[PATCH v3 22/28] drm/amdgpu: round robin through clear_entities in amdgpu_fill_buffer

Pierre-Eric Pelloux-Prayer posted 28 patches 1 week, 3 days ago
[PATCH v3 22/28] drm/amdgpu: round robin through clear_entities in amdgpu_fill_buffer
Posted by Pierre-Eric Pelloux-Prayer 1 week, 3 days ago
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 |  4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    | 12 ++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h    |  2 ++
 3 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 56663e82efef..7d8d70135cc2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1322,8 +1322,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
 	if (r)
 		goto out;
 
-	r = amdgpu_fill_buffer(adev,
-			       &adev->mman.clear_entities[0], abo, 0, &bo->base._resv,
+	r = amdgpu_fill_buffer(adev, 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 438e8a3b7a06..8d70bea66dd0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -2277,6 +2277,7 @@ 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;
 
@@ -2576,6 +2577,17 @@ int amdgpu_fill_buffer(struct amdgpu_device *adev,
 	return r;
 }
 
+struct amdgpu_ttm_buffer_entity *
+amdgpu_ttm_next_clear_entity(struct amdgpu_device *adev)
+{
+	struct amdgpu_mman *mman = &adev->mman;
+	int i;
+
+	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 eabc5a1549e9..887531126d9d 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;
@@ -189,6 +190,7 @@ int amdgpu_fill_buffer(struct amdgpu_device *adev,
 		       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);
-- 
2.43.0
Re: [PATCH v3 22/28] drm/amdgpu: round robin through clear_entities in amdgpu_fill_buffer
Posted by Christian König 1 week, 3 days ago
On 11/21/25 11:12, Pierre-Eric Pelloux-Prayer wrote:
> 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>

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_object.c |  4 ++--
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    | 12 ++++++++++++
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h    |  2 ++
>  3 files changed, 16 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> index 56663e82efef..7d8d70135cc2 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> @@ -1322,8 +1322,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
>  	if (r)
>  		goto out;
>  
> -	r = amdgpu_fill_buffer(adev,
> -			       &adev->mman.clear_entities[0], abo, 0, &bo->base._resv,
> +	r = amdgpu_fill_buffer(adev, 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 438e8a3b7a06..8d70bea66dd0 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -2277,6 +2277,7 @@ 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;
>  
> @@ -2576,6 +2577,17 @@ int amdgpu_fill_buffer(struct amdgpu_device *adev,
>  	return r;
>  }
>  
> +struct amdgpu_ttm_buffer_entity *
> +amdgpu_ttm_next_clear_entity(struct amdgpu_device *adev)
> +{
> +	struct amdgpu_mman *mman = &adev->mman;
> +	int i;
> +
> +	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 eabc5a1549e9..887531126d9d 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;
> @@ -189,6 +190,7 @@ int amdgpu_fill_buffer(struct amdgpu_device *adev,
>  		       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);