Merge tag 'drm-next-2021-08-31-1' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Highlights:

   - i915 has seen a lot of refactoring and uAPI cleanups due to a
     change in the upstream direction going forward

     This has all been audited with known userspace, but there may be
     some pitfalls that were missed.

   - i915 now uses common TTM to enable discrete memory on DG1/2 GPUs

   - i915 enables Jasper and Elkhart Lake by default and has preliminary
     XeHP/DG2 support

   - amdgpu adds support for Cyan Skillfish

   - lots of implicit fencing rules documented and fixed up in drivers

   - msm now uses the core scheduler

   - the irq midlayer has been removed for non-legacy drivers

   - the sysfb code now works on more than x86.

  Otherwise the usual smattering of stuff everywhere, panels, bridges,
  refactorings.

  Detailed summary:

  core:
   - extract i915 eDP backlight into core
   - DP aux bus support
   - drm_device.irq_enabled removed
   - port drivers to native irq interfaces
   - export gem shadow plane handling for vgem
   - print proper driver name in framebuffer registration
   - driver fixes for implicit fencing rules
   - ARM fixed rate compression modifier added
   - updated fb damage handling
   - rmfb ioctl logging/docs
   - drop drm_gem_object_put_locked
   - define DRM_FORMAT_MAX_PLANES
   - add gem fb vmap/vunmap helpers
   - add lockdep_assert(once) helpers
   - mark drm irq midlayer as legacy
   - use offset adjusted bo mapping conversion

  vgaarb:
   - cleanups

  fbdev:
   - extend efifb handling to all arches
   - div by 0 fixes for multiple drivers

  udmabuf:
   - add hugepage mapping support

  dma-buf:
   - non-dynamic exporter fixups
   - document implicit fencing rules

  amdgpu:
   - Initial Cyan Skillfish support
   - switch virtual DCE over to vkms based atomic
   - VCN/JPEG power down fixes
   - NAVI PCIE link handling fixes
   - AMD HDMI freesync fixes
   - Yellow Carp + Beige Goby fixes
   - Clockgating/S0ix/SMU/EEPROM fixes
   - embed hw fence in job
   - rework dma-resv handling
   - ensure eviction to system ram

  amdkfd:
   - uapi: SVM address range query added
   - sysfs leak fix
   - GPUVM TLB optimizations
   - vmfault/migration counters

  i915:
   - Enable JSL and EHL by default
   - preliminary XeHP/DG2 support
   - remove all CNL support (never shipped)
   - move to TTM for discrete memory support
   - allow mixed object mmap handling
   - GEM uAPI spring cleaning
       - add I915_MMAP_OBJECT_FIXED
       - reinstate ADL-P mmap ioctls
       - drop a bunch of unused by userspace features
       - disable and remove GPU relocations
   - revert some i915 misfeatures
   - major refactoring of GuC for Gen11+
   - execbuffer object locking separate step
   - reject caching/set-domain on discrete
   - Enable pipe DMC loading on XE-LPD and ADL-P
   - add PSF GV point support
   - Refactor and fix DDI buffer translations
   - Clean up FBC CFB allocation code
   - Finish INTEL_GEN() and friends macro conversions

  nouveau:
   - add eDP backlight support
   - implicit fence fix

  msm:
   - a680/7c3 support
   - drm/scheduler conversion

  panfrost:
   - rework GPU reset

  virtio:
   - fix fencing for planes

  ast:
   - add detect support

  bochs:
   - move to tiny GPU driver

  vc4:
   - use hotplug irqs
   - HDMI codec support

  vmwgfx:
   - use internal vmware device headers

  ingenic:
   - demidlayering irq

  rcar-du:
   - shutdown fixes
   - convert to bridge connector helpers

  zynqmp-dsub:
   - misc fixes

  mgag200:
   - convert PLL handling to atomic

  mediatek:
   - MT8133 AAL support
   - gem mmap object support
   - MT8167 support

  etnaviv:
   - NXP Layerscape LS1028A SoC support
   - GEM mmap cleanups

  tegra:
   - new user API

  exynos:
   - missing unlock fix
   - build warning fix
   - use refcount_t"

* tag 'drm-next-2021-08-31-1' of git://anongit.freedesktop.org/drm/drm: (1318 commits)
  drm/amd/display: Move AllowDRAMSelfRefreshOrDRAMClockChangeInVblank to bounding box
  drm/amd/display: Remove duplicate dml init
  drm/amd/display: Update bounding box states (v2)
  drm/amd/display: Update number of DCN3 clock states
  drm/amdgpu: disable GFX CGCG in aldebaran
  drm/amdgpu: Clear RAS interrupt status on aldebaran
  drm/amdgpu: Add support for RAS XGMI err query
  drm/amdkfd: Account for SH/SE count when setting up cu masks.
  drm/amdgpu: rename amdgpu_bo_get_preferred_pin_domain
  drm/amdgpu: drop redundant cancel_delayed_work_sync call
  drm/amdgpu: add missing cleanups for more ASICs on UVD/VCE suspend
  drm/amdgpu: add missing cleanups for Polaris12 UVD/VCE on suspend
  drm/amdkfd: map SVM range with correct access permission
  drm/amdkfd: check access permisson to restore retry fault
  drm/amdgpu: Update RAS XGMI Error Query
  drm/amdgpu: Add driver infrastructure for MCA RAS
  drm/amd/display: Add Logging for HDMI color depth information
  drm/amd/amdgpu: consolidate PSP TA init shared buf functions
  drm/amd/amdgpu: add name field back to ras_common_if
  drm/amdgpu: Fix build with missing pm_suspend_target_state module export
  ...

10 files changed, 1273 insertions, 122 deletions

diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index d043752a74cf..3b810b53ba8b 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -635,8 +635,8 @@ 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.
  */
@@ -1050,6 +1050,16 @@ 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/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index f7156322aba5..9f4bb4a6f358 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/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/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 9b6722d45f36..90c55383f1ee 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/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/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index c2c7759b7d2e..bde5860b3686 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/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/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index f075851021c3..6b8fffc28a50 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/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 */
@@ -304,6 +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/uapi/drm/tegra_drm.h b/include/uapi/drm/tegra_drm.h
index c4df3c3668b3..94cfc306d50a 100644
--- a/include/uapi/drm/tegra_drm.h
+++ b/include/uapi/drm/tegra_drm.h
@@ -1,24 +1,5 @@
-/*
- * Copyright (c) 2012-2013, NVIDIA CORPORATION.  All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- */
+/* SPDX-License-Identifier: MIT */
+/* Copyright (c) 2012-2020 NVIDIA Corporation */
 
 #ifndef _UAPI_TEGRA_DRM_H_
 #define _UAPI_TEGRA_DRM_H_
@@ -29,6 +10,8 @@
 extern "C" {
 #endif
 
+/* Tegra DRM legacy UAPI. Only enabled with STAGING */
+
 #define DRM_TEGRA_GEM_CREATE_TILED     (1 << 0)
 #define DRM_TEGRA_GEM_CREATE_BOTTOM_UP (1 << 1)
 
@@ -649,8 +632,8 @@ struct drm_tegra_gem_get_flags {
 #define DRM_TEGRA_SYNCPT_READ		0x02
 #define DRM_TEGRA_SYNCPT_INCR		0x03
 #define DRM_TEGRA_SYNCPT_WAIT		0x04
-#define DRM_TEGRA_OPEN_CHANNEL		0x05
-#define DRM_TEGRA_CLOSE_CHANNEL		0x06
+#define DRM_TEGRA_OPEN_CHANNEL	        0x05
+#define DRM_TEGRA_CLOSE_CHANNEL	        0x06
 #define DRM_TEGRA_GET_SYNCPT		0x07
 #define DRM_TEGRA_SUBMIT		0x08
 #define DRM_TEGRA_GET_SYNCPT_BASE	0x09
@@ -674,6 +657,402 @@ struct drm_tegra_gem_get_flags {
 #define DRM_IOCTL_TEGRA_GEM_SET_FLAGS DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GEM_SET_FLAGS, struct drm_tegra_gem_set_flags)
 #define DRM_IOCTL_TEGRA_GEM_GET_FLAGS DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GEM_GET_FLAGS, struct drm_tegra_gem_get_flags)
 
+/* New Tegra DRM UAPI */
+
+/*
+ * Reported by the driver in the `capabilities` field.
+ *
+ * DRM_TEGRA_CHANNEL_CAP_CACHE_COHERENT: If set, the engine is cache coherent
+ * with regard to the system memory.
+ */
+#define DRM_TEGRA_CHANNEL_CAP_CACHE_COHERENT (1 << 0)
+
+struct drm_tegra_channel_open {
+	/**
+	 * @host1x_class: [in]
+	 *
+	 * Host1x class of the engine that will be programmed using this
+	 * channel.
+	 */
+	__u32 host1x_class;
+
+	/**
+	 * @flags: [in]
+	 *
+	 * Flags.
+	 */
+	__u32 flags;
+
+	/**
+	 * @context: [out]
+	 *
+	 * Opaque identifier corresponding to the opened channel.
+	 */
+	__u32 context;
+
+	/**
+	 * @version: [out]
+	 *
+	 * Version of the engine hardware. This can be used by userspace
+	 * to determine how the engine needs to be programmed.
+	 */
+	__u32 version;
+
+	/**
+	 * @capabilities: [out]
+	 *
+	 * Flags describing the hardware capabilities.
+	 */
+	__u32 capabilities;
+	__u32 padding;
+};
+
+struct drm_tegra_channel_close {
+	/**
+	 * @context: [in]
+	 *
+	 * Identifier of the channel to close.
+	 */
+	__u32 context;
+	__u32 padding;
+};
+
+/*
+ * Mapping flags that can be used to influence how the mapping is created.
+ *
+ * DRM_TEGRA_CHANNEL_MAP_READ: create mapping that allows HW read access
+ * DRM_TEGRA_CHANNEL_MAP_WRITE: create mapping that allows HW write access
+ */
+#define DRM_TEGRA_CHANNEL_MAP_READ  (1 << 0)
+#define DRM_TEGRA_CHANNEL_MAP_WRITE (1 << 1)
+#define DRM_TEGRA_CHANNEL_MAP_READ_WRITE (DRM_TEGRA_CHANNEL_MAP_READ | \
+					  DRM_TEGRA_CHANNEL_MAP_WRITE)
+
+struct drm_tegra_channel_map {
+	/**
+	 * @context: [in]
+	 *
+	 * Identifier of the channel to which make memory available for.
+	 */
+	__u32 context;
+
+	/**
+	 * @handle: [in]
+	 *
+	 * GEM handle of the memory to map.
+	 */
+	__u32 handle;
+
+	/**
+	 * @flags: [in]
+	 *
+	 * Flags.
+	 */
+	__u32 flags;
+
+	/**
+	 * @mapping: [out]
+	 *
+	 * Identifier corresponding to the mapping, to be used for
+	 * relocations or unmapping later.
+	 */
+	__u32 mapping;
+};
+
+struct drm_tegra_channel_unmap {
+	/**
+	 * @context: [in]
+	 *
+	 * Channel identifier of the channel to unmap memory from.
+	 */
+	__u32 context;
+
+	/**
+	 * @mapping: [in]
+	 *
+	 * Mapping identifier of the memory mapping to unmap.
+	 */
+	__u32 mapping;
+};
+
+/* Submission */
+
+/**
+ * Specify that bit 39 of the patched-in address should be set to switch
+ * swizzling between Tegra and non-Tegra sector layout on systems that store
+ * surfaces in system memory in non-Tegra sector layout.
+ */
+#define DRM_TEGRA_SUBMIT_RELOC_SECTOR_LAYOUT (1 << 0)
+
+struct drm_tegra_submit_buf {
+	/**
+	 * @mapping: [in]
+	 *
+	 * Identifier of the mapping to use in the submission.
+	 */
+	__u32 mapping;
+
+	/**
+	 * @flags: [in]
+	 *
+	 * Flags.
+	 */
+	__u32 flags;
+
+	/**
+	 * Information for relocation patching.
+	 */
+	struct {
+		/**
+		 * @target_offset: [in]
+		 *
+		 * Offset from the start of the mapping of the data whose
+		 * address is to be patched into the gather.
+		 */
+		__u64 target_offset;
+
+		/**
+		 * @gather_offset_words: [in]
+		 *
+		 * Offset in words from the start of the gather data to
+		 * where the address should be patched into.
+		 */
+		__u32 gather_offset_words;
+
+		/**
+		 * @shift: [in]
+		 *
+		 * Number of bits the address should be shifted right before
+		 * patching in.
+		 */
+		__u32 shift;
+	} reloc;
+};
+
+/**
+ * Execute `words` words of Host1x opcodes specified in the `gather_data_ptr`
+ * buffer. Each GATHER_UPTR command uses successive words from the buffer.
+ */
+#define DRM_TEGRA_SUBMIT_CMD_GATHER_UPTR		0
+/**
+ * Wait for a syncpoint to reach a value before continuing with further
+ * commands.
+ */
+#define DRM_TEGRA_SUBMIT_CMD_WAIT_SYNCPT		1
+/**
+ * Wait for a syncpoint to reach a value before continuing with further
+ * commands. The threshold is calculated relative to the start of the job.
+ */
+#define DRM_TEGRA_SUBMIT_CMD_WAIT_SYNCPT_RELATIVE	2
+
+struct drm_tegra_submit_cmd_gather_uptr {
+	__u32 words;
+	__u32 reserved[3];
+};
+
+struct drm_tegra_submit_cmd_wait_syncpt {
+	__u32 id;
+	__u32 value;
+	__u32 reserved[2];
+};
+
+struct drm_tegra_submit_cmd {
+	/**
+	 * @type: [in]
+	 *
+	 * Command type to execute. One of the DRM_TEGRA_SUBMIT_CMD*
+	 * defines.
+	 */
+	__u32 type;
+
+	/**
+	 * @flags: [in]
+	 *
+	 * Flags.
+	 */
+	__u32 flags;
+
+	union {
+		struct drm_tegra_submit_cmd_gather_uptr gather_uptr;
+		struct drm_tegra_submit_cmd_wait_syncpt wait_syncpt;
+		__u32 reserved[4];
+	};
+};
+
+struct drm_tegra_submit_syncpt {
+	/**
+	 * @id: [in]
+	 *
+	 * ID of the syncpoint that the job will increment.
+	 */
+	__u32 id;
+
+	/**
+	 * @flags: [in]
+	 *
+	 * Flags.
+	 */
+	__u32 flags;
+
+	/**
+	 * @increments: [in]
+	 *
+	 * Number of times the job will increment this syncpoint.
+	 */
+	__u32 increments;
+
+	/**
+	 * @value: [out]
+	 *
+	 * Value the syncpoint will have once the job has completed all
+	 * its specified syncpoint increments.
+	 *
+	 * Note that the kernel may increment the syncpoint before or after
+	 * the job. These increments are not reflected in this field.
+	 *
+	 * If the job hangs or times out, not all of the increments may
+	 * get executed.
+	 */
+	__u32 value;
+};
+
+struct drm_tegra_channel_submit {
+	/**
+	 * @context: [in]
+	 *
+	 * Identifier of the channel to submit this job to.
+	 */
+	__u32 context;
+
+	/**
+	 * @num_bufs: [in]
+	 *
+	 * Number of elements in the `bufs_ptr` array.
+	 */
+	__u32 num_bufs;
+
+	/**
+	 * @num_cmds: [in]
+	 *
+	 * Number of elements in the `cmds_ptr` array.
+	 */
+	__u32 num_cmds;
+
+	/**
+	 * @gather_data_words: [in]
+	 *
+	 * Number of 32-bit words in the `gather_data_ptr` array.
+	 */
+	__u32 gather_data_words;
+
+	/**
+	 * @bufs_ptr: [in]
+	 *
+	 * Pointer to an array of drm_tegra_submit_buf structures.
+	 */
+	__u64 bufs_ptr;
+
+	/**
+	 * @cmds_ptr: [in]
+	 *
+	 * Pointer to an array of drm_tegra_submit_cmd structures.
+	 */
+	__u64 cmds_ptr;
+
+	/**
+	 * @gather_data_ptr: [in]
+	 *
+	 * Pointer to an array of Host1x opcodes to be used by GATHER_UPTR
+	 * commands.
+	 */
+	__u64 gather_data_ptr;
+
+	/**
+	 * @syncobj_in: [in]
+	 *
+	 * Handle for DRM syncobj that will be waited before submission.
+	 * Ignored if zero.
+	 */
+	__u32 syncobj_in;
+
+	/**
+	 * @syncobj_out: [in]
+	 *
+	 * Handle for DRM syncobj that will have its fence replaced with
+	 * the job's completion fence. Ignored if zero.
+	 */
+	__u32 syncobj_out;
+
+	/**
+	 * @syncpt_incr: [in,out]
+	 *
+	 * Information about the syncpoint the job will increment.
+	 */
+	struct drm_tegra_submit_syncpt syncpt;
+};
+
+struct drm_tegra_syncpoint_allocate {
+	/**
+	 * @id: [out]
+	 *
+	 * ID of allocated syncpoint.
+	 */
+	__u32 id;
+	__u32 padding;
+};
+
+struct drm_tegra_syncpoint_free {
+	/**
+	 * @id: [in]
+	 *
+	 * ID of syncpoint to free.
+	 */
+	__u32 id;
+	__u32 padding;
+};
+
+struct drm_tegra_syncpoint_wait {
+	/**
+	 * @timeout: [in]
+	 *
+	 * Absolute timestamp at which the wait will time out.
+	 */
+	__s64 timeout_ns;
+
+	/**
+	 * @id: [in]
+	 *
+	 * ID of syncpoint to wait on.
+	 */
+	__u32 id;
+
+	/**
+	 * @threshold: [in]
+	 *
+	 * Threshold to wait for.
+	 */
+	__u32 threshold;
+
+	/**
+	 * @value: [out]
+	 *
+	 * Value of the syncpoint upon wait completion.
+	 */
+	__u32 value;
+
+	__u32 padding;
+};
+
+#define DRM_IOCTL_TEGRA_CHANNEL_OPEN DRM_IOWR(DRM_COMMAND_BASE + 0x10, struct drm_tegra_channel_open)
+#define DRM_IOCTL_TEGRA_CHANNEL_CLOSE DRM_IOWR(DRM_COMMAND_BASE + 0x11, struct drm_tegra_channel_close)
+#define DRM_IOCTL_TEGRA_CHANNEL_MAP DRM_IOWR(DRM_COMMAND_BASE + 0x12, struct drm_tegra_channel_map)
+#define DRM_IOCTL_TEGRA_CHANNEL_UNMAP DRM_IOWR(DRM_COMMAND_BASE + 0x13, struct drm_tegra_channel_unmap)
+#define DRM_IOCTL_TEGRA_CHANNEL_SUBMIT DRM_IOWR(DRM_COMMAND_BASE + 0x14, struct drm_tegra_channel_submit)
+
+#define DRM_IOCTL_TEGRA_SYNCPOINT_ALLOCATE DRM_IOWR(DRM_COMMAND_BASE + 0x20, struct drm_tegra_syncpoint_allocate)
+#define DRM_IOCTL_TEGRA_SYNCPOINT_FREE DRM_IOWR(DRM_COMMAND_BASE + 0x21, struct drm_tegra_syncpoint_free)
+#define DRM_IOCTL_TEGRA_SYNCPOINT_WAIT DRM_IOWR(DRM_COMMAND_BASE + 0x22, struct drm_tegra_syncpoint_wait)
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h
index 1ce746e228d9..4104f22fb3d3 100644
--- a/include/uapi/drm/v3d_drm.h
+++ b/include/uapi/drm/v3d_drm.h
@@ -38,6 +38,9 @@ extern "C" {
 #define DRM_V3D_GET_BO_OFFSET                     0x05
 #define DRM_V3D_SUBMIT_TFU                        0x06
 #define DRM_V3D_SUBMIT_CSD                        0x07
+#define DRM_V3D_PERFMON_CREATE                    0x08
+#define DRM_V3D_PERFMON_DESTROY                   0x09
+#define DRM_V3D_PERFMON_GET_VALUES                0x0a
 
 #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)
@@ -47,6 +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_V3D_SUBMIT_CL_FLUSH_CACHE             0x01
 
@@ -127,6 +136,11 @@ struct drm_v3d_submit_cl {
 	__u32 bo_handle_count;
 
 	__u32 flags;
+
+	/* ID of the perfmon to attach to this job. 0 means no perfmon. */
+	__u32 perfmon_id;
+
+	__u32 pad;
 };
 
 /**
@@ -195,6 +209,7 @@ enum drm_v3d_param {
 	DRM_V3D_PARAM_SUPPORTS_TFU,
 	DRM_V3D_PARAM_SUPPORTS_CSD,
 	DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH,
+	DRM_V3D_PARAM_SUPPORTS_PERFMON,
 };
 
 struct drm_v3d_get_param {
@@ -258,6 +273,127 @@ struct drm_v3d_submit_csd {
 	__u32 in_sync;
 	/* Sync object to signal when the CSD job is done. */
 	__u32 out_sync;
+
+	/* ID of the perfmon to attach to this job. 0 means no perfmon. */
+	__u32 perfmon_id;
+};
+
+enum {
+	V3D_PERFCNT_FEP_VALID_PRIMTS_NO_PIXELS,
+	V3D_PERFCNT_FEP_VALID_PRIMS,
+	V3D_PERFCNT_FEP_EZ_NFCLIP_QUADS,
+	V3D_PERFCNT_FEP_VALID_QUADS,
+	V3D_PERFCNT_TLB_QUADS_STENCIL_FAIL,
+	V3D_PERFCNT_TLB_QUADS_STENCILZ_FAIL,
+	V3D_PERFCNT_TLB_QUADS_STENCILZ_PASS,
+	V3D_PERFCNT_TLB_QUADS_ZERO_COV,
+	V3D_PERFCNT_TLB_QUADS_NONZERO_COV,
+	V3D_PERFCNT_TLB_QUADS_WRITTEN,
+	V3D_PERFCNT_PTB_PRIM_VIEWPOINT_DISCARD,
+	V3D_PERFCNT_PTB_PRIM_CLIP,
+	V3D_PERFCNT_PTB_PRIM_REV,
+	V3D_PERFCNT_QPU_IDLE_CYCLES,
+	V3D_PERFCNT_QPU_ACTIVE_CYCLES_VERTEX_COORD_USER,
+	V3D_PERFCNT_QPU_ACTIVE_CYCLES_FRAG,
+	V3D_PERFCNT_QPU_CYCLES_VALID_INSTR,
+	V3D_PERFCNT_QPU_CYCLES_TMU_STALL,
+	V3D_PERFCNT_QPU_CYCLES_SCOREBOARD_STALL,
+	V3D_PERFCNT_QPU_CYCLES_VARYINGS_STALL,
+	V3D_PERFCNT_QPU_IC_HIT,
+	V3D_PERFCNT_QPU_IC_MISS,
+	V3D_PERFCNT_QPU_UC_HIT,
+	V3D_PERFCNT_QPU_UC_MISS,
+	V3D_PERFCNT_TMU_TCACHE_ACCESS,
+	V3D_PERFCNT_TMU_TCACHE_MISS,
+	V3D_PERFCNT_VPM_VDW_STALL,
+	V3D_PERFCNT_VPM_VCD_STALL,
+	V3D_PERFCNT_BIN_ACTIVE,
+	V3D_PERFCNT_RDR_ACTIVE,
+	V3D_PERFCNT_L2T_HITS,
+	V3D_PERFCNT_L2T_MISSES,
+	V3D_PERFCNT_CYCLE_COUNT,
+	V3D_PERFCNT_QPU_CYCLES_STALLED_VERTEX_COORD_USER,
+	V3D_PERFCNT_QPU_CYCLES_STALLED_FRAGMENT,
+	V3D_PERFCNT_PTB_PRIMS_BINNED,
+	V3D_PERFCNT_AXI_WRITES_WATCH_0,
+	V3D_PERFCNT_AXI_READS_WATCH_0,
+	V3D_PERFCNT_AXI_WRITE_STALLS_WATCH_0,
+	V3D_PERFCNT_AXI_READ_STALLS_WATCH_0,
+	V3D_PERFCNT_AXI_WRITE_BYTES_WATCH_0,
+	V3D_PERFCNT_AXI_READ_BYTES_WATCH_0,
+	V3D_PERFCNT_AXI_WRITES_WATCH_1,
+	V3D_PERFCNT_AXI_READS_WATCH_1,
+	V3D_PERFCNT_AXI_WRITE_STALLS_WATCH_1,
+	V3D_PERFCNT_AXI_READ_STALLS_WATCH_1,
+	V3D_PERFCNT_AXI_WRITE_BYTES_WATCH_1,
+	V3D_PERFCNT_AXI_READ_BYTES_WATCH_1,
+	V3D_PERFCNT_TLB_PARTIAL_QUADS,
+	V3D_PERFCNT_TMU_CONFIG_ACCESSES,
+	V3D_PERFCNT_L2T_NO_ID_STALL,
+	V3D_PERFCNT_L2T_COM_QUE_STALL,
+	V3D_PERFCNT_L2T_TMU_WRITES,
+	V3D_PERFCNT_TMU_ACTIVE_CYCLES,
+	V3D_PERFCNT_TMU_STALLED_CYCLES,
+	V3D_PERFCNT_CLE_ACTIVE,
+	V3D_PERFCNT_L2T_TMU_READS,
+	V3D_PERFCNT_L2T_CLE_READS,
+	V3D_PERFCNT_L2T_VCD_READS,
+	V3D_PERFCNT_L2T_TMUCFG_READS,
+	V3D_PERFCNT_L2T_SLC0_READS,
+	V3D_PERFCNT_L2T_SLC1_READS,
+	V3D_PERFCNT_L2T_SLC2_READS,
+	V3D_PERFCNT_L2T_TMU_W_MISSES,
+	V3D_PERFCNT_L2T_TMU_R_MISSES,
+	V3D_PERFCNT_L2T_CLE_MISSES,
+	V3D_PERFCNT_L2T_VCD_MISSES,
+	V3D_PERFCNT_L2T_TMUCFG_MISSES,
+	V3D_PERFCNT_L2T_SLC0_MISSES,
+	V3D_PERFCNT_L2T_SLC1_MISSES,
+	V3D_PERFCNT_L2T_SLC2_MISSES,
+	V3D_PERFCNT_CORE_MEM_WRITES,
+	V3D_PERFCNT_L2T_MEM_WRITES,
+	V3D_PERFCNT_PTB_MEM_WRITES,
+	V3D_PERFCNT_TLB_MEM_WRITES,
+	V3D_PERFCNT_CORE_MEM_READS,
+	V3D_PERFCNT_L2T_MEM_READS,
+	V3D_PERFCNT_PTB_MEM_READS,
+	V3D_PERFCNT_PSE_MEM_READS,
+	V3D_PERFCNT_TLB_MEM_READS,
+	V3D_PERFCNT_GMP_MEM_READS,
+	V3D_PERFCNT_PTB_W_MEM_WORDS,
+	V3D_PERFCNT_TLB_W_MEM_WORDS,
+	V3D_PERFCNT_PSE_R_MEM_WORDS,
+	V3D_PERFCNT_TLB_R_MEM_WORDS,
+	V3D_PERFCNT_TMU_MRU_HITS,
+	V3D_PERFCNT_COMPUTE_ACTIVE,
+	V3D_PERFCNT_NUM,
+};
+
+#define DRM_V3D_MAX_PERF_COUNTERS                 32
+
+struct drm_v3d_perfmon_create {
+	__u32 id;
+	__u32 ncounters;
+	__u8 counters[DRM_V3D_MAX_PERF_COUNTERS];
+};
+
+struct drm_v3d_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_v3d_perfmon_get_values {
+	__u32 id;
+	__u32 pad;
+	__u64 values_ptr;
 };
 
 #if defined(__cplusplus)
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index 02e917507479..9078775feb51 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -72,6 +72,9 @@ extern "C" {
 #define DRM_VMW_GB_SURFACE_CREATE_EXT   27
 #define DRM_VMW_GB_SURFACE_REF_EXT      28
 #define DRM_VMW_MSG                     29
+#define DRM_VMW_MKSSTAT_RESET           30
+#define DRM_VMW_MKSSTAT_ADD             31
+#define DRM_VMW_MKSSTAT_REMOVE          32
 
 /*************************************************************************/
 /**
@@ -1236,6 +1239,44 @@ struct drm_vmw_msg_arg {
 	__u32 receive_len;
 };
 
+/**
+ * struct drm_vmw_mksstat_add_arg
+ *
+ * @stat: Pointer to user-space stat-counters array, page-aligned.
+ * @info: Pointer to user-space counter-infos array, page-aligned.
+ * @strs: Pointer to user-space stat strings, page-aligned.
+ * @stat_len: Length in bytes of stat-counters array.
+ * @info_len: Length in bytes of counter-infos array.
+ * @strs_len: Length in bytes of the stat strings, terminators included.
+ * @description: Pointer to instance descriptor string; will be truncated
+ *               to MKS_GUEST_STAT_INSTANCE_DESC_LENGTH chars.
+ * @id: Output identifier of the produced record; -1 if error.
+ *
+ * Argument to the DRM_VMW_MKSSTAT_ADD ioctl.
+ */
+struct drm_vmw_mksstat_add_arg {
+	__u64 stat;
+	__u64 info;
+	__u64 strs;
+	__u64 stat_len;
+	__u64 info_len;
+	__u64 strs_len;
+	__u64 description;
+	__u64 id;
+};
+
+/**
+ * struct drm_vmw_mksstat_remove_arg
+ *
+ * @id: Identifier of the record being disposed, originally obtained through
+ *      DRM_VMW_MKSSTAT_ADD ioctl.
+ *
+ * Argument to the DRM_VMW_MKSSTAT_REMOVE ioctl.
+ */
+struct drm_vmw_mksstat_remove_arg {
+	__u64 id;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h
index 7f30393b92c3..8e4a2ca0bcbf 100644
--- a/include/uapi/linux/dma-buf.h
+++ b/include/uapi/linux/dma-buf.h
@@ -22,8 +22,56 @@
 
 #include <linux/types.h>
 
-/* begin/end dma-buf functions used for userspace mmap. */
+/**
+ * struct dma_buf_sync - Synchronize with CPU access.
+ *
+ * When a DMA buffer is accessed from the CPU via mmap, it is not always
+ * possible to guarantee coherency between the CPU-visible map and underlying
+ * memory.  To manage coherency, DMA_BUF_IOCTL_SYNC must be used to bracket
+ * any CPU access to give the kernel the chance to shuffle memory around if
+ * needed.
+ *
+ * Prior to accessing the map, the client must call DMA_BUF_IOCTL_SYNC
+ * with DMA_BUF_SYNC_START and the appropriate read/write flags.  Once the
+ * access is complete, the client should call DMA_BUF_IOCTL_SYNC with
+ * DMA_BUF_SYNC_END and the same read/write flags.
+ *
+ * The synchronization provided via DMA_BUF_IOCTL_SYNC only provides cache
+ * coherency.  It does not prevent other processes or devices from
+ * accessing the memory at the same time.  If synchronization with a GPU or
+ * other device driver is required, it is the client's responsibility to
+ * wait for buffer to be ready for reading or writing before calling this
+ * ioctl with DMA_BUF_SYNC_START.  Likewise, the client must ensure that
+ * follow-up work is not submitted to GPU or other device driver until
+ * after this ioctl has been called with DMA_BUF_SYNC_END?
+ *
+ * If the driver or API with which the client is interacting uses implicit
+ * synchronization, waiting for prior work to complete can be done via
+ * poll() on the DMA buffer file descriptor.  If the driver or API requires
+ * explicit synchronization, the client may have to wait on a sync_file or
+ * other synchronization primitive outside the scope of the DMA buffer API.
+ */
 struct dma_buf_sync {
+	/**
+	 * @flags: Set of access flags
+	 *
+	 * DMA_BUF_SYNC_START:
+	 *     Indicates the start of a map access session.
+	 *
+	 * DMA_BUF_SYNC_END:
+	 *     Indicates the end of a map access session.
+	 *
+	 * DMA_BUF_SYNC_READ:
+	 *     Indicates that the mapped DMA buffer will be read by the
+	 *     client via the CPU map.
+	 *
+	 * DMA_BUF_SYNC_WRITE:
+	 *     Indicates that the mapped DMA buffer will be written by the
+	 *     client via the CPU map.
+	 *
+	 * DMA_BUF_SYNC_RW:
+	 *     An alias for DMA_BUF_SYNC_READ | DMA_BUF_SYNC_WRITE.
+	 */
 	__u64 flags;
 };
 
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 3cb5b5dd9f77..af96af174dc4 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -31,9 +31,10 @@
  * - 1.3 - Add SMI events support
  * - 1.4 - Indicate new SRAM EDC bit in device properties
  * - 1.5 - Add SVM API
+ * - 1.6 - Query clear flags in SVM get_attr API
  */
 #define KFD_IOCTL_MAJOR_VERSION 1
-#define KFD_IOCTL_MINOR_VERSION 5
+#define KFD_IOCTL_MINOR_VERSION 6
 
 struct kfd_ioctl_get_version_args {
 	__u32 major_version;	/* from KFD */
@@ -575,18 +576,19 @@ struct kfd_ioctl_svm_attribute {
  * @KFD_IOCTL_SVM_ATTR_PREFERRED_LOC or
  * @KFD_IOCTL_SVM_ATTR_PREFETCH_LOC resepctively. For
  * @KFD_IOCTL_SVM_ATTR_SET_FLAGS, flags of all pages will be
- * aggregated by bitwise AND. The minimum  migration granularity
- * throughout the range will be returned for
- * @KFD_IOCTL_SVM_ATTR_GRANULARITY.
+ * aggregated by bitwise AND. That means, a flag will be set in the
+ * output, if that flag is set for all pages in the range. For
+ * @KFD_IOCTL_SVM_ATTR_CLR_FLAGS, flags of all pages will be
+ * aggregated by bitwise NOR. That means, a flag will be set in the
+ * output, if that flag is clear for all pages in the range.
+ * The minimum migration granularity throughout the range will be
+ * returned for @KFD_IOCTL_SVM_ATTR_GRANULARITY.
  *
  * Querying of accessibility attributes works by initializing the
  * attribute type to @KFD_IOCTL_SVM_ATTR_ACCESS and the value to the
  * GPUID being queried. Multiple attributes can be given to allow
  * querying multiple GPUIDs. The ioctl function overwrites the
  * attribute type to indicate the access for the specified GPU.
- *
- * @KFD_IOCTL_SVM_ATTR_CLR_FLAGS is invalid for
- * @KFD_IOCTL_SVM_OP_GET_ATTR.
  */
 struct kfd_ioctl_svm_args {
 	__u64 start_addr;