Merge tag 'drm-for-v4.9' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "Core:
   - Fence destaging work
   - DRIVER_LEGACY to split off legacy drm drivers
   - drm_mm refactoring
   - Splitting drm_crtc.c into chunks and documenting better
   - Display info fixes
   - rbtree support for prime buffer lookup
   - Simple VGA DAC driver

  Panel:
   - Add Nexus 7 panel
   - More simple panels

  i915:
   - Refactoring GEM naming
   - Refactored vma/active tracking
   - Lockless request lookups
   - Better stolen memory support
   - FBC fixes
   - SKL watermark fixes
   - VGPU improvements
   - dma-buf fencing support
   - Better DP dongle support

  amdgpu:
   - Powerplay for Iceland asics
   - Improved GPU reset support
   - UVD/VEC powergating support for CZ/ST
   - Preinitialised VRAM buffer support
   - Virtual display support
   - Initial SI support
   - GTT rework
   - PCI shutdown callback support
   - HPD IRQ storm fixes

  amdkfd:
   - bugfixes

  tilcdc:
   - Atomic modesetting support

  mediatek:
   - AAL + GAMMA engine support
   - Hook up gamma LUT
   - Temporal dithering support

  imx:
   - Pixel clock from devicetree
   - drm bridge support for LVDS bridges
   - active plane reconfiguration
   - VDIC deinterlacer support
   - Frame synchronisation unit support
   - Color space conversion support

  analogix:
   - PSR support
   - Better panel on/off support

  rockchip:
   - rk3399 vop/crtc support
   - PSR support

  vc4:
   - Interlaced vblank timing
   - 3D rendering CPU overhead reduction
   - HDMI output fixes

  tda998x:
   - HDMI audio ASoC support

  sunxi:
   - Allwinner A33 support
   - better TCON support

  msm:
   - DT binding cleanups
   - Explicit fence-fd support

  sti:
   - remove sti415/416 support

  etnaviv:
   - MMUv2 refactoring
   - GC3000 support

  exynos:
   - Refactoring HDMI DCC/PHY
   - G2D pm regression fix
   - Page fault issues with wait for vblank

  There is no nouveau work in this tree, as Ben didn't get a pull
  request in, and he was fighting moving to atomic and adding mst
  support, so maybe best it waits for a cycle"

* tag 'drm-for-v4.9' of git://people.freedesktop.org/~airlied/linux: (1412 commits)
  drm/crtc: constify drm_crtc_index parameter
  drm/i915: Fix conflict resolution from backmerge of v4.8-rc8 to drm-next
  drm/i915/guc: Unwind GuC workqueue reservation if request construction fails
  drm/i915: Reset the breadcrumbs IRQ more carefully
  drm/i915: Force relocations via cpu if we run out of idle aperture
  drm/i915: Distinguish last emitted request from last submitted request
  drm/i915: Allow DP to work w/o EDID
  drm/i915: Move long hpd handling into the hotplug work
  drm/i915/execlists: Reinitialise context image after GPU hang
  drm/i915: Use correct index for backtracking HUNG semaphores
  drm/i915: Unalias obj->phys_handle and obj->userptr
  drm/i915: Just clear the mmiodebug before a register access
  drm/i915/gen9: only add the planes actually affected by ddb changes
  drm/i915: Allow PCH DPLL sharing regardless of DPLL_SDVO_HIGH_SPEED
  drm/i915/bxt: Fix HDMI DPLL configuration
  drm/i915/gen9: fix the watermark res_blocks value
  drm/i915/gen9: fix plane_blocks_per_line on watermarks calculations
  drm/i915/gen9: minimum scanlines for Y tile is not always 4
  drm/i915/gen9: fix the WaWmMemoryReadLatency implementation
  drm/i915/kbl: KBL also needs to run the SAGV code
  ...

7 files changed, 123 insertions, 19 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 462246aa200e..d6b5a21f3d3c 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -77,6 +77,10 @@ extern "C" {
 #define AMDGPU_GEM_CREATE_NO_CPU_ACCESS		(1 << 1)
 /* Flag that USWC attributes should be used for GTT */
 #define AMDGPU_GEM_CREATE_CPU_GTT_USWC		(1 << 2)
+/* Flag that the memory should be in VRAM and cleared */
+#define AMDGPU_GEM_CREATE_VRAM_CLEARED		(1 << 3)
+/* Flag that create shadow bo(GTT) while allocating vram bo */
+#define AMDGPU_GEM_CREATE_SHADOW		(1 << 4)
 
 struct drm_amdgpu_gem_create_in  {
 	/** the requested memory size */
@@ -481,6 +485,8 @@ struct drm_amdgpu_cs_chunk_data {
 #define AMDGPU_INFO_DEV_INFO			0x16
 /* visible vram usage */
 #define AMDGPU_INFO_VIS_VRAM_USAGE		0x17
+/* number of TTM buffer evictions */
+#define AMDGPU_INFO_NUM_EVICTIONS		0x18
 
 #define AMDGPU_INFO_MMR_SE_INDEX_SHIFT	0
 #define AMDGPU_INFO_MMR_SE_INDEX_MASK	0xff
@@ -643,6 +649,7 @@ struct drm_amdgpu_info_hw_ip {
  * Supported GPU families
  */
 #define AMDGPU_FAMILY_UNKNOWN			0
+#define AMDGPU_FAMILY_SI			110 /* Hainan, Oland, Verde, Pitcairn, Tahiti */
 #define AMDGPU_FAMILY_CI			120 /* Bonaire, Hawaii */
 #define AMDGPU_FAMILY_KV			125 /* Kaveri, Kabini, Mullins */
 #define AMDGPU_FAMILY_VI			130 /* Iceland, Tonga */
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 452675fb55d9..b2c52843bc70 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -646,6 +646,7 @@ struct drm_gem_open {
 #define DRM_CAP_CURSOR_WIDTH		0x8
 #define DRM_CAP_CURSOR_HEIGHT		0x9
 #define DRM_CAP_ADDFB2_MODIFIERS	0x10
+#define DRM_CAP_PAGE_FLIP_TARGET	0x11
 
 /** DRM_IOCTL_GET_CAP ioctl argument type */
 struct drm_get_cap {
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 49a72659b801..df0e3504c349 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -520,7 +520,13 @@ struct drm_color_lut {
 
 #define DRM_MODE_PAGE_FLIP_EVENT 0x01
 #define DRM_MODE_PAGE_FLIP_ASYNC 0x02
-#define DRM_MODE_PAGE_FLIP_FLAGS (DRM_MODE_PAGE_FLIP_EVENT|DRM_MODE_PAGE_FLIP_ASYNC)
+#define DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE 0x4
+#define DRM_MODE_PAGE_FLIP_TARGET_RELATIVE 0x8
+#define DRM_MODE_PAGE_FLIP_TARGET (DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE | \
+				   DRM_MODE_PAGE_FLIP_TARGET_RELATIVE)
+#define DRM_MODE_PAGE_FLIP_FLAGS (DRM_MODE_PAGE_FLIP_EVENT | \
+				  DRM_MODE_PAGE_FLIP_ASYNC | \
+				  DRM_MODE_PAGE_FLIP_TARGET)
 
 /*
  * Request a page flip on the specified crtc.
@@ -543,8 +549,7 @@ struct drm_color_lut {
  * 'as soon as possible', meaning that it not delay waiting for vblank.
  * This may cause tearing on the screen.
  *
- * The reserved field must be zero until we figure out something
- * clever to use it for.
+ * The reserved field must be zero.
  */
 
 struct drm_mode_crtc_page_flip {
@@ -555,6 +560,34 @@ struct drm_mode_crtc_page_flip {
 	__u64 user_data;
 };
 
+/*
+ * Request a page flip on the specified crtc.
+ *
+ * Same as struct drm_mode_crtc_page_flip, but supports new flags and
+ * re-purposes the reserved field:
+ *
+ * The sequence field must be zero unless either of the
+ * DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE/RELATIVE flags is specified. When
+ * the ABSOLUTE flag is specified, the sequence field denotes the absolute
+ * vblank sequence when the flip should take effect. When the RELATIVE
+ * flag is specified, the sequence field denotes the relative (to the
+ * current one when the ioctl is called) vblank sequence when the flip
+ * should take effect. NOTE: DRM_IOCTL_WAIT_VBLANK must still be used to
+ * make sure the vblank sequence before the target one has passed before
+ * calling this ioctl. The purpose of the
+ * DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE/RELATIVE flags is merely to clarify
+ * the target for when code dealing with a page flip runs during a
+ * vertical blank period.
+ */
+
+struct drm_mode_crtc_page_flip_target {
+	__u32 crtc_id;
+	__u32 fb_id;
+	__u32 flags;
+	__u32 sequence;
+	__u64 user_data;
+};
+
 /* create a dumb scanout buffer */
 struct drm_mode_create_dumb {
 	__u32 height;
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index d7e81a3886fd..03725fe89859 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -62,6 +62,30 @@ extern "C" {
 #define I915_ERROR_UEVENT		"ERROR"
 #define I915_RESET_UEVENT		"RESET"
 
+/*
+ * MOCS indexes used for GPU surfaces, defining the cacheability of the
+ * surface data and the coherency for this data wrt. CPU vs. GPU accesses.
+ */
+enum i915_mocs_table_index {
+	/*
+	 * Not cached anywhere, coherency between CPU and GPU accesses is
+	 * guaranteed.
+	 */
+	I915_MOCS_UNCACHED,
+	/*
+	 * Cacheability and coherency controlled by the kernel automatically
+	 * based on the DRM_I915_GEM_SET_CACHING IOCTL setting and the current
+	 * usage of the surface (used for display scanout or not).
+	 */
+	I915_MOCS_PTE,
+	/*
+	 * Cached in all GPU caches available on the platform.
+	 * Coherency between CPU and GPU accesses to the surface is not
+	 * guaranteed without extra synchronization.
+	 */
+	I915_MOCS_CACHED,
+};
+
 /* Each region is a minimum of 16k, and there are at most 255 of them.
  */
 #define I915_NR_TEX_REGIONS 255	/* table size 2k - maximum due to use
@@ -363,6 +387,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_EXEC_SOFTPIN	 37
 #define I915_PARAM_HAS_POOLED_EU	 38
 #define I915_PARAM_MIN_EU_IN_POOL	 39
+#define I915_PARAM_MMAP_GTT_VERSION	 40
 
 typedef struct drm_i915_getparam {
 	__s32 param;
@@ -698,15 +723,20 @@ struct drm_i915_gem_exec_object2 {
 	 */
 	__u64 offset;
 
-#define EXEC_OBJECT_NEEDS_FENCE (1<<0)
-#define EXEC_OBJECT_NEEDS_GTT	(1<<1)
-#define EXEC_OBJECT_WRITE	(1<<2)
+#define EXEC_OBJECT_NEEDS_FENCE		 (1<<0)
+#define EXEC_OBJECT_NEEDS_GTT		 (1<<1)
+#define EXEC_OBJECT_WRITE		 (1<<2)
 #define EXEC_OBJECT_SUPPORTS_48B_ADDRESS (1<<3)
-#define EXEC_OBJECT_PINNED	(1<<4)
-#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_PINNED<<1)
+#define EXEC_OBJECT_PINNED		 (1<<4)
+#define EXEC_OBJECT_PAD_TO_SIZE		 (1<<5)
+/* All remaining bits are MBZ and RESERVED FOR FUTURE USE */
+#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_PAD_TO_SIZE<<1)
 	__u64 flags;
 
-	__u64 rsvd1;
+	union {
+		__u64 rsvd1;
+		__u64 pad_to_size;
+	};
 	__u64 rsvd2;
 };
 
@@ -826,7 +856,16 @@ struct drm_i915_gem_busy {
 	 * having flushed any pending activity), and a non-zero return that
 	 * the object is still in-flight on the GPU. (The GPU has not yet
 	 * signaled completion for all pending requests that reference the
-	 * object.)
+	 * object.) An object is guaranteed to become idle eventually (so
+	 * long as no new GPU commands are executed upon it). Due to the
+	 * asynchronous nature of the hardware, an object reported
+	 * as busy may become idle before the ioctl is completed.
+	 *
+	 * Furthermore, if the object is busy, which engine is busy is only
+	 * provided as a guide. There are race conditions which prevent the
+	 * report of which engines are busy from being always accurate.
+	 * However, the converse is not true. If the object is idle, the
+	 * result of the ioctl, that all engines are idle, is accurate.
 	 *
 	 * The returned dword is split into two fields to indicate both
 	 * the engines on which the object is being read, and the
@@ -849,6 +888,11 @@ struct drm_i915_gem_busy {
 	 * execution engines, e.g. multiple media engines, which are
 	 * mapped to the same identifier in the EXECBUFFER2 ioctl and
 	 * so are not separately reported for busyness.
+	 *
+	 * Caveat emptor:
+	 * Only the boolean result of this query is reliable; that is whether
+	 * the object is idle or busy. The report of which engines are busy
+	 * should be only used as a heuristic.
 	 */
 	__u32 busy;
 };
@@ -897,6 +941,7 @@ struct drm_i915_gem_caching {
 #define I915_TILING_NONE	0
 #define I915_TILING_X		1
 #define I915_TILING_Y		2
+#define I915_TILING_LAST	I915_TILING_Y
 
 #define I915_BIT_6_SWIZZLE_NONE		0
 #define I915_BIT_6_SWIZZLE_9		1
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index 49f778de8e06..8c51e8a0df89 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -42,6 +42,15 @@ extern "C" {
 #define MSM_PIPE_2D1         0x02
 #define MSM_PIPE_3D0         0x10
 
+/* The pipe-id just uses the lower bits, so can be OR'd with flags in
+ * the upper 16 bits (which could be extended further, if needed, maybe
+ * we extend/overload the pipe-id some day to deal with multiple rings,
+ * but even then I don't think we need the full lower 16 bits).
+ */
+#define MSM_PIPE_ID_MASK     0xffff
+#define MSM_PIPE_ID(x)       ((x) & MSM_PIPE_ID_MASK)
+#define MSM_PIPE_FLAGS(x)    ((x) & ~MSM_PIPE_ID_MASK)
+
 /* timeouts are specified in clock-monotonic absolute times (to simplify
  * restarting interrupted ioctls).  The following struct is logically the
  * same as 'struct timespec' but 32/64b ABI safe.
@@ -175,17 +184,28 @@ struct drm_msm_gem_submit_bo {
 	__u64 presumed;       /* in/out, presumed buffer address */
 };
 
+/* Valid submit ioctl flags: */
+#define MSM_SUBMIT_NO_IMPLICIT   0x80000000 /* disable implicit sync */
+#define MSM_SUBMIT_FENCE_FD_IN   0x40000000 /* enable input fence_fd */
+#define MSM_SUBMIT_FENCE_FD_OUT  0x20000000 /* enable output fence_fd */
+#define MSM_SUBMIT_FLAGS                ( \
+		MSM_SUBMIT_NO_IMPLICIT   | \
+		MSM_SUBMIT_FENCE_FD_IN   | \
+		MSM_SUBMIT_FENCE_FD_OUT  | \
+		0)
+
 /* 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.
  */
 struct drm_msm_gem_submit {
-	__u32 pipe;           /* in, MSM_PIPE_x */
+	__u32 flags;          /* MSM_PIPE_x | MSM_SUBMIT_x */
 	__u32 fence;          /* out */
 	__u32 nr_bos;         /* in, number of submit_bo's */
 	__u32 nr_cmds;        /* in, number of submit_cmd's */
 	__u64 __user bos;     /* in, ptr to array of submit_bo's */
 	__u64 __user cmds;    /* in, ptr to array of submit_cmd's */
+	__s32 fence_fd;       /* in/out fence fd (see MSM_SUBMIT_FENCE_FD_IN/OUT) */
 };
 
 /* The normal way to synchronize with the GPU is just to CPU_PREP on
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 929aba253764..6965d0909554 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -399,6 +399,7 @@ header-y += string.h
 header-y += suspend_ioctls.h
 header-y += swab.h
 header-y += synclink.h
+header-y += sync_file.h
 header-y += sysctl.h
 header-y += sysinfo.h
 header-y += target_core_user.h
diff --git a/include/uapi/linux/sync_file.h b/include/uapi/linux/sync_file.h
index 413303d37b56..5b287d6970b3 100644
--- a/include/uapi/linux/sync_file.h
+++ b/include/uapi/linux/sync_file.h
@@ -85,15 +85,12 @@ struct sync_file_info {
 #define SYNC_IOC_MERGE		_IOWR(SYNC_IOC_MAGIC, 3, struct sync_merge_data)
 
 /**
- * DOC: SYNC_IOC_FENCE_INFO - get detailed information on a fence
+ * DOC: SYNC_IOC_FILE_INFO - get detailed information on a sync_file
  *
- * Takes a struct sync_file_info_data with extra space allocated for pt_info.
- * Caller should write the size of the buffer into len.  On return, len is
- * updated to reflect the total size of the sync_file_info_data including
- * pt_info.
- *
- * pt_info is a buffer containing sync_pt_infos for every sync_pt in the fence.
- * To iterate over the sync_pt_infos, use the sync_pt_info.len field.
+ * Takes a struct sync_file_info. If num_fences is 0, the field is updated
+ * with the actual number of fences. If num_fences is > 0, the system will
+ * use the pointer provided on sync_fence_info to return up to num_fences of
+ * struct sync_fence_info, with detailed fence information.
  */
 #define SYNC_IOC_FILE_INFO	_IOWR(SYNC_IOC_MAGIC, 4, struct sync_file_info)