Merge drm/drm-next into drm-xe-next

Backmerging to bring in 7.00-rc3. Important ahead GPU SVM merging THP
support.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>

5 files changed, 191 insertions, 38 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index f80aa4c9d88f..9f3090db2f16 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -105,8 +105,6 @@ extern "C" {
  *
  * %AMDGPU_GEM_DOMAIN_DOORBELL	Doorbell. It is an MMIO region for
  * signalling user mode queues.
- *
- * %AMDGPU_GEM_DOMAIN_MMIO_REMAP	MMIO remap page (special mapping for HDP flushing).
  */
 #define AMDGPU_GEM_DOMAIN_CPU		0x1
 #define AMDGPU_GEM_DOMAIN_GTT		0x2
@@ -115,15 +113,13 @@ extern "C" {
 #define AMDGPU_GEM_DOMAIN_GWS		0x10
 #define AMDGPU_GEM_DOMAIN_OA		0x20
 #define AMDGPU_GEM_DOMAIN_DOORBELL	0x40
-#define AMDGPU_GEM_DOMAIN_MMIO_REMAP	0x80
 #define AMDGPU_GEM_DOMAIN_MASK		(AMDGPU_GEM_DOMAIN_CPU | \
 					 AMDGPU_GEM_DOMAIN_GTT | \
 					 AMDGPU_GEM_DOMAIN_VRAM | \
 					 AMDGPU_GEM_DOMAIN_GDS | \
 					 AMDGPU_GEM_DOMAIN_GWS | \
 					 AMDGPU_GEM_DOMAIN_OA |	\
-					 AMDGPU_GEM_DOMAIN_DOORBELL | \
-					 AMDGPU_GEM_DOMAIN_MMIO_REMAP)
+					 AMDGPU_GEM_DOMAIN_DOORBELL)
 
 /* Flag that CPU access will be required for the case of VRAM domain */
 #define AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED	(1 << 0)
@@ -483,7 +479,9 @@ struct drm_amdgpu_userq_signal {
 	 * @num_syncobj_handles: A count that represents the number of syncobj handles in
 	 * @syncobj_handles.
 	 */
-	__u64	num_syncobj_handles;
+	__u16	num_syncobj_handles;
+	__u16	pad0;
+	__u32	pad1;
 	/**
 	 * @bo_read_handles: The list of BO handles that the submitted user queue job
 	 * is using for read only. This will update BO fences in the kernel.
@@ -567,7 +565,8 @@ struct drm_amdgpu_userq_wait {
 	 * @num_syncobj_handles: A count that represents the number of syncobj handles in
 	 * @syncobj_handles.
 	 */
-	__u32	num_syncobj_handles;
+	__u16	num_syncobj_handles;
+	__u16	pad0;
 	/**
 	 * @num_bo_read_handles: A count that represents the number of read BO handles in
 	 * @bo_read_handles.
@@ -883,7 +882,7 @@ struct drm_amdgpu_gem_list_handles_entry {
 #define AMDGPU_VM_PAGE_WRITEABLE	(1 << 2)
 /* executable mapping, new for VI */
 #define AMDGPU_VM_PAGE_EXECUTABLE	(1 << 3)
-/* partially resident texture */
+/* unmapped page of partially resident textures */
 #define AMDGPU_VM_PAGE_PRT		(1 << 4)
 /* MTYPE flags use bit 5 to 8 */
 #define AMDGPU_VM_MTYPE_MASK		(0xf << 5)
@@ -1427,6 +1426,7 @@ struct drm_amdgpu_info_vbios {
 #define AMDGPU_VRAM_TYPE_LPDDR4 11
 #define AMDGPU_VRAM_TYPE_LPDDR5 12
 #define AMDGPU_VRAM_TYPE_HBM3E 13
+#define AMDGPU_VRAM_TYPE_HBM4 14
 
 struct drm_amdgpu_info_device {
 	/** PCI Device ID */
@@ -1629,9 +1629,25 @@ struct drm_amdgpu_info_uq_metadata_gfx {
 	__u32 csa_alignment;
 };
 
+struct drm_amdgpu_info_uq_metadata_compute {
+	/* EOP size for gfx11 */
+	__u32 eop_size;
+	/* EOP base virtual alignment for gfx11 */
+	__u32 eop_alignment;
+};
+
+struct drm_amdgpu_info_uq_metadata_sdma {
+	/* context save area size for sdma6 */
+	__u32 csa_size;
+	/* context save area base virtual alignment for sdma6 */
+	__u32 csa_alignment;
+};
+
 struct drm_amdgpu_info_uq_metadata {
 	union {
 		struct drm_amdgpu_info_uq_metadata_gfx gfx;
+		struct drm_amdgpu_info_uq_metadata_compute compute;
+		struct drm_amdgpu_info_uq_metadata_sdma sdma;
 	};
 };
 
@@ -1654,6 +1670,7 @@ struct drm_amdgpu_info_uq_metadata {
 #define AMDGPU_FAMILY_GC_10_3_6			149 /* GC 10.3.6 */
 #define AMDGPU_FAMILY_GC_10_3_7			151 /* GC 10.3.7 */
 #define AMDGPU_FAMILY_GC_11_5_0			150 /* GC 11.5.0 */
+#define AMDGPU_FAMILY_GC_11_5_4			154 /* GC 11.5.4 */
 #define AMDGPU_FAMILY_GC_12_0_0			152 /* GC 12.0.0 */
 
 #if defined(__cplusplus)
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index e527b24bd824..ac66fa93b5a3 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -401,8 +401,8 @@ extern "C" {
  * implementation can multiply the values by 2^6=64. For that reason the padding
  * must only contain zeros.
  * index 0 = Y plane, [15:0] z:Y [6:10] little endian
- * index 1 = Cr plane, [15:0] z:Cr [6:10] little endian
- * index 2 = Cb plane, [15:0] z:Cb [6:10] little endian
+ * index 1 = Cb plane, [15:0] z:Cb [6:10] little endian
+ * index 2 = Cr plane, [15:0] z:Cr [6:10] little endian
  */
 #define DRM_FORMAT_S010	fourcc_code('S', '0', '1', '0') /* 2x2 subsampled Cb (1) and Cr (2) planes 10 bits per channel */
 #define DRM_FORMAT_S210	fourcc_code('S', '2', '1', '0') /* 2x1 subsampled Cb (1) and Cr (2) planes 10 bits per channel */
@@ -414,8 +414,8 @@ extern "C" {
  * implementation can multiply the values by 2^4=16. For that reason the padding
  * must only contain zeros.
  * index 0 = Y plane, [15:0] z:Y [4:12] little endian
- * index 1 = Cr plane, [15:0] z:Cr [4:12] little endian
- * index 2 = Cb plane, [15:0] z:Cb [4:12] little endian
+ * index 1 = Cb plane, [15:0] z:Cb [4:12] little endian
+ * index 2 = Cr plane, [15:0] z:Cr [4:12] little endian
  */
 #define DRM_FORMAT_S012	fourcc_code('S', '0', '1', '2') /* 2x2 subsampled Cb (1) and Cr (2) planes 12 bits per channel */
 #define DRM_FORMAT_S212	fourcc_code('S', '2', '1', '2') /* 2x1 subsampled Cb (1) and Cr (2) planes 12 bits per channel */
@@ -424,8 +424,8 @@ extern "C" {
 /*
  * 3 plane YCbCr
  * index 0 = Y plane, [15:0] Y little endian
- * index 1 = Cr plane, [15:0] Cr little endian
- * index 2 = Cb plane, [15:0] Cb little endian
+ * index 1 = Cb plane, [15:0] Cb little endian
+ * index 2 = Cr plane, [15:0] Cr little endian
  */
 #define DRM_FORMAT_S016	fourcc_code('S', '0', '1', '6') /* 2x2 subsampled Cb (1) and Cr (2) planes 16 bits per channel */
 #define DRM_FORMAT_S216	fourcc_code('S', '2', '1', '6') /* 2x1 subsampled Cb (1) and Cr (2) planes 16 bits per channel */
@@ -1423,6 +1423,22 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
 	DRM_FORMAT_MOD_ARM_CODE(DRM_FORMAT_MOD_ARM_TYPE_MISC, 1ULL)
 
 /*
+ * ARM 64k interleaved modifier
+ *
+ * This is used by ARM Mali v10+ GPUs. With this modifier, the plane is divided
+ * into 64k byte 1:1 or 2:1 -sided tiles. The 64k tiles are laid out linearly.
+ * Each 64k tile is divided into blocks of 16x16 texel blocks, which are
+ * themselves laid out linearly within a 64k tile. Then within each 16x16
+ * block, texel blocks are laid out according to U order, similar to
+ * 16X16_BLOCK_U_INTERLEAVED.
+ *
+ * Note that unlike 16X16_BLOCK_U_INTERLEAVED, the layout does not change
+ * depending on whether a format is compressed or not.
+ */
+#define DRM_FORMAT_MOD_ARM_INTERLEAVED_64K \
+	DRM_FORMAT_MOD_ARM_CODE(DRM_FORMAT_MOD_ARM_TYPE_MISC, 2ULL)
+
+/*
  * Allwinner tiled modifier
  *
  * This tiling mode is implemented by the VPU found on all Allwinner platforms,
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index cbbbfc1dfe2b..3693d82b5279 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -166,6 +166,10 @@ extern "C" {
 #define DRM_MODE_LINK_STATUS_GOOD	0
 #define DRM_MODE_LINK_STATUS_BAD	1
 
+/* Panel type property */
+#define DRM_MODE_PANEL_TYPE_UNKNOWN	0
+#define DRM_MODE_PANEL_TYPE_OLED	1
+
 /*
  * DRM_MODE_ROTATE_<degrees>
  *
diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h
index dd87f8f30793..1fa82fa6af38 100644
--- a/include/uapi/drm/nouveau_drm.h
+++ b/include/uapi/drm/nouveau_drm.h
@@ -432,6 +432,69 @@ struct drm_nouveau_exec {
 	__u64 push_ptr;
 };
 
+struct drm_nouveau_get_zcull_info {
+	/**
+	 * @width_align_pixels: required alignment for region widths, in pixels
+	 * (typically #TPC's * 16).
+	 */
+	__u32 width_align_pixels;
+	/**
+	 * @height_align_pixels: required alignment for region heights, in
+	 * pixels (typically 32).
+	 */
+	__u32 height_align_pixels;
+	/**
+	 * @pixel_squares_by_aliquots: the pixel area covered by an aliquot
+	 * (typically #Zcull_banks * 16 * 16).
+	 */
+	__u32 pixel_squares_by_aliquots;
+	/**
+	 * @aliquot_total: the total aliquot pool available in hardware
+	 */
+	__u32 aliquot_total;
+	/**
+	 * @zcull_region_byte_multiplier: the size of an aliquot in bytes, which
+	 * is used for save/restore operations on a region
+	 */
+	__u32 zcull_region_byte_multiplier;
+	/**
+	 * @zcull_region_header_size: the region header size in bytes, which is
+	 * used for save/restore operations on a region
+	 */
+	__u32 zcull_region_header_size;
+	/**
+	 * @zcull_subregion_header_size: the subregion header size in bytes,
+	 * which is used for save/restore operations on a region
+	 */
+	__u32 zcull_subregion_header_size;
+	/**
+	 * @subregion_count: the total number of subregions the hardware
+	 * supports
+	 */
+	__u32 subregion_count;
+	/**
+	 * @subregion_width_align_pixels: required alignment for subregion
+	 * widths, in pixels (typically #TPC's * 16).
+	 */
+	__u32 subregion_width_align_pixels;
+	/**
+	 * @subregion_height_align_pixels: required alignment for subregion
+	 * heights, in pixels
+	 */
+	__u32 subregion_height_align_pixels;
+
+	/**
+	 * @ctxsw_size: the size, in bytes, of a zcull context switching region.
+	 * Will be zero if the kernel does not support zcull context switching.
+	 */
+	__u32 ctxsw_size;
+	/**
+	 * @ctxsw_align: the alignment, in bytes, of a zcull context switching
+	 * region
+	 */
+	__u32 ctxsw_align;
+};
+
 #define DRM_NOUVEAU_GETPARAM           0x00
 #define DRM_NOUVEAU_SETPARAM           0x01 /* deprecated */
 #define DRM_NOUVEAU_CHANNEL_ALLOC      0x02
@@ -445,6 +508,7 @@ struct drm_nouveau_exec {
 #define DRM_NOUVEAU_VM_INIT            0x10
 #define DRM_NOUVEAU_VM_BIND            0x11
 #define DRM_NOUVEAU_EXEC               0x12
+#define DRM_NOUVEAU_GET_ZCULL_INFO     0x13
 #define DRM_NOUVEAU_GEM_NEW            0x40
 #define DRM_NOUVEAU_GEM_PUSHBUF        0x41
 #define DRM_NOUVEAU_GEM_CPU_PREP       0x42
@@ -513,6 +577,8 @@ struct drm_nouveau_svm_bind {
 #define DRM_IOCTL_NOUVEAU_VM_INIT            DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_VM_INIT, struct drm_nouveau_vm_init)
 #define DRM_IOCTL_NOUVEAU_VM_BIND            DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_VM_BIND, struct drm_nouveau_vm_bind)
 #define DRM_IOCTL_NOUVEAU_EXEC               DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_EXEC, struct drm_nouveau_exec)
+
+#define DRM_IOCTL_NOUVEAU_GET_ZCULL_INFO     DRM_IOR (DRM_COMMAND_BASE + DRM_NOUVEAU_GET_ZCULL_INFO, struct drm_nouveau_get_zcull_info)
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/rocket_accel.h b/include/uapi/drm/rocket_accel.h
index 14b2e12b7c49..d0685e372b79 100644
--- a/include/uapi/drm/rocket_accel.h
+++ b/include/uapi/drm/rocket_accel.h
@@ -26,20 +26,27 @@ extern "C" {
  *
  */
 struct drm_rocket_create_bo {
-	/** Input: Size of the requested BO. */
+	/**
+	 * @size: Input: Size of the requested BO.
+	 */
 	__u32 size;
 
-	/** Output: GEM handle for the BO. */
+	/**
+	 * @handle: Output: GEM handle for the BO.
+	 */
 	__u32 handle;
 
 	/**
-	 * Output: DMA address for the BO in the NPU address space.  This address
-	 * is private to the DRM fd and is valid for the lifetime of the GEM
-	 * handle.
+	 * @dma_address: Output: DMA address for the BO in the NPU address
+	 * space.  This address is private to the DRM fd and is valid for
+	 * the lifetime of the GEM handle.
 	 */
 	__u64 dma_address;
 
-	/** Output: Offset into the drm node to use for subsequent mmap call. */
+	/**
+	 * @offset: Output: Offset into the drm node to use for subsequent
+	 * mmap call.
+	 */
 	__u64 offset;
 };
 
@@ -50,13 +57,19 @@ struct drm_rocket_create_bo {
  * synchronization.
  */
 struct drm_rocket_prep_bo {
-	/** Input: GEM handle of the buffer object. */
+	/**
+	 * @handle: Input: GEM handle of the buffer object.
+	 */
 	__u32 handle;
 
-	/** Reserved, must be zero. */
+	/**
+	 * @reserved: Reserved, must be zero.
+	 */
 	__u32 reserved;
 
-	/** Input: Amount of time to wait for NPU jobs. */
+	/**
+	 * @timeout_ns: Input: Amount of time to wait for NPU jobs.
+	 */
 	__s64 timeout_ns;
 };
 
@@ -66,10 +79,14 @@ struct drm_rocket_prep_bo {
  * Synchronize caches for NPU access.
  */
 struct drm_rocket_fini_bo {
-	/** Input: GEM handle of the buffer object. */
+	/**
+	 * @handle: Input: GEM handle of the buffer object.
+	 */
 	__u32 handle;
 
-	/** Reserved, must be zero. */
+	/**
+	 * @reserved: Reserved, must be zero.
+	 */
 	__u32 reserved;
 };
 
@@ -79,10 +96,15 @@ struct drm_rocket_fini_bo {
  * A task is the smallest unit of work that can be run on the NPU.
  */
 struct drm_rocket_task {
-	/** Input: DMA address to NPU mapping of register command buffer */
+	/**
+	 * @regcmd: Input: DMA address to NPU mapping of register command buffer
+	 */
 	__u32 regcmd;
 
-	/** Input: Number of commands in the register command buffer */
+	/**
+	 * @regcmd_count: Input: Number of commands in the register command
+	 * buffer
+	 */
 	__u32 regcmd_count;
 };
 
@@ -94,25 +116,44 @@ struct drm_rocket_task {
  * sequentially on the same core, to benefit from memory residency in SRAM.
  */
 struct drm_rocket_job {
-	/** Input: Pointer to an array of struct drm_rocket_task. */
+	/**
+	 * @tasks: Input: Pointer to an array of struct drm_rocket_task.
+	 */
 	__u64 tasks;
 
-	/** Input: Pointer to a u32 array of the BOs that are read by the job. */
+	/**
+	 * @in_bo_handles: Input: Pointer to a u32 array of the BOs that
+	 * are read by the job.
+	 */
 	__u64 in_bo_handles;
 
-	/** Input: Pointer to a u32 array of the BOs that are written to by the job. */
+	/**
+	 * @out_bo_handles: Input: Pointer to a u32 array of the BOs that
+	 * are written to by the job.
+	 */
 	__u64 out_bo_handles;
 
-	/** Input: Number of tasks passed in. */
+	/**
+	 * @task_count: Input: Number of tasks passed in.
+	 */
 	__u32 task_count;
 
-	/** Input: Size in bytes of the structs in the @tasks field. */
+	/**
+	 * @task_struct_size: Input: Size in bytes of the structs in the
+	 * @tasks field.
+	 */
 	__u32 task_struct_size;
 
-	/** Input: Number of input BO handles passed in (size is that times 4). */
+	/**
+	 * @in_bo_handle_count: Input: Number of input BO handles passed in
+	 * (size is that times 4).
+	 */
 	__u32 in_bo_handle_count;
 
-	/** Input: Number of output BO handles passed in (size is that times 4). */
+	/**
+	 * @out_bo_handle_count: Input: Number of output BO handles passed in
+	 * (size is that times 4).
+	 */
 	__u32 out_bo_handle_count;
 };
 
@@ -122,16 +163,25 @@ struct drm_rocket_job {
  * The kernel will schedule the execution of these jobs in dependency order.
  */
 struct drm_rocket_submit {
-	/** Input: Pointer to an array of struct drm_rocket_job. */
+	/**
+	 * @jobs: Input: Pointer to an array of struct drm_rocket_job.
+	 */
 	__u64 jobs;
 
-	/** Input: Number of jobs passed in. */
+	/**
+	 * @job_count: Input: Number of jobs passed in.
+	 */
 	__u32 job_count;
 
-	/** Input: Size in bytes of the structs in the @jobs field. */
+	/**
+	 * @job_struct_size: Input: Size in bytes of the structs in the
+	 * @jobs field.
+	 */
 	__u32 job_struct_size;
 
-	/** Reserved, must be zero. */
+	/**
+	 * @reserved: Reserved, must be zero.
+	 */
 	__u64 reserved;
 };