[PATCH v2 11/20] drm/amdgpu: round robin through clear_entities in amdgpu_fill_buffer

[Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>]

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>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    | 9 ++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h    | 1 +
 3 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index be3532134e46..33b397107778 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1321,7 +1321,7 @@ 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(NULL, abo, 0, &bo->base._resv,
 			       &fence, NULL, 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 411997db70eb..486c701d0d5b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -2224,6 +2224,7 @@ u32 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_entity;
 
@@ -2489,7 +2490,7 @@ int amdgpu_fill_buffer(struct amdgpu_ttm_buffer_entity *entity,
 	struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
 	struct dma_fence *fence = NULL;
 	struct amdgpu_res_cursor dst;
-	int r;
+	int r, e;
 
 	if (!adev->mman.buffer_funcs_enabled) {
 		dev_err(adev->dev,
@@ -2497,6 +2498,12 @@ int amdgpu_fill_buffer(struct amdgpu_ttm_buffer_entity *entity,
 		return -EINVAL;
 	}
 
+	if (entity == NULL) {
+		e = atomic_inc_return(&adev->mman.next_clear_entity) %
+				      adev->mman.num_clear_entities;
+		entity = &adev->mman.clear_entities[e];
+	}
+
 	amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &dst);
 
 	mutex_lock(&entity->gart_window_lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index e8f8165f5bcf..781b0bdca56c 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 {
 
 	struct amdgpu_ttm_buffer_entity default_entity; /* has no gart windows */
 	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;
-- 
2.43.0