Merge branch 'drm-next-4.16' of git://people.freedesktop.org/~agd5f/linux into drm-next

First feature request for 4.16.  Highlights:
- RV and Vega header cleanups
- TTM operation context support
- 48 bit GPUVM fixes for Vega/RV
- More smatch fixes
- ECC support for vega10
- Resizeable BAR support
- Multi-display sync support in DC
- SR-IOV fixes
- Various scheduler improvements
- GPU reset fixes and vram lost tracking
- Clean up DC/powerplay interfaces
- DCN display fixes
- Various DC fixes

* 'drm-next-4.16' of git://people.freedesktop.org/~agd5f/linux: (291 commits)
  drm/radeon: Use drm_fb_helper_lastclose() and _poll_changed()
  drm/amdgpu: Use drm_fb_helper_lastclose() and _poll_changed()
  drm/amd/display: Use drm_fb_helper_poll_changed()
  drm/ttm: swap consecutive allocated pooled pages v4
  drm/amdgpu: fix amdgpu_sync_resv v2
  drm/ttm: swap consecutive allocated cached pages v3
  drm/amd/amdgpu: set gtt size according to system memory size only
  drm/amdgpu: Get rid of dep_sync as a seperate object.
  drm/amdgpu: allow specifying vm_block_size for multi level PDs v2
  drm/amdgpu: move validation of the VM size into the VM code
  drm/amdgpu: allow non pot VM size values
  drm/amdgpu: choose number of VM levels based on VM size
  drm/amdgpu: unify VM size handling of Vega10 with older generation
  drm/amdgpu: fix amdgpu_vm_num_entries
  drm/amdgpu: fix VM PD addr shift
  drm/amdgpu: correct vce4.0 fw config for SRIOV (V2)
  drm/amd/display: Don't call dm_log_to_buffer directly in dc_conn_log
  drm/amd/display: Add dm_logger_append_va API
  drm/ttm: Use a static string instead of an array of char *
  drm/amd/display: remove usage of legacy_cursor_update
  ...

1 files changed, 25 insertions, 27 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 0cfc68db575b..bdc210ac74f8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -37,10 +37,7 @@ static void amdgpu_job_timedout(struct amd_sched_job *s_job)
 		  atomic_read(&job->ring->fence_drv.last_seq),
 		  job->ring->fence_drv.sync_seq);
 
-	if (amdgpu_sriov_vf(job->adev))
-		amdgpu_sriov_gpu_reset(job->adev, job);
-	else
-		amdgpu_gpu_reset(job->adev);
+	amdgpu_gpu_recover(job->adev, job);
 }
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
@@ -63,7 +60,6 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
 	(*job)->num_ibs = num_ibs;
 
 	amdgpu_sync_create(&(*job)->sync);
-	amdgpu_sync_create(&(*job)->dep_sync);
 	amdgpu_sync_create(&(*job)->sched_sync);
 	(*job)->vram_lost_counter = atomic_read(&adev->vram_lost_counter);
 
@@ -104,10 +100,9 @@ static void amdgpu_job_free_cb(struct amd_sched_job *s_job)
 {
 	struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base);
 
-	amdgpu_ring_priority_put(job->ring, amd_sched_get_job_priority(s_job));
+	amdgpu_ring_priority_put(job->ring, s_job->s_priority);
 	dma_fence_put(job->fence);
 	amdgpu_sync_free(&job->sync);
-	amdgpu_sync_free(&job->dep_sync);
 	amdgpu_sync_free(&job->sched_sync);
 	kfree(job);
 }
@@ -118,7 +113,6 @@ void amdgpu_job_free(struct amdgpu_job *job)
 
 	dma_fence_put(job->fence);
 	amdgpu_sync_free(&job->sync);
-	amdgpu_sync_free(&job->dep_sync);
 	amdgpu_sync_free(&job->sched_sync);
 	kfree(job);
 }
@@ -141,28 +135,29 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
 	job->fence_ctx = entity->fence_context;
 	*f = dma_fence_get(&job->base.s_fence->finished);
 	amdgpu_job_free_resources(job);
-	amdgpu_ring_priority_get(job->ring,
-				 amd_sched_get_job_priority(&job->base));
-	amd_sched_entity_push_job(&job->base);
+	amdgpu_ring_priority_get(job->ring, job->base.s_priority);
+	amd_sched_entity_push_job(&job->base, entity);
 
 	return 0;
 }
 
-static struct dma_fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)
+static struct dma_fence *amdgpu_job_dependency(struct amd_sched_job *sched_job,
+					       struct amd_sched_entity *s_entity)
 {
 	struct amdgpu_job *job = to_amdgpu_job(sched_job);
 	struct amdgpu_vm *vm = job->vm;
-
-	struct dma_fence *fence = amdgpu_sync_get_fence(&job->dep_sync);
+	bool explicit = false;
 	int r;
-
-	if (amd_sched_dependency_optimized(fence, sched_job->s_entity)) {
-		r = amdgpu_sync_fence(job->adev, &job->sched_sync, fence);
-		if (r)
-			DRM_ERROR("Error adding fence to sync (%d)\n", r);
+	struct dma_fence *fence = amdgpu_sync_get_fence(&job->sync, &explicit);
+
+	if (fence && explicit) {
+		if (amd_sched_dependency_optimized(fence, s_entity)) {
+			r = amdgpu_sync_fence(job->adev, &job->sched_sync, fence, false);
+			if (r)
+				DRM_ERROR("Error adding fence to sync (%d)\n", r);
+		}
 	}
-	if (!fence)
-		fence = amdgpu_sync_get_fence(&job->sync);
+
 	while (fence == NULL && vm && !job->vm_id) {
 		struct amdgpu_ring *ring = job->ring;
 
@@ -172,7 +167,7 @@ static struct dma_fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)
 		if (r)
 			DRM_ERROR("Error getting VM ID (%d)\n", r);
 
-		fence = amdgpu_sync_get_fence(&job->sync);
+		fence = amdgpu_sync_get_fence(&job->sync, NULL);
 	}
 
 	return fence;
@@ -180,7 +175,7 @@ static struct dma_fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)
 
 static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)
 {
-	struct dma_fence *fence = NULL;
+	struct dma_fence *fence = NULL, *finished;
 	struct amdgpu_device *adev;
 	struct amdgpu_job *job;
 	int r;
@@ -190,15 +185,18 @@ static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)
 		return NULL;
 	}
 	job = to_amdgpu_job(sched_job);
+	finished = &job->base.s_fence->finished;
 	adev = job->adev;
 
 	BUG_ON(amdgpu_sync_peek_fence(&job->sync, NULL));
 
 	trace_amdgpu_sched_run_job(job);
-	/* skip ib schedule when vram is lost */
-	if (job->vram_lost_counter != atomic_read(&adev->vram_lost_counter)) {
-		dma_fence_set_error(&job->base.s_fence->finished, -ECANCELED);
-		DRM_ERROR("Skip scheduling IBs!\n");
+
+	if (job->vram_lost_counter != atomic_read(&adev->vram_lost_counter))
+		dma_fence_set_error(finished, -ECANCELED);/* skip IB as well if VRAM lost */
+
+	if (finished->error < 0) {
+		DRM_INFO("Skip scheduling IBs!\n");
 	} else {
 		r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs, job,
 				       &fence);