Fixes: 2ae0aa4758b0 ("ice: Move devlink port to PF/VF struct") Reviewed-by: Wojciech Drewek Suggested-by: Jiri Pirko Signed-off-by: Michal Swiatkowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/devlink/devlink_port.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c index 00fed5a61d62..62ef8e2fb5f1 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c @@ -337,7 +337,7 @@ int ice_devlink_create_pf_port(struct ice_pf *pf) return -EIO; attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - attrs.phys.port_number = pf->hw.bus.func; + attrs.phys.port_number = pf->hw.pf_id; /* As FW supports only port split options for whole device, * set port split options only for first PF. @@ -455,7 +455,7 @@ int ice_devlink_create_vf_port(struct ice_vf *vf) return -EINVAL; attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF; - attrs.pci_vf.pf = pf->hw.bus.func; + attrs.pci_vf.pf = pf->hw.pf_id; attrs.pci_vf.vf = vf->vf_id; ice_devlink_set_switch_id(pf, &attrs.switch_id); From c50e7475961c36ec4d21d60af055b32f9436b431 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 17 Aug 2024 09:52:46 +0300 Subject: [PATCH 457/562] dpaa2-switch: Fix error checking in dpaa2_switch_seed_bp() The dpaa2_switch_add_bufs() function returns the number of bufs that it was able to add. It returns BUFS_PER_CMD (7) for complete success or a smaller number if there are not enough pages available. However, the error checking is looking at the total number of bufs instead of the number which were added on this iteration. Thus the error checking only works correctly for the first iteration through the loop and subsequent iterations are always counted as a success. Fix this by checking only the bufs added in the current iteration. Fixes: 0b1b71370458 ("staging: dpaa2-switch: handle Rx path on control interface") Signed-off-by: Dan Carpenter Reviewed-by: Simon Horman Reviewed-by: Ioana Ciornei Tested-by: Ioana Ciornei Link: https://patch.msgid.link/eec27f30-b43f-42b6-b8ee-04a6f83423b6@stanley.mountain Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index a71f848adc05..a293b08f36d4 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -2638,13 +2638,14 @@ static int dpaa2_switch_refill_bp(struct ethsw_core *ethsw) static int dpaa2_switch_seed_bp(struct ethsw_core *ethsw) { - int *count, i; + int *count, ret, i; for (i = 0; i < DPAA2_ETHSW_NUM_BUFS; i += BUFS_PER_CMD) { + ret = dpaa2_switch_add_bufs(ethsw, ethsw->bpid); count = ðsw->buf_count; - *count += dpaa2_switch_add_bufs(ethsw, ethsw->bpid); + *count += ret; - if (unlikely(*count < BUFS_PER_CMD)) + if (unlikely(ret < BUFS_PER_CMD)) return -ENOMEM; } From 80a1e7b83bb1834b5568a3872e64c05795d88f31 Mon Sep 17 00:00:00 2001 From: Nikolay Kuratov Date: Mon, 19 Aug 2024 10:54:08 +0300 Subject: [PATCH 458/562] cxgb4: add forgotten u64 ivlan cast before shift It is done everywhere in cxgb4 code, e.g. in is_filter_exact_match() There is no reason it should not be done here Found by Linux Verification Center (linuxtesting.org) with SVACE Signed-off-by: Nikolay Kuratov Cc: stable@vger.kernel.org Fixes: 12b276fbf6e0 ("cxgb4: add support to create hash filters") Reviewed-by: Simon Horman Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20240819075408.92378-1-kniv@yandex-team.ru Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 786ceae34488..dd9e68465e69 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -1244,7 +1244,8 @@ static u64 hash_filter_ntuple(struct ch_filter_specification *fs, * in the Compressed Filter Tuple. */ if (tp->vlan_shift >= 0 && fs->mask.ivlan) - ntuple |= (FT_VLAN_VLD_F | fs->val.ivlan) << tp->vlan_shift; + ntuple |= (u64)(FT_VLAN_VLD_F | + fs->val.ivlan) << tp->vlan_shift; if (tp->port_shift >= 0 && fs->mask.iport) ntuple |= (u64)fs->val.iport << tp->port_shift; From 8aba27c4a5020abdf60149239198297f88338a8d Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 16 Aug 2024 17:20:34 +0200 Subject: [PATCH 459/562] igb: cope with large MAX_SKB_FRAGS Sabrina reports that the igb driver does not cope well with large MAX_SKB_FRAG values: setting MAX_SKB_FRAG to 45 causes payload corruption on TX. An easy reproducer is to run ssh to connect to the machine. With MAX_SKB_FRAGS=17 it works, with MAX_SKB_FRAGS=45 it fails. This has been reported originally in https://bugzilla.redhat.com/show_bug.cgi?id=2265320 The root cause of the issue is that the driver does not take into account properly the (possibly large) shared info size when selecting the ring layout, and will try to fit two packets inside the same 4K page even when the 1st fraglist will trump over the 2nd head. Address the issue by checking if 2K buffers are insufficient. Fixes: 3948b05950fd ("net: introduce a config option to tweak MAX_SKB_FRAGS") Reported-by: Jan Tluka Reported-by: Jirka Hladky Reported-by: Sabrina Dubroca Tested-by: Sabrina Dubroca Tested-by: Corinna Vinschen Signed-off-by: Paolo Abeni Signed-off-by: Corinna Vinschen Link: https://patch.msgid.link/20240816152034.1453285-1-vinschen@redhat.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igb/igb_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 11be39f435f3..33a42b4c21e0 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4808,6 +4808,7 @@ static void igb_set_rx_buffer_len(struct igb_adapter *adapter, #if (PAGE_SIZE < 8192) if (adapter->max_frame_size > IGB_MAX_FRAME_BUILD_SKB || + IGB_2K_TOO_SMALL_WITH_PADDING || rd32(E1000_RCTL) & E1000_RCTL_SBP) set_ring_uses_large_buffer(rx_ring); #endif From 6efea5135417ae8194485d1d05ea79a21cf1a11c Mon Sep 17 00:00:00 2001 From: Martin Whitaker Date: Sat, 17 Aug 2024 10:41:41 +0100 Subject: [PATCH 460/562] net: dsa: microchip: fix PTP config failure when using multiple ports When performing the port_hwtstamp_set operation, ptp_schedule_worker() will be called if hardware timestamoing is enabled on any of the ports. When using multiple ports for PTP, port_hwtstamp_set is executed for each port. When called for the first time ptp_schedule_worker() returns 0. On subsequent calls it returns 1, indicating the worker is already scheduled. Currently the ksz driver treats 1 as an error and fails to complete the port_hwtstamp_set operation, thus leaving the timestamping configuration for those ports unchanged. This patch fixes this by ignoring the ptp_schedule_worker() return value. Cc: stable@vger.kernel.org Link: https://lore.kernel.org/7aae307a-35ca-4209-a850-7b2749d40f90@martin-whitaker.me.uk Fixes: bb01ad30570b0 ("net: dsa: microchip: ptp: manipulating absolute time using ptp hw clock") Signed-off-by: Martin Whitaker Reviewed-by: Andrew Lunn Acked-by: Arun Ramadoss Link: https://patch.msgid.link/20240817094141.3332-1-foss@martin-whitaker.me.uk Signed-off-by: Jakub Kicinski --- drivers/net/dsa/microchip/ksz_ptp.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c index f0bd46e5d4ec..050f17c43ef6 100644 --- a/drivers/net/dsa/microchip/ksz_ptp.c +++ b/drivers/net/dsa/microchip/ksz_ptp.c @@ -266,7 +266,6 @@ static int ksz_ptp_enable_mode(struct ksz_device *dev) struct ksz_port *prt; struct dsa_port *dp; bool tag_en = false; - int ret; dsa_switch_for_each_user_port(dp, dev->ds) { prt = &dev->ports[dp->index]; @@ -277,9 +276,7 @@ static int ksz_ptp_enable_mode(struct ksz_device *dev) } if (tag_en) { - ret = ptp_schedule_worker(ptp_data->clock, 0); - if (ret) - return ret; + ptp_schedule_worker(ptp_data->clock, 0); } else { ptp_cancel_worker_sync(ptp_data->clock); } From 528876d867a23b5198022baf2e388052ca67c952 Mon Sep 17 00:00:00 2001 From: Joseph Huang Date: Mon, 19 Aug 2024 19:52:50 -0400 Subject: [PATCH 461/562] net: dsa: mv88e6xxx: Fix out-of-bound access If an ATU violation was caused by a CPU Load operation, the SPID could be larger than DSA_MAX_PORTS (the size of mv88e6xxx_chip.ports[] array). Fixes: 75c05a74e745 ("net: dsa: mv88e6xxx: Fix counting of ATU violations") Signed-off-by: Joseph Huang Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20240819235251.1331763-1-Joseph.Huang@garmin.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/mv88e6xxx/global1_atu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index ce3b3690c3c0..c47f068f56b3 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -457,7 +457,8 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) trace_mv88e6xxx_atu_full_violation(chip->dev, spid, entry.portvec, entry.mac, fid); - chip->ports[spid].atu_full_violation++; + if (spid < ARRAY_SIZE(chip->ports)) + chip->ports[spid].atu_full_violation++; } return IRQ_HANDLED; From c07ff8592d57ed258afee5a5e04991a48dbaf382 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Mon, 19 Aug 2024 10:56:45 -0700 Subject: [PATCH 462/562] netem: fix return value if duplicate enqueue fails There is a bug in netem_enqueue() introduced by commit 5845f706388a ("net: netem: fix skb length BUG_ON in __skb_to_sgvec") that can lead to a use-after-free. This commit made netem_enqueue() always return NET_XMIT_SUCCESS when a packet is duplicated, which can cause the parent qdisc's q.qlen to be mistakenly incremented. When this happens qlen_notify() may be skipped on the parent during destruction, leaving a dangling pointer for some classful qdiscs like DRR. There are two ways for the bug happen: - If the duplicated packet is dropped by rootq->enqueue() and then the original packet is also dropped. - If rootq->enqueue() sends the duplicated packet to a different qdisc and the original packet is dropped. In both cases NET_XMIT_SUCCESS is returned even though no packets are enqueued at the netem qdisc. The fix is to defer the enqueue of the duplicate packet until after the original packet has been guaranteed to return NET_XMIT_SUCCESS. Fixes: 5845f706388a ("net: netem: fix skb length BUG_ON in __skb_to_sgvec") Reported-by: Budimir Markovic Signed-off-by: Stephen Hemminger Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240819175753.5151-1-stephen@networkplumber.org Signed-off-by: Jakub Kicinski --- net/sched/sch_netem.c | 47 ++++++++++++++++++++++++++----------------- 1 file changed, 29 insertions(+), 18 deletions(-) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index edc72962ae63..0f8d581438c3 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -446,12 +446,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct netem_sched_data *q = qdisc_priv(sch); /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; - struct sk_buff *skb2; + struct sk_buff *skb2 = NULL; struct sk_buff *segs = NULL; unsigned int prev_len = qdisc_pkt_len(skb); int count = 1; - int rc = NET_XMIT_SUCCESS; - int rc_drop = NET_XMIT_DROP; /* Do not fool qdisc_drop_all() */ skb->prev = NULL; @@ -480,19 +478,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, skb_orphan_partial(skb); /* - * If we need to duplicate packet, then re-insert at top of the - * qdisc tree, since parent queuer expects that only one - * skb will be queued. + * If we need to duplicate packet, then clone it before + * original is modified. */ - if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) { - struct Qdisc *rootq = qdisc_root_bh(sch); - u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ - - q->duplicate = 0; - rootq->enqueue(skb2, rootq, to_free); - q->duplicate = dupsave; - rc_drop = NET_XMIT_SUCCESS; - } + if (count > 1) + skb2 = skb_clone(skb, GFP_ATOMIC); /* * Randomized packet corruption. @@ -504,7 +494,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb_is_gso(skb)) { skb = netem_segment(skb, sch, to_free); if (!skb) - return rc_drop; + goto finish_segs; + segs = skb->next; skb_mark_not_on_list(skb); qdisc_skb_cb(skb)->pkt_len = skb->len; @@ -530,7 +521,24 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* re-link segs, so that qdisc_drop_all() frees them all */ skb->next = segs; qdisc_drop_all(skb, sch, to_free); - return rc_drop; + if (skb2) + __qdisc_drop(skb2, to_free); + return NET_XMIT_DROP; + } + + /* + * If doing duplication then re-insert at top of the + * qdisc tree, since parent queuer expects that only one + * skb will be queued. + */ + if (skb2) { + struct Qdisc *rootq = qdisc_root_bh(sch); + u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ + + q->duplicate = 0; + rootq->enqueue(skb2, rootq, to_free); + q->duplicate = dupsave; + skb2 = NULL; } qdisc_qstats_backlog_inc(sch, skb); @@ -601,9 +609,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, } finish_segs: + if (skb2) + __qdisc_drop(skb2, to_free); + if (segs) { unsigned int len, last_len; - int nb; + int rc, nb; len = skb ? skb->len : 0; nb = skb ? 1 : 0; From 0005e01e1e875c5e27130c5e2ed0189749d1e08a Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Tue, 20 Aug 2024 16:56:19 +0800 Subject: [PATCH 463/562] erofs: fix out-of-bound access when z_erofs_gbuf_growsize() partially fails If z_erofs_gbuf_growsize() partially fails on a global buffer due to memory allocation failure or fault injection (as reported by syzbot [1]), new pages need to be freed by comparing to the existing pages to avoid memory leaks. However, the old gbuf->pages[] array may not be large enough, which can lead to null-ptr-deref or out-of-bound access. Fix this by checking against gbuf->nrpages in advance. [1] https://lore.kernel.org/r/000000000000f7b96e062018c6e3@google.com Reported-by: syzbot+242ee56aaa9585553766@syzkaller.appspotmail.com Fixes: d6db47e571dc ("erofs: do not use pagepool in z_erofs_gbuf_growsize()") Cc: # 6.10+ Reviewed-by: Chunhai Guo Reviewed-by: Sandeep Dhavale Signed-off-by: Gao Xiang Link: https://lore.kernel.org/r/20240820085619.1375963-1-hsiangkao@linux.alibaba.com --- fs/erofs/zutil.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c index 9b53883e5caf..37afe2024840 100644 --- a/fs/erofs/zutil.c +++ b/fs/erofs/zutil.c @@ -111,7 +111,8 @@ int z_erofs_gbuf_growsize(unsigned int nrpages) out: if (i < z_erofs_gbuf_count && tmp_pages) { for (j = 0; j < nrpages; ++j) - if (tmp_pages[j] && tmp_pages[j] != gbuf->pages[j]) + if (tmp_pages[j] && (j >= gbuf->nrpages || + tmp_pages[j] != gbuf->pages[j])) __free_page(tmp_pages[j]); kfree(tmp_pages); } From e255683c06df572ead96db5efb5d21be30c0efaa Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:19 +0200 Subject: [PATCH 464/562] mptcp: pm: re-using ID of unused removed ADD_ADDR If no subflow is attached to the 'signal' endpoint that is being removed, the addr ID will not be marked as available again. Mark the linked ID as available when removing the address entry from the list to cover this case. Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-1-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 4cae2aa7be5c..26f0329e16bb 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1431,7 +1431,10 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, ret = remove_anno_list_by_saddr(msk, addr); if (ret || force) { spin_lock_bh(&msk->pm.lock); - msk->pm.add_addr_signaled -= ret; + if (ret) { + __set_bit(addr->id, msk->pm.id_avail_bitmap); + msk->pm.add_addr_signaled--; + } mptcp_pm_remove_addr(msk, &list); spin_unlock_bh(&msk->pm.lock); } From a13d5aad4dd9a309eecdc33cfd75045bd5f376a3 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:20 +0200 Subject: [PATCH 465/562] selftests: mptcp: join: check re-using ID of unused ADD_ADDR This test extends "delete re-add signal" to validate the previous commit. An extra address is announced by the server, but this address cannot be used by the client. The result is that no subflow will be established to this address. Later, the server will delete this extra endpoint, and set a new one, with a valid address, but re-using the same ID. Before the previous commit, the server would not have been able to announce this new address. While at it, extra checks have been added to validate the expected numbers of MPJ, ADD_ADDR and RM_ADDR. The 'Fixes' tag here below is the same as the one from the previous commit: this patch here is not fixing anything wrong in the selftests, but it validates the previous fix for an issue introduced by this commit ID. Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-2-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/mptcp/mptcp_join.sh | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 9ea6d698e9d3..25077ccf31d2 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3601,9 +3601,11 @@ endpoint_tests() # remove and re-add if reset "delete re-add signal" && mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then - pm_nl_set_limits $ns1 1 1 - pm_nl_set_limits $ns2 1 1 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal + # broadcast IP: no packet for this address will be received on ns1 + pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal test_linkfail=4 speed=20 \ run_tests $ns1 $ns2 10.0.1.1 & local tests_pid=$! @@ -3615,15 +3617,21 @@ endpoint_tests() chk_mptcp_info subflows 1 subflows 1 pm_nl_del_endpoint $ns1 1 10.0.2.1 + pm_nl_del_endpoint $ns1 2 224.0.0.1 sleep 0.5 chk_subflow_nr "after delete" 1 chk_mptcp_info subflows 0 subflows 0 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal wait_mpj $ns2 - chk_subflow_nr "after re-add" 2 - chk_mptcp_info subflows 1 subflows 1 + chk_subflow_nr "after re-add" 3 + chk_mptcp_info subflows 2 subflows 2 mptcp_lib_kill_wait $tests_pid + + chk_join_nr 3 3 3 + chk_add_nr 4 4 + chk_rm_nr 2 1 invert fi } From edd8b5d868a4d459f3065493001e293901af758d Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:21 +0200 Subject: [PATCH 466/562] mptcp: pm: re-using ID of unused removed subflows If no subflow is attached to the 'subflow' endpoint that is being removed, the addr ID will not be marked as available again. Mark the linked ID as available when removing the 'subflow' endpoint if no subflow is attached to it. While at it, the local_addr_used counter is decremented if the ID was marked as being used to reflect the reality, but also to allow adding new endpoints after that. Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-3-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 26f0329e16bb..8b232a210a06 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1469,8 +1469,17 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr); mptcp_pm_remove_anno_addr(msk, addr, remove_subflow && !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)); - if (remove_subflow) + + if (remove_subflow) { mptcp_pm_remove_subflow(msk, &list); + } else if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { + /* If the subflow has been used, but now closed */ + spin_lock_bh(&msk->pm.lock); + if (!__test_and_set_bit(entry->addr.id, msk->pm.id_avail_bitmap)) + msk->pm.local_addr_used--; + spin_unlock_bh(&msk->pm.lock); + } + release_sock(sk); next: From 65fb58afa341ad68e71e5c4d816b407e6a683a66 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:22 +0200 Subject: [PATCH 467/562] selftests: mptcp: join: check re-using ID of closed subflow This test extends "delete and re-add" to validate the previous commit. A new 'subflow' endpoint is added, but the subflow request will be rejected. The result is that no subflow will be established from this address. Later, the endpoint is removed and re-added after having cleared the firewall rule. Before the previous commit, the client would not have been able to create this new subflow. While at it, extra checks have been added to validate the expected numbers of MPJ and RM_ADDR. The 'Fixes' tag here below is the same as the one from the previous commit: this patch here is not fixing anything wrong in the selftests, but it validates the previous fix for an issue introduced by this commit ID. Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-4-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/mptcp/mptcp_join.sh | 27 +++++++++++++++---- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 25077ccf31d2..fbb0174145ad 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -436,9 +436,10 @@ reset_with_tcp_filter() local ns="${!1}" local src="${2}" local target="${3}" + local chain="${4:-INPUT}" if ! ip netns exec "${ns}" ${iptables} \ - -A INPUT \ + -A "${chain}" \ -s "${src}" \ -p tcp \ -j "${target}"; then @@ -3571,10 +3572,10 @@ endpoint_tests() mptcp_lib_kill_wait $tests_pid fi - if reset "delete and re-add" && + if reset_with_tcp_filter "delete and re-add" ns2 10.0.3.2 REJECT OUTPUT && mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then - pm_nl_set_limits $ns1 1 1 - pm_nl_set_limits $ns2 1 1 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow test_linkfail=4 speed=20 \ run_tests $ns1 $ns2 10.0.1.1 & @@ -3591,11 +3592,27 @@ endpoint_tests() chk_subflow_nr "after delete" 1 chk_mptcp_info subflows 0 subflows 0 - pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow wait_mpj $ns2 chk_subflow_nr "after re-add" 2 chk_mptcp_info subflows 1 subflows 1 + + pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow + wait_attempt_fail $ns2 + chk_subflow_nr "after new reject" 2 + chk_mptcp_info subflows 1 subflows 1 + + ip netns exec "${ns2}" ${iptables} -D OUTPUT -s "10.0.3.2" -p tcp -j REJECT + pm_nl_del_endpoint $ns2 3 10.0.3.2 + pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow + wait_mpj $ns2 + chk_subflow_nr "after no reject" 3 + chk_mptcp_info subflows 2 subflows 2 + mptcp_lib_kill_wait $tests_pid + + chk_join_nr 3 3 3 + chk_rm_nr 1 1 fi # remove and re-add From ef34a6ea0cab1800f4b3c9c3c2cefd5091e03379 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:23 +0200 Subject: [PATCH 468/562] mptcp: pm: re-using ID of unused flushed subflows If no subflows are attached to the 'subflow' endpoints that are being flushed, the corresponding addr IDs will not be marked as available again. Mark all ID as being available when flushing all the 'subflow' endpoints, and reset local_addr_used counter to cover these cases. Note that mptcp_pm_remove_addrs_and_subflows() helper is only called for flushing operations, not to remove a specific set of addresses and subflows. Fixes: 06faa2271034 ("mptcp: remove multi addresses and subflows in PM") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-5-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 8b232a210a06..2c26696b820e 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1623,8 +1623,15 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, mptcp_pm_remove_addr(msk, &alist); spin_unlock_bh(&msk->pm.lock); } + if (slist.nr) mptcp_pm_remove_subflow(msk, &slist); + + /* Reset counters: maybe some subflows have been removed before */ + spin_lock_bh(&msk->pm.lock); + bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); + msk->pm.local_addr_used = 0; + spin_unlock_bh(&msk->pm.lock); } static void mptcp_nl_remove_addrs_list(struct net *net, From e06959e9eebdfea4654390f53b65cff57691872e Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:24 +0200 Subject: [PATCH 469/562] selftests: mptcp: join: test for flush/re-add endpoints After having flushed endpoints that didn't cause the creation of new subflows, it is important to check endpoints can be re-created, re-using previously used IDs. Before the previous commit, the client would not have been able to re-create the subflow that was previously rejected. The 'Fixes' tag here below is the same as the one from the previous commit: this patch here is not fixing anything wrong in the selftests, but it validates the previous fix for an issue introduced by this commit ID. Fixes: 06faa2271034 ("mptcp: remove multi addresses and subflows in PM") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-6-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/mptcp/mptcp_join.sh | 30 +++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index fbb0174145ad..f609c02c6123 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3651,6 +3651,36 @@ endpoint_tests() chk_rm_nr 2 1 invert fi + # flush and re-add + if reset_with_tcp_filter "flush re-add" ns2 10.0.3.2 REJECT OUTPUT && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + # broadcast IP: no packet for this address will be received on ns1 + pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow + test_linkfail=4 speed=20 \ + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! + + wait_attempt_fail $ns2 + chk_subflow_nr "before flush" 1 + chk_mptcp_info subflows 0 subflows 0 + + pm_nl_flush_endpoint $ns2 + pm_nl_flush_endpoint $ns1 + wait_rm_addr $ns2 0 + ip netns exec "${ns2}" ${iptables} -D OUTPUT -s "10.0.3.2" -p tcp -j REJECT + pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow + wait_mpj $ns2 + pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal + wait_mpj $ns2 + mptcp_lib_kill_wait $tests_pid + + chk_join_nr 2 2 2 + chk_add_nr 2 2 + chk_rm_nr 1 0 invert + fi } # [$1: error message] From f448451aa62d54be16acb0034223c17e0d12bc69 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:25 +0200 Subject: [PATCH 470/562] mptcp: pm: remove mptcp_pm_remove_subflow() This helper is confusing. It is in pm.c, but it is specific to the in-kernel PM and it cannot be used by the userspace one. Also, it simply calls one in-kernel specific function with the PM lock, while the similar mptcp_pm_remove_addr() helper requires the PM lock. What's left is the pr_debug(), which is not that useful, because a similar one is present in the only function called by this helper: mptcp_pm_nl_rm_subflow_received() After these modifications, this helper can be marked as 'static', and the lock can be taken only once in mptcp_pm_flush_addrs_and_subflows(). Note that it is not a bug fix, but it will help backporting the following commits. Fixes: 0ee4261a3681 ("mptcp: implement mptcp_pm_remove_subflow") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-7-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm.c | 10 ---------- net/mptcp/pm_netlink.c | 16 +++++++--------- net/mptcp/protocol.h | 3 --- 3 files changed, 7 insertions(+), 22 deletions(-) diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 23bb89c94e90..925123e99889 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -60,16 +60,6 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ return 0; } -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list) -{ - pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr); - - spin_lock_bh(&msk->pm.lock); - mptcp_pm_nl_rm_subflow_received(msk, rm_list); - spin_unlock_bh(&msk->pm.lock); - return 0; -} - /* path manager event handlers */ void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 2c26696b820e..44fc1c5959ac 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -857,8 +857,8 @@ static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk) mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR); } -void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, - const struct mptcp_rm_list *rm_list) +static void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, + const struct mptcp_rm_list *rm_list) { mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW); } @@ -1471,7 +1471,9 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)); if (remove_subflow) { - mptcp_pm_remove_subflow(msk, &list); + spin_lock_bh(&msk->pm.lock); + mptcp_pm_nl_rm_subflow_received(msk, &list); + spin_unlock_bh(&msk->pm.lock); } else if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { /* If the subflow has been used, but now closed */ spin_lock_bh(&msk->pm.lock); @@ -1617,18 +1619,14 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, alist.ids[alist.nr++] = entry->addr.id; } + spin_lock_bh(&msk->pm.lock); if (alist.nr) { - spin_lock_bh(&msk->pm.lock); msk->pm.add_addr_signaled -= alist.nr; mptcp_pm_remove_addr(msk, &alist); - spin_unlock_bh(&msk->pm.lock); } - if (slist.nr) - mptcp_pm_remove_subflow(msk, &slist); - + mptcp_pm_nl_rm_subflow_received(msk, &slist); /* Reset counters: maybe some subflows have been removed before */ - spin_lock_bh(&msk->pm.lock); bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); msk->pm.local_addr_used = 0; spin_unlock_bh(&msk->pm.lock); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 60c6b073d65f..a1c1b0ff1ce1 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1026,7 +1026,6 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool echo); int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list); void mptcp_free_local_addr_list(struct mptcp_sock *msk); @@ -1133,8 +1132,6 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_work(struct mptcp_sock *msk); -void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, - const struct mptcp_rm_list *rm_list); unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk); From 322ea3778965da72862cca2a0c50253aacf65fe6 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:26 +0200 Subject: [PATCH 471/562] mptcp: pm: only mark 'subflow' endp as available Adding the following warning ... WARN_ON_ONCE(msk->pm.local_addr_used == 0) ... before decrementing the local_addr_used counter helped to find a bug when running the "remove single address" subtest from the mptcp_join.sh selftests. Removing a 'signal' endpoint will trigger the removal of all subflows linked to this endpoint via mptcp_pm_nl_rm_addr_or_subflow() with rm_type == MPTCP_MIB_RMSUBFLOW. This will decrement the local_addr_used counter, which is wrong in this case because this counter is linked to 'subflow' endpoints, and here it is a 'signal' endpoint that is being removed. Now, the counter is decremented, only if the ID is being used outside of mptcp_pm_nl_rm_addr_or_subflow(), only for 'subflow' endpoints, and if the ID is not 0 -- local_addr_used is not taking into account these ones. This marking of the ID as being available, and the decrement is done no matter if a subflow using this ID is currently available, because the subflow could have been closed before. Fixes: 06faa2271034 ("mptcp: remove multi addresses and subflows in PM") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-8-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 44fc1c5959ac..4cf7cc851f80 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -833,10 +833,10 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, if (rm_type == MPTCP_MIB_RMSUBFLOW) __MPTCP_INC_STATS(sock_net(sk), rm_type); } - if (rm_type == MPTCP_MIB_RMSUBFLOW) - __set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap); - else if (rm_type == MPTCP_MIB_RMADDR) + + if (rm_type == MPTCP_MIB_RMADDR) __MPTCP_INC_STATS(sock_net(sk), rm_type); + if (!removed) continue; @@ -846,8 +846,6 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, if (rm_type == MPTCP_MIB_RMADDR) { msk->pm.add_addr_accepted--; WRITE_ONCE(msk->pm.accept_addr, true); - } else if (rm_type == MPTCP_MIB_RMSUBFLOW) { - msk->pm.local_addr_used--; } } } @@ -1441,6 +1439,14 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, return ret; } +static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id) +{ + /* If it was marked as used, and not ID 0, decrement local_addr_used */ + if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) && + id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0)) + msk->pm.local_addr_used--; +} + static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, const struct mptcp_pm_addr_entry *entry) { @@ -1474,11 +1480,11 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, spin_lock_bh(&msk->pm.lock); mptcp_pm_nl_rm_subflow_received(msk, &list); spin_unlock_bh(&msk->pm.lock); - } else if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { - /* If the subflow has been used, but now closed */ + } + + if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { spin_lock_bh(&msk->pm.lock); - if (!__test_and_set_bit(entry->addr.id, msk->pm.id_avail_bitmap)) - msk->pm.local_addr_used--; + __mark_subflow_endp_available(msk, list.ids[0]); spin_unlock_bh(&msk->pm.lock); } @@ -1516,6 +1522,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net, spin_lock_bh(&msk->pm.lock); mptcp_pm_remove_addr(msk, &list); mptcp_pm_nl_rm_subflow_received(msk, &list); + __mark_subflow_endp_available(msk, 0); spin_unlock_bh(&msk->pm.lock); release_sock(sk); @@ -1917,6 +1924,7 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk, spin_lock_bh(&msk->pm.lock); mptcp_pm_nl_rm_subflow_received(msk, &list); + __mark_subflow_endp_available(msk, list.ids[0]); mptcp_pm_create_subflow_or_signal_addr(msk); spin_unlock_bh(&msk->pm.lock); } From 1c1f721375989579e46741f59523e39ec9b2a9bd Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:27 +0200 Subject: [PATCH 472/562] mptcp: pm: only decrement add_addr_accepted for MPJ req Adding the following warning ... WARN_ON_ONCE(msk->pm.add_addr_accepted == 0) ... before decrementing the add_addr_accepted counter helped to find a bug when running the "remove single subflow" subtest from the mptcp_join.sh selftest. Removing a 'subflow' endpoint will first trigger a RM_ADDR, then the subflow closure. Before this patch, and upon the reception of the RM_ADDR, the other peer will then try to decrement this add_addr_accepted. That's not correct because the attached subflows have not been created upon the reception of an ADD_ADDR. A way to solve that is to decrement the counter only if the attached subflow was an MP_JOIN to a remote id that was not 0, and initiated by the host receiving the RM_ADDR. Fixes: d0876b2284cf ("mptcp: add the incoming RM_ADDR support") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-9-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 4cf7cc851f80..882781571c7b 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -829,7 +829,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, mptcp_close_ssk(sk, ssk, subflow); spin_lock_bh(&msk->pm.lock); - removed = true; + removed |= subflow->request_join; if (rm_type == MPTCP_MIB_RMSUBFLOW) __MPTCP_INC_STATS(sock_net(sk), rm_type); } @@ -843,7 +843,11 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, if (!mptcp_pm_is_kernel(msk)) continue; - if (rm_type == MPTCP_MIB_RMADDR) { + if (rm_type == MPTCP_MIB_RMADDR && rm_id && + !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) { + /* Note: if the subflow has been closed before, this + * add_addr_accepted counter will not be decremented. + */ msk->pm.add_addr_accepted--; WRITE_ONCE(msk->pm.accept_addr, true); } From 0137a3c7c2ea3f9df8ebfc65d78b4ba712a187bb Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:28 +0200 Subject: [PATCH 473/562] mptcp: pm: check add_addr_accept_max before accepting new ADD_ADDR The limits might have changed in between, it is best to check them before accepting new ADD_ADDR. Fixes: d0876b2284cf ("mptcp: add the incoming RM_ADDR support") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-10-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 882781571c7b..28a9a3726146 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -848,8 +848,8 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, /* Note: if the subflow has been closed before, this * add_addr_accepted counter will not be decremented. */ - msk->pm.add_addr_accepted--; - WRITE_ONCE(msk->pm.accept_addr, true); + if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk)) + WRITE_ONCE(msk->pm.accept_addr, true); } } } From ca6e55a703ca2894611bb5c5bca8bfd2290fd91e Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:29 +0200 Subject: [PATCH 474/562] mptcp: pm: only in-kernel cannot have entries with ID 0 The ID 0 is specific per MPTCP connections. The per netns entries cannot have this special ID 0 then. But that's different for the userspace PM where the entries are per connection, they can then use this special ID 0. Fixes: f40be0db0b76 ("mptcp: unify pm get_flags_and_ifindex_by_id") Cc: stable@vger.kernel.org Acked-by: Geliang Tang Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-11-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm.c | 3 --- net/mptcp/pm_netlink.c | 4 ++++ 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 925123e99889..3e6e0f5510bb 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -434,9 +434,6 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id *flags = 0; *ifindex = 0; - if (!id) - return 0; - if (mptcp_pm_is_userspace(msk)) return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 28a9a3726146..d0a80f537fc3 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1395,6 +1395,10 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int struct sock *sk = (struct sock *)msk; struct net *net = sock_net(sk); + /* No entries with ID 0 */ + if (id == 0) + return 0; + rcu_read_lock(); entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id); if (entry) { From 09355f7abb9fbfc1a240be029837921ea417bf4f Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:30 +0200 Subject: [PATCH 475/562] mptcp: pm: fullmesh: select the right ID later When reacting upon the reception of an ADD_ADDR, the in-kernel PM first looks for fullmesh endpoints. If there are some, it will pick them, using their entry ID. It should set the ID 0 when using the endpoint corresponding to the initial subflow, it is a special case imposed by the MPTCP specs. Note that msk->mpc_endpoint_id might not be set when receiving the first ADD_ADDR from the server. So better to compare the addresses. Fixes: 1a0d6136c5f0 ("mptcp: local addresses fullmesh") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-12-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index d0a80f537fc3..a2e37ab1c40f 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -636,6 +636,7 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, { struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *entry; + struct mptcp_addr_info mpc_addr; struct pm_nl_pernet *pernet; unsigned int subflows_max; int i = 0; @@ -643,6 +644,8 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, pernet = pm_nl_get_pernet_from_msk(msk); subflows_max = mptcp_pm_get_subflows_max(msk); + mptcp_local_address((struct sock_common *)msk, &mpc_addr); + rcu_read_lock(); list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH)) @@ -653,7 +656,13 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, if (msk->pm.subflows < subflows_max) { msk->pm.subflows++; - addrs[i++] = entry->addr; + addrs[i] = entry->addr; + + /* Special case for ID0: set the correct ID */ + if (mptcp_addresses_equal(&entry->addr, &mpc_addr, entry->addr.port)) + addrs[i].id = 0; + + i++; } } rcu_read_unlock(); From 4878f9f8421f4587bee7b232c1c8a9d3a7d4d782 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:31 +0200 Subject: [PATCH 476/562] selftests: mptcp: join: validate fullmesh endp on 1st sf This case was not covered, and the wrong ID was set before the previous commit. The rest is not modified, it is just that it will increase the code coverage. The right address ID can be verified by looking at the packet traces. We could automate that using Netfilter with some cBPF code for example, but that's always a bit cryptic. Packetdrill seems better fitted for that. Fixes: 4f49d63352da ("selftests: mptcp: add fullmesh testcases") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-13-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index f609c02c6123..89e553e0e0c2 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3059,6 +3059,7 @@ fullmesh_tests() pm_nl_set_limits $ns1 1 3 pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,fullmesh fullmesh=1 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 From 48e50dcbcbaaf713d82bf2da5c16aeced94ad07d Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:32 +0200 Subject: [PATCH 477/562] mptcp: pm: avoid possible UaF when selecting endp select_local_address() and select_signal_address() both select an endpoint entry from the list inside an RCU protected section, but return a reference to it, to be read later on. If the entry is dereferenced after the RCU unlock, reading info could cause a Use-after-Free. A simple solution is to copy the required info while inside the RCU protected section to avoid any risk of UaF later. The address ID might need to be modified later to handle the ID0 case later, so a copy seems OK to deal with. Reported-by: Paolo Abeni Closes: https://lore.kernel.org/45cd30d3-7710-491c-ae4d-a1368c00beb1@redhat.com Fixes: 01cacb00b35c ("mptcp: add netlink-based PM") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-14-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 64 ++++++++++++++++++++++-------------------- 1 file changed, 34 insertions(+), 30 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index a2e37ab1c40f..3e4ad801786f 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -143,11 +143,13 @@ static bool lookup_subflow_by_daddr(const struct list_head *list, return false; } -static struct mptcp_pm_addr_entry * +static bool select_local_address(const struct pm_nl_pernet *pernet, - const struct mptcp_sock *msk) + const struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *new_entry) { - struct mptcp_pm_addr_entry *entry, *ret = NULL; + struct mptcp_pm_addr_entry *entry; + bool found = false; msk_owned_by_me(msk); @@ -159,17 +161,21 @@ select_local_address(const struct pm_nl_pernet *pernet, if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap)) continue; - ret = entry; + *new_entry = *entry; + found = true; break; } rcu_read_unlock(); - return ret; + + return found; } -static struct mptcp_pm_addr_entry * -select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) +static bool +select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *new_entry) { - struct mptcp_pm_addr_entry *entry, *ret = NULL; + struct mptcp_pm_addr_entry *entry; + bool found = false; rcu_read_lock(); /* do not keep any additional per socket state, just signal @@ -184,11 +190,13 @@ select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) continue; - ret = entry; + *new_entry = *entry; + found = true; break; } rcu_read_unlock(); - return ret; + + return found; } unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk) @@ -512,9 +520,10 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info) static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { - struct mptcp_pm_addr_entry *local, *signal_and_subflow = NULL; struct sock *sk = (struct sock *)msk; + struct mptcp_pm_addr_entry local; unsigned int add_addr_signal_max; + bool signal_and_subflow = false; unsigned int local_addr_max; struct pm_nl_pernet *pernet; unsigned int subflows_max; @@ -565,23 +574,22 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL)) return; - local = select_signal_address(pernet, msk); - if (!local) + if (!select_signal_address(pernet, msk, &local)) goto subflow; /* If the alloc fails, we are on memory pressure, not worth * continuing, and trying to create subflows. */ - if (!mptcp_pm_alloc_anno_list(msk, &local->addr)) + if (!mptcp_pm_alloc_anno_list(msk, &local.addr)) return; - __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); + __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); msk->pm.add_addr_signaled++; - mptcp_pm_announce_addr(msk, &local->addr, false); + mptcp_pm_announce_addr(msk, &local.addr, false); mptcp_pm_nl_addr_send_ack(msk); - if (local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) - signal_and_subflow = local; + if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) + signal_and_subflow = true; } subflow: @@ -592,26 +600,22 @@ subflow: bool fullmesh; int i, nr; - if (signal_and_subflow) { - local = signal_and_subflow; - signal_and_subflow = NULL; - } else { - local = select_local_address(pernet, msk); - if (!local) - break; - } + if (signal_and_subflow) + signal_and_subflow = false; + else if (!select_local_address(pernet, msk, &local)) + break; - fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH); + fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH); msk->pm.local_addr_used++; - __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); - nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs); + __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); + nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs); if (nr == 0) continue; spin_unlock_bh(&msk->pm.lock); for (i = 0; i < nr; i++) - __mptcp_subflow_connect(sk, &local->addr, &addrs[i]); + __mptcp_subflow_connect(sk, &local.addr, &addrs[i]); spin_lock_bh(&msk->pm.lock); } mptcp_pm_nl_check_work_pending(msk); From 0b43312902d165c4c8429cd49e8c91479f52b7c4 Mon Sep 17 00:00:00 2001 From: Yang Wang Date: Tue, 13 Aug 2024 13:51:48 +0800 Subject: [PATCH 478/562] drm/amdgpu: fixing rlc firmware loading failure issue Skip rlc firmware validation to ignore firmware header size mismatch issues. This restores the workaround added in commit 849e133c973c ("drm/amdgpu: Fix the null pointer when load rlc firmware") Fixes: 3af2c80ae2f5 ("drm/amdgpu: refine gfx10 firmware loading") Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3551 Signed-off-by: Yang Wang Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit 89ec85d16eb8110d88c273d1d34f1fe5a70ba8cc) --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 2957702fca0c..e444e621ddaa 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -4116,6 +4116,7 @@ static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev) static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) { + char fw_name[53]; char ucode_prefix[30]; const char *wks = ""; int err; @@ -4149,8 +4150,8 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_CE); if (!amdgpu_sriov_vf(adev)) { - err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, - "amdgpu/%s_rlc.bin", ucode_prefix); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", ucode_prefix); + err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev); if (err) goto out; From e3e4bf58bad1576ac732a1429f53e3d4bfb82b4b Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 14 Aug 2024 10:28:24 -0400 Subject: [PATCH 479/562] drm/amdgpu/sdma5.2: limit wptr workaround to sdma 5.2.1 The workaround seems to cause stability issues on other SDMA 5.2.x IPs. Fixes: a03ebf116303 ("drm/amdgpu/sdma5.2: Update wptr registers as well as doorbell") Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3556 Acked-by: Ruijing Dong Signed-off-by: Alex Deucher (cherry picked from commit 2dc3851ef7d9c5439ea8e9623fc36878f3b40649) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index af1e90159ce3..2e72d445415f 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -176,14 +176,16 @@ static void sdma_v5_2_ring_set_wptr(struct amdgpu_ring *ring) DRM_DEBUG("calling WDOORBELL64(0x%08x, 0x%016llx)\n", ring->doorbell_index, ring->wptr << 2); WDOORBELL64(ring->doorbell_index, ring->wptr << 2); - /* SDMA seems to miss doorbells sometimes when powergating kicks in. - * Updating the wptr directly will wake it. This is only safe because - * we disallow gfxoff in begin_use() and then allow it again in end_use(). - */ - WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR), - lower_32_bits(ring->wptr << 2)); - WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI), - upper_32_bits(ring->wptr << 2)); + if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) == IP_VERSION(5, 2, 1)) { + /* SDMA seems to miss doorbells sometimes when powergating kicks in. + * Updating the wptr directly will wake it. This is only safe because + * we disallow gfxoff in begin_use() and then allow it again in end_use(). + */ + WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR), + lower_32_bits(ring->wptr << 2)); + WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI), + upper_32_bits(ring->wptr << 2)); + } } else { DRM_DEBUG("Not using doorbell -- " "mmSDMA%i_GFX_RB_WPTR == 0x%08x " From c99769bceab4ecb6a067b9af11f9db281eea3e2a Mon Sep 17 00:00:00 2001 From: Candice Li Date: Thu, 15 Aug 2024 11:37:28 +0800 Subject: [PATCH 480/562] drm/amdgpu: Validate TA binary size Add TA binary size validation to avoid OOB write. Signed-off-by: Candice Li Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher (cherry picked from commit c0a04e3570d72aaf090962156ad085e37c62e442) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c index 0c856005df6b..38face981c3e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c @@ -166,6 +166,9 @@ static ssize_t ta_if_load_debugfs_write(struct file *fp, const char *buf, size_t if (ret) return -EFAULT; + if (ta_bin_len > PSP_1_MEG) + return -EINVAL; + copy_pos += sizeof(uint32_t); ta_bin = kzalloc(ta_bin_len, GFP_KERNEL); From 9cead81eff635e3b3cbce51b40228f3bdc6f2b8c Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 19 Aug 2024 11:14:29 -0400 Subject: [PATCH 481/562] drm/amdgpu: fix eGPU hotplug regression The driver needs to wait for the on board firmware to finish its initialization before probing the card. Commit 959056982a9b ("drm/amdgpu: Fix discovery initialization failure during pci rescan") switched from using msleep() to using usleep_range() which seems to have caused init failures on some navi1x boards. Switch back to msleep(). Fixes: 959056982a9b ("drm/amdgpu: Fix discovery initialization failure during pci rescan") Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3559 Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3500 Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher Cc: Ma Jun (cherry picked from commit c69b07f7bbc905022491c45097923d3487479529) Cc: stable@vger.kernel.org # 6.10.x --- drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index ac108fca64fe..7b561e8e3caf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -278,7 +278,7 @@ static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev, msg = RREG32(mmMP0_SMN_C2PMSG_33); if (msg & 0x80000000) break; - usleep_range(1000, 1100); + msleep(1); } } From 822c8020aebcf5804a143b891e34f29873fee5e2 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 20 Aug 2024 13:03:58 +1000 Subject: [PATCH 482/562] ata: pata_macio: Fix DMA table overflow MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Kolbjørn and Jonáš reported that their 32-bit PowerMacs were crashing in pata-macio since commit 09fe2bfa6b83 ("ata: pata_macio: Fix max_segment_size with PAGE_SIZE == 64K"). For example: kernel BUG at drivers/ata/pata_macio.c:544! Oops: Exception in kernel mode, sig: 5 [#1] BE PAGE_SIZE=4K MMU=Hash SMP NR_CPUS=2 DEBUG_PAGEALLOC PowerMac ... NIP pata_macio_qc_prep+0xf4/0x190 LR pata_macio_qc_prep+0xfc/0x190 Call Trace: 0xc1421660 (unreliable) ata_qc_issue+0x14c/0x2d4 __ata_scsi_queuecmd+0x200/0x53c ata_scsi_queuecmd+0x50/0xe0 scsi_queue_rq+0x788/0xb1c __blk_mq_issue_directly+0x58/0xf4 blk_mq_plug_issue_direct+0x8c/0x1b4 blk_mq_flush_plug_list.part.0+0x584/0x5e0 __blk_flush_plug+0xf8/0x194 __submit_bio+0x1b8/0x2e0 submit_bio_noacct_nocheck+0x230/0x304 btrfs_work_helper+0x200/0x338 process_one_work+0x1a8/0x338 worker_thread+0x364/0x4c0 kthread+0x100/0x104 start_kernel_thread+0x10/0x14 That commit increased max_segment_size to 64KB, with the justification that the SCSI core was already using that size when PAGE_SIZE == 64KB, and that there was existing logic to split over-sized requests. However with a sufficiently large request, the splitting logic causes each sg to be split into two commands in the DMA table, leading to overflow of the DMA table, triggering the BUG_ON(). With default settings the bug doesn't trigger, because the request size is limited by max_sectors_kb == 1280, however max_sectors_kb can be increased, and apparently some distros do that by default using udev rules. Fix the bug for 4KB kernels by reverting to the old max_segment_size. For 64KB kernels the sg_tablesize needs to be halved, to allow for the possibility that each sg will be split into two. Fixes: 09fe2bfa6b83 ("ata: pata_macio: Fix max_segment_size with PAGE_SIZE == 64K") Cc: stable@vger.kernel.org # v6.10+ Reported-by: Kolbjørn Barmen Closes: https://lore.kernel.org/all/62d248bb-e97a-25d2-bcf2-9160c518cae5@kolla.no/ Reported-by: Jonáš Vidra Closes: https://lore.kernel.org/all/3b6441b8-06e6-45da-9e55-f92f2c86933e@ufal.mff.cuni.cz/ Tested-by: Kolbjørn Barmen Signed-off-by: Michael Ellerman Signed-off-by: Damien Le Moal --- drivers/ata/pata_macio.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index 1b85e8bf4ef9..1cb8d24b088f 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -208,6 +208,19 @@ static const char* macio_ata_names[] = { /* Don't let a DMA segment go all the way to 64K */ #define MAX_DBDMA_SEG 0xff00 +#ifdef CONFIG_PAGE_SIZE_64KB +/* + * The SCSI core requires the segment size to cover at least a page, so + * for 64K page size kernels it must be at least 64K. However the + * hardware can't handle 64K, so pata_macio_qc_prep() will split large + * requests. To handle the split requests the tablesize must be halved. + */ +#define PATA_MACIO_MAX_SEGMENT_SIZE SZ_64K +#define PATA_MACIO_SG_TABLESIZE (MAX_DCMDS / 2) +#else +#define PATA_MACIO_MAX_SEGMENT_SIZE MAX_DBDMA_SEG +#define PATA_MACIO_SG_TABLESIZE MAX_DCMDS +#endif /* * Wait 1s for disk to answer on IDE bus after a hard reset @@ -912,16 +925,10 @@ static int pata_macio_do_resume(struct pata_macio_priv *priv) static const struct scsi_host_template pata_macio_sht = { __ATA_BASE_SHT(DRV_NAME), - .sg_tablesize = MAX_DCMDS, + .sg_tablesize = PATA_MACIO_SG_TABLESIZE, /* We may not need that strict one */ .dma_boundary = ATA_DMA_BOUNDARY, - /* - * The SCSI core requires the segment size to cover at least a page, so - * for 64K page size kernels this must be at least 64K. However the - * hardware can't handle 64K, so pata_macio_qc_prep() will split large - * requests. - */ - .max_segment_size = SZ_64K, + .max_segment_size = PATA_MACIO_MAX_SEGMENT_SIZE, .device_configure = pata_macio_device_configure, .sdev_groups = ata_common_sdev_groups, .can_queue = ATA_DEF_QUEUE, From d4bc0a264fb482b019c84fbc7202dd3cab059087 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 20 Aug 2024 13:04:07 +1000 Subject: [PATCH 483/562] ata: pata_macio: Use WARN instead of BUG The overflow/underflow conditions in pata_macio_qc_prep() should never happen. But if they do there's no need to kill the system entirely, a WARN and failing the IO request should be sufficient and might allow the system to keep running. Signed-off-by: Michael Ellerman Signed-off-by: Damien Le Moal --- drivers/ata/pata_macio.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index 1cb8d24b088f..f2f36e55a1f4 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -554,7 +554,8 @@ static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc) while (sg_len) { /* table overflow should never happen */ - BUG_ON (pi++ >= MAX_DCMDS); + if (WARN_ON_ONCE(pi >= MAX_DCMDS)) + return AC_ERR_SYSTEM; len = (sg_len < MAX_DBDMA_SEG) ? sg_len : MAX_DBDMA_SEG; table->command = cpu_to_le16(write ? OUTPUT_MORE: INPUT_MORE); @@ -566,11 +567,13 @@ static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc) addr += len; sg_len -= len; ++table; + ++pi; } } /* Should never happen according to Tejun */ - BUG_ON(!pi); + if (WARN_ON_ONCE(!pi)) + return AC_ERR_SYSTEM; /* Convert the last command to an input/output */ table--; From e0ee967630c8ee67bb47a5b38d235cd5a8789c48 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 20 Aug 2024 18:31:58 -0600 Subject: [PATCH 484/562] io_uring/kbuf: sanitize peek buffer setup Harden the buffer peeking a bit, by adding a sanity check for it having a valid size. Outside of that, arg->max_len is a size_t, though it's only ever set to a 32-bit value (as it's governed by MAX_RW_COUNT). Bump our needed check to a size_t so we know it fits. Finally, cap the calculated needed iov value to the PEEK_MAX_IMPORT, which is the maximum number of segments that should be peeked. Fixes: 35c8711c8fc4 ("io_uring/kbuf: add helpers for getting/peeking multiple buffers") Signed-off-by: Jens Axboe --- io_uring/kbuf.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index c95dc1736dd9..1af2bd56af44 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -218,10 +218,13 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, buf = io_ring_head_to_buf(br, head, bl->mask); if (arg->max_len) { - int needed; + u32 len = READ_ONCE(buf->len); + size_t needed; - needed = (arg->max_len + buf->len - 1) / buf->len; - needed = min(needed, PEEK_MAX_IMPORT); + if (unlikely(!len)) + return -ENOBUFS; + needed = (arg->max_len + len - 1) / len; + needed = min_not_zero(needed, (size_t) PEEK_MAX_IMPORT); if (nr_avail > needed) nr_avail = needed; } From a3ca27c405faad584af6e8e38cdafe5be73230a1 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Fri, 9 Aug 2024 08:47:15 +0200 Subject: [PATCH 485/562] s390/mm: Prevent lowcore vs identity mapping overlap The identity mapping position in virtual memory is randomized together with the kernel mapping. That position can never overlap with the lowcore even when the lowcore is relocated. Prevent overlapping with the lowcore to allow independent positioning of the identity mapping. With the current value of the alternative lowcore address of 0x70000 the overlap could happen in case the identity mapping is placed at zero. This is a prerequisite for uncoupling of randomization base of kernel image and identity mapping in virtual memory. Acked-by: Vasily Gorbik Signed-off-by: Alexander Gordeev Signed-off-by: Vasily Gorbik --- arch/s390/kernel/setup.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 4ec99f73fa27..a3fea683b227 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -734,7 +734,23 @@ static void __init memblock_add_physmem_info(void) } /* - * Reserve memory used for lowcore/command line/kernel image. + * Reserve memory used for lowcore. + */ +static void __init reserve_lowcore(void) +{ + void *lowcore_start = get_lowcore(); + void *lowcore_end = lowcore_start + sizeof(struct lowcore); + void *start, *end; + + if ((void *)__identity_base < lowcore_end) { + start = max(lowcore_start, (void *)__identity_base); + end = min(lowcore_end, (void *)(__identity_base + ident_map_size)); + memblock_reserve(__pa(start), __pa(end)); + } +} + +/* + * Reserve memory used for absolute lowcore/command line/kernel image. */ static void __init reserve_kernel(void) { @@ -918,6 +934,7 @@ void __init setup_arch(char **cmdline_p) /* Do some memory reservations *before* memory is added to memblock */ reserve_pgtables(); + reserve_lowcore(); reserve_kernel(); reserve_initrd(); reserve_certificate_list(); From 32db401965f165f7c44447d0508097f070c8f576 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Fri, 9 Aug 2024 08:47:16 +0200 Subject: [PATCH 486/562] s390/mm: Pin identity mapping base to zero SIE instruction performs faster when the virtual address of SIE block matches the physical one. Pin the identity mapping base to zero for the benefit of SIE and other instructions that have similar performance impact. Still, randomize the base when DEBUG_VM kernel configuration option is enabled. Suggested-by: Vasily Gorbik Reviewed-by: Christian Borntraeger Signed-off-by: Alexander Gordeev Signed-off-by: Vasily Gorbik --- arch/s390/Kconfig | 13 +++++++++++++ arch/s390/boot/startup.c | 3 ++- 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index a822f952f64a..c60e699e99f5 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -604,6 +604,19 @@ config RANDOMIZE_BASE as a security feature that deters exploit attempts relying on knowledge of the location of kernel internals. +config RANDOMIZE_IDENTITY_BASE + bool "Randomize the address of the identity mapping base" + depends on RANDOMIZE_BASE + default DEBUG_VM + help + The identity mapping base address is pinned to zero by default. + Allow randomization of that base to expose otherwise missed + notion of physical and virtual addresses of data structures. + That does not have any impact on the base address at which the + kernel image is loaded. + + If unsure, say N + config KERNEL_IMAGE_BASE hex "Kernel image base address" range 0x100000 0x1FFFFFE0000000 if !KASAN diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index ce232552bc1c..cff34744b5a9 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -341,7 +341,8 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size) BUILD_BUG_ON(MAX_DCSS_ADDR > (1UL << MAX_PHYSMEM_BITS)); max_mappable = max(ident_map_size, MAX_DCSS_ADDR); max_mappable = min(max_mappable, vmemmap_start); - __identity_base = round_down(vmemmap_start - max_mappable, rte_size); + if (IS_ENABLED(CONFIG_RANDOMIZE_IDENTITY_BASE)) + __identity_base = round_down(vmemmap_start - max_mappable, rte_size); return asce_limit; } From b4f5bd60d558f6ba451d7e76aa05782c07a182a3 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Tue, 6 Aug 2024 12:06:23 +0200 Subject: [PATCH 487/562] s390/ap: Refine AP bus bindings complete processing With the rework of the AP bus scan and the introduction of a bindings complete completion also the timing until the userspace finally receives a AP bus binding complete uevent had increased. Unfortunately this event triggers some important jobs for preparation of KVM guests, for example the modification of card/queue masks to reassign AP resources to the alternate AP queue device driver (vfio_ap) which is the precondition for building mediated devices which may be a precondition for starting KVM guests using AP resources. This small fix now triggers the check for binding complete each time an AP device driver has registered. With this patch the bindings complete may be posted up to 30s earlier as there is no need to wait for the next AP bus scan any more. Fixes: 778412ab915d ("s390/ap: rearm APQNs bindings complete completion") Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Cc: stable@vger.kernel.org Acked-by: Alexander Gordeev Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/ap_bus.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 0998b17ecb37..f9f682f19415 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -971,11 +971,16 @@ int ap_driver_register(struct ap_driver *ap_drv, struct module *owner, char *name) { struct device_driver *drv = &ap_drv->driver; + int rc; drv->bus = &ap_bus_type; drv->owner = owner; drv->name = name; - return driver_register(drv); + rc = driver_register(drv); + + ap_check_bindings_complete(); + + return rc; } EXPORT_SYMBOL(ap_driver_register); From a6f78359ac75f24cac3c1bdd753c49c1877bcd82 Mon Sep 17 00:00:00 2001 From: Stuart Summers Date: Sat, 17 Aug 2024 02:47:30 +0000 Subject: [PATCH 488/562] drm/xe: Fix missing workqueue destroy in xe_gt_pagefault On driver reload we never free up the memory for the pagefault and access counter workqueues. Add those destroy calls here. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Stuart Summers Reviewed-by: Rodrigo Vivi Signed-off-by: Matthew Brost Link: https://patchwork.freedesktop.org/patch/msgid/c9a951505271dc3a7aee76de7656679f69c11518.1723862633.git.stuart.summers@intel.com (cherry picked from commit 7586fc52b14e0b8edd0d1f8a434e0de2078b7b2b) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_gt_pagefault.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index 9292d5468868..b2a7fa55bd18 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -382,6 +382,18 @@ static void pf_queue_work_func(struct work_struct *w) static void acc_queue_work_func(struct work_struct *w); +static void pagefault_fini(void *arg) +{ + struct xe_gt *gt = arg; + struct xe_device *xe = gt_to_xe(gt); + + if (!xe->info.has_usm) + return; + + destroy_workqueue(gt->usm.acc_wq); + destroy_workqueue(gt->usm.pf_wq); +} + int xe_gt_pagefault_init(struct xe_gt *gt) { struct xe_device *xe = gt_to_xe(gt); @@ -409,10 +421,12 @@ int xe_gt_pagefault_init(struct xe_gt *gt) gt->usm.acc_wq = alloc_workqueue("xe_gt_access_counter_work_queue", WQ_UNBOUND | WQ_HIGHPRI, NUM_ACC_QUEUE); - if (!gt->usm.acc_wq) + if (!gt->usm.acc_wq) { + destroy_workqueue(gt->usm.pf_wq); return -ENOMEM; + } - return 0; + return devm_add_action_or_reset(xe->drm.dev, pagefault_fini, gt); } void xe_gt_pagefault_reset(struct xe_gt *gt) From dd3e840a33b57b92812fbec26273b3f0b4eb5ae3 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Thu, 15 Aug 2024 12:35:22 -0700 Subject: [PATCH 489/562] drm/xe: Drop HW fence pointer to HW fence ctx The HW fence ctx objects are not ref counted rather tied to the life of an LRC object. HW fences reference the HW fence ctx, HW fences can outlive LRCs thus resulting in UAF. Drop the HW fence pointer to HW fence ctx rather just store what is needed directly in HW fence. v2: - Fix typo in commit (Ashutosh) - Use snprintf (Ashutosh) Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Matthew Brost Reviewed-by: Ashutosh Dixit Link: https://patchwork.freedesktop.org/patch/msgid/20240815193522.16008-1-matthew.brost@intel.com (cherry picked from commit 60db6f540af9f93144d5039140aa2ed17171d168) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_hw_fence.c | 9 +++++---- drivers/gpu/drm/xe/xe_hw_fence_types.h | 7 +++++-- drivers/gpu/drm/xe/xe_trace.h | 2 +- 3 files changed, 11 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_hw_fence.c b/drivers/gpu/drm/xe/xe_hw_fence.c index 45a9789cf501..0b4f12be3692 100644 --- a/drivers/gpu/drm/xe/xe_hw_fence.c +++ b/drivers/gpu/drm/xe/xe_hw_fence.c @@ -148,20 +148,20 @@ static const char *xe_hw_fence_get_driver_name(struct dma_fence *dma_fence) { struct xe_hw_fence *fence = to_xe_hw_fence(dma_fence); - return dev_name(gt_to_xe(fence->ctx->gt)->drm.dev); + return dev_name(fence->xe->drm.dev); } static const char *xe_hw_fence_get_timeline_name(struct dma_fence *dma_fence) { struct xe_hw_fence *fence = to_xe_hw_fence(dma_fence); - return fence->ctx->name; + return fence->name; } static bool xe_hw_fence_signaled(struct dma_fence *dma_fence) { struct xe_hw_fence *fence = to_xe_hw_fence(dma_fence); - struct xe_device *xe = gt_to_xe(fence->ctx->gt); + struct xe_device *xe = fence->xe; u32 seqno = xe_map_rd(xe, &fence->seqno_map, 0, u32); return dma_fence->error || @@ -253,7 +253,8 @@ void xe_hw_fence_init(struct dma_fence *fence, struct xe_hw_fence_ctx *ctx, struct xe_hw_fence *hw_fence = container_of(fence, typeof(*hw_fence), dma); - hw_fence->ctx = ctx; + hw_fence->xe = gt_to_xe(ctx->gt); + snprintf(hw_fence->name, sizeof(hw_fence->name), "%s", ctx->name); hw_fence->seqno_map = seqno_map; INIT_LIST_HEAD(&hw_fence->irq_link); diff --git a/drivers/gpu/drm/xe/xe_hw_fence_types.h b/drivers/gpu/drm/xe/xe_hw_fence_types.h index b33c4956e8ea..364a61f4bfda 100644 --- a/drivers/gpu/drm/xe/xe_hw_fence_types.h +++ b/drivers/gpu/drm/xe/xe_hw_fence_types.h @@ -12,6 +12,7 @@ #include #include +struct xe_device; struct xe_gt; /** @@ -61,8 +62,10 @@ struct xe_hw_fence_ctx { struct xe_hw_fence { /** @dma: base dma fence for hardware fence context */ struct dma_fence dma; - /** @ctx: hardware fence context */ - struct xe_hw_fence_ctx *ctx; + /** @xe: Xe device for hw fence driver name */ + struct xe_device *xe; + /** @name: name of hardware fence context */ + char name[MAX_FENCE_NAME_LEN]; /** @seqno_map: I/O map for seqno */ struct iosys_map seqno_map; /** @irq_link: Link in struct xe_hw_fence_irq.pending */ diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h index baba14fb1e32..01837f6f609f 100644 --- a/drivers/gpu/drm/xe/xe_trace.h +++ b/drivers/gpu/drm/xe/xe_trace.h @@ -309,7 +309,7 @@ DECLARE_EVENT_CLASS(xe_hw_fence, TP_ARGS(fence), TP_STRUCT__entry( - __string(dev, __dev_name_gt(fence->ctx->gt)) + __string(dev, __dev_name_xe(fence->xe)) __field(u64, ctx) __field(u32, seqno) __field(struct xe_hw_fence *, fence) From 9e7f30563677fbeff62d368d5d2a5ac7aaa9746a Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Tue, 20 Aug 2024 13:23:09 -0700 Subject: [PATCH 490/562] drm/xe: Free job before xe_exec_queue_put Free job depends on job->vm being valid, the last xe_exec_queue_put can destroy the VM. Prevent UAF by freeing job before xe_exec_queue_put. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Matthew Brost Reviewed-by: Nirmoy Das Reviewed-by: Jagmeet Randhawa Link: https://patchwork.freedesktop.org/patch/msgid/20240820202309.1260755-1-matthew.brost@intel.com (cherry picked from commit 32a42c93b74c8ca6d0915ea3eba21bceff53042f) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_sched_job.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c index 44d534e362cd..9628f9deb3c0 100644 --- a/drivers/gpu/drm/xe/xe_sched_job.c +++ b/drivers/gpu/drm/xe/xe_sched_job.c @@ -171,12 +171,13 @@ void xe_sched_job_destroy(struct kref *ref) struct xe_sched_job *job = container_of(ref, struct xe_sched_job, refcount); struct xe_device *xe = job_to_xe(job); + struct xe_exec_queue *q = job->q; xe_sched_job_free_fences(job); - xe_exec_queue_put(job->q); dma_fence_put(job->fence); drm_sched_job_cleanup(&job->drm); job_free(job); + xe_exec_queue_put(q); xe_pm_runtime_put(xe); } From 57df60e1f981fa8c288a49012a4bbb02ae0ecdbc Mon Sep 17 00:00:00 2001 From: Yang Ruibin <11162571@vivo.com> Date: Wed, 21 Aug 2024 03:59:33 -0400 Subject: [PATCH 491/562] thermal/debugfs: Fix the NULL vs IS_ERR() confusion in debugfs_create_dir() The debugfs_create_dir() return value is never NULL, it is either a valid pointer or an error one. Use IS_ERR() to check it. Fixes: 7ef01f228c9f ("thermal/debugfs: Add thermal debugfs information for mitigation episodes") Fixes: 755113d76786 ("thermal/debugfs: Add thermal cooling device debugfs information") Signed-off-by: Yang Ruibin <11162571@vivo.com> Link: https://patch.msgid.link/20240821075934.12145-1-11162571@vivo.com [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki --- drivers/thermal/thermal_debugfs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c index 7dd67bf48571..939d3e5f1817 100644 --- a/drivers/thermal/thermal_debugfs.c +++ b/drivers/thermal/thermal_debugfs.c @@ -178,11 +178,11 @@ struct thermal_debugfs { void thermal_debug_init(void) { d_root = debugfs_create_dir("thermal", NULL); - if (!d_root) + if (IS_ERR(d_root)) return; d_cdev = debugfs_create_dir("cooling_devices", d_root); - if (!d_cdev) + if (IS_ERR(d_cdev)) return; d_tz = debugfs_create_dir("thermal_zones", d_root); @@ -202,7 +202,7 @@ static struct thermal_debugfs *thermal_debugfs_add_id(struct dentry *d, int id) snprintf(ids, IDSLENGTH, "%d", id); thermal_dbg->d_top = debugfs_create_dir(ids, d); - if (!thermal_dbg->d_top) { + if (IS_ERR(thermal_dbg->d_top)) { kfree(thermal_dbg); return NULL; } From b128ed5ab27330deeeaf51ea8bb69f1442a96f7f Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Mon, 19 Aug 2024 17:06:21 +0200 Subject: [PATCH 492/562] udp: fix receiving fraglist GSO packets When assembling fraglist GSO packets, udp4_gro_complete does not set skb->csum_start, which makes the extra validation in __udp_gso_segment fail. Fixes: 89add40066f9 ("net: drop bad gso csum_start and offset in virtio_net_hdr") Signed-off-by: Felix Fietkau Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20240819150621.59833-1-nbd@nbd.name Signed-off-by: Jakub Kicinski --- net/ipv4/udp_offload.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index b254a5dadfcf..d842303587af 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -279,7 +279,8 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, return ERR_PTR(-EINVAL); if (unlikely(skb_checksum_start(gso_skb) != - skb_transport_header(gso_skb))) + skb_transport_header(gso_skb) && + !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST))) return ERR_PTR(-EINVAL); /* We don't know if egress device can segment and checksum the packet From f8669d7b5f5d2d88959456ae9123d8bb6fdc1ebe Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 20 Aug 2024 12:53:47 +0200 Subject: [PATCH 493/562] selftests: mlxsw: ethtool_lanes: Source ethtool lib from correct path Source the ethtool library from the correct path and avoid the following error: ./ethtool_lanes.sh: line 14: ./../../../net/forwarding/ethtool_lib.sh: No such file or directory Fixes: 40d269c000bd ("selftests: forwarding: Move several selftests") Signed-off-by: Ido Schimmel Signed-off-by: Petr Machata Reviewed-by: Simon Horman Link: https://patch.msgid.link/2112faff02e536e1ac14beb4c2be09c9574b90ae.1724150067.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh b/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh index 877cd6df94a1..fe905a7f34b3 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh @@ -2,6 +2,7 @@ # SPDX-License-Identifier: GPL-2.0 lib_dir=$(dirname $0)/../../../net/forwarding +ethtool_lib_dir=$(dirname $0)/../hw ALL_TESTS=" autoneg @@ -11,7 +12,7 @@ ALL_TESTS=" NUM_NETIFS=2 : ${TIMEOUT:=30000} # ms source $lib_dir/lib.sh -source $lib_dir/ethtool_lib.sh +source $ethtool_lib_dir/ethtool_lib.sh setup_prepare() { From 007d4271a5f10638cba6f0b99698557ef30014b9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Aug 2024 16:20:53 +0000 Subject: [PATCH 494/562] netpoll: do not export netpoll_poll_[disable|enable]() netpoll_poll_disable() and netpoll_poll_enable() are only used from core networking code, there is no need to export them. Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240820162053.3870927-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/core/netpoll.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 55bcacf67df3..d657b042d5a0 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -228,7 +228,6 @@ void netpoll_poll_disable(struct net_device *dev) down(&ni->dev_lock); srcu_read_unlock(&netpoll_srcu, idx); } -EXPORT_SYMBOL(netpoll_poll_disable); void netpoll_poll_enable(struct net_device *dev) { @@ -239,7 +238,6 @@ void netpoll_poll_enable(struct net_device *dev) up(&ni->dev_lock); rcu_read_unlock(); } -EXPORT_SYMBOL(netpoll_poll_enable); static void refill_skbs(void) { From faa389b2fbaaec7fd27a390b4896139f9da662e3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Aug 2024 16:08:57 +0000 Subject: [PATCH 495/562] ipv6: prevent UAF in ip6_send_skb() syzbot reported an UAF in ip6_send_skb() [1] After ip6_local_out() has returned, we no longer can safely dereference rt, unless we hold rcu_read_lock(). A similar issue has been fixed in commit a688caa34beb ("ipv6: take rcu lock in rawv6_send_hdrinc()") Another potential issue in ip6_finish_output2() is handled in a separate patch. [1] BUG: KASAN: slab-use-after-free in ip6_send_skb+0x18d/0x230 net/ipv6/ip6_output.c:1964 Read of size 8 at addr ffff88806dde4858 by task syz.1.380/6530 CPU: 1 UID: 0 PID: 6530 Comm: syz.1.380 Not tainted 6.11.0-rc3-syzkaller-00306-gdf6cbc62cc9b #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/06/2024 Call Trace: __dump_stack lib/dump_stack.c:93 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:119 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 ip6_send_skb+0x18d/0x230 net/ipv6/ip6_output.c:1964 rawv6_push_pending_frames+0x75c/0x9e0 net/ipv6/raw.c:588 rawv6_sendmsg+0x19c7/0x23c0 net/ipv6/raw.c:926 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x1a6/0x270 net/socket.c:745 sock_write_iter+0x2dd/0x400 net/socket.c:1160 do_iter_readv_writev+0x60a/0x890 vfs_writev+0x37c/0xbb0 fs/read_write.c:971 do_writev+0x1b1/0x350 fs/read_write.c:1018 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f936bf79e79 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f936cd7f038 EFLAGS: 00000246 ORIG_RAX: 0000000000000014 RAX: ffffffffffffffda RBX: 00007f936c115f80 RCX: 00007f936bf79e79 RDX: 0000000000000001 RSI: 0000000020000040 RDI: 0000000000000004 RBP: 00007f936bfe7916 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00007f936c115f80 R15: 00007fff2860a7a8 Allocated by task 6530: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 unpoison_slab_object mm/kasan/common.c:312 [inline] __kasan_slab_alloc+0x66/0x80 mm/kasan/common.c:338 kasan_slab_alloc include/linux/kasan.h:201 [inline] slab_post_alloc_hook mm/slub.c:3988 [inline] slab_alloc_node mm/slub.c:4037 [inline] kmem_cache_alloc_noprof+0x135/0x2a0 mm/slub.c:4044 dst_alloc+0x12b/0x190 net/core/dst.c:89 ip6_blackhole_route+0x59/0x340 net/ipv6/route.c:2670 make_blackhole net/xfrm/xfrm_policy.c:3120 [inline] xfrm_lookup_route+0xd1/0x1c0 net/xfrm/xfrm_policy.c:3313 ip6_dst_lookup_flow+0x13e/0x180 net/ipv6/ip6_output.c:1257 rawv6_sendmsg+0x1283/0x23c0 net/ipv6/raw.c:898 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x1a6/0x270 net/socket.c:745 ____sys_sendmsg+0x525/0x7d0 net/socket.c:2597 ___sys_sendmsg net/socket.c:2651 [inline] __sys_sendmsg+0x2b0/0x3a0 net/socket.c:2680 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f Freed by task 45: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:579 poison_slab_object+0xe0/0x150 mm/kasan/common.c:240 __kasan_slab_free+0x37/0x60 mm/kasan/common.c:256 kasan_slab_free include/linux/kasan.h:184 [inline] slab_free_hook mm/slub.c:2252 [inline] slab_free mm/slub.c:4473 [inline] kmem_cache_free+0x145/0x350 mm/slub.c:4548 dst_destroy+0x2ac/0x460 net/core/dst.c:124 rcu_do_batch kernel/rcu/tree.c:2569 [inline] rcu_core+0xafd/0x1830 kernel/rcu/tree.c:2843 handle_softirqs+0x2c4/0x970 kernel/softirq.c:554 __do_softirq kernel/softirq.c:588 [inline] invoke_softirq kernel/softirq.c:428 [inline] __irq_exit_rcu+0xf4/0x1c0 kernel/softirq.c:637 irq_exit_rcu+0x9/0x30 kernel/softirq.c:649 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1043 [inline] sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1043 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:702 Last potentially related work creation: kasan_save_stack+0x3f/0x60 mm/kasan/common.c:47 __kasan_record_aux_stack+0xac/0xc0 mm/kasan/generic.c:541 __call_rcu_common kernel/rcu/tree.c:3106 [inline] call_rcu+0x167/0xa70 kernel/rcu/tree.c:3210 refdst_drop include/net/dst.h:263 [inline] skb_dst_drop include/net/dst.h:275 [inline] nf_ct_frag6_queue net/ipv6/netfilter/nf_conntrack_reasm.c:306 [inline] nf_ct_frag6_gather+0xb9a/0x2080 net/ipv6/netfilter/nf_conntrack_reasm.c:485 ipv6_defrag+0x2c8/0x3c0 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:67 nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline] nf_hook_slow+0xc3/0x220 net/netfilter/core.c:626 nf_hook include/linux/netfilter.h:269 [inline] __ip6_local_out+0x6fa/0x800 net/ipv6/output_core.c:143 ip6_local_out+0x26/0x70 net/ipv6/output_core.c:153 ip6_send_skb+0x112/0x230 net/ipv6/ip6_output.c:1959 rawv6_push_pending_frames+0x75c/0x9e0 net/ipv6/raw.c:588 rawv6_sendmsg+0x19c7/0x23c0 net/ipv6/raw.c:926 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x1a6/0x270 net/socket.c:745 sock_write_iter+0x2dd/0x400 net/socket.c:1160 do_iter_readv_writev+0x60a/0x890 Fixes: 0625491493d9 ("ipv6: ip6_push_pending_frames() should increment IPSTATS_MIB_OUTDISCARDS") Signed-off-by: Eric Dumazet Reported-by: syzbot Reviewed-by: David Ahern Link: https://patch.msgid.link/20240820160859.3786976-2-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_output.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ab504d31f0cd..f7b53effc80f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1956,6 +1956,7 @@ int ip6_send_skb(struct sk_buff *skb) struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); int err; + rcu_read_lock(); err = ip6_local_out(net, skb->sk, skb); if (err) { if (err > 0) @@ -1965,6 +1966,7 @@ int ip6_send_skb(struct sk_buff *skb) IPSTATS_MIB_OUTDISCARDS); } + rcu_read_unlock(); return err; } From da273b377ae0d9bd255281ed3c2adb228321687b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Aug 2024 16:08:58 +0000 Subject: [PATCH 496/562] ipv6: fix possible UAF in ip6_finish_output2() If skb_expand_head() returns NULL, skb has been freed and associated dst/idev could also have been freed. We need to hold rcu_read_lock() to make sure the dst and associated idev are alive. Fixes: 5796015fa968 ("ipv6: allocate enough headroom in ip6_finish_output2()") Signed-off-by: Eric Dumazet Cc: Vasily Averin Reviewed-by: David Ahern Link: https://patch.msgid.link/20240820160859.3786976-3-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_output.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index f7b53effc80f..1b9ebee7308f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -70,11 +70,15 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * /* Be paranoid, rather than too clever. */ if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) { + /* Make sure idev stays alive */ + rcu_read_lock(); skb = skb_expand_head(skb, hh_len); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); return -ENOMEM; } + rcu_read_unlock(); } hdr = ipv6_hdr(skb); From 2d5ff7e339d04622d8282661df36151906d0e1c7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Aug 2024 16:08:59 +0000 Subject: [PATCH 497/562] ipv6: prevent possible UAF in ip6_xmit() If skb_expand_head() returns NULL, skb has been freed and the associated dst/idev could also have been freed. We must use rcu_read_lock() to prevent a possible UAF. Fixes: 0c9f227bee11 ("ipv6: use skb_expand_head in ip6_xmit") Signed-off-by: Eric Dumazet Cc: Vasily Averin Reviewed-by: David Ahern Link: https://patch.msgid.link/20240820160859.3786976-4-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_output.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 1b9ebee7308f..f26841f1490f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -287,11 +287,15 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, head_room += opt->opt_nflen + opt->opt_flen; if (unlikely(head_room > skb_headroom(skb))) { + /* Make sure idev stays alive */ + rcu_read_lock(); skb = skb_expand_head(skb, head_room); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); return -ENOBUFS; } + rcu_read_unlock(); } if (opt) { From 8baeef7616d5194045c5a6b97fd1246b87c55b13 Mon Sep 17 00:00:00 2001 From: Somnath Kotur Date: Tue, 20 Aug 2024 13:34:15 -0700 Subject: [PATCH 498/562] bnxt_en: Fix double DMA unmapping for XDP_REDIRECT Remove the dma_unmap_page_attrs() call in the driver's XDP_REDIRECT code path. This should have been removed when we let the page pool handle the DMA mapping. This bug causes the warning: WARNING: CPU: 7 PID: 59 at drivers/iommu/dma-iommu.c:1198 iommu_dma_unmap_page+0xd5/0x100 CPU: 7 PID: 59 Comm: ksoftirqd/7 Tainted: G W 6.8.0-1010-gcp #11-Ubuntu Hardware name: Dell Inc. PowerEdge R7525/0PYVT1, BIOS 2.15.2 04/02/2024 RIP: 0010:iommu_dma_unmap_page+0xd5/0x100 Code: 89 ee 48 89 df e8 cb f2 69 ff 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d 31 c0 31 d2 31 c9 31 f6 31 ff 45 31 c0 e9 ab 17 71 00 <0f> 0b 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d 31 c0 31 d2 31 c9 RSP: 0018:ffffab1fc0597a48 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff99ff838280c8 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffab1fc0597a78 R08: 0000000000000002 R09: ffffab1fc0597c1c R10: ffffab1fc0597cd3 R11: ffff99ffe375acd8 R12: 00000000e65b9000 R13: 0000000000000050 R14: 0000000000001000 R15: 0000000000000002 FS: 0000000000000000(0000) GS:ffff9a06efb80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000565c34c37210 CR3: 00000005c7e3e000 CR4: 0000000000350ef0 ? show_regs+0x6d/0x80 ? __warn+0x89/0x150 ? iommu_dma_unmap_page+0xd5/0x100 ? report_bug+0x16a/0x190 ? handle_bug+0x51/0xa0 ? exc_invalid_op+0x18/0x80 ? iommu_dma_unmap_page+0xd5/0x100 ? iommu_dma_unmap_page+0x35/0x100 dma_unmap_page_attrs+0x55/0x220 ? bpf_prog_4d7e87c0d30db711_xdp_dispatcher+0x64/0x9f bnxt_rx_xdp+0x237/0x520 [bnxt_en] bnxt_rx_pkt+0x640/0xdd0 [bnxt_en] __bnxt_poll_work+0x1a1/0x3d0 [bnxt_en] bnxt_poll+0xaa/0x1e0 [bnxt_en] __napi_poll+0x33/0x1e0 net_rx_action+0x18a/0x2f0 Fixes: 578fcfd26e2a ("bnxt_en: Let the page pool manage the DMA mapping") Reviewed-by: Andy Gospodarek Reviewed-by: Kalesh AP Signed-off-by: Somnath Kotur Signed-off-by: Michael Chan Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20240820203415.168178-1-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 345681d5007e..f88b641533fc 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -297,11 +297,6 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, * redirect is coming from a frame received by the * bnxt_en driver. */ - rx_buf = &rxr->rx_buf_ring[cons]; - mapping = rx_buf->mapping - bp->rx_dma_offset; - dma_unmap_page_attrs(&pdev->dev, mapping, - BNXT_RX_PAGE_SIZE, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); /* if we are unable to allocate a new buffer, abort and reuse */ if (bnxt_alloc_rx_data(bp, rxr, rxr->rx_prod, GFP_ATOMIC)) { From 3f53d050416e88122d53aabbadb1fede998004da Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sun, 18 Aug 2024 12:22:23 -0400 Subject: [PATCH 499/562] bcachefs: bch2_data_update_init() cleanup Factor out some helpers - this function has gotten much too big. Signed-off-by: Kent Overstreet --- fs/bcachefs/data_update.c | 177 +++++++++++++++++++++----------------- 1 file changed, 100 insertions(+), 77 deletions(-) diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 1ca628e93e87..5f49f4953b19 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -20,6 +20,76 @@ #include "subvolume.h" #include "trace.h" +static void bkey_put_dev_refs(struct bch_fs *c, struct bkey_s_c k) +{ + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + + bkey_for_each_ptr(ptrs, ptr) + bch2_dev_put(bch2_dev_have_ref(c, ptr->dev)); +} + +static bool bkey_get_dev_refs(struct bch_fs *c, struct bkey_s_c k) +{ + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + + bkey_for_each_ptr(ptrs, ptr) { + if (!bch2_dev_tryget(c, ptr->dev)) { + bkey_for_each_ptr(ptrs, ptr2) { + if (ptr2 == ptr) + break; + bch2_dev_put(bch2_dev_have_ref(c, ptr2->dev)); + } + return false; + } + } + return true; +} + +static void bkey_nocow_unlock(struct bch_fs *c, struct bkey_s_c k) +{ + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + + bkey_for_each_ptr(ptrs, ptr) { + struct bch_dev *ca = bch2_dev_have_ref(c, ptr->dev); + struct bpos bucket = PTR_BUCKET_POS(ca, ptr); + + bch2_bucket_nocow_unlock(&c->nocow_locks, bucket, 0); + } +} + +static bool bkey_nocow_lock(struct bch_fs *c, struct moving_context *ctxt, struct bkey_s_c k) +{ + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + + bkey_for_each_ptr(ptrs, ptr) { + struct bch_dev *ca = bch2_dev_have_ref(c, ptr->dev); + struct bpos bucket = PTR_BUCKET_POS(ca, ptr); + + if (ctxt) { + bool locked; + + move_ctxt_wait_event(ctxt, + (locked = bch2_bucket_nocow_trylock(&c->nocow_locks, bucket, 0)) || + list_empty(&ctxt->ios)); + + if (!locked) + bch2_bucket_nocow_lock(&c->nocow_locks, bucket, 0); + } else { + if (!bch2_bucket_nocow_trylock(&c->nocow_locks, bucket, 0)) { + bkey_for_each_ptr(ptrs, ptr2) { + if (ptr2 == ptr) + break; + + bucket = PTR_BUCKET_POS(ca, ptr2); + bch2_bucket_nocow_unlock(&c->nocow_locks, bucket, 0); + } + return false; + } + } + } + return true; +} + static void trace_move_extent_finish2(struct bch_fs *c, struct bkey_s_c k) { if (trace_move_extent_finish_enabled()) { @@ -355,17 +425,11 @@ void bch2_data_update_read_done(struct data_update *m, void bch2_data_update_exit(struct data_update *update) { struct bch_fs *c = update->op.c; - struct bkey_ptrs_c ptrs = - bch2_bkey_ptrs_c(bkey_i_to_s_c(update->k.k)); - - bkey_for_each_ptr(ptrs, ptr) { - struct bch_dev *ca = bch2_dev_have_ref(c, ptr->dev); - if (c->opts.nocow_enabled) - bch2_bucket_nocow_unlock(&c->nocow_locks, - PTR_BUCKET_POS(ca, ptr), 0); - bch2_dev_put(ca); - } + struct bkey_s_c k = bkey_i_to_s_c(update->k.k); + if (c->opts.nocow_enabled) + bkey_nocow_unlock(c, k); + bkey_put_dev_refs(c, k); bch2_bkey_buf_exit(&update->k, c); bch2_disk_reservation_put(c, &update->op.res); bch2_bio_free_pages_pool(c, &update->op.wbio.bio); @@ -546,7 +610,6 @@ int bch2_data_update_init(struct btree_trans *trans, const union bch_extent_entry *entry; struct extent_ptr_decoded p; unsigned i, reserve_sectors = k.k->size * data_opts.extra_replicas; - unsigned ptrs_locked = 0; int ret = 0; /* @@ -557,6 +620,15 @@ int bch2_data_update_init(struct btree_trans *trans, if (unlikely(k.k->p.snapshot && !bch2_snapshot_equiv(c, k.k->p.snapshot))) return -BCH_ERR_data_update_done; + if (!bkey_get_dev_refs(c, k)) + return -BCH_ERR_data_update_done; + + if (c->opts.nocow_enabled && + !bkey_nocow_lock(c, ctxt, k)) { + bkey_put_dev_refs(c, k); + return -BCH_ERR_nocow_lock_blocked; + } + bch2_bkey_buf_init(&m->k); bch2_bkey_buf_reassemble(&m->k, c, k); m->btree_id = btree_id; @@ -578,40 +650,24 @@ int bch2_data_update_init(struct btree_trans *trans, m->op.compression_opt = background_compression(io_opts); m->op.watermark = m->data_opts.btree_insert_flags & BCH_WATERMARK_MASK; - bkey_for_each_ptr(ptrs, ptr) { - if (!bch2_dev_tryget(c, ptr->dev)) { - bkey_for_each_ptr(ptrs, ptr2) { - if (ptr2 == ptr) - break; - bch2_dev_put(bch2_dev_have_ref(c, ptr2->dev)); - } - return -BCH_ERR_data_update_done; - } - } - unsigned durability_have = 0, durability_removing = 0; i = 0; bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { - struct bch_dev *ca = bch2_dev_have_ref(c, p.ptr.dev); - struct bpos bucket = PTR_BUCKET_POS(ca, &p.ptr); - bool locked; + if (!p.ptr.cached) { + rcu_read_lock(); + if (BIT(i) & m->data_opts.rewrite_ptrs) { + if (crc_is_compressed(p.crc)) + reserve_sectors += k.k->size; - rcu_read_lock(); - if (((1U << i) & m->data_opts.rewrite_ptrs)) { - BUG_ON(p.ptr.cached); - - if (crc_is_compressed(p.crc)) - reserve_sectors += k.k->size; - - m->op.nr_replicas += bch2_extent_ptr_desired_durability(c, &p); - durability_removing += bch2_extent_ptr_desired_durability(c, &p); - } else if (!p.ptr.cached && - !((1U << i) & m->data_opts.kill_ptrs)) { - bch2_dev_list_add_dev(&m->op.devs_have, p.ptr.dev); - durability_have += bch2_extent_ptr_durability(c, &p); + m->op.nr_replicas += bch2_extent_ptr_desired_durability(c, &p); + durability_removing += bch2_extent_ptr_desired_durability(c, &p); + } else if (!(BIT(i) & m->data_opts.kill_ptrs)) { + bch2_dev_list_add_dev(&m->op.devs_have, p.ptr.dev); + durability_have += bch2_extent_ptr_durability(c, &p); + } + rcu_read_unlock(); } - rcu_read_unlock(); /* * op->csum_type is normally initialized from the fs/file's @@ -626,24 +682,6 @@ int bch2_data_update_init(struct btree_trans *trans, if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible) m->op.incompressible = true; - if (c->opts.nocow_enabled) { - if (ctxt) { - move_ctxt_wait_event(ctxt, - (locked = bch2_bucket_nocow_trylock(&c->nocow_locks, - bucket, 0)) || - list_empty(&ctxt->ios)); - - if (!locked) - bch2_bucket_nocow_lock(&c->nocow_locks, bucket, 0); - } else { - if (!bch2_bucket_nocow_trylock(&c->nocow_locks, bucket, 0)) { - ret = -BCH_ERR_nocow_lock_blocked; - goto err; - } - } - ptrs_locked |= (1U << i); - } - i++; } @@ -664,7 +702,7 @@ int bch2_data_update_init(struct btree_trans *trans, /* if iter == NULL, it's just a promote */ if (iter) ret = bch2_extent_drop_ptrs(trans, iter, k, m->data_opts); - goto done; + goto out; } m->op.nr_replicas = min(durability_removing, durability_required) + @@ -684,8 +722,7 @@ int bch2_data_update_init(struct btree_trans *trans, bch2_data_update_to_text(&buf, m); WARN(1, "trying to move an extent, but nr_replicas=0\n%s", buf.buf); printbuf_exit(&buf); - ret = -BCH_ERR_data_update_done; - goto done; + goto out; } m->op.nr_replicas_required = m->op.nr_replicas; @@ -696,30 +733,16 @@ int bch2_data_update_init(struct btree_trans *trans, ? 0 : BCH_DISK_RESERVATION_NOFAIL); if (ret) - goto err; + goto out; } if (bkey_extent_is_unwritten(k)) { bch2_update_unwritten_extent(trans, m); - goto done; + goto out; } return 0; -err: - i = 0; - bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { - struct bch_dev *ca = bch2_dev_have_ref(c, p.ptr.dev); - struct bpos bucket = PTR_BUCKET_POS(ca, &p.ptr); - if ((1U << i) & ptrs_locked) - bch2_bucket_nocow_unlock(&c->nocow_locks, bucket, 0); - bch2_dev_put(ca); - i++; - } - - bch2_bkey_buf_exit(&m->k, c); - bch2_bio_free_pages_pool(c, &m->op.wbio.bio); - return ret; -done: +out: bch2_data_update_exit(m); return ret ?: -BCH_ERR_data_update_done; } From 8cc0e50614520c6c609c6ae32a65d0591b7865a1 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sun, 18 Aug 2024 13:13:39 -0400 Subject: [PATCH 500/562] bcachefs: Fix "trying to move an extent, but nr_replicas=0" data_update_init() does a bunch of complicated stuff to decide how many replicas to add, since we only want to increase an extent's durability on an explicit rereplicate, but extent pointers may be on devices with different durability settings. There was a corner case when evacuating a device that had been set to durability=0 after data had been written to it, and extents on that device had already been rereplicated - then evacuate only needs to drop pointers on that device, not move them. So the assert for !m->op.nr_replicas was spurious; this was a perfectly legitimate case that needed to be handled. Signed-off-by: Kent Overstreet --- fs/bcachefs/data_update.c | 29 ++++++++++++----------------- 1 file changed, 12 insertions(+), 17 deletions(-) diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 5f49f4953b19..65176d51b502 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -695,16 +695,6 @@ int bch2_data_update_init(struct btree_trans *trans, * Increasing replication is an explicit operation triggered by * rereplicate, currently, so that users don't get an unexpected -ENOSPC */ - if (!(m->data_opts.write_flags & BCH_WRITE_CACHED) && - !durability_required) { - m->data_opts.kill_ptrs |= m->data_opts.rewrite_ptrs; - m->data_opts.rewrite_ptrs = 0; - /* if iter == NULL, it's just a promote */ - if (iter) - ret = bch2_extent_drop_ptrs(trans, iter, k, m->data_opts); - goto out; - } - m->op.nr_replicas = min(durability_removing, durability_required) + m->data_opts.extra_replicas; @@ -716,17 +706,22 @@ int bch2_data_update_init(struct btree_trans *trans, if (!(durability_have + durability_removing)) m->op.nr_replicas = max((unsigned) m->op.nr_replicas, 1); - if (!m->op.nr_replicas) { - struct printbuf buf = PRINTBUF; + m->op.nr_replicas_required = m->op.nr_replicas; - bch2_data_update_to_text(&buf, m); - WARN(1, "trying to move an extent, but nr_replicas=0\n%s", buf.buf); - printbuf_exit(&buf); + /* + * It might turn out that we don't need any new replicas, if the + * replicas or durability settings have been changed since the extent + * was written: + */ + if (!m->op.nr_replicas) { + m->data_opts.kill_ptrs |= m->data_opts.rewrite_ptrs; + m->data_opts.rewrite_ptrs = 0; + /* if iter == NULL, it's just a promote */ + if (iter) + ret = bch2_extent_drop_ptrs(trans, iter, k, m->data_opts); goto out; } - m->op.nr_replicas_required = m->op.nr_replicas; - if (reserve_sectors) { ret = bch2_disk_reservation_add(c, &m->op.res, reserve_sectors, m->data_opts.extra_replicas From 548e7f51679bf0ec3cdc2027d780c5d06a2a7ac6 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sun, 18 Aug 2024 13:24:26 -0400 Subject: [PATCH 501/562] bcachefs: setting bcachefs_effective.* xattrs is a noop bcachefs_effective.* xattrs show the options inherited from parent directories (as well as explicitly set); this namespace is not for setting bcachefs options. Change the .set() handler to a noop so that if e.g. rsync is copying xattrs it'll do the right thing, and only copy xattrs in the bcachefs.* namespace. We don't want to return an error, because that will cause rsync to bail out or get spammy. Signed-off-by: Kent Overstreet --- fs/bcachefs/xattr.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/fs/bcachefs/xattr.c b/fs/bcachefs/xattr.c index f2b4c17a0307..331f944d73dc 100644 --- a/fs/bcachefs/xattr.c +++ b/fs/bcachefs/xattr.c @@ -612,10 +612,20 @@ static int bch2_xattr_bcachefs_get_effective( name, buffer, size, true); } +/* Noop - xattrs in the bcachefs_effective namespace are inherited */ +static int bch2_xattr_bcachefs_set_effective(const struct xattr_handler *handler, + struct mnt_idmap *idmap, + struct dentry *dentry, struct inode *vinode, + const char *name, const void *value, + size_t size, int flags) +{ + return 0; +} + static const struct xattr_handler bch_xattr_bcachefs_effective_handler = { .prefix = "bcachefs_effective.", .get = bch2_xattr_bcachefs_get_effective, - .set = bch2_xattr_bcachefs_set, + .set = bch2_xattr_bcachefs_set_effective, }; #endif /* NO_BCACHEFS_FS */ From 49203a6b9d12bfd1a223a67847a631a78f1cd782 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sun, 18 Aug 2024 15:08:12 -0400 Subject: [PATCH 502/562] bcachefs: Fix failure to relock in btree_node_get() discovered by new trans->locked asserts Signed-off-by: Kent Overstreet --- fs/bcachefs/btree_cache.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index f5d85b50b6f2..cc778d7e769e 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -974,6 +974,10 @@ retry: bch2_btree_node_wait_on_read(b); + ret = bch2_trans_relock(trans); + if (ret) + return ERR_PTR(ret); + /* * should_be_locked is not set on this path yet, so we need to * relock it specifically: From e150a7e89c4727176d07f5a0a8966fc2af05821c Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sun, 18 Aug 2024 20:18:34 -0400 Subject: [PATCH 503/562] bcachefs: Fix bch2_trigger_alloc assert On testing on an old mangled filesystem, we missed a case. Fixes: bd864bc2d907 ("bcachefs: Fix bch2_trigger_alloc when upgrading from old versions") Signed-off-by: Kent Overstreet --- fs/bcachefs/alloc_background.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index fd3a2522bc3e..488d0710f7b9 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -829,7 +829,7 @@ int bch2_trigger_alloc(struct btree_trans *trans, if (likely(new.k->type == KEY_TYPE_alloc_v4)) { new_a = bkey_s_to_alloc_v4(new).v; } else { - BUG_ON(!(flags & BTREE_TRIGGER_gc)); + BUG_ON(!(flags & (BTREE_TRIGGER_gc|BTREE_TRIGGER_check_repair))); struct bkey_i_alloc_v4 *new_ka = bch2_alloc_to_v4_mut_inlined(trans, new.s_c); ret = PTR_ERR_OR_ZERO(new_ka); From c2a503f3e98e191d86738f5438a3a2b69575c830 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sun, 18 Aug 2024 20:38:49 -0400 Subject: [PATCH 504/562] bcachefs: Fix bch2_bucket_gens_init() Comparing the wrong bpos - this was missed because normally bucket_gens_init() runs on brand new filesystems, but this bug caused it to overwrite bucket_gens keys with 0s when upgrading ancient filesystems. Signed-off-by: Kent Overstreet --- fs/bcachefs/alloc_background.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index 488d0710f7b9..ac933142aeda 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -556,7 +556,7 @@ int bch2_bucket_gens_init(struct bch_fs *c) struct bpos pos = alloc_gens_pos(iter.pos, &offset); int ret2 = 0; - if (have_bucket_gens_key && bkey_cmp(iter.pos, pos)) { + if (have_bucket_gens_key && !bkey_eq(g.k.p, pos)) { ret2 = bch2_btree_insert_trans(trans, BTREE_ID_bucket_gens, &g.k_i, 0) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); if (ret2) From b8db1bd8020d5fecb3bf46cd8b954a657c20ba14 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 19 Aug 2024 16:13:16 -0400 Subject: [PATCH 505/562] bcachefs: fix time_stats_to_text() Fixes: 7423330e30ab ("bcachefs: prt_printf() now respects \r\n\t") Signed-off-by: Kent Overstreet --- fs/bcachefs/util.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c index 138320eaa2ad..1b8554460af4 100644 --- a/fs/bcachefs/util.c +++ b/fs/bcachefs/util.c @@ -416,7 +416,6 @@ void bch2_time_stats_to_text(struct printbuf *out, struct bch2_time_stats *stats printbuf_tabstop_push(out, TABSTOP_SIZE + 2); prt_printf(out, "\tsince mount\r\trecent\r\n"); - prt_printf(out, "recent"); printbuf_tabstops_reset(out); printbuf_tabstop_push(out, out->indent + 20); From cecc328240609df17395dfd0ea03cc813d8be36d Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 20 Aug 2024 11:25:39 -0400 Subject: [PATCH 506/562] bcachefs: fix missing bch2_err_str() Signed-off-by: Kent Overstreet --- fs/bcachefs/fsck.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 9138944c5ae6..267c2336b115 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -2469,8 +2469,7 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino : bch2_inode_unpack(inode_k, &inode); if (ret) { /* Should have been caught in dirents pass */ - if (!bch2_err_matches(ret, BCH_ERR_transaction_restart)) - bch_err(c, "error looking up parent directory: %i", ret); + bch_err_msg(c, ret, "error looking up parent directory"); break; } From 1dceae4cc12aa6389d9a8706f0d2a94d1679e79d Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 20 Aug 2024 12:10:33 -0400 Subject: [PATCH 507/562] bcachefs: unlock_long() before resort in journal replay Fix another SRCU splat - this one pretty harmless. Signed-off-by: Kent Overstreet --- fs/bcachefs/recovery.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index d89eb43c5ce9..11368dfa96b2 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -322,6 +322,7 @@ int bch2_journal_replay(struct bch_fs *c) } } + bch2_trans_unlock_long(trans); /* * Now, replay any remaining keys in the order in which they appear in * the journal, unpinning those journal entries as we go: From 3c5d0b72a8e8c19c960e8fefb7463067e58b6bc4 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 19 Aug 2024 15:22:55 -0400 Subject: [PATCH 508/562] bcachefs: fix failure to relock in bch2_btree_node_mem_alloc() We weren't always so strict about trans->locked state - but now we are, and new assertions are shaking some bugs out. Signed-off-by: Kent Overstreet --- fs/bcachefs/btree_cache.c | 17 +++++++++++ fs/bcachefs/btree_cache.h | 2 ++ fs/bcachefs/btree_update_interior.c | 46 ++++++++++++++++------------- 3 files changed, 44 insertions(+), 21 deletions(-) diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index cc778d7e769e..063725ecb2b3 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -159,6 +159,16 @@ struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *c) return b; } +void bch2_btree_node_to_freelist(struct bch_fs *c, struct btree *b) +{ + mutex_lock(&c->btree_cache.lock); + list_move(&b->list, &c->btree_cache.freeable); + mutex_unlock(&c->btree_cache.lock); + + six_unlock_write(&b->c.lock); + six_unlock_intent(&b->c.lock); +} + /* Btree in memory cache - hash table */ void bch2_btree_node_hash_remove(struct btree_cache *bc, struct btree *b) @@ -736,6 +746,13 @@ out: start_time); memalloc_nofs_restore(flags); + + int ret = bch2_trans_relock(trans); + if (unlikely(ret)) { + bch2_btree_node_to_freelist(c, b); + return ERR_PTR(ret); + } + return b; err: mutex_lock(&bc->lock); diff --git a/fs/bcachefs/btree_cache.h b/fs/bcachefs/btree_cache.h index c0eb87a057cc..f82064007127 100644 --- a/fs/bcachefs/btree_cache.h +++ b/fs/bcachefs/btree_cache.h @@ -12,6 +12,8 @@ struct btree_iter; void bch2_recalc_btree_reserve(struct bch_fs *); +void bch2_btree_node_to_freelist(struct bch_fs *, struct btree *); + void bch2_btree_node_hash_remove(struct btree_cache *, struct btree *); int __bch2_btree_node_hash_insert(struct btree_cache *, struct btree *); int bch2_btree_node_hash_insert(struct btree_cache *, struct btree *, diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index b3454d4619e8..8fd112026e7a 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -317,6 +317,12 @@ static struct btree *__bch2_btree_node_alloc(struct btree_trans *trans, : 0; int ret; + b = bch2_btree_node_mem_alloc(trans, interior_node); + if (IS_ERR(b)) + return b; + + BUG_ON(b->ob.nr); + mutex_lock(&c->btree_reserve_cache_lock); if (c->btree_reserve_cache_nr > nr_reserve) { struct btree_alloc *a = @@ -325,10 +331,9 @@ static struct btree *__bch2_btree_node_alloc(struct btree_trans *trans, obs = a->ob; bkey_copy(&tmp.k, &a->k); mutex_unlock(&c->btree_reserve_cache_lock); - goto mem_alloc; + goto out; } mutex_unlock(&c->btree_reserve_cache_lock); - retry: ret = bch2_alloc_sectors_start_trans(trans, c->opts.metadata_target ?: @@ -341,7 +346,7 @@ retry: c->opts.metadata_replicas_required), watermark, 0, cl, &wp); if (unlikely(ret)) - return ERR_PTR(ret); + goto err; if (wp->sectors_free < btree_sectors(c)) { struct open_bucket *ob; @@ -360,19 +365,16 @@ retry: bch2_open_bucket_get(c, wp, &obs); bch2_alloc_sectors_done(c, wp); -mem_alloc: - b = bch2_btree_node_mem_alloc(trans, interior_node); +out: + bkey_copy(&b->key, &tmp.k); + b->ob = obs; six_unlock_write(&b->c.lock); six_unlock_intent(&b->c.lock); - /* we hold cannibalize_lock: */ - BUG_ON(IS_ERR(b)); - BUG_ON(b->ob.nr); - - bkey_copy(&b->key, &tmp.k); - b->ob = obs; - return b; +err: + bch2_btree_node_to_freelist(c, b); + return ERR_PTR(ret); } static struct btree *bch2_btree_node_alloc(struct btree_update *as, @@ -2439,6 +2441,9 @@ int bch2_btree_node_update_key(struct btree_trans *trans, struct btree_iter *ite } new_hash = bch2_btree_node_mem_alloc(trans, false); + ret = PTR_ERR_OR_ZERO(new_hash); + if (ret) + goto err; } path->intent_ref++; @@ -2446,14 +2451,9 @@ int bch2_btree_node_update_key(struct btree_trans *trans, struct btree_iter *ite commit_flags, skip_triggers); --path->intent_ref; - if (new_hash) { - mutex_lock(&c->btree_cache.lock); - list_move(&new_hash->list, &c->btree_cache.freeable); - mutex_unlock(&c->btree_cache.lock); - - six_unlock_write(&new_hash->c.lock); - six_unlock_intent(&new_hash->c.lock); - } + if (new_hash) + bch2_btree_node_to_freelist(c, new_hash); +err: closure_sync(&cl); bch2_btree_cache_cannibalize_unlock(trans); return ret; @@ -2522,6 +2522,10 @@ int bch2_btree_root_alloc_fake_trans(struct btree_trans *trans, enum btree_id id b = bch2_btree_node_mem_alloc(trans, false); bch2_btree_cache_cannibalize_unlock(trans); + ret = PTR_ERR_OR_ZERO(b); + if (ret) + return ret; + set_btree_node_fake(b); set_btree_node_need_rewrite(b); b->c.level = level; @@ -2553,7 +2557,7 @@ int bch2_btree_root_alloc_fake_trans(struct btree_trans *trans, enum btree_id id void bch2_btree_root_alloc_fake(struct bch_fs *c, enum btree_id id, unsigned level) { - bch2_trans_run(c, bch2_btree_root_alloc_fake_trans(trans, id, level)); + bch2_trans_run(c, lockrestart_do(trans, bch2_btree_root_alloc_fake_trans(trans, id, level))); } static void bch2_btree_update_to_text(struct printbuf *out, struct btree_update *as) From 5dbfc4ef72f15508882aff58c307b8425cf037a8 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 20 Aug 2024 15:04:15 -0400 Subject: [PATCH 509/562] bcachefs: fix failure to relock in btree_node_fill() Signed-off-by: Kent Overstreet --- fs/bcachefs/btree_cache.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index 063725ecb2b3..e52a06d3418c 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -873,6 +873,10 @@ static noinline struct btree *bch2_btree_node_fill(struct btree_trans *trans, bch2_btree_node_read(trans, b, sync); + int ret = bch2_trans_relock(trans); + if (ret) + return ERR_PTR(ret); + if (!sync) return NULL; From 6575b8c9877c3dd1f7db1d0d61bd250a0bf18b6d Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 20 Aug 2024 19:31:20 -0400 Subject: [PATCH 510/562] bcachefs: Fix locking in bch2_ioc_setlabel() Fixes: 7a254053a590 ("bcachefs: support FS_IOC_SETFSLABEL") Reported-by: syzbot+7e9efdfec27fbde0141d@syzkaller.appspotmail.com Signed-off-by: Kent Overstreet --- fs/bcachefs/fs-ioctl.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c index aea8132d2c40..99c7fe987c74 100644 --- a/fs/bcachefs/fs-ioctl.c +++ b/fs/bcachefs/fs-ioctl.c @@ -328,9 +328,8 @@ static int bch2_ioc_setlabel(struct bch_fs *c, mutex_lock(&c->sb_lock); strscpy(c->disk_sb.sb->label, label, BCH_SB_LABEL_SIZE); - mutex_unlock(&c->sb_lock); - ret = bch2_write_super(c); + mutex_unlock(&c->sb_lock); mnt_drop_write_file(file); return ret; From cab18be6957b6af8cbe3502fd5f6d7b9f02ccceb Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 21 Aug 2024 20:49:07 -0400 Subject: [PATCH 511/562] bcachefs: Fix replay_now_at() assert Journal replay, in the slowpath where we insert keys in journal order, was inserting keys in the wrong order; keys from early repair come last. Reported-by: syzbot+2c4fcb257ce2b6a29d0e@syzkaller.appspotmail.com Signed-off-by: Kent Overstreet --- fs/bcachefs/recovery.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index 11368dfa96b2..36de1c6fe8c3 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -241,7 +241,13 @@ static int journal_sort_seq_cmp(const void *_l, const void *_r) const struct journal_key *l = *((const struct journal_key **)_l); const struct journal_key *r = *((const struct journal_key **)_r); - return cmp_int(l->journal_seq, r->journal_seq); + /* + * Map 0 to U64_MAX, so that keys with journal_seq === 0 come last + * + * journal_seq == 0 means that the key comes from early repair, and + * should be inserted last so as to avoid overflowing the journal + */ + return cmp_int(l->journal_seq - 1, r->journal_seq - 1); } int bch2_journal_replay(struct bch_fs *c) From bdbdd4759f081ca2d0a5d9e8af21d742ffaf8439 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 21 Aug 2024 21:10:45 -0400 Subject: [PATCH 512/562] bcachefs: Fix missing validation in bch2_sb_journal_v2_validate() Reported-by: syzbot+47ecc948aadfb2ab3efc@syzkaller.appspotmail.com Signed-off-by: Kent Overstreet --- fs/bcachefs/journal_sb.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/fs/bcachefs/journal_sb.c b/fs/bcachefs/journal_sb.c index db80e506e3ab..62b910f2fb27 100644 --- a/fs/bcachefs/journal_sb.c +++ b/fs/bcachefs/journal_sb.c @@ -104,6 +104,7 @@ static int bch2_sb_journal_v2_validate(struct bch_sb *sb, struct bch_sb_field *f struct bch_sb_field_journal_v2 *journal = field_to_type(f, journal_v2); struct bch_member m = bch2_sb_member_get(sb, sb->dev_idx); int ret = -BCH_ERR_invalid_sb_journal; + u64 sum = 0; unsigned nr; unsigned i; struct u64_range *b; @@ -119,6 +120,15 @@ static int bch2_sb_journal_v2_validate(struct bch_sb *sb, struct bch_sb_field *f for (i = 0; i < nr; i++) { b[i].start = le64_to_cpu(journal->d[i].start); b[i].end = b[i].start + le64_to_cpu(journal->d[i].nr); + + if (b[i].end <= b[i].start) { + prt_printf(err, "journal buckets entry with bad nr: %llu+%llu", + le64_to_cpu(journal->d[i].start), + le64_to_cpu(journal->d[i].nr)); + goto err; + } + + sum += le64_to_cpu(journal->d[i].nr); } sort(b, nr, sizeof(*b), u64_range_cmp, NULL); @@ -148,6 +158,11 @@ static int bch2_sb_journal_v2_validate(struct bch_sb *sb, struct bch_sb_field *f } } + if (sum > UINT_MAX) { + prt_printf(err, "too many journal buckets: %llu > %u", sum, UINT_MAX); + goto err; + } + ret = 0; err: kfree(b); From 06f67437ab356e3140f51aea272d33ce28421f66 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 21 Aug 2024 22:06:44 -0400 Subject: [PATCH 513/562] fs/super.c: improve get_tree() error message seeing an odd bug where we fail to correctly return an error from .get_tree(): https://syzkaller.appspot.com/bug?extid=c0360e8367d6d8d04a66 we need to be able to distinguish between accidently returning a positive error (as implied by the log) and no error. Cc: David Howells Signed-off-by: Kent Overstreet --- fs/super.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/super.c b/fs/super.c index 38d72a3cf6fc..b7913b55debc 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1802,8 +1802,8 @@ int vfs_get_tree(struct fs_context *fc) return error; if (!fc->root) { - pr_err("Filesystem %s get_tree() didn't set fc->root\n", - fc->fs_type->name); + pr_err("Filesystem %s get_tree() didn't set fc->root, returned %i\n", + fc->fs_type->name, error); /* We don't know what the locking state of the superblock is - * if there is a superblock. */ From 7f2de6947f92cfa4be8e5eaa1237e962bb8ee65f Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 21 Aug 2024 22:27:45 -0400 Subject: [PATCH 514/562] bcachefs: Fix warning in bch2_fs_journal_stop() j->last_empty_seq needs to match j->seq when the journal is empty Reported-by: syzbot+4093905737cf289b6b38@syzkaller.appspotmail.com Signed-off-by: Kent Overstreet --- fs/bcachefs/journal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c index 649e3a01608a..f5f7db50ca31 100644 --- a/fs/bcachefs/journal.c +++ b/fs/bcachefs/journal.c @@ -1260,7 +1260,7 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq) } if (!had_entries) - j->last_empty_seq = cur_seq; + j->last_empty_seq = cur_seq - 1; /* to match j->seq */ spin_lock(&j->lock); From 8ed823b19214e403ca485532f48c0e02035021ae Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 21 Aug 2024 22:57:56 -0400 Subject: [PATCH 515/562] bcachefs: Fix compat issue with old alloc_v4 keys we allow new fields to be added to existing key types, and new versions should treat them as being zeroed; this was not handled in alloc_v4_validate. Reported-by: syzbot+3b2968fa4953885dd66a@syzkaller.appspotmail.com Signed-off-by: Kent Overstreet --- fs/bcachefs/alloc_background.c | 50 ++++++++++++++------------- fs/bcachefs/alloc_background_format.h | 1 + fs/bcachefs/btree_iter.h | 9 +++++ 3 files changed, 36 insertions(+), 24 deletions(-) diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index ac933142aeda..dc97b1f8bc08 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -240,71 +240,73 @@ fsck_err: int bch2_alloc_v4_validate(struct bch_fs *c, struct bkey_s_c k, enum bch_validate_flags flags) { - struct bkey_s_c_alloc_v4 a = bkey_s_c_to_alloc_v4(k); + struct bch_alloc_v4 a; int ret = 0; - bkey_fsck_err_on(alloc_v4_u64s_noerror(a.v) > bkey_val_u64s(k.k), + bkey_val_copy(&a, bkey_s_c_to_alloc_v4(k)); + + bkey_fsck_err_on(alloc_v4_u64s_noerror(&a) > bkey_val_u64s(k.k), c, alloc_v4_val_size_bad, "bad val size (%u > %zu)", - alloc_v4_u64s_noerror(a.v), bkey_val_u64s(k.k)); + alloc_v4_u64s_noerror(&a), bkey_val_u64s(k.k)); - bkey_fsck_err_on(!BCH_ALLOC_V4_BACKPOINTERS_START(a.v) && - BCH_ALLOC_V4_NR_BACKPOINTERS(a.v), + bkey_fsck_err_on(!BCH_ALLOC_V4_BACKPOINTERS_START(&a) && + BCH_ALLOC_V4_NR_BACKPOINTERS(&a), c, alloc_v4_backpointers_start_bad, "invalid backpointers_start"); - bkey_fsck_err_on(alloc_data_type(*a.v, a.v->data_type) != a.v->data_type, + bkey_fsck_err_on(alloc_data_type(a, a.data_type) != a.data_type, c, alloc_key_data_type_bad, "invalid data type (got %u should be %u)", - a.v->data_type, alloc_data_type(*a.v, a.v->data_type)); + a.data_type, alloc_data_type(a, a.data_type)); for (unsigned i = 0; i < 2; i++) - bkey_fsck_err_on(a.v->io_time[i] > LRU_TIME_MAX, + bkey_fsck_err_on(a.io_time[i] > LRU_TIME_MAX, c, alloc_key_io_time_bad, "invalid io_time[%s]: %llu, max %llu", i == READ ? "read" : "write", - a.v->io_time[i], LRU_TIME_MAX); + a.io_time[i], LRU_TIME_MAX); - unsigned stripe_sectors = BCH_ALLOC_V4_BACKPOINTERS_START(a.v) * sizeof(u64) > + unsigned stripe_sectors = BCH_ALLOC_V4_BACKPOINTERS_START(&a) * sizeof(u64) > offsetof(struct bch_alloc_v4, stripe_sectors) - ? a.v->stripe_sectors + ? a.stripe_sectors : 0; - switch (a.v->data_type) { + switch (a.data_type) { case BCH_DATA_free: case BCH_DATA_need_gc_gens: case BCH_DATA_need_discard: bkey_fsck_err_on(stripe_sectors || - a.v->dirty_sectors || - a.v->cached_sectors || - a.v->stripe, + a.dirty_sectors || + a.cached_sectors || + a.stripe, c, alloc_key_empty_but_have_data, "empty data type free but have data %u.%u.%u %u", stripe_sectors, - a.v->dirty_sectors, - a.v->cached_sectors, - a.v->stripe); + a.dirty_sectors, + a.cached_sectors, + a.stripe); break; case BCH_DATA_sb: case BCH_DATA_journal: case BCH_DATA_btree: case BCH_DATA_user: case BCH_DATA_parity: - bkey_fsck_err_on(!a.v->dirty_sectors && + bkey_fsck_err_on(!a.dirty_sectors && !stripe_sectors, c, alloc_key_dirty_sectors_0, "data_type %s but dirty_sectors==0", - bch2_data_type_str(a.v->data_type)); + bch2_data_type_str(a.data_type)); break; case BCH_DATA_cached: - bkey_fsck_err_on(!a.v->cached_sectors || - a.v->dirty_sectors || + bkey_fsck_err_on(!a.cached_sectors || + a.dirty_sectors || stripe_sectors || - a.v->stripe, + a.stripe, c, alloc_key_cached_inconsistency, "data type inconsistency"); - bkey_fsck_err_on(!a.v->io_time[READ] && + bkey_fsck_err_on(!a.io_time[READ] && c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_to_lru_refs, c, alloc_key_cached_but_read_time_zero, "cached bucket with read_time == 0"); diff --git a/fs/bcachefs/alloc_background_format.h b/fs/bcachefs/alloc_background_format.h index 47d9d006502c..f754a2951d8a 100644 --- a/fs/bcachefs/alloc_background_format.h +++ b/fs/bcachefs/alloc_background_format.h @@ -69,6 +69,7 @@ struct bch_alloc_v4 { __u64 io_time[2]; __u32 stripe; __u32 nr_external_backpointers; + /* end of fields in original version of alloc_v4 */ __u64 fragmentation_lru; __u32 stripe_sectors; __u32 pad; diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h index dca62375d7d3..222b7ce8a901 100644 --- a/fs/bcachefs/btree_iter.h +++ b/fs/bcachefs/btree_iter.h @@ -569,6 +569,15 @@ static inline struct bkey_s_c bch2_bkey_get_iter(struct btree_trans *trans, bkey_s_c_to_##_type(__bch2_bkey_get_iter(_trans, _iter, \ _btree_id, _pos, _flags, KEY_TYPE_##_type)) +#define bkey_val_copy(_dst_v, _src_k) \ +do { \ + unsigned b = min_t(unsigned, sizeof(*_dst_v), \ + bkey_val_bytes(_src_k.k)); \ + memcpy(_dst_v, _src_k.v, b); \ + if (b < sizeof(*_dst_v)) \ + memset((void *) (_dst_v) + b, 0, sizeof(*_dst_v) - b); \ +} while (0) + static inline int __bch2_bkey_get_val_typed(struct btree_trans *trans, unsigned btree_id, struct bpos pos, unsigned flags, unsigned type, From 0b50b7313ef2494926df30ce8e2ce284f1b847fc Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 21 Aug 2024 23:21:52 -0400 Subject: [PATCH 516/562] bcachefs: Fix refcounting in discard path bch_dev->io_ref does not protect against the filesystem going away; bch_fs->writes does. Thus the filesystem write ref needs to be the last ref we release. Reported-by: syzbot+9e0404b505e604f67e41@syzkaller.appspotmail.com Signed-off-by: Kent Overstreet --- fs/bcachefs/alloc_background.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index dc97b1f8bc08..ba46f1c1d78a 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -1874,26 +1874,26 @@ static void bch2_do_discards_work(struct work_struct *work) trace_discard_buckets(c, s.seen, s.open, s.need_journal_commit, s.discarded, bch2_err_str(ret)); - bch2_write_ref_put(c, BCH_WRITE_REF_discard); percpu_ref_put(&ca->io_ref); + bch2_write_ref_put(c, BCH_WRITE_REF_discard); } void bch2_dev_do_discards(struct bch_dev *ca) { struct bch_fs *c = ca->fs; - if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE)) + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_discard)) return; - if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_discard)) - goto put_ioref; + if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE)) + goto put_write_ref; if (queue_work(c->write_ref_wq, &ca->discard_work)) return; - bch2_write_ref_put(c, BCH_WRITE_REF_discard); -put_ioref: percpu_ref_put(&ca->io_ref); +put_write_ref: + bch2_write_ref_put(c, BCH_WRITE_REF_discard); } void bch2_do_discards(struct bch_fs *c) From dedb2fe37574857c84e9598b9f5272505dedf7af Mon Sep 17 00:00:00 2001 From: Yuesong Li Date: Thu, 22 Aug 2024 14:21:58 +0800 Subject: [PATCH 517/562] bcachefs: Fix double assignment in check_dirent_to_subvol() ret was assigned twice in check_dirent_to_subvol(). Reported by cocci. Signed-off-by: Yuesong Li Signed-off-by: Kent Overstreet --- fs/bcachefs/fsck.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 267c2336b115..6801c37ee803 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -2006,7 +2006,6 @@ static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter * if (ret) { bch_err(c, "subvol %u points to missing inode root %llu", target_subvol, target_inum); ret = -BCH_ERR_fsck_repair_unimplemented; - ret = 0; goto err; } From 87313ac1f134d6ee1e7c858da8bdea9147b537a9 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Thu, 22 Aug 2024 02:13:02 -0400 Subject: [PATCH 518/562] bcachefs: clear path->should_be_locked in bch2_btree_key_cache_drop() bch2_btree_key_cache_drop() evicts the key cache entry - it's used when we're doing an update that bypasses the key cache, because for cache coherency reasons a key can't be in the key cache unless it also exists in the btree - i.e. creates have to bypass the cache. After evicting, the path no longer points to a key cache key, and relock() will always fail if should_be_locked is true. Prep for improving path->should_be_locked assertions Signed-off-by: Kent Overstreet --- fs/bcachefs/btree_key_cache.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 79954490627c..9b3ec2a3b8ce 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -726,6 +726,7 @@ void bch2_btree_key_cache_drop(struct btree_trans *trans, mark_btree_node_locked(trans, path, 0, BTREE_NODE_UNLOCKED); btree_path_set_dirty(path, BTREE_ITER_NEED_TRAVERSE); + path->should_be_locked = false; } static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, From 1d8c3c23a6bc1527e253b305b4b68c03d833b824 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Thu, 22 Aug 2024 07:17:09 +0000 Subject: [PATCH 519/562] KVM: arm64: Ensure canonical IPA is hugepage-aligned when handling fault Zenghui reports that VMs backed by hugetlb pages are no longer booting after commit fd276e71d1e7 ("KVM: arm64: nv: Handle shadow stage 2 page faults"). Support for shadow stage-2 MMUs introduced the concept of a fault IPA and canonical IPA to stage-2 fault handling. These are identical in the non-nested case, as the hardware stage-2 context is always that of the canonical IPA space. Both addresses need to be hugepage-aligned when preparing to install a hugepage mapping to ensure that KVM uses the correct GFN->PFN translation and installs that at the correct IPA for the current stage-2. And now I'm feeling thirsty after all this talk of IPAs... Fixes: fd276e71d1e7 ("KVM: arm64: nv: Handle shadow stage 2 page faults") Reported-by: Zenghui Yu Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20240822071710.2291690-1-oliver.upton@linux.dev Signed-off-by: Oliver Upton --- arch/arm64/kvm/mmu.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 6981b1bc0946..a509b63bd4dd 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1540,8 +1540,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, vma_pagesize = min(vma_pagesize, (long)max_map_size); } - if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) + /* + * Both the canonical IPA and fault IPA must be hugepage-aligned to + * ensure we find the right PFN and lay down the mapping in the right + * place. + */ + if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) { fault_ipa &= ~(vma_pagesize - 1); + ipa &= ~(vma_pagesize - 1); + } gfn = ipa >> PAGE_SHIFT; mte_allowed = kvm_vma_mte_allowed(vma); From 3e6245ebe7ef341639e9a7e402b3ade8ad45a19f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 20 Aug 2024 11:03:38 +0100 Subject: [PATCH 520/562] KVM: arm64: Make ICC_*SGI*_EL1 undef in the absence of a vGICv3 On a system with a GICv3, if a guest hasn't been configured with GICv3 and that the host is not capable of GICv2 emulation, a write to any of the ICC_*SGI*_EL1 registers is trapped to EL2. We therefore try to emulate the SGI access, only to hit a NULL pointer as no private interrupt is allocated (no GIC, remember?). The obvious fix is to give the guest what it deserves, in the shape of a UNDEF exception. Reported-by: Alexander Potapenko Signed-off-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240820100349.3544850-2-maz@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/kvm/sys_regs.c | 6 ++++++ arch/arm64/kvm/vgic/vgic.h | 7 +++++++ 2 files changed, 13 insertions(+) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index c90324060436..31e49da867ff 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -33,6 +33,7 @@ #include #include "sys_regs.h" +#include "vgic/vgic.h" #include "trace.h" @@ -435,6 +436,11 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu, { bool g1; + if (!kvm_has_gicv3(vcpu->kvm)) { + kvm_inject_undefined(vcpu); + return false; + } + if (!p->is_write) return read_from_write_only(vcpu, p, r); diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index ba8f790431bd..8532bfe3fed4 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -346,4 +346,11 @@ void vgic_v4_configure_vsgis(struct kvm *kvm); void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val); int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq); +static inline bool kvm_has_gicv3(struct kvm *kvm) +{ + return (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) && + irqchip_in_kernel(kvm) && + kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3); +} + #endif From 6ea14ccb60c8ab829349979b22b58a941ec4a3ee Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 13 Aug 2024 12:39:46 +0200 Subject: [PATCH 521/562] netfilter: flowtable: validate vlan header Ensure there is sufficient room to access the protocol field of the VLAN header, validate it once before the flowtable lookup. ===================================================== BUG: KMSAN: uninit-value in nf_flow_offload_inet_hook+0x45a/0x5f0 net/netfilter/nf_flow_table_inet.c:32 nf_flow_offload_inet_hook+0x45a/0x5f0 net/netfilter/nf_flow_table_inet.c:32 nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline] nf_hook_slow+0xf4/0x400 net/netfilter/core.c:626 nf_hook_ingress include/linux/netfilter_netdev.h:34 [inline] nf_ingress net/core/dev.c:5440 [inline] Fixes: 4cd91f7c290f ("netfilter: flowtable: add vlan support") Reported-by: syzbot+8407d9bb88cd4c6bf61a@syzkaller.appspotmail.com Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_flow_table_inet.c | 3 +++ net/netfilter/nf_flow_table_ip.c | 3 +++ 2 files changed, 6 insertions(+) diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 88787b45e30d..8b541a080342 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -17,6 +17,9 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, switch (skb->protocol) { case htons(ETH_P_8021Q): + if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth))) + return NF_ACCEPT; + veth = (struct vlan_ethhdr *)skb_mac_header(skb); proto = veth->h_vlan_encapsulated_proto; break; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index c2c005234dcd..98edcaa37b38 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -281,6 +281,9 @@ static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto, switch (skb->protocol) { case htons(ETH_P_8021Q): + if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth))) + return false; + veth = (struct vlan_ethhdr *)skb_mac_header(skb); if (veth->h_vlan_encapsulated_proto == proto) { *offset += VLAN_HLEN; From f2916c83d746eb99f50f42c15cf4c47c2ea5f3b3 Mon Sep 17 00:00:00 2001 From: Mengyuan Lou Date: Tue, 20 Aug 2024 11:04:25 +0800 Subject: [PATCH 522/562] net: ngbe: Fix phy mode set to external phy The MAC only has add the TX delay and it can not be modified. MAC and PHY are both set the TX delay cause transmission problems. So just disable TX delay in PHY, when use rgmii to attach to external phy, set PHY_INTERFACE_MODE_RGMII_RXID to phy drivers. And it is does not matter to internal phy. Fixes: bc2426d74aa3 ("net: ngbe: convert phylib to phylink") Signed-off-by: Mengyuan Lou Cc: stable@vger.kernel.org # 6.3+ Reviewed-by: Jacob Keller Link: https://patch.msgid.link/E6759CF1387CF84C+20240820030425.93003-1-mengyuanlou@net-swift.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c index ec54b18c5fe7..a5e9b779c44d 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c @@ -124,8 +124,12 @@ static int ngbe_phylink_init(struct wx *wx) MAC_SYM_PAUSE | MAC_ASYM_PAUSE; config->mac_managed_pm = true; - phy_mode = PHY_INTERFACE_MODE_RGMII_ID; - __set_bit(PHY_INTERFACE_MODE_RGMII_ID, config->supported_interfaces); + /* The MAC only has add the Tx delay and it can not be modified. + * So just disable TX delay in PHY, and it is does not matter to + * internal phy. + */ + phy_mode = PHY_INTERFACE_MODE_RGMII_RXID; + __set_bit(PHY_INTERFACE_MODE_RGMII_RXID, config->supported_interfaces); phylink = phylink_create(config, NULL, phy_mode, &ngbe_mac_ops); if (IS_ERR(phylink)) From a2f5c505b4378cd6fc7c4a44ff3665ccef2037db Mon Sep 17 00:00:00 2001 From: Sava Jakovljev Date: Wed, 21 Aug 2024 04:16:57 +0200 Subject: [PATCH 523/562] net: phy: realtek: Fix setting of PHY LEDs Mode B bit on RTL8211F The current implementation incorrectly sets the mode bit of the PHY chip. Bit 15 (RTL8211F_LEDCR_MODE) should not be shifted together with the configuration nibble of a LED- it should be set independently of the index of the LED being configured. As a consequence, the RTL8211F LED control is actually operating in Mode A. Fix the error by or-ing final register value to write with a const-value of RTL8211F_LEDCR_MODE, thus setting Mode bit explicitly. Fixes: 17784801d888 ("net: phy: realtek: Add support for PHY LEDs on RTL8211F") Signed-off-by: Sava Jakovljev Reviewed-by: Marek Vasut Link: https://patch.msgid.link/PAWP192MB21287372F30C4E55B6DF6158C38E2@PAWP192MB2128.EURP192.PROD.OUTLOOK.COM Signed-off-by: Paolo Abeni --- drivers/net/phy/realtek.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 87865918dab6..25e5bfbb6f89 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -555,7 +555,7 @@ static int rtl8211f_led_hw_control_set(struct phy_device *phydev, u8 index, unsigned long rules) { const u16 mask = RTL8211F_LEDCR_MASK << (RTL8211F_LEDCR_SHIFT * index); - u16 reg = RTL8211F_LEDCR_MODE; /* Mode B */ + u16 reg = 0; if (index >= RTL8211F_LED_COUNT) return -EINVAL; @@ -575,6 +575,7 @@ static int rtl8211f_led_hw_control_set(struct phy_device *phydev, u8 index, } reg <<= RTL8211F_LEDCR_SHIFT * index; + reg |= RTL8211F_LEDCR_MODE; /* Mode B */ return phy_modify_paged(phydev, 0xd04, RTL8211F_LEDCR, mask, reg); } From af688a99eb1fc7ef69774665d61e6be51cea627a Mon Sep 17 00:00:00 2001 From: Bharat Bhushan Date: Wed, 21 Aug 2024 12:35:58 +0530 Subject: [PATCH 524/562] octeontx2-af: Fix CPT AF register offset calculation Some CPT AF registers are per LF and others are global. Translation of PF/VF local LF slot number to actual LF slot number is required only for accessing perf LF registers. CPT AF global registers access do not require any LF slot number. Also, there is no reason CPT PF/VF to know actual lf's register offset. Without this fix microcode loading will fail, VFs cannot be created and hardware is not usable. Fixes: bc35e28af789 ("octeontx2-af: replace cpt slot with lf id on reg write") Signed-off-by: Bharat Bhushan Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240821070558.1020101-1-bbhushan2@marvell.com Signed-off-by: Paolo Abeni --- .../ethernet/marvell/octeontx2/af/rvu_cpt.c | 23 +++++++++---------- 1 file changed, 11 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c index 3e09d2285814..daf4b951e905 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c @@ -632,7 +632,9 @@ int rvu_mbox_handler_cpt_inline_ipsec_cfg(struct rvu *rvu, return ret; } -static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req) +static bool validate_and_update_reg_offset(struct rvu *rvu, + struct cpt_rd_wr_reg_msg *req, + u64 *reg_offset) { u64 offset = req->reg_offset; int blkaddr, num_lfs, lf; @@ -663,6 +665,11 @@ static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req) if (lf < 0) return false; + /* Translate local LF's offset to global CPT LF's offset to + * access LFX register. + */ + *reg_offset = (req->reg_offset & 0xFF000) + (lf << 3); + return true; } else if (!(req->hdr.pcifunc & RVU_PFVF_FUNC_MASK)) { /* Registers that can be accessed from PF */ @@ -697,7 +704,7 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu, struct cpt_rd_wr_reg_msg *rsp) { u64 offset = req->reg_offset; - int blkaddr, lf; + int blkaddr; blkaddr = validate_and_get_cpt_blkaddr(req->blkaddr); if (blkaddr < 0) @@ -708,18 +715,10 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu, !is_cpt_vf(rvu, req->hdr.pcifunc)) return CPT_AF_ERR_ACCESS_DENIED; - if (!is_valid_offset(rvu, req)) + if (!validate_and_update_reg_offset(rvu, req, &offset)) return CPT_AF_ERR_ACCESS_DENIED; - /* Translate local LF used by VFs to global CPT LF */ - lf = rvu_get_lf(rvu, &rvu->hw->block[blkaddr], req->hdr.pcifunc, - (offset & 0xFFF) >> 3); - - /* Translate local LF's offset to global CPT LF's offset */ - offset &= 0xFF000; - offset += lf << 3; - - rsp->reg_offset = offset; + rsp->reg_offset = req->reg_offset; rsp->ret_val = req->ret_val; rsp->is_write = req->is_write; From 9a8fc292dd93b93db30e01c94c0da4c944852f28 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 22 Aug 2024 14:30:53 +0300 Subject: [PATCH 525/562] spi: pxa2xx: Do not override dev->platform_data on probe The platform_data field may be supplied by legacy board code. In other cases we override it, and module remove and probe cycle will crash the kernel since it will carry a stale pointer. Fix this by supplying a third argument to the pxa2xx_spi_probe() and avoid overriding dev->platform_data. Reported-by: Hao Ma Fixes: cc160697a576 ("spi: pxa2xx: Convert PCI driver to use spi-pxa2xx code directly") Fixes: 3d8f037fbcab ("spi: pxa2xx: Move platform driver to a separate file") Fixes: 20ade9b9771c ("spi: pxa2xx: Extract pxa2xx_spi_platform_*() callbacks") Signed-off-by: Andy Shevchenko Link: https://patch.msgid.link/20240822113408.750831-2-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- drivers/spi/spi-pxa2xx-pci.c | 2 +- drivers/spi/spi-pxa2xx-platform.c | 6 ++---- drivers/spi/spi-pxa2xx.c | 5 ++--- drivers/spi/spi-pxa2xx.h | 3 ++- 4 files changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c index 616d032f1a89..c98bb214b6ae 100644 --- a/drivers/spi/spi-pxa2xx-pci.c +++ b/drivers/spi/spi-pxa2xx-pci.c @@ -297,7 +297,7 @@ static int pxa2xx_spi_pci_probe(struct pci_dev *dev, return ret; ssp->irq = pci_irq_vector(dev, 0); - return pxa2xx_spi_probe(&dev->dev, ssp); + return pxa2xx_spi_probe(&dev->dev, ssp, pdata); } static void pxa2xx_spi_pci_remove(struct pci_dev *dev) diff --git a/drivers/spi/spi-pxa2xx-platform.c b/drivers/spi/spi-pxa2xx-platform.c index 98a8ceb7db6f..f9504cddc7ba 100644 --- a/drivers/spi/spi-pxa2xx-platform.c +++ b/drivers/spi/spi-pxa2xx-platform.c @@ -63,7 +63,7 @@ static struct ssp_device *pxa2xx_spi_ssp_request(struct platform_device *pdev) ssp = pxa_ssp_request(pdev->id, pdev->name); if (!ssp) - return ssp; + return NULL; status = devm_add_action_or_reset(&pdev->dev, pxa2xx_spi_ssp_release, ssp); if (status) @@ -148,8 +148,6 @@ static int pxa2xx_spi_platform_probe(struct platform_device *pdev) platform_info = pxa2xx_spi_init_pdata(pdev); if (IS_ERR(platform_info)) return dev_err_probe(dev, PTR_ERR(platform_info), "missing platform data\n"); - - dev->platform_data = platform_info; } ssp = pxa2xx_spi_ssp_request(pdev); @@ -158,7 +156,7 @@ static int pxa2xx_spi_platform_probe(struct platform_device *pdev) if (!ssp) ssp = &platform_info->ssp; - return pxa2xx_spi_probe(dev, ssp); + return pxa2xx_spi_probe(dev, ssp, platform_info); } static void pxa2xx_spi_platform_remove(struct platform_device *pdev) diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index 16b96eb176cd..e3a95adc5279 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -1277,16 +1277,15 @@ static size_t pxa2xx_spi_max_dma_transfer_size(struct spi_device *spi) return MAX_DMA_LEN; } -int pxa2xx_spi_probe(struct device *dev, struct ssp_device *ssp) +int pxa2xx_spi_probe(struct device *dev, struct ssp_device *ssp, + struct pxa2xx_spi_controller *platform_info) { - struct pxa2xx_spi_controller *platform_info; struct spi_controller *controller; struct driver_data *drv_data; const struct lpss_config *config; int status; u32 tmp; - platform_info = dev_get_platdata(dev); if (platform_info->is_target) controller = devm_spi_alloc_target(dev, sizeof(*drv_data)); else diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h index a470d3d634d3..447be0369384 100644 --- a/drivers/spi/spi-pxa2xx.h +++ b/drivers/spi/spi-pxa2xx.h @@ -132,7 +132,8 @@ extern void pxa2xx_spi_dma_stop(struct driver_data *drv_data); extern int pxa2xx_spi_dma_setup(struct driver_data *drv_data); extern void pxa2xx_spi_dma_release(struct driver_data *drv_data); -int pxa2xx_spi_probe(struct device *dev, struct ssp_device *ssp); +int pxa2xx_spi_probe(struct device *dev, struct ssp_device *ssp, + struct pxa2xx_spi_controller *platform_info); void pxa2xx_spi_remove(struct device *dev); extern const struct dev_pm_ops pxa2xx_spi_pm_ops; From e17465f78eb92ebb4be17e35d6c0584406f643a0 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 22 Aug 2024 14:30:54 +0300 Subject: [PATCH 526/562] spi: pxa2xx: Move PM runtime handling to the glue drivers PCI and platform buses have different defaults for runtime PM. In particular PCI probe is assumed to be called when PM runtime is enabled by the PCI core. In this case if we try enable it again the PM runtime complaints with pxa2xx_spi_pci 0000:00:07.0: Unbalanced pm_runtime_enable! Fix this by moving PM runtime handling from the SPI PXA2xx core to the glue drivers. Fixes: cc160697a576 ("spi: pxa2xx: Convert PCI driver to use spi-pxa2xx code directly") Fixes: 3d8f037fbcab ("spi: pxa2xx: Move platform driver to a separate file") Fixes: 20ade9b9771c ("spi: pxa2xx: Extract pxa2xx_spi_platform_*() callbacks") Signed-off-by: Andy Shevchenko Link: https://patch.msgid.link/20240822113408.750831-3-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- drivers/spi/spi-pxa2xx-pci.c | 15 ++++++++++++++- drivers/spi/spi-pxa2xx-platform.c | 22 ++++++++++++++++++++-- drivers/spi/spi-pxa2xx.c | 15 +-------------- 3 files changed, 35 insertions(+), 17 deletions(-) diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c index c98bb214b6ae..cc8dcf782399 100644 --- a/drivers/spi/spi-pxa2xx-pci.c +++ b/drivers/spi/spi-pxa2xx-pci.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -297,11 +298,23 @@ static int pxa2xx_spi_pci_probe(struct pci_dev *dev, return ret; ssp->irq = pci_irq_vector(dev, 0); - return pxa2xx_spi_probe(&dev->dev, ssp, pdata); + ret = pxa2xx_spi_probe(&dev->dev, ssp, pdata); + if (ret) + return ret; + + pm_runtime_set_autosuspend_delay(&dev->dev, 50); + pm_runtime_use_autosuspend(&dev->dev); + pm_runtime_put_autosuspend(&dev->dev); + pm_runtime_allow(&dev->dev); + + return 0; } static void pxa2xx_spi_pci_remove(struct pci_dev *dev) { + pm_runtime_forbid(&dev->dev); + pm_runtime_get_noresume(&dev->dev); + pxa2xx_spi_remove(&dev->dev); } diff --git a/drivers/spi/spi-pxa2xx-platform.c b/drivers/spi/spi-pxa2xx-platform.c index f9504cddc7ba..595af9fa4e0f 100644 --- a/drivers/spi/spi-pxa2xx-platform.c +++ b/drivers/spi/spi-pxa2xx-platform.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include @@ -142,6 +143,7 @@ static int pxa2xx_spi_platform_probe(struct platform_device *pdev) struct pxa2xx_spi_controller *platform_info; struct device *dev = &pdev->dev; struct ssp_device *ssp; + int ret; platform_info = dev_get_platdata(dev); if (!platform_info) { @@ -156,12 +158,28 @@ static int pxa2xx_spi_platform_probe(struct platform_device *pdev) if (!ssp) ssp = &platform_info->ssp; - return pxa2xx_spi_probe(dev, ssp, platform_info); + pm_runtime_set_autosuspend_delay(dev, 50); + pm_runtime_use_autosuspend(dev); + pm_runtime_set_active(dev); + pm_runtime_enable(dev); + + ret = pxa2xx_spi_probe(dev, ssp, platform_info); + if (ret) + pm_runtime_disable(dev); + + return ret; } static void pxa2xx_spi_platform_remove(struct platform_device *pdev) { - pxa2xx_spi_remove(&pdev->dev); + struct device *dev = &pdev->dev; + + pm_runtime_get_sync(dev); + + pxa2xx_spi_remove(dev); + + pm_runtime_put_noidle(dev); + pm_runtime_disable(dev); } static const struct acpi_device_id pxa2xx_spi_acpi_match[] = { diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index e3a95adc5279..bf1f34b0ffc8 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -1449,24 +1449,16 @@ int pxa2xx_spi_probe(struct device *dev, struct ssp_device *ssp, } } - pm_runtime_set_autosuspend_delay(dev, 50); - pm_runtime_use_autosuspend(dev); - pm_runtime_set_active(dev); - pm_runtime_enable(dev); - /* Register with the SPI framework */ dev_set_drvdata(dev, drv_data); status = spi_register_controller(controller); if (status) { dev_err_probe(dev, status, "problem registering SPI controller\n"); - goto out_error_pm_runtime_enabled; + goto out_error_clock_enabled; } return status; -out_error_pm_runtime_enabled: - pm_runtime_disable(dev); - out_error_clock_enabled: clk_disable_unprepare(ssp->clk); @@ -1483,8 +1475,6 @@ void pxa2xx_spi_remove(struct device *dev) struct driver_data *drv_data = dev_get_drvdata(dev); struct ssp_device *ssp = drv_data->ssp; - pm_runtime_get_sync(dev); - spi_unregister_controller(drv_data->controller); /* Disable the SSP at the peripheral and SOC level */ @@ -1495,9 +1485,6 @@ void pxa2xx_spi_remove(struct device *dev) if (drv_data->controller_info->enable_dma) pxa2xx_spi_dma_release(drv_data); - pm_runtime_put_noidle(dev); - pm_runtime_disable(dev); - /* Release IRQ */ free_irq(ssp->irq, drv_data); } From 1ac66c4960e1c735eb6edfd3e6d52bebb2aa347e Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 21 Aug 2024 09:46:44 +0100 Subject: [PATCH 527/562] MAINTAINERS: Add sonet.h to ATM section of MAINTAINERS This is part of an effort to assign a section in MAINTAINERS to header files that relate to Networking. In this case the files with "net" in their name. It seems that sonet.h is included in ATM related source files, and thus that ATM is the most relevant section for these files. Cc: Chas Williams <3chas3@gmail.com> Signed-off-by: Simon Horman Signed-off-by: Paolo Abeni --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index a964a34651f5..c682203915a2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3504,7 +3504,9 @@ S: Maintained W: http://linux-atm.sourceforge.net F: drivers/atm/ F: include/linux/atm* +F: include/linux/sonet.h F: include/uapi/linux/atm* +F: include/uapi/linux/sonet.h ATMEL MACB ETHERNET DRIVER M: Nicolas Ferre From eb208fecd77d898709c25af680487289fd5f3e16 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 21 Aug 2024 09:46:45 +0100 Subject: [PATCH 528/562] MAINTAINERS: Add net_tstamp.h to SOCKET TIMESTAMPING section This is part of an effort to assign a section in MAINTAINERS to header files that relate to Networking. In this case the files with "net" in their name. Cc: Richard Cochran Cc: Willem de Bruijn Signed-off-by: Simon Horman Acked-by: Willem de Bruijn Signed-off-by: Paolo Abeni --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index c682203915a2..e5b9a4d9bc21 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -21057,6 +21057,7 @@ SOCKET TIMESTAMPING M: Willem de Bruijn S: Maintained F: Documentation/networking/timestamping.rst +F: include/linux/net_tstamp.h F: include/uapi/linux/net_tstamp.h F: tools/testing/selftests/net/so_txtime.c From 8cb0a938d90b25f123fcb2e24bbda9eaabd79c9e Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 21 Aug 2024 09:46:46 +0100 Subject: [PATCH 529/562] MAINTAINERS: Add limited globs for Networking headers This aims to add limited globs to improve the coverage of header files in the NETWORKING DRIVERS and NETWORKING [GENERAL] sections. It is done so in a minimal way to exclude overlap with other sections. And so as not to require "X" entries to exclude files otherwise matched by these new globs. While imperfect, due to it's limited nature, this does extend coverage of header files by these sections. And aims to automatically cover new files that seem very likely belong to these sections. The include/linux/netdev* glob (both sections) + Subsumes the entries for: - include/linux/netdevice.h + Extends the sections to cover - include/linux/netdevice_xmit.h - include/linux/netdev_features.h The include/uapi/linux/netdev* globs: (both sections) + Subsumes the entries for: - include/linux/netdevice.h + Extends the sections to cover - include/linux/netdev.h The include/linux/skbuff* glob (NETWORKING [GENERAL] section only): + Subsumes the entry for: - include/linux/skbuff.h + Extends the section to cover - include/linux/skbuff_ref.h A include/uapi/linux/net_* glob was not added to the NETWORKING [GENERAL] section. Although it would subsume the entry for include/uapi/linux/net_namespace.h, which is fine, it would also extend coverage to: - include/uapi/linux/net_dropmon.h, which belongs to the NETWORK DROP MONITOR section - include/uapi/linux/net_tstamp.h which, as per an earlier patch in this series, belongs to the SOCKET TIMESTAMPING section Signed-off-by: Simon Horman Signed-off-by: Paolo Abeni --- MAINTAINERS | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index e5b9a4d9bc21..03d571b131eb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15884,10 +15884,10 @@ F: include/linux/fddidevice.h F: include/linux/hippidevice.h F: include/linux/if_* F: include/linux/inetdevice.h -F: include/linux/netdevice.h +F: include/linux/netdev* F: include/uapi/linux/cn_proc.h F: include/uapi/linux/if_* -F: include/uapi/linux/netdevice.h +F: include/uapi/linux/netdev* F: tools/testing/selftests/drivers/net/ X: drivers/net/wireless/ @@ -15940,13 +15940,13 @@ F: include/linux/framer/framer.h F: include/linux/in.h F: include/linux/indirect_call_wrapper.h F: include/linux/net.h -F: include/linux/netdevice.h -F: include/linux/skbuff.h +F: include/linux/netdev* +F: include/linux/skbuff* F: include/net/ F: include/uapi/linux/in.h F: include/uapi/linux/net.h F: include/uapi/linux/net_namespace.h -F: include/uapi/linux/netdevice.h +F: include/uapi/linux/netdev* F: lib/net_utils.c F: lib/random32.c F: net/ From f2d20c9b97f0df64841b89fa1ad3e9c92f7377ae Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 21 Aug 2024 09:46:47 +0100 Subject: [PATCH 530/562] MAINTAINERS: Add header files to NETWORKING sections This is part of an effort to assign a section in MAINTAINERS to header files that relate to Networking. In this case the files with "net" or "skbuff" in their name. This patch adds a number of such files to the NETWORKING DRIVERS and NETWORKING [GENERAL] sections. Signed-off-by: Simon Horman Signed-off-by: Paolo Abeni --- MAINTAINERS | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 03d571b131eb..798f1ffcbbaa 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15879,13 +15879,16 @@ F: drivers/net/ F: include/dt-bindings/net/ F: include/linux/cn_proc.h F: include/linux/etherdevice.h +F: include/linux/ethtool_netlink.h F: include/linux/fcdevice.h F: include/linux/fddidevice.h F: include/linux/hippidevice.h F: include/linux/if_* F: include/linux/inetdevice.h F: include/linux/netdev* +F: include/linux/platform_data/wiznet.h F: include/uapi/linux/cn_proc.h +F: include/uapi/linux/ethtool_netlink.h F: include/uapi/linux/if_* F: include/uapi/linux/netdev* F: tools/testing/selftests/drivers/net/ @@ -15939,14 +15942,28 @@ F: include/linux/framer/framer-provider.h F: include/linux/framer/framer.h F: include/linux/in.h F: include/linux/indirect_call_wrapper.h +F: include/linux/inet.h +F: include/linux/inet_diag.h F: include/linux/net.h F: include/linux/netdev* +F: include/linux/netlink.h +F: include/linux/netpoll.h +F: include/linux/rtnetlink.h +F: include/linux/seq_file_net.h F: include/linux/skbuff* F: include/net/ +F: include/uapi/linux/genetlink.h +F: include/uapi/linux/hsr_netlink.h F: include/uapi/linux/in.h +F: include/uapi/linux/inet_diag.h +F: include/uapi/linux/nbd-netlink.h F: include/uapi/linux/net.h F: include/uapi/linux/net_namespace.h +F: include/uapi/linux/netconf.h F: include/uapi/linux/netdev* +F: include/uapi/linux/netlink.h +F: include/uapi/linux/netlink_diag.h +F: include/uapi/linux/rtnetlink.h F: lib/net_utils.c F: lib/random32.c F: net/ From 46097a92662496394628cb41138e681d6074cce7 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 21 Aug 2024 09:46:48 +0100 Subject: [PATCH 531/562] MAINTAINERS: Mark JME Network Driver as Odd Fixes This driver only appears to have received sporadic clean-ups, typically part of some tree-wide activity, and fixes for quite some time. And according to the maintainer, Guo-Fu Tseng, the device has been EOLed for a long time (see Link). Accordingly, it seems appropriate to mark this driver as odd fixes. Cc: Moon Yeounsu Cc: Guo-Fu Tseng Link: https://lore.kernel.org/netdev/20240805003139.M94125@cooldavid.org/ Signed-off-by: Simon Horman Signed-off-by: Paolo Abeni --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 798f1ffcbbaa..0c94ec0ca478 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11995,7 +11995,7 @@ F: fs/jfs/ JME NETWORK DRIVER M: Guo-Fu Tseng L: netdev@vger.kernel.org -S: Maintained +S: Odd Fixes F: drivers/net/ethernet/jme.* JOURNALLING FLASH FILE SYSTEM V2 (JFFS2) From 3e878fe5a0b139838a65f50a3df3caf3299dbc24 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Thu, 22 Aug 2024 03:57:39 -0400 Subject: [PATCH 532/562] bcachefs: add missing inode_walker_exit() fix a small leak Signed-off-by: Kent Overstreet --- fs/bcachefs/fsck.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 6801c37ee803..83bd31b44aad 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -2215,6 +2215,8 @@ int bch2_check_xattrs(struct bch_fs *c) NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_xattr(trans, &iter, k, &hash_info, &inode))); + + inode_walker_exit(&inode); bch_err_fn(c, ret); return ret; } From a592cdf5164d3feb821085df71f63e70e8b8b08c Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 19 Aug 2024 16:41:00 -0400 Subject: [PATCH 533/562] bcachefs: don't use rht_bucket() in btree_key_cache_scan() rht_bucket() does strange complicated things when a rehash is in progress. Instead, just skip scanning when a rehash is in progress: scanning is going to be more expensive (many more empty slots to cover), and some sort of infinite loop is being observed Signed-off-by: Kent Overstreet --- fs/bcachefs/btree_key_cache.c | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 9b3ec2a3b8ce..fda7998734cb 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -778,6 +778,20 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, rcu_read_lock(); tbl = rht_dereference_rcu(bc->table.tbl, &bc->table); + + /* + * Scanning is expensive while a rehash is in progress - most elements + * will be on the new hashtable, if it's in progress + * + * A rehash could still start while we're scanning - that's ok, we'll + * still see most elements. + */ + if (unlikely(tbl->nest)) { + rcu_read_unlock(); + srcu_read_unlock(&c->btree_trans_barrier, srcu_idx); + return SHRINK_STOP; + } + if (bc->shrink_iter >= tbl->size) bc->shrink_iter = 0; start = bc->shrink_iter; @@ -785,7 +799,7 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, do { struct rhash_head *pos, *next; - pos = rht_ptr_rcu(rht_bucket(tbl, bc->shrink_iter)); + pos = rht_ptr_rcu(&tbl->buckets[bc->shrink_iter]); while (!rht_is_a_nulls(pos)) { next = rht_dereference_bucket_rcu(pos->next, tbl, bc->shrink_iter); @@ -866,12 +880,22 @@ void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc) while (atomic_long_read(&bc->nr_keys)) { rcu_read_lock(); tbl = rht_dereference_rcu(bc->table.tbl, &bc->table); - if (tbl) + if (tbl) { + if (tbl->nest) { + /* wait for in progress rehash */ + rcu_read_unlock(); + mutex_lock(&bc->table.mutex); + mutex_unlock(&bc->table.mutex); + rcu_read_lock(); + continue; + } for (i = 0; i < tbl->size; i++) - rht_for_each_entry_rcu(ck, pos, tbl, i, hash) { + while (pos = rht_ptr_rcu(&tbl->buckets[i]), !rht_is_a_nulls(pos)) { + ck = container_of(pos, struct bkey_cached, hash); bkey_cached_evict(bc, ck); list_add(&ck->list, &items); } + } rcu_read_unlock(); } From ce61b605a00502c59311d0a4b1f58d62b48272d0 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 20 Aug 2024 22:07:38 +0900 Subject: [PATCH 534/562] ksmbd: the buffer of smb2 query dir response has at least 1 byte When STATUS_NO_MORE_FILES status is set to smb2 query dir response, ->StructureSize is set to 9, which mean buffer has 1 byte. This issue occurs because ->Buffer[1] in smb2_query_directory_rsp to flex-array. Fixes: eb3e28c1e89b ("smb3: Replace smb2pdu 1-element arrays with flex-arrays") Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 0bc9edf22ba4..e9204180919e 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -4409,7 +4409,8 @@ int smb2_query_dir(struct ksmbd_work *work) rsp->OutputBufferLength = cpu_to_le32(0); rsp->Buffer[0] = 0; rc = ksmbd_iov_pin_rsp(work, (void *)rsp, - sizeof(struct smb2_query_directory_rsp)); + offsetof(struct smb2_query_directory_rsp, Buffer) + + 1); if (rc) goto err_out; } else { From 2186a116538a715b20e15f84fdd3545e5fe0a39b Mon Sep 17 00:00:00 2001 From: ChenXiaoSong Date: Thu, 22 Aug 2024 08:20:50 +0000 Subject: [PATCH 535/562] smb/server: fix return value of smb2_open() In most error cases, error code is not returned in smb2_open(), __process_request() will not print error message. Fix this by returning the correct value at the end of smb2_open(). Signed-off-by: ChenXiaoSong Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index e9204180919e..55d4e69bd9c9 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3713,7 +3713,7 @@ err_out2: kfree(name); kfree(lc); - return 0; + return rc; } static int readdir_info_level_struct_sz(int info_level) From 4e8771a3666c8f216eefd6bd2fd50121c6c437db Mon Sep 17 00:00:00 2001 From: ChenXiaoSong Date: Thu, 22 Aug 2024 08:20:51 +0000 Subject: [PATCH 536/562] smb/server: fix potential null-ptr-deref of lease_ctx_info in smb2_open() null-ptr-deref will occur when (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) and parse_lease_state() return NULL. Fix this by check if 'lease_ctx_info' is NULL. Additionally, remove the redundant parentheses in parse_durable_handle_context(). Signed-off-by: ChenXiaoSong Signed-off-by: Steve French --- fs/smb/server/oplock.c | 2 +- fs/smb/server/smb2pdu.c | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index a8f52c4ebbda..e546ffa57b55 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1510,7 +1510,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) * parse_lease_state() - parse lease context containted in file open request * @open_req: buffer containing smb2 file open(create) request * - * Return: oplock state, -ENOENT if create lease context not found + * Return: allocated lease context object on success, otherwise NULL */ struct lease_ctx_info *parse_lease_state(void *open_req) { diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 55d4e69bd9c9..5d170ab0817d 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2770,8 +2770,8 @@ static int parse_durable_handle_context(struct ksmbd_work *work, } } - if (((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) || - req_op_level == SMB2_OPLOCK_LEVEL_BATCH)) { + if ((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) || + req_op_level == SMB2_OPLOCK_LEVEL_BATCH) { dh_info->CreateGuid = durable_v2_blob->CreateGuid; dh_info->persistent = @@ -2791,8 +2791,8 @@ static int parse_durable_handle_context(struct ksmbd_work *work, goto out; } - if (((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) || - req_op_level == SMB2_OPLOCK_LEVEL_BATCH)) { + if ((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) || + req_op_level == SMB2_OPLOCK_LEVEL_BATCH) { ksmbd_debug(SMB, "Request for durable open\n"); dh_info->type = dh_idx; } @@ -3414,7 +3414,7 @@ int smb2_open(struct ksmbd_work *work) goto err_out1; } } else { - if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) { + if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE && lc) { if (S_ISDIR(file_inode(filp)->i_mode)) { lc->req_state &= ~SMB2_LEASE_WRITE_CACHING_LE; lc->is_dir = true; From 0dd771b7d60b8281f10f6721783c60716d22075f Mon Sep 17 00:00:00 2001 From: ChenXiaoSong Date: Thu, 22 Aug 2024 08:20:52 +0000 Subject: [PATCH 537/562] smb/server: remove useless assignment of 'file_present' in smb2_open() The variable is already true here. Signed-off-by: ChenXiaoSong Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 5d170ab0817d..cd23517d9640 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3096,7 +3096,6 @@ int smb2_open(struct ksmbd_work *work) goto err_out; } - file_present = true; idmap = mnt_idmap(path.mnt); } else { if (rc != -ENOENT) From 2b7e0573a49064d9c94c114b4471327cd96ae39c Mon Sep 17 00:00:00 2001 From: ChenXiaoSong Date: Thu, 22 Aug 2024 08:20:54 +0000 Subject: [PATCH 538/562] smb/server: update misguided comment of smb2_allocate_rsp_buf() smb2_allocate_rsp_buf() will return other error code except -ENOMEM. Signed-off-by: ChenXiaoSong Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index cd23517d9640..20846a4d3031 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -519,7 +519,7 @@ int init_smb2_rsp_hdr(struct ksmbd_work *work) * smb2_allocate_rsp_buf() - allocate smb2 response buffer * @work: smb work containing smb request buffer * - * Return: 0 on success, otherwise -ENOMEM + * Return: 0 on success, otherwise error */ int smb2_allocate_rsp_buf(struct ksmbd_work *work) { From d7fd2941ae9a67423d1c7bee985f240e4686634f Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 21 Aug 2024 18:55:06 +0200 Subject: [PATCH 539/562] s390/boot: Avoid possible physmem_info segment corruption When physical memory for the kernel image is allocated it does not consider extra memory required for offsetting the image start to match it with the lower 20 bits of KASLR virtual base address. That might lead to kernel access beyond its memory range. Suggested-by: Vasily Gorbik Fixes: 693d41f7c938 ("s390/mm: Restore mapping of kernel image using large pages") Signed-off-by: Alexander Gordeev Acked-by: Vasily Gorbik Signed-off-by: Vasily Gorbik --- arch/s390/boot/startup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index cff34744b5a9..d69f1dfd3b1e 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -457,9 +457,9 @@ void startup_kernel(void) */ kaslr_large_page_offset = __kaslr_offset & ~_SEGMENT_MASK; if (kaslr_enabled()) { - unsigned long end = ident_map_size - kaslr_large_page_offset; + unsigned long size = kernel_size + kaslr_large_page_offset; - __kaslr_offset_phys = randomize_within_range(kernel_size, _SEGMENT_SIZE, 0, end); + __kaslr_offset_phys = randomize_within_range(size, _SEGMENT_SIZE, 0, ident_map_size); } if (!__kaslr_offset_phys) __kaslr_offset_phys = nokaslr_offset_phys; From 1642285e511c2a40b14e87a41aa8feace6123036 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 21 Aug 2024 18:55:07 +0200 Subject: [PATCH 540/562] s390/boot: Fix KASLR base offset off by __START_KERNEL bytes Symbol offsets to the KASLR base do not match symbol address in the vmlinux image. That is the result of setting the KASLR base to the beginning of .text section as result of an optimization. Revert that optimization and allocate virtual memory for the whole kernel image including __START_KERNEL bytes as per the linker script. That allows keeping the semantics of the KASLR base offset in sync with other architectures. Rename __START_KERNEL to TEXT_OFFSET, since it represents the offset of the .text section within the kernel image, rather than a virtual address. Still skip mapping TEXT_OFFSET bytes to save memory on pgtables and provoke exceptions in case an attempt to access this area is made, as no kernel symbol may reside there. In case CONFIG_KASAN is enabled the location counter might exceed the value of TEXT_OFFSET, while the decompressor linker script forcefully resets it to TEXT_OFFSET, which leads to a sections overlap link failure. Use MAX() expression to avoid that. Reported-by: Omar Sandoval Closes: https://lore.kernel.org/linux-s390/ZnS8dycxhtXBZVky@telecaster.dhcp.thefacebook.com/ Fixes: 56b1069c40c7 ("s390/boot: Rework deployment of the kernel image") Signed-off-by: Alexander Gordeev Acked-by: Vasily Gorbik Signed-off-by: Vasily Gorbik --- arch/s390/boot/startup.c | 55 ++++++++++++++++++---------------- arch/s390/boot/vmem.c | 14 +++++++-- arch/s390/boot/vmlinux.lds.S | 7 ++++- arch/s390/include/asm/page.h | 3 +- arch/s390/kernel/vmlinux.lds.S | 2 +- arch/s390/tools/relocs.c | 2 +- 6 files changed, 52 insertions(+), 31 deletions(-) diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index d69f1dfd3b1e..c73b5118ad42 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -162,7 +162,7 @@ static void kaslr_adjust_relocs(unsigned long min_addr, unsigned long max_addr, loc = (long)*reloc + phys_offset; if (loc < min_addr || loc > max_addr) error("64-bit relocation outside of kernel!\n"); - *(u64 *)loc += offset - __START_KERNEL; + *(u64 *)loc += offset; } } @@ -177,7 +177,7 @@ static void kaslr_adjust_got(unsigned long offset) */ for (entry = (u64 *)vmlinux.got_start; entry < (u64 *)vmlinux.got_end; entry++) { if (*entry) - *entry += offset - __START_KERNEL; + *entry += offset; } } @@ -252,7 +252,7 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size) vmemmap_size = SECTION_ALIGN_UP(pages) * sizeof(struct page); /* choose kernel address space layout: 4 or 3 levels. */ - BUILD_BUG_ON(!IS_ALIGNED(__START_KERNEL, THREAD_SIZE)); + BUILD_BUG_ON(!IS_ALIGNED(TEXT_OFFSET, THREAD_SIZE)); BUILD_BUG_ON(!IS_ALIGNED(__NO_KASLR_START_KERNEL, THREAD_SIZE)); BUILD_BUG_ON(__NO_KASLR_END_KERNEL > _REGION1_SIZE); vsize = get_vmem_size(ident_map_size, vmemmap_size, vmalloc_size, _REGION3_SIZE); @@ -389,31 +389,25 @@ static void kaslr_adjust_vmlinux_info(long offset) #endif } -static void fixup_vmlinux_info(void) -{ - vmlinux.entry -= __START_KERNEL; - kaslr_adjust_vmlinux_info(-__START_KERNEL); -} - void startup_kernel(void) { - unsigned long kernel_size = vmlinux.image_size + vmlinux.bss_size; - unsigned long nokaslr_offset_phys, kaslr_large_page_offset; - unsigned long amode31_lma = 0; + unsigned long vmlinux_size = vmlinux.image_size + vmlinux.bss_size; + unsigned long nokaslr_text_lma, text_lma = 0, amode31_lma = 0; + unsigned long kernel_size = TEXT_OFFSET + vmlinux_size; + unsigned long kaslr_large_page_offset; unsigned long max_physmem_end; unsigned long asce_limit; unsigned long safe_addr; psw_t psw; - fixup_vmlinux_info(); setup_lpp(); /* * Non-randomized kernel physical start address must be _SEGMENT_SIZE * aligned (see blow). */ - nokaslr_offset_phys = ALIGN(mem_safe_offset(), _SEGMENT_SIZE); - safe_addr = PAGE_ALIGN(nokaslr_offset_phys + kernel_size); + nokaslr_text_lma = ALIGN(mem_safe_offset(), _SEGMENT_SIZE); + safe_addr = PAGE_ALIGN(nokaslr_text_lma + vmlinux_size); /* * Reserve decompressor memory together with decompression heap, @@ -457,16 +451,27 @@ void startup_kernel(void) */ kaslr_large_page_offset = __kaslr_offset & ~_SEGMENT_MASK; if (kaslr_enabled()) { - unsigned long size = kernel_size + kaslr_large_page_offset; + unsigned long size = vmlinux_size + kaslr_large_page_offset; - __kaslr_offset_phys = randomize_within_range(size, _SEGMENT_SIZE, 0, ident_map_size); + text_lma = randomize_within_range(size, _SEGMENT_SIZE, TEXT_OFFSET, ident_map_size); } - if (!__kaslr_offset_phys) - __kaslr_offset_phys = nokaslr_offset_phys; - __kaslr_offset_phys |= kaslr_large_page_offset; + if (!text_lma) + text_lma = nokaslr_text_lma; + text_lma |= kaslr_large_page_offset; + + /* + * [__kaslr_offset_phys..__kaslr_offset_phys + TEXT_OFFSET] region is + * never accessed via the kernel image mapping as per the linker script: + * + * . = TEXT_OFFSET; + * + * Therefore, this region could be used for something else and does + * not need to be reserved. See how it is skipped in setup_vmem(). + */ + __kaslr_offset_phys = text_lma - TEXT_OFFSET; kaslr_adjust_vmlinux_info(__kaslr_offset_phys); - physmem_reserve(RR_VMLINUX, __kaslr_offset_phys, kernel_size); - deploy_kernel((void *)__kaslr_offset_phys); + physmem_reserve(RR_VMLINUX, text_lma, vmlinux_size); + deploy_kernel((void *)text_lma); /* vmlinux decompression is done, shrink reserved low memory */ physmem_reserve(RR_DECOMPRESSOR, 0, (unsigned long)_decompressor_end); @@ -489,7 +494,7 @@ void startup_kernel(void) amode31_lma = randomize_within_range(vmlinux.amode31_size, PAGE_SIZE, amode31_min, SZ_2G); } if (!amode31_lma) - amode31_lma = __kaslr_offset_phys - vmlinux.amode31_size; + amode31_lma = text_lma - vmlinux.amode31_size; physmem_reserve(RR_AMODE31, amode31_lma, vmlinux.amode31_size); /* @@ -505,8 +510,8 @@ void startup_kernel(void) * - copy_bootdata() must follow setup_vmem() to propagate changes * to bootdata made by setup_vmem() */ - clear_bss_section(__kaslr_offset_phys); - kaslr_adjust_relocs(__kaslr_offset_phys, __kaslr_offset_phys + vmlinux.image_size, + clear_bss_section(text_lma); + kaslr_adjust_relocs(text_lma, text_lma + vmlinux.image_size, __kaslr_offset, __kaslr_offset_phys); kaslr_adjust_got(__kaslr_offset); setup_vmem(__kaslr_offset, __kaslr_offset + kernel_size, asce_limit); diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 2847cc059ab7..145035f84a0e 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -90,7 +90,7 @@ static void kasan_populate_shadow(unsigned long kernel_start, unsigned long kern } memgap_start = end; } - kasan_populate(kernel_start, kernel_end, POPULATE_KASAN_MAP_SHADOW); + kasan_populate(kernel_start + TEXT_OFFSET, kernel_end, POPULATE_KASAN_MAP_SHADOW); kasan_populate(0, (unsigned long)__identity_va(0), POPULATE_KASAN_ZERO_SHADOW); kasan_populate(AMODE31_START, AMODE31_END, POPULATE_KASAN_ZERO_SHADOW); if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { @@ -475,7 +475,17 @@ void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned l (unsigned long)__identity_va(end), POPULATE_IDENTITY); } - pgtable_populate(kernel_start, kernel_end, POPULATE_KERNEL); + + /* + * [kernel_start..kernel_start + TEXT_OFFSET] region is never + * accessed as per the linker script: + * + * . = TEXT_OFFSET; + * + * Therefore, skip mapping TEXT_OFFSET bytes to prevent access to + * [__kaslr_offset_phys..__kaslr_offset_phys + TEXT_OFFSET] region. + */ + pgtable_populate(kernel_start + TEXT_OFFSET, kernel_end, POPULATE_KERNEL); pgtable_populate(AMODE31_START, AMODE31_END, POPULATE_DIRECT); pgtable_populate(__abs_lowcore, __abs_lowcore + sizeof(struct lowcore), POPULATE_ABS_LOWCORE); diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S index a750711d44c8..66670212a361 100644 --- a/arch/s390/boot/vmlinux.lds.S +++ b/arch/s390/boot/vmlinux.lds.S @@ -109,7 +109,12 @@ SECTIONS #ifdef CONFIG_KERNEL_UNCOMPRESSED . = ALIGN(PAGE_SIZE); . += AMODE31_SIZE; /* .amode31 section */ - . = ALIGN(1 << 20); /* _SEGMENT_SIZE */ + + /* + * Make sure the location counter is not less than TEXT_OFFSET. + * _SEGMENT_SIZE is not available, use ALIGN(1 << 20) instead. + */ + . = MAX(TEXT_OFFSET, ALIGN(1 << 20)); #else . = ALIGN(8); #endif diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 06416b3f94f5..16e4caa931f1 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -279,8 +279,9 @@ static inline unsigned long virt_to_pfn(const void *kaddr) #define AMODE31_SIZE (3 * PAGE_SIZE) #define KERNEL_IMAGE_SIZE (512 * 1024 * 1024) -#define __START_KERNEL 0x100000 #define __NO_KASLR_START_KERNEL CONFIG_KERNEL_IMAGE_BASE #define __NO_KASLR_END_KERNEL (__NO_KASLR_START_KERNEL + KERNEL_IMAGE_SIZE) +#define TEXT_OFFSET 0x100000 + #endif /* _S390_PAGE_H */ diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index e67cd409b858..ae5d0a9d6911 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -39,7 +39,7 @@ PHDRS { SECTIONS { - . = __START_KERNEL; + . = TEXT_OFFSET; .text : { _stext = .; /* Start of text section */ _text = .; /* Text and read-only data */ diff --git a/arch/s390/tools/relocs.c b/arch/s390/tools/relocs.c index a74dbd5c9896..30a732c808f3 100644 --- a/arch/s390/tools/relocs.c +++ b/arch/s390/tools/relocs.c @@ -280,7 +280,7 @@ static int do_reloc(struct section *sec, Elf_Rel *rel) case R_390_GOTOFF64: break; case R_390_64: - add_reloc(&relocs64, offset - ehdr.e_entry); + add_reloc(&relocs64, offset); break; default: die("Unsupported relocation type: %d\n", r_type); From 15179cf2806f91685410e598f82813a7fcf90f6c Mon Sep 17 00:00:00 2001 From: Steve French Date: Fri, 16 Aug 2024 16:47:39 -0500 Subject: [PATCH 541/562] smb3: fix problem unloading module due to leaked refcount on shutdown The shutdown ioctl can leak a refcount on the tlink which can prevent rmmod (unloading the cifs.ko) module from working. Found while debugging xfstest generic/043 Fixes: 69ca1f57555f ("smb3: add dynamic tracepoints for shutdown ioctl") Reviewed-by: Meetakshi Setiya Reviewed-by: Shyam Prasad N Signed-off-by: Steve French --- fs/smb/client/connect.c | 3 +++ fs/smb/client/ioctl.c | 2 ++ fs/smb/client/link.c | 1 + 3 files changed, 6 insertions(+) diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index d2307162a2de..c1c14274930a 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -4194,6 +4194,9 @@ tlink_rb_insert(struct rb_root *root, struct tcon_link *new_tlink) * * If one doesn't exist then insert a new tcon_link struct into the tree and * try to construct a new one. + * + * REMEMBER to call cifs_put_tlink() after successful calls to cifs_sb_tlink, + * to avoid refcount issues */ struct tcon_link * cifs_sb_tlink(struct cifs_sb_info *cifs_sb) diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index 44dbaf9929a4..9bb5c869f4db 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -229,9 +229,11 @@ static int cifs_shutdown(struct super_block *sb, unsigned long arg) shutdown_good: trace_smb3_shutdown_done(flags, tcon->tid); + cifs_put_tlink(tlink); return 0; shutdown_out_err: trace_smb3_shutdown_err(rc, flags, tcon->tid); + cifs_put_tlink(tlink); return rc; } diff --git a/fs/smb/client/link.c b/fs/smb/client/link.c index d86da949a919..80099bbb333b 100644 --- a/fs/smb/client/link.c +++ b/fs/smb/client/link.c @@ -588,6 +588,7 @@ cifs_symlink(struct mnt_idmap *idmap, struct inode *inode, tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) { rc = PTR_ERR(tlink); + /* BB could be clearer if skipped put_tlink on error here, but harmless */ goto symlink_exit; } pTcon = tlink_tcon(tlink); From ec686804117a0421cf31d54427768aaf93aa0069 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Wed, 21 Aug 2024 00:45:03 -0300 Subject: [PATCH 542/562] smb: client: ignore unhandled reparse tags Just ignore reparse points that the client can't parse rather than bailing out and not opening the file or directory. Reported-by: Marc <1marc1@gmail.com> Closes: https://lore.kernel.org/r/CAMHwNVv-B+Q6wa0FEXrAuzdchzcJRsPKDDRrNaYZJd6X-+iJzw@mail.gmail.com Fixes: 539aad7f14da ("smb: client: introduce ->parse_reparse_point()") Tested-by: Anthony Nandaa (Microsoft) Signed-off-by: Paulo Alcantara (Red Hat) Signed-off-by: Steve French --- fs/smb/client/reparse.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 689d8a506d45..48c27581ec51 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -378,6 +378,8 @@ int parse_reparse_point(struct reparse_data_buffer *buf, u32 plen, struct cifs_sb_info *cifs_sb, bool unicode, struct cifs_open_info_data *data) { + struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + data->reparse.buf = buf; /* See MS-FSCC 2.1.2 */ @@ -394,12 +396,13 @@ int parse_reparse_point(struct reparse_data_buffer *buf, case IO_REPARSE_TAG_LX_FIFO: case IO_REPARSE_TAG_LX_CHR: case IO_REPARSE_TAG_LX_BLK: - return 0; + break; default: - cifs_dbg(VFS, "%s: unhandled reparse tag: 0x%08x\n", - __func__, le32_to_cpu(buf->ReparseTag)); - return -EOPNOTSUPP; + cifs_tcon_dbg(VFS | ONCE, "unhandled reparse tag: 0x%08x\n", + le32_to_cpu(buf->ReparseTag)); + break; } + return 0; } int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb, From 8fb4ac1cee88a57e7a56faba49b408a41a4af4db Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 18 Aug 2024 16:07:11 +0900 Subject: [PATCH 543/562] kbuild: fix typos "prequisites" to "prerequisites" This typo in scripts/Makefile.build has been present for more than 20 years. It was accidentally copy-pasted to other scripts/Makefile.* files. Fix them all. Signed-off-by: Masahiro Yamada Reviewed-by: Nathan Chancellor --- scripts/Makefile.build | 2 +- scripts/Makefile.modfinal | 2 +- scripts/Makefile.vmlinux | 2 +- scripts/Makefile.vmlinux_o | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index efacca63c897..a5ac8ed1936f 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -487,7 +487,7 @@ $(subdir-ym): need-modorder=$(if $(filter $@/modules.order, $(subdir-modorder)),1) \ $(filter $@/%, $(single-subdir-goals)) -# Add FORCE to the prequisites of a target to force it to be always rebuilt. +# Add FORCE to the prerequisites of a target to force it to be always rebuilt. # --------------------------------------------------------------------------- PHONY += FORCE diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal index 1fa98b5e952b..306a6bb86e4d 100644 --- a/scripts/Makefile.modfinal +++ b/scripts/Makefile.modfinal @@ -62,7 +62,7 @@ endif targets += $(modules:%.o=%.ko) $(modules:%.o=%.mod.o) -# Add FORCE to the prequisites of a target to force it to be always rebuilt. +# Add FORCE to the prerequisites of a target to force it to be always rebuilt. # --------------------------------------------------------------------------- PHONY += FORCE diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux index 49946cb96844..5ceecbed31eb 100644 --- a/scripts/Makefile.vmlinux +++ b/scripts/Makefile.vmlinux @@ -33,7 +33,7 @@ targets += vmlinux vmlinux: scripts/link-vmlinux.sh vmlinux.o $(KBUILD_LDS) FORCE +$(call if_changed_dep,link_vmlinux) -# Add FORCE to the prequisites of a target to force it to be always rebuilt. +# Add FORCE to the prerequisites of a target to force it to be always rebuilt. # --------------------------------------------------------------------------- PHONY += FORCE diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o index 6de297916ce6..d64070b6b4bc 100644 --- a/scripts/Makefile.vmlinux_o +++ b/scripts/Makefile.vmlinux_o @@ -87,7 +87,7 @@ targets += modules.builtin modules.builtin: modules.builtin.modinfo FORCE $(call if_changed,modules_builtin) -# Add FORCE to the prequisites of a target to force it to be always rebuilt. +# Add FORCE to the prerequisites of a target to force it to be always rebuilt. # --------------------------------------------------------------------------- PHONY += FORCE From afc954fd223ded70b1fa000767e2531db55cce58 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 14 Aug 2024 21:58:21 +0200 Subject: [PATCH 544/562] thermal: of: Fix OF node leak in thermal_of_trips_init() error path Terminating for_each_child_of_node() loop requires dropping OF node reference, so bailing out after thermal_of_populate_trip() error misses this. Solve the OF node reference leak with scoped for_each_child_of_node_scoped(). Fixes: d0c75fa2c17f ("thermal/of: Initialize trip points separately") Cc: All applicable Signed-off-by: Krzysztof Kozlowski Reviewed-by: Chen-Yu Tsai Reviewed-by: Daniel Lezcano Link: https://patch.msgid.link/20240814195823.437597-1-krzysztof.kozlowski@linaro.org Signed-off-by: Rafael J. Wysocki --- drivers/thermal/thermal_of.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c index aa34b6e82e26..30f8d6e70484 100644 --- a/drivers/thermal/thermal_of.c +++ b/drivers/thermal/thermal_of.c @@ -125,7 +125,7 @@ static int thermal_of_populate_trip(struct device_node *np, static struct thermal_trip *thermal_of_trips_init(struct device_node *np, int *ntrips) { struct thermal_trip *tt; - struct device_node *trips, *trip; + struct device_node *trips; int ret, count; trips = of_get_child_by_name(np, "trips"); @@ -150,7 +150,7 @@ static struct thermal_trip *thermal_of_trips_init(struct device_node *np, int *n *ntrips = count; count = 0; - for_each_child_of_node(trips, trip) { + for_each_child_of_node_scoped(trips, trip) { ret = thermal_of_populate_trip(trip, &tt[count++]); if (ret) goto out_kfree; From 662b52b761bfe0ba970e5823759798faf809b896 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 14 Aug 2024 21:58:22 +0200 Subject: [PATCH 545/562] thermal: of: Fix OF node leak in thermal_of_zone_register() thermal_of_zone_register() calls of_thermal_zone_find() which will iterate over OF nodes with for_each_available_child_of_node() to find matching thermal zone node. When it finds such, it exits the loop and returns the node. Prematurely ending for_each_available_child_of_node() loops requires dropping OF node reference, thus success of of_thermal_zone_find() means that caller must drop the reference. Fixes: 3fd6d6e2b4e8 ("thermal/of: Rework the thermal device tree initialization") Cc: All applicable Signed-off-by: Krzysztof Kozlowski Reviewed-by: Chen-Yu Tsai Reviewed-by: Daniel Lezcano Link: https://patch.msgid.link/20240814195823.437597-2-krzysztof.kozlowski@linaro.org Signed-off-by: Rafael J. Wysocki --- drivers/thermal/thermal_of.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c index 30f8d6e70484..b08a9b64718d 100644 --- a/drivers/thermal/thermal_of.c +++ b/drivers/thermal/thermal_of.c @@ -491,7 +491,8 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node * trips = thermal_of_trips_init(np, &ntrips); if (IS_ERR(trips)) { pr_err("Failed to find trip points for %pOFn id=%d\n", sensor, id); - return ERR_CAST(trips); + ret = PTR_ERR(trips); + goto out_of_node_put; } ret = thermal_of_monitor_init(np, &delay, &pdelay); @@ -519,6 +520,7 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node * goto out_kfree_trips; } + of_node_put(np); kfree(trips); ret = thermal_zone_device_enable(tz); @@ -533,6 +535,8 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node * out_kfree_trips: kfree(trips); +out_of_node_put: + of_node_put(np); return ERR_PTR(ret); } From c0a1ef9c5be72ff28a5413deb1b3e1a066593c13 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 14 Aug 2024 21:58:23 +0200 Subject: [PATCH 546/562] thermal: of: Fix OF node leak in of_thermal_zone_find() error paths Terminating for_each_available_child_of_node() loop requires dropping OF node reference, so bailing out on errors misses this. Solve the OF node reference leak with scoped for_each_available_child_of_node_scoped(). Fixes: 3fd6d6e2b4e8 ("thermal/of: Rework the thermal device tree initialization") Cc: Signed-off-by: Krzysztof Kozlowski Reviewed-by: Chen-Yu Tsai Reviewed-by: Daniel Lezcano Link: https://patch.msgid.link/20240814195823.437597-3-krzysztof.kozlowski@linaro.org Signed-off-by: Rafael J. Wysocki --- drivers/thermal/thermal_of.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c index b08a9b64718d..1f252692815a 100644 --- a/drivers/thermal/thermal_of.c +++ b/drivers/thermal/thermal_of.c @@ -184,14 +184,14 @@ static struct device_node *of_thermal_zone_find(struct device_node *sensor, int * Search for each thermal zone, a defined sensor * corresponding to the one passed as parameter */ - for_each_available_child_of_node(np, tz) { + for_each_available_child_of_node_scoped(np, child) { int count, i; - count = of_count_phandle_with_args(tz, "thermal-sensors", + count = of_count_phandle_with_args(child, "thermal-sensors", "#thermal-sensor-cells"); if (count <= 0) { - pr_err("%pOFn: missing thermal sensor\n", tz); + pr_err("%pOFn: missing thermal sensor\n", child); tz = ERR_PTR(-EINVAL); goto out; } @@ -200,18 +200,19 @@ static struct device_node *of_thermal_zone_find(struct device_node *sensor, int int ret; - ret = of_parse_phandle_with_args(tz, "thermal-sensors", + ret = of_parse_phandle_with_args(child, "thermal-sensors", "#thermal-sensor-cells", i, &sensor_specs); if (ret < 0) { - pr_err("%pOFn: Failed to read thermal-sensors cells: %d\n", tz, ret); + pr_err("%pOFn: Failed to read thermal-sensors cells: %d\n", child, ret); tz = ERR_PTR(ret); goto out; } if ((sensor == sensor_specs.np) && id == (sensor_specs.args_count ? sensor_specs.args[0] : 0)) { - pr_debug("sensor %pOFn id=%d belongs to %pOFn\n", sensor, id, tz); + pr_debug("sensor %pOFn id=%d belongs to %pOFn\n", sensor, id, child); + tz = no_free_ptr(child); goto out; } } From 4ae738dfef2c0323752ab81786e2d298c9939321 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Thu, 22 Aug 2024 11:40:55 -0400 Subject: [PATCH 547/562] net: xilinx: axienet: Always disable promiscuous mode If promiscuous mode is disabled when there are fewer than four multicast addresses, then it will not be reflected in the hardware. Fix this by always clearing the promiscuous mode flag even when we program multicast addresses. Fixes: 8a3b7a252dca ("drivers/net/ethernet/xilinx: added Xilinx AXI Ethernet driver") Signed-off-by: Sean Anderson Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240822154059.1066595-2-sean.anderson@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 02fdf66e07fa..163d05248007 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -450,6 +450,10 @@ static void axienet_set_multicast_list(struct net_device *ndev) } else if (!netdev_mc_empty(ndev)) { struct netdev_hw_addr *ha; + reg = axienet_ior(lp, XAE_FMI_OFFSET); + reg &= ~XAE_FMI_PM_MASK; + axienet_iow(lp, XAE_FMI_OFFSET, reg); + i = 0; netdev_for_each_mc_addr(ha, ndev) { if (i >= XAE_MULTICAST_CAM_TABLE_NUM) From 797a68c9de0f5a5447baf4bd3bb9c10a3993435b Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Thu, 22 Aug 2024 11:40:56 -0400 Subject: [PATCH 548/562] net: xilinx: axienet: Fix dangling multicast addresses If a multicast address is removed but there are still some multicast addresses, that address would remain programmed into the frame filter. Fix this by explicitly setting the enable bit for each filter. Fixes: 8a3b7a252dca ("drivers/net/ethernet/xilinx: added Xilinx AXI Ethernet driver") Signed-off-by: Sean Anderson Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240822154059.1066595-3-sean.anderson@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/xilinx/xilinx_axienet.h | 1 + .../net/ethernet/xilinx/xilinx_axienet_main.c | 21 ++++++++----------- 2 files changed, 10 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index c7d9221fafdc..09c9f9787180 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -170,6 +170,7 @@ #define XAE_UAW0_OFFSET 0x00000700 /* Unicast address word 0 */ #define XAE_UAW1_OFFSET 0x00000704 /* Unicast address word 1 */ #define XAE_FMI_OFFSET 0x00000708 /* Frame Filter Control */ +#define XAE_FFE_OFFSET 0x0000070C /* Frame Filter Enable */ #define XAE_AF0_OFFSET 0x00000710 /* Address Filter 0 */ #define XAE_AF1_OFFSET 0x00000714 /* Address Filter 1 */ diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 163d05248007..9aeb7b9f3ae4 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -432,7 +432,7 @@ static int netdev_set_mac_address(struct net_device *ndev, void *p) */ static void axienet_set_multicast_list(struct net_device *ndev) { - int i; + int i = 0; u32 reg, af0reg, af1reg; struct axienet_local *lp = netdev_priv(ndev); @@ -454,7 +454,6 @@ static void axienet_set_multicast_list(struct net_device *ndev) reg &= ~XAE_FMI_PM_MASK; axienet_iow(lp, XAE_FMI_OFFSET, reg); - i = 0; netdev_for_each_mc_addr(ha, ndev) { if (i >= XAE_MULTICAST_CAM_TABLE_NUM) break; @@ -473,6 +472,7 @@ static void axienet_set_multicast_list(struct net_device *ndev) axienet_iow(lp, XAE_FMI_OFFSET, reg); axienet_iow(lp, XAE_AF0_OFFSET, af0reg); axienet_iow(lp, XAE_AF1_OFFSET, af1reg); + axienet_iow(lp, XAE_FFE_OFFSET, 1); i++; } } else { @@ -480,18 +480,15 @@ static void axienet_set_multicast_list(struct net_device *ndev) reg &= ~XAE_FMI_PM_MASK; axienet_iow(lp, XAE_FMI_OFFSET, reg); - - for (i = 0; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) { - reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00; - reg |= i; - - axienet_iow(lp, XAE_FMI_OFFSET, reg); - axienet_iow(lp, XAE_AF0_OFFSET, 0); - axienet_iow(lp, XAE_AF1_OFFSET, 0); - } - dev_info(&ndev->dev, "Promiscuous mode disabled.\n"); } + + for (; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) { + reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00; + reg |= i; + axienet_iow(lp, XAE_FMI_OFFSET, reg); + axienet_iow(lp, XAE_FFE_OFFSET, 0); + } } /** From 57fb67783c4011581882f32e656d738da1f82042 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 21 Aug 2024 20:32:52 +0800 Subject: [PATCH 549/562] net: ovs: fix ovs_drop_reasons error There is something wrong with ovs_drop_reasons. ovs_drop_reasons[0] is "OVS_DROP_LAST_ACTION", but OVS_DROP_LAST_ACTION == __OVS_DROP_REASON + 1, which means that ovs_drop_reasons[1] should be "OVS_DROP_LAST_ACTION". And as Adrian tested, without the patch, adding flow to drop packets results in: drop at: do_execute_actions+0x197/0xb20 [openvsw (0xffffffffc0db6f97) origin: software input port ifindex: 8 timestamp: Tue Aug 20 10:19:17 2024 859853461 nsec protocol: 0x800 length: 98 original length: 98 drop reason: OVS_DROP_ACTION_ERROR With the patch, the same results in: drop at: do_execute_actions+0x197/0xb20 [openvsw (0xffffffffc0db6f97) origin: software input port ifindex: 8 timestamp: Tue Aug 20 10:16:13 2024 475856608 nsec protocol: 0x800 length: 98 original length: 98 drop reason: OVS_DROP_LAST_ACTION Fix this by initializing ovs_drop_reasons with index. Fixes: 9d802da40b7c ("net: openvswitch: add last-action drop reason") Signed-off-by: Menglong Dong Tested-by: Adrian Moreno Reviewed-by: Adrian Moreno Link: https://patch.msgid.link/20240821123252.186305-1-dongml2@chinatelecom.cn Signed-off-by: Jakub Kicinski --- net/openvswitch/datapath.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 99d72543abd3..78d9961fcd44 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2706,7 +2706,7 @@ static struct pernet_operations ovs_net_ops = { }; static const char * const ovs_drop_reasons[] = { -#define S(x) (#x), +#define S(x) [(x) & ~SKB_DROP_REASON_SUBSYS_MASK] = (#x), OVS_DROP_REASONS(S) #undef S }; From 0124fb0ebf3b0ef89892d42147c9387be3105318 Mon Sep 17 00:00:00 2001 From: Alexandra Winter Date: Wed, 21 Aug 2024 11:13:37 +0200 Subject: [PATCH 550/562] s390/iucv: Fix vargs handling in iucv_alloc_device() iucv_alloc_device() gets a format string and a varying number of arguments. This is incorrectly forwarded by calling dev_set_name() with the format string and a va_list, while dev_set_name() expects also a varying number of arguments. Symptoms: Corrupted iucv device names, which can result in log messages like: sysfs: cannot create duplicate filename '/devices/iucv/hvc_iucv1827699952' Fixes: 4452e8ef8c36 ("s390/iucv: Provide iucv_alloc_device() / iucv_release_device()") Link: https://bugzilla.suse.com/show_bug.cgi?id=1228425 Signed-off-by: Alexandra Winter Reviewed-by: Thorsten Winkler Reviewed-by: Przemek Kitszel Link: https://patch.msgid.link/20240821091337.3627068-1-wintera@linux.ibm.com Signed-off-by: Jakub Kicinski --- net/iucv/iucv.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 1e42e13ad24e..d3e9efab7f4b 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -86,13 +86,15 @@ struct device *iucv_alloc_device(const struct attribute_group **attrs, { struct device *dev; va_list vargs; + char buf[20]; int rc; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) goto out_error; va_start(vargs, fmt); - rc = dev_set_name(dev, fmt, vargs); + vsnprintf(buf, sizeof(buf), fmt, vargs); + rc = dev_set_name(dev, "%s", buf); va_end(vargs); if (rc) goto out_error; From a54a93d0e3599b05856971734e15418ac551a14c Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 13 Aug 2024 09:35:27 +0800 Subject: [PATCH 551/562] nvme: move stopping keep-alive into nvme_uninit_ctrl() Commit 4733b65d82bd ("nvme: start keep-alive after admin queue setup") moves starting keep-alive from nvme_start_ctrl() into nvme_init_ctrl_finish(), but don't move stopping keep-alive into nvme_uninit_ctrl(), so keep-alive work can be started and keep pending after failing to start controller, finally use-after-free is triggered if nvme host driver is unloaded. This patch fixes kernel panic when running nvme/004 in case that connection failure is triggered, by moving stopping keep-alive into nvme_uninit_ctrl(). This way is reasonable because keep-alive is now started in nvme_init_ctrl_finish(). Fixes: 3af755a46881 ("nvme: move nvme_stop_keep_alive() back to original position") Cc: Hannes Reinecke Cc: Mark O'Donovan Reported-by: Changhui Zhong Reviewed-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Reviewed-by: Hannes Reinecke Signed-off-by: Ming Lei Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 33fa01c599ad..0dc8bcc664f2 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4612,7 +4612,6 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl) { nvme_mpath_stop(ctrl); nvme_auth_stop(ctrl); - nvme_stop_keep_alive(ctrl); nvme_stop_failfast_work(ctrl); flush_work(&ctrl->async_event_work); cancel_work_sync(&ctrl->fw_act_work); @@ -4648,6 +4647,7 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl); void nvme_uninit_ctrl(struct nvme_ctrl *ctrl) { + nvme_stop_keep_alive(ctrl); nvme_hwmon_exit(ctrl); nvme_fault_inject_fini(&ctrl->fault_inject); dev_pm_qos_hide_latency_tolerance(ctrl->device); From fe01751347359862c65c715d51c0b3f4fa8ee2f0 Mon Sep 17 00:00:00 2001 From: Nilay Shroff Date: Wed, 14 Aug 2024 19:26:50 +0530 Subject: [PATCH 552/562] nvme: Remove unused field The "name" field in struct nvme_ctrl is unsued so removing it. This would help save 12 bytes of space for each nvme_ctrl instance created. Signed-off-by: Nilay Shroff Reviewed-by: Kanchan Joshi Signed-off-by: Keith Busch --- drivers/nvme/host/nvme.h | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index ae5314d32943..da57947130cc 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -301,7 +301,6 @@ struct nvme_ctrl { struct opal_dev *opal_dev; - char name[12]; u16 cntlid; u16 mtfa; From 5e51224d2afbda57f33f47485871ee5532145e18 Mon Sep 17 00:00:00 2001 From: ChenXiaoSong Date: Tue, 20 Aug 2024 14:33:15 +0000 Subject: [PATCH 553/562] smb/client: fix typo: GlobalMid_Sem -> GlobalMid_Lock The comments have typos, fix that to not confuse readers. Signed-off-by: ChenXiaoSong Reviewed-by: Namjae Jeon --- fs/smb/client/cifsfs.c | 6 +++--- fs/smb/client/cifsglob.h | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 2c4b357d85e2..d89485235425 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -75,9 +75,9 @@ unsigned int sign_CIFS_PDUs = 1; /* * Global transaction id (XID) information */ -unsigned int GlobalCurrentXid; /* protected by GlobalMid_Sem */ -unsigned int GlobalTotalActiveXid; /* prot by GlobalMid_Sem */ -unsigned int GlobalMaxActiveXid; /* prot by GlobalMid_Sem */ +unsigned int GlobalCurrentXid; /* protected by GlobalMid_Lock */ +unsigned int GlobalTotalActiveXid; /* prot by GlobalMid_Lock */ +unsigned int GlobalMaxActiveXid; /* prot by GlobalMid_Lock */ spinlock_t GlobalMid_Lock; /* protects above & list operations on midQ entries */ /* diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 5c9b3e6cd95f..7ebe80a25d04 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -2017,9 +2017,9 @@ extern spinlock_t cifs_tcp_ses_lock; /* * Global transaction id (XID) information */ -extern unsigned int GlobalCurrentXid; /* protected by GlobalMid_Sem */ -extern unsigned int GlobalTotalActiveXid; /* prot by GlobalMid_Sem */ -extern unsigned int GlobalMaxActiveXid; /* prot by GlobalMid_Sem */ +extern unsigned int GlobalCurrentXid; /* protected by GlobalMid_Lock */ +extern unsigned int GlobalTotalActiveXid; /* prot by GlobalMid_Lock */ +extern unsigned int GlobalMaxActiveXid; /* prot by GlobalMid_Lock */ extern spinlock_t GlobalMid_Lock; /* protects above & list operations on midQ entries */ /* From cb78f9b7d0c0c9f86d8c0ac9c46b8b684d8785a9 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 15 Aug 2024 10:18:41 -0400 Subject: [PATCH 554/562] nfs: fix the fetch of FATTR4_OPEN_ARGUMENTS The client doesn't properly request FATTR4_OPEN_ARGUMENTS in the initial SERVER_CAPS getattr. Add FATTR4_WORD2_OPEN_ARGUMENTS to the initial request. Fixes: 707f13b3d081 (NFSv4: Add support for the FATTR4_OPEN_ARGUMENTS attribute) Signed-off-by: Jeff Layton Reviewed-by: Benjamin Coddington Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 8883016c551c..06df74362e94 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3931,7 +3931,8 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f FATTR4_WORD0_CASE_INSENSITIVE | FATTR4_WORD0_CASE_PRESERVING; if (minorversion) - bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT; + bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT | + FATTR4_WORD2_OPEN_ARGUMENTS; status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); if (status == 0) { From 95832998fb6edc50d4f2f6a958d9f90142d4be48 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 21 Aug 2024 08:28:25 -0400 Subject: [PATCH 555/562] nfs: fix bitmap decoder to handle a 3rd word It only decodes the first two words at this point. Have it decode the third word as well. Without this, the client doesn't send delegated timestamps in the CB_GETATTR response. With this change we also need to expand the on-stack bitmap in decode_recallany_args to 3 elements, in case the server sends a larger bitmap than expected. Fixes: 43df7110f4a9 ("NFSv4: Add CB_GETATTR support for delegated attributes") Signed-off-by: Jeff Layton Reviewed-by: Benjamin Coddington Signed-off-by: Anna Schumaker --- fs/nfs/callback_xdr.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 29c49a7e5fe1..6df77f008d3f 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -118,7 +118,9 @@ static __be32 decode_bitmap(struct xdr_stream *xdr, uint32_t *bitmap) if (likely(attrlen > 0)) bitmap[0] = ntohl(*p++); if (attrlen > 1) - bitmap[1] = ntohl(*p); + bitmap[1] = ntohl(*p++); + if (attrlen > 2) + bitmap[2] = ntohl(*p); return 0; } @@ -446,7 +448,7 @@ static __be32 decode_recallany_args(struct svc_rqst *rqstp, void *argp) { struct cb_recallanyargs *args = argp; - uint32_t bitmap[2]; + uint32_t bitmap[3]; __be32 *p, status; p = xdr_inline_decode(xdr, 4); From a017ad1313fc91bdf235097fd0a02f673fc7bb11 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 21 Aug 2024 14:05:00 -0400 Subject: [PATCH 556/562] NFSv4: Add missing rescheduling points in nfs_client_return_marked_delegations We're seeing reports of soft lockups when iterating through the loops, so let's add rescheduling points. Signed-off-by: Trond Myklebust Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfs/super.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index cbbd4866b0b7..97b386032b71 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include #include @@ -228,6 +229,7 @@ static int __nfs_list_for_each_server(struct list_head *head, ret = fn(server, data); if (ret) goto out; + cond_resched(); rcu_read_lock(); } rcu_read_unlock(); From d72b7963115bea971a28eaa2cb76722c023f9fdf Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 21 Aug 2024 14:05:01 -0400 Subject: [PATCH 557/562] NFSv4: Fix clearing of layout segments in layoutreturn Make sure that we clear the layout segments in cases where we see a fatal error, and also in the case where the layout is invalid. Signed-off-by: Trond Myklebust Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 9 ++++++--- fs/nfs/pnfs.c | 5 ++--- 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 06df74362e94..b8ffbe52ba15 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -9998,6 +9998,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) fallthrough; default: task->tk_status = 0; + lrp->res.lrs_present = 0; fallthrough; case 0: break; @@ -10011,9 +10012,11 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) task->tk_status = 0; break; case -NFS4ERR_DELAY: - if (nfs4_async_handle_error(task, server, NULL, NULL) != -EAGAIN) - break; - goto out_restart; + if (nfs4_async_handle_error(task, server, NULL, NULL) == + -EAGAIN) + goto out_restart; + lrp->res.lrs_present = 0; + break; } return; out_restart: diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index aa698481bec8..0d16b383a452 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1284,10 +1284,9 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo, LIST_HEAD(freeme); spin_lock(&inode->i_lock); - if (!pnfs_layout_is_valid(lo) || - !nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid)) + if (!nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid)) goto out_unlock; - if (stateid) { + if (stateid && pnfs_layout_is_valid(lo)) { u32 seq = be32_to_cpu(arg_stateid->seqid); pnfs_mark_matching_lsegs_invalid(lo, &freeme, range, seq); From f92214e4c312f6ea9d78650cc6291d200f17abb6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 21 Aug 2024 14:05:02 -0400 Subject: [PATCH 558/562] NFS: Avoid unnecessary rescanning of the per-server delegation list If the call to nfs_delegation_grab_inode() fails, we will not have dropped any locks that require us to rescan the list. Signed-off-by: Trond Myklebust Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfs/delegation.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index d5edb3b3eeef..20cb2008f9e4 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -647,6 +647,9 @@ restart: prev = delegation; continue; } + inode = nfs_delegation_grab_inode(delegation); + if (inode == NULL) + continue; if (prev) { struct inode *tmp = nfs_delegation_grab_inode(prev); @@ -657,12 +660,6 @@ restart: } } - inode = nfs_delegation_grab_inode(delegation); - if (inode == NULL) { - rcu_read_unlock(); - iput(to_put); - goto restart; - } delegation = nfs_start_delegation_return_locked(NFS_I(inode)); rcu_read_unlock(); @@ -1184,7 +1181,6 @@ static int nfs_server_reap_unclaimed_delegations(struct nfs_server *server, struct inode *inode; restart: rcu_read_lock(); -restart_locked: list_for_each_entry_rcu(delegation, &server->delegations, super_list) { if (test_bit(NFS_DELEGATION_INODE_FREEING, &delegation->flags) || @@ -1195,7 +1191,7 @@ restart_locked: continue; inode = nfs_delegation_grab_inode(delegation); if (inode == NULL) - goto restart_locked; + continue; delegation = nfs_start_delegation_return_locked(NFS_I(inode)); rcu_read_unlock(); if (delegation != NULL) { @@ -1318,7 +1314,6 @@ static int nfs_server_reap_expired_delegations(struct nfs_server *server, restart: rcu_read_lock(); -restart_locked: list_for_each_entry_rcu(delegation, &server->delegations, super_list) { if (test_bit(NFS_DELEGATION_INODE_FREEING, &delegation->flags) || @@ -1330,7 +1325,7 @@ restart_locked: continue; inode = nfs_delegation_grab_inode(delegation); if (inode == NULL) - goto restart_locked; + continue; spin_lock(&delegation->lock); cred = get_cred_rcu(delegation->cred); nfs4_stateid_copy(&stateid, &delegation->stateid); From d3204616a67e53fdcad14c7026869330fb382fd4 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 23 Aug 2024 17:38:41 -0400 Subject: [PATCH 559/562] bcachefs: Fix failure to flush moves before sleeping in copygc This fixes an apparent deadlock - rebalance would get stuck trying to take nocow locks because they weren't being released by copygc. Signed-off-by: Kent Overstreet --- fs/bcachefs/movinggc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c index deef4f024d20..d86565bf07c8 100644 --- a/fs/bcachefs/movinggc.c +++ b/fs/bcachefs/movinggc.c @@ -383,7 +383,7 @@ static int bch2_copygc_thread(void *arg) if (min_member_capacity == U64_MAX) min_member_capacity = 128 * 2048; - bch2_trans_unlock_long(ctxt.trans); + move_buckets_wait(&ctxt, buckets, true); bch2_kthread_io_clock_wait(clock, last + (min_member_capacity >> 6), MAX_SCHEDULE_TIMEOUT); } From 49aa7830396bce33b00fa7ee734c35de36521138 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 23 Aug 2024 15:35:22 -0400 Subject: [PATCH 560/562] bcachefs: Fix rebalance_work accounting rebalance_work was keying off of the presence of rebelance_opts in the extent - but that was incorrect, we keep those around after rebalance for indirect extents since the inode's options are not directly available Fixes: 20ac515a9cc7 ("bcachefs: bch_acct_rebalance_work") Signed-off-by: Kent Overstreet --- fs/bcachefs/bcachefs_format.h | 3 +- fs/bcachefs/buckets.c | 74 +++++++++++++++++++++++------------ fs/bcachefs/extents.c | 39 ++++++++++++++++++ fs/bcachefs/extents.h | 1 + fs/bcachefs/sb-downgrade.c | 8 +++- 5 files changed, 98 insertions(+), 27 deletions(-) diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index c75f2e0f32bb..14ce726bf5a3 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -677,7 +677,8 @@ struct bch_sb_field_ext { x(bucket_stripe_sectors, BCH_VERSION(1, 8)) \ x(disk_accounting_v2, BCH_VERSION(1, 9)) \ x(disk_accounting_v3, BCH_VERSION(1, 10)) \ - x(disk_accounting_inum, BCH_VERSION(1, 11)) + x(disk_accounting_inum, BCH_VERSION(1, 11)) \ + x(rebalance_work_acct_fix, BCH_VERSION(1, 12)) enum bcachefs_metadata_version { bcachefs_metadata_version_min = 9, diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index be2bbd248631..a2274429e7f4 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -699,7 +699,8 @@ err: static int __trigger_extent(struct btree_trans *trans, enum btree_id btree_id, unsigned level, struct bkey_s_c k, - enum btree_iter_update_trigger_flags flags) + enum btree_iter_update_trigger_flags flags, + s64 *replicas_sectors) { bool gc = flags & BTREE_TRIGGER_gc; struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); @@ -708,7 +709,6 @@ static int __trigger_extent(struct btree_trans *trans, enum bch_data_type data_type = bkey_is_btree_ptr(k.k) ? BCH_DATA_btree : BCH_DATA_user; - s64 replicas_sectors = 0; int ret = 0; struct disk_accounting_pos acc_replicas_key = { @@ -739,7 +739,7 @@ static int __trigger_extent(struct btree_trans *trans, if (ret) return ret; } else if (!p.has_ec) { - replicas_sectors += disk_sectors; + *replicas_sectors += disk_sectors; acc_replicas_key.replicas.devs[acc_replicas_key.replicas.nr_devs++] = p.ptr.dev; } else { ret = bch2_trigger_stripe_ptr(trans, k, p, data_type, disk_sectors, flags); @@ -777,7 +777,7 @@ static int __trigger_extent(struct btree_trans *trans, } if (acc_replicas_key.replicas.nr_devs) { - ret = bch2_disk_accounting_mod(trans, &acc_replicas_key, &replicas_sectors, 1, gc); + ret = bch2_disk_accounting_mod(trans, &acc_replicas_key, replicas_sectors, 1, gc); if (ret) return ret; } @@ -787,7 +787,7 @@ static int __trigger_extent(struct btree_trans *trans, .type = BCH_DISK_ACCOUNTING_snapshot, .snapshot.id = k.k->p.snapshot, }; - ret = bch2_disk_accounting_mod(trans, &acc_snapshot_key, &replicas_sectors, 1, gc); + ret = bch2_disk_accounting_mod(trans, &acc_snapshot_key, replicas_sectors, 1, gc); if (ret) return ret; } @@ -807,7 +807,7 @@ static int __trigger_extent(struct btree_trans *trans, .type = BCH_DISK_ACCOUNTING_btree, .btree.id = btree_id, }; - ret = bch2_disk_accounting_mod(trans, &acc_btree_key, &replicas_sectors, 1, gc); + ret = bch2_disk_accounting_mod(trans, &acc_btree_key, replicas_sectors, 1, gc); if (ret) return ret; } else { @@ -819,22 +819,13 @@ static int __trigger_extent(struct btree_trans *trans, s64 v[3] = { insert ? 1 : -1, insert ? k.k->size : -((s64) k.k->size), - replicas_sectors, + *replicas_sectors, }; ret = bch2_disk_accounting_mod(trans, &acc_inum_key, v, ARRAY_SIZE(v), gc); if (ret) return ret; } - if (bch2_bkey_rebalance_opts(k)) { - struct disk_accounting_pos acc = { - .type = BCH_DISK_ACCOUNTING_rebalance_work, - }; - ret = bch2_disk_accounting_mod(trans, &acc, &replicas_sectors, 1, gc); - if (ret) - return ret; - } - return 0; } @@ -843,6 +834,7 @@ int bch2_trigger_extent(struct btree_trans *trans, struct bkey_s_c old, struct bkey_s new, enum btree_iter_update_trigger_flags flags) { + struct bch_fs *c = trans->c; struct bkey_ptrs_c new_ptrs = bch2_bkey_ptrs_c(new.s_c); struct bkey_ptrs_c old_ptrs = bch2_bkey_ptrs_c(old); unsigned new_ptrs_bytes = (void *) new_ptrs.end - (void *) new_ptrs.start; @@ -858,22 +850,54 @@ int bch2_trigger_extent(struct btree_trans *trans, new_ptrs_bytes)) return 0; - if (flags & BTREE_TRIGGER_transactional) { - struct bch_fs *c = trans->c; - int mod = (int) bch2_bkey_needs_rebalance(c, new.s_c) - - (int) bch2_bkey_needs_rebalance(c, old); + if (flags & (BTREE_TRIGGER_transactional|BTREE_TRIGGER_gc)) { + s64 old_replicas_sectors = 0, new_replicas_sectors = 0; - if (mod) { + if (old.k->type) { + int ret = __trigger_extent(trans, btree, level, old, + flags & ~BTREE_TRIGGER_insert, + &old_replicas_sectors); + if (ret) + return ret; + } + + if (new.k->type) { + int ret = __trigger_extent(trans, btree, level, new.s_c, + flags & ~BTREE_TRIGGER_overwrite, + &new_replicas_sectors); + if (ret) + return ret; + } + + int need_rebalance_delta = 0; + s64 need_rebalance_sectors_delta = 0; + + s64 s = bch2_bkey_sectors_need_rebalance(c, old); + need_rebalance_delta -= s != 0; + need_rebalance_sectors_delta -= s; + + s = bch2_bkey_sectors_need_rebalance(c, old); + need_rebalance_delta += s != 0; + need_rebalance_sectors_delta += s; + + if ((flags & BTREE_TRIGGER_transactional) && need_rebalance_delta) { int ret = bch2_btree_bit_mod_buffered(trans, BTREE_ID_rebalance_work, - new.k->p, mod > 0); + new.k->p, need_rebalance_delta > 0); + if (ret) + return ret; + } + + if (need_rebalance_sectors_delta) { + struct disk_accounting_pos acc = { + .type = BCH_DISK_ACCOUNTING_rebalance_work, + }; + int ret = bch2_disk_accounting_mod(trans, &acc, &need_rebalance_sectors_delta, 1, + flags & BTREE_TRIGGER_gc); if (ret) return ret; } } - if (flags & (BTREE_TRIGGER_transactional|BTREE_TRIGGER_gc)) - return trigger_run_overwrite_then_insert(__trigger_extent, trans, btree, level, old, new, flags); - return 0; } diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index 9406f82fc255..e317df3644a1 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -1379,6 +1379,45 @@ bool bch2_bkey_needs_rebalance(struct bch_fs *c, struct bkey_s_c k) return r != NULL; } +static u64 __bch2_bkey_sectors_need_rebalance(struct bch_fs *c, struct bkey_s_c k, + unsigned target, unsigned compression) +{ + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + const union bch_extent_entry *entry; + struct extent_ptr_decoded p; + u64 sectors = 0; + + if (compression) { + unsigned compression_type = bch2_compression_opt_to_type(compression); + + bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { + if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible || + p.ptr.unwritten) { + sectors = 0; + goto incompressible; + } + + if (!p.ptr.cached && p.crc.compression_type != compression_type) + sectors += p.crc.compressed_size; + } + } +incompressible: + if (target && bch2_target_accepts_data(c, BCH_DATA_user, target)) { + bkey_for_each_ptr_decode(k.k, ptrs, p, entry) + if (!p.ptr.cached && !bch2_dev_in_target(c, p.ptr.dev, target)) + sectors += p.crc.compressed_size; + } + + return sectors; +} + +u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *c, struct bkey_s_c k) +{ + const struct bch_extent_rebalance *r = bch2_bkey_rebalance_opts(k); + + return r ? __bch2_bkey_sectors_need_rebalance(c, k, r->target, r->compression) : 0; +} + int bch2_bkey_set_needs_rebalance(struct bch_fs *c, struct bkey_i *_k, struct bch_io_opts *opts) { diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h index 1a6ddee48041..709dd83183be 100644 --- a/fs/bcachefs/extents.h +++ b/fs/bcachefs/extents.h @@ -692,6 +692,7 @@ const struct bch_extent_rebalance *bch2_bkey_rebalance_opts(struct bkey_s_c); unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *, struct bkey_s_c, unsigned, unsigned); bool bch2_bkey_needs_rebalance(struct bch_fs *, struct bkey_s_c); +u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *, struct bkey_s_c); int bch2_bkey_set_needs_rebalance(struct bch_fs *, struct bkey_i *, struct bch_io_opts *); diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index 650a1f77ca40..c7e4cdd3f6a5 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -74,6 +74,9 @@ BCH_FSCK_ERR_accounting_key_replicas_devs_unsorted, \ BCH_FSCK_ERR_accounting_key_junk_at_end) \ x(disk_accounting_inum, \ + BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ + BCH_FSCK_ERR_accounting_mismatch) \ + x(rebalance_work_acct_fix, \ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ BCH_FSCK_ERR_accounting_mismatch) @@ -108,7 +111,10 @@ BCH_FSCK_ERR_fs_usage_persistent_reserved_wrong, \ BCH_FSCK_ERR_fs_usage_replicas_wrong, \ BCH_FSCK_ERR_accounting_replicas_not_marked, \ - BCH_FSCK_ERR_bkey_version_in_future) + BCH_FSCK_ERR_bkey_version_in_future) \ + x(rebalance_work_acct_fix, \ + BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ + BCH_FSCK_ERR_accounting_mismatch) struct upgrade_downgrade_entry { u64 recovery_passes; From 5be63fc19fcaa4c236b307420483578a56986a37 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 25 Aug 2024 19:07:11 +1200 Subject: [PATCH 561/562] Linux 6.11-rc5 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 2c1db7a6f793..7b60eb103c5d 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 11 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Baby Opossum Posse # *DOCUMENTATION* From b2f44814680b569be98e58111bd582fd3a689d4d Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Tue, 6 Aug 2024 17:34:46 -0700 Subject: [PATCH 562/562] iommufd/device: Enforce reserved IOVA also when attached to hwpt_nested Currently, device reserved regions are only enforced when the device is attached to an hwpt_paging. In other words, if the device gets attached to an hwpt_nested directly, the parent hwpt_paging of the hwpt_nested's would not enforce those reserved IOVAs. This works for most of reserved region types, but not for IOMMU_RESV_SW_MSI, which is a unique software defined window, required by a nesting case too to setup an MSI doorbell on the parent stage-2 hwpt/domain. Kevin pointed out in 1 that: 1) there is no usage using up closely the entire IOVA space yet, 2) guest may change the viommu mode to switch between nested and paging then VMM has to take all devices' reserved regions into consideration anyway, when composing the GPA space. So it would be actually convenient for us to also enforce reserved IOVA onto the parent hwpt_paging, when attaching a device to an hwpt_nested. Repurpose the existing attach/replace_paging helpers to attach device's reserved IOVAs exclusively. Add a new find_hwpt_paging helper, which is only used by these reserved IOVA functions, to allow an IOMMUFD_OBJ_HWPT_NESTED hwpt to redirect to its parent hwpt_paging. Return a NULL in these two helpers for any new HWPT type in the future. Link: https://patch.msgid.link/r/20240807003446.3740368-1-nicolinc@nvidia.com Link: https://lore.kernel.org/all/BN9PR11MB5276497781C96415272E6FED8CB12@BN9PR11MB5276.namprd11.prod.outlook.com/ #1 Suggested-by: Kevin Tian Signed-off-by: Nicolin Chen Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/device.c | 52 ++++++++++++------------- drivers/iommu/iommufd/iommufd_private.h | 19 +++++++++ 2 files changed, 45 insertions(+), 26 deletions(-) diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index 3214a4c17c6b..bcbcd6d94062 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -327,8 +327,9 @@ static int iommufd_group_setup_msi(struct iommufd_group *igroup, return 0; } -static int iommufd_hwpt_paging_attach(struct iommufd_hwpt_paging *hwpt_paging, - struct iommufd_device *idev) +static int +iommufd_device_attach_reserved_iova(struct iommufd_device *idev, + struct iommufd_hwpt_paging *hwpt_paging) { int rc; @@ -354,6 +355,7 @@ static int iommufd_hwpt_paging_attach(struct iommufd_hwpt_paging *hwpt_paging, int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt, struct iommufd_device *idev) { + struct iommufd_hwpt_paging *hwpt_paging = find_hwpt_paging(hwpt); int rc; mutex_lock(&idev->igroup->lock); @@ -363,8 +365,8 @@ int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt, goto err_unlock; } - if (hwpt_is_paging(hwpt)) { - rc = iommufd_hwpt_paging_attach(to_hwpt_paging(hwpt), idev); + if (hwpt_paging) { + rc = iommufd_device_attach_reserved_iova(idev, hwpt_paging); if (rc) goto err_unlock; } @@ -387,9 +389,8 @@ int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt, mutex_unlock(&idev->igroup->lock); return 0; err_unresv: - if (hwpt_is_paging(hwpt)) - iopt_remove_reserved_iova(&to_hwpt_paging(hwpt)->ioas->iopt, - idev->dev); + if (hwpt_paging) + iopt_remove_reserved_iova(&hwpt_paging->ioas->iopt, idev->dev); err_unlock: mutex_unlock(&idev->igroup->lock); return rc; @@ -399,6 +400,7 @@ struct iommufd_hw_pagetable * iommufd_hw_pagetable_detach(struct iommufd_device *idev) { struct iommufd_hw_pagetable *hwpt = idev->igroup->hwpt; + struct iommufd_hwpt_paging *hwpt_paging = find_hwpt_paging(hwpt); mutex_lock(&idev->igroup->lock); list_del(&idev->group_item); @@ -406,9 +408,8 @@ iommufd_hw_pagetable_detach(struct iommufd_device *idev) iommufd_hwpt_detach_device(hwpt, idev); idev->igroup->hwpt = NULL; } - if (hwpt_is_paging(hwpt)) - iopt_remove_reserved_iova(&to_hwpt_paging(hwpt)->ioas->iopt, - idev->dev); + if (hwpt_paging) + iopt_remove_reserved_iova(&hwpt_paging->ioas->iopt, idev->dev); mutex_unlock(&idev->igroup->lock); /* Caller must destroy hwpt */ @@ -440,17 +441,17 @@ iommufd_group_remove_reserved_iova(struct iommufd_group *igroup, } static int -iommufd_group_do_replace_paging(struct iommufd_group *igroup, - struct iommufd_hwpt_paging *hwpt_paging) +iommufd_group_do_replace_reserved_iova(struct iommufd_group *igroup, + struct iommufd_hwpt_paging *hwpt_paging) { - struct iommufd_hw_pagetable *old_hwpt = igroup->hwpt; + struct iommufd_hwpt_paging *old_hwpt_paging; struct iommufd_device *cur; int rc; lockdep_assert_held(&igroup->lock); - if (!hwpt_is_paging(old_hwpt) || - hwpt_paging->ioas != to_hwpt_paging(old_hwpt)->ioas) { + old_hwpt_paging = find_hwpt_paging(igroup->hwpt); + if (!old_hwpt_paging || hwpt_paging->ioas != old_hwpt_paging->ioas) { list_for_each_entry(cur, &igroup->device_list, group_item) { rc = iopt_table_enforce_dev_resv_regions( &hwpt_paging->ioas->iopt, cur->dev, NULL); @@ -473,6 +474,8 @@ static struct iommufd_hw_pagetable * iommufd_device_do_replace(struct iommufd_device *idev, struct iommufd_hw_pagetable *hwpt) { + struct iommufd_hwpt_paging *hwpt_paging = find_hwpt_paging(hwpt); + struct iommufd_hwpt_paging *old_hwpt_paging; struct iommufd_group *igroup = idev->igroup; struct iommufd_hw_pagetable *old_hwpt; unsigned int num_devices; @@ -491,9 +494,8 @@ iommufd_device_do_replace(struct iommufd_device *idev, } old_hwpt = igroup->hwpt; - if (hwpt_is_paging(hwpt)) { - rc = iommufd_group_do_replace_paging(igroup, - to_hwpt_paging(hwpt)); + if (hwpt_paging) { + rc = iommufd_group_do_replace_reserved_iova(igroup, hwpt_paging); if (rc) goto err_unlock; } @@ -502,11 +504,10 @@ iommufd_device_do_replace(struct iommufd_device *idev, if (rc) goto err_unresv; - if (hwpt_is_paging(old_hwpt) && - (!hwpt_is_paging(hwpt) || - to_hwpt_paging(hwpt)->ioas != to_hwpt_paging(old_hwpt)->ioas)) - iommufd_group_remove_reserved_iova(igroup, - to_hwpt_paging(old_hwpt)); + old_hwpt_paging = find_hwpt_paging(old_hwpt); + if (old_hwpt_paging && + (!hwpt_paging || hwpt_paging->ioas != old_hwpt_paging->ioas)) + iommufd_group_remove_reserved_iova(igroup, old_hwpt_paging); igroup->hwpt = hwpt; @@ -524,9 +525,8 @@ iommufd_device_do_replace(struct iommufd_device *idev, /* Caller must destroy old_hwpt */ return old_hwpt; err_unresv: - if (hwpt_is_paging(hwpt)) - iommufd_group_remove_reserved_iova(igroup, - to_hwpt_paging(hwpt)); + if (hwpt_paging) + iommufd_group_remove_reserved_iova(igroup, hwpt_paging); err_unlock: mutex_unlock(&idev->igroup->lock); return ERR_PTR(rc); diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 92efe30a8f0d..0bfacaf40c05 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -324,6 +324,25 @@ to_hwpt_paging(struct iommufd_hw_pagetable *hwpt) return container_of(hwpt, struct iommufd_hwpt_paging, common); } +static inline struct iommufd_hwpt_nested * +to_hwpt_nested(struct iommufd_hw_pagetable *hwpt) +{ + return container_of(hwpt, struct iommufd_hwpt_nested, common); +} + +static inline struct iommufd_hwpt_paging * +find_hwpt_paging(struct iommufd_hw_pagetable *hwpt) +{ + switch (hwpt->obj.type) { + case IOMMUFD_OBJ_HWPT_PAGING: + return to_hwpt_paging(hwpt); + case IOMMUFD_OBJ_HWPT_NESTED: + return to_hwpt_nested(hwpt)->parent; + default: + return NULL; + } +} + static inline struct iommufd_hwpt_paging * iommufd_get_hwpt_paging(struct iommufd_ucmd *ucmd, u32 id) {