Merge drm/drm-next into drm-misc-next

Backmerging to get v6.15-rc1 into drm-misc-next. Also fixes a
build issue when enabling CONFIG_DRM_SCHED_KUNIT_TEST.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>

include/uapi/drm/amdgpu_drm.h

@@ -763,6 +763,16 @@ struct drm_amdgpu_cs_chunk_cp_gfx_shadow {
 #define AMDGPU_IDS_FLAGS_TMZ            0x4
 #define AMDGPU_IDS_FLAGS_CONFORMANT_TRUNC_COORD 0x8
 
+/*
+ *  Query h/w info: Flag identifying VF/PF/PT mode
+ *
+ */
+#define AMDGPU_IDS_FLAGS_MODE_MASK      0x300
+#define AMDGPU_IDS_FLAGS_MODE_SHIFT     0x8
+#define AMDGPU_IDS_FLAGS_MODE_PF        0x0
+#define AMDGPU_IDS_FLAGS_MODE_VF        0x1
+#define AMDGPU_IDS_FLAGS_MODE_PT        0x2
+
 /* indicate if acceleration can be working */
 #define AMDGPU_INFO_ACCEL_WORKING		0x00
 /* get the crtc_id from the mode object id? */

include/uapi/drm/xe_drm.h

@@ -393,6 +393,10 @@ struct drm_xe_query_mem_regions {
  *
  *    - %DRM_XE_QUERY_CONFIG_FLAG_HAS_VRAM - Flag is set if the device
  *      has usable VRAM
+ *    - %DRM_XE_QUERY_CONFIG_FLAG_HAS_LOW_LATENCY - Flag is set if the device
+ *      has low latency hint support
+ *    - %DRM_XE_QUERY_CONFIG_FLAG_HAS_CPU_ADDR_MIRROR - Flag is set if the
+ *      device has CPU address mirroring support
  *  - %DRM_XE_QUERY_CONFIG_MIN_ALIGNMENT - Minimal memory alignment
  *    required by this device, typically SZ_4K or SZ_64K
  *  - %DRM_XE_QUERY_CONFIG_VA_BITS - Maximum bits of a virtual address
@@ -409,6 +413,8 @@ struct drm_xe_query_config {
 #define DRM_XE_QUERY_CONFIG_REV_AND_DEVICE_ID	0
 #define DRM_XE_QUERY_CONFIG_FLAGS			1
 	#define DRM_XE_QUERY_CONFIG_FLAG_HAS_VRAM	(1 << 0)
+	#define DRM_XE_QUERY_CONFIG_FLAG_HAS_LOW_LATENCY	(1 << 1)
+	#define DRM_XE_QUERY_CONFIG_FLAG_HAS_CPU_ADDR_MIRROR	(1 << 2)
 #define DRM_XE_QUERY_CONFIG_MIN_ALIGNMENT		2
 #define DRM_XE_QUERY_CONFIG_VA_BITS			3
 #define DRM_XE_QUERY_CONFIG_MAX_EXEC_QUEUE_PRIORITY	4
@@ -629,6 +635,39 @@ struct drm_xe_query_uc_fw_version {
 	__u64 reserved;
 };
 
+/**
+ * struct drm_xe_query_pxp_status - query if PXP is ready
+ *
+ * If PXP is enabled and no fatal error has occurred, the status will be set to
+ * one of the following values:
+ * 0: PXP init still in progress
+ * 1: PXP init complete
+ *
+ * If PXP is not enabled or something has gone wrong, the query will be failed
+ * with one of the following error codes:
+ * -ENODEV: PXP not supported or disabled;
+ * -EIO: fatal error occurred during init, so PXP will never be enabled;
+ * -EINVAL: incorrect value provided as part of the query;
+ * -EFAULT: error copying the memory between kernel and userspace.
+ *
+ * The status can only be 0 in the first few seconds after driver load. If
+ * everything works as expected, the status will transition to init complete in
+ * less than 1 second, while in case of errors the driver might take longer to
+ * start returning an error code, but it should still take less than 10 seconds.
+ *
+ * The supported session type bitmask is based on the values in
+ * enum drm_xe_pxp_session_type. TYPE_NONE is always supported and therefore
+ * is not reported in the bitmask.
+ *
+ */
+struct drm_xe_query_pxp_status {
+	/** @status: current PXP status */
+	__u32 status;
+
+	/** @supported_session_types: bitmask of supported PXP session types */
+	__u32 supported_session_types;
+};
+
 /**
  * struct drm_xe_device_query - Input of &DRM_IOCTL_XE_DEVICE_QUERY - main
  * structure to query device information
@@ -648,6 +687,7 @@ struct drm_xe_query_uc_fw_version {
  *    attributes.
  *  - %DRM_XE_DEVICE_QUERY_GT_TOPOLOGY
  *  - %DRM_XE_DEVICE_QUERY_ENGINE_CYCLES
+ *  - %DRM_XE_DEVICE_QUERY_PXP_STATUS
  *
  * If size is set to 0, the driver fills it with the required size for
  * the requested type of data to query. If size is equal to the required
@@ -700,6 +740,8 @@ struct drm_xe_device_query {
 #define DRM_XE_DEVICE_QUERY_ENGINE_CYCLES	6
 #define DRM_XE_DEVICE_QUERY_UC_FW_VERSION	7
 #define DRM_XE_DEVICE_QUERY_OA_UNITS		8
+#define DRM_XE_DEVICE_QUERY_PXP_STATUS		9
+#define DRM_XE_DEVICE_QUERY_EU_STALL		10
 	/** @query: The type of data to query */
 	__u32 query;
 
@@ -743,8 +785,23 @@ struct drm_xe_device_query {
  *  - %DRM_XE_GEM_CPU_CACHING_WC - Allocate the pages as write-combined. This
  *    is uncached. Scanout surfaces should likely use this. All objects
  *    that can be placed in VRAM must use this.
+ *
+ * This ioctl supports setting the following properties via the
+ * %DRM_XE_GEM_CREATE_EXTENSION_SET_PROPERTY extension, which uses the
+ * generic @drm_xe_ext_set_property struct:
+ *
+ *  - %DRM_XE_GEM_CREATE_SET_PROPERTY_PXP_TYPE - set the type of PXP session
+ *    this object will be used with. Valid values are listed in enum
+ *    drm_xe_pxp_session_type. %DRM_XE_PXP_TYPE_NONE is the default behavior, so
+ *    there is no need to explicitly set that. Objects used with session of type
+ *    %DRM_XE_PXP_TYPE_HWDRM will be marked as invalid if a PXP invalidation
+ *    event occurs after their creation. Attempting to flip an invalid object
+ *    will cause a black frame to be displayed instead. Submissions with invalid
+ *    objects mapped in the VM will be rejected.
  */
 struct drm_xe_gem_create {
+#define DRM_XE_GEM_CREATE_EXTENSION_SET_PROPERTY	0
+#define   DRM_XE_GEM_CREATE_SET_PROPERTY_PXP_TYPE	0
 	/** @extensions: Pointer to the first extension struct, if any */
 	__u64 extensions;
 
@@ -811,6 +868,32 @@ struct drm_xe_gem_create {
 
 /**
  * struct drm_xe_gem_mmap_offset - Input of &DRM_IOCTL_XE_GEM_MMAP_OFFSET
+ *
+ * The @flags can be:
+ *  - %DRM_XE_MMAP_OFFSET_FLAG_PCI_BARRIER - For user to query special offset
+ *    for use in mmap ioctl. Writing to the returned mmap address will generate a
+ *    PCI memory barrier with low overhead (avoiding IOCTL call as well as writing
+ *    to VRAM which would also add overhead), acting like an MI_MEM_FENCE
+ *    instruction.
+ *
+ * Note: The mmap size can be at most 4K, due to HW limitations. As a result
+ * this interface is only supported on CPU architectures that support 4K page
+ * size. The mmap_offset ioctl will detect this and gracefully return an
+ * error, where userspace is expected to have a different fallback method for
+ * triggering a barrier.
+ *
+ * Roughly the usage would be as follows:
+ *
+ * .. code-block:: C
+ *
+ *     struct drm_xe_gem_mmap_offset mmo = {
+ *         .handle = 0, // must be set to 0
+ *         .flags = DRM_XE_MMAP_OFFSET_FLAG_PCI_BARRIER,
+ *     };
+ *
+ *     err = ioctl(fd, DRM_IOCTL_XE_GEM_MMAP_OFFSET, &mmo);
+ *     map = mmap(NULL, size, PROT_WRITE, MAP_SHARED, fd, mmo.offset);
+ *     map[i] = 0xdeadbeaf; // issue barrier
  */
 struct drm_xe_gem_mmap_offset {
 	/** @extensions: Pointer to the first extension struct, if any */
@@ -819,7 +902,8 @@ struct drm_xe_gem_mmap_offset {
 	/** @handle: Handle for the object being mapped. */
 	__u32 handle;
 
-	/** @flags: Must be zero */
+#define DRM_XE_MMAP_OFFSET_FLAG_PCI_BARRIER     (1 << 0)
+	/** @flags: Flags */
 	__u32 flags;
 
 	/** @offset: The fake offset to use for subsequent mmap call */
@@ -906,6 +990,15 @@ struct drm_xe_vm_destroy {
  *    will only be valid for DRM_XE_VM_BIND_OP_MAP operations, the BO
  *    handle MBZ, and the BO offset MBZ. This flag is intended to
  *    implement VK sparse bindings.
+ *  - %DRM_XE_VM_BIND_FLAG_CHECK_PXP - If the object is encrypted via PXP,
+ *    reject the binding if the encryption key is no longer valid. This
+ *    flag has no effect on BOs that are not marked as using PXP.
+ *  - %DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR - When the CPU address mirror flag is
+ *    set, no mappings are created rather the range is reserved for CPU address
+ *    mirroring which will be populated on GPU page faults or prefetches. Only
+ *    valid on VMs with DRM_XE_VM_CREATE_FLAG_FAULT_MODE set. The CPU address
+ *    mirror flag are only valid for DRM_XE_VM_BIND_OP_MAP operations, the BO
+ *    handle MBZ, and the BO offset MBZ.
  */
 struct drm_xe_vm_bind_op {
 	/** @extensions: Pointer to the first extension struct, if any */
@@ -958,7 +1051,9 @@ struct drm_xe_vm_bind_op {
 	 * on the @pat_index. For such mappings there is no actual memory being
 	 * mapped (the address in the PTE is invalid), so the various PAT memory
 	 * attributes likely do not apply.  Simply leaving as zero is one
-	 * option (still a valid pat_index).
+	 * option (still a valid pat_index). Same applies to
+	 * DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR bindings as for such mapping
+	 * there is no actual memory being mapped.
 	 */
 	__u16 pat_index;
 
@@ -974,6 +1069,14 @@ struct drm_xe_vm_bind_op {
 
 		/** @userptr: user pointer to bind on */
 		__u64 userptr;
+
+		/**
+		 * @cpu_addr_mirror_offset: Offset from GPU @addr to create
+		 * CPU address mirror mappings. MBZ with current level of
+		 * support (e.g. 1 to 1 mapping between GPU and CPU mappings
+		 * only supported).
+		 */
+		__s64 cpu_addr_mirror_offset;
 	};
 
 	/**
@@ -996,6 +1099,8 @@ struct drm_xe_vm_bind_op {
 #define DRM_XE_VM_BIND_FLAG_IMMEDIATE	(1 << 1)
 #define DRM_XE_VM_BIND_FLAG_NULL	(1 << 2)
 #define DRM_XE_VM_BIND_FLAG_DUMPABLE	(1 << 3)
+#define DRM_XE_VM_BIND_FLAG_CHECK_PXP	(1 << 4)
+#define DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR	(1 << 5)
 	/** @flags: Bind flags */
 	__u32 flags;
 
@@ -1087,6 +1192,24 @@ struct drm_xe_vm_bind {
 /**
  * struct drm_xe_exec_queue_create - Input of &DRM_IOCTL_XE_EXEC_QUEUE_CREATE
  *
+ * This ioctl supports setting the following properties via the
+ * %DRM_XE_EXEC_QUEUE_EXTENSION_SET_PROPERTY extension, which uses the
+ * generic @drm_xe_ext_set_property struct:
+ *
+ *  - %DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY - set the queue priority.
+ *    CAP_SYS_NICE is required to set a value above normal.
+ *  - %DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE - set the queue timeslice
+ *    duration in microseconds.
+ *  - %DRM_XE_EXEC_QUEUE_SET_PROPERTY_PXP_TYPE - set the type of PXP session
+ *    this queue will be used with. Valid values are listed in enum
+ *    drm_xe_pxp_session_type. %DRM_XE_PXP_TYPE_NONE is the default behavior, so
+ *    there is no need to explicitly set that. When a queue of type
+ *    %DRM_XE_PXP_TYPE_HWDRM is created, the PXP default HWDRM session
+ *    (%XE_PXP_HWDRM_DEFAULT_SESSION) will be started, if isn't already running.
+ *    Given that going into a power-saving state kills PXP HWDRM sessions,
+ *    runtime PM will be blocked while queues of this type are alive.
+ *    All PXP queues will be killed if a PXP invalidation event occurs.
+ *
  * The example below shows how to use @drm_xe_exec_queue_create to create
  * a simple exec_queue (no parallel submission) of class
  * &DRM_XE_ENGINE_CLASS_RENDER.
@@ -1105,12 +1228,27 @@ struct drm_xe_vm_bind {
  *     };
  *     ioctl(fd, DRM_IOCTL_XE_EXEC_QUEUE_CREATE, &exec_queue_create);
  *
+ *     Allow users to provide a hint to kernel for cases demanding low latency
+ *     profile. Please note it will have impact on power consumption. User can
+ *     indicate low latency hint with flag while creating exec queue as
+ *     mentioned below,
+ *
+ *     struct drm_xe_exec_queue_create exec_queue_create = {
+ *          .flags = DRM_XE_EXEC_QUEUE_LOW_LATENCY_HINT,
+ *          .extensions = 0,
+ *          .vm_id = vm,
+ *          .num_bb_per_exec = 1,
+ *          .num_eng_per_bb = 1,
+ *          .instances = to_user_pointer(&instance),
+ *     };
+ *     ioctl(fd, DRM_IOCTL_XE_EXEC_QUEUE_CREATE, &exec_queue_create);
+ *
  */
 struct drm_xe_exec_queue_create {
 #define DRM_XE_EXEC_QUEUE_EXTENSION_SET_PROPERTY		0
 #define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY		0
 #define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE		1
-
+#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_PXP_TYPE		2
 	/** @extensions: Pointer to the first extension struct, if any */
 	__u64 extensions;
 
@@ -1123,7 +1261,8 @@ struct drm_xe_exec_queue_create {
 	/** @vm_id: VM to use for this exec queue */
 	__u32 vm_id;
 
-	/** @flags: MBZ */
+#define DRM_XE_EXEC_QUEUE_LOW_LATENCY_HINT	(1 << 0)
+	/** @flags: flags to use for this exec queue */
 	__u32 flags;
 
 	/** @exec_queue_id: Returned exec queue ID */
@@ -1397,6 +1536,8 @@ struct drm_xe_wait_user_fence {
 enum drm_xe_observation_type {
 	/** @DRM_XE_OBSERVATION_TYPE_OA: OA observation stream type */
 	DRM_XE_OBSERVATION_TYPE_OA,
+	/** @DRM_XE_OBSERVATION_TYPE_EU_STALL: EU stall sampling observation stream type */
+	DRM_XE_OBSERVATION_TYPE_EU_STALL,
 };
 
 /**
@@ -1729,6 +1870,97 @@ struct drm_xe_oa_stream_info {
 	__u64 reserved[3];
 };
 
+/**
+ * enum drm_xe_pxp_session_type - Supported PXP session types.
+ *
+ * We currently only support HWDRM sessions, which are used for protected
+ * content that ends up being displayed, but the HW supports multiple types, so
+ * we might extend support in the future.
+ */
+enum drm_xe_pxp_session_type {
+	/** @DRM_XE_PXP_TYPE_NONE: PXP not used */
+	DRM_XE_PXP_TYPE_NONE = 0,
+	/**
+	 * @DRM_XE_PXP_TYPE_HWDRM: HWDRM sessions are used for content that ends
+	 * up on the display.
+	 */
+	DRM_XE_PXP_TYPE_HWDRM = 1,
+};
+
+/* ID of the protected content session managed by Xe when PXP is active */
+#define DRM_XE_PXP_HWDRM_DEFAULT_SESSION 0xf
+
+/**
+ * enum drm_xe_eu_stall_property_id - EU stall sampling input property ids.
+ *
+ * These properties are passed to the driver at open as a chain of
+ * @drm_xe_ext_set_property structures with @property set to these
+ * properties' enums and @value set to the corresponding values of these
+ * properties. @drm_xe_user_extension base.name should be set to
+ * @DRM_XE_EU_STALL_EXTENSION_SET_PROPERTY.
+ *
+ * With the file descriptor obtained from open, user space must enable
+ * the EU stall stream fd with @DRM_XE_OBSERVATION_IOCTL_ENABLE before
+ * calling read(). EIO errno from read() indicates HW dropped data
+ * due to full buffer.
+ */
+enum drm_xe_eu_stall_property_id {
+#define DRM_XE_EU_STALL_EXTENSION_SET_PROPERTY		0
+	/**
+	 * @DRM_XE_EU_STALL_PROP_GT_ID: @gt_id of the GT on which
+	 * EU stall data will be captured.
+	 */
+	DRM_XE_EU_STALL_PROP_GT_ID = 1,
+
+	/**
+	 * @DRM_XE_EU_STALL_PROP_SAMPLE_RATE: Sampling rate in
+	 * GPU cycles from @sampling_rates in struct @drm_xe_query_eu_stall
+	 */
+	DRM_XE_EU_STALL_PROP_SAMPLE_RATE,
+
+	/**
+	 * @DRM_XE_EU_STALL_PROP_WAIT_NUM_REPORTS: Minimum number of
+	 * EU stall data reports to be present in the kernel buffer
+	 * before unblocking a blocked poll or read.
+	 */
+	DRM_XE_EU_STALL_PROP_WAIT_NUM_REPORTS,
+};
+
+/**
+ * struct drm_xe_query_eu_stall - Information about EU stall sampling.
+ *
+ * If a query is made with a struct @drm_xe_device_query where .query
+ * is equal to @DRM_XE_DEVICE_QUERY_EU_STALL, then the reply uses
+ * struct @drm_xe_query_eu_stall in .data.
+ */
+struct drm_xe_query_eu_stall {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @capabilities: EU stall capabilities bit-mask */
+	__u64 capabilities;
+#define DRM_XE_EU_STALL_CAPS_BASE		(1 << 0)
+
+	/** @record_size: size of each EU stall data record */
+	__u64 record_size;
+
+	/** @per_xecore_buf_size: internal per XeCore buffer size */
+	__u64 per_xecore_buf_size;
+
+	/** @reserved: Reserved */
+	__u64 reserved[5];
+
+	/** @num_sampling_rates: Number of sampling rates in @sampling_rates array */
+	__u64 num_sampling_rates;
+
+	/**
+	 * @sampling_rates: Flexible array of sampling rates
+	 * sorted in the fastest to slowest order.
+	 * Sampling rates are specified in GPU clock cycles.
+	 */
+	__u64 sampling_rates[];
+};
+
 #if defined(__cplusplus)
 }
 #endif