Merge tag 'drm-next-2018-08-15' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for 4.19.

  Rob has some new hardware support for new qualcomm hw that I'll send
  along separately. This has the display part of it, the remaining pull
  is for the acceleration engine.

  This also contains a wound-wait/wait-die mutex rework, Peter has acked
  it for merging via my tree.

  Otherwise mostly the usual level of activity. Summary:

  core:
   - Wound-wait/wait-die mutex rework
   - Add writeback connector type
   - Add "content type" property for HDMI
   - Move GEM bo to drm_framebuffer
   - Initial gpu scheduler documentation
   - GPU scheduler fixes for dying processes
   - Console deferred fbcon takeover support
   - Displayport support for CEC tunneling over AUX

  panel:
   - otm8009a panel driver fixes
   - Innolux TV123WAM and G070Y2-L01 panel driver
   - Ilitek ILI9881c panel driver
   - Rocktech RK070ER9427 LCD
   - EDT ETM0700G0EDH6 and EDT ETM0700G0BDH6
   - DLC DLC0700YZG-1
   - BOE HV070WSA-100
   - newhaven, nhd-4.3-480272ef-atxl LCD
   - DataImage SCF0700C48GGU18
   - Sharp LQ035Q7DB03
   - p079zca: Refactor to support multiple panels

  tinydrm:
   - ILI9341 display panel

  New driver:
   - vkms - virtual kms driver to testing.

  i915:
   - Icelake:
        Display enablement
        DSI support
        IRQ support
        Powerwell support
   - GPU reset fixes and improvements
   - Full ppgtt support refactoring
   - PSR fixes and improvements
   - Execlist improvments
   - GuC related fixes

  amdgpu:
   - Initial amdgpu documentation
   - JPEG engine support on VCN
   - CIK uses powerplay by default
   - Move to using core PCIE functionality for gens/lanes
   - DC/Powerplay interface rework
   - Stutter mode support for RV
   - Vega12 Powerplay updates
   - GFXOFF fixes
   - GPUVM fault debugging
   - Vega12 GFXOFF
   - DC improvements
   - DC i2c/aux changes
   - UVD 7.2 fixes
   - Powerplay fixes for Polaris12, CZ/ST
   - command submission bo_list fixes

  amdkfd:
   - Raven support
   - Power management fixes

  udl:
   - Cleanups and fixes

  nouveau:
   - misc fixes and cleanups.

  msm:
   - DPU1 support display controller in sdm845
   - GPU coredump support.

  vmwgfx:
   - Atomic modesetting validation fixes
   - Support for multisample surfaces

  armada:
   - Atomic modesetting support completed.

  exynos:
   - IPPv2 fixes
   - Move g2d to component framework
   - Suspend/resume support cleanups
   - Driver cleanups

  imx:
   - CSI configuration improvements
   - Driver cleanups
   - Use atomic suspend/resume helpers
   - ipu-v3 V4L2 XRGB32/XBGR32 support

  pl111:
   - Add Nomadik LCDC variant

  v3d:
   - GPU scheduler jobs management

  sun4i:
   - R40 display engine support
   - TCON TOP driver

  mediatek:
   - MT2712 SoC support

  rockchip:
   - vop fixes

  omapdrm:
   - Workaround for DRA7 errata i932
   - Fix mm_list locking

  mali-dp:
   - Writeback implementation
        PM improvements
   - Internal error reporting debugfs

  tilcdc:
   - Single fix for deferred probing

  hdlcd:
   - Teardown fixes

  tda998x:
   - Converted to a bridge driver.

  etnaviv:
   - Misc fixes"

* tag 'drm-next-2018-08-15' of git://anongit.freedesktop.org/drm/drm: (1506 commits)
  drm/amdgpu/sriov: give 8s for recover vram under RUNTIME
  drm/scheduler: fix param documentation
  drm/i2c: tda998x: correct PLL divider calculation
  drm/i2c: tda998x: get rid of private fill_modes function
  drm/i2c: tda998x: move mode_valid() to bridge
  drm/i2c: tda998x: register bridge outside of component helper
  drm/i2c: tda998x: cleanup from previous changes
  drm/i2c: tda998x: allocate tda998x_priv inside tda998x_create()
  drm/i2c: tda998x: convert to bridge driver
  drm/scheduler: fix timeout worker setup for out of order job completions
  drm/amd/display: display connected to dp-1 does not light up
  drm/amd/display: update clk for various HDMI color depths
  drm/amd/display: program display clock on cache match
  drm/amd/display: Add NULL check for enabling dp ss
  drm/amd/display: add vbios table check for enabling dp ss
  drm/amd/display: Don't share clk source between DP and HDMI
  drm/amd/display: Fix DP HBR2 Eye Diagram Pattern on Carrizo
  drm/amd/display: Use calculated disp_clk_khz value for dce110
  drm/amd/display: Implement custom degamma lut on dcn
  drm/amd/display: Destroy aux_engines only once
  ...

6 files changed, 377 insertions, 42 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 78b4dd89fcb4..1ceec56de015 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -72,6 +72,29 @@ extern "C" {
 #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)
 
+/**
+ * DOC: memory domains
+ *
+ * %AMDGPU_GEM_DOMAIN_CPU	System memory that is not GPU accessible.
+ * Memory in this pool could be swapped out to disk if there is pressure.
+ *
+ * %AMDGPU_GEM_DOMAIN_GTT	GPU accessible system memory, mapped into the
+ * GPU's virtual address space via gart. Gart memory linearizes non-contiguous
+ * pages of system memory, allows GPU access system memory in a linezrized
+ * fashion.
+ *
+ * %AMDGPU_GEM_DOMAIN_VRAM	Local video memory. For APUs, it is memory
+ * carved out by the BIOS.
+ *
+ * %AMDGPU_GEM_DOMAIN_GDS	Global on-chip data storage used to share data
+ * across shader threads.
+ *
+ * %AMDGPU_GEM_DOMAIN_GWS	Global wave sync, used to synchronize the
+ * execution of all the waves on a device.
+ *
+ * %AMDGPU_GEM_DOMAIN_OA	Ordered append, used by 3D or Compute engines
+ * for appending data.
+ */
 #define AMDGPU_GEM_DOMAIN_CPU		0x1
 #define AMDGPU_GEM_DOMAIN_GTT		0x2
 #define AMDGPU_GEM_DOMAIN_VRAM		0x4
@@ -483,7 +506,8 @@ struct drm_amdgpu_gem_va {
 #define AMDGPU_HW_IP_UVD_ENC      5
 #define AMDGPU_HW_IP_VCN_DEC      6
 #define AMDGPU_HW_IP_VCN_ENC      7
-#define AMDGPU_HW_IP_NUM          8
+#define AMDGPU_HW_IP_VCN_JPEG     8
+#define AMDGPU_HW_IP_NUM          9
 
 #define AMDGPU_HW_IP_INSTANCE_MAX_COUNT 1
 
@@ -492,6 +516,7 @@ struct drm_amdgpu_gem_va {
 #define AMDGPU_CHUNK_ID_DEPENDENCIES	0x03
 #define AMDGPU_CHUNK_ID_SYNCOBJ_IN      0x04
 #define AMDGPU_CHUNK_ID_SYNCOBJ_OUT     0x05
+#define AMDGPU_CHUNK_ID_BO_HANDLES      0x06
 
 struct drm_amdgpu_cs_chunk {
 	__u32		chunk_id;
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 9c660e1688ab..300f336633f2 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -687,6 +687,15 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_ASPECT_RATIO    4
 
+/**
+ * DRM_CLIENT_CAP_WRITEBACK_CONNECTORS
+ *
+ * If set to 1, the DRM core will expose special connectors to be used for
+ * writing back to memory the scene setup in the commit. Depends on client
+ * also supporting DRM_CLIENT_CAP_ATOMIC
+ */
+#define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS	5
+
 /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index e04613d30a13..721ab7e54d96 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -183,6 +183,7 @@ extern "C" {
 #define DRM_FORMAT_MOD_VENDOR_QCOM    0x05
 #define DRM_FORMAT_MOD_VENDOR_VIVANTE 0x06
 #define DRM_FORMAT_MOD_VENDOR_BROADCOM 0x07
+#define DRM_FORMAT_MOD_VENDOR_ARM     0x08
 /* add more to the end as needed */
 
 #define DRM_FORMAT_RESERVED	      ((1ULL << 56) - 1)
@@ -298,6 +299,19 @@ extern "C" {
  */
 #define DRM_FORMAT_MOD_SAMSUNG_64_32_TILE	fourcc_mod_code(SAMSUNG, 1)
 
+/*
+ * Qualcomm Compressed Format
+ *
+ * Refers to a compressed variant of the base format that is compressed.
+ * Implementation may be platform and base-format specific.
+ *
+ * Each macrotile consists of m x n (mostly 4 x 4) tiles.
+ * Pixel data pitch/stride is aligned with macrotile width.
+ * Pixel data height is aligned with macrotile height.
+ * Entire pixel data buffer is aligned with 4k(bytes).
+ */
+#define DRM_FORMAT_MOD_QCOM_COMPRESSED	fourcc_mod_code(QCOM, 1)
+
 /* Vivante framebuffer modifiers */
 
 /*
@@ -385,6 +399,23 @@ extern "C" {
 	fourcc_mod_code(NVIDIA, 0x15)
 
 /*
+ * Some Broadcom modifiers take parameters, for example the number of
+ * vertical lines in the image. Reserve the lower 32 bits for modifier
+ * type, and the next 24 bits for parameters. Top 8 bits are the
+ * vendor code.
+ */
+#define __fourcc_mod_broadcom_param_shift 8
+#define __fourcc_mod_broadcom_param_bits 48
+#define fourcc_mod_broadcom_code(val, params) \
+	fourcc_mod_code(BROADCOM, ((((__u64)params) << __fourcc_mod_broadcom_param_shift) | val))
+#define fourcc_mod_broadcom_param(m) \
+	((int)(((m) >> __fourcc_mod_broadcom_param_shift) &	\
+	       ((1ULL << __fourcc_mod_broadcom_param_bits) - 1)))
+#define fourcc_mod_broadcom_mod(m) \
+	((m) & ~(((1ULL << __fourcc_mod_broadcom_param_bits) - 1) <<	\
+		 __fourcc_mod_broadcom_param_shift))
+
+/*
  * Broadcom VC4 "T" format
  *
  * This is the primary layout that the V3D GPU can texture from (it
@@ -405,6 +436,151 @@ extern "C" {
  */
 #define DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED fourcc_mod_code(BROADCOM, 1)
 
+/*
+ * Broadcom SAND format
+ *
+ * This is the native format that the H.264 codec block uses.  For VC4
+ * HVS, it is only valid for H.264 (NV12/21) and RGBA modes.
+ *
+ * The image can be considered to be split into columns, and the
+ * columns are placed consecutively into memory.  The width of those
+ * columns can be either 32, 64, 128, or 256 pixels, but in practice
+ * only 128 pixel columns are used.
+ *
+ * The pitch between the start of each column is set to optimally
+ * switch between SDRAM banks. This is passed as the number of lines
+ * of column width in the modifier (we can't use the stride value due
+ * to various core checks that look at it , so you should set the
+ * stride to width*cpp).
+ *
+ * Note that the column height for this format modifier is the same
+ * for all of the planes, assuming that each column contains both Y
+ * and UV.  Some SAND-using hardware stores UV in a separate tiled
+ * image from Y to reduce the column height, which is not supported
+ * with these modifiers.
+ */
+
+#define DRM_FORMAT_MOD_BROADCOM_SAND32_COL_HEIGHT(v) \
+	fourcc_mod_broadcom_code(2, v)
+#define DRM_FORMAT_MOD_BROADCOM_SAND64_COL_HEIGHT(v) \
+	fourcc_mod_broadcom_code(3, v)
+#define DRM_FORMAT_MOD_BROADCOM_SAND128_COL_HEIGHT(v) \
+	fourcc_mod_broadcom_code(4, v)
+#define DRM_FORMAT_MOD_BROADCOM_SAND256_COL_HEIGHT(v) \
+	fourcc_mod_broadcom_code(5, v)
+
+#define DRM_FORMAT_MOD_BROADCOM_SAND32 \
+	DRM_FORMAT_MOD_BROADCOM_SAND32_COL_HEIGHT(0)
+#define DRM_FORMAT_MOD_BROADCOM_SAND64 \
+	DRM_FORMAT_MOD_BROADCOM_SAND64_COL_HEIGHT(0)
+#define DRM_FORMAT_MOD_BROADCOM_SAND128 \
+	DRM_FORMAT_MOD_BROADCOM_SAND128_COL_HEIGHT(0)
+#define DRM_FORMAT_MOD_BROADCOM_SAND256 \
+	DRM_FORMAT_MOD_BROADCOM_SAND256_COL_HEIGHT(0)
+
+/* Broadcom UIF format
+ *
+ * This is the common format for the current Broadcom multimedia
+ * blocks, including V3D 3.x and newer, newer video codecs, and
+ * displays.
+ *
+ * The image consists of utiles (64b blocks), UIF blocks (2x2 utiles),
+ * and macroblocks (4x4 UIF blocks).  Those 4x4 UIF block groups are
+ * stored in columns, with padding between the columns to ensure that
+ * moving from one column to the next doesn't hit the same SDRAM page
+ * bank.
+ *
+ * To calculate the padding, it is assumed that each hardware block
+ * and the software driving it knows the platform's SDRAM page size,
+ * number of banks, and XOR address, and that it's identical between
+ * all blocks using the format.  This tiling modifier will use XOR as
+ * necessary to reduce the padding.  If a hardware block can't do XOR,
+ * the assumption is that a no-XOR tiling modifier will be created.
+ */
+#define DRM_FORMAT_MOD_BROADCOM_UIF fourcc_mod_code(BROADCOM, 6)
+
+/*
+ * Arm Framebuffer Compression (AFBC) modifiers
+ *
+ * AFBC is a proprietary lossless image compression protocol and format.
+ * It provides fine-grained random access and minimizes the amount of data
+ * transferred between IP blocks.
+ *
+ * AFBC has several features which may be supported and/or used, which are
+ * represented using bits in the modifier. Not all combinations are valid,
+ * and different devices or use-cases may support different combinations.
+ */
+#define DRM_FORMAT_MOD_ARM_AFBC(__afbc_mode)	fourcc_mod_code(ARM, __afbc_mode)
+
+/*
+ * AFBC superblock size
+ *
+ * Indicates the superblock size(s) used for the AFBC buffer. The buffer
+ * size (in pixels) must be aligned to a multiple of the superblock size.
+ * Four lowest significant bits(LSBs) are reserved for block size.
+ */
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_MASK      0xf
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_16x16     (1ULL)
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_32x8      (2ULL)
+
+/*
+ * AFBC lossless colorspace transform
+ *
+ * Indicates that the buffer makes use of the AFBC lossless colorspace
+ * transform.
+ */
+#define AFBC_FORMAT_MOD_YTR     (1ULL <<  4)
+
+/*
+ * AFBC block-split
+ *
+ * Indicates that the payload of each superblock is split. The second
+ * half of the payload is positioned at a predefined offset from the start
+ * of the superblock payload.
+ */
+#define AFBC_FORMAT_MOD_SPLIT   (1ULL <<  5)
+
+/*
+ * AFBC sparse layout
+ *
+ * This flag indicates that the payload of each superblock must be stored at a
+ * predefined position relative to the other superblocks in the same AFBC
+ * buffer. This order is the same order used by the header buffer. In this mode
+ * each superblock is given the same amount of space as an uncompressed
+ * superblock of the particular format would require, rounding up to the next
+ * multiple of 128 bytes in size.
+ */
+#define AFBC_FORMAT_MOD_SPARSE  (1ULL <<  6)
+
+/*
+ * AFBC copy-block restrict
+ *
+ * Buffers with this flag must obey the copy-block restriction. The restriction
+ * is such that there are no copy-blocks referring across the border of 8x8
+ * blocks. For the subsampled data the 8x8 limitation is also subsampled.
+ */
+#define AFBC_FORMAT_MOD_CBR     (1ULL <<  7)
+
+/*
+ * AFBC tiled layout
+ *
+ * The tiled layout groups superblocks in 8x8 or 4x4 tiles, where all
+ * superblocks inside a tile are stored together in memory. 8x8 tiles are used
+ * for pixel formats up to and including 32 bpp while 4x4 tiles are used for
+ * larger bpp formats. The order between the tiles is scan line.
+ * When the tiled layout is used, the buffer size (in pixels) must be aligned
+ * to the tile size.
+ */
+#define AFBC_FORMAT_MOD_TILED   (1ULL <<  8)
+
+/*
+ * AFBC solid color blocks
+ *
+ * Indicates that the buffer makes use of solid-color blocks, whereby bandwidth
+ * can be reduced if a whole superblock is a single color.
+ */
+#define AFBC_FORMAT_MOD_SC      (1ULL <<  9)
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 4b3a1bb58e68..8d67243952f4 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -96,6 +96,13 @@ extern "C" {
 #define DRM_MODE_PICTURE_ASPECT_64_27		3
 #define DRM_MODE_PICTURE_ASPECT_256_135		4
 
+/* Content type options */
+#define DRM_MODE_CONTENT_TYPE_NO_DATA		0
+#define DRM_MODE_CONTENT_TYPE_GRAPHICS		1
+#define DRM_MODE_CONTENT_TYPE_PHOTO		2
+#define DRM_MODE_CONTENT_TYPE_CINEMA		3
+#define DRM_MODE_CONTENT_TYPE_GAME		4
+
 /* Aspect ratio flag bitmask (4 bits 22:19) */
 #define DRM_MODE_FLAG_PIC_AR_MASK		(0x0F<<19)
 #define  DRM_MODE_FLAG_PIC_AR_NONE \
@@ -344,6 +351,7 @@ enum drm_mode_subconnector {
 #define DRM_MODE_CONNECTOR_VIRTUAL      15
 #define DRM_MODE_CONNECTOR_DSI		16
 #define DRM_MODE_CONNECTOR_DPI		17
+#define DRM_MODE_CONNECTOR_WRITEBACK	18
 
 struct drm_mode_get_connector {
 
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index 0bc784f5e0db..399f58317cff 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -40,6 +40,7 @@ extern "C" {
 
 #define DRM_VMW_GET_PARAM            0
 #define DRM_VMW_ALLOC_DMABUF         1
+#define DRM_VMW_ALLOC_BO             1
 #define DRM_VMW_UNREF_DMABUF         2
 #define DRM_VMW_HANDLE_CLOSE         2
 #define DRM_VMW_CURSOR_BYPASS        3
@@ -68,6 +69,8 @@ extern "C" {
 #define DRM_VMW_GB_SURFACE_REF       24
 #define DRM_VMW_SYNCCPU              25
 #define DRM_VMW_CREATE_EXTENDED_CONTEXT 26
+#define DRM_VMW_GB_SURFACE_CREATE_EXT   27
+#define DRM_VMW_GB_SURFACE_REF_EXT      28
 
 /*************************************************************************/
 /**
@@ -79,6 +82,9 @@ extern "C" {
  *
  * DRM_VMW_PARAM_OVERLAY_IOCTL:
  * Does the driver support the overlay ioctl.
+ *
+ * DRM_VMW_PARAM_SM4_1
+ * SM4_1 support is enabled.
  */
 
 #define DRM_VMW_PARAM_NUM_STREAMS      0
@@ -94,6 +100,8 @@ extern "C" {
 #define DRM_VMW_PARAM_MAX_MOB_SIZE     10
 #define DRM_VMW_PARAM_SCREEN_TARGET    11
 #define DRM_VMW_PARAM_DX               12
+#define DRM_VMW_PARAM_HW_CAPS2         13
+#define DRM_VMW_PARAM_SM4_1            14
 
 /**
  * enum drm_vmw_handle_type - handle type for ref ioctls
@@ -356,9 +364,9 @@ struct drm_vmw_fence_rep {
 
 /*************************************************************************/
 /**
- * DRM_VMW_ALLOC_DMABUF
+ * DRM_VMW_ALLOC_BO
  *
- * Allocate a DMA buffer that is visible also to the host.
+ * Allocate a buffer object that is visible also to the host.
  * NOTE: The buffer is
  * identified by a handle and an offset, which are private to the guest, but
  * useable in the command stream. The guest kernel may translate these
@@ -366,27 +374,28 @@ struct drm_vmw_fence_rep {
  * be zero at all times, or it may disappear from the interface before it is
  * fixed.
  *
- * The DMA buffer may stay user-space mapped in the guest at all times,
+ * The buffer object may stay user-space mapped in the guest at all times,
  * and is thus suitable for sub-allocation.
  *
- * DMA buffers are mapped using the mmap() syscall on the drm device.
+ * Buffer objects are mapped using the mmap() syscall on the drm device.
  */
 
 /**
- * struct drm_vmw_alloc_dmabuf_req
+ * struct drm_vmw_alloc_bo_req
  *
  * @size: Required minimum size of the buffer.
  *
- * Input data to the DRM_VMW_ALLOC_DMABUF Ioctl.
+ * Input data to the DRM_VMW_ALLOC_BO Ioctl.
  */
 
-struct drm_vmw_alloc_dmabuf_req {
+struct drm_vmw_alloc_bo_req {
 	__u32 size;
 	__u32 pad64;
 };
+#define drm_vmw_alloc_dmabuf_req drm_vmw_alloc_bo_req
 
 /**
- * struct drm_vmw_dmabuf_rep
+ * struct drm_vmw_bo_rep
  *
  * @map_handle: Offset to use in the mmap() call used to map the buffer.
  * @handle: Handle unique to this buffer. Used for unreferencing.
@@ -395,50 +404,32 @@ struct drm_vmw_alloc_dmabuf_req {
  * @cur_gmr_offset: Offset to use in the command stream when this buffer is
  * referenced. See note above.
  *
- * Output data from the DRM_VMW_ALLOC_DMABUF Ioctl.
+ * Output data from the DRM_VMW_ALLOC_BO Ioctl.
  */
 
-struct drm_vmw_dmabuf_rep {
+struct drm_vmw_bo_rep {
 	__u64 map_handle;
 	__u32 handle;
 	__u32 cur_gmr_id;
 	__u32 cur_gmr_offset;
 	__u32 pad64;
 };
+#define drm_vmw_dmabuf_rep drm_vmw_bo_rep
 
 /**
- * union drm_vmw_dmabuf_arg
+ * union drm_vmw_alloc_bo_arg
  *
  * @req: Input data as described above.
  * @rep: Output data as described above.
  *
- * Argument to the DRM_VMW_ALLOC_DMABUF Ioctl.
+ * Argument to the DRM_VMW_ALLOC_BO Ioctl.
  */
 
-union drm_vmw_alloc_dmabuf_arg {
-	struct drm_vmw_alloc_dmabuf_req req;
-	struct drm_vmw_dmabuf_rep rep;
-};
-
-/*************************************************************************/
-/**
- * DRM_VMW_UNREF_DMABUF - Free a DMA buffer.
- *
- */
-
-/**
- * struct drm_vmw_unref_dmabuf_arg
- *
- * @handle: Handle indicating what buffer to free. Obtained from the
- * DRM_VMW_ALLOC_DMABUF Ioctl.
- *
- * Argument to the DRM_VMW_UNREF_DMABUF Ioctl.
- */
-
-struct drm_vmw_unref_dmabuf_arg {
-	__u32 handle;
-	__u32 pad64;
+union drm_vmw_alloc_bo_arg {
+	struct drm_vmw_alloc_bo_req req;
+	struct drm_vmw_bo_rep rep;
 };
+#define drm_vmw_alloc_dmabuf_arg drm_vmw_alloc_bo_arg
 
 /*************************************************************************/
 /**
@@ -1103,9 +1094,8 @@ union drm_vmw_extended_context_arg {
  * DRM_VMW_HANDLE_CLOSE - Close a user-space handle and release its
  * underlying resource.
  *
- * Note that this ioctl is overlaid on the DRM_VMW_UNREF_DMABUF Ioctl.
- * The ioctl arguments therefore need to be identical in layout.
- *
+ * Note that this ioctl is overlaid on the deprecated DRM_VMW_UNREF_DMABUF
+ * Ioctl.
  */
 
 /**
@@ -1119,7 +1109,107 @@ struct drm_vmw_handle_close_arg {
 	__u32 handle;
 	__u32 pad64;
 };
+#define drm_vmw_unref_dmabuf_arg drm_vmw_handle_close_arg
+
+/*************************************************************************/
+/**
+ * DRM_VMW_GB_SURFACE_CREATE_EXT - Create a host guest-backed surface.
+ *
+ * Allocates a surface handle and queues a create surface command
+ * for the host on the first use of the surface. The surface ID can
+ * be used as the surface ID in commands referencing the surface.
+ *
+ * This new command extends DRM_VMW_GB_SURFACE_CREATE by adding version
+ * parameter and 64 bit svga flag.
+ */
+
+/**
+ * enum drm_vmw_surface_version
+ *
+ * @drm_vmw_surface_gb_v1: Corresponds to current gb surface format with
+ * svga3d surface flags split into 2, upper half and lower half.
+ */
+enum drm_vmw_surface_version {
+	drm_vmw_gb_surface_v1
+};
+
+/**
+ * struct drm_vmw_gb_surface_create_ext_req
+ *
+ * @base: Surface create parameters.
+ * @version: Version of surface create ioctl.
+ * @svga3d_flags_upper_32_bits: Upper 32 bits of svga3d flags.
+ * @multisample_pattern: Multisampling pattern when msaa is supported.
+ * @quality_level: Precision settings for each sample.
+ * @must_be_zero: Reserved for future usage.
+ *
+ * Input argument to the  DRM_VMW_GB_SURFACE_CREATE_EXT Ioctl.
+ * Part of output argument for the DRM_VMW_GB_SURFACE_REF_EXT Ioctl.
+ */
+struct drm_vmw_gb_surface_create_ext_req {
+	struct drm_vmw_gb_surface_create_req base;
+	enum drm_vmw_surface_version version;
+	uint32_t svga3d_flags_upper_32_bits;
+	SVGA3dMSPattern multisample_pattern;
+	SVGA3dMSQualityLevel quality_level;
+	uint64_t must_be_zero;
+};
+
+/**
+ * union drm_vmw_gb_surface_create_ext_arg
+ *
+ * @req: Input argument as described above.
+ * @rep: Output argument as described above.
+ *
+ * Argument to the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl.
+ */
+union drm_vmw_gb_surface_create_ext_arg {
+	struct drm_vmw_gb_surface_create_rep rep;
+	struct drm_vmw_gb_surface_create_ext_req req;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_GB_SURFACE_REF_EXT - Reference a host surface.
+ *
+ * Puts a reference on a host surface with a given handle, as previously
+ * returned by the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl.
+ * A reference will make sure the surface isn't destroyed while we hold
+ * it and will allow the calling client to use the surface handle in
+ * the command stream.
+ *
+ * On successful return, the Ioctl returns the surface information given
+ * to and returned from the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl.
+ */
 
+/**
+ * struct drm_vmw_gb_surface_ref_ext_rep
+ *
+ * @creq: The data used as input when the surface was created, as described
+ *        above at "struct drm_vmw_gb_surface_create_ext_req"
+ * @crep: Additional data output when the surface was created, as described
+ *        above at "struct drm_vmw_gb_surface_create_rep"
+ *
+ * Output Argument to the DRM_VMW_GB_SURFACE_REF_EXT ioctl.
+ */
+struct drm_vmw_gb_surface_ref_ext_rep {
+	struct drm_vmw_gb_surface_create_ext_req creq;
+	struct drm_vmw_gb_surface_create_rep crep;
+};
+
+/**
+ * union drm_vmw_gb_surface_reference_ext_arg
+ *
+ * @req: Input data as described above at "struct drm_vmw_surface_arg"
+ * @rep: Output data as described above at
+ *       "struct drm_vmw_gb_surface_ref_ext_rep"
+ *
+ * Argument to the DRM_VMW_GB_SURFACE_REF Ioctl.
+ */
+union drm_vmw_gb_surface_reference_ext_arg {
+	struct drm_vmw_gb_surface_ref_ext_rep rep;
+	struct drm_vmw_surface_arg req;
+};
 
 #if defined(__cplusplus)
 }
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index b4f5073dbac2..01674b56e14f 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -76,6 +76,12 @@ struct kfd_ioctl_update_queue_args {
 	__u32 queue_priority;	/* to KFD */
 };
 
+struct kfd_ioctl_set_cu_mask_args {
+	__u32 queue_id;		/* to KFD */
+	__u32 num_cu_mask;		/* to KFD */
+	__u64 cu_mask_ptr;		/* to KFD */
+};
+
 /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */
 #define KFD_IOC_CACHE_POLICY_COHERENT 0
 #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1
@@ -189,6 +195,15 @@ struct kfd_ioctl_dbg_wave_control_args {
 
 #define KFD_SIGNAL_EVENT_LIMIT			4096
 
+/* For kfd_event_data.hw_exception_data.reset_type. */
+#define KFD_HW_EXCEPTION_WHOLE_GPU_RESET	0
+#define KFD_HW_EXCEPTION_PER_ENGINE_RESET	1
+
+/* For kfd_event_data.hw_exception_data.reset_cause. */
+#define KFD_HW_EXCEPTION_GPU_HANG	0
+#define KFD_HW_EXCEPTION_ECC		1
+
+
 struct kfd_ioctl_create_event_args {
 	__u64 event_page_offset;	/* from KFD */
 	__u32 event_trigger_data;	/* from KFD - signal events only */
@@ -219,7 +234,7 @@ struct kfd_memory_exception_failure {
 	__u32 NotPresent;	/* Page not present or supervisor privilege */
 	__u32 ReadOnly;	/* Write access to a read-only page */
 	__u32 NoExecute;	/* Execute access to a page marked NX */
-	__u32 pad;
+	__u32 imprecise;	/* Can't determine the	exact fault address */
 };
 
 /* memory exception data*/
@@ -230,10 +245,19 @@ struct kfd_hsa_memory_exception_data {
 	__u32 pad;
 };
 
-/* Event data*/
+/* hw exception data */
+struct kfd_hsa_hw_exception_data {
+	uint32_t reset_type;
+	uint32_t reset_cause;
+	uint32_t memory_lost;
+	uint32_t gpu_id;
+};
+
+/* Event data */
 struct kfd_event_data {
 	union {
 		struct kfd_hsa_memory_exception_data memory_exception_data;
+		struct kfd_hsa_hw_exception_data hw_exception_data;
 	};				/* From KFD */
 	__u64 kfd_event_data_ext;	/* pointer to an extension structure
 					   for future exception types */
@@ -448,7 +472,10 @@ struct kfd_ioctl_unmap_memory_from_gpu_args {
 #define AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU	\
 		AMDKFD_IOWR(0x19, struct kfd_ioctl_unmap_memory_from_gpu_args)
 
+#define AMDKFD_IOC_SET_CU_MASK		\
+		AMDKFD_IOW(0x1A, struct kfd_ioctl_set_cu_mask_args)
+
 #define AMDKFD_COMMAND_START		0x01
-#define AMDKFD_COMMAND_END		0x1A
+#define AMDKFD_COMMAND_END		0x1B
 
 #endif