Merge tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for v4.15.

  Core:
   - Atomic object lifetime fixes
   - Atomic iterator improvements
   - Sparse/smatch fixes
   - Legacy kms ioctls to be interruptible
   - EDID override improvements
   - fb/gem helper cleanups
   - Simple outreachy patches
   - Documentation improvements
   - Fix dma-buf rcu races
   - DRM mode object leasing for improving VR use cases.
   - vgaarb improvements for non-x86 platforms.

  New driver:
   - tve200: Faraday Technology TVE200 block.

     This "TV Encoder" encodes a ITU-T BT.656 stream and can be found in
     the StorLink SL3516 (later Cortina Systems CS3516) as well as the
     Grain Media GM8180.

  New bridges:
   - SiI9234 support

  New panels:
   - S6E63J0X03, OTM8009A, Seiko 43WVF1G, 7" rpi touch panel, Toshiba
     LT089AC19000, Innolux AT043TN24

  i915:
   - Remove Coffeelake from alpha support
   - Cannonlake workarounds
   - Infoframe refactoring for DisplayPort
   - VBT updates
   - DisplayPort vswing/emph/buffer translation refactoring
   - CCS fixes
   - Restore GPU clock boost on missed vblanks
   - Scatter list updates for userptr allocations
   - Gen9+ transition watermarks
   - Display IPC (Isochronous Priority Control)
   - Private PAT management
   - GVT: improved error handling and pci config sanitizing
   - Execlist refactoring
   - Transparent Huge Page support
   - User defined priorities support
   - HuC/GuC firmware refactoring
   - DP MST fixes
   - eDP power sequencing fixes
   - Use RCU instead of stop_machine
   - PSR state tracking support
   - Eviction fixes
   - BDW DP aux channel timeout fixes
   - LSPCON fixes
   - Cannonlake PLL fixes

  amdgpu:
   - Per VM BO support
   - Powerplay cleanups
   - CI powerplay support
   - PASID mgr for kfd
   - SR-IOV fixes
   - initial GPU reset for vega10
   - Prime mmap support
   - TTM updates
   - Clock query interface for Raven
   - Fence to handle ioctl
   - UVD encode ring support on Polaris
   - Transparent huge page DMA support
   - Compute LRU pipe tweaks
   - BO flag to allow buffers to opt out of implicit sync
   - CTX priority setting API
   - VRAM lost infrastructure plumbing

  qxl:
   - fix flicker since atomic rework

  amdkfd:
   - Further improvements from internal AMD tree
   - Usermode events
   - Drop radeon support

  nouveau:
   - Pascal temperature sensor support
   - Improved BAR2 handling
   - MMU rework to support Pascal MMU

  exynos:
   - Improved HDMI/mixer support
   - HDMI audio interface support

  tegra:
   - Prep work for tegra186
   - Cleanup/fixes

  msm:
   - Preemption support for a5xx
   - Display fixes for 8x96 (snapdragon 820)
   - Async cursor plane fixes
   - FW loading rework
   - GPU debugging improvements

  vc4:
   - Prep for DSI panels
   - fix T-format tiling scanout
   - New madvise ioctl

  Rockchip:
   - LVDS support

  omapdrm:
   - omap4 HDMI CEC support

  etnaviv:
   - GPU performance counters groundwork

  sun4i:
   - refactor driver load + TCON backend
   - HDMI improvements
   - A31 support
   - Misc fixes

  udl:
   - Probe/EDID read fixes.

  tilcdc:
   - Misc fixes.

  pl111:
   - Support more variants

  adv7511:
   - Improve EDID handling.
   - HDMI CEC support

  sii8620:
   - Add remote control support"

* tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux: (1480 commits)
  drm/rockchip: analogix_dp: Use mutex rather than spinlock
  drm/mode_object: fix documentation for object lookups.
  drm/i915: Reorder context-close to avoid calling i915_vma_close() under RCU
  drm/i915: Move init_clock_gating() back to where it was
  drm/i915: Prune the reservation shared fence array
  drm/i915: Idle the GPU before shinking everything
  drm/i915: Lock llist_del_first() vs llist_del_all()
  drm/i915: Calculate ironlake intermediate watermarks correctly, v2.
  drm/i915: Disable lazy PPGTT page table optimization for vGPU
  drm/i915/execlists: Remove the priority "optimisation"
  drm/i915: Filter out spurious execlists context-switch interrupts
  drm/amdgpu: use irq-safe lock for kiq->ring_lock
  drm/amdgpu: bypass lru touch for KIQ ring submission
  drm/amdgpu: Potential uninitialized variable in amdgpu_vm_update_directories()
  drm/amdgpu: potential uninitialized variable in amdgpu_vce_ring_parse_cs()
  drm/amd/powerplay: initialize a variable before using it
  drm/amd/powerplay: suppress KASAN out of bounds warning in vega10_populate_all_memory_levels
  drm/amd/amdgpu: fix evicted VRAM bo adjudgement condition
  drm/vblank: Tune drm_crtc_accurate_vblank_count() WARN down to a debug
  drm/rockchip: add CONFIG_OF dependency for lvds
  ...

8 files changed, 271 insertions, 11 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 7b8fa11c2285..919248fb4028 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -52,6 +52,8 @@ extern "C" {
 #define DRM_AMDGPU_GEM_USERPTR		0x11
 #define DRM_AMDGPU_WAIT_FENCES		0x12
 #define DRM_AMDGPU_VM			0x13
+#define DRM_AMDGPU_FENCE_TO_HANDLE	0x14
+#define DRM_AMDGPU_SCHED		0x15
 
 #define DRM_IOCTL_AMDGPU_GEM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_CREATE, union drm_amdgpu_gem_create)
 #define DRM_IOCTL_AMDGPU_GEM_MMAP	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_MMAP, union drm_amdgpu_gem_mmap)
@@ -67,6 +69,8 @@ extern "C" {
 #define DRM_IOCTL_AMDGPU_GEM_USERPTR	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_USERPTR, struct drm_amdgpu_gem_userptr)
 #define DRM_IOCTL_AMDGPU_WAIT_FENCES	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_WAIT_FENCES, union drm_amdgpu_wait_fences)
 #define DRM_IOCTL_AMDGPU_VM		DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_VM, union drm_amdgpu_vm)
+#define DRM_IOCTL_AMDGPU_FENCE_TO_HANDLE DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_FENCE_TO_HANDLE, union drm_amdgpu_fence_to_handle)
+#define DRM_IOCTL_AMDGPU_SCHED		DRM_IOW(DRM_COMMAND_BASE + DRM_AMDGPU_SCHED, union drm_amdgpu_sched)
 
 #define AMDGPU_GEM_DOMAIN_CPU		0x1
 #define AMDGPU_GEM_DOMAIN_GTT		0x2
@@ -87,6 +91,10 @@ extern "C" {
 #define AMDGPU_GEM_CREATE_SHADOW		(1 << 4)
 /* Flag that allocating the BO should use linear VRAM */
 #define AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS	(1 << 5)
+/* Flag that BO is always valid in this VM */
+#define AMDGPU_GEM_CREATE_VM_ALWAYS_VALID	(1 << 6)
+/* Flag that BO sharing will be explicitly synchronized */
+#define AMDGPU_GEM_CREATE_EXPLICIT_SYNC		(1 << 7)
 
 struct drm_amdgpu_gem_create_in  {
 	/** the requested memory size */
@@ -162,13 +170,22 @@ union drm_amdgpu_bo_list {
 /* unknown cause */
 #define AMDGPU_CTX_UNKNOWN_RESET	3
 
+/* Context priority level */
+#define AMDGPU_CTX_PRIORITY_UNSET       -2048
+#define AMDGPU_CTX_PRIORITY_VERY_LOW    -1023
+#define AMDGPU_CTX_PRIORITY_LOW         -512
+#define AMDGPU_CTX_PRIORITY_NORMAL      0
+/* Selecting a priority above NORMAL requires CAP_SYS_NICE or DRM_MASTER */
+#define AMDGPU_CTX_PRIORITY_HIGH        512
+#define AMDGPU_CTX_PRIORITY_VERY_HIGH   1023
+
 struct drm_amdgpu_ctx_in {
 	/** AMDGPU_CTX_OP_* */
 	__u32	op;
 	/** For future use, no flags defined so far */
 	__u32	flags;
 	__u32	ctx_id;
-	__u32	_pad;
+	__s32	priority;
 };
 
 union drm_amdgpu_ctx_out {
@@ -212,6 +229,21 @@ union drm_amdgpu_vm {
 	struct drm_amdgpu_vm_out out;
 };
 
+/* sched ioctl */
+#define AMDGPU_SCHED_OP_PROCESS_PRIORITY_OVERRIDE	1
+
+struct drm_amdgpu_sched_in {
+	/* AMDGPU_SCHED_OP_* */
+	__u32	op;
+	__u32	fd;
+	__s32	priority;
+	__u32	flags;
+};
+
+union drm_amdgpu_sched {
+	struct drm_amdgpu_sched_in in;
+};
+
 /*
  * This is not a reliable API and you should expect it to fail for any
  * number of reasons and have fallback path that do not use userptr to
@@ -513,6 +545,21 @@ struct drm_amdgpu_cs_chunk_sem {
 	__u32 handle;
 };
 
+#define AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ	0
+#define AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ_FD	1
+#define AMDGPU_FENCE_TO_HANDLE_GET_SYNC_FILE_FD	2
+
+union drm_amdgpu_fence_to_handle {
+	struct {
+		struct drm_amdgpu_fence fence;
+		__u32 what;
+		__u32 pad;
+	} in;
+	struct {
+		__u32 handle;
+	} out;
+};
+
 struct drm_amdgpu_cs_chunk_data {
 	union {
 		struct drm_amdgpu_cs_chunk_ib		ib_data;
@@ -611,6 +658,7 @@ struct drm_amdgpu_cs_chunk_data {
 	#define AMDGPU_INFO_SENSOR_VDDGFX		0x7
 /* Number of VRAM page faults on CPU access. */
 #define AMDGPU_INFO_NUM_VRAM_CPU_PAGE_FAULTS	0x1E
+#define AMDGPU_INFO_VRAM_LOST_COUNTER		0x1F
 
 #define AMDGPU_INFO_MMR_SE_INDEX_SHIFT	0
 #define AMDGPU_INFO_MMR_SE_INDEX_MASK	0xff
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 97677cd6964d..6fdff5945c8a 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -737,6 +737,28 @@ struct drm_syncobj_array {
 	__u32 pad;
 };
 
+/* Query current scanout sequence number */
+struct drm_crtc_get_sequence {
+	__u32 crtc_id;		/* requested crtc_id */
+	__u32 active;		/* return: crtc output is active */
+	__u64 sequence;		/* return: most recent vblank sequence */
+	__s64 sequence_ns;	/* return: most recent time of first pixel out */
+};
+
+/* Queue event to be delivered at specified sequence. Time stamp marks
+ * when the first pixel of the refresh cycle leaves the display engine
+ * for the display
+ */
+#define DRM_CRTC_SEQUENCE_RELATIVE		0x00000001	/* sequence is relative to current */
+#define DRM_CRTC_SEQUENCE_NEXT_ON_MISS		0x00000002	/* Use next sequence if we've missed */
+
+struct drm_crtc_queue_sequence {
+	__u32 crtc_id;
+	__u32 flags;
+	__u64 sequence;		/* on input, target sequence. on output, actual sequence */
+	__u64 user_data;	/* user data passed to event */
+};
+
 #if defined(__cplusplus)
 }
 #endif
@@ -819,6 +841,9 @@ extern "C" {
 
 #define DRM_IOCTL_WAIT_VBLANK		DRM_IOWR(0x3a, union drm_wait_vblank)
 
+#define DRM_IOCTL_CRTC_GET_SEQUENCE	DRM_IOWR(0x3b, struct drm_crtc_get_sequence)
+#define DRM_IOCTL_CRTC_QUEUE_SEQUENCE	DRM_IOWR(0x3c, struct drm_crtc_queue_sequence)
+
 #define DRM_IOCTL_UPDATE_DRAW		DRM_IOW(0x3f, struct drm_update_draw)
 
 #define DRM_IOCTL_MODE_GETRESOURCES	DRM_IOWR(0xA0, struct drm_mode_card_res)
@@ -863,6 +888,11 @@ extern "C" {
 #define DRM_IOCTL_SYNCOBJ_RESET		DRM_IOWR(0xC4, struct drm_syncobj_array)
 #define DRM_IOCTL_SYNCOBJ_SIGNAL	DRM_IOWR(0xC5, struct drm_syncobj_array)
 
+#define DRM_IOCTL_MODE_CREATE_LEASE	DRM_IOWR(0xC6, struct drm_mode_create_lease)
+#define DRM_IOCTL_MODE_LIST_LESSEES	DRM_IOWR(0xC7, struct drm_mode_list_lessees)
+#define DRM_IOCTL_MODE_GET_LEASE	DRM_IOWR(0xC8, struct drm_mode_get_lease)
+#define DRM_IOCTL_MODE_REVOKE_LEASE	DRM_IOWR(0xC9, struct drm_mode_revoke_lease)
+
 /**
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
@@ -893,6 +923,7 @@ struct drm_event {
 
 #define DRM_EVENT_VBLANK 0x01
 #define DRM_EVENT_FLIP_COMPLETE 0x02
+#define DRM_EVENT_CRTC_SEQUENCE	0x03
 
 struct drm_event_vblank {
 	struct drm_event base;
@@ -903,6 +934,16 @@ struct drm_event_vblank {
 	__u32 crtc_id; /* 0 on older kernels that do not support this */
 };
 
+/* Event delivered at sequence. Time stamp marks when the first pixel
+ * of the refresh cycle leaves the display engine for the display
+ */
+struct drm_event_crtc_sequence {
+	struct drm_event	base;
+	__u64			user_data;
+	__s64			time_ns;
+	__u64			sequence;
+};
+
 /* typedef area */
 #ifndef __KERNEL__
 typedef struct drm_clip_rect drm_clip_rect_t;
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 54fc38c3c3f1..5597a87154e5 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -749,9 +749,9 @@ struct drm_format_modifier {
 	 * If the number formats grew to 128, and formats 98-102 are
 	 * supported with the modifier:
 	 *
-	 * 0x0000003c00000000 0000000000000000
+	 * 0x0000007c00000000 0000000000000000
 	 *		  ^
-	 *		  |__offset = 64, formats = 0x3c00000000
+	 *		  |__offset = 64, formats = 0x7c00000000
 	 *
 	 */
 	__u64 formats;
@@ -782,6 +782,72 @@ struct drm_mode_destroy_blob {
 	__u32 blob_id;
 };
 
+/**
+ * Lease mode resources, creating another drm_master.
+ */
+struct drm_mode_create_lease {
+	/** Pointer to array of object ids (__u32) */
+	__u64 object_ids;
+	/** Number of object ids */
+	__u32 object_count;
+	/** flags for new FD (O_CLOEXEC, etc) */
+	__u32 flags;
+
+	/** Return: unique identifier for lessee. */
+	__u32 lessee_id;
+	/** Return: file descriptor to new drm_master file */
+	__u32 fd;
+};
+
+/**
+ * List lesses from a drm_master
+ */
+struct drm_mode_list_lessees {
+	/** Number of lessees.
+	 * On input, provides length of the array.
+	 * On output, provides total number. No
+	 * more than the input number will be written
+	 * back, so two calls can be used to get
+	 * the size and then the data.
+	 */
+	__u32 count_lessees;
+	__u32 pad;
+
+	/** Pointer to lessees.
+	 * pointer to __u64 array of lessee ids
+	 */
+	__u64 lessees_ptr;
+};
+
+/**
+ * Get leased objects
+ */
+struct drm_mode_get_lease {
+	/** Number of leased objects.
+	 * On input, provides length of the array.
+	 * On output, provides total number. No
+	 * more than the input number will be written
+	 * back, so two calls can be used to get
+	 * the size and then the data.
+	 */
+	__u32 count_objects;
+	__u32 pad;
+
+	/** Pointer to objects.
+	 * pointer to __u32 array of object ids
+	 */
+	__u64 objects_ptr;
+};
+
+/**
+ * Revoke lease
+ */
+struct drm_mode_revoke_lease {
+	/** Unique ID of lessee
+	 */
+	__u32 lessee_id;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/etnaviv_drm.h b/include/uapi/drm/etnaviv_drm.h
index d4463f3fa427..e9b997a0ef27 100644
--- a/include/uapi/drm/etnaviv_drm.h
+++ b/include/uapi/drm/etnaviv_drm.h
@@ -151,6 +151,19 @@ struct drm_etnaviv_gem_submit_bo {
 	__u64 presumed;       /* in/out, presumed buffer address */
 };
 
+/* performance monitor request (pmr) */
+#define ETNA_PM_PROCESS_PRE             0x0001
+#define ETNA_PM_PROCESS_POST            0x0002
+struct drm_etnaviv_gem_submit_pmr {
+	__u32 flags;          /* in, when to process request (ETNA_PM_PROCESS_x) */
+	__u8  domain;         /* in, pm domain */
+	__u8  pad;
+	__u16 signal;         /* in, pm signal */
+	__u32 sequence;       /* in, sequence number */
+	__u32 read_offset;    /* in, offset from read_bo */
+	__u32 read_idx;       /* in, index of read_bo buffer */
+};
+
 /* Each cmdstream submit consists of a table of buffers involved, and
  * one or more cmdstream buffers.  This allows for conditional execution
  * (context-restore), and IB buffers needed for per tile/bin draw cmds.
@@ -176,6 +189,9 @@ struct drm_etnaviv_gem_submit {
 	__u64 stream;         /* in, ptr to cmdstream */
 	__u32 flags;          /* in, mask of ETNA_SUBMIT_x */
 	__s32 fence_fd;       /* in/out, fence fd (see ETNA_SUBMIT_FENCE_FD_x) */
+	__u64 pmrs;           /* in, ptr to array of submit_pmr's */
+	__u32 nr_pmrs;        /* in, number of submit_pmr's */
+	__u32 pad;
 };
 
 /* The normal way to synchronize with the GPU is just to CPU_PREP on
@@ -211,6 +227,27 @@ struct drm_etnaviv_gem_wait {
 	struct drm_etnaviv_timespec timeout;	/* in */
 };
 
+/*
+ * Performance Monitor (PM):
+ */
+
+struct drm_etnaviv_pm_domain {
+	__u32 pipe;       /* in */
+	__u8  iter;       /* in/out, select pm domain at index iter */
+	__u8  id;         /* out, id of domain */
+	__u16 nr_signals; /* out, how many signals does this domain provide */
+	char  name[64];   /* out, name of domain */
+};
+
+struct drm_etnaviv_pm_signal {
+	__u32 pipe;       /* in */
+	__u8  domain;     /* in, pm domain index */
+	__u8  pad;
+	__u16 iter;       /* in/out, select pm source at index iter */
+	__u16 id;         /* out, id of signal */
+	char  name[64];   /* out, name of domain */
+};
+
 #define DRM_ETNAVIV_GET_PARAM          0x00
 /* placeholder:
 #define DRM_ETNAVIV_SET_PARAM          0x01
@@ -223,7 +260,9 @@ struct drm_etnaviv_gem_wait {
 #define DRM_ETNAVIV_WAIT_FENCE         0x07
 #define DRM_ETNAVIV_GEM_USERPTR        0x08
 #define DRM_ETNAVIV_GEM_WAIT           0x09
-#define DRM_ETNAVIV_NUM_IOCTLS         0x0a
+#define DRM_ETNAVIV_PM_QUERY_DOM       0x0a
+#define DRM_ETNAVIV_PM_QUERY_SIG       0x0b
+#define DRM_ETNAVIV_NUM_IOCTLS         0x0c
 
 #define DRM_IOCTL_ETNAVIV_GET_PARAM    DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_GET_PARAM, struct drm_etnaviv_param)
 #define DRM_IOCTL_ETNAVIV_GEM_NEW      DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_GEM_NEW, struct drm_etnaviv_gem_new)
@@ -234,6 +273,8 @@ struct drm_etnaviv_gem_wait {
 #define DRM_IOCTL_ETNAVIV_WAIT_FENCE   DRM_IOW(DRM_COMMAND_BASE + DRM_ETNAVIV_WAIT_FENCE, struct drm_etnaviv_wait_fence)
 #define DRM_IOCTL_ETNAVIV_GEM_USERPTR  DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_GEM_USERPTR, struct drm_etnaviv_gem_userptr)
 #define DRM_IOCTL_ETNAVIV_GEM_WAIT     DRM_IOW(DRM_COMMAND_BASE + DRM_ETNAVIV_GEM_WAIT, struct drm_etnaviv_gem_wait)
+#define DRM_IOCTL_ETNAVIV_PM_QUERY_DOM DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_PM_QUERY_DOM, struct drm_etnaviv_pm_domain)
+#define DRM_IOCTL_ETNAVIV_PM_QUERY_SIG DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_PM_QUERY_SIG, struct drm_etnaviv_pm_signal)
 
 #if defined(__cplusplus)
 }
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 9816590d3ad2..ac3c6503ca27 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -397,10 +397,20 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_MIN_EU_IN_POOL	 39
 #define I915_PARAM_MMAP_GTT_VERSION	 40
 
-/* Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
  * priorities and the driver will attempt to execute batches in priority order.
+ * The param returns a capability bitmask, nonzero implies that the scheduler
+ * is enabled, with different features present according to the mask.
+ *
+ * The initial priority for each batch is supplied by the context and is
+ * controlled via I915_CONTEXT_PARAM_PRIORITY.
  */
 #define I915_PARAM_HAS_SCHEDULER	 41
+#define   I915_SCHEDULER_CAP_ENABLED	(1ul << 0)
+#define   I915_SCHEDULER_CAP_PRIORITY	(1ul << 1)
+#define   I915_SCHEDULER_CAP_PREEMPTION	(1ul << 2)
+
 #define I915_PARAM_HUC_STATUS		 42
 
 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of
@@ -1309,14 +1319,16 @@ struct drm_i915_reg_read {
 	 * be specified
 	 */
 	__u64 offset;
+#define I915_REG_READ_8B_WA (1ul << 0)
+
 	__u64 val; /* Return value */
 };
 /* Known registers:
  *
  * Render engine timestamp - 0x2358 + 64bit - gen7+
  * - Note this register returns an invalid value if using the default
- *   single instruction 8byte read, in order to workaround that use
- *   offset (0x2538 | 1) instead.
+ *   single instruction 8byte read, in order to workaround that pass
+ *   flag I915_REG_READ_8B_WA in offset field.
  *
  */
 
@@ -1359,6 +1371,10 @@ struct drm_i915_gem_context_param {
 #define I915_CONTEXT_PARAM_GTT_SIZE	0x3
 #define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE	0x4
 #define I915_CONTEXT_PARAM_BANNABLE	0x5
+#define I915_CONTEXT_PARAM_PRIORITY	0x6
+#define   I915_CONTEXT_MAX_USER_PRIORITY	1023 /* inclusive */
+#define   I915_CONTEXT_DEFAULT_PRIORITY		0
+#define   I915_CONTEXT_MIN_USER_PRIORITY	-1023 /* inclusive */
 	__u64 value;
 };
 
@@ -1510,9 +1526,14 @@ struct drm_i915_perf_oa_config {
 	__u32 n_boolean_regs;
 	__u32 n_flex_regs;
 
-	__u64 __user mux_regs_ptr;
-	__u64 __user boolean_regs_ptr;
-	__u64 __user flex_regs_ptr;
+	/*
+	 * These fields are pointers to tuples of u32 values (register
+	 * address, value). For example the expected length of the buffer
+	 * pointed by mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
+	 */
+	__u64 mux_regs_ptr;
+	__u64 boolean_regs_ptr;
+	__u64 flex_regs_ptr;
 };
 
 #if defined(__cplusplus)
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index ad4eb2863e70..bbbaffad772d 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -73,6 +73,7 @@ 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
 
 struct drm_msm_param {
 	__u32 pipe;           /* in, MSM_PIPE_x */
@@ -218,6 +219,7 @@ struct drm_msm_gem_submit {
 	__u64 bos;            /* in, ptr to array of submit_bo's */
 	__u64 cmds;           /* in, ptr to array of submit_cmd's */
 	__s32 fence_fd;       /* in/out fence fd (see MSM_SUBMIT_FENCE_FD_IN/OUT) */
+	__u32 queueid;         /* in, submitqueue id */
 };
 
 /* The normal way to synchronize with the GPU is just to CPU_PREP on
@@ -231,6 +233,7 @@ struct drm_msm_wait_fence {
 	__u32 fence;          /* in */
 	__u32 pad;
 	struct drm_msm_timespec timeout;   /* in */
+	__u32 queueid;         /* in, submitqueue id */
 };
 
 /* madvise provides a way to tell the kernel in case a buffers contents
@@ -254,6 +257,20 @@ struct drm_msm_gem_madvise {
 	__u32 retained;       /* out, whether backing store still exists */
 };
 
+/*
+ * Draw queues allow the user to set specific submission parameter. Command
+ * submissions specify a specific submitqueue to use.  ID 0 is reserved for
+ * backwards compatibility as a "default" submitqueue
+ */
+
+#define MSM_SUBMITQUEUE_FLAGS (0)
+
+struct drm_msm_submitqueue {
+	__u32 flags;   /* in, MSM_SUBMITQUEUE_x */
+	__u32 prio;    /* in, Priority level */
+	__u32 id;      /* out, identifier */
+};
+
 #define DRM_MSM_GET_PARAM              0x00
 /* placeholder:
 #define DRM_MSM_SET_PARAM              0x01
@@ -265,6 +282,11 @@ struct drm_msm_gem_madvise {
 #define DRM_MSM_GEM_SUBMIT             0x06
 #define DRM_MSM_WAIT_FENCE             0x07
 #define DRM_MSM_GEM_MADVISE            0x08
+/* placeholder:
+#define DRM_MSM_GEM_SVM_NEW            0x09
+ */
+#define DRM_MSM_SUBMITQUEUE_NEW        0x0A
+#define DRM_MSM_SUBMITQUEUE_CLOSE      0x0B
 
 #define DRM_IOCTL_MSM_GET_PARAM        DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GET_PARAM, struct drm_msm_param)
 #define DRM_IOCTL_MSM_GEM_NEW          DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_NEW, struct drm_msm_gem_new)
@@ -274,6 +296,8 @@ struct drm_msm_gem_madvise {
 #define DRM_IOCTL_MSM_GEM_SUBMIT       DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_SUBMIT, struct drm_msm_gem_submit)
 #define DRM_IOCTL_MSM_WAIT_FENCE       DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_WAIT_FENCE, struct drm_msm_wait_fence)
 #define DRM_IOCTL_MSM_GEM_MADVISE      DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_MADVISE, struct drm_msm_gem_madvise)
+#define DRM_IOCTL_MSM_SUBMITQUEUE_NEW    DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_NEW, struct drm_msm_submitqueue)
+#define DRM_IOCTL_MSM_SUBMITQUEUE_CLOSE  DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_CLOSE, __u32)
 
 #if defined(__cplusplus)
 }
diff --git a/include/uapi/drm/vc4_drm.h b/include/uapi/drm/vc4_drm.h
index afae87004963..52263b575bdc 100644
--- a/include/uapi/drm/vc4_drm.h
+++ b/include/uapi/drm/vc4_drm.h
@@ -41,6 +41,7 @@ extern "C" {
 #define DRM_VC4_SET_TILING                        0x08
 #define DRM_VC4_GET_TILING                        0x09
 #define DRM_VC4_LABEL_BO                          0x0a
+#define DRM_VC4_GEM_MADVISE                       0x0b
 
 #define DRM_IOCTL_VC4_SUBMIT_CL           DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_SUBMIT_CL, struct drm_vc4_submit_cl)
 #define DRM_IOCTL_VC4_WAIT_SEQNO          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_WAIT_SEQNO, struct drm_vc4_wait_seqno)
@@ -53,6 +54,7 @@ extern "C" {
 #define DRM_IOCTL_VC4_SET_TILING          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_SET_TILING, struct drm_vc4_set_tiling)
 #define DRM_IOCTL_VC4_GET_TILING          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GET_TILING, struct drm_vc4_get_tiling)
 #define DRM_IOCTL_VC4_LABEL_BO            DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_LABEL_BO, struct drm_vc4_label_bo)
+#define DRM_IOCTL_VC4_GEM_MADVISE         DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GEM_MADVISE, struct drm_vc4_gem_madvise)
 
 struct drm_vc4_submit_rcl_surface {
 	__u32 hindex; /* Handle index, or ~0 if not present. */
@@ -305,6 +307,7 @@ struct drm_vc4_get_hang_state {
 #define DRM_VC4_PARAM_SUPPORTS_ETC1		4
 #define DRM_VC4_PARAM_SUPPORTS_THREADED_FS	5
 #define DRM_VC4_PARAM_SUPPORTS_FIXED_RCL_ORDER	6
+#define DRM_VC4_PARAM_SUPPORTS_MADVISE		7
 
 struct drm_vc4_get_param {
 	__u32 param;
@@ -333,6 +336,22 @@ struct drm_vc4_label_bo {
 	__u64 name;
 };
 
+/*
+ * States prefixed with '__' are internal states and cannot be passed to the
+ * DRM_IOCTL_VC4_GEM_MADVISE ioctl.
+ */
+#define VC4_MADV_WILLNEED			0
+#define VC4_MADV_DONTNEED			1
+#define __VC4_MADV_PURGED			2
+#define __VC4_MADV_NOTSUPP			3
+
+struct drm_vc4_gem_madvise {
+	__u32 handle;
+	__u32 madv;
+	__u32 retained;
+	__u32 pad;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 26283fefdf5f..731d0df722e3 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -169,7 +169,7 @@ struct kfd_ioctl_dbg_wave_control_args {
 #define KFD_IOC_WAIT_RESULT_TIMEOUT		1
 #define KFD_IOC_WAIT_RESULT_FAIL		2
 
-#define KFD_SIGNAL_EVENT_LIMIT			256
+#define KFD_SIGNAL_EVENT_LIMIT			4096
 
 struct kfd_ioctl_create_event_args {
 	__u64 event_page_offset;	/* from KFD */