Merge tag 'v5.1' into next

Sync up with mainline to bring in the latest APIs.

8 files changed, 308 insertions, 12 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 370e9a5536ef..4a53f6cfa034 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -272,13 +272,14 @@ union drm_amdgpu_vm {
 
 /* sched ioctl */
 #define AMDGPU_SCHED_OP_PROCESS_PRIORITY_OVERRIDE	1
+#define AMDGPU_SCHED_OP_CONTEXT_PRIORITY_OVERRIDE	2
 
 struct drm_amdgpu_sched_in {
 	/* AMDGPU_SCHED_OP_* */
 	__u32	op;
 	__u32	fd;
 	__s32	priority;
-	__u32	flags;
+	__u32   ctx_id;
 };
 
 union drm_amdgpu_sched {
@@ -326,6 +327,12 @@ struct drm_amdgpu_gem_userptr {
 /* GFX9 and later: */
 #define AMDGPU_TILING_SWIZZLE_MODE_SHIFT		0
 #define AMDGPU_TILING_SWIZZLE_MODE_MASK			0x1f
+#define AMDGPU_TILING_DCC_OFFSET_256B_SHIFT		5
+#define AMDGPU_TILING_DCC_OFFSET_256B_MASK		0xFFFFFF
+#define AMDGPU_TILING_DCC_PITCH_MAX_SHIFT		29
+#define AMDGPU_TILING_DCC_PITCH_MAX_MASK		0x3FFF
+#define AMDGPU_TILING_DCC_INDEPENDENT_64B_SHIFT		43
+#define AMDGPU_TILING_DCC_INDEPENDENT_64B_MASK		0x1
 
 /* Set/Get helpers for tiling flags. */
 #define AMDGPU_TILING_SET(field, value) \
@@ -517,6 +524,7 @@ struct drm_amdgpu_gem_va {
 #define AMDGPU_CHUNK_ID_SYNCOBJ_IN      0x04
 #define AMDGPU_CHUNK_ID_SYNCOBJ_OUT     0x05
 #define AMDGPU_CHUNK_ID_BO_HANDLES      0x06
+#define AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES	0x07
 
 struct drm_amdgpu_cs_chunk {
 	__u32		chunk_id;
@@ -559,6 +567,11 @@ union drm_amdgpu_cs {
  * caches (L2/vL1/sL1/I$). */
 #define AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE (1 << 3)
 
+/* Set GDS_COMPUTE_MAX_WAVE_ID = DEFAULT before PACKET3_INDIRECT_BUFFER.
+ * This will reset wave ID counters for the IB.
+ */
+#define AMDGPU_IB_FLAG_RESET_GDS_MAX_WAVE_ID (1 << 4)
+
 struct drm_amdgpu_cs_chunk_ib {
 	__u32 _pad;
 	/** AMDGPU_IB_FLAG_* */
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 0cd40ebfa1b1..bab20298f422 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -151,6 +151,21 @@ extern "C" {
 #define DRM_FORMAT_VYUY		fourcc_code('V', 'Y', 'U', 'Y') /* [31:0] Y1:Cb0:Y0:Cr0 8:8:8:8 little endian */
 
 #define DRM_FORMAT_AYUV		fourcc_code('A', 'Y', 'U', 'V') /* [31:0] A:Y:Cb:Cr 8:8:8:8 little endian */
+#define DRM_FORMAT_XYUV8888		fourcc_code('X', 'Y', 'U', 'V') /* [31:0] X:Y:Cb:Cr 8:8:8:8 little endian */
+
+/*
+ * packed YCbCr420 2x2 tiled formats
+ * first 64 bits will contain Y,Cb,Cr components for a 2x2 tile
+ */
+/* [63:0]   A3:A2:Y3:0:Cr0:0:Y2:0:A1:A0:Y1:0:Cb0:0:Y0:0  1:1:8:2:8:2:8:2:1:1:8:2:8:2:8:2 little endian */
+#define DRM_FORMAT_Y0L0		fourcc_code('Y', '0', 'L', '0')
+/* [63:0]   X3:X2:Y3:0:Cr0:0:Y2:0:X1:X0:Y1:0:Cb0:0:Y0:0  1:1:8:2:8:2:8:2:1:1:8:2:8:2:8:2 little endian */
+#define DRM_FORMAT_X0L0		fourcc_code('X', '0', 'L', '0')
+
+/* [63:0]   A3:A2:Y3:Cr0:Y2:A1:A0:Y1:Cb0:Y0  1:1:10:10:10:1:1:10:10:10 little endian */
+#define DRM_FORMAT_Y0L2		fourcc_code('Y', '0', 'L', '2')
+/* [63:0]   X3:X2:Y3:Cr0:Y2:X1:X0:Y1:Cb0:Y0  1:1:10:10:10:1:1:10:10:10 little endian */
+#define DRM_FORMAT_X0L2		fourcc_code('X', '0', 'L', '2')
 
 /*
  * 2 plane RGB + A
@@ -181,6 +196,27 @@ extern "C" {
 #define DRM_FORMAT_NV42		fourcc_code('N', 'V', '4', '2') /* non-subsampled Cb:Cr plane */
 
 /*
+ * 2 plane YCbCr MSB aligned
+ * index 0 = Y plane, [15:0] Y:x [10:6] little endian
+ * index 1 = Cr:Cb plane, [31:0] Cr:x:Cb:x [10:6:10:6] little endian
+ */
+#define DRM_FORMAT_P010		fourcc_code('P', '0', '1', '0') /* 2x2 subsampled Cr:Cb plane 10 bits per channel */
+
+/*
+ * 2 plane YCbCr MSB aligned
+ * index 0 = Y plane, [15:0] Y:x [12:4] little endian
+ * index 1 = Cr:Cb plane, [31:0] Cr:x:Cb:x [12:4:12:4] little endian
+ */
+#define DRM_FORMAT_P012		fourcc_code('P', '0', '1', '2') /* 2x2 subsampled Cr:Cb plane 12 bits per channel */
+
+/*
+ * 2 plane YCbCr MSB aligned
+ * index 0 = Y plane, [15:0] Y little endian
+ * index 1 = Cr:Cb plane, [31:0] Cr:Cb [16:16] little endian
+ */
+#define DRM_FORMAT_P016		fourcc_code('P', '0', '1', '6') /* 2x2 subsampled Cr:Cb plane 16 bits per channel */
+
+/*
  * 3 plane YCbCr
  * index 0: Y plane, [7:0] Y
  * index 1: Cb plane, [7:0] Cb
@@ -223,6 +259,8 @@ extern "C" {
 #define DRM_FORMAT_MOD_VENDOR_VIVANTE 0x06
 #define DRM_FORMAT_MOD_VENDOR_BROADCOM 0x07
 #define DRM_FORMAT_MOD_VENDOR_ARM     0x08
+#define DRM_FORMAT_MOD_VENDOR_ALLWINNER 0x09
+
 /* add more to the end as needed */
 
 #define DRM_FORMAT_RESERVED	      ((1ULL << 56) - 1)
@@ -557,6 +595,9 @@ extern "C" {
  * AFBC has several features which may be supported and/or used, which are
  * represented using bits in the modifier. Not all combinations are valid,
  * and different devices or use-cases may support different combinations.
+ *
+ * Further information on the use of AFBC modifiers can be found in
+ * Documentation/gpu/afbc.rst
  */
 #define DRM_FORMAT_MOD_ARM_AFBC(__afbc_mode)	fourcc_mod_code(ARM, __afbc_mode)
 
@@ -566,10 +607,18 @@ extern "C" {
  * Indicates the superblock size(s) used for the AFBC buffer. The buffer
  * size (in pixels) must be aligned to a multiple of the superblock size.
  * Four lowest significant bits(LSBs) are reserved for block size.
+ *
+ * Where one superblock size is specified, it applies to all planes of the
+ * buffer (e.g. 16x16, 32x8). When multiple superblock sizes are specified,
+ * the first applies to the Luma plane and the second applies to the Chroma
+ * plane(s). e.g. (32x8_64x4 means 32x8 Luma, with 64x4 Chroma).
+ * Multiple superblock sizes are only valid for multi-plane YCbCr formats.
  */
 #define AFBC_FORMAT_MOD_BLOCK_SIZE_MASK      0xf
 #define AFBC_FORMAT_MOD_BLOCK_SIZE_16x16     (1ULL)
 #define AFBC_FORMAT_MOD_BLOCK_SIZE_32x8      (2ULL)
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_64x4      (3ULL)
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_32x8_64x4 (4ULL)
 
 /*
  * AFBC lossless colorspace transform
@@ -629,6 +678,35 @@ extern "C" {
  */
 #define AFBC_FORMAT_MOD_SC      (1ULL <<  9)
 
+/*
+ * AFBC double-buffer
+ *
+ * Indicates that the buffer is allocated in a layout safe for front-buffer
+ * rendering.
+ */
+#define AFBC_FORMAT_MOD_DB      (1ULL << 10)
+
+/*
+ * AFBC buffer content hints
+ *
+ * Indicates that the buffer includes per-superblock content hints.
+ */
+#define AFBC_FORMAT_MOD_BCH     (1ULL << 11)
+
+/*
+ * Allwinner tiled modifier
+ *
+ * This tiling mode is implemented by the VPU found on all Allwinner platforms,
+ * codenamed sunxi. It is associated with a YUV format that uses either 2 or 3
+ * planes.
+ *
+ * With this tiling, the luminance samples are disposed in tiles representing
+ * 32x32 pixels and the chrominance samples in tiles representing 32x64 pixels.
+ * The pixel order in each tile is linear and the tiles are disposed linearly,
+ * both in row-major order.
+ */
+#define DRM_FORMAT_MOD_ALLWINNER_TILED fourcc_mod_code(ALLWINNER, 1)
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index d3e0fe31efc5..a439c2e67896 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -888,6 +888,25 @@ struct drm_mode_revoke_lease {
 	__u32 lessee_id;
 };
 
+/**
+ * struct drm_mode_rect - Two dimensional rectangle.
+ * @x1: Horizontal starting coordinate (inclusive).
+ * @y1: Vertical starting coordinate (inclusive).
+ * @x2: Horizontal ending coordinate (exclusive).
+ * @y2: Vertical ending coordinate (exclusive).
+ *
+ * With drm subsystem using struct drm_rect to manage rectangular area this
+ * export it to user-space.
+ *
+ * Currently used by drm_mode_atomic blob property FB_DAMAGE_CLIPS.
+ */
+struct drm_mode_rect {
+	__s32 x1;
+	__s32 y1;
+	__s32 x2;
+	__s32 y2;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index a4446f452040..397810fa2d33 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -412,6 +412,14 @@ typedef struct drm_i915_irq_wait {
 	int irq_seq;
 } drm_i915_irq_wait_t;
 
+/*
+ * Different modes of per-process Graphics Translation Table,
+ * see I915_PARAM_HAS_ALIASING_PPGTT
+ */
+#define I915_GEM_PPGTT_NONE	0
+#define I915_GEM_PPGTT_ALIASING	1
+#define I915_GEM_PPGTT_FULL	2
+
 /* Ioctl to query kernel params:
  */
 #define I915_PARAM_IRQ_ACTIVE            1
@@ -1478,9 +1486,73 @@ struct drm_i915_gem_context_param {
 #define   I915_CONTEXT_MAX_USER_PRIORITY	1023 /* inclusive */
 #define   I915_CONTEXT_DEFAULT_PRIORITY		0
 #define   I915_CONTEXT_MIN_USER_PRIORITY	-1023 /* inclusive */
+	/*
+	 * When using the following param, value should be a pointer to
+	 * drm_i915_gem_context_param_sseu.
+	 */
+#define I915_CONTEXT_PARAM_SSEU		0x7
 	__u64 value;
 };
 
+/**
+ * Context SSEU programming
+ *
+ * It may be necessary for either functional or performance reason to configure
+ * a context to run with a reduced number of SSEU (where SSEU stands for Slice/
+ * Sub-slice/EU).
+ *
+ * This is done by configuring SSEU configuration using the below
+ * @struct drm_i915_gem_context_param_sseu for every supported engine which
+ * userspace intends to use.
+ *
+ * Not all GPUs or engines support this functionality in which case an error
+ * code -ENODEV will be returned.
+ *
+ * Also, flexibility of possible SSEU configuration permutations varies between
+ * GPU generations and software imposed limitations. Requesting such a
+ * combination will return an error code of -EINVAL.
+ *
+ * NOTE: When perf/OA is active the context's SSEU configuration is ignored in
+ * favour of a single global setting.
+ */
+struct drm_i915_gem_context_param_sseu {
+	/*
+	 * Engine class & instance to be configured or queried.
+	 */
+	__u16 engine_class;
+	__u16 engine_instance;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * Mask of slices to enable for the context. Valid values are a subset
+	 * of the bitmask value returned for I915_PARAM_SLICE_MASK.
+	 */
+	__u64 slice_mask;
+
+	/*
+	 * Mask of subslices to enable for the context. Valid values are a
+	 * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK.
+	 */
+	__u64 subslice_mask;
+
+	/*
+	 * Minimum/Maximum number of EUs to enable per subslice for the
+	 * context. min_eus_per_subslice must be inferior or equal to
+	 * max_eus_per_subslice.
+	 */
+	__u16 min_eus_per_subslice;
+	__u16 max_eus_per_subslice;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 rsvd;
+};
+
 enum drm_i915_oa_format {
 	I915_OA_FORMAT_A13 = 1,	    /* HSW only */
 	I915_OA_FORMAT_A29,	    /* HSW only */
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index c06d0a5bdd80..91a16b333c69 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -105,14 +105,24 @@ struct drm_msm_gem_new {
 	__u32 handle;         /* out */
 };
 
-#define MSM_INFO_IOVA	0x01
-
-#define MSM_INFO_FLAGS (MSM_INFO_IOVA)
+/* Get or set GEM buffer info.  The requested value can be passed
+ * directly in 'value', or for data larger than 64b 'value' is a
+ * pointer to userspace buffer, with 'len' specifying the number of
+ * bytes copied into that buffer.  For info returned by pointer,
+ * calling the GEM_INFO ioctl with null 'value' will return the
+ * required buffer size in 'len'
+ */
+#define MSM_INFO_GET_OFFSET	0x00   /* get mmap() offset, returned by value */
+#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 */
 
 struct drm_msm_gem_info {
 	__u32 handle;         /* in */
-	__u32 flags;	      /* in - combination of MSM_INFO_* flags */
-	__u64 offset;         /* out, mmap() offset or iova */
+	__u32 info;           /* in - one of MSM_INFO_* */
+	__u64 value;          /* in or out */
+	__u32 len;            /* in or out */
+	__u32 pad;
 };
 
 #define MSM_PREP_READ        0x01
@@ -188,8 +198,11 @@ struct drm_msm_gem_submit_cmd {
  */
 #define MSM_SUBMIT_BO_READ             0x0001
 #define MSM_SUBMIT_BO_WRITE            0x0002
+#define MSM_SUBMIT_BO_DUMP             0x0004
 
-#define MSM_SUBMIT_BO_FLAGS            (MSM_SUBMIT_BO_READ | MSM_SUBMIT_BO_WRITE)
+#define MSM_SUBMIT_BO_FLAGS            (MSM_SUBMIT_BO_READ | \
+					MSM_SUBMIT_BO_WRITE | \
+					MSM_SUBMIT_BO_DUMP)
 
 struct drm_msm_gem_submit_bo {
 	__u32 flags;          /* in, mask of MSM_SUBMIT_BO_x */
diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h
index 259588a4b61b..9459a6e3bc1f 100644
--- a/include/uapi/drm/nouveau_drm.h
+++ b/include/uapi/drm/nouveau_drm.h
@@ -133,12 +133,63 @@ struct drm_nouveau_gem_cpu_fini {
 #define DRM_NOUVEAU_NOTIFIEROBJ_ALLOC  0x05 /* deprecated */
 #define DRM_NOUVEAU_GPUOBJ_FREE        0x06 /* deprecated */
 #define DRM_NOUVEAU_NVIF               0x07
+#define DRM_NOUVEAU_SVM_INIT           0x08
+#define DRM_NOUVEAU_SVM_BIND           0x09
 #define DRM_NOUVEAU_GEM_NEW            0x40
 #define DRM_NOUVEAU_GEM_PUSHBUF        0x41
 #define DRM_NOUVEAU_GEM_CPU_PREP       0x42
 #define DRM_NOUVEAU_GEM_CPU_FINI       0x43
 #define DRM_NOUVEAU_GEM_INFO           0x44
 
+struct drm_nouveau_svm_init {
+	__u64 unmanaged_addr;
+	__u64 unmanaged_size;
+};
+
+struct drm_nouveau_svm_bind {
+	__u64 header;
+	__u64 va_start;
+	__u64 va_end;
+	__u64 npages;
+	__u64 stride;
+	__u64 result;
+	__u64 reserved0;
+	__u64 reserved1;
+};
+
+#define NOUVEAU_SVM_BIND_COMMAND_SHIFT          0
+#define NOUVEAU_SVM_BIND_COMMAND_BITS           8
+#define NOUVEAU_SVM_BIND_COMMAND_MASK           ((1 << 8) - 1)
+#define NOUVEAU_SVM_BIND_PRIORITY_SHIFT         8
+#define NOUVEAU_SVM_BIND_PRIORITY_BITS          8
+#define NOUVEAU_SVM_BIND_PRIORITY_MASK          ((1 << 8) - 1)
+#define NOUVEAU_SVM_BIND_TARGET_SHIFT           16
+#define NOUVEAU_SVM_BIND_TARGET_BITS            32
+#define NOUVEAU_SVM_BIND_TARGET_MASK            0xffffffff
+
+/*
+ * Below is use to validate ioctl argument, userspace can also use it to make
+ * sure that no bit are set beyond known fields for a given kernel version.
+ */
+#define NOUVEAU_SVM_BIND_VALID_BITS     48
+#define NOUVEAU_SVM_BIND_VALID_MASK     ((1ULL << NOUVEAU_SVM_BIND_VALID_BITS) - 1)
+
+
+/*
+ * NOUVEAU_BIND_COMMAND__MIGRATE: synchronous migrate to target memory.
+ * result: number of page successfuly migrate to the target memory.
+ */
+#define NOUVEAU_SVM_BIND_COMMAND__MIGRATE               0
+
+/*
+ * NOUVEAU_SVM_BIND_HEADER_TARGET__GPU_VRAM: target the GPU VRAM memory.
+ */
+#define NOUVEAU_SVM_BIND_TARGET__GPU_VRAM               (1UL << 31)
+
+
+#define DRM_IOCTL_NOUVEAU_SVM_INIT           DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_SVM_INIT, struct drm_nouveau_svm_init)
+#define DRM_IOCTL_NOUVEAU_SVM_BIND           DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_SVM_BIND, struct drm_nouveau_svm_bind)
+
 #define DRM_IOCTL_NOUVEAU_GEM_NEW            DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_GEM_NEW, struct drm_nouveau_gem_new)
 #define DRM_IOCTL_NOUVEAU_GEM_PUSHBUF        DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_GEM_PUSHBUF, struct drm_nouveau_gem_pushbuf)
 #define DRM_IOCTL_NOUVEAU_GEM_CPU_PREP       DRM_IOW (DRM_COMMAND_BASE + DRM_NOUVEAU_GEM_CPU_PREP, struct drm_nouveau_gem_cpu_prep)
diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h
index 7b6627783608..ea70669d2138 100644
--- a/include/uapi/drm/v3d_drm.h
+++ b/include/uapi/drm/v3d_drm.h
@@ -36,6 +36,7 @@ extern "C" {
 #define DRM_V3D_MMAP_BO                           0x03
 #define DRM_V3D_GET_PARAM                         0x04
 #define DRM_V3D_GET_BO_OFFSET                     0x05
+#define DRM_V3D_SUBMIT_TFU                        0x06
 
 #define DRM_IOCTL_V3D_SUBMIT_CL           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CL, struct drm_v3d_submit_cl)
 #define DRM_IOCTL_V3D_WAIT_BO             DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_WAIT_BO, struct drm_v3d_wait_bo)
@@ -43,6 +44,7 @@ extern "C" {
 #define DRM_IOCTL_V3D_MMAP_BO             DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_MMAP_BO, struct drm_v3d_mmap_bo)
 #define DRM_IOCTL_V3D_GET_PARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_GET_PARAM, struct drm_v3d_get_param)
 #define DRM_IOCTL_V3D_GET_BO_OFFSET       DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_GET_BO_OFFSET, struct drm_v3d_get_bo_offset)
+#define DRM_IOCTL_V3D_SUBMIT_TFU          DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_TFU, struct drm_v3d_submit_tfu)
 
 /**
  * struct drm_v3d_submit_cl - ioctl argument for submitting commands to the 3D
@@ -50,6 +52,14 @@ extern "C" {
  *
  * This asks the kernel to have the GPU execute an optional binner
  * command list, and a render command list.
+ *
+ * The L1T, slice, L2C, L2T, and GCA caches will be flushed before
+ * each CL executes.  The VCD cache should be flushed (if necessary)
+ * by the submitted CLs.  The TLB writes are guaranteed to have been
+ * flushed by the time the render done IRQ happens, which is the
+ * trigger for out_sync.  Any dirtying of cachelines by the job (only
+ * possible using TMU writes) must be flushed by the caller using the
+ * CL's cache flush commands.
  */
 struct drm_v3d_submit_cl {
 	/* Pointer to the binner command list.
@@ -58,10 +68,15 @@ struct drm_v3d_submit_cl {
 	 * coordinate shader to determine where primitives land on the screen,
 	 * then writes out the state updates and draw calls necessary per tile
 	 * to the tile allocation BO.
+	 *
+	 * This BCL will block on any previous BCL submitted on the
+	 * same FD, but not on any RCL or BCLs submitted by other
+	 * clients -- that is left up to the submitter to control
+	 * using in_sync_bcl if necessary.
 	 */
 	__u32 bcl_start;
 
-	 /** End address of the BCL (first byte after the BCL) */
+	/** End address of the BCL (first byte after the BCL) */
 	__u32 bcl_end;
 
 	/* Offset of the render command list.
@@ -69,10 +84,15 @@ struct drm_v3d_submit_cl {
 	 * This is the second set of commands executed, which will either
 	 * execute the tiles that have been set up by the BCL, or a fixed set
 	 * of tiles (in the case of RCL-only blits).
+	 *
+	 * This RCL will block on this submit's BCL, and any previous
+	 * RCL submitted on the same FD, but not on any RCL or BCLs
+	 * submitted by other clients -- that is left up to the
+	 * submitter to control using in_sync_rcl if necessary.
 	 */
 	__u32 rcl_start;
 
-	 /** End address of the RCL (first byte after the RCL) */
+	/** End address of the RCL (first byte after the RCL) */
 	__u32 rcl_end;
 
 	/** An optional sync object to wait on before starting the BCL. */
@@ -169,6 +189,7 @@ enum drm_v3d_param {
 	DRM_V3D_PARAM_V3D_CORE0_IDENT0,
 	DRM_V3D_PARAM_V3D_CORE0_IDENT1,
 	DRM_V3D_PARAM_V3D_CORE0_IDENT2,
+	DRM_V3D_PARAM_SUPPORTS_TFU,
 };
 
 struct drm_v3d_get_param {
@@ -187,6 +208,28 @@ struct drm_v3d_get_bo_offset {
 	__u32 offset;
 };
 
+struct drm_v3d_submit_tfu {
+	__u32 icfg;
+	__u32 iia;
+	__u32 iis;
+	__u32 ica;
+	__u32 iua;
+	__u32 ioa;
+	__u32 ios;
+	__u32 coef[4];
+	/* First handle is the output BO, following are other inputs.
+	 * 0 for unused.
+	 */
+	__u32 bo_handles[4];
+	/* sync object to block on before running the TFU job.  Each TFU
+	 * job will execute in the order submitted to its FD.  Synchronization
+	 * against rendering jobs requires using sync objects.
+	 */
+	__u32 in_sync;
+	/* Sync object to signal when the TFU job is done. */
+	__u32 out_sync;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h
index 9a781f0611df..f06a789f34cd 100644
--- a/include/uapi/drm/virtgpu_drm.h
+++ b/include/uapi/drm/virtgpu_drm.h
@@ -47,6 +47,13 @@ extern "C" {
 #define DRM_VIRTGPU_WAIT     0x08
 #define DRM_VIRTGPU_GET_CAPS  0x09
 
+#define VIRTGPU_EXECBUF_FENCE_FD_IN	0x01
+#define VIRTGPU_EXECBUF_FENCE_FD_OUT	0x02
+#define VIRTGPU_EXECBUF_FLAGS  (\
+		VIRTGPU_EXECBUF_FENCE_FD_IN |\
+		VIRTGPU_EXECBUF_FENCE_FD_OUT |\
+		0)
+
 struct drm_virtgpu_map {
 	__u64 offset; /* use for mmap system call */
 	__u32 handle;
@@ -54,12 +61,12 @@ struct drm_virtgpu_map {
 };
 
 struct drm_virtgpu_execbuffer {
-	__u32		flags;		/* for future use */
+	__u32 flags;
 	__u32 size;
 	__u64 command; /* void* */
 	__u64 bo_handles;
 	__u32 num_bo_handles;
-	__u32 pad;
+	__s32 fence_fd; /* in/out fence fd (see VIRTGPU_EXECBUF_FENCE_FD_IN/OUT) */
 };
 
 #define VIRTGPU_PARAM_3D_FEATURES 1 /* do we have 3D features in the hw */
@@ -137,7 +144,7 @@ struct drm_virtgpu_get_caps {
 	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_MAP, struct drm_virtgpu_map)
 
 #define DRM_IOCTL_VIRTGPU_EXECBUFFER \
-	DRM_IOW(DRM_COMMAND_BASE + DRM_VIRTGPU_EXECBUFFER,\
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_EXECBUFFER,\
 		struct drm_virtgpu_execbuffer)
 
 #define DRM_IOCTL_VIRTGPU_GETPARAM \