Merge tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "Cannonlake and Vega12 support are probably the two major things. This
  pull lacks nouveau, Ben had some unforseen leave and a few other
  blockers so we'll see how things look or maybe leave it for this merge
  window.

  core:
   - Device links to handle sound/gpu pm dependency
   - Color encoding/range properties
   - Plane clipping into plane check helper
   - Backlight helpers
   - DP TP4 + HBR3 helper support

  amdgpu:
   - Vega12 support
   - Enable DC by default on all supported GPUs
   - Powerplay restructuring and cleanup
   - DC bandwidth calc updates
   - DC backlight on pre-DCE11
   - TTM backing store dropping support
   - SR-IOV fixes
   - Adding "wattman" like functionality
   - DC crc support
   - Improved DC dual-link handling

  amdkfd:
   - GPUVM support for dGPU
   - KFD events for dGPU
   - Enable PCIe atomics for dGPUs
   - HSA process eviction support
   - Live-lock fixes for process eviction
   - VM page table allocation fix for large-bar systems

  panel:
   - Raydium RM68200
   - AUO G104SN02 V2
   - KEO TX31D200VM0BAA
   - ARM Versatile panels

  i915:
   - Cannonlake support enabled
   - AUX-F port support added
   - Icelake base enabling until internal milestone of forcewake support
   - Query uAPI interface (used for GPU topology information currently)
   - Compressed framebuffer support for sprites
   - kmem cache shrinking when GPU is idle
   - Avoid boosting GPU when waited item is being processed already
   - Avoid retraining LSPCON link unnecessarily
   - Decrease request signaling latency
   - Deprecation of I915_SET_COLORKEY_NONE
   - Kerneldoc and compiler warning cleanup for upcoming CI enforcements
   - Full range ycbcr toggling
   - HDCP support

  i915/gvt:
   - Big refactor for shadow ppgtt
   - KBL context save/restore via LRI cmd (Weinan)
   - Properly unmap dma for guest page (Changbin)

  vmwgfx:
   - Lots of various improvements

  etnaviv:
   - Use the drm gpu scheduler
   - prep work for GC7000L support

  vc4:
   - fix alpha blending
   - Expose perf counters to userspace

  pl111:
   - Bandwidth checking/limiting
   - Versatile panel support

  sun4i:
   - A83T HDMI support
   - A80 support
   - YUV plane support
   - H3/H5 HDMI support

  omapdrm:
   - HPD support for DVI connector
   - remove lots of static variables

  msm:
   - DSI updates from 10nm / SDM845
   - fix for race condition with a3xx/a4xx fence completion irq
   - some refactoring/prep work for eventual a6xx support (ie. when we
     have a userspace)
   - a5xx debugfs enhancements
   - some mdp5 fixes/cleanups to prepare for eventually merging
     writeback
   - support (ie. when we have a userspace)

  tegra:
   - mmap() fixes for fbdev devices
   - Overlay plane for hw cursor fix
   - dma-buf cache maintenance support

  mali-dp:
   - YUV->RGB conversion support

  rockchip:
   - rk3399/chromebook fixes and improvements

  rcar-du:
   - LVDS support move to drm bridge
   - DT bindings for R8A77995
   - Driver/DT support for R8A77970

  tilcdc:
   - DRM panel support"

* tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux: (1646 commits)
  drm/i915: Fix hibernation with ACPI S0 target state
  drm/i915/execlists: Use a locked clear_bit() for synchronisation with interrupt
  drm/i915: Specify which engines to reset following semaphore/event lockups
  drm/i915/dp: Write to SET_POWER dpcd to enable MST hub.
  drm/amdkfd: Use ordered workqueue to restore processes
  drm/amdgpu: Fix acquiring VM on large-BAR systems
  drm/amd/pp: clean header file hwmgr.h
  drm/amd/pp: use mlck_table.count for array loop index limit
  drm: Fix uabi regression by allowing garbage mode->type from userspace
  drm/amdgpu: Add an ATPX quirk for hybrid laptop
  drm/amdgpu: fix spelling mistake: "asssert" -> "assert"
  drm/amd/pp: Add new asic support in pp_psm.c
  drm/amd/pp: Clean up powerplay code on Vega12
  drm/amd/pp: Add smu irq handlers for legacy asics
  drm/amd/pp: Fix set wrong temperature range on smu7
  drm/amdgpu: Don't change preferred domian when fallback GTT v5
  drm/vmwgfx: Bump version patchlevel and date
  drm/vmwgfx: use monotonic event timestamps
  drm/vmwgfx: Unpin the screen object backup buffer when not used
  drm/vmwgfx: Stricter count of legacy surface device resources
  ...

1 files changed, 49 insertions, 75 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 5c26a8e806b9..627542b22ae4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -68,6 +68,7 @@
 #define FIRMWARE_POLARIS12	"amdgpu/polaris12_uvd.bin"
 
 #define FIRMWARE_VEGA10		"amdgpu/vega10_uvd.bin"
+#define FIRMWARE_VEGA12		"amdgpu/vega12_uvd.bin"
 
 #define mmUVD_GPCOM_VCPU_DATA0_VEGA10 (0x03c4 + 0x7e00)
 #define mmUVD_GPCOM_VCPU_DATA1_VEGA10 (0x03c5 + 0x7e00)
@@ -110,6 +111,7 @@ MODULE_FIRMWARE(FIRMWARE_POLARIS11);
 MODULE_FIRMWARE(FIRMWARE_POLARIS12);
 
 MODULE_FIRMWARE(FIRMWARE_VEGA10);
+MODULE_FIRMWARE(FIRMWARE_VEGA12);
 
 static void amdgpu_uvd_idle_work_handler(struct work_struct *work);
 
@@ -161,11 +163,14 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	case CHIP_POLARIS11:
 		fw_name = FIRMWARE_POLARIS11;
 		break;
+	case CHIP_POLARIS12:
+		fw_name = FIRMWARE_POLARIS12;
+		break;
 	case CHIP_VEGA10:
 		fw_name = FIRMWARE_VEGA10;
 		break;
-	case CHIP_POLARIS12:
-		fw_name = FIRMWARE_POLARIS12;
+	case CHIP_VEGA12:
+		fw_name = FIRMWARE_VEGA12;
 		break;
 	default:
 		return -EINVAL;
@@ -955,37 +960,28 @@ int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, uint32_t ib_idx)
 static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 			       bool direct, struct dma_fence **fence)
 {
-	struct ttm_operation_ctx ctx = { true, false };
-	struct ttm_validate_buffer tv;
-	struct ww_acquire_ctx ticket;
-	struct list_head head;
+	struct amdgpu_device *adev = ring->adev;
+	struct dma_fence *f = NULL;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
-	struct dma_fence *f = NULL;
-	struct amdgpu_device *adev = ring->adev;
-	uint64_t addr;
 	uint32_t data[4];
-	int i, r;
-
-	memset(&tv, 0, sizeof(tv));
-	tv.bo = &bo->tbo;
-
-	INIT_LIST_HEAD(&head);
-	list_add(&tv.head, &head);
+	uint64_t addr;
+	long r;
+	int i;
 
-	r = ttm_eu_reserve_buffers(&ticket, &head, true, NULL);
-	if (r)
-		return r;
+	amdgpu_bo_kunmap(bo);
+	amdgpu_bo_unpin(bo);
 
 	if (!ring->adev->uvd.address_64_bit) {
+		struct ttm_operation_ctx ctx = { true, false };
+
 		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM);
 		amdgpu_uvd_force_into_uvd_segment(bo);
+		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+		if (r)
+			goto err;
 	}
 
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
-	if (r)
-		goto err;
-
 	r = amdgpu_job_alloc_with_ib(adev, 64, &job);
 	if (r)
 		goto err;
@@ -1017,6 +1013,14 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 	ib->length_dw = 16;
 
 	if (direct) {
+		r = reservation_object_wait_timeout_rcu(bo->tbo.resv,
+							true, false,
+							msecs_to_jiffies(10));
+		if (r == 0)
+			r = -ETIMEDOUT;
+		if (r < 0)
+			goto err_free;
+
 		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
 		job->fence = dma_fence_get(f);
 		if (r)
@@ -1024,17 +1028,23 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 
 		amdgpu_job_free(job);
 	} else {
+		r = amdgpu_sync_resv(adev, &job->sync, bo->tbo.resv,
+				     AMDGPU_FENCE_OWNER_UNDEFINED, false);
+		if (r)
+			goto err_free;
+
 		r = amdgpu_job_submit(job, ring, &adev->uvd.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
 		if (r)
 			goto err_free;
 	}
 
-	ttm_eu_fence_buffer_objects(&ticket, &head, f);
+	amdgpu_bo_fence(bo, f, false);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
 
 	if (fence)
 		*fence = dma_fence_get(f);
-	amdgpu_bo_unref(&bo);
 	dma_fence_put(f);
 
 	return 0;
@@ -1043,7 +1053,8 @@ err_free:
 	amdgpu_job_free(job);
 
 err:
-	ttm_eu_backoff_reservation(&ticket, &head);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
 	return r;
 }
 
@@ -1054,31 +1065,16 @@ int amdgpu_uvd_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 			      struct dma_fence **fence)
 {
 	struct amdgpu_device *adev = ring->adev;
-	struct amdgpu_bo *bo;
+	struct amdgpu_bo *bo = NULL;
 	uint32_t *msg;
 	int r, i;
 
-	r = amdgpu_bo_create(adev, 1024, PAGE_SIZE, true,
-			     AMDGPU_GEM_DOMAIN_VRAM,
-			     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
-			     AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS,
-			     NULL, NULL, 0, &bo);
+	r = amdgpu_bo_create_reserved(adev, 1024, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &bo, NULL, (void **)&msg);
 	if (r)
 		return r;
 
-	r = amdgpu_bo_reserve(bo, false);
-	if (r) {
-		amdgpu_bo_unref(&bo);
-		return r;
-	}
-
-	r = amdgpu_bo_kmap(bo, (void **)&msg);
-	if (r) {
-		amdgpu_bo_unreserve(bo);
-		amdgpu_bo_unref(&bo);
-		return r;
-	}
-
 	/* stitch together an UVD create msg */
 	msg[0] = cpu_to_le32(0x00000de4);
 	msg[1] = cpu_to_le32(0x00000000);
@@ -1094,9 +1090,6 @@ int amdgpu_uvd_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 	for (i = 11; i < 1024; ++i)
 		msg[i] = cpu_to_le32(0x0);
 
-	amdgpu_bo_kunmap(bo);
-	amdgpu_bo_unreserve(bo);
-
 	return amdgpu_uvd_send_msg(ring, bo, true, fence);
 }
 
@@ -1104,31 +1097,16 @@ int amdgpu_uvd_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 			       bool direct, struct dma_fence **fence)
 {
 	struct amdgpu_device *adev = ring->adev;
-	struct amdgpu_bo *bo;
+	struct amdgpu_bo *bo = NULL;
 	uint32_t *msg;
 	int r, i;
 
-	r = amdgpu_bo_create(adev, 1024, PAGE_SIZE, true,
-			     AMDGPU_GEM_DOMAIN_VRAM,
-			     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
-			     AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS,
-			     NULL, NULL, 0, &bo);
+	r = amdgpu_bo_create_reserved(adev, 1024, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &bo, NULL, (void **)&msg);
 	if (r)
 		return r;
 
-	r = amdgpu_bo_reserve(bo, false);
-	if (r) {
-		amdgpu_bo_unref(&bo);
-		return r;
-	}
-
-	r = amdgpu_bo_kmap(bo, (void **)&msg);
-	if (r) {
-		amdgpu_bo_unreserve(bo);
-		amdgpu_bo_unref(&bo);
-		return r;
-	}
-
 	/* stitch together an UVD destroy msg */
 	msg[0] = cpu_to_le32(0x00000de4);
 	msg[1] = cpu_to_le32(0x00000002);
@@ -1137,9 +1115,6 @@ int amdgpu_uvd_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 	for (i = 4; i < 1024; ++i)
 		msg[i] = cpu_to_le32(0x0);
 
-	amdgpu_bo_kunmap(bo);
-	amdgpu_bo_unreserve(bo);
-
 	return amdgpu_uvd_send_msg(ring, bo, direct, fence);
 }
 
@@ -1149,9 +1124,6 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
 		container_of(work, struct amdgpu_device, uvd.idle_work.work);
 	unsigned fences = amdgpu_fence_count_emitted(&adev->uvd.ring);
 
-	if (amdgpu_sriov_vf(adev))
-		return;
-
 	if (fences == 0) {
 		if (adev->pm.dpm_enabled) {
 			amdgpu_dpm_enable_uvd(adev, false);
@@ -1171,11 +1143,12 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
 void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	bool set_clocks = !cancel_delayed_work_sync(&adev->uvd.idle_work);
+	bool set_clocks;
 
 	if (amdgpu_sriov_vf(adev))
 		return;
 
+	set_clocks = !cancel_delayed_work_sync(&adev->uvd.idle_work);
 	if (set_clocks) {
 		if (adev->pm.dpm_enabled) {
 			amdgpu_dpm_enable_uvd(adev, true);
@@ -1191,7 +1164,8 @@ void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring)
 
 void amdgpu_uvd_ring_end_use(struct amdgpu_ring *ring)
 {
-	schedule_delayed_work(&ring->adev->uvd.idle_work, UVD_IDLE_TIMEOUT);
+	if (!amdgpu_sriov_vf(ring->adev))
+		schedule_delayed_work(&ring->adev->uvd.idle_work, UVD_IDLE_TIMEOUT);
 }
 
 /**