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
  ...

1 files changed, 26 insertions, 59 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 4aa993d19018..e3281cacc586 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -201,39 +201,14 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	bo_size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8)
 		  +  AMDGPU_UVD_STACK_SIZE + AMDGPU_UVD_HEAP_SIZE
 		  +  AMDGPU_UVD_SESSION_SIZE * adev->uvd.max_handles;
-	r = amdgpu_bo_create(adev, bo_size, PAGE_SIZE, true,
-			     AMDGPU_GEM_DOMAIN_VRAM,
-			     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-			     NULL, NULL, &adev->uvd.vcpu_bo);
+	r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE,
+				    AMDGPU_GEM_DOMAIN_VRAM, &adev->uvd.vcpu_bo,
+				    &adev->uvd.gpu_addr, &adev->uvd.cpu_addr);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to allocate UVD bo\n", r);
 		return r;
 	}
 
-	r = amdgpu_bo_reserve(adev->uvd.vcpu_bo, false);
-	if (r) {
-		amdgpu_bo_unref(&adev->uvd.vcpu_bo);
-		dev_err(adev->dev, "(%d) failed to reserve UVD bo\n", r);
-		return r;
-	}
-
-	r = amdgpu_bo_pin(adev->uvd.vcpu_bo, AMDGPU_GEM_DOMAIN_VRAM,
-			  &adev->uvd.gpu_addr);
-	if (r) {
-		amdgpu_bo_unreserve(adev->uvd.vcpu_bo);
-		amdgpu_bo_unref(&adev->uvd.vcpu_bo);
-		dev_err(adev->dev, "(%d) UVD bo pin failed\n", r);
-		return r;
-	}
-
-	r = amdgpu_bo_kmap(adev->uvd.vcpu_bo, &adev->uvd.cpu_addr);
-	if (r) {
-		dev_err(adev->dev, "(%d) UVD map failed\n", r);
-		return r;
-	}
-
-	amdgpu_bo_unreserve(adev->uvd.vcpu_bo);
-
 	ring = &adev->uvd.ring;
 	rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
 	r = amd_sched_entity_init(&ring->sched, &adev->uvd.entity,
@@ -274,22 +249,13 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 
 int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
 {
-	int r;
-
 	kfree(adev->uvd.saved_bo);
 
 	amd_sched_entity_fini(&adev->uvd.ring.sched, &adev->uvd.entity);
 
-	if (adev->uvd.vcpu_bo) {
-		r = amdgpu_bo_reserve(adev->uvd.vcpu_bo, false);
-		if (!r) {
-			amdgpu_bo_kunmap(adev->uvd.vcpu_bo);
-			amdgpu_bo_unpin(adev->uvd.vcpu_bo);
-			amdgpu_bo_unreserve(adev->uvd.vcpu_bo);
-		}
-
-		amdgpu_bo_unref(&adev->uvd.vcpu_bo);
-	}
+	amdgpu_bo_free_kernel(&adev->uvd.vcpu_bo,
+			      &adev->uvd.gpu_addr,
+			      (void **)&adev->uvd.cpu_addr);
 
 	amdgpu_ring_fini(&adev->uvd.ring);
 
@@ -323,7 +289,7 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 	if (!adev->uvd.saved_bo)
 		return -ENOMEM;
 
-	memcpy(adev->uvd.saved_bo, ptr, size);
+	memcpy_fromio(adev->uvd.saved_bo, ptr, size);
 
 	return 0;
 }
@@ -340,7 +306,7 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev)
 	ptr = adev->uvd.cpu_addr;
 
 	if (adev->uvd.saved_bo != NULL) {
-		memcpy(ptr, adev->uvd.saved_bo, size);
+		memcpy_toio(ptr, adev->uvd.saved_bo, size);
 		kfree(adev->uvd.saved_bo);
 		adev->uvd.saved_bo = NULL;
 	} else {
@@ -349,11 +315,11 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev)
 
 		hdr = (const struct common_firmware_header *)adev->uvd.fw->data;
 		offset = le32_to_cpu(hdr->ucode_array_offset_bytes);
-		memcpy(adev->uvd.cpu_addr, (adev->uvd.fw->data) + offset,
-			(adev->uvd.fw->size) - offset);
+		memcpy_toio(adev->uvd.cpu_addr, adev->uvd.fw->data + offset,
+			    le32_to_cpu(hdr->ucode_size_bytes));
 		size -= le32_to_cpu(hdr->ucode_size_bytes);
 		ptr += le32_to_cpu(hdr->ucode_size_bytes);
-		memset(ptr, 0, size);
+		memset_io(ptr, 0, size);
 	}
 
 	return 0;
@@ -385,12 +351,12 @@ void amdgpu_uvd_free_handles(struct amdgpu_device *adev, struct drm_file *filp)
 	}
 }
 
-static void amdgpu_uvd_force_into_uvd_segment(struct amdgpu_bo *rbo)
+static void amdgpu_uvd_force_into_uvd_segment(struct amdgpu_bo *abo)
 {
 	int i;
-	for (i = 0; i < rbo->placement.num_placement; ++i) {
-		rbo->placements[i].fpfn = 0 >> PAGE_SHIFT;
-		rbo->placements[i].lpfn = (256 * 1024 * 1024) >> PAGE_SHIFT;
+	for (i = 0; i < abo->placement.num_placement; ++i) {
+		abo->placements[i].fpfn = 0 >> PAGE_SHIFT;
+		abo->placements[i].lpfn = (256 * 1024 * 1024) >> PAGE_SHIFT;
 	}
 }
 
@@ -843,6 +809,7 @@ static int amdgpu_uvd_cs_reg(struct amdgpu_uvd_cs_ctx *ctx,
 				return r;
 			break;
 		case mmUVD_ENGINE_CNTL:
+		case mmUVD_NO_OP:
 			break;
 		default:
 			DRM_ERROR("Invalid reg 0x%X!\n", reg);
@@ -915,6 +882,10 @@ int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, uint32_t ib_idx)
 		return -EINVAL;
 	}
 
+	r = amdgpu_cs_sysvm_access_required(parser);
+	if (r)
+		return r;
+
 	ctx.parser = parser;
 	ctx.buf_sizes = buf_sizes;
 	ctx.ib_idx = ib_idx;
@@ -981,8 +952,10 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 	ib->ptr[3] = addr >> 32;
 	ib->ptr[4] = PACKET0(mmUVD_GPCOM_VCPU_CMD, 0);
 	ib->ptr[5] = 0;
-	for (i = 6; i < 16; ++i)
-		ib->ptr[i] = PACKET2(0);
+	for (i = 6; i < 16; i += 2) {
+		ib->ptr[i] = PACKET0(mmUVD_NO_OP, 0);
+		ib->ptr[i+1] = 0;
+	}
 	ib->length_dw = 16;
 
 	if (direct) {
@@ -1114,15 +1087,9 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
 {
 	struct amdgpu_device *adev =
 		container_of(work, struct amdgpu_device, uvd.idle_work.work);
-	unsigned i, fences, handles = 0;
-
-	fences = amdgpu_fence_count_emitted(&adev->uvd.ring);
-
-	for (i = 0; i < adev->uvd.max_handles; ++i)
-		if (atomic_read(&adev->uvd.handles[i]))
-			++handles;
+	unsigned fences = amdgpu_fence_count_emitted(&adev->uvd.ring);
 
-	if (fences == 0 && handles == 0) {
+	if (fences == 0) {
 		if (adev->pm.dpm_enabled) {
 			amdgpu_dpm_enable_uvd(adev, false);
 		} else {