Merge tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This seems to have been a comparatively quieter merge window, I assume
  due to holidays etc. The "biggest" change is AMD header cleanups, which
  merge/remove a bunch of them. The AMD gpu scheduler is now being made generic
  with the etnaviv driver wanting to reuse the code, hopefully other drivers
  can go in the same direction.

  Otherwise it's the usual lots of stuff in i915/amdgpu, not so much stuff
  elsewhere.

  Core:
   - Add .last_close and .output_poll_changed helpers to reduce driver footprints
   - Fix plane clipping
   - Improved debug printing support
   - Add panel orientation property
   - Update edid derived properties at edid setting
   - Reduction in fbdev driver footprint
   - Move amdgpu scheduler into core for other drivers to use.

  i915:
   - Selftest and IGT improvements
   - Fast boot prep work on IPS, pipe config
   - HW workarounds for Cannonlake, Geminilake
   - Cannonlake clock and HDMI2.0 fixes
   - GPU cache invalidation and context switch improvements
   - Display planes cleanup
   - New PMU interface for perf queries
   - New firmware support for KBL/SKL
   - Geminilake HW workaround for perforamce
   - Coffeelake stolen memory improvements
   - GPU reset robustness work
   - Cannonlake horizontal plane flipping
   - GVT work

  amdgpu/radeon:
   - RV and Vega header file cleanups (lots of lines gone!)
   - TTM operation context support
   - 48-bit GPUVM support for Vega/RV
   - ECC support for Vega
   - Resizeable BAR support
   - Multi-display sync support
   - Enable swapout for reserved BOs during allocation
   - S3 fixes on Raven
   - GPU reset cleanup and fixes
   - 2+1 level GPU page table

  amdkfd:
   - GFX7/8 SDMA user queues support
   - Hardware scheduling for multiple processes
   - dGPU prep work

  rcar:
   - Added R8A7743/5 support
   - System suspend/resume support

  sun4i:
   - Multi-plane support for YUV formats
   - A83T and LVDS support

  msm:
   - Devfreq support for GPU

  tegra:
   - Prep work for adding Tegra186 support
   - Tegra186 HDMI support
   - HDMI2.0 and zpos support by using generic helpers

  tilcdc:
   - Misc fixes

  omapdrm:
   - Support memory bandwidth limits
   - DSI command mode panel cleanups
   - DMM error handling

  exynos:
   - drop the old IPP subdriver.

  etnaviv:
   - Occlusion query fixes
   - Job handling fixes
   - Prep work for hooking in gpu scheduler

  armada:
   - Move closer to atomic modesetting
   - Allow disabling primary plane if overlay is full screen

  imx:
   - Format modifier support
   - Add tile prefetch to PRE
   - Runtime PM support for PRG

  ast:
   - fix LUT loading"

* tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux: (1471 commits)
  drm/ast: Load lut in crtc_commit
  drm: Check for lessee in DROP_MASTER ioctl
  drm: fix gpu scheduler link order
  drm/amd/display: Demote error print to debug print when ATOM impl missing
  dma-buf: fix reservation_object_wait_timeout_rcu once more v2
  drm/amdgpu: Avoid leaking PM domain on driver unbind (v2)
  drm/amd/amdgpu: Add Polaris version check
  drm/amdgpu: Reenable manual GPU reset from sysfs
  drm/amdgpu: disable MMHUB power gating on raven
  drm/ttm: Don't unreserve swapped BOs that were previously reserved
  drm/ttm: Don't add swapped BOs to swap-LRU list
  drm/amdgpu: only check for ECC on Vega10
  drm/amd/powerplay: Fix smu_table_entry.handle type
  drm/ttm: add VADDR_FLAG_UPDATED_COUNT to correctly update dma_page global count
  drm: Fix PANEL_ORIENTATION_QUIRKS breaking the Kconfig DRM menuconfig
  drm/radeon: fill in rb backend map on evergreen/ni.
  drm/amdgpu/gfx9: fix ngg enablement to clear gds reserved memory (v2)
  drm/ttm: only free pages rather than update global memory count together
  drm/amdgpu: fix CPU based VM updates
  drm/amdgpu: fix typo in amdgpu_vce_validate_bo
  ...

1 files changed, 44 insertions, 35 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 57abf7abd7a9..e80fc38141b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -90,6 +90,12 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 		goto free_chunk;
 	}
 
+	/* skip guilty context job */
+	if (atomic_read(&p->ctx->guilty) == 1) {
+		ret = -ECANCELED;
+		goto free_chunk;
+	}
+
 	mutex_lock(&p->ctx->lock);
 
 	/* get chunks */
@@ -337,7 +343,12 @@ 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, bytes_moved;
+	struct ttm_operation_ctx ctx = {
+		.interruptible = true,
+		.no_wait_gpu = false,
+		.allow_reserved_eviction = false,
+		.resv = bo->tbo.resv
+	};
 	uint32_t domain;
 	int r;
 
@@ -367,15 +378,13 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
 
 retry:
 	amdgpu_ttm_placement_from_domain(bo, domain);
-	initial_bytes_moved = atomic64_read(&adev->num_bytes_moved);
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
-	bytes_moved = atomic64_read(&adev->num_bytes_moved) -
-		      initial_bytes_moved;
-	p->bytes_moved += bytes_moved;
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+
+	p->bytes_moved += ctx.bytes_moved;
 	if (adev->mc.visible_vram_size < adev->mc.real_vram_size &&
 	    bo->tbo.mem.mem_type == TTM_PL_VRAM &&
 	    bo->tbo.mem.start < adev->mc.visible_vram_size >> PAGE_SHIFT)
-		p->bytes_moved_vis += bytes_moved;
+		p->bytes_moved_vis += ctx.bytes_moved;
 
 	if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) {
 		domain = bo->allowed_domains;
@@ -390,6 +399,7 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 				struct amdgpu_bo *validated)
 {
 	uint32_t domain = validated->allowed_domains;
+	struct ttm_operation_ctx ctx = { true, false };
 	int r;
 
 	if (!p->evictable)
@@ -431,7 +441,7 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 			bo->tbo.mem.mem_type == TTM_PL_VRAM &&
 			bo->tbo.mem.start < adev->mc.visible_vram_size >> PAGE_SHIFT;
 		initial_bytes_moved = atomic64_read(&adev->num_bytes_moved);
-		r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
+		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		bytes_moved = atomic64_read(&adev->num_bytes_moved) -
 			initial_bytes_moved;
 		p->bytes_moved += bytes_moved;
@@ -470,6 +480,7 @@ static int amdgpu_cs_validate(void *param, struct amdgpu_bo *bo)
 static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 			    struct list_head *validated)
 {
+	struct ttm_operation_ctx ctx = { true, false };
 	struct amdgpu_bo_list_entry *lobj;
 	int r;
 
@@ -487,8 +498,7 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 		    lobj->user_pages) {
 			amdgpu_ttm_placement_from_domain(bo,
 							 AMDGPU_GEM_DOMAIN_CPU);
-			r = ttm_bo_validate(&bo->tbo, &bo->placement, true,
-					    false);
+			r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 			if (r)
 				return r;
 			amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm,
@@ -678,7 +688,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	if (!r && p->uf_entry.robj) {
 		struct amdgpu_bo *uf = p->uf_entry.robj;
 
-		r = amdgpu_ttm_bind(&uf->tbo, &uf->tbo.mem);
+		r = amdgpu_ttm_alloc_gart(&uf->tbo);
 		p->job->uf_addr += amdgpu_bo_gpu_offset(uf);
 	}
 
@@ -768,10 +778,6 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 	struct amdgpu_bo *bo;
 	int i, r;
 
-	r = amdgpu_vm_update_directories(adev, vm);
-	if (r)
-		return r;
-
 	r = amdgpu_vm_clear_freed(adev, vm, NULL);
 	if (r)
 		return r;
@@ -781,7 +787,7 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 		return r;
 
 	r = amdgpu_sync_fence(adev, &p->job->sync,
-			      fpriv->prt_va->last_pt_update);
+			      fpriv->prt_va->last_pt_update, false);
 	if (r)
 		return r;
 
@@ -795,7 +801,7 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 			return r;
 
 		f = bo_va->last_pt_update;
-		r = amdgpu_sync_fence(adev, &p->job->sync, f);
+		r = amdgpu_sync_fence(adev, &p->job->sync, f, false);
 		if (r)
 			return r;
 	}
@@ -818,7 +824,7 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 				return r;
 
 			f = bo_va->last_pt_update;
-			r = amdgpu_sync_fence(adev, &p->job->sync, f);
+			r = amdgpu_sync_fence(adev, &p->job->sync, f, false);
 			if (r)
 				return r;
 		}
@@ -829,7 +835,11 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_sync_fence(adev, &p->job->sync, vm->last_update);
+	r = amdgpu_vm_update_directories(adev, vm);
+	if (r)
+		return r;
+
+	r = amdgpu_sync_fence(adev, &p->job->sync, vm->last_update, false);
 	if (r)
 		return r;
 
@@ -865,8 +875,8 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 			struct amdgpu_bo_va_mapping *m;
 			struct amdgpu_bo *aobj = NULL;
 			struct amdgpu_cs_chunk *chunk;
+			uint64_t offset, va_start;
 			struct amdgpu_ib *ib;
-			uint64_t offset;
 			uint8_t *kptr;
 
 			chunk = &p->chunks[i];
@@ -876,14 +886,14 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 			if (chunk->chunk_id != AMDGPU_CHUNK_ID_IB)
 				continue;
 
-			r = amdgpu_cs_find_mapping(p, chunk_ib->va_start,
-						   &aobj, &m);
+			va_start = chunk_ib->va_start & AMDGPU_VA_HOLE_MASK;
+			r = amdgpu_cs_find_mapping(p, va_start, &aobj, &m);
 			if (r) {
 				DRM_ERROR("IB va_start is invalid\n");
 				return r;
 			}
 
-			if ((chunk_ib->va_start + chunk_ib->ib_bytes) >
+			if ((va_start + chunk_ib->ib_bytes) >
 			    (m->last + 1) * AMDGPU_GPU_PAGE_SIZE) {
 				DRM_ERROR("IB va_start+ib_bytes is invalid\n");
 				return -EINVAL;
@@ -896,7 +906,7 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 			}
 
 			offset = m->start * AMDGPU_GPU_PAGE_SIZE;
-			kptr += chunk_ib->va_start - offset;
+			kptr += va_start - offset;
 
 			memcpy(ib->ptr, kptr, chunk_ib->ib_bytes);
 			amdgpu_bo_kunmap(aobj);
@@ -1033,8 +1043,8 @@ static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p,
 			amdgpu_ctx_put(ctx);
 			return r;
 		} else if (fence) {
-			r = amdgpu_sync_fence(p->adev, &p->job->sync,
-					      fence);
+			r = amdgpu_sync_fence(p->adev, &p->job->sync, fence,
+					true);
 			dma_fence_put(fence);
 			amdgpu_ctx_put(ctx);
 			if (r)
@@ -1053,7 +1063,7 @@ static int amdgpu_syncobj_lookup_and_add_to_sync(struct amdgpu_cs_parser *p,
 	if (r)
 		return r;
 
-	r = amdgpu_sync_fence(p->adev, &p->job->sync, fence);
+	r = amdgpu_sync_fence(p->adev, &p->job->sync, fence, true);
 	dma_fence_put(fence);
 
 	return r;
@@ -1145,7 +1155,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 			    union drm_amdgpu_cs *cs)
 {
 	struct amdgpu_ring *ring = p->job->ring;
-	struct amd_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
+	struct drm_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
 	struct amdgpu_job *job;
 	unsigned i;
 	uint64_t seq;
@@ -1168,7 +1178,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	job = p->job;
 	p->job = NULL;
 
-	r = amd_sched_job_init(&job->base, &ring->sched, entity, p->filp);
+	r = drm_sched_job_init(&job->base, &ring->sched, entity, p->filp);
 	if (r) {
 		amdgpu_job_free(job);
 		amdgpu_mn_unlock(p->mn);
@@ -1194,11 +1204,10 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	job->uf_sequence = seq;
 
 	amdgpu_job_free_resources(job);
-	amdgpu_ring_priority_get(job->ring,
-				 amd_sched_get_job_priority(&job->base));
+	amdgpu_ring_priority_get(job->ring, job->base.s_priority);
 
 	trace_amdgpu_cs_ioctl(job);
-	amd_sched_entity_push_job(&job->base);
+	drm_sched_entity_push_job(&job->base, entity);
 
 	ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence);
 	amdgpu_mn_unlock(p->mn);
@@ -1570,6 +1579,7 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser,
 			   struct amdgpu_bo_va_mapping **map)
 {
 	struct amdgpu_fpriv *fpriv = parser->filp->driver_priv;
+	struct ttm_operation_ctx ctx = { false, false };
 	struct amdgpu_vm *vm = &fpriv->vm;
 	struct amdgpu_bo_va_mapping *mapping;
 	int r;
@@ -1590,11 +1600,10 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser,
 	if (!((*bo)->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) {
 		(*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);
+		r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx);
 		if (r)
 			return r;
 	}
 
-	return amdgpu_ttm_bind(&(*bo)->tbo, &(*bo)->tbo.mem);
+	return amdgpu_ttm_alloc_gart(&(*bo)->tbo);
 }