headers: Sync with drm-next

Taken from the drm-next pull for 4.17-rc1 (694f54f680f7), and manually
reconciled:

  core:
    - Dropped DRM_MODE_TYPE_ALL and DRM_MODE_FLAG_ALL; these are purely
      internal details of the bits accepted by the currently running
      kernel, and can not be generally relied on by userspace
    - Add HDCP flags
    - Note CTM entry representation is sign-magnitude format, not
      two's-complement
  amdgpu:
    - Add QUERY_STATE2 context op
    - Add VCN firmware version query
  etnaviv:
    - Add more GPU feature flags
  i915:
    - Add caps, params and ioctls for PMU / perf-stream
    - Add support for explicit fencing
  nouveau:
    - Add TILE_COMP layout
  vc4:
    - Add perfmon ioctls
  virtgpu:
    - Add capset-fix param
  vmware:
    - Add handle-close ioctl and explicit-fencing support

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>

7 files changed, 444 insertions, 26 deletions

diff --git a/include/drm/amdgpu_drm.h b/include/drm/amdgpu_drm.h
index f784f248..c363b67f 100644
--- a/include/drm/amdgpu_drm.h
+++ b/include/drm/amdgpu_drm.h
@@ -160,6 +160,7 @@ union drm_amdgpu_bo_list {
 #define AMDGPU_CTX_OP_ALLOC_CTX	1
 #define AMDGPU_CTX_OP_FREE_CTX	2
 #define AMDGPU_CTX_OP_QUERY_STATE	3
+#define AMDGPU_CTX_OP_QUERY_STATE2	4
 
 /* GPU reset status */
 #define AMDGPU_CTX_NO_RESET		0
@@ -170,6 +171,13 @@ union drm_amdgpu_bo_list {
 /* unknown cause */
 #define AMDGPU_CTX_UNKNOWN_RESET	3
 
+/* indicate gpu reset occured after ctx created */
+#define AMDGPU_CTX_QUERY2_FLAGS_RESET    (1<<0)
+/* indicate vram lost occured after ctx created */
+#define AMDGPU_CTX_QUERY2_FLAGS_VRAMLOST (1<<1)
+/* indicate some job from this context once cause gpu hang */
+#define AMDGPU_CTX_QUERY2_FLAGS_GUILTY   (1<<2)
+
 /* Context priority level */
 #define AMDGPU_CTX_PRIORITY_UNSET       -2048
 #define AMDGPU_CTX_PRIORITY_VERY_LOW    -1023
@@ -610,6 +618,8 @@ struct drm_amdgpu_cs_chunk_data {
 	#define AMDGPU_INFO_FW_SOS		0x0c
 	/* Subquery id: Query PSP ASD firmware version */
 	#define AMDGPU_INFO_FW_ASD		0x0d
+	/* Subquery id: Query VCN firmware version */
+	#define AMDGPU_INFO_FW_VCN		0x0e
 /* number of bytes moved for TTM migration */
 #define AMDGPU_INFO_NUM_BYTES_MOVED		0x0f
 /* the used VRAM size */
@@ -798,6 +808,7 @@ struct drm_amdgpu_info_firmware {
 #define AMDGPU_VRAM_TYPE_GDDR5 5
 #define AMDGPU_VRAM_TYPE_HBM   6
 #define AMDGPU_VRAM_TYPE_DDR3  7
+#define AMDGPU_VRAM_TYPE_DDR4  8
 
 struct drm_amdgpu_info_device {
 	/** PCI Device ID */
diff --git a/include/drm/drm_mode.h b/include/drm/drm_mode.h
index 5597a871..5f9fadbd 100644
--- a/include/drm/drm_mode.h
+++ b/include/drm/drm_mode.h
@@ -38,11 +38,11 @@ extern "C" {
 #define DRM_DISPLAY_MODE_LEN	32
 #define DRM_PROP_NAME_LEN	32
 
-#define DRM_MODE_TYPE_BUILTIN	(1<<0)
-#define DRM_MODE_TYPE_CLOCK_C	((1<<1) | DRM_MODE_TYPE_BUILTIN)
-#define DRM_MODE_TYPE_CRTC_C	((1<<2) | DRM_MODE_TYPE_BUILTIN)
+#define DRM_MODE_TYPE_BUILTIN	(1<<0) /* deprecated */
+#define DRM_MODE_TYPE_CLOCK_C	((1<<1) | DRM_MODE_TYPE_BUILTIN) /* deprecated */
+#define DRM_MODE_TYPE_CRTC_C	((1<<2) | DRM_MODE_TYPE_BUILTIN) /* deprecated */
 #define DRM_MODE_TYPE_PREFERRED	(1<<3)
-#define DRM_MODE_TYPE_DEFAULT	(1<<4)
+#define DRM_MODE_TYPE_DEFAULT	(1<<4) /* deprecated */
 #define DRM_MODE_TYPE_USERDEF	(1<<5)
 #define DRM_MODE_TYPE_DRIVER	(1<<6)
 
@@ -66,8 +66,8 @@ extern "C" {
 #define DRM_MODE_FLAG_PCSYNC			(1<<7)
 #define DRM_MODE_FLAG_NCSYNC			(1<<8)
 #define DRM_MODE_FLAG_HSKEW			(1<<9) /* hskew provided */
-#define DRM_MODE_FLAG_BCAST			(1<<10)
-#define DRM_MODE_FLAG_PIXMUX			(1<<11)
+#define DRM_MODE_FLAG_BCAST			(1<<10) /* deprecated */
+#define DRM_MODE_FLAG_PIXMUX			(1<<11) /* deprecated */
 #define DRM_MODE_FLAG_DBLCLK			(1<<12)
 #define DRM_MODE_FLAG_CLKDIV2			(1<<13)
  /*
@@ -173,6 +173,10 @@ extern "C" {
 		DRM_MODE_REFLECT_X | \
 		DRM_MODE_REFLECT_Y)
 
+/* Content Protection Flags */
+#define DRM_MODE_CONTENT_PROTECTION_UNDESIRED	0
+#define DRM_MODE_CONTENT_PROTECTION_DESIRED     1
+#define DRM_MODE_CONTENT_PROTECTION_ENABLED     2
 
 struct drm_mode_modeinfo {
 	__u32 clock;
@@ -341,7 +345,7 @@ struct drm_mode_get_connector {
 	__u32 pad;
 };
 
-#define DRM_MODE_PROP_PENDING	(1<<0)
+#define DRM_MODE_PROP_PENDING	(1<<0) /* deprecated, do not use */
 #define DRM_MODE_PROP_RANGE	(1<<1)
 #define DRM_MODE_PROP_IMMUTABLE	(1<<2)
 #define DRM_MODE_PROP_ENUM	(1<<3) /* enumerated type with text strings */
@@ -576,8 +580,11 @@ struct drm_mode_crtc_lut {
 };
 
 struct drm_color_ctm {
-	/* Conversion matrix in S31.32 format. */
-	__s64 matrix[9];
+	/*
+	 * Conversion matrix in S31.32 sign-magnitude
+	 * (not two's complement!) format.
+	 */
+	__u64 matrix[9];
 };
 
 struct drm_color_lut {
diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h
index 5ebe0462..16e452aa 100644
--- a/include/drm/i915_drm.h
+++ b/include/drm/i915_drm.h
@@ -86,6 +86,62 @@ enum i915_mocs_table_index {
 	I915_MOCS_CACHED,
 };
 
+/*
+ * 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.
+ */
+enum drm_i915_gem_engine_class {
+	I915_ENGINE_CLASS_RENDER	= 0,
+	I915_ENGINE_CLASS_COPY		= 1,
+	I915_ENGINE_CLASS_VIDEO		= 2,
+	I915_ENGINE_CLASS_VIDEO_ENHANCE	= 3,
+
+	I915_ENGINE_CLASS_INVALID	= -1
+};
+
+/**
+ * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915
+ *
+ */
+
+enum drm_i915_pmu_engine_sample {
+	I915_SAMPLE_BUSY = 0,
+	I915_SAMPLE_WAIT = 1,
+	I915_SAMPLE_SEMA = 2
+};
+
+#define I915_PMU_SAMPLE_BITS (4)
+#define I915_PMU_SAMPLE_MASK (0xf)
+#define I915_PMU_SAMPLE_INSTANCE_BITS (8)
+#define I915_PMU_CLASS_SHIFT \
+	(I915_PMU_SAMPLE_BITS + I915_PMU_SAMPLE_INSTANCE_BITS)
+
+#define __I915_PMU_ENGINE(class, instance, sample) \
+	((class) << I915_PMU_CLASS_SHIFT | \
+	(instance) << I915_PMU_SAMPLE_BITS | \
+	(sample))
+
+#define I915_PMU_ENGINE_BUSY(class, instance) \
+	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_BUSY)
+
+#define I915_PMU_ENGINE_WAIT(class, instance) \
+	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_WAIT)
+
+#define I915_PMU_ENGINE_SEMA(class, instance) \
+	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA)
+
+#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x))
+
+#define I915_PMU_ACTUAL_FREQUENCY	__I915_PMU_OTHER(0)
+#define I915_PMU_REQUESTED_FREQUENCY	__I915_PMU_OTHER(1)
+#define I915_PMU_INTERRUPTS		__I915_PMU_OTHER(2)
+#define I915_PMU_RC6_RESIDENCY		__I915_PMU_OTHER(3)
+
+#define I915_PMU_LAST I915_PMU_RC6_RESIDENCY
+
 /* Each region is a minimum of 16k, and there are at most 255 of them.
  */
 #define I915_NR_TEX_REGIONS 255	/* table size 2k - maximum due to use
@@ -260,6 +316,9 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_GEM_CONTEXT_GETPARAM	0x34
 #define DRM_I915_GEM_CONTEXT_SETPARAM	0x35
 #define DRM_I915_PERF_OPEN		0x36
+#define DRM_I915_PERF_ADD_CONFIG	0x37
+#define DRM_I915_PERF_REMOVE_CONFIG	0x38
+#define DRM_I915_QUERY			0x39
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
 #define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
@@ -315,6 +374,9 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param)
 #define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param)
 #define DRM_IOCTL_I915_PERF_OPEN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
+#define DRM_IOCTL_I915_PERF_ADD_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
+#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
+#define DRM_IOCTL_I915_QUERY			DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -393,10 +455,20 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_MIN_EU_IN_POOL	 39
 #define I915_PARAM_MMAP_GTT_VERSION	 40
 
-/* Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
  * priorities and the driver will attempt to execute batches in priority order.
+ * The param returns a capability bitmask, nonzero implies that the scheduler
+ * is enabled, with different features present according to the mask.
+ *
+ * The initial priority for each batch is supplied by the context and is
+ * controlled via I915_CONTEXT_PARAM_PRIORITY.
  */
 #define I915_PARAM_HAS_SCHEDULER	 41
+#define   I915_SCHEDULER_CAP_ENABLED	(1ul << 0)
+#define   I915_SCHEDULER_CAP_PRIORITY	(1ul << 1)
+#define   I915_SCHEDULER_CAP_PREEMPTION	(1ul << 2)
+
 #define I915_PARAM_HUC_STATUS		 42
 
 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of
@@ -412,6 +484,51 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_HAS_EXEC_FENCE	 44
 
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture
+ * user specified bufffers for post-mortem debugging of GPU hangs. See
+ * EXEC_OBJECT_CAPTURE.
+ */
+#define I915_PARAM_HAS_EXEC_CAPTURE	 45
+
+#define I915_PARAM_SLICE_MASK		 46
+
+/* Assuming it's uniform for each slice, this queries the mask of subslices
+ * per-slice for this system.
+ */
+#define I915_PARAM_SUBSLICE_MASK	 47
+
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying the batch buffer
+ * as the first execobject as opposed to the last. See I915_EXEC_BATCH_FIRST.
+ */
+#define I915_PARAM_HAS_EXEC_BATCH_FIRST	 48
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * drm_i915_gem_exec_fence structures.  See I915_EXEC_FENCE_ARRAY.
+ */
+#define I915_PARAM_HAS_EXEC_FENCE_ARRAY  49
+
+/*
+ * Query whether every context (both per-file default and user created) is
+ * isolated (insofar as HW supports). If this parameter is not true, then
+ * freshly created contexts may inherit values from an existing context,
+ * rather than default HW values. If true, it also ensures (insofar as HW
+ * supports) that all state set by this context will not leak to any other
+ * context.
+ *
+ * As not every engine across every gen support contexts, the returned
+ * value reports the support of context isolation for individual engines by
+ * returning a bitmask of each engine class set to true if that class supports
+ * isolation.
+ */
+#define I915_PARAM_HAS_CONTEXT_ISOLATION 50
+
+/* Frequency of the command streamer timestamps given by the *_TIMESTAMP
+ * registers. This used to be fixed per platform but from CNL onwards, this
+ * might vary depending on the parts.
+ */
+#define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51
+
 typedef struct drm_i915_getparam {
 	__s32 param;
 	/*
@@ -666,6 +783,8 @@ struct drm_i915_gem_relocation_entry {
 #define I915_GEM_DOMAIN_VERTEX		0x00000020
 /** GTT domain - aperture and scanout */
 #define I915_GEM_DOMAIN_GTT		0x00000040
+/** WC domain - uncached access */
+#define I915_GEM_DOMAIN_WC		0x00000080
 /** @} */
 
 struct drm_i915_gem_exec_object {
@@ -773,8 +892,15 @@ struct drm_i915_gem_exec_object2 {
  * I915_PARAM_HAS_EXEC_FENCE to order execbufs and execute them asynchronously.
  */
 #define EXEC_OBJECT_ASYNC		(1<<6)
+/* Request that the contents of this execobject be copied into the error
+ * state upon a GPU hang involving this batch for post-mortem debugging.
+ * These buffers are recorded in no particular order as "user" in
+ * /sys/class/drm/cardN/error. Query I915_PARAM_HAS_EXEC_CAPTURE to see
+ * if the kernel supports this flag.
+ */
+#define EXEC_OBJECT_CAPTURE		(1<<7)
 /* All remaining bits are MBZ and RESERVED FOR FUTURE USE */
-#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_ASYNC<<1)
+#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_CAPTURE<<1)
 	__u64 flags;
 
 	union {
@@ -784,6 +910,18 @@ struct drm_i915_gem_exec_object2 {
 	__u64 rsvd2;
 };
 
+struct drm_i915_gem_exec_fence {
+	/**
+	 * User's handle for a drm_syncobj to wait on or signal.
+	 */
+	__u32 handle;
+
+#define I915_EXEC_FENCE_WAIT            (1<<0)
+#define I915_EXEC_FENCE_SIGNAL          (1<<1)
+#define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SIGNAL << 1))
+	__u32 flags;
+};
+
 struct drm_i915_gem_execbuffer2 {
 	/**
 	 * List of gem_exec_object2 structs
@@ -798,7 +936,11 @@ struct drm_i915_gem_execbuffer2 {
 	__u32 DR1;
 	__u32 DR4;
 	__u32 num_cliprects;
-	/** This is a struct drm_clip_rect *cliprects */
+	/**
+	 * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
+	 * is not set.  If I915_EXEC_FENCE_ARRAY is set, then this is a
+	 * struct drm_i915_gem_exec_fence *fences.
+	 */
 	__u64 cliprects_ptr;
 #define I915_EXEC_RING_MASK              (7<<0)
 #define I915_EXEC_DEFAULT                (0<<0)
@@ -889,7 +1031,24 @@ struct drm_i915_gem_execbuffer2 {
  */
 #define I915_EXEC_FENCE_OUT		(1<<17)
 
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_OUT<<1))
+/*
+ * Traditionally the execbuf ioctl has only considered the final element in
+ * the execobject[] to be the executable batch. Often though, the client
+ * will known the batch object prior to construction and being able to place
+ * it into the execobject[] array first can simplify the relocation tracking.
+ * Setting I915_EXEC_BATCH_FIRST tells execbuf to use element 0 of the
+ * execobject[] as the * batch instead (the default is to use the last
+ * element).
+ */
+#define I915_EXEC_BATCH_FIRST		(1<<18)
+
+/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr
+ * define an array of i915_gem_exec_fence structures which specify a set of
+ * dma fences to wait upon or signal.
+ */
+#define I915_EXEC_FENCE_ARRAY   (1<<19)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1))
 
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
@@ -1201,7 +1360,9 @@ struct drm_intel_overlay_attrs {
  * active on a given plane.
  */
 
-#define I915_SET_COLORKEY_NONE		(1<<0) /* disable color key matching */
+#define I915_SET_COLORKEY_NONE		(1<<0) /* Deprecated. Instead set
+						* flags==0 to disable colorkeying.
+						*/
 #define I915_SET_COLORKEY_DESTINATION	(1<<1)
 #define I915_SET_COLORKEY_SOURCE	(1<<2)
 struct drm_intel_sprite_colorkey {
@@ -1239,14 +1400,16 @@ struct drm_i915_reg_read {
 	 * be specified
 	 */
 	__u64 offset;
+#define I915_REG_READ_8B_WA (1ul << 0)
+
 	__u64 val; /* Return value */
 };
 /* Known registers:
  *
  * Render engine timestamp - 0x2358 + 64bit - gen7+
  * - Note this register returns an invalid value if using the default
- *   single instruction 8byte read, in order to workaround that use
- *   offset (0x2538 | 1) instead.
+ *   single instruction 8byte read, in order to workaround that pass
+ *   flag I915_REG_READ_8B_WA in offset field.
  *
  */
 
@@ -1289,17 +1452,26 @@ struct drm_i915_gem_context_param {
 #define I915_CONTEXT_PARAM_GTT_SIZE	0x3
 #define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE	0x4
 #define I915_CONTEXT_PARAM_BANNABLE	0x5
+#define I915_CONTEXT_PARAM_PRIORITY	0x6
+#define   I915_CONTEXT_MAX_USER_PRIORITY	1023 /* inclusive */
+#define   I915_CONTEXT_DEFAULT_PRIORITY		0
+#define   I915_CONTEXT_MIN_USER_PRIORITY	-1023 /* inclusive */
 	__u64 value;
 };
 
 enum drm_i915_oa_format {
-	I915_OA_FORMAT_A13 = 1,
-	I915_OA_FORMAT_A29,
-	I915_OA_FORMAT_A13_B8_C8,
-	I915_OA_FORMAT_B4_C8,
-	I915_OA_FORMAT_A45_B8_C8,
-	I915_OA_FORMAT_B4_C8_A16,
-	I915_OA_FORMAT_C4_B8,
+	I915_OA_FORMAT_A13 = 1,	    /* HSW only */
+	I915_OA_FORMAT_A29,	    /* HSW only */
+	I915_OA_FORMAT_A13_B8_C8,   /* HSW only */
+	I915_OA_FORMAT_B4_C8,	    /* HSW only */
+	I915_OA_FORMAT_A45_B8_C8,   /* HSW only */
+	I915_OA_FORMAT_B4_C8_A16,   /* HSW only */
+	I915_OA_FORMAT_C4_B8,	    /* HSW+ */
+
+	/* Gen8+ */
+	I915_OA_FORMAT_A12,
+	I915_OA_FORMAT_A12_B8_C8,
+	I915_OA_FORMAT_A32u40_A4u32_B8_C8,
 
 	I915_OA_FORMAT_MAX	    /* non-ABI */
 };
@@ -1424,6 +1596,127 @@ enum drm_i915_perf_record_type {
 	DRM_I915_PERF_RECORD_MAX /* non-ABI */
 };
 
+/**
+ * Structure to upload perf dynamic configuration into the kernel.
+ */
+struct drm_i915_perf_oa_config {
+	/** String formatted like "%08x-%04x-%04x-%04x-%012x" */
+	char uuid[36];
+
+	__u32 n_mux_regs;
+	__u32 n_boolean_regs;
+	__u32 n_flex_regs;
+
+	/*
+	 * These fields are pointers to tuples of u32 values (register address,
+	 * value). For example the expected length of the buffer pointed by
+	 * mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
+	 */
+	__u64 mux_regs_ptr;
+	__u64 boolean_regs_ptr;
+	__u64 flex_regs_ptr;
+};
+
+struct drm_i915_query_item {
+	__u64 query_id;
+#define DRM_I915_QUERY_TOPOLOGY_INFO    1
+
+	/*
+	 * When set to zero by userspace, this is filled with the size of the
+	 * data to be written at the data_ptr pointer. The kernel sets this
+	 * value to a negative value to signal an error on a particular query
+	 * item.
+	 */
+	__s32 length;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * Data will be written at the location pointed by data_ptr when the
+	 * value of length matches the length of the data to be written by the
+	 * kernel.
+	 */
+	__u64 data_ptr;
+};
+
+struct drm_i915_query {
+	__u32 num_items;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * This points to an array of num_items drm_i915_query_item structures.
+	 */
+	__u64 items_ptr;
+};
+
+/*
+ * Data written by the kernel with query DRM_I915_QUERY_TOPOLOGY_INFO :
+ *
+ * data: contains the 3 pieces of information :
+ *
+ * - the slice mask with one bit per slice telling whether a slice is
+ *   available. The availability of slice X can be queried with the following
+ *   formula :
+ *
+ *           (data[X / 8] >> (X % 8)) & 1
+ *
+ * - the subslice mask for each slice with one bit per subslice telling
+ *   whether a subslice is available. The availability of subslice Y in slice
+ *   X can be queried with the following formula :
+ *
+ *           (data[subslice_offset +
+ *                 X * subslice_stride +
+ *                 Y / 8] >> (Y % 8)) & 1
+ *
+ * - the EU mask for each subslice in each slice with one bit per EU telling
+ *   whether an EU is available. The availability of EU Z in subslice Y in
+ *   slice X can be queried with the following formula :
+ *
+ *           (data[eu_offset +
+ *                 (X * max_subslices + Y) * eu_stride +
+ *                 Z / 8] >> (Z % 8)) & 1
+ */
+struct drm_i915_query_topology_info {
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u16 flags;
+
+	__u16 max_slices;
+	__u16 max_subslices;
+	__u16 max_eus_per_subslice;
+
+	/*
+	 * Offset in data[] at which the subslice masks are stored.
+	 */
+	__u16 subslice_offset;
+
+	/*
+	 * Stride at which each of the subslice masks for each slice are
+	 * stored.
+	 */
+	__u16 subslice_stride;
+
+	/*
+	 * Offset in data[] at which the EU masks are stored.
+	 */
+	__u16 eu_offset;
+
+	/*
+	 * Stride at which each of the EU masks for each subslice are stored.
+	 */
+	__u16 eu_stride;
+
+	__u8 data[];
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/drm/nouveau_drm.h b/include/drm/nouveau_drm.h
index cb077821..d42105c8 100644
--- a/include/drm/nouveau_drm.h
+++ b/include/drm/nouveau_drm.h
@@ -104,6 +104,7 @@ struct drm_nouveau_setparam {
 #define NOUVEAU_GEM_DOMAIN_MAPPABLE  (1 << 3)
 #define NOUVEAU_GEM_DOMAIN_COHERENT  (1 << 4)
 
+#define NOUVEAU_GEM_TILE_COMP        0x00030000 /* nv50-only */
 #define NOUVEAU_GEM_TILE_LAYOUT_MASK 0x0000ff00
 #define NOUVEAU_GEM_TILE_16BPP       0x00000001
 #define NOUVEAU_GEM_TILE_32BPP       0x00000002
diff --git a/include/drm/vc4_drm.h b/include/drm/vc4_drm.h
index 3415a4b7..4117117b 100644
--- a/include/drm/vc4_drm.h
+++ b/include/drm/vc4_drm.h
@@ -42,6 +42,9 @@ extern "C" {
 #define DRM_VC4_GET_TILING                        0x09
 #define DRM_VC4_LABEL_BO                          0x0a
 #define DRM_VC4_GEM_MADVISE                       0x0b
+#define DRM_VC4_PERFMON_CREATE                    0x0c
+#define DRM_VC4_PERFMON_DESTROY                   0x0d
+#define DRM_VC4_PERFMON_GET_VALUES                0x0e
 
 #define DRM_IOCTL_VC4_SUBMIT_CL           DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_SUBMIT_CL, struct drm_vc4_submit_cl)
 #define DRM_IOCTL_VC4_WAIT_SEQNO          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_WAIT_SEQNO, struct drm_vc4_wait_seqno)
@@ -55,6 +58,9 @@ extern "C" {
 #define DRM_IOCTL_VC4_GET_TILING          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GET_TILING, struct drm_vc4_get_tiling)
 #define DRM_IOCTL_VC4_LABEL_BO            DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_LABEL_BO, struct drm_vc4_label_bo)
 #define DRM_IOCTL_VC4_GEM_MADVISE         DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GEM_MADVISE, struct drm_vc4_gem_madvise)
+#define DRM_IOCTL_VC4_PERFMON_CREATE      DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_PERFMON_CREATE, struct drm_vc4_perfmon_create)
+#define DRM_IOCTL_VC4_PERFMON_DESTROY     DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_PERFMON_DESTROY, struct drm_vc4_perfmon_destroy)
+#define DRM_IOCTL_VC4_PERFMON_GET_VALUES  DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_PERFMON_GET_VALUES, struct drm_vc4_perfmon_get_values)
 
 struct drm_vc4_submit_rcl_surface {
 	__u32 hindex; /* Handle index, or ~0 if not present. */
@@ -173,6 +179,15 @@ struct drm_vc4_submit_cl {
 	 * wait ioctl).
 	 */
 	__u64 seqno;
+
+	/* ID of the perfmon to attach to this job. 0 means no perfmon. */
+	__u32 perfmonid;
+
+	/* Unused field to align this struct on 64 bits. Must be set to 0.
+	 * If one ever needs to add an u32 field to this struct, this field
+	 * can be used.
+	 */
+	__u32 pad2;
 };
 
 /**
@@ -308,6 +323,7 @@ struct drm_vc4_get_hang_state {
 #define DRM_VC4_PARAM_SUPPORTS_THREADED_FS	5
 #define DRM_VC4_PARAM_SUPPORTS_FIXED_RCL_ORDER	6
 #define DRM_VC4_PARAM_SUPPORTS_MADVISE		7
+#define DRM_VC4_PARAM_SUPPORTS_PERFMON		8
 
 struct drm_vc4_get_param {
 	__u32 param;
@@ -352,6 +368,66 @@ struct drm_vc4_gem_madvise {
 	__u32 pad;
 };
 
+enum {
+	VC4_PERFCNT_FEP_VALID_PRIMS_NO_RENDER,
+	VC4_PERFCNT_FEP_VALID_PRIMS_RENDER,
+	VC4_PERFCNT_FEP_CLIPPED_QUADS,
+	VC4_PERFCNT_FEP_VALID_QUADS,
+	VC4_PERFCNT_TLB_QUADS_NOT_PASSING_STENCIL,
+	VC4_PERFCNT_TLB_QUADS_NOT_PASSING_Z_AND_STENCIL,
+	VC4_PERFCNT_TLB_QUADS_PASSING_Z_AND_STENCIL,
+	VC4_PERFCNT_TLB_QUADS_ZERO_COVERAGE,
+	VC4_PERFCNT_TLB_QUADS_NON_ZERO_COVERAGE,
+	VC4_PERFCNT_TLB_QUADS_WRITTEN_TO_COLOR_BUF,
+	VC4_PERFCNT_PLB_PRIMS_OUTSIDE_VIEWPORT,
+	VC4_PERFCNT_PLB_PRIMS_NEED_CLIPPING,
+	VC4_PERFCNT_PSE_PRIMS_REVERSED,
+	VC4_PERFCNT_QPU_TOTAL_IDLE_CYCLES,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_VERTEX_COORD_SHADING,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_FRAGMENT_SHADING,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_EXEC_VALID_INST,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_WAITING_TMUS,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_WAITING_SCOREBOARD,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_WAITING_VARYINGS,
+	VC4_PERFCNT_QPU_TOTAL_INST_CACHE_HIT,
+	VC4_PERFCNT_QPU_TOTAL_INST_CACHE_MISS,
+	VC4_PERFCNT_QPU_TOTAL_UNIFORM_CACHE_HIT,
+	VC4_PERFCNT_QPU_TOTAL_UNIFORM_CACHE_MISS,
+	VC4_PERFCNT_TMU_TOTAL_TEXT_QUADS_PROCESSED,
+	VC4_PERFCNT_TMU_TOTAL_TEXT_CACHE_MISS,
+	VC4_PERFCNT_VPM_TOTAL_CLK_CYCLES_VDW_STALLED,
+	VC4_PERFCNT_VPM_TOTAL_CLK_CYCLES_VCD_STALLED,
+	VC4_PERFCNT_L2C_TOTAL_L2_CACHE_HIT,
+	VC4_PERFCNT_L2C_TOTAL_L2_CACHE_MISS,
+	VC4_PERFCNT_NUM_EVENTS,
+};
+
+#define DRM_VC4_MAX_PERF_COUNTERS	16
+
+struct drm_vc4_perfmon_create {
+	__u32 id;
+	__u32 ncounters;
+	__u8 events[DRM_VC4_MAX_PERF_COUNTERS];
+};
+
+struct drm_vc4_perfmon_destroy {
+	__u32 id;
+};
+
+/*
+ * Returns the values of the performance counters tracked by this
+ * perfmon (as an array of ncounters u64 values).
+ *
+ * No implicit synchronization is performed, so the user has to
+ * guarantee that any jobs using this perfmon have already been
+ * completed  (probably by blocking on the seqno returned by the
+ * last exec that used the perfmon).
+ */
+struct drm_vc4_perfmon_get_values {
+	__u32 id;
+	__u64 values_ptr;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/drm/virtgpu_drm.h b/include/drm/virtgpu_drm.h
index 91a31ffe..9a781f06 100644
--- a/include/drm/virtgpu_drm.h
+++ b/include/drm/virtgpu_drm.h
@@ -63,6 +63,7 @@ struct drm_virtgpu_execbuffer {
 };
 
 #define VIRTGPU_PARAM_3D_FEATURES 1 /* do we have 3D features in the hw */
+#define VIRTGPU_PARAM_CAPSET_QUERY_FIX 2 /* do we have the capset fix */
 
 struct drm_virtgpu_getparam {
 	__u64 param;
diff --git a/include/drm/vmwgfx_drm.h b/include/drm/vmwgfx_drm.h
index d325a410..0bc784f5 100644
--- a/include/drm/vmwgfx_drm.h
+++ b/include/drm/vmwgfx_drm.h
@@ -41,6 +41,7 @@ extern "C" {
 #define DRM_VMW_GET_PARAM            0
 #define DRM_VMW_ALLOC_DMABUF         1
 #define DRM_VMW_UNREF_DMABUF         2
+#define DRM_VMW_HANDLE_CLOSE         2
 #define DRM_VMW_CURSOR_BYPASS        3
 /* guarded by DRM_VMW_PARAM_NUM_STREAMS != 0*/
 #define DRM_VMW_CONTROL_STREAM       4
@@ -296,13 +297,17 @@ union drm_vmw_surface_reference_arg {
  * @version: Allows expanding the execbuf ioctl parameters without breaking
  * backwards compatibility, since user-space will always tell the kernel
  * which version it uses.
- * @flags: Execbuf flags. None currently.
+ * @flags: Execbuf flags.
+ * @imported_fence_fd:  FD for a fence imported from another device
  *
  * Argument to the DRM_VMW_EXECBUF Ioctl.
  */
 
 #define DRM_VMW_EXECBUF_VERSION 2
 
+#define DRM_VMW_EXECBUF_FLAG_IMPORT_FENCE_FD (1 << 0)
+#define DRM_VMW_EXECBUF_FLAG_EXPORT_FENCE_FD (1 << 1)
+
 struct drm_vmw_execbuf_arg {
 	__u64 commands;
 	__u32 command_size;
@@ -311,7 +316,7 @@ struct drm_vmw_execbuf_arg {
 	__u32 version;
 	__u32 flags;
 	__u32 context_handle;
-	__u32 pad64;
+	__s32 imported_fence_fd;
 };
 
 /**
@@ -327,6 +332,7 @@ struct drm_vmw_execbuf_arg {
  * @passed_seqno: The highest seqno number processed by the hardware
  * so far. This can be used to mark user-space fence objects as signaled, and
  * to determine whether a fence seqno might be stale.
+ * @fd: FD associated with the fence, -1 if not exported
  * @error: This member should've been set to -EFAULT on submission.
  * The following actions should be take on completion:
  * error == -EFAULT: Fence communication failed. The host is synchronized.
@@ -344,7 +350,7 @@ struct drm_vmw_fence_rep {
 	__u32 mask;
 	__u32 seqno;
 	__u32 passed_seqno;
-	__u32 pad64;
+	__s32 fd;
 	__s32 error;
 };
 
@@ -1092,6 +1098,29 @@ union drm_vmw_extended_context_arg {
 	struct drm_vmw_context_arg rep;
 };
 
+/*************************************************************************/
+/*
+ * DRM_VMW_HANDLE_CLOSE - Close a user-space handle and release its
+ * underlying resource.
+ *
+ * Note that this ioctl is overlaid on the DRM_VMW_UNREF_DMABUF Ioctl.
+ * The ioctl arguments therefore need to be identical in layout.
+ *
+ */
+
+/**
+ * struct drm_vmw_handle_close_arg
+ *
+ * @handle: Handle to close.
+ *
+ * Argument to the DRM_VMW_HANDLE_CLOSE Ioctl.
+ */
+struct drm_vmw_handle_close_arg {
+	__u32 handle;
+	__u32 pad64;
+};
+
+
 #if defined(__cplusplus)
 }
 #endif