drm/amdgpu: round robin through clear_entities in amdgpu_fill_buffer

This makes clear of different BOs run in parallel. Partial jobs to
clear a single BO still execute sequentially.

Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

3 files changed, 20 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 029a4bde91e7..27f7567df7bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1325,7 +1325,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
 	if (r)
 		goto out;
 
-	r = amdgpu_fill_buffer(&adev->mman.clear_entities[0], abo, 0, &bo->base._resv,
+	r = amdgpu_fill_buffer(amdgpu_ttm_next_clear_entity(adev),
+			       abo, 0, &bo->base._resv,
 			       &fence, AMDGPU_KERNEL_JOB_ID_CLEAR_ON_RELEASE);
 	if (WARN_ON(r))
 		goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 97448a055125..375c3414b0a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -2369,6 +2369,7 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 		adev->mman.clear_entities = kcalloc(num_clear_entities,
 						    sizeof(struct amdgpu_ttm_buffer_entity),
 						    GFP_KERNEL);
+		atomic_set(&adev->mman.next_clear_entity, 0);
 		if (!adev->mman.clear_entities)
 			goto error_free_default_entity;
 
@@ -2642,11 +2643,8 @@ int amdgpu_fill_buffer(struct amdgpu_ttm_buffer_entity *entity,
 	struct amdgpu_res_cursor dst;
 	int r;
 
-	if (!adev->mman.buffer_funcs_enabled) {
-		dev_err(adev->dev,
-			"Trying to clear memory with ring turned off.\n");
+	if (!entity)
 		return -EINVAL;
-	}
 
 	amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &dst);
 
@@ -2682,6 +2680,20 @@ error:
 	return r;
 }
 
+struct amdgpu_ttm_buffer_entity *
+amdgpu_ttm_next_clear_entity(struct amdgpu_device *adev)
+{
+	struct amdgpu_mman *mman = &adev->mman;
+	u32 i;
+
+	if (mman->num_clear_entities == 0)
+		return NULL;
+
+	i = atomic_inc_return(&mman->next_clear_entity) %
+			      mman->num_clear_entities;
+	return &mman->clear_entities[i];
+}
+
 /**
  * amdgpu_ttm_evict_resources - evict memory buffers
  * @adev: amdgpu device object
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index cd24ca851b6d..cf32db3defb1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -73,6 +73,7 @@ struct amdgpu_mman {
 	/* @default_entity: for workarounds, has no gart windows */
 	struct amdgpu_ttm_buffer_entity default_entity;
 	struct amdgpu_ttm_buffer_entity *clear_entities;
+	atomic_t next_clear_entity;
 	u32 num_clear_entities;
 	struct amdgpu_ttm_buffer_entity move_entities[TTM_NUM_MOVE_FENCES];
 	u32 num_move_entities;
@@ -193,6 +194,7 @@ int amdgpu_fill_buffer(struct amdgpu_ttm_buffer_entity *entity,
 		       struct dma_resv *resv,
 		       struct dma_fence **f,
 		       u64 k_job_id);
+struct amdgpu_ttm_buffer_entity *amdgpu_ttm_next_clear_entity(struct amdgpu_device *adev);
 
 int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo);
 void amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo);