include/drm-uapi: Bump headers

From drm-next at the following commit:

    commit a22c074fd1dd52a8b41dd6789220409b64093e9c
    Merge: cb22f12f3025 3bfa7d40ce73
    Author: Dave Airlie <airlied@redhat.com>
    Date:   Thu Aug 12 11:20:16 2021 +1000

        Merge tag 'drm-intel-next-2021-08-10-1' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Acked-by: Kenneth Graunke <kenneth@whitecape.org>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11888>

6 files changed, 645 insertions, 98 deletions

diff --git a/include/drm-uapi/drm.h b/include/drm-uapi/drm.h
index 398c396f799..5e54c3aa4c3 100644
--- a/include/drm-uapi/drm.h
+++ b/include/drm-uapi/drm.h
@@ -629,8 +629,8 @@ struct drm_gem_open {
 /**
  * DRM_CAP_VBLANK_HIGH_CRTC
  *
- * If set to 1, the kernel supports specifying a CRTC index in the high bits of
- * &drm_wait_vblank_request.type.
+ * If set to 1, the kernel supports specifying a :ref:`CRTC index<crtc_index>`
+ * in the high bits of &drm_wait_vblank_request.type.
  *
  * Starting kernel version 2.6.39, this capability is always set to 1.
  */
@@ -1044,6 +1044,16 @@ extern "C" {
 #define DRM_IOCTL_MODE_GETPROPBLOB	DRM_IOWR(0xAC, struct drm_mode_get_blob)
 #define DRM_IOCTL_MODE_GETFB		DRM_IOWR(0xAD, struct drm_mode_fb_cmd)
 #define DRM_IOCTL_MODE_ADDFB		DRM_IOWR(0xAE, struct drm_mode_fb_cmd)
+/**
+ * DRM_IOCTL_MODE_RMFB - Remove a framebuffer.
+ *
+ * This removes a framebuffer previously added via ADDFB/ADDFB2. The IOCTL
+ * argument is a framebuffer object ID.
+ *
+ * Warning: removing a framebuffer currently in-use on an enabled plane will
+ * disable that plane. The CRTC the plane is linked to may also be disabled
+ * (depending on driver capabilities).
+ */
 #define DRM_IOCTL_MODE_RMFB		DRM_IOWR(0xAF, unsigned int)
 #define DRM_IOCTL_MODE_PAGE_FLIP	DRM_IOWR(0xB0, struct drm_mode_crtc_page_flip)
 #define DRM_IOCTL_MODE_DIRTYFB		DRM_IOWR(0xB1, struct drm_mode_fb_dirty_cmd)
diff --git a/include/drm-uapi/drm_fourcc.h b/include/drm-uapi/drm_fourcc.h
index cd3ce8a8c60..957c7be2923 100644
--- a/include/drm-uapi/drm_fourcc.h
+++ b/include/drm-uapi/drm_fourcc.h
@@ -900,9 +900,9 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
 
 /*
  * The top 4 bits (out of the 56 bits alloted for specifying vendor specific
- * modifiers) denote the category for modifiers. Currently we have only two
- * categories of modifiers ie AFBC and MISC. We can have a maximum of sixteen
- * different categories.
+ * modifiers) denote the category for modifiers. Currently we have three
+ * categories of modifiers ie AFBC, MISC and AFRC. We can have a maximum of
+ * sixteen different categories.
  */
 #define DRM_FORMAT_MOD_ARM_CODE(__type, __val) \
 	fourcc_mod_code(ARM, ((__u64)(__type) << 52) | ((__val) & 0x000fffffffffffffULL))
@@ -1018,6 +1018,109 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
 #define AFBC_FORMAT_MOD_USM	(1ULL << 12)
 
 /*
+ * Arm Fixed-Rate Compression (AFRC) modifiers
+ *
+ * AFRC is a proprietary fixed rate image compression protocol and format,
+ * designed to provide guaranteed bandwidth and memory footprint
+ * reductions in graphics and media use-cases.
+ *
+ * AFRC buffers consist of one or more planes, with the same components
+ * and meaning as an uncompressed buffer using the same pixel format.
+ *
+ * Within each plane, the pixel/luma/chroma values are grouped into
+ * "coding unit" blocks which are individually compressed to a
+ * fixed size (in bytes). All coding units within a given plane of a buffer
+ * store the same number of values, and have the same compressed size.
+ *
+ * The coding unit size is configurable, allowing different rates of compression.
+ *
+ * The start of each AFRC buffer plane must be aligned to an alignment granule which
+ * depends on the coding unit size.
+ *
+ * Coding Unit Size   Plane Alignment
+ * ----------------   ---------------
+ * 16 bytes           1024 bytes
+ * 24 bytes           512  bytes
+ * 32 bytes           2048 bytes
+ *
+ * Coding units are grouped into paging tiles. AFRC buffer dimensions must be aligned
+ * to a multiple of the paging tile dimensions.
+ * The dimensions of each paging tile depend on whether the buffer is optimised for
+ * scanline (SCAN layout) or rotated (ROT layout) access.
+ *
+ * Layout   Paging Tile Width   Paging Tile Height
+ * ------   -----------------   ------------------
+ * SCAN     16 coding units     4 coding units
+ * ROT      8  coding units     8 coding units
+ *
+ * The dimensions of each coding unit depend on the number of components
+ * in the compressed plane and whether the buffer is optimised for
+ * scanline (SCAN layout) or rotated (ROT layout) access.
+ *
+ * Number of Components in Plane   Layout      Coding Unit Width   Coding Unit Height
+ * -----------------------------   ---------   -----------------   ------------------
+ * 1                               SCAN        16 samples          4 samples
+ * Example: 16x4 luma samples in a 'Y' plane
+ *          16x4 chroma 'V' values, in the 'V' plane of a fully-planar YUV buffer
+ * -----------------------------   ---------   -----------------   ------------------
+ * 1                               ROT         8 samples           8 samples
+ * Example: 8x8 luma samples in a 'Y' plane
+ *          8x8 chroma 'V' values, in the 'V' plane of a fully-planar YUV buffer
+ * -----------------------------   ---------   -----------------   ------------------
+ * 2                               DONT CARE   8 samples           4 samples
+ * Example: 8x4 chroma pairs in the 'UV' plane of a semi-planar YUV buffer
+ * -----------------------------   ---------   -----------------   ------------------
+ * 3                               DONT CARE   4 samples           4 samples
+ * Example: 4x4 pixels in an RGB buffer without alpha
+ * -----------------------------   ---------   -----------------   ------------------
+ * 4                               DONT CARE   4 samples           4 samples
+ * Example: 4x4 pixels in an RGB buffer with alpha
+ */
+
+#define DRM_FORMAT_MOD_ARM_TYPE_AFRC 0x02
+
+#define DRM_FORMAT_MOD_ARM_AFRC(__afrc_mode) \
+	DRM_FORMAT_MOD_ARM_CODE(DRM_FORMAT_MOD_ARM_TYPE_AFRC, __afrc_mode)
+
+/*
+ * AFRC coding unit size modifier.
+ *
+ * Indicates the number of bytes used to store each compressed coding unit for
+ * one or more planes in an AFRC encoded buffer. The coding unit size for chrominance
+ * is the same for both Cb and Cr, which may be stored in separate planes.
+ *
+ * AFRC_FORMAT_MOD_CU_SIZE_P0 indicates the number of bytes used to store
+ * each compressed coding unit in the first plane of the buffer. For RGBA buffers
+ * this is the only plane, while for semi-planar and fully-planar YUV buffers,
+ * this corresponds to the luma plane.
+ *
+ * AFRC_FORMAT_MOD_CU_SIZE_P12 indicates the number of bytes used to store
+ * each compressed coding unit in the second and third planes in the buffer.
+ * For semi-planar and fully-planar YUV buffers, this corresponds to the chroma plane(s).
+ *
+ * For single-plane buffers, AFRC_FORMAT_MOD_CU_SIZE_P0 must be specified
+ * and AFRC_FORMAT_MOD_CU_SIZE_P12 must be zero.
+ * For semi-planar and fully-planar buffers, both AFRC_FORMAT_MOD_CU_SIZE_P0 and
+ * AFRC_FORMAT_MOD_CU_SIZE_P12 must be specified.
+ */
+#define AFRC_FORMAT_MOD_CU_SIZE_MASK 0xf
+#define AFRC_FORMAT_MOD_CU_SIZE_16 (1ULL)
+#define AFRC_FORMAT_MOD_CU_SIZE_24 (2ULL)
+#define AFRC_FORMAT_MOD_CU_SIZE_32 (3ULL)
+
+#define AFRC_FORMAT_MOD_CU_SIZE_P0(__afrc_cu_size) (__afrc_cu_size)
+#define AFRC_FORMAT_MOD_CU_SIZE_P12(__afrc_cu_size) ((__afrc_cu_size) << 4)
+
+/*
+ * AFRC scanline memory layout.
+ *
+ * Indicates if the buffer uses the scanline-optimised layout
+ * for an AFRC encoded buffer, otherwise, it uses the rotation-optimised layout.
+ * The memory layout is the same for all planes.
+ */
+#define AFRC_FORMAT_MOD_LAYOUT_SCAN (1ULL << 8)
+
+/*
  * Arm 16x16 Block U-Interleaved modifier
  *
  * This is used by Arm Mali Utgard and Midgard GPUs. It divides the image
diff --git a/include/drm-uapi/drm_mode.h b/include/drm-uapi/drm_mode.h
index 9b6722d45f3..90c55383f1e 100644
--- a/include/drm-uapi/drm_mode.h
+++ b/include/drm-uapi/drm_mode.h
@@ -312,16 +312,48 @@ struct drm_mode_set_plane {
 	__u32 src_w;
 };
 
+/**
+ * struct drm_mode_get_plane - Get plane metadata.
+ *
+ * Userspace can perform a GETPLANE ioctl to retrieve information about a
+ * plane.
+ *
+ * To retrieve the number of formats supported, set @count_format_types to zero
+ * and call the ioctl. @count_format_types will be updated with the value.
+ *
+ * To retrieve these formats, allocate an array with the memory needed to store
+ * @count_format_types formats. Point @format_type_ptr to this array and call
+ * the ioctl again (with @count_format_types still set to the value returned in
+ * the first ioctl call).
+ */
 struct drm_mode_get_plane {
+	/**
+	 * @plane_id: Object ID of the plane whose information should be
+	 * retrieved. Set by caller.
+	 */
 	__u32 plane_id;
 
+	/** @crtc_id: Object ID of the current CRTC. */
 	__u32 crtc_id;
+	/** @fb_id: Object ID of the current fb. */
 	__u32 fb_id;
 
+	/**
+	 * @possible_crtcs: Bitmask of CRTC's compatible with the plane. CRTC's
+	 * are created and they receive an index, which corresponds to their
+	 * position in the bitmask. Bit N corresponds to
+	 * :ref:`CRTC index<crtc_index>` N.
+	 */
 	__u32 possible_crtcs;
+	/** @gamma_size: Never used. */
 	__u32 gamma_size;
 
+	/** @count_format_types: Number of formats. */
 	__u32 count_format_types;
+	/**
+	 * @format_type_ptr: Pointer to ``__u32`` array of formats that are
+	 * supported by the plane. These formats do not require modifiers.
+	 */
 	__u64 format_type_ptr;
 };
 
@@ -509,22 +541,74 @@ struct drm_mode_get_connector {
  */
 #define DRM_MODE_PROP_ATOMIC        0x80000000
 
+/**
+ * struct drm_mode_property_enum - Description for an enum/bitfield entry.
+ * @value: numeric value for this enum entry.
+ * @name: symbolic name for this enum entry.
+ *
+ * See struct drm_property_enum for details.
+ */
 struct drm_mode_property_enum {
 	__u64 value;
 	char name[DRM_PROP_NAME_LEN];
 };
 
+/**
+ * struct drm_mode_get_property - Get property metadata.
+ *
+ * User-space can perform a GETPROPERTY ioctl to retrieve information about a
+ * property. The same property may be attached to multiple objects, see
+ * "Modeset Base Object Abstraction".
+ *
+ * The meaning of the @values_ptr field changes depending on the property type.
+ * See &drm_property.flags for more details.
+ *
+ * The @enum_blob_ptr and @count_enum_blobs fields are only meaningful when the
+ * property has the type &DRM_MODE_PROP_ENUM or &DRM_MODE_PROP_BITMASK. For
+ * backwards compatibility, the kernel will always set @count_enum_blobs to
+ * zero when the property has the type &DRM_MODE_PROP_BLOB. User-space must
+ * ignore these two fields if the property has a different type.
+ *
+ * User-space is expected to retrieve values and enums by performing this ioctl
+ * at least twice: the first time to retrieve the number of elements, the
+ * second time to retrieve the elements themselves.
+ *
+ * To retrieve the number of elements, set @count_values and @count_enum_blobs
+ * to zero, then call the ioctl. @count_values will be updated with the number
+ * of elements. If the property has the type &DRM_MODE_PROP_ENUM or
+ * &DRM_MODE_PROP_BITMASK, @count_enum_blobs will be updated as well.
+ *
+ * To retrieve the elements themselves, allocate an array for @values_ptr and
+ * set @count_values to its capacity. If the property has the type
+ * &DRM_MODE_PROP_ENUM or &DRM_MODE_PROP_BITMASK, allocate an array for
+ * @enum_blob_ptr and set @count_enum_blobs to its capacity. Calling the ioctl
+ * again will fill the arrays.
+ */
 struct drm_mode_get_property {
-	__u64 values_ptr; /* values and blob lengths */
-	__u64 enum_blob_ptr; /* enum and blob id ptrs */
+	/** @values_ptr: Pointer to a ``__u64`` array. */
+	__u64 values_ptr;
+	/** @enum_blob_ptr: Pointer to a struct drm_mode_property_enum array. */
+	__u64 enum_blob_ptr;
 
+	/**
+	 * @prop_id: Object ID of the property which should be retrieved. Set
+	 * by the caller.
+	 */
 	__u32 prop_id;
+	/**
+	 * @flags: ``DRM_MODE_PROP_*`` bitfield. See &drm_property.flags for
+	 * a definition of the flags.
+	 */
 	__u32 flags;
+	/**
+	 * @name: Symbolic property name. User-space should use this field to
+	 * recognize properties.
+	 */
 	char name[DRM_PROP_NAME_LEN];
 
+	/** @count_values: Number of elements in @values_ptr. */
 	__u32 count_values;
-	/* This is only used to count enum values, not blobs. The _blobs is
-	 * simply because of a historical reason, i.e. backwards compat. */
+	/** @count_enum_blobs: Number of elements in @enum_blob_ptr. */
 	__u32 count_enum_blobs;
 };
 
diff --git a/include/drm-uapi/i915_drm.h b/include/drm-uapi/i915_drm.h
index a1c0030c397..c788a1ab423 100644
--- a/include/drm-uapi/i915_drm.h
+++ b/include/drm-uapi/i915_drm.h
@@ -572,6 +572,15 @@ typedef struct drm_i915_irq_wait {
 #define   I915_SCHEDULER_CAP_PREEMPTION	(1ul << 2)
 #define   I915_SCHEDULER_CAP_SEMAPHORES	(1ul << 3)
 #define   I915_SCHEDULER_CAP_ENGINE_BUSY_STATS	(1ul << 4)
+/*
+ * Indicates the 2k user priority levels are statically mapped into 3 buckets as
+ * follows:
+ *
+ * -1k to -1	Low priority
+ * 0		Normal priority
+ * 1 to 1k	Highest priority
+ */
+#define   I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP	(1ul << 5)
 
 #define I915_PARAM_HUC_STATUS		 42
 
@@ -674,6 +683,9 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55
 
+/* Query if the kernel supports the I915_USERPTR_PROBE flag. */
+#define I915_PARAM_HAS_USERPTR_PROBE 56
+
 /* Must be kept compact -- no holes and well documented */
 
 typedef struct drm_i915_getparam {
@@ -849,45 +861,113 @@ struct drm_i915_gem_mmap_gtt {
 	__u64 offset;
 };
 
+/**
+ * struct drm_i915_gem_mmap_offset - Retrieve an offset so we can mmap this buffer object.
+ *
+ * This struct is passed as argument to the `DRM_IOCTL_I915_GEM_MMAP_OFFSET` ioctl,
+ * and is used to retrieve the fake offset to mmap an object specified by &handle.
+ *
+ * The legacy way of using `DRM_IOCTL_I915_GEM_MMAP` is removed on gen12+.
+ * `DRM_IOCTL_I915_GEM_MMAP_GTT` is an older supported alias to this struct, but will behave
+ * as setting the &extensions to 0, and &flags to `I915_MMAP_OFFSET_GTT`.
+ */
 struct drm_i915_gem_mmap_offset {
-	/** Handle for the object being mapped. */
+	/** @handle: Handle for the object being mapped. */
 	__u32 handle;
+	/** @pad: Must be zero */
 	__u32 pad;
 	/**
-	 * Fake offset to use for subsequent mmap call
+	 * @offset: The fake offset to use for subsequent mmap call
 	 *
 	 * This is a fixed-size type for 32/64 compatibility.
 	 */
 	__u64 offset;
 
 	/**
-	 * Flags for extended behaviour.
+	 * @flags: Flags for extended behaviour.
+	 *
+	 * It is mandatory that one of the `MMAP_OFFSET` types
+	 * should be included:
 	 *
-	 * It is mandatory that one of the MMAP_OFFSET types
-	 * (GTT, WC, WB, UC, etc) should be included.
+	 * - `I915_MMAP_OFFSET_GTT`: Use mmap with the object bound to GTT. (Write-Combined)
+	 * - `I915_MMAP_OFFSET_WC`: Use Write-Combined caching.
+	 * - `I915_MMAP_OFFSET_WB`: Use Write-Back caching.
+	 * - `I915_MMAP_OFFSET_FIXED`: Use object placement to determine caching.
+	 *
+	 * On devices with local memory `I915_MMAP_OFFSET_FIXED` is the only valid
+	 * type. On devices without local memory, this caching mode is invalid.
+	 *
+	 * As caching mode when specifying `I915_MMAP_OFFSET_FIXED`, WC or WB will
+	 * be used, depending on the object placement on creation. WB will be used
+	 * when the object can only exist in system memory, WC otherwise.
 	 */
 	__u64 flags;
-#define I915_MMAP_OFFSET_GTT 0
-#define I915_MMAP_OFFSET_WC  1
-#define I915_MMAP_OFFSET_WB  2
-#define I915_MMAP_OFFSET_UC  3
 
-	/*
-	 * Zero-terminated chain of extensions.
+#define I915_MMAP_OFFSET_GTT	0
+#define I915_MMAP_OFFSET_WC	1
+#define I915_MMAP_OFFSET_WB	2
+#define I915_MMAP_OFFSET_UC	3
+#define I915_MMAP_OFFSET_FIXED	4
+
+	/**
+	 * @extensions: Zero-terminated chain of extensions.
 	 *
 	 * No current extensions defined; mbz.
 	 */
 	__u64 extensions;
 };
 
+/**
+ * struct drm_i915_gem_set_domain - Adjust the objects write or read domain, in
+ * preparation for accessing the pages via some CPU domain.
+ *
+ * Specifying a new write or read domain will flush the object out of the
+ * previous domain(if required), before then updating the objects domain
+ * tracking with the new domain.
+ *
+ * Note this might involve waiting for the object first if it is still active on
+ * the GPU.
+ *
+ * Supported values for @read_domains and @write_domain:
+ *
+ *	- I915_GEM_DOMAIN_WC: Uncached write-combined domain
+ *	- I915_GEM_DOMAIN_CPU: CPU cache domain
+ *	- I915_GEM_DOMAIN_GTT: Mappable aperture domain
+ *
+ * All other domains are rejected.
+ *
+ * Note that for discrete, starting from DG1, this is no longer supported, and
+ * is instead rejected. On such platforms the CPU domain is effectively static,
+ * where we also only support a single &drm_i915_gem_mmap_offset cache mode,
+ * which can't be set explicitly and instead depends on the object placements,
+ * as per the below.
+ *
+ * Implicit caching rules, starting from DG1:
+ *
+ *	- If any of the object placements (see &drm_i915_gem_create_ext_memory_regions)
+ *	  contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and
+ *	  mapped as write-combined only.
+ *
+ *	- Everything else is always allocated and mapped as write-back, with the
+ *	  guarantee that everything is also coherent with the GPU.
+ *
+ * Note that this is likely to change in the future again, where we might need
+ * more flexibility on future devices, so making this all explicit as part of a
+ * new &drm_i915_gem_create_ext extension is probable.
+ */
 struct drm_i915_gem_set_domain {
-	/** Handle for the object */
+	/** @handle: Handle for the object. */
 	__u32 handle;
 
-	/** New read domains */
+	/** @read_domains: New read domains. */
 	__u32 read_domains;
 
-	/** New write domain */
+	/**
+	 * @write_domain: New write domain.
+	 *
+	 * Note that having something in the write domain implies it's in the
+	 * read domain, and only that read domain.
+	 */
 	__u32 write_domain;
 };
 
@@ -1348,12 +1428,11 @@ struct drm_i915_gem_busy {
 	 * reading from the object simultaneously.
 	 *
 	 * The value of each engine class is the same as specified in the
-	 * I915_CONTEXT_SET_ENGINES parameter and via perf, i.e.
+	 * I915_CONTEXT_PARAM_ENGINES context parameter and via perf, i.e.
 	 * I915_ENGINE_CLASS_RENDER, I915_ENGINE_CLASS_COPY, etc.
-	 * reported as active itself. Some hardware may have parallel
-	 * execution engines, e.g. multiple media engines, which are
-	 * mapped to the same class identifier and so are not separately
-	 * reported for busyness.
+	 * Some hardware may have parallel execution engines, e.g. multiple
+	 * media engines, which are mapped to the same class identifier and so
+	 * are not separately reported for busyness.
 	 *
 	 * Caveat emptor:
 	 * Only the boolean result of this query is reliable; that is whether
@@ -1364,43 +1443,79 @@ struct drm_i915_gem_busy {
 };
 
 /**
- * I915_CACHING_NONE
- *
- * GPU access is not coherent with cpu caches. Default for machines without an
- * LLC.
- */
-#define I915_CACHING_NONE		0
-/**
- * I915_CACHING_CACHED
- *
- * GPU access is coherent with cpu caches and furthermore the data is cached in
- * last-level caches shared between cpu cores and the gpu GT. Default on
- * machines with HAS_LLC.
+ * struct drm_i915_gem_caching - Set or get the caching for given object
+ * handle.
+ *
+ * Allow userspace to control the GTT caching bits for a given object when the
+ * object is later mapped through the ppGTT(or GGTT on older platforms lacking
+ * ppGTT support, or if the object is used for scanout). Note that this might
+ * require unbinding the object from the GTT first, if its current caching value
+ * doesn't match.
+ *
+ * Note that this all changes on discrete platforms, starting from DG1, the
+ * set/get caching is no longer supported, and is now rejected.  Instead the CPU
+ * caching attributes(WB vs WC) will become an immutable creation time property
+ * for the object, along with the GTT caching level. For now we don't expose any
+ * new uAPI for this, instead on DG1 this is all implicit, although this largely
+ * shouldn't matter since DG1 is coherent by default(without any way of
+ * controlling it).
+ *
+ * Implicit caching rules, starting from DG1:
+ *
+ *     - If any of the object placements (see &drm_i915_gem_create_ext_memory_regions)
+ *       contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and
+ *       mapped as write-combined only.
+ *
+ *     - Everything else is always allocated and mapped as write-back, with the
+ *       guarantee that everything is also coherent with the GPU.
+ *
+ * Note that this is likely to change in the future again, where we might need
+ * more flexibility on future devices, so making this all explicit as part of a
+ * new &drm_i915_gem_create_ext extension is probable.
+ *
+ * Side note: Part of the reason for this is that changing the at-allocation-time CPU
+ * caching attributes for the pages might be required(and is expensive) if we
+ * need to then CPU map the pages later with different caching attributes. This
+ * inconsistent caching behaviour, while supported on x86, is not universally
+ * supported on other architectures. So for simplicity we opt for setting
+ * everything at creation time, whilst also making it immutable, on discrete
+ * platforms.
  */
-#define I915_CACHING_CACHED		1
-/**
- * I915_CACHING_DISPLAY
- *
- * Special GPU caching mode which is coherent with the scanout engines.
- * Transparently falls back to I915_CACHING_NONE on platforms where no special
- * cache mode (like write-through or gfdt flushing) is available. The kernel
- * automatically sets this mode when using a buffer as a scanout target.
- * Userspace can manually set this mode to avoid a costly stall and clflush in
- * the hotpath of drawing the first frame.
- */
-#define I915_CACHING_DISPLAY		2
-
 struct drm_i915_gem_caching {
 	/**
-	 * Handle of the buffer to set/get the caching level of. */
+	 * @handle: Handle of the buffer to set/get the caching level.
+	 */
 	__u32 handle;
 
 	/**
-	 * Cacheing level to apply or return value
+	 * @caching: The GTT caching level to apply or possible return value.
+	 *
+	 * The supported @caching values:
 	 *
-	 * bits0-15 are for generic caching control (i.e. the above defined
-	 * values). bits16-31 are reserved for platform-specific variations
-	 * (e.g. l3$ caching on gen7). */
+	 * I915_CACHING_NONE:
+	 *
+	 * GPU access is not coherent with CPU caches.  Default for machines
+	 * without an LLC. This means manual flushing might be needed, if we
+	 * want GPU access to be coherent.
+	 *
+	 * I915_CACHING_CACHED:
+	 *
+	 * GPU access is coherent with CPU caches and furthermore the data is
+	 * cached in last-level caches shared between CPU cores and the GPU GT.
+	 *
+	 * I915_CACHING_DISPLAY:
+	 *
+	 * Special GPU caching mode which is coherent with the scanout engines.
+	 * Transparently falls back to I915_CACHING_NONE on platforms where no
+	 * special cache mode (like write-through or gfdt flushing) is
+	 * available. The kernel automatically sets this mode when using a
+	 * buffer as a scanout target.  Userspace can manually set this mode to
+	 * avoid a costly stall and clflush in the hotpath of drawing the first
+	 * frame.
+	 */
+#define I915_CACHING_NONE		0
+#define I915_CACHING_CACHED		1
+#define I915_CACHING_DISPLAY		2
 	__u32 caching;
 };
 
@@ -1639,6 +1754,10 @@ struct drm_i915_gem_context_param {
 	__u32 size;
 	__u64 param;
 #define I915_CONTEXT_PARAM_BAN_PERIOD	0x1
+/* I915_CONTEXT_PARAM_NO_ZEROMAP has been removed.  On the off chance
+ * someone somewhere has attempted to use it, never re-use this context
+ * param number.
+ */
 #define I915_CONTEXT_PARAM_NO_ZEROMAP	0x2
 #define I915_CONTEXT_PARAM_GTT_SIZE	0x3
 #define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE	0x4
@@ -1723,24 +1842,8 @@ struct drm_i915_gem_context_param {
  */
 #define I915_CONTEXT_PARAM_PERSISTENCE	0xb
 
-/*
- * I915_CONTEXT_PARAM_RINGSIZE:
- *
- * Sets the size of the CS ringbuffer to use for logical ring contexts. This
- * applies a limit of how many batches can be queued to HW before the caller
- * is blocked due to lack of space for more commands.
- *
- * Only reliably possible to be set prior to first use, i.e. during
- * construction. At any later point, the current execution must be flushed as
- * the ring can only be changed while the context is idle. Note, the ringsize
- * can be specified as a constructor property, see
- * I915_CONTEXT_CREATE_EXT_SETPARAM, but can also be set later if required.
- *
- * Only applies to the current set of engine and lost when those engines
- * are replaced by a new mapping (see I915_CONTEXT_PARAM_ENGINES).
- *
- * Must be between 4 - 512 KiB, in intervals of page size [4 KiB].
- * Default is 16 KiB.
+/* This API has been removed.  On the off chance someone somewhere has
+ * attempted to use it, never re-use this context param number.
  */
 #define I915_CONTEXT_PARAM_RINGSIZE	0xc
 /* Must be kept compact -- no holes and well documented */
@@ -1807,6 +1910,69 @@ struct drm_i915_gem_context_param_sseu {
 	__u32 rsvd;
 };
 
+/**
+ * DOC: Virtual Engine uAPI
+ *
+ * Virtual engine is a concept where userspace is able to configure a set of
+ * physical engines, submit a batch buffer, and let the driver execute it on any
+ * engine from the set as it sees fit.
+ *
+ * This is primarily useful on parts which have multiple instances of a same
+ * class engine, like for example GT3+ Skylake parts with their two VCS engines.
+ *
+ * For instance userspace can enumerate all engines of a certain class using the
+ * previously described `Engine Discovery uAPI`_. After that userspace can
+ * create a GEM context with a placeholder slot for the virtual engine (using
+ * `I915_ENGINE_CLASS_INVALID` and `I915_ENGINE_CLASS_INVALID_NONE` for class
+ * and instance respectively) and finally using the
+ * `I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE` extension place a virtual engine in
+ * the same reserved slot.
+ *
+ * Example of creating a virtual engine and submitting a batch buffer to it:
+ *
+ * .. code-block:: C
+ *
+ * 	I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(virtual, 2) = {
+ * 		.base.name = I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE,
+ * 		.engine_index = 0, // Place this virtual engine into engine map slot 0
+ * 		.num_siblings = 2,
+ * 		.engines = { { I915_ENGINE_CLASS_VIDEO, 0 },
+ * 			     { I915_ENGINE_CLASS_VIDEO, 1 }, },
+ * 	};
+ * 	I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 1) = {
+ * 		.engines = { { I915_ENGINE_CLASS_INVALID,
+ * 			       I915_ENGINE_CLASS_INVALID_NONE } },
+ * 		.extensions = to_user_pointer(&virtual), // Chains after load_balance extension
+ * 	};
+ * 	struct drm_i915_gem_context_create_ext_setparam p_engines = {
+ * 		.base = {
+ * 			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ * 		},
+ * 		.param = {
+ * 			.param = I915_CONTEXT_PARAM_ENGINES,
+ * 			.value = to_user_pointer(&engines),
+ * 			.size = sizeof(engines),
+ * 		},
+ * 	};
+ * 	struct drm_i915_gem_context_create_ext create = {
+ * 		.flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
+ * 		.extensions = to_user_pointer(&p_engines);
+ * 	};
+ *
+ * 	ctx_id = gem_context_create_ext(drm_fd, &create);
+ *
+ * 	// Now we have created a GEM context with its engine map containing a
+ * 	// single virtual engine. Submissions to this slot can go either to
+ * 	// vcs0 or vcs1, depending on the load balancing algorithm used inside
+ * 	// the driver. The load balancing is dynamic from one batch buffer to
+ * 	// another and transparent to userspace.
+ *
+ * 	...
+ * 	execbuf.rsvd1 = ctx_id;
+ * 	execbuf.flags = 0; // Submits to index 0 which is the virtual engine
+ * 	gem_execbuf(drm_fd, &execbuf);
+ */
+
 /*
  * i915_context_engines_load_balance:
  *
@@ -1883,6 +2049,61 @@ struct i915_context_engines_bond {
 	struct i915_engine_class_instance engines[N__]; \
 } __attribute__((packed)) name__
 
+/**
+ * DOC: Context Engine Map uAPI
+ *
+ * Context engine map is a new way of addressing engines when submitting batch-
+ * buffers, replacing the existing way of using identifiers like `I915_EXEC_BLT`
+ * inside the flags field of `struct drm_i915_gem_execbuffer2`.
+ *
+ * To use it created GEM contexts need to be configured with a list of engines
+ * the user is intending to submit to. This is accomplished using the
+ * `I915_CONTEXT_PARAM_ENGINES` parameter and `struct
+ * i915_context_param_engines`.
+ *
+ * For such contexts the `I915_EXEC_RING_MASK` field becomes an index into the
+ * configured map.
+ *
+ * Example of creating such context and submitting against it:
+ *
+ * .. code-block:: C
+ *
+ * 	I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 2) = {
+ * 		.engines = { { I915_ENGINE_CLASS_RENDER, 0 },
+ * 			     { I915_ENGINE_CLASS_COPY, 0 } }
+ * 	};
+ * 	struct drm_i915_gem_context_create_ext_setparam p_engines = {
+ * 		.base = {
+ * 			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ * 		},
+ * 		.param = {
+ * 			.param = I915_CONTEXT_PARAM_ENGINES,
+ * 			.value = to_user_pointer(&engines),
+ * 			.size = sizeof(engines),
+ * 		},
+ * 	};
+ * 	struct drm_i915_gem_context_create_ext create = {
+ * 		.flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
+ * 		.extensions = to_user_pointer(&p_engines);
+ * 	};
+ *
+ * 	ctx_id = gem_context_create_ext(drm_fd, &create);
+ *
+ * 	// We have now created a GEM context with two engines in the map:
+ * 	// Index 0 points to rcs0 while index 1 points to bcs0. Other engines
+ * 	// will not be accessible from this context.
+ *
+ * 	...
+ * 	execbuf.rsvd1 = ctx_id;
+ * 	execbuf.flags = 0; // Submits to index 0, which is rcs0 for this context
+ * 	gem_execbuf(drm_fd, &execbuf);
+ *
+ * 	...
+ * 	execbuf.rsvd1 = ctx_id;
+ * 	execbuf.flags = 1; // Submits to index 0, which is bcs0 for this context
+ * 	gem_execbuf(drm_fd, &execbuf);
+ */
+
 struct i915_context_param_engines {
 	__u64 extensions; /* linked chain of extension blocks, 0 terminates */
 #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
@@ -1901,20 +2122,10 @@ struct drm_i915_gem_context_create_ext_setparam {
 	struct drm_i915_gem_context_param param;
 };
 
-struct drm_i915_gem_context_create_ext_clone {
+/* This API has been removed.  On the off chance someone somewhere has
+ * attempted to use it, never re-use this extension number.
+ */
 #define I915_CONTEXT_CREATE_EXT_CLONE 1
-	struct i915_user_extension base;
-	__u32 clone_id;
-	__u32 flags;
-#define I915_CONTEXT_CLONE_ENGINES	(1u << 0)
-#define I915_CONTEXT_CLONE_FLAGS	(1u << 1)
-#define I915_CONTEXT_CLONE_SCHEDATTR	(1u << 2)
-#define I915_CONTEXT_CLONE_SSEU		(1u << 3)
-#define I915_CONTEXT_CLONE_TIMELINE	(1u << 4)
-#define I915_CONTEXT_CLONE_VM		(1u << 5)
-#define I915_CONTEXT_CLONE_UNKNOWN -(I915_CONTEXT_CLONE_VM << 1)
-	__u64 rsvd;
-};
 
 struct drm_i915_gem_context_destroy {
 	__u32 ctx_id;
@@ -1986,14 +2197,69 @@ struct drm_i915_reset_stats {
 	__u32 pad;
 };
 
+/**
+ * struct drm_i915_gem_userptr - Create GEM object from user allocated memory.
+ *
+ * Userptr objects have several restrictions on what ioctls can be used with the
+ * object handle.
+ */
 struct drm_i915_gem_userptr {
+	/**
+	 * @user_ptr: The pointer to the allocated memory.
+	 *
+	 * Needs to be aligned to PAGE_SIZE.
+	 */
 	__u64 user_ptr;
+
+	/**
+	 * @user_size:
+	 *
+	 * The size in bytes for the allocated memory. This will also become the
+	 * object size.
+	 *
+	 * Needs to be aligned to PAGE_SIZE, and should be at least PAGE_SIZE,
+	 * or larger.
+	 */
 	__u64 user_size;
+
+	/**
+	 * @flags:
+	 *
+	 * Supported flags:
+	 *
+	 * I915_USERPTR_READ_ONLY:
+	 *
+	 * Mark the object as readonly, this also means GPU access can only be
+	 * readonly. This is only supported on HW which supports readonly access
+	 * through the GTT. If the HW can't support readonly access, an error is
+	 * returned.
+	 *
+	 * I915_USERPTR_PROBE:
+	 *
+	 * Probe the provided @user_ptr range and validate that the @user_ptr is
+	 * indeed pointing to normal memory and that the range is also valid.
+	 * For example if some garbage address is given to the kernel, then this
+	 * should complain.
+	 *
+	 * Returns -EFAULT if the probe failed.
+	 *
+	 * Note that this doesn't populate the backing pages, and also doesn't
+	 * guarantee that the object will remain valid when the object is
+	 * eventually used.
+	 *
+	 * The kernel supports this feature if I915_PARAM_HAS_USERPTR_PROBE
+	 * returns a non-zero value.
+	 *
+	 * I915_USERPTR_UNSYNCHRONIZED:
+	 *
+	 * NOT USED. Setting this flag will result in an error.
+	 */
 	__u32 flags;
 #define I915_USERPTR_READ_ONLY 0x1
+#define I915_USERPTR_PROBE 0x2
 #define I915_USERPTR_UNSYNCHRONIZED 0x80000000
 	/**
-	 * Returned handle for the object.
+	 * @handle: Returned handle for the object.
 	 *
 	 * Object handles are nonzero.
 	 */
@@ -2377,6 +2643,76 @@ struct drm_i915_query_topology_info {
 };
 
 /**
+ * DOC: Engine Discovery uAPI
+ *
+ * Engine discovery uAPI is a way of enumerating physical engines present in a
+ * GPU associated with an open i915 DRM file descriptor. This supersedes the old
+ * way of using `DRM_IOCTL_I915_GETPARAM` and engine identifiers like
+ * `I915_PARAM_HAS_BLT`.
+ *
+ * The need for this interface came starting with Icelake and newer GPUs, which
+ * started to establish a pattern of having multiple engines of a same class,
+ * where not all instances were always completely functionally equivalent.
+ *
+ * Entry point for this uapi is `DRM_IOCTL_I915_QUERY` with the
+ * `DRM_I915_QUERY_ENGINE_INFO` as the queried item id.
+ *
+ * Example for getting the list of engines:
+ *
+ * .. code-block:: C
+ *
+ * 	struct drm_i915_query_engine_info *info;
+ * 	struct drm_i915_query_item item = {
+ * 		.query_id = DRM_I915_QUERY_ENGINE_INFO;
+ * 	};
+ * 	struct drm_i915_query query = {
+ * 		.num_items = 1,
+ * 		.items_ptr = (uintptr_t)&item,
+ * 	};
+ * 	int err, i;
+ *
+ * 	// First query the size of the blob we need, this needs to be large
+ * 	// enough to hold our array of engines. The kernel will fill out the
+ * 	// item.length for us, which is the number of bytes we need.
+ * 	//
+ * 	// Alternatively a large buffer can be allocated straight away enabling
+ * 	// querying in one pass, in which case item.length should contain the
+ * 	// length of the provided buffer.
+ * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
+ * 	if (err) ...
+ *
+ * 	info = calloc(1, item.length);
+ * 	// Now that we allocated the required number of bytes, we call the ioctl
+ * 	// again, this time with the data_ptr pointing to our newly allocated
+ * 	// blob, which the kernel can then populate with info on all engines.
+ * 	item.data_ptr = (uintptr_t)&info,
+ *
+ * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
+ * 	if (err) ...
+ *
+ * 	// We can now access each engine in the array
+ * 	for (i = 0; i < info->num_engines; i++) {
+ * 		struct drm_i915_engine_info einfo = info->engines[i];
+ * 		u16 class = einfo.engine.class;
+ * 		u16 instance = einfo.engine.instance;
+ * 		....
+ * 	}
+ *
+ * 	free(info);
+ *
+ * Each of the enumerated engines, apart from being defined by its class and
+ * instance (see `struct i915_engine_class_instance`), also can have flags and
+ * capabilities defined as documented in i915_drm.h.
+ *
+ * For instance video engines which support HEVC encoding will have the
+ * `I915_VIDEO_CLASS_CAPABILITY_HEVC` capability bit set.
+ *
+ * Engine discovery only fully comes to its own when combined with the new way
+ * of addressing engines when submitting batch buffers using contexts with
+ * engine maps configured.
+ */
+
+/**
  * struct drm_i915_engine_info
  *
  * Describes one engine and it's capabilities as known to the driver.
diff --git a/include/drm-uapi/msm_drm.h b/include/drm-uapi/msm_drm.h
index 5596d7c37f9..6b8fffc28a5 100644
--- a/include/drm-uapi/msm_drm.h
+++ b/include/drm-uapi/msm_drm.h
@@ -73,11 +73,19 @@ struct drm_msm_timespec {
 #define MSM_PARAM_MAX_FREQ   0x04
 #define MSM_PARAM_TIMESTAMP  0x05
 #define MSM_PARAM_GMEM_BASE  0x06
-#define MSM_PARAM_NR_RINGS   0x07
+#define MSM_PARAM_PRIORITIES 0x07  /* The # of priority levels */
 #define MSM_PARAM_PP_PGTABLE 0x08  /* => 1 for per-process pagetables, else 0 */
 #define MSM_PARAM_FAULTS     0x09
 #define MSM_PARAM_SUSPENDS   0x0a
 
+/* For backwards compat.  The original support for preemption was based on
+ * a single ring per priority level so # of priority levels equals the #
+ * of rings.  With drm/scheduler providing additional levels of priority,
+ * the number of priorities is greater than the # of rings.  The param is
+ * renamed to better reflect this.
+ */
+#define MSM_PARAM_NR_RINGS   MSM_PARAM_PRIORITIES
+
 struct drm_msm_param {
 	__u32 pipe;           /* in, MSM_PIPE_x */
 	__u32 param;          /* in, MSM_PARAM_x */
@@ -94,13 +102,12 @@ struct drm_msm_param {
 /* cache modes */
 #define MSM_BO_CACHED        0x00010000
 #define MSM_BO_WC            0x00020000
-#define MSM_BO_UNCACHED      0x00040000
+#define MSM_BO_UNCACHED      0x00040000 /* deprecated, use MSM_BO_WC */
+#define MSM_BO_CACHED_COHERENT 0x080000
 
 #define MSM_BO_FLAGS         (MSM_BO_SCANOUT | \
                               MSM_BO_GPU_READONLY | \
-                              MSM_BO_CACHED | \
-                              MSM_BO_WC | \
-                              MSM_BO_UNCACHED)
+                              MSM_BO_CACHE_MASK)
 
 struct drm_msm_gem_new {
 	__u64 size;           /* in */
@@ -305,6 +312,10 @@ struct drm_msm_gem_madvise {
 
 #define MSM_SUBMITQUEUE_FLAGS (0)
 
+/*
+ * The submitqueue priority should be between 0 and MSM_PARAM_PRIORITIES-1,
+ * a lower numeric value is higher priority.
+ */
 struct drm_msm_submitqueue {
 	__u32 flags;   /* in, MSM_SUBMITQUEUE_x */
 	__u32 prio;    /* in, Priority level */
diff --git a/include/drm-uapi/v3d_drm.h b/include/drm-uapi/v3d_drm.h
index 87e7ab554fc..4104f22fb3d 100644
--- a/include/drm-uapi/v3d_drm.h
+++ b/include/drm-uapi/v3d_drm.h
@@ -50,9 +50,12 @@ extern "C" {
 #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)
 #define DRM_IOCTL_V3D_SUBMIT_CSD          DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CSD, struct drm_v3d_submit_csd)
-#define DRM_IOCTL_V3D_PERFMON_CREATE      DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_CREATE, struct drm_v3d_perfmon_create)
-#define DRM_IOCTL_V3D_PERFMON_DESTROY     DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_DESTROY, struct drm_v3d_perfmon_destroy)
-#define DRM_IOCTL_V3D_PERFMON_GET_VALUES  DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_GET_VALUES, struct drm_v3d_perfmon_get_values)
+#define DRM_IOCTL_V3D_PERFMON_CREATE      DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_CREATE, \
+						   struct drm_v3d_perfmon_create)
+#define DRM_IOCTL_V3D_PERFMON_DESTROY     DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_DESTROY, \
+						   struct drm_v3d_perfmon_destroy)
+#define DRM_IOCTL_V3D_PERFMON_GET_VALUES  DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_GET_VALUES, \
+						   struct drm_v3d_perfmon_get_values)
 
 #define DRM_V3D_SUBMIT_CL_FLUSH_CACHE             0x01