Merge tag 'drm-for-v4.10' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main pull request for drm for 4.10 kernel.

  New drivers:
   - ZTE VOU display driver (zxdrm)
   - Amlogic Meson Graphic Controller GXBB/GXL/GXM SoCs (meson)
   - MXSFB support (mxsfb)

  Core:
   - Format handling has been reworked
   - Better atomic state debugging
   - drm_mm leak debugging
   - Atomic explicit fencing support
   - fbdev helper ops
   - Documentation updates
   - MST fbcon fixes

  Bridge:
   - Silicon Image SiI8620 driver

  Panel:
   - Add support for new simple panels

  i915:
   - GVT Device model
   - Better HDMI2.0 support on skylake
   - More watermark fixes
   - GPU idling rework for suspend/resume
   - DP Audio workarounds
   - Scheduler prep-work
   - Opregion CADL handling
   - GPU scheduler and priority boosting

  amdgfx/radeon:
   - Support for virtual devices
   - New VM manager for non-contig VRAM buffers
   - UVD powergating
   - SI register header cleanup
   - Cursor fixes
   - Powermanagement fixes

  nouveau:
   - Powermangement reworks for better voltage/clock changes
   - Atomic modesetting support
   - Displayport Multistream (MST) support.
   - GP102/104 hang and cursor fixes
   - GP106 support

  hisilicon:
   - hibmc support (BMC chip for aarch64 servers)

  armada:
   - add tracing support for overlay change
   - refactor plane support
   - de-midlayer the driver

  omapdrm:
   - Timing code cleanups

  rcar-du:
   - R8A7792/R8A7796 support
   - Misc fixes.

  sunxi:
   - A31 SoC display engine support

  imx-drm:
   - YUV format support
   - Cleanup plane atomic update

  mali-dp:
   - Misc fixes

  dw-hdmi:
   - Add support for HDMI i2c master controller

  tegra:
   - IOMMU support fixes
   - Error handling fixes

  tda998x:
   - Fix connector registration
   - Improved robustness
   - Fix infoframe/audio compliance

  virtio:
   - fix busid issues
   - allocate more vbufs

  qxl:
   - misc fixes and cleanups.

  vc4:
   - Fragment shader threading
   - ETC1 support
   - VEC (tv-out) support

  msm:
   - A5XX GPU support
   - Lots of atomic changes

  tilcdc:
   - Misc fixes and cleanups.

  etnaviv:
   - Fix dma-buf export path
   - DRAW_INSTANCED support
   - fix driver on i.MX6SX

  exynos:
   - HDMI refactoring

  fsl-dcu:
   - fbdev changes"

* tag 'drm-for-v4.10' of git://people.freedesktop.org/~airlied/linux: (1343 commits)
  drm/nouveau/kms/nv50: fix atomic regression on original G80
  drm/nouveau/bl: Do not register interface if Apple GMUX detected
  drm/nouveau/bl: Assign different names to interfaces
  drm/nouveau/bios/dp: fix handling of LevelEntryTableIndex on DP table 4.2
  drm/nouveau/ltc: protect clearing of comptags with mutex
  drm/nouveau/gr/gf100-: handle GPC/TPC/MPC trap
  drm/nouveau/core: recognise GP106 chipset
  drm/nouveau/ttm: wait for bo fence to signal before unmapping vmas
  drm/nouveau/gr/gf100-: FECS intr handling is not relevant on proprietary ucode
  drm/nouveau/gr/gf100-: properly ack all FECS error interrupts
  drm/nouveau/fifo/gf100-: recover from host mmu faults
  drm: Add fake controlD* symlinks for backwards compat
  drm/vc4: Don't use drm_put_dev
  drm/vc4: Document VEC DT binding
  drm/vc4: Add support for the VEC (Video Encoder) IP
  drm: Add TV connector states to drm_connector_state
  drm: Turn DRM_MODE_SUBCONNECTOR_xx definitions into an enum
  drm/vc4: Fix ->clock_select setting for the VEC encoder
  drm/amdgpu/dce6: Set MASTER_UPDATE_MODE to 0 in resume_mc_access as well
  drm/amdgpu: use pin rather than pin_restricted in a few cases
  ...

1 files changed, 248 insertions, 59 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 82dc8d20e28a..29d6d84d1c28 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -355,6 +355,7 @@ static void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev,
 static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
 				 struct amdgpu_bo *bo)
 {
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	u64 initial_bytes_moved;
 	uint32_t domain;
 	int r;
@@ -372,9 +373,9 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
 
 retry:
 	amdgpu_ttm_placement_from_domain(bo, domain);
-	initial_bytes_moved = atomic64_read(&bo->adev->num_bytes_moved);
+	initial_bytes_moved = atomic64_read(&adev->num_bytes_moved);
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
-	p->bytes_moved += atomic64_read(&bo->adev->num_bytes_moved) -
+	p->bytes_moved += atomic64_read(&adev->num_bytes_moved) -
 		initial_bytes_moved;
 
 	if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) {
@@ -387,9 +388,9 @@ retry:
 
 /* Last resort, try to evict something from the current working set */
 static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
-				struct amdgpu_bo_list_entry *lobj)
+				struct amdgpu_bo *validated)
 {
-	uint32_t domain = lobj->robj->allowed_domains;
+	uint32_t domain = validated->allowed_domains;
 	int r;
 
 	if (!p->evictable)
@@ -400,11 +401,12 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 
 		struct amdgpu_bo_list_entry *candidate = p->evictable;
 		struct amdgpu_bo *bo = candidate->robj;
+		struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 		u64 initial_bytes_moved;
 		uint32_t other;
 
 		/* If we reached our current BO we can forget it */
-		if (candidate == lobj)
+		if (candidate->robj == validated)
 			break;
 
 		other = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
@@ -420,9 +422,9 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 
 		/* Good we can try to move this BO somewhere else */
 		amdgpu_ttm_placement_from_domain(bo, other);
-		initial_bytes_moved = atomic64_read(&bo->adev->num_bytes_moved);
+		initial_bytes_moved = atomic64_read(&adev->num_bytes_moved);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
-		p->bytes_moved += atomic64_read(&bo->adev->num_bytes_moved) -
+		p->bytes_moved += atomic64_read(&adev->num_bytes_moved) -
 			initial_bytes_moved;
 
 		if (unlikely(r))
@@ -437,6 +439,23 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 	return false;
 }
 
+static int amdgpu_cs_validate(void *param, struct amdgpu_bo *bo)
+{
+	struct amdgpu_cs_parser *p = param;
+	int r;
+
+	do {
+		r = amdgpu_cs_bo_validate(p, bo);
+	} while (r == -ENOMEM && amdgpu_cs_try_evict(p, bo));
+	if (r)
+		return r;
+
+	if (bo->shadow)
+		r = amdgpu_cs_bo_validate(p, bo->shadow);
+
+	return r;
+}
+
 static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 			    struct list_head *validated)
 {
@@ -464,18 +483,10 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 		if (p->evictable == lobj)
 			p->evictable = NULL;
 
-		do {
-			r = amdgpu_cs_bo_validate(p, bo);
-		} while (r == -ENOMEM && amdgpu_cs_try_evict(p, lobj));
+		r = amdgpu_cs_validate(p, bo);
 		if (r)
 			return r;
 
-		if (bo->shadow) {
-			r = amdgpu_cs_bo_validate(p, bo);
-			if (r)
-				return r;
-		}
-
 		if (binding_userptr) {
 			drm_free_large(lobj->user_pages);
 			lobj->user_pages = NULL;
@@ -594,14 +605,19 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		list_splice(&need_pages, &p->validated);
 	}
 
-	amdgpu_vm_get_pt_bos(p->adev, &fpriv->vm, &duplicates);
-
 	p->bytes_moved_threshold = amdgpu_cs_get_threshold_for_moves(p->adev);
 	p->bytes_moved = 0;
 	p->evictable = list_last_entry(&p->validated,
 				       struct amdgpu_bo_list_entry,
 				       tv.head);
 
+	r = amdgpu_vm_validate_pt_bos(p->adev, &fpriv->vm,
+				      amdgpu_cs_validate, p);
+	if (r) {
+		DRM_ERROR("amdgpu_vm_validate_pt_bos() failed.\n");
+		goto error_validate;
+	}
+
 	r = amdgpu_cs_list_validate(p, &duplicates);
 	if (r) {
 		DRM_ERROR("amdgpu_cs_list_validate(duplicates) failed.\n");
@@ -720,7 +736,7 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bo
 		ttm_eu_backoff_reservation(&parser->ticket,
 					   &parser->validated);
 	}
-	fence_put(parser->fence);
+	dma_fence_put(parser->fence);
 
 	if (parser->ctx)
 		amdgpu_ctx_put(parser->ctx);
@@ -757,7 +773,7 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p,
 
 	if (p->bo_list) {
 		for (i = 0; i < p->bo_list->num_entries; i++) {
-			struct fence *f;
+			struct dma_fence *f;
 
 			/* ignore duplicates */
 			bo = p->bo_list->array[i].robj;
@@ -807,13 +823,14 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 
 	/* Only for UVD/VCE VM emulation */
 	if (ring->funcs->parse_cs) {
-		p->job->vm = NULL;
 		for (i = 0; i < p->job->num_ibs; i++) {
 			r = amdgpu_ring_parse_cs(ring, p, i);
 			if (r)
 				return r;
 		}
-	} else {
+	}
+
+	if (p->job->vm) {
 		p->job->vm_pd_addr = amdgpu_bo_gpu_offset(vm->page_directory);
 
 		r = amdgpu_bo_vm_update_pte(p, vm);
@@ -824,16 +841,6 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 	return amdgpu_cs_sync_rings(p);
 }
 
-static int amdgpu_cs_handle_lockup(struct amdgpu_device *adev, int r)
-{
-	if (r == -EDEADLK) {
-		r = amdgpu_gpu_reset(adev);
-		if (!r)
-			r = -EAGAIN;
-	}
-	return r;
-}
-
 static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 			     struct amdgpu_cs_parser *parser)
 {
@@ -902,7 +909,7 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 			offset = ((uint64_t)m->it.start) * AMDGPU_GPU_PAGE_SIZE;
 			kptr += chunk_ib->va_start - offset;
 
-			r =  amdgpu_ib_get(adev, NULL, chunk_ib->ib_bytes, ib);
+			r =  amdgpu_ib_get(adev, vm, chunk_ib->ib_bytes, ib);
 			if (r) {
 				DRM_ERROR("Failed to get ib !\n");
 				return r;
@@ -917,9 +924,9 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 				return r;
 			}
 
-			ib->gpu_addr = chunk_ib->va_start;
 		}
 
+		ib->gpu_addr = chunk_ib->va_start;
 		ib->length_dw = chunk_ib->ib_bytes / 4;
 		ib->flags = chunk_ib->flags;
 		j++;
@@ -927,8 +934,8 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 
 	/* UVD & VCE fw doesn't support user fences */
 	if (parser->job->uf_addr && (
-	    parser->job->ring->type == AMDGPU_RING_TYPE_UVD ||
-	    parser->job->ring->type == AMDGPU_RING_TYPE_VCE))
+	    parser->job->ring->funcs->type == AMDGPU_RING_TYPE_UVD ||
+	    parser->job->ring->funcs->type == AMDGPU_RING_TYPE_VCE))
 		return -EINVAL;
 
 	return 0;
@@ -957,7 +964,7 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 		for (j = 0; j < num_deps; ++j) {
 			struct amdgpu_ring *ring;
 			struct amdgpu_ctx *ctx;
-			struct fence *fence;
+			struct dma_fence *fence;
 
 			r = amdgpu_cs_get_ring(adev, deps[j].ip_type,
 					       deps[j].ip_instance,
@@ -979,7 +986,7 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 			} else if (fence) {
 				r = amdgpu_sync_fence(adev, &p->job->sync,
 						      fence);
-				fence_put(fence);
+				dma_fence_put(fence);
 				amdgpu_ctx_put(ctx);
 				if (r)
 					return r;
@@ -1009,7 +1016,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 
 	job->owner = p->filp;
 	job->fence_ctx = entity->fence_context;
-	p->fence = fence_get(&job->base.s_fence->finished);
+	p->fence = dma_fence_get(&job->base.s_fence->finished);
 	cs->out.handle = amdgpu_ctx_add_fence(p->ctx, ring, p->fence);
 	job->uf_sequence = cs->out.handle;
 	amdgpu_job_free_resources(job);
@@ -1037,29 +1044,29 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	r = amdgpu_cs_parser_init(&parser, data);
 	if (r) {
 		DRM_ERROR("Failed to initialize parser !\n");
-		amdgpu_cs_parser_fini(&parser, r, false);
-		r = amdgpu_cs_handle_lockup(adev, r);
-		return r;
-	}
-	r = amdgpu_cs_parser_bos(&parser, data);
-	if (r == -ENOMEM)
-		DRM_ERROR("Not enough memory for command submission!\n");
-	else if (r && r != -ERESTARTSYS)
-		DRM_ERROR("Failed to process the buffer list %d!\n", r);
-	else if (!r) {
-		reserved_buffers = true;
-		r = amdgpu_cs_ib_fill(adev, &parser);
+		goto out;
 	}
 
-	if (!r) {
-		r = amdgpu_cs_dependencies(adev, &parser);
-		if (r)
-			DRM_ERROR("Failed in the dependencies handling %d!\n", r);
+	r = amdgpu_cs_parser_bos(&parser, data);
+	if (r) {
+		if (r == -ENOMEM)
+			DRM_ERROR("Not enough memory for command submission!\n");
+		else if (r != -ERESTARTSYS)
+			DRM_ERROR("Failed to process the buffer list %d!\n", r);
+		goto out;
 	}
 
+	reserved_buffers = true;
+	r = amdgpu_cs_ib_fill(adev, &parser);
 	if (r)
 		goto out;
 
+	r = amdgpu_cs_dependencies(adev, &parser);
+	if (r) {
+		DRM_ERROR("Failed in the dependencies handling %d!\n", r);
+		goto out;
+	}
+
 	for (i = 0; i < parser.job->num_ibs; i++)
 		trace_amdgpu_cs(&parser, i);
 
@@ -1071,7 +1078,6 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 out:
 	amdgpu_cs_parser_fini(&parser, r, reserved_buffers);
-	r = amdgpu_cs_handle_lockup(adev, r);
 	return r;
 }
 
@@ -1092,7 +1098,7 @@ int amdgpu_cs_wait_ioctl(struct drm_device *dev, void *data,
 	unsigned long timeout = amdgpu_gem_timeout(wait->in.timeout);
 	struct amdgpu_ring *ring = NULL;
 	struct amdgpu_ctx *ctx;
-	struct fence *fence;
+	struct dma_fence *fence;
 	long r;
 
 	r = amdgpu_cs_get_ring(adev, wait->in.ip_type, wait->in.ip_instance,
@@ -1108,8 +1114,8 @@ int amdgpu_cs_wait_ioctl(struct drm_device *dev, void *data,
 	if (IS_ERR(fence))
 		r = PTR_ERR(fence);
 	else if (fence) {
-		r = fence_wait_timeout(fence, true, timeout);
-		fence_put(fence);
+		r = dma_fence_wait_timeout(fence, true, timeout);
+		dma_fence_put(fence);
 	} else
 		r = 1;
 
@@ -1124,6 +1130,180 @@ int amdgpu_cs_wait_ioctl(struct drm_device *dev, void *data,
 }
 
 /**
+ * amdgpu_cs_get_fence - helper to get fence from drm_amdgpu_fence
+ *
+ * @adev: amdgpu device
+ * @filp: file private
+ * @user: drm_amdgpu_fence copied from user space
+ */
+static struct dma_fence *amdgpu_cs_get_fence(struct amdgpu_device *adev,
+					     struct drm_file *filp,
+					     struct drm_amdgpu_fence *user)
+{
+	struct amdgpu_ring *ring;
+	struct amdgpu_ctx *ctx;
+	struct dma_fence *fence;
+	int r;
+
+	r = amdgpu_cs_get_ring(adev, user->ip_type, user->ip_instance,
+			       user->ring, &ring);
+	if (r)
+		return ERR_PTR(r);
+
+	ctx = amdgpu_ctx_get(filp->driver_priv, user->ctx_id);
+	if (ctx == NULL)
+		return ERR_PTR(-EINVAL);
+
+	fence = amdgpu_ctx_get_fence(ctx, ring, user->seq_no);
+	amdgpu_ctx_put(ctx);
+
+	return fence;
+}
+
+/**
+ * amdgpu_cs_wait_all_fence - wait on all fences to signal
+ *
+ * @adev: amdgpu device
+ * @filp: file private
+ * @wait: wait parameters
+ * @fences: array of drm_amdgpu_fence
+ */
+static int amdgpu_cs_wait_all_fences(struct amdgpu_device *adev,
+				     struct drm_file *filp,
+				     union drm_amdgpu_wait_fences *wait,
+				     struct drm_amdgpu_fence *fences)
+{
+	uint32_t fence_count = wait->in.fence_count;
+	unsigned int i;
+	long r = 1;
+
+	for (i = 0; i < fence_count; i++) {
+		struct dma_fence *fence;
+		unsigned long timeout = amdgpu_gem_timeout(wait->in.timeout_ns);
+
+		fence = amdgpu_cs_get_fence(adev, filp, &fences[i]);
+		if (IS_ERR(fence))
+			return PTR_ERR(fence);
+		else if (!fence)
+			continue;
+
+		r = dma_fence_wait_timeout(fence, true, timeout);
+		if (r < 0)
+			return r;
+
+		if (r == 0)
+			break;
+	}
+
+	memset(wait, 0, sizeof(*wait));
+	wait->out.status = (r > 0);
+
+	return 0;
+}
+
+/**
+ * amdgpu_cs_wait_any_fence - wait on any fence to signal
+ *
+ * @adev: amdgpu device
+ * @filp: file private
+ * @wait: wait parameters
+ * @fences: array of drm_amdgpu_fence
+ */
+static int amdgpu_cs_wait_any_fence(struct amdgpu_device *adev,
+				    struct drm_file *filp,
+				    union drm_amdgpu_wait_fences *wait,
+				    struct drm_amdgpu_fence *fences)
+{
+	unsigned long timeout = amdgpu_gem_timeout(wait->in.timeout_ns);
+	uint32_t fence_count = wait->in.fence_count;
+	uint32_t first = ~0;
+	struct dma_fence **array;
+	unsigned int i;
+	long r;
+
+	/* Prepare the fence array */
+	array = kcalloc(fence_count, sizeof(struct dma_fence *), GFP_KERNEL);
+
+	if (array == NULL)
+		return -ENOMEM;
+
+	for (i = 0; i < fence_count; i++) {
+		struct dma_fence *fence;
+
+		fence = amdgpu_cs_get_fence(adev, filp, &fences[i]);
+		if (IS_ERR(fence)) {
+			r = PTR_ERR(fence);
+			goto err_free_fence_array;
+		} else if (fence) {
+			array[i] = fence;
+		} else { /* NULL, the fence has been already signaled */
+			r = 1;
+			goto out;
+		}
+	}
+
+	r = dma_fence_wait_any_timeout(array, fence_count, true, timeout,
+				       &first);
+	if (r < 0)
+		goto err_free_fence_array;
+
+out:
+	memset(wait, 0, sizeof(*wait));
+	wait->out.status = (r > 0);
+	wait->out.first_signaled = first;
+	/* set return value 0 to indicate success */
+	r = 0;
+
+err_free_fence_array:
+	for (i = 0; i < fence_count; i++)
+		dma_fence_put(array[i]);
+	kfree(array);
+
+	return r;
+}
+
+/**
+ * amdgpu_cs_wait_fences_ioctl - wait for multiple command submissions to finish
+ *
+ * @dev: drm device
+ * @data: data from userspace
+ * @filp: file private
+ */
+int amdgpu_cs_wait_fences_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *filp)
+{
+	struct amdgpu_device *adev = dev->dev_private;
+	union drm_amdgpu_wait_fences *wait = data;
+	uint32_t fence_count = wait->in.fence_count;
+	struct drm_amdgpu_fence *fences_user;
+	struct drm_amdgpu_fence *fences;
+	int r;
+
+	/* Get the fences from userspace */
+	fences = kmalloc_array(fence_count, sizeof(struct drm_amdgpu_fence),
+			GFP_KERNEL);
+	if (fences == NULL)
+		return -ENOMEM;
+
+	fences_user = (void __user *)(unsigned long)(wait->in.fences);
+	if (copy_from_user(fences, fences_user,
+		sizeof(struct drm_amdgpu_fence) * fence_count)) {
+		r = -EFAULT;
+		goto err_free_fences;
+	}
+
+	if (wait->in.wait_all)
+		r = amdgpu_cs_wait_all_fences(adev, filp, wait, fences);
+	else
+		r = amdgpu_cs_wait_any_fence(adev, filp, wait, fences);
+
+err_free_fences:
+	kfree(fences);
+
+	return r;
+}
+
+/**
  * amdgpu_cs_find_bo_va - find bo_va for VM address
  *
  * @parser: command submission parser context
@@ -1196,6 +1376,15 @@ int amdgpu_cs_sysvm_access_required(struct amdgpu_cs_parser *parser)
 		r = amdgpu_ttm_bind(&bo->tbo, &bo->tbo.mem);
 		if (unlikely(r))
 			return r;
+
+		if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)
+			continue;
+
+		bo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
+		amdgpu_ttm_placement_from_domain(bo, bo->allowed_domains);
+		r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
+		if (unlikely(r))
+			return r;
 	}
 
 	return 0;