[PATCH v3 27/28] drm/amdgpu: get rid of amdgpu_ttm_clear_buffer

Pierre-Eric Pelloux-Prayer posted 28 patches 1 week, 3 days ago
[PATCH v3 27/28] drm/amdgpu: get rid of amdgpu_ttm_clear_buffer
Posted by Pierre-Eric Pelloux-Prayer 1 week, 3 days ago
It's doing the same thing as amdgpu_fill_buffer(src_data=0), so drop it.

The only caveat is that amdgpu_res_cleared() return value is only valid
right after allocation.

---
v2: introduce new "bool consider_clear_status" arg
---

Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 16 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    | 90 +++++-----------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h    |  7 +-
 3 files changed, 33 insertions(+), 80 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 7d8d70135cc2..dccc31d0128e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -725,13 +725,17 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 	    bo->tbo.resource->mem_type == TTM_PL_VRAM) {
 		struct dma_fence *fence;
 
-		r = amdgpu_ttm_clear_buffer(adev, bo, bo->tbo.base.resv, &fence);
+		r = amdgpu_fill_buffer(adev, amdgpu_ttm_next_clear_entity(adev),
+				       bo, 0, NULL, &fence,
+				       true, AMDGPU_KERNEL_JOB_ID_TTM_CLEAR_BUFFER);
 		if (unlikely(r))
 			goto fail_unreserve;
 
-		dma_resv_add_fence(bo->tbo.base.resv, fence,
-				   DMA_RESV_USAGE_KERNEL);
-		dma_fence_put(fence);
+		if (fence) {
+			dma_resv_add_fence(bo->tbo.base.resv, fence,
+					   DMA_RESV_USAGE_KERNEL);
+			dma_fence_put(fence);
+		}
 	}
 	if (!bp->resv)
 		amdgpu_bo_unreserve(bo);
@@ -1323,8 +1327,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
 		goto out;
 
 	r = amdgpu_fill_buffer(adev, amdgpu_ttm_next_clear_entity(adev),
-			       abo, 0, &bo->base._resv,
-			       &fence, AMDGPU_KERNEL_JOB_ID_CLEAR_ON_RELEASE);
+			       abo, 0, &bo->base._resv, &fence,
+			       false, 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 39cfe2dbdf03..c65c411ce26e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -459,7 +459,7 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 
 		r = amdgpu_fill_buffer(adev, entity,
 				       abo, 0, NULL, &wipe_fence,
-				       AMDGPU_KERNEL_JOB_ID_MOVE_BLIT);
+				       false, AMDGPU_KERNEL_JOB_ID_MOVE_BLIT);
 		if (r) {
 			goto error;
 		} else if (wipe_fence) {
@@ -2459,79 +2459,28 @@ static int amdgpu_ttm_fill_mem(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_ttm_clear_buffer - clear memory buffers
+ * amdgpu_fill_buffer - fill a buffer with a given value
  * @adev: amdgpu device object
- * @bo: amdgpu buffer object
- * @resv: reservation object
- * @fence: dma_fence associated with the operation
+ * @entity: optional entity to use. If NULL, the clearing entities will be
+ *          used to load-balance the partial clears
+ * @bo: the bo to fill
+ * @src_data: the value to set
+ * @resv: fences contained in this reservation will be used as dependencies.
+ * @out_fence: the fence from the last clear will be stored here. It might be
+ *             NULL if no job was run.
+ * @dependency: optional input dependency fence.
+ * @consider_clear_status: true if region reported as cleared by amdgpu_res_cleared()
+ *                         are skipped.
+ * @k_job_id: trace id
  *
- * Clear the memory buffer resource.
- *
- * Returns:
- * 0 for success or a negative error code on failure.
  */
-int amdgpu_ttm_clear_buffer(struct amdgpu_device *adev,
-			    struct amdgpu_bo *bo,
-			    struct dma_resv *resv,
-			    struct dma_fence **fence)
-{
-	struct amdgpu_ttm_buffer_entity *entity;
-	struct amdgpu_res_cursor cursor;
-	u64 addr;
-	int r = 0;
-
-	if (!adev->mman.buffer_funcs_enabled)
-		return -EINVAL;
-
-	if (!fence)
-		return -EINVAL;
-	entity = &adev->mman.clear_entities[0];
-	*fence = dma_fence_get_stub();
-
-	amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &cursor);
-
-	mutex_lock(&entity->lock);
-	while (cursor.remaining) {
-		struct dma_fence *next = NULL;
-		u64 size;
-
-		if (amdgpu_res_cleared(&cursor)) {
-			amdgpu_res_next(&cursor, cursor.size);
-			continue;
-		}
-
-		/* Never clear more than 256MiB at once to avoid timeouts */
-		size = min(cursor.size, 256ULL << 20);
-
-		r = amdgpu_ttm_map_buffer(adev, entity,
-					  &bo->tbo, bo->tbo.resource, &cursor,
-					  1, false, false, &size, &addr);
-		if (r)
-			goto err;
-
-		r = amdgpu_ttm_fill_mem(adev, entity, 0, addr, size, resv,
-					&next, true,
-					AMDGPU_KERNEL_JOB_ID_TTM_CLEAR_BUFFER);
-		if (r)
-			goto err;
-
-		dma_fence_put(*fence);
-		*fence = next;
-
-		amdgpu_res_next(&cursor, size);
-	}
-err:
-	mutex_unlock(&entity->lock);
-
-	return r;
-}
-
 int amdgpu_fill_buffer(struct amdgpu_device *adev,
 		       struct amdgpu_ttm_buffer_entity *entity,
 		       struct amdgpu_bo *bo,
 		       uint32_t src_data,
 		       struct dma_resv *resv,
-		       struct dma_fence **f,
+		       struct dma_fence **out_fence,
+		       bool consider_clear_status,
 		       u64 k_job_id)
 {
 	struct dma_fence *fence = NULL;
@@ -2551,6 +2500,11 @@ int amdgpu_fill_buffer(struct amdgpu_device *adev,
 		struct dma_fence *next;
 		uint64_t cur_size, to;
 
+		if (consider_clear_status && amdgpu_res_cleared(&dst)) {
+			amdgpu_res_next(&dst, dst.size);
+			continue;
+		}
+
 		/* Never fill more than 256MiB at once to avoid timeouts */
 		cur_size = min(dst.size, 256ULL << 20);
 
@@ -2574,9 +2528,7 @@ int amdgpu_fill_buffer(struct amdgpu_device *adev,
 	}
 error:
 	mutex_unlock(&entity->lock);
-	if (f)
-		*f = dma_fence_get(fence);
-	dma_fence_put(fence);
+	*out_fence = fence;
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 653a4d17543e..f3bdbcec9afc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -181,16 +181,13 @@ int amdgpu_copy_buffer(struct amdgpu_device *adev,
 		       struct dma_resv *resv,
 		       struct dma_fence **fence,
 		       bool vm_needs_flush, uint32_t copy_flags);
-int amdgpu_ttm_clear_buffer(struct amdgpu_device *adev,
-			    struct amdgpu_bo *bo,
-			    struct dma_resv *resv,
-			    struct dma_fence **fence);
 int amdgpu_fill_buffer(struct amdgpu_device *adev,
 		       struct amdgpu_ttm_buffer_entity *entity,
 		       struct amdgpu_bo *bo,
 		       uint32_t src_data,
 		       struct dma_resv *resv,
-		       struct dma_fence **f,
+		       struct dma_fence **out_fence,
+		       bool consider_clear_status,
 		       u64 k_job_id);
 struct amdgpu_ttm_buffer_entity *amdgpu_ttm_next_clear_entity(struct amdgpu_device *adev);
 
-- 
2.43.0
Re: [PATCH v3 27/28] drm/amdgpu: get rid of amdgpu_ttm_clear_buffer
Posted by Christian König 1 week, 3 days ago
On 11/21/25 11:12, Pierre-Eric Pelloux-Prayer wrote:
> It's doing the same thing as amdgpu_fill_buffer(src_data=0), so drop it.
> 
> The only caveat is that amdgpu_res_cleared() return value is only valid
> right after allocation.
> 
> ---
> v2: introduce new "bool consider_clear_status" arg
> ---
> 
> Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>

It would be better to have that ealier in the patch set, but I guess that gives you rebasing problems?

Christian.

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 16 ++--
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    | 90 +++++-----------------
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h    |  7 +-
>  3 files changed, 33 insertions(+), 80 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> index 7d8d70135cc2..dccc31d0128e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> @@ -725,13 +725,17 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
>  	    bo->tbo.resource->mem_type == TTM_PL_VRAM) {
>  		struct dma_fence *fence;
>  
> -		r = amdgpu_ttm_clear_buffer(adev, bo, bo->tbo.base.resv, &fence);
> +		r = amdgpu_fill_buffer(adev, amdgpu_ttm_next_clear_entity(adev),
> +				       bo, 0, NULL, &fence,
> +				       true, AMDGPU_KERNEL_JOB_ID_TTM_CLEAR_BUFFER);
>  		if (unlikely(r))
>  			goto fail_unreserve;
>  
> -		dma_resv_add_fence(bo->tbo.base.resv, fence,
> -				   DMA_RESV_USAGE_KERNEL);
> -		dma_fence_put(fence);
> +		if (fence) {
> +			dma_resv_add_fence(bo->tbo.base.resv, fence,
> +					   DMA_RESV_USAGE_KERNEL);
> +			dma_fence_put(fence);
> +		}
>  	}
>  	if (!bp->resv)
>  		amdgpu_bo_unreserve(bo);
> @@ -1323,8 +1327,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
>  		goto out;
>  
>  	r = amdgpu_fill_buffer(adev, amdgpu_ttm_next_clear_entity(adev),
> -			       abo, 0, &bo->base._resv,
> -			       &fence, AMDGPU_KERNEL_JOB_ID_CLEAR_ON_RELEASE);
> +			       abo, 0, &bo->base._resv, &fence,
> +			       false, 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 39cfe2dbdf03..c65c411ce26e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -459,7 +459,7 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
>  
>  		r = amdgpu_fill_buffer(adev, entity,
>  				       abo, 0, NULL, &wipe_fence,
> -				       AMDGPU_KERNEL_JOB_ID_MOVE_BLIT);
> +				       false, AMDGPU_KERNEL_JOB_ID_MOVE_BLIT);
>  		if (r) {
>  			goto error;
>  		} else if (wipe_fence) {
> @@ -2459,79 +2459,28 @@ static int amdgpu_ttm_fill_mem(struct amdgpu_device *adev,
>  }
>  
>  /**
> - * amdgpu_ttm_clear_buffer - clear memory buffers
> + * amdgpu_fill_buffer - fill a buffer with a given value
>   * @adev: amdgpu device object
> - * @bo: amdgpu buffer object
> - * @resv: reservation object
> - * @fence: dma_fence associated with the operation
> + * @entity: optional entity to use. If NULL, the clearing entities will be
> + *          used to load-balance the partial clears
> + * @bo: the bo to fill
> + * @src_data: the value to set
> + * @resv: fences contained in this reservation will be used as dependencies.
> + * @out_fence: the fence from the last clear will be stored here. It might be
> + *             NULL if no job was run.
> + * @dependency: optional input dependency fence.
> + * @consider_clear_status: true if region reported as cleared by amdgpu_res_cleared()
> + *                         are skipped.
> + * @k_job_id: trace id
>   *
> - * Clear the memory buffer resource.
> - *
> - * Returns:
> - * 0 for success or a negative error code on failure.
>   */
> -int amdgpu_ttm_clear_buffer(struct amdgpu_device *adev,
> -			    struct amdgpu_bo *bo,
> -			    struct dma_resv *resv,
> -			    struct dma_fence **fence)
> -{
> -	struct amdgpu_ttm_buffer_entity *entity;
> -	struct amdgpu_res_cursor cursor;
> -	u64 addr;
> -	int r = 0;
> -
> -	if (!adev->mman.buffer_funcs_enabled)
> -		return -EINVAL;
> -
> -	if (!fence)
> -		return -EINVAL;
> -	entity = &adev->mman.clear_entities[0];
> -	*fence = dma_fence_get_stub();
> -
> -	amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &cursor);
> -
> -	mutex_lock(&entity->lock);
> -	while (cursor.remaining) {
> -		struct dma_fence *next = NULL;
> -		u64 size;
> -
> -		if (amdgpu_res_cleared(&cursor)) {
> -			amdgpu_res_next(&cursor, cursor.size);
> -			continue;
> -		}
> -
> -		/* Never clear more than 256MiB at once to avoid timeouts */
> -		size = min(cursor.size, 256ULL << 20);
> -
> -		r = amdgpu_ttm_map_buffer(adev, entity,
> -					  &bo->tbo, bo->tbo.resource, &cursor,
> -					  1, false, false, &size, &addr);
> -		if (r)
> -			goto err;
> -
> -		r = amdgpu_ttm_fill_mem(adev, entity, 0, addr, size, resv,
> -					&next, true,
> -					AMDGPU_KERNEL_JOB_ID_TTM_CLEAR_BUFFER);
> -		if (r)
> -			goto err;
> -
> -		dma_fence_put(*fence);
> -		*fence = next;
> -
> -		amdgpu_res_next(&cursor, size);
> -	}
> -err:
> -	mutex_unlock(&entity->lock);
> -
> -	return r;
> -}
> -
>  int amdgpu_fill_buffer(struct amdgpu_device *adev,
>  		       struct amdgpu_ttm_buffer_entity *entity,
>  		       struct amdgpu_bo *bo,
>  		       uint32_t src_data,
>  		       struct dma_resv *resv,
> -		       struct dma_fence **f,
> +		       struct dma_fence **out_fence,
> +		       bool consider_clear_status,
>  		       u64 k_job_id)
>  {
>  	struct dma_fence *fence = NULL;
> @@ -2551,6 +2500,11 @@ int amdgpu_fill_buffer(struct amdgpu_device *adev,
>  		struct dma_fence *next;
>  		uint64_t cur_size, to;
>  
> +		if (consider_clear_status && amdgpu_res_cleared(&dst)) {
> +			amdgpu_res_next(&dst, dst.size);
> +			continue;
> +		}
> +
>  		/* Never fill more than 256MiB at once to avoid timeouts */
>  		cur_size = min(dst.size, 256ULL << 20);
>  
> @@ -2574,9 +2528,7 @@ int amdgpu_fill_buffer(struct amdgpu_device *adev,
>  	}
>  error:
>  	mutex_unlock(&entity->lock);
> -	if (f)
> -		*f = dma_fence_get(fence);
> -	dma_fence_put(fence);
> +	*out_fence = fence;
>  	return r;
>  }
>  
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> index 653a4d17543e..f3bdbcec9afc 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> @@ -181,16 +181,13 @@ int amdgpu_copy_buffer(struct amdgpu_device *adev,
>  		       struct dma_resv *resv,
>  		       struct dma_fence **fence,
>  		       bool vm_needs_flush, uint32_t copy_flags);
> -int amdgpu_ttm_clear_buffer(struct amdgpu_device *adev,
> -			    struct amdgpu_bo *bo,
> -			    struct dma_resv *resv,
> -			    struct dma_fence **fence);
>  int amdgpu_fill_buffer(struct amdgpu_device *adev,
>  		       struct amdgpu_ttm_buffer_entity *entity,
>  		       struct amdgpu_bo *bo,
>  		       uint32_t src_data,
>  		       struct dma_resv *resv,
> -		       struct dma_fence **f,
> +		       struct dma_fence **out_fence,
> +		       bool consider_clear_status,
>  		       u64 k_job_id);
>  struct amdgpu_ttm_buffer_entity *amdgpu_ttm_next_clear_entity(struct amdgpu_device *adev);
>