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

Backmerging from drm/drm-next for the final fixes that will go
into v5.20.

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

4 files changed, 119 insertions, 12 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 1d65c1fbc4ec..18d3246d636e 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -140,6 +140,10 @@ extern "C" {
  * not require GTT memory accounting
  */
 #define AMDGPU_GEM_CREATE_PREEMPTIBLE		(1 << 11)
+/* Flag that BO can be discarded under memory pressure without keeping the
+ * content.
+ */
+#define AMDGPU_GEM_CREATE_DISCARDABLE		(1 << 12)
 
 struct drm_amdgpu_gem_create_in  {
 	/** the requested memory size */
@@ -529,6 +533,8 @@ struct drm_amdgpu_gem_op {
 #define AMDGPU_VM_MTYPE_UC		(4 << 5)
 /* Use Read Write MTYPE instead of default MTYPE */
 #define AMDGPU_VM_MTYPE_RW		(5 << 5)
+/* don't allocate MALL */
+#define AMDGPU_VM_PAGE_NOALLOC		(1 << 9)
 
 struct drm_amdgpu_gem_va {
 	/** GEM object handle */
@@ -988,6 +994,8 @@ struct drm_amdgpu_info_vbios {
 #define AMDGPU_VRAM_TYPE_DDR4  8
 #define AMDGPU_VRAM_TYPE_GDDR6 9
 #define AMDGPU_VRAM_TYPE_DDR5  10
+#define AMDGPU_VRAM_TYPE_LPDDR4 11
+#define AMDGPU_VRAM_TYPE_LPDDR5 12
 
 struct drm_amdgpu_info_device {
 	/** PCI Device ID */
@@ -1150,7 +1158,9 @@ struct drm_amdgpu_info_video_caps {
 #define AMDGPU_FAMILY_RV			142 /* Raven */
 #define AMDGPU_FAMILY_NV			143 /* Navi10 */
 #define AMDGPU_FAMILY_VGH			144 /* Van Gogh */
+#define AMDGPU_FAMILY_GC_11_0_0			145 /* GC 11.0.0 */
 #define AMDGPU_FAMILY_YC			146 /* Yellow Carp */
+#define AMDGPU_FAMILY_GC_11_0_1			148 /* GC 11.0.1 */
 #define AMDGPU_FAMILY_GC_10_3_6			149 /* GC 10.3.6 */
 #define AMDGPU_FAMILY_GC_10_3_7			151 /* GC 10.3.7 */
 
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index e5074162bcdd..0206f812c569 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -559,7 +559,7 @@ extern "C" {
  *
  * The main surface is Y-tiled and is at plane index 0 whereas CCS is linear
  * and at index 1. The clear color is stored at index 2, and the pitch should
- * be ignored. The clear color structure is 256 bits. The first 128 bits
+ * be 64 bytes aligned. The clear color structure is 256 bits. The first 128 bits
  * represents Raw Clear Color Red, Green, Blue and Alpha color each represented
  * by 32 bits. The raw clear color is consumed by the 3d engine and generates
  * the converted clear color of size 64 bits. The first 32 bits store the Lower
@@ -612,9 +612,9 @@ extern "C" {
  * outside of the GEM object in a reserved memory area dedicated for the
  * storage of the CCS data for all RC/RC_CC/MC compressible GEM objects. The
  * main surface pitch is required to be a multiple of four Tile 4 widths. The
- * clear color is stored at plane index 1 and the pitch should be ignored. The
- * format of the 256 bits of clear color data matches the one used for the
- * I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC modifier, see its description
+ * clear color is stored at plane index 1 and the pitch should be 64 bytes
+ * aligned. The format of the 256 bits of clear color data matches the one used
+ * for the I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC modifier, see its description
  * for details.
  */
 #define I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC fourcc_mod_code(INTEL, 12)
@@ -656,6 +656,28 @@ extern "C" {
  */
 #define DRM_FORMAT_MOD_QCOM_COMPRESSED	fourcc_mod_code(QCOM, 1)
 
+/*
+ * Qualcomm Tiled Format
+ *
+ * Similar to DRM_FORMAT_MOD_QCOM_COMPRESSED but not compressed.
+ * Implementation may be platform and base-format specific.
+ *
+ * Each macrotile consists of m x n (mostly 4 x 4) tiles.
+ * Pixel data pitch/stride is aligned with macrotile width.
+ * Pixel data height is aligned with macrotile height.
+ * Entire pixel data buffer is aligned with 4k(bytes).
+ */
+#define DRM_FORMAT_MOD_QCOM_TILED3	fourcc_mod_code(QCOM, 3)
+
+/*
+ * Qualcomm Alternate Tiled Format
+ *
+ * Alternate tiled format typically only used within GMEM.
+ * Implementation may be platform and base-format specific.
+ */
+#define DRM_FORMAT_MOD_QCOM_TILED2	fourcc_mod_code(QCOM, 2)
+
+
 /* Vivante framebuffer modifiers */
 
 /*
@@ -1341,6 +1363,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
 #define AMD_FMT_MOD_TILE_VER_GFX9 1
 #define AMD_FMT_MOD_TILE_VER_GFX10 2
 #define AMD_FMT_MOD_TILE_VER_GFX10_RBPLUS 3
+#define AMD_FMT_MOD_TILE_VER_GFX11 4
 
 /*
  * 64K_S is the same for GFX9/GFX10/GFX10_RBPLUS and hence has GFX9 as canonical
@@ -1356,6 +1379,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
 #define AMD_FMT_MOD_TILE_GFX9_64K_S_X 25
 #define AMD_FMT_MOD_TILE_GFX9_64K_D_X 26
 #define AMD_FMT_MOD_TILE_GFX9_64K_R_X 27
+#define AMD_FMT_MOD_TILE_GFX11_256K_R_X 31
 
 #define AMD_FMT_MOD_DCC_BLOCK_64B 0
 #define AMD_FMT_MOD_DCC_BLOCK_128B 1
@@ -1422,11 +1446,11 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
 #define AMD_FMT_MOD_PIPE_MASK 0x7
 
 #define AMD_FMT_MOD_SET(field, value) \
-	((uint64_t)(value) << AMD_FMT_MOD_##field##_SHIFT)
+	((__u64)(value) << AMD_FMT_MOD_##field##_SHIFT)
 #define AMD_FMT_MOD_GET(field, value) \
 	(((value) >> AMD_FMT_MOD_##field##_SHIFT) & AMD_FMT_MOD_##field##_MASK)
 #define AMD_FMT_MOD_CLEAR(field) \
-	(~((uint64_t)AMD_FMT_MOD_##field##_MASK << AMD_FMT_MOD_##field##_SHIFT))
+	(~((__u64)AMD_FMT_MOD_##field##_MASK << AMD_FMT_MOD_##field##_SHIFT))
 
 #if defined(__cplusplus)
 }
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 35ca528803fd..de49b68b4fc8 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -154,21 +154,71 @@ enum i915_mocs_table_index {
 	I915_MOCS_CACHED,
 };
 
-/*
+/**
+ * enum drm_i915_gem_engine_class - uapi engine type enumeration
+ *
  * Different engines serve different roles, and there may be more than one
- * engine serving each role. enum drm_i915_gem_engine_class provides a
- * classification of the role of the engine, which may be used when requesting
- * operations to be performed on a certain subset of engines, or for providing
- * information about that group.
+ * engine serving each role.  This enum provides a classification of the role
+ * of the engine, which may be used when requesting operations to be performed
+ * on a certain subset of engines, or for providing information about that
+ * group.
  */
 enum drm_i915_gem_engine_class {
+	/**
+	 * @I915_ENGINE_CLASS_RENDER:
+	 *
+	 * Render engines support instructions used for 3D, Compute (GPGPU),
+	 * and programmable media workloads.  These instructions fetch data and
+	 * dispatch individual work items to threads that operate in parallel.
+	 * The threads run small programs (called "kernels" or "shaders") on
+	 * the GPU's execution units (EUs).
+	 */
 	I915_ENGINE_CLASS_RENDER	= 0,
+
+	/**
+	 * @I915_ENGINE_CLASS_COPY:
+	 *
+	 * Copy engines (also referred to as "blitters") support instructions
+	 * that move blocks of data from one location in memory to another,
+	 * or that fill a specified location of memory with fixed data.
+	 * Copy engines can perform pre-defined logical or bitwise operations
+	 * on the source, destination, or pattern data.
+	 */
 	I915_ENGINE_CLASS_COPY		= 1,
+
+	/**
+	 * @I915_ENGINE_CLASS_VIDEO:
+	 *
+	 * Video engines (also referred to as "bit stream decode" (BSD) or
+	 * "vdbox") support instructions that perform fixed-function media
+	 * decode and encode.
+	 */
 	I915_ENGINE_CLASS_VIDEO		= 2,
+
+	/**
+	 * @I915_ENGINE_CLASS_VIDEO_ENHANCE:
+	 *
+	 * Video enhancement engines (also referred to as "vebox") support
+	 * instructions related to image enhancement.
+	 */
 	I915_ENGINE_CLASS_VIDEO_ENHANCE	= 3,
 
-	/* should be kept compact */
+	/**
+	 * @I915_ENGINE_CLASS_COMPUTE:
+	 *
+	 * Compute engines support a subset of the instructions available
+	 * on render engines:  compute engines support Compute (GPGPU) and
+	 * programmable media workloads, but do not support the 3D pipeline.
+	 */
+	I915_ENGINE_CLASS_COMPUTE	= 4,
+
+	/* Values in this enum should be kept compact. */
 
+	/**
+	 * @I915_ENGINE_CLASS_INVALID:
+	 *
+	 * Placeholder value to represent an invalid engine class assignment.
+	 */
 	I915_ENGINE_CLASS_INVALID	= -1
 };
 
@@ -3393,6 +3443,22 @@ struct drm_i915_gem_create_ext {
  * At which point we get the object handle in &drm_i915_gem_create_ext.handle,
  * along with the final object size in &drm_i915_gem_create_ext.size, which
  * should account for any rounding up, if required.
+ *
+ * Note that userspace has no means of knowing the current backing region
+ * for objects where @num_regions is larger than one. The kernel will only
+ * ensure that the priority order of the @regions array is honoured, either
+ * when initially placing the object, or when moving memory around due to
+ * memory pressure
+ *
+ * On Flat-CCS capable HW, compression is supported for the objects residing
+ * in I915_MEMORY_CLASS_DEVICE. When such objects (compressed) have other
+ * memory class in @regions and migrated (by i915, due to memory
+ * constraints) to the non I915_MEMORY_CLASS_DEVICE region, then i915 needs to
+ * decompress the content. But i915 doesn't have the required information to
+ * decompress the userspace compressed objects.
+ *
+ * So i915 supports Flat-CCS, on the objects which can reside only on
+ * I915_MEMORY_CLASS_DEVICE regions.
  */
 struct drm_i915_gem_create_ext_memory_regions {
 	/** @base: Extension link. See struct i915_user_extension. */
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index 07efc8033492..3c7b097c4e3d 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -82,6 +82,10 @@ struct drm_msm_timespec {
 #define MSM_PARAM_FAULTS     0x09  /* RO */
 #define MSM_PARAM_SUSPENDS   0x0a  /* RO */
 #define MSM_PARAM_SYSPROF    0x0b  /* WO: 1 preserves perfcntrs, 2 also disables suspend */
+#define MSM_PARAM_COMM       0x0c  /* WO: override for task->comm */
+#define MSM_PARAM_CMDLINE    0x0d  /* WO: override for task cmdline */
+#define MSM_PARAM_VA_START   0x0e  /* RO: start of valid GPU iova range */
+#define MSM_PARAM_VA_SIZE    0x0f  /* RO: size of valid GPU iova range (bytes) */
 
 /* For backwards compat.  The original support for preemption was based on
  * a single ring per priority level so # of priority levels equals the #
@@ -95,6 +99,8 @@ struct drm_msm_param {
 	__u32 pipe;           /* in, MSM_PIPE_x */
 	__u32 param;          /* in, MSM_PARAM_x */
 	__u64 value;          /* out (get_param) or in (set_param) */
+	__u32 len;            /* zero for non-pointer params */
+	__u32 pad;            /* must be zero */
 };
 
 /*
@@ -131,6 +137,7 @@ struct drm_msm_gem_new {
 #define MSM_INFO_GET_IOVA	0x01   /* get iova, returned by value */
 #define MSM_INFO_SET_NAME	0x02   /* set the debug name (by pointer) */
 #define MSM_INFO_GET_NAME	0x03   /* get debug name, returned by pointer */
+#define MSM_INFO_SET_IOVA	0x04   /* set the iova, passed by value */
 
 struct drm_msm_gem_info {
 	__u32 handle;         /* in */