Merge tag 'drm-for-v4.14' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for 4.14 merge window.

  I'm sending this early, as my continuing journey into fatherhood is
  occurring really soon now, I'm going to be mostly useless for the next
  couple of weeks, though I may be able to read email, I doubt I'll be
  doing much patch applications or git sending. If anything urgent pops
  up I've asked Daniel/Jani/Alex/Sean to try and direct stuff towards
  you.

  Outside drm changes:

  Some rcar-du updates that touch the V4L tree, all acks should be in
  place. It adds one export to the radix tree code for new i915 use
  case. There are some minor AGP cleanups (don't see that too often).
  Changes to the vbox driver in staging to avoid breaking compilation.

  Summary:

  core:
   - Atomic helper fixes
   - Atomic UAPI fixes
   - Add YCBCR 4:2:0 support
   - Drop set_busid hook
   - Refactor fb_helper locking
   - Remove a bunch of internal APIs
   - Add a bunch of better default handlers
   - Format modifier/blob plane property added
   - More internal header refactoring
   - Make more internal API names consistent
   - Enhanced syncobj APIs (wait/signal/reset/create signalled)

  bridge:
   - Add Synopsys Designware MIPI DSI host bridge driver

  tiny:
   - Add Pervasive Displays RePaper displays
   - Add support for LEGO MINDSTORMS EV3 LCD

  i915:
   - Lots of GEN10/CNL  support patches
   - drm syncobj support
   - Skylake+ watermark refactoring
   - GVT vGPU 48-bit ppgtt support
   - GVT performance improvements
   - NOA change ioctl
   - CCS (color compression) scanout support
   - GPU reset improvements

  amdgpu:
   - Initial hugepage support
   - BO migration logic rework
   - Vega10 improvements
   - Powerplay fixes
   - Stop reprogramming the MC
   - Fixes for ACP audio on stoney
   - SR-IOV fixes/improvements
   - Command submission overhead improvements

  amdkfd:
   - Non-dGPU upstreaming patches
   - Scratch VA ioctl
   - Image tiling modes
   - Update PM4 headers for new firmware
   - Drop all BUG_ONs.

  nouveau:
   - GP108 modesetting support.
   - Disable MSI on big endian.

  vmwgfx:
   - Add fence fd support.

  msm:
   - Runtime PM improvements

  exynos:
   - NV12MT support
   - Refactor KMS drivers

  imx-drm:
   - Lock scanout channel to improve memory bw
   - Cleanups

  etnaviv:
   - GEM object population fixes

  tegra:
   - Prep work for Tegra186 support
   - PRIME mmap support

  sunxi:
   - HDMI support improvements
   - HDMI CEC support

  omapdrm:
   - HDMI hotplug IRQ support
   - Big driver cleanup
   - OMAP5 DSI support

  rcar-du:
   - vblank fixes
   - VSP1 updates

  arcgpu:
   - Minor fixes

  stm:
   - Add STM32 DSI controller driver

  dw_hdmi:
   - Add support for Rockchip RK3399
   - HDMI CEC support

  atmel-hlcdc:
   - Add 8-bit color support

  vc4:
   - Atomic fixes
   - New ioctl to attach a label to a buffer object
   - HDMI CEC support
   - Allow userspace to dictate rendering order on submit ioctl"

* tag 'drm-for-v4.14' of git://people.freedesktop.org/~airlied/linux: (1074 commits)
  drm/syncobj: Add a signal ioctl (v3)
  drm/syncobj: Add a reset ioctl (v3)
  drm/syncobj: Add a syncobj_array_find helper
  drm/syncobj: Allow wait for submit and signal behavior (v5)
  drm/syncobj: Add a CREATE_SIGNALED flag
  drm/syncobj: Add a callback mechanism for replace_fence (v3)
  drm/syncobj: add sync obj wait interface. (v8)
  i915: Use drm_syncobj_fence_get
  drm/syncobj: Add a race-free drm_syncobj_fence_get helper (v2)
  drm/syncobj: Rename fence_get to find_fence
  drm: kirin: Add mode_valid logic to avoid mode clocks we can't generate
  drm/vmwgfx: Bump the version for fence FD support
  drm/vmwgfx: Add export fence to file descriptor support
  drm/vmwgfx: Add support for imported Fence File Descriptor
  drm/vmwgfx: Prepare to support fence fd
  drm/vmwgfx: Fix incorrect command header offset at restart
  drm/vmwgfx: Support the NOP_ERROR command
  drm/vmwgfx: Restart command buffers after errors
  drm/vmwgfx: Move irq bottom half processing to threads
  drm/vmwgfx: Don't use drm_irq_[un]install
  ...

9 files changed, 232 insertions, 20 deletions

diff --git a/include/uapi/drm/armada_drm.h b/include/uapi/drm/armada_drm.h
index 72e326f..0cb9324 100644
--- a/include/uapi/drm/armada_drm.h
+++ b/include/uapi/drm/armada_drm.h
@@ -23,27 +23,27 @@ extern "C" {
 	DRM_##dir(DRM_COMMAND_BASE + DRM_ARMADA_##name, struct drm_armada_##str)
 
 struct drm_armada_gem_create {
-	uint32_t handle;
-	uint32_t size;
+	__u32 handle;
+	__u32 size;
 };
 #define DRM_IOCTL_ARMADA_GEM_CREATE \
 	ARMADA_IOCTL(IOWR, GEM_CREATE, gem_create)
 
 struct drm_armada_gem_mmap {
-	uint32_t handle;
-	uint32_t pad;
-	uint64_t offset;
-	uint64_t size;
-	uint64_t addr;
+	__u32 handle;
+	__u32 pad;
+	__u64 offset;
+	__u64 size;
+	__u64 addr;
 };
 #define DRM_IOCTL_ARMADA_GEM_MMAP \
 	ARMADA_IOCTL(IOWR, GEM_MMAP, gem_mmap)
 
 struct drm_armada_gem_pwrite {
-	uint64_t ptr;
-	uint32_t handle;
-	uint32_t offset;
-	uint32_t size;
+	__u64 ptr;
+	__u32 handle;
+	__u32 offset;
+	__u32 size;
 };
 #define DRM_IOCTL_ARMADA_GEM_PWRITE \
 	ARMADA_IOCTL(IOW, GEM_PWRITE, gem_pwrite)
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 101593a..97677cd 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -700,6 +700,7 @@ struct drm_prime_handle {
 
 struct drm_syncobj_create {
 	__u32 handle;
+#define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0)
 	__u32 flags;
 };
 
@@ -718,6 +719,24 @@ struct drm_syncobj_handle {
 	__u32 pad;
 };
 
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
+struct drm_syncobj_wait {
+	__u64 handles;
+	/* absolute timeout */
+	__s64 timeout_nsec;
+	__u32 count_handles;
+	__u32 flags;
+	__u32 first_signaled; /* only valid when not waiting all */
+	__u32 pad;
+};
+
+struct drm_syncobj_array {
+	__u64 handles;
+	__u32 count_handles;
+	__u32 pad;
+};
+
 #if defined(__cplusplus)
 }
 #endif
@@ -840,6 +859,9 @@ extern "C" {
 #define DRM_IOCTL_SYNCOBJ_DESTROY	DRM_IOWR(0xC0, struct drm_syncobj_destroy)
 #define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD	DRM_IOWR(0xC1, struct drm_syncobj_handle)
 #define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE	DRM_IOWR(0xC2, struct drm_syncobj_handle)
+#define DRM_IOCTL_SYNCOBJ_WAIT		DRM_IOWR(0xC3, struct drm_syncobj_wait)
+#define DRM_IOCTL_SYNCOBJ_RESET		DRM_IOWR(0xC4, struct drm_syncobj_array)
+#define DRM_IOCTL_SYNCOBJ_SIGNAL	DRM_IOWR(0xC5, struct drm_syncobj_array)
 
 /**
  * Device specific ioctls should only be in their respective headers
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 7586c46..3ad838d 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -185,6 +185,8 @@ extern "C" {
 #define DRM_FORMAT_MOD_VENDOR_BROADCOM 0x07
 /* add more to the end as needed */
 
+#define DRM_FORMAT_RESERVED	      ((1ULL << 56) - 1)
+
 #define fourcc_mod_code(vendor, val) \
 	((((__u64)DRM_FORMAT_MOD_VENDOR_## vendor) << 56) | (val & 0x00ffffffffffffffULL))
 
@@ -197,6 +199,15 @@ extern "C" {
  */
 
 /*
+ * Invalid Modifier
+ *
+ * This modifier can be used as a sentinel to terminate the format modifiers
+ * list, or to initialize a variable with an invalid modifier. It might also be
+ * used to report an error back to userspace for certain APIs.
+ */
+#define DRM_FORMAT_MOD_INVALID	fourcc_mod_code(NONE, DRM_FORMAT_RESERVED)
+
+/*
  * Linear Layout
  *
  * Just plain linear layout. Note that this is different from no specifying any
@@ -253,6 +264,26 @@ extern "C" {
 #define I915_FORMAT_MOD_Yf_TILED fourcc_mod_code(INTEL, 3)
 
 /*
+ * Intel color control surface (CCS) for render compression
+ *
+ * The framebuffer format must be one of the 8:8:8:8 RGB formats.
+ * The main surface will be plane index 0 and must be Y/Yf-tiled,
+ * the CCS will be plane index 1.
+ *
+ * Each CCS tile matches a 1024x512 pixel area of the main surface.
+ * To match certain aspects of the 3D hardware the CCS is
+ * considered to be made up of normal 128Bx32 Y tiles, Thus
+ * the CCS pitch must be specified in multiples of 128 bytes.
+ *
+ * In reality the CCS tile appears to be a 64Bx64 Y tile, composed
+ * of QWORD (8 bytes) chunks instead of OWORD (16 bytes) chunks.
+ * But that fact is not relevant unless the memory is accessed
+ * directly.
+ */
+#define I915_FORMAT_MOD_Y_TILED_CCS	fourcc_mod_code(INTEL, 4)
+#define I915_FORMAT_MOD_Yf_TILED_CCS	fourcc_mod_code(INTEL, 5)
+
+/*
  * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks
  *
  * Macroblocks are laid in a Z-shape, and each pixel data is following the
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 403339f..54fc38c 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -712,6 +712,56 @@ struct drm_mode_atomic {
 	__u64 user_data;
 };
 
+struct drm_format_modifier_blob {
+#define FORMAT_BLOB_CURRENT 1
+	/* Version of this blob format */
+	__u32 version;
+
+	/* Flags */
+	__u32 flags;
+
+	/* Number of fourcc formats supported */
+	__u32 count_formats;
+
+	/* Where in this blob the formats exist (in bytes) */
+	__u32 formats_offset;
+
+	/* Number of drm_format_modifiers */
+	__u32 count_modifiers;
+
+	/* Where in this blob the modifiers exist (in bytes) */
+	__u32 modifiers_offset;
+
+	/* __u32 formats[] */
+	/* struct drm_format_modifier modifiers[] */
+};
+
+struct drm_format_modifier {
+	/* Bitmask of formats in get_plane format list this info applies to. The
+	 * offset allows a sliding window of which 64 formats (bits).
+	 *
+	 * Some examples:
+	 * In today's world with < 65 formats, and formats 0, and 2 are
+	 * supported
+	 * 0x0000000000000005
+	 *		  ^-offset = 0, formats = 5
+	 *
+	 * If the number formats grew to 128, and formats 98-102 are
+	 * supported with the modifier:
+	 *
+	 * 0x0000003c00000000 0000000000000000
+	 *		  ^
+	 *		  |__offset = 64, formats = 0x3c00000000
+	 *
+	 */
+	__u64 formats;
+	__u32 offset;
+	__u32 pad;
+
+	/* The modifier that applies to the >get_plane format list bitmask. */
+	__u64 modifier;
+};
+
 /**
  * Create a new 'blob' data property, copying length bytes from data pointer,
  * and returning new blob ID.
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 7ccbd6a..6598fb7 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -260,6 +260,8 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_GEM_CONTEXT_GETPARAM	0x34
 #define DRM_I915_GEM_CONTEXT_SETPARAM	0x35
 #define DRM_I915_PERF_OPEN		0x36
+#define DRM_I915_PERF_ADD_CONFIG	0x37
+#define DRM_I915_PERF_REMOVE_CONFIG	0x38
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
 #define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
@@ -315,6 +317,8 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param)
 #define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param)
 #define DRM_IOCTL_I915_PERF_OPEN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
+#define DRM_IOCTL_I915_PERF_ADD_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
+#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -431,6 +435,11 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_HAS_EXEC_BATCH_FIRST	 48
 
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * drm_i915_gem_exec_fence structures.  See I915_EXEC_FENCE_ARRAY.
+ */
+#define I915_PARAM_HAS_EXEC_FENCE_ARRAY  49
+
 typedef struct drm_i915_getparam {
 	__s32 param;
 	/*
@@ -812,6 +821,17 @@ struct drm_i915_gem_exec_object2 {
 	__u64 rsvd2;
 };
 
+struct drm_i915_gem_exec_fence {
+	/**
+	 * User's handle for a drm_syncobj to wait on or signal.
+	 */
+	__u32 handle;
+
+#define I915_EXEC_FENCE_WAIT            (1<<0)
+#define I915_EXEC_FENCE_SIGNAL          (1<<1)
+	__u32 flags;
+};
+
 struct drm_i915_gem_execbuffer2 {
 	/**
 	 * List of gem_exec_object2 structs
@@ -826,7 +846,11 @@ struct drm_i915_gem_execbuffer2 {
 	__u32 DR1;
 	__u32 DR4;
 	__u32 num_cliprects;
-	/** This is a struct drm_clip_rect *cliprects */
+	/**
+	 * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
+	 * is not set.  If I915_EXEC_FENCE_ARRAY is set, then this is a
+	 * struct drm_i915_gem_exec_fence *fences.
+	 */
 	__u64 cliprects_ptr;
 #define I915_EXEC_RING_MASK              (7<<0)
 #define I915_EXEC_DEFAULT                (0<<0)
@@ -927,7 +951,14 @@ struct drm_i915_gem_execbuffer2 {
  * element).
  */
 #define I915_EXEC_BATCH_FIRST		(1<<18)
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_BATCH_FIRST<<1))
+
+/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr
+ * define an array of i915_gem_exec_fence structures which specify a set of
+ * dma fences to wait upon or signal.
+ */
+#define I915_EXEC_FENCE_ARRAY   (1<<19)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1))
 
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
@@ -1467,6 +1498,22 @@ enum drm_i915_perf_record_type {
 	DRM_I915_PERF_RECORD_MAX /* non-ABI */
 };
 
+/**
+ * Structure to upload perf dynamic configuration into the kernel.
+ */
+struct drm_i915_perf_oa_config {
+	/** String formatted like "%08x-%04x-%04x-%04x-%012x" */
+	char uuid[36];
+
+	__u32 n_mux_regs;
+	__u32 n_boolean_regs;
+	__u32 n_flex_regs;
+
+	__u64 __user mux_regs_ptr;
+	__u64 __user boolean_regs_ptr;
+	__u64 __user flex_regs_ptr;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/qxl_drm.h b/include/uapi/drm/qxl_drm.h
index 7eef422..880999d2 100644
--- a/include/uapi/drm/qxl_drm.h
+++ b/include/uapi/drm/qxl_drm.h
@@ -80,8 +80,8 @@ struct drm_qxl_reloc {
 };
 
 struct drm_qxl_command {
-	__u64	 __user command; /* void* */
-	__u64	 __user relocs; /* struct drm_qxl_reloc* */
+	__u64		command; /* void* */
+	__u64		relocs; /* struct drm_qxl_reloc* */
 	__u32		type;
 	__u32		command_size;
 	__u32		relocs_num;
@@ -91,7 +91,7 @@ struct drm_qxl_command {
 struct drm_qxl_execbuffer {
 	__u32		flags;		/* for future use */
 	__u32		commands_num;
-	__u64	 __user commands;	/* struct drm_qxl_command* */
+	__u64		commands;	/* struct drm_qxl_command* */
 };
 
 struct drm_qxl_update_area {
diff --git a/include/uapi/drm/vc4_drm.h b/include/uapi/drm/vc4_drm.h
index 6ac4c5c..afae870 100644
--- a/include/uapi/drm/vc4_drm.h
+++ b/include/uapi/drm/vc4_drm.h
@@ -40,6 +40,7 @@ extern "C" {
 #define DRM_VC4_GET_PARAM                         0x07
 #define DRM_VC4_SET_TILING                        0x08
 #define DRM_VC4_GET_TILING                        0x09
+#define DRM_VC4_LABEL_BO                          0x0a
 
 #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)
@@ -51,6 +52,7 @@ extern "C" {
 #define DRM_IOCTL_VC4_GET_PARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GET_PARAM, struct drm_vc4_get_param)
 #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)
 
 struct drm_vc4_submit_rcl_surface {
 	__u32 hindex; /* Handle index, or ~0 if not present. */
@@ -153,6 +155,16 @@ struct drm_vc4_submit_cl {
 	__u32 pad:24;
 
 #define VC4_SUBMIT_CL_USE_CLEAR_COLOR			(1 << 0)
+/* By default, the kernel gets to choose the order that the tiles are
+ * rendered in.  If this is set, then the tiles will be rendered in a
+ * raster order, with the right-to-left vs left-to-right and
+ * top-to-bottom vs bottom-to-top dictated by
+ * VC4_SUBMIT_CL_RCL_ORDER_INCREASING_*.  This allows overlapping
+ * blits to be implemented using the 3D engine.
+ */
+#define VC4_SUBMIT_CL_FIXED_RCL_ORDER			(1 << 1)
+#define VC4_SUBMIT_CL_RCL_ORDER_INCREASING_X		(1 << 2)
+#define VC4_SUBMIT_CL_RCL_ORDER_INCREASING_Y		(1 << 3)
 	__u32 flags;
 
 	/* Returned value of the seqno of this render job (for the
@@ -292,6 +304,7 @@ struct drm_vc4_get_hang_state {
 #define DRM_VC4_PARAM_SUPPORTS_BRANCHES		3
 #define DRM_VC4_PARAM_SUPPORTS_ETC1		4
 #define DRM_VC4_PARAM_SUPPORTS_THREADED_FS	5
+#define DRM_VC4_PARAM_SUPPORTS_FIXED_RCL_ORDER	6
 
 struct drm_vc4_get_param {
 	__u32 param;
@@ -311,6 +324,15 @@ struct drm_vc4_set_tiling {
 	__u64 modifier;
 };
 
+/**
+ * struct drm_vc4_label_bo - Attach a name to a BO for debug purposes.
+ */
+struct drm_vc4_label_bo {
+	__u32 handle;
+	__u32 len;
+	__u64 name;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index d9dfde9..0bc784f 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -297,13 +297,17 @@ union drm_vmw_surface_reference_arg {
  * @version: Allows expanding the execbuf ioctl parameters without breaking
  * backwards compatibility, since user-space will always tell the kernel
  * which version it uses.
- * @flags: Execbuf flags. None currently.
+ * @flags: Execbuf flags.
+ * @imported_fence_fd:  FD for a fence imported from another device
  *
  * Argument to the DRM_VMW_EXECBUF Ioctl.
  */
 
 #define DRM_VMW_EXECBUF_VERSION 2
 
+#define DRM_VMW_EXECBUF_FLAG_IMPORT_FENCE_FD (1 << 0)
+#define DRM_VMW_EXECBUF_FLAG_EXPORT_FENCE_FD (1 << 1)
+
 struct drm_vmw_execbuf_arg {
 	__u64 commands;
 	__u32 command_size;
@@ -312,7 +316,7 @@ struct drm_vmw_execbuf_arg {
 	__u32 version;
 	__u32 flags;
 	__u32 context_handle;
-	__u32 pad64;
+	__s32 imported_fence_fd;
 };
 
 /**
@@ -328,6 +332,7 @@ struct drm_vmw_execbuf_arg {
  * @passed_seqno: The highest seqno number processed by the hardware
  * so far. This can be used to mark user-space fence objects as signaled, and
  * to determine whether a fence seqno might be stale.
+ * @fd: FD associated with the fence, -1 if not exported
  * @error: This member should've been set to -EFAULT on submission.
  * The following actions should be take on completion:
  * error == -EFAULT: Fence communication failed. The host is synchronized.
@@ -345,7 +350,7 @@ struct drm_vmw_fence_rep {
 	__u32 mask;
 	__u32 seqno;
 	__u32 passed_seqno;
-	__u32 pad64;
+	__s32 fd;
 	__s32 error;
 };
 
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index d683342..7b4567b 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -232,6 +232,35 @@ struct kfd_ioctl_wait_events_args {
 	uint32_t wait_result;		/* from KFD */
 };
 
+struct kfd_ioctl_set_scratch_backing_va_args {
+	uint64_t va_addr;	/* to KFD */
+	uint32_t gpu_id;	/* to KFD */
+	uint32_t pad;
+};
+
+struct kfd_ioctl_get_tile_config_args {
+	/* to KFD: pointer to tile array */
+	uint64_t tile_config_ptr;
+	/* to KFD: pointer to macro tile array */
+	uint64_t macro_tile_config_ptr;
+	/* to KFD: array size allocated by user mode
+	 * from KFD: array size filled by kernel
+	 */
+	uint32_t num_tile_configs;
+	/* to KFD: array size allocated by user mode
+	 * from KFD: array size filled by kernel
+	 */
+	uint32_t num_macro_tile_configs;
+
+	uint32_t gpu_id;		/* to KFD */
+	uint32_t gb_addr_config;	/* from KFD */
+	uint32_t num_banks;		/* from KFD */
+	uint32_t num_ranks;		/* from KFD */
+	/* struct size can be extended later if needed
+	 * without breaking ABI compatibility
+	 */
+};
+
 #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)
@@ -286,7 +315,13 @@ struct kfd_ioctl_wait_events_args {
 #define AMDKFD_IOC_DBG_WAVE_CONTROL		\
 		AMDKFD_IOW(0x10, struct kfd_ioctl_dbg_wave_control_args)
 
+#define AMDKFD_IOC_SET_SCRATCH_BACKING_VA	\
+		AMDKFD_IOWR(0x11, struct kfd_ioctl_set_scratch_backing_va_args)
+
+#define AMDKFD_IOC_GET_TILE_CONFIG                                      \
+		AMDKFD_IOWR(0x12, struct kfd_ioctl_get_tile_config_args)
+
 #define AMDKFD_COMMAND_START		0x01
-#define AMDKFD_COMMAND_END		0x11
+#define AMDKFD_COMMAND_END		0x13
 
 #endif