Merge tag 'drm-next-2019-07-16' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "The biggest thing in this is the AMD Navi GPU support, this again
  contains a bunch of header files that are large. These are the new AMD
  RX5700 GPUs that just recently became available.

  New drivers:
   - ST-Ericsson MCDE driver
   - Ingenic JZ47xx SoC

  UAPI change:
   - HDR source metadata property

  Core:
   - HDR inforframes and EDID parsing
   - drm hdmi infoframe unpacking
   - remove prime sg_table caching into dma-buf
   - New gem vram helpers to reduce driver code
   - Lots of drmP.h removal
   - reservation fencing fix
   - documentation updates
   - drm_fb_helper_connector removed
   - mode name command handler rewrite

  fbcon:
   - Remove the fbcon notifiers

  ttm:
   - forward progress fixes

  dma-buf:
   - make mmap call optional
   - debugfs refcount fixes
   - dma-fence free with pending signals fix
   - each dma-buf gets an inode

  Panels:
   - Lots of additional panel bindings

  amdgpu:
   - initial navi10 support
   - avoid hw reset
   - HDR metadata support
   - new thermal sensors for vega asics
   - RAS fixes
   - use HMM rather than MMU notifier
   - xgmi topology via kfd
   - SR-IOV fixes
   - driver reload fixes
   - DC use a core bpc attribute
   - Aux fixes for DC
   - Bandwidth calc updates for DC
   - Clock handling refactor
   - kfd VEGAM support

  vmwgfx:
   - Coherent memory support changes

  i915:
   - HDR Support
   - HDMI i2c link
   - Icelake multi-segmented gamma support
   - GuC firmware update
   - Mule Creek Canyon PCH support for EHL
   - EHL platform updtes
   - move i915.alpha_support to i915.force_probe
   - runtime PM refactoring
   - VBT parsing refactoring
   - DSI fixes
   - struct mutex dependency reduction
   - GEM code reorg

  mali-dp:
   - Komeda driver features

  msm:
   - dsi vs EPROBE_DEFER fixes
   - msm8998 snapdragon 835 support
   - a540 gpu support
   - mdp5 and dpu interconnect support

  exynos:
   - drmP.h removal

  tegra:
   - misc fixes

  tda998x:
   - audio support improvements
   - pixel repeated mode support
   - quantisation range handling corrections
   - HDMI vendor info fix

  armada:
   - interlace support fix
   - overlay/video plane register handling refactor
   - add gamma support

  rockchip:
   - RX3328 support

  panfrost:
   - expose perf counters via hidden ioctls

  vkms:
   - enumerate CRC sources list

  ast:
   - rework BO handling

  mgag200:
   - rework BO handling

  dw-hdmi:
   - suspend/resume support

  rcar-du:
   - R8A774A1 Soc Support
   - LVDS dual-link mode support
   - Additional formats
   - Misc fixes

  omapdrm:
   - DSI command mode display support

  stm
   - fb modifier support
   - runtime PM support

  sun4i:
   - use vmap ops

  vc4:
   - binner bo binding rework

  v3d:
   - compute shader support
   - resync/sync fixes
   - job management refactoring

  lima:
   - NULL pointer in irq handler fix
   - scheduler default timeout

  virtio:
   - fence seqno support
   - trace events

  bochs:
   - misc fixes

  tc458767:
   - IRQ/HDP handling

  sii902x:
   - HDMI audio support

  atmel-hlcdc:
   - misc fixes

  meson:
   - zpos support"

* tag 'drm-next-2019-07-16' of git://anongit.freedesktop.org/drm/drm: (1815 commits)
  Revert "Merge branch 'vmwgfx-next' of git://people.freedesktop.org/~thomash/linux into drm-next"
  Revert "mm: adjust apply_to_pfn_range interface for dropped token."
  mm: adjust apply_to_pfn_range interface for dropped token.
  drm/amdgpu/navi10: add uclk activity sensor
  drm/amdgpu: properly guard the generic discovery code
  drm/amdgpu: add missing documentation on new module parameters
  drm/amdgpu: don't invalidate caches in RELEASE_MEM, only do the writeback
  drm/amd/display: avoid 64-bit division
  drm/amdgpu/psp11: simplify the ucode register logic
  drm/amdgpu: properly guard DC support in navi code
  drm/amd/powerplay: vega20: fix uninitialized variable use
  drm/amd/display: dcn20: include linux/delay.h
  amdgpu: make pmu support optional
  drm/amd/powerplay: Zero initialize current_rpm in vega20_get_fan_speed_percent
  drm/amd/powerplay: Zero initialize freq in smu_v11_0_get_current_clk_freq
  drm/amd/powerplay: Use memset to initialize metrics structs
  drm/amdgpu/mes10.1: Fix header guard
  drm/amd/powerplay: add temperature sensor support for navi10
  drm/amdgpu: fix scheduler timeout calc
  drm/amdgpu: Prepare for hmm_range_register API change (v2)
  ...

9 files changed, 415 insertions, 7 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 4788730dbe78..d799858b9e53 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -912,6 +912,7 @@ struct drm_amdgpu_info_firmware {
 #define AMDGPU_VRAM_TYPE_HBM   6
 #define AMDGPU_VRAM_TYPE_DDR3  7
 #define AMDGPU_VRAM_TYPE_DDR4  8
+#define AMDGPU_VRAM_TYPE_GDDR6 9
 
 struct drm_amdgpu_info_device {
 	/** PCI Device ID */
@@ -991,6 +992,8 @@ struct drm_amdgpu_info_device {
 	__u64 high_va_offset;
 	/** The maximum high virtual address */
 	__u64 high_va_max;
+	/* gfx10 pa_sc_tile_steering_override */
+	__u32 pa_sc_tile_steering_override;
 };
 
 struct drm_amdgpu_info_hw_ip {
@@ -1044,6 +1047,7 @@ struct drm_amdgpu_info_vce_clock_table {
 #define AMDGPU_FAMILY_CZ			135 /* Carrizo, Stoney */
 #define AMDGPU_FAMILY_AI			141 /* Vega10 */
 #define AMDGPU_FAMILY_RV			142 /* Raven */
+#define AMDGPU_FAMILY_NV			143 /* Navi10 */
 
 #if defined(__cplusplus)
 }
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 661d73f9a919..8a5b2f8f8eb9 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -50,6 +50,7 @@ typedef unsigned int drm_handle_t;
 
 #else /* One of the BSDs */
 
+#include <stdint.h>
 #include <sys/ioccom.h>
 #include <sys/types.h>
 typedef int8_t   __s8;
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 83cd1636b9be..5ab331e5dc23 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -33,6 +33,15 @@
 extern "C" {
 #endif
 
+/**
+ * DOC: overview
+ *
+ * DRM exposes many UAPI and structure definition to have a consistent
+ * and standardized interface with user.
+ * Userspace can refer to these structure definitions and UAPI formats
+ * to communicate to driver
+ */
+
 #define DRM_CONNECTOR_NAME_LEN	32
 #define DRM_DISPLAY_MODE_LEN	32
 #define DRM_PROP_NAME_LEN	32
@@ -630,6 +639,92 @@ struct drm_color_lut {
 	__u16 reserved;
 };
 
+/**
+ * struct hdr_metadata_infoframe - HDR Metadata Infoframe Data.
+ *
+ * HDR Metadata Infoframe as per CTA 861.G spec. This is expected
+ * to match exactly with the spec.
+ *
+ * Userspace is expected to pass the metadata information as per
+ * the format described in this structure.
+ */
+struct hdr_metadata_infoframe {
+	/**
+	 * @eotf: Electro-Optical Transfer Function (EOTF)
+	 * used in the stream.
+	 */
+	__u8 eotf;
+	/**
+	 * @metadata_type: Static_Metadata_Descriptor_ID.
+	 */
+	__u8 metadata_type;
+	/**
+	 * @display_primaries: Color Primaries of the Data.
+	 * These are coded as unsigned 16-bit values in units of
+	 * 0.00002, where 0x0000 represents zero and 0xC350
+	 * represents 1.0000.
+	 * @display_primaries.x: X cordinate of color primary.
+	 * @display_primaries.y: Y cordinate of color primary.
+	 */
+	struct {
+		__u16 x, y;
+		} display_primaries[3];
+	/**
+	 * @white_point: White Point of Colorspace Data.
+	 * These are coded as unsigned 16-bit values in units of
+	 * 0.00002, where 0x0000 represents zero and 0xC350
+	 * represents 1.0000.
+	 * @white_point.x: X cordinate of whitepoint of color primary.
+	 * @white_point.y: Y cordinate of whitepoint of color primary.
+	 */
+	struct {
+		__u16 x, y;
+		} white_point;
+	/**
+	 * @max_display_mastering_luminance: Max Mastering Display Luminance.
+	 * This value is coded as an unsigned 16-bit value in units of 1 cd/m2,
+	 * where 0x0001 represents 1 cd/m2 and 0xFFFF represents 65535 cd/m2.
+	 */
+	__u16 max_display_mastering_luminance;
+	/**
+	 * @min_display_mastering_luminance: Min Mastering Display Luminance.
+	 * This value is coded as an unsigned 16-bit value in units of
+	 * 0.0001 cd/m2, where 0x0001 represents 0.0001 cd/m2 and 0xFFFF
+	 * represents 6.5535 cd/m2.
+	 */
+	__u16 min_display_mastering_luminance;
+	/**
+	 * @max_cll: Max Content Light Level.
+	 * This value is coded as an unsigned 16-bit value in units of 1 cd/m2,
+	 * where 0x0001 represents 1 cd/m2 and 0xFFFF represents 65535 cd/m2.
+	 */
+	__u16 max_cll;
+	/**
+	 * @max_fall: Max Frame Average Light Level.
+	 * This value is coded as an unsigned 16-bit value in units of 1 cd/m2,
+	 * where 0x0001 represents 1 cd/m2 and 0xFFFF represents 65535 cd/m2.
+	 */
+	__u16 max_fall;
+};
+
+/**
+ * struct hdr_output_metadata - HDR output metadata
+ *
+ * Metadata Information to be passed from userspace
+ */
+struct hdr_output_metadata {
+	/**
+	 * @metadata_type: Static_Metadata_Descriptor_ID.
+	 */
+	__u32 metadata_type;
+	/**
+	 * @hdmi_metadata_type1: HDR Metadata Infoframe.
+	 */
+	union {
+		struct hdr_metadata_infoframe hdmi_metadata_type1;
+	};
+};
+
 #define DRM_MODE_PAGE_FLIP_EVENT 0x01
 #define DRM_MODE_PAGE_FLIP_ASYNC 0x02
 #define DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE 0x4
@@ -803,6 +898,10 @@ struct drm_format_modifier {
 };
 
 /**
+ * struct drm_mode_create_blob - Create New block property
+ * @data: Pointer to data to copy.
+ * @length: Length of data to copy.
+ * @blob_id: new property ID.
  * Create a new 'blob' data property, copying length bytes from data pointer,
  * and returning new blob ID.
  */
@@ -816,6 +915,8 @@ struct drm_mode_create_blob {
 };
 
 /**
+ * struct drm_mode_destroy_blob - Destroy user blob
+ * @blob_id: blob_id to destroy
  * Destroy a user-created blob property.
  */
 struct drm_mode_destroy_blob {
@@ -823,6 +924,12 @@ struct drm_mode_destroy_blob {
 };
 
 /**
+ * struct drm_mode_create_lease - Create lease
+ * @object_ids: Pointer to array of object ids.
+ * @object_count: Number of object ids.
+ * @flags: flags for new FD.
+ * @lessee_id: unique identifier for lessee.
+ * @fd: file descriptor to new drm_master file.
  * Lease mode resources, creating another drm_master.
  */
 struct drm_mode_create_lease {
@@ -840,6 +947,10 @@ struct drm_mode_create_lease {
 };
 
 /**
+ * struct drm_mode_list_lessees - List lessees
+ * @count_lessees: Number of lessees.
+ * @pad: pad.
+ * @lessees_ptr: Pointer to lessess.
  * List lesses from a drm_master
  */
 struct drm_mode_list_lessees {
@@ -860,6 +971,10 @@ struct drm_mode_list_lessees {
 };
 
 /**
+ * struct drm_mode_get_lease - Get Lease
+ * @count_objects: Number of leased objects.
+ * @pad: pad.
+ * @objects_ptr: Pointer to objects.
  * Get leased objects
  */
 struct drm_mode_get_lease {
@@ -880,6 +995,8 @@ struct drm_mode_get_lease {
 };
 
 /**
+ * struct drm_mode_revoke_lease - Revoke lease
+ * @lessee_id: Unique ID of lessee.
  * Revoke lease
  */
 struct drm_mode_revoke_lease {
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 3a73f5316766..328d05e77d9f 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -136,6 +136,8 @@ enum drm_i915_gem_engine_class {
 struct i915_engine_class_instance {
 	__u16 engine_class; /* see enum drm_i915_gem_engine_class */
 	__u16 engine_instance;
+#define I915_ENGINE_CLASS_INVALID_NONE -1
+#define I915_ENGINE_CLASS_INVALID_VIRTUAL -2
 };
 
 /**
@@ -355,6 +357,8 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_PERF_ADD_CONFIG	0x37
 #define DRM_I915_PERF_REMOVE_CONFIG	0x38
 #define DRM_I915_QUERY			0x39
+#define DRM_I915_GEM_VM_CREATE		0x3a
+#define DRM_I915_GEM_VM_DESTROY		0x3b
 /* Must be kept compact -- no holes */
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
@@ -415,6 +419,8 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_PERF_ADD_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
 #define DRM_IOCTL_I915_PERF_REMOVE_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
 #define DRM_IOCTL_I915_QUERY			DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query)
+#define DRM_IOCTL_I915_GEM_VM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_VM_CREATE, struct drm_i915_gem_vm_control)
+#define DRM_IOCTL_I915_GEM_VM_DESTROY	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_VM_DESTROY, struct drm_i915_gem_vm_control)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -598,6 +604,12 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_MMAP_GTT_COHERENT	52
 
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports coordination of parallel
+ * execution through use of explicit fence support.
+ * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT.
+ */
+#define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53
 /* Must be kept compact -- no holes and well documented */
 
 typedef struct drm_i915_getparam {
@@ -1120,7 +1132,16 @@ struct drm_i915_gem_execbuffer2 {
  */
 #define I915_EXEC_FENCE_ARRAY   (1<<19)
 
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1))
+/*
+ * Setting I915_EXEC_FENCE_SUBMIT implies that lower_32_bits(rsvd2) represent
+ * a sync_file fd to wait upon (in a nonblocking manner) prior to executing
+ * the batch.
+ *
+ * Returns -EINVAL if the sync_file fd cannot be found.
+ */
+#define I915_EXEC_FENCE_SUBMIT		(1 << 20)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1))
 
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
@@ -1464,8 +1485,9 @@ struct drm_i915_gem_context_create_ext {
 	__u32 ctx_id; /* output: id of new context*/
 	__u32 flags;
 #define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS	(1u << 0)
+#define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE	(1u << 1)
 #define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \
-	(-(I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS << 1))
+	(-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1))
 	__u64 extensions;
 };
 
@@ -1507,6 +1529,41 @@ struct drm_i915_gem_context_param {
  * On creation, all new contexts are marked as recoverable.
  */
 #define I915_CONTEXT_PARAM_RECOVERABLE	0x8
+
+	/*
+	 * The id of the associated virtual memory address space (ppGTT) of
+	 * this context. Can be retrieved and passed to another context
+	 * (on the same fd) for both to use the same ppGTT and so share
+	 * address layouts, and avoid reloading the page tables on context
+	 * switches between themselves.
+	 *
+	 * See DRM_I915_GEM_VM_CREATE and DRM_I915_GEM_VM_DESTROY.
+	 */
+#define I915_CONTEXT_PARAM_VM		0x9
+
+/*
+ * I915_CONTEXT_PARAM_ENGINES:
+ *
+ * Bind this context to operate on this subset of available engines. Henceforth,
+ * the I915_EXEC_RING selector for DRM_IOCTL_I915_GEM_EXECBUFFER2 operates as
+ * an index into this array of engines; I915_EXEC_DEFAULT selecting engine[0]
+ * and upwards. Slots 0...N are filled in using the specified (class, instance).
+ * Use
+ *	engine_class: I915_ENGINE_CLASS_INVALID,
+ *	engine_instance: I915_ENGINE_CLASS_INVALID_NONE
+ * to specify a gap in the array that can be filled in later, e.g. by a
+ * virtual engine used for load balancing.
+ *
+ * Setting the number of engines bound to the context to 0, by passing a zero
+ * sized argument, will revert back to default settings.
+ *
+ * See struct i915_context_param_engines.
+ *
+ * Extensions:
+ *   i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE)
+ *   i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
+ */
+#define I915_CONTEXT_PARAM_ENGINES	0xa
 /* Must be kept compact -- no holes and well documented */
 
 	__u64 value;
@@ -1540,9 +1597,10 @@ struct drm_i915_gem_context_param_sseu {
 	struct i915_engine_class_instance engine;
 
 	/*
-	 * Unused for now. Must be cleared to zero.
+	 * Unknown flags must be cleared to zero.
 	 */
 	__u32 flags;
+#define I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX (1u << 0)
 
 	/*
 	 * Mask of slices to enable for the context. Valid values are a subset
@@ -1570,12 +1628,115 @@ struct drm_i915_gem_context_param_sseu {
 	__u32 rsvd;
 };
 
+/*
+ * i915_context_engines_load_balance:
+ *
+ * Enable load balancing across this set of engines.
+ *
+ * Into the I915_EXEC_DEFAULT slot [0], a virtual engine is created that when
+ * used will proxy the execbuffer request onto one of the set of engines
+ * in such a way as to distribute the load evenly across the set.
+ *
+ * The set of engines must be compatible (e.g. the same HW class) as they
+ * will share the same logical GPU context and ring.
+ *
+ * To intermix rendering with the virtual engine and direct rendering onto
+ * the backing engines (bypassing the load balancing proxy), the context must
+ * be defined to use a single timeline for all engines.
+ */
+struct i915_context_engines_load_balance {
+	struct i915_user_extension base;
+
+	__u16 engine_index;
+	__u16 num_siblings;
+	__u32 flags; /* all undefined flags must be zero */
+
+	__u64 mbz64; /* reserved for future use; must be zero */
+
+	struct i915_engine_class_instance engines[0];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(name__, N__) struct { \
+	struct i915_user_extension base; \
+	__u16 engine_index; \
+	__u16 num_siblings; \
+	__u32 flags; \
+	__u64 mbz64; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+/*
+ * i915_context_engines_bond:
+ *
+ * Constructed bonded pairs for execution within a virtual engine.
+ *
+ * All engines are equal, but some are more equal than others. Given
+ * the distribution of resources in the HW, it may be preferable to run
+ * a request on a given subset of engines in parallel to a request on a
+ * specific engine. We enable this selection of engines within a virtual
+ * engine by specifying bonding pairs, for any given master engine we will
+ * only execute on one of the corresponding siblings within the virtual engine.
+ *
+ * To execute a request in parallel on the master engine and a sibling requires
+ * coordination with a I915_EXEC_FENCE_SUBMIT.
+ */
+struct i915_context_engines_bond {
+	struct i915_user_extension base;
+
+	struct i915_engine_class_instance master;
+
+	__u16 virtual_index; /* index of virtual engine in ctx->engines[] */
+	__u16 num_bonds;
+
+	__u64 flags; /* all undefined flags must be zero */
+	__u64 mbz64[4]; /* reserved for future use; must be zero */
+
+	struct i915_engine_class_instance engines[0];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_ENGINES_BOND(name__, N__) struct { \
+	struct i915_user_extension base; \
+	struct i915_engine_class_instance master; \
+	__u16 virtual_index; \
+	__u16 num_bonds; \
+	__u64 flags; \
+	__u64 mbz64[4]; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+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 */
+#define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */
+	struct i915_engine_class_instance engines[0];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \
+	__u64 extensions; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
 struct drm_i915_gem_context_create_ext_setparam {
 #define I915_CONTEXT_CREATE_EXT_SETPARAM 0
 	struct i915_user_extension base;
 	struct drm_i915_gem_context_param param;
 };
 
+struct drm_i915_gem_context_create_ext_clone {
+#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;
 	__u32 pad;
@@ -1821,6 +1982,7 @@ struct drm_i915_perf_oa_config {
 struct drm_i915_query_item {
 	__u64 query_id;
 #define DRM_I915_QUERY_TOPOLOGY_INFO    1
+#define DRM_I915_QUERY_ENGINE_INFO	2
 /* Must be kept compact -- no holes and well documented */
 
 	/*
@@ -1919,6 +2081,47 @@ struct drm_i915_query_topology_info {
 	__u8 data[];
 };
 
+/**
+ * struct drm_i915_engine_info
+ *
+ * Describes one engine and it's capabilities as known to the driver.
+ */
+struct drm_i915_engine_info {
+	/** Engine class and instance. */
+	struct i915_engine_class_instance engine;
+
+	/** Reserved field. */
+	__u32 rsvd0;
+
+	/** Engine flags. */
+	__u64 flags;
+
+	/** Capabilities of this engine. */
+	__u64 capabilities;
+#define I915_VIDEO_CLASS_CAPABILITY_HEVC		(1 << 0)
+#define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC	(1 << 1)
+
+	/** Reserved fields. */
+	__u64 rsvd1[4];
+};
+
+/**
+ * struct drm_i915_query_engine_info
+ *
+ * Engine info query enumerates all engines known to the driver by filling in
+ * an array of struct drm_i915_engine_info structures.
+ */
+struct drm_i915_query_engine_info {
+	/** Number of struct drm_i915_engine_info structs following. */
+	__u32 num_engines;
+
+	/** MBZ */
+	__u32 rsvd[3];
+
+	/** Marker for drm_i915_engine_info structures. */
+	struct drm_i915_engine_info engines[];
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/panfrost_drm.h b/include/uapi/drm/panfrost_drm.h
index a52e0283b90d..b5d370638846 100644
--- a/include/uapi/drm/panfrost_drm.h
+++ b/include/uapi/drm/panfrost_drm.h
@@ -18,6 +18,8 @@ extern "C" {
 #define DRM_PANFROST_MMAP_BO			0x03
 #define DRM_PANFROST_GET_PARAM			0x04
 #define DRM_PANFROST_GET_BO_OFFSET		0x05
+#define DRM_PANFROST_PERFCNT_ENABLE		0x06
+#define DRM_PANFROST_PERFCNT_DUMP		0x07
 
 #define DRM_IOCTL_PANFROST_SUBMIT		DRM_IOW(DRM_COMMAND_BASE + DRM_PANFROST_SUBMIT, struct drm_panfrost_submit)
 #define DRM_IOCTL_PANFROST_WAIT_BO		DRM_IOW(DRM_COMMAND_BASE + DRM_PANFROST_WAIT_BO, struct drm_panfrost_wait_bo)
@@ -26,6 +28,15 @@ extern "C" {
 #define DRM_IOCTL_PANFROST_GET_PARAM		DRM_IOWR(DRM_COMMAND_BASE + DRM_PANFROST_GET_PARAM, struct drm_panfrost_get_param)
 #define DRM_IOCTL_PANFROST_GET_BO_OFFSET	DRM_IOWR(DRM_COMMAND_BASE + DRM_PANFROST_GET_BO_OFFSET, struct drm_panfrost_get_bo_offset)
 
+/*
+ * Unstable ioctl(s): only exposed when the unsafe unstable_ioctls module
+ * param is set to true.
+ * All these ioctl(s) are subject to deprecation, so please don't rely on
+ * them for anything but debugging purpose.
+ */
+#define DRM_IOCTL_PANFROST_PERFCNT_ENABLE	DRM_IOW(DRM_COMMAND_BASE + DRM_PANFROST_PERFCNT_ENABLE, struct drm_panfrost_perfcnt_enable)
+#define DRM_IOCTL_PANFROST_PERFCNT_DUMP		DRM_IOW(DRM_COMMAND_BASE + DRM_PANFROST_PERFCNT_DUMP, struct drm_panfrost_perfcnt_dump)
+
 #define PANFROST_JD_REQ_FS (1 << 0)
 /**
  * struct drm_panfrost_submit - ioctl argument for submitting commands to the 3D
@@ -135,6 +146,19 @@ struct drm_panfrost_get_bo_offset {
 	__u64 offset;
 };
 
+struct drm_panfrost_perfcnt_enable {
+	__u32 enable;
+	/*
+	 * On bifrost we have 2 sets of counters, this parameter defines the
+	 * one to track.
+	 */
+	__u32 counterset;
+};
+
+struct drm_panfrost_perfcnt_dump {
+	__u64 buf_ptr;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h
index ea70669d2138..58fbe48c91e9 100644
--- a/include/uapi/drm/v3d_drm.h
+++ b/include/uapi/drm/v3d_drm.h
@@ -37,6 +37,7 @@ extern "C" {
 #define DRM_V3D_GET_PARAM                         0x04
 #define DRM_V3D_GET_BO_OFFSET                     0x05
 #define DRM_V3D_SUBMIT_TFU                        0x06
+#define DRM_V3D_SUBMIT_CSD                        0x07
 
 #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)
@@ -45,6 +46,7 @@ extern "C" {
 #define DRM_IOCTL_V3D_GET_PARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_GET_PARAM, struct drm_v3d_get_param)
 #define DRM_IOCTL_V3D_GET_BO_OFFSET       DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_GET_BO_OFFSET, struct drm_v3d_get_bo_offset)
 #define DRM_IOCTL_V3D_SUBMIT_TFU          DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_TFU, struct drm_v3d_submit_tfu)
+#define DRM_IOCTL_V3D_SUBMIT_CSD          DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CSD, struct drm_v3d_submit_csd)
 
 /**
  * struct drm_v3d_submit_cl - ioctl argument for submitting commands to the 3D
@@ -190,6 +192,7 @@ enum drm_v3d_param {
 	DRM_V3D_PARAM_V3D_CORE0_IDENT1,
 	DRM_V3D_PARAM_V3D_CORE0_IDENT2,
 	DRM_V3D_PARAM_SUPPORTS_TFU,
+	DRM_V3D_PARAM_SUPPORTS_CSD,
 };
 
 struct drm_v3d_get_param {
@@ -230,6 +233,31 @@ struct drm_v3d_submit_tfu {
 	__u32 out_sync;
 };
 
+/* Submits a compute shader for dispatch.  This job will block on any
+ * previous compute shaders submitted on this fd, and any other
+ * synchronization must be performed with in_sync/out_sync.
+ */
+struct drm_v3d_submit_csd {
+	__u32 cfg[7];
+	__u32 coef[4];
+
+	/* Pointer to a u32 array of the BOs that are referenced by the job.
+	 */
+	__u64 bo_handles;
+
+	/* Number of BO handles passed in (size is that times 4). */
+	__u32 bo_handle_count;
+
+	/* sync object to block on before running the CSD job.  Each
+	 * CSD job will execute in the order submitted to its FD.
+	 * Synchronization against rendering/TFU jobs or CSD from
+	 * other fds requires using sync objects.
+	 */
+	__u32 in_sync;
+	/* Sync object to signal when the CSD job is done. */
+	__u32 out_sync;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h
index d75df5210a4a..dbc7092e04b5 100644
--- a/include/uapi/linux/dma-buf.h
+++ b/include/uapi/linux/dma-buf.h
@@ -35,7 +35,10 @@ struct dma_buf_sync {
 #define DMA_BUF_SYNC_VALID_FLAGS_MASK \
 	(DMA_BUF_SYNC_RW | DMA_BUF_SYNC_END)
 
+#define DMA_BUF_NAME_LEN	32
+
 #define DMA_BUF_BASE		'b'
 #define DMA_BUF_IOCTL_SYNC	_IOW(DMA_BUF_BASE, 0, struct dma_buf_sync)
+#define DMA_BUF_SET_NAME	_IOW(DMA_BUF_BASE, 1, const char *)
 
 #endif
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index dc067ed0b72d..070d1bc7e725 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -35,9 +35,10 @@ struct kfd_ioctl_get_version_args {
 };
 
 /* For kfd_ioctl_create_queue_args.queue_type. */
-#define KFD_IOC_QUEUE_TYPE_COMPUTE	0
-#define KFD_IOC_QUEUE_TYPE_SDMA		1
-#define KFD_IOC_QUEUE_TYPE_COMPUTE_AQL	2
+#define KFD_IOC_QUEUE_TYPE_COMPUTE		0x0
+#define KFD_IOC_QUEUE_TYPE_SDMA			0x1
+#define KFD_IOC_QUEUE_TYPE_COMPUTE_AQL		0x2
+#define KFD_IOC_QUEUE_TYPE_SDMA_XGMI		0x3
 
 #define KFD_MAX_QUEUE_PERCENTAGE	100
 #define KFD_MAX_QUEUE_PRIORITY		15
@@ -338,6 +339,7 @@ struct kfd_ioctl_acquire_vm_args {
 #define KFD_IOC_ALLOC_MEM_FLAGS_GTT		(1 << 1)
 #define KFD_IOC_ALLOC_MEM_FLAGS_USERPTR		(1 << 2)
 #define KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL	(1 << 3)
+#define KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP	(1 << 4)
 /* Allocation flags: attributes/access options */
 #define KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE	(1 << 31)
 #define KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE	(1 << 30)
@@ -408,6 +410,21 @@ struct kfd_ioctl_unmap_memory_from_gpu_args {
 	__u32 n_success;		/* to/from KFD */
 };
 
+/* Allocate GWS for specific queue
+ *
+ * @gpu_id:      device identifier
+ * @queue_id:    queue's id that GWS is allocated for
+ * @num_gws:     how many GWS to allocate
+ * @first_gws:   index of the first GWS allocated.
+ *               only support contiguous GWS allocation
+ */
+struct kfd_ioctl_alloc_queue_gws_args {
+	__u32 gpu_id;		/* to KFD */
+	__u32 queue_id;		/* to KFD */
+	__u32 num_gws;		/* to KFD */
+	__u32 first_gws;	/* from KFD */
+};
+
 struct kfd_ioctl_get_dmabuf_info_args {
 	__u64 size;		/* from KFD */
 	__u64 metadata_ptr;	/* to KFD */
@@ -426,6 +443,13 @@ struct kfd_ioctl_import_dmabuf_args {
 	__u32 dmabuf_fd;	/* to KFD */
 };
 
+/* Register offset inside the remapped mmio page
+ */
+enum kfd_mmio_remap {
+	KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL = 0,
+	KFD_MMIO_REMAP_HDP_REG_FLUSH_CNTL = 4,
+};
+
 #define AMDKFD_IOCTL_BASE 'K'
 #define AMDKFD_IO(nr)			_IO(AMDKFD_IOCTL_BASE, nr)
 #define AMDKFD_IOR(nr, type)		_IOR(AMDKFD_IOCTL_BASE, nr, type)
@@ -520,7 +544,10 @@ struct kfd_ioctl_import_dmabuf_args {
 #define AMDKFD_IOC_IMPORT_DMABUF		\
 		AMDKFD_IOWR(0x1D, struct kfd_ioctl_import_dmabuf_args)
 
+#define AMDKFD_IOC_ALLOC_QUEUE_GWS		\
+		AMDKFD_IOWR(0x1E, struct kfd_ioctl_alloc_queue_gws_args)
+
 #define AMDKFD_COMMAND_START		0x01
-#define AMDKFD_COMMAND_END		0x1E
+#define AMDKFD_COMMAND_END		0x1F
 
 #endif
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index f8c00045d537..665e18627f78 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -91,5 +91,6 @@
 #define UDF_SUPER_MAGIC		0x15013346
 #define BALLOON_KVM_MAGIC	0x13661366
 #define ZSMALLOC_MAGIC		0x58295829
+#define DMA_BUF_MAGIC		0x444d4142	/* "DMAB" */
 
 #endif /* __LINUX_MAGIC_H__ */