Re: [PATCH v3 09/28] drm/amdgpu: pass the entity to use to ttm public functions

["Christian König" <christian.koenig@amd.com>]

On 11/21/25 11:12, Pierre-Eric Pelloux-Prayer wrote:
> This way the caller can select the one it wants to use.
> 
> Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>

I'm wondering if it wouldn't make sense to put a pointer to adev into each amdgpu_ttm_buffer_entity.

But that is maybe something for another patch. For now:

Reviewed-by: Christian König <christian.koenig@amd.com>

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c |  3 +-
>  drivers/gpu/drm/amd/amdgpu/amdgpu_object.c    |  4 +--
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c       | 34 +++++++++----------
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h       | 16 +++++----
>  drivers/gpu/drm/amd/amdkfd/kfd_migrate.c      |  3 +-
>  5 files changed, 32 insertions(+), 28 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> index 3636b757c974..a050167e76a4 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> @@ -37,7 +37,8 @@ static int amdgpu_benchmark_do_move(struct amdgpu_device *adev, unsigned size,
>  
>  	stime = ktime_get();
>  	for (i = 0; i < n; i++) {
> -		r = amdgpu_copy_buffer(adev, saddr, daddr, size, NULL, &fence,
> +		r = amdgpu_copy_buffer(adev, &adev->mman.default_entity,
> +				       saddr, daddr, size, NULL, &fence,
>  				       false, 0);
>  		if (r)
>  			goto exit_do_move;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> index 926a3f09a776..858eb9fa061b 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(abo, 0, &bo->base._resv, &fence, true,
> -			       AMDGPU_KERNEL_JOB_ID_CLEAR_ON_RELEASE);
> +	r = amdgpu_fill_buffer(&adev->mman.clear_entity, 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 3d850893b97f..1d3afad885da 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -359,7 +359,7 @@ static int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
>  							     write_compress_disable));
>  		}
>  
> -		r = amdgpu_copy_buffer(adev, from, to, cur_size, resv,
> +		r = amdgpu_copy_buffer(adev, entity, from, to, cur_size, resv,
>  				       &next, true, copy_flags);
>  		if (r)
>  			goto error;
> @@ -414,8 +414,9 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
>  	    (abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) {
>  		struct dma_fence *wipe_fence = NULL;
>  
> -		r = amdgpu_fill_buffer(abo, 0, NULL, &wipe_fence,
> -				       false, AMDGPU_KERNEL_JOB_ID_MOVE_BLIT);
> +		r = amdgpu_fill_buffer(&adev->mman.move_entity,
> +				       abo, 0, NULL, &wipe_fence,
> +				       AMDGPU_KERNEL_JOB_ID_MOVE_BLIT);
>  		if (r) {
>  			goto error;
>  		} else if (wipe_fence) {
> @@ -2258,7 +2259,9 @@ static int amdgpu_ttm_prepare_job(struct amdgpu_device *adev,
>  						   DMA_RESV_USAGE_BOOKKEEP);
>  }
>  
> -int amdgpu_copy_buffer(struct amdgpu_device *adev, uint64_t src_offset,
> +int amdgpu_copy_buffer(struct amdgpu_device *adev,
> +		       struct amdgpu_ttm_buffer_entity *entity,
> +		       uint64_t src_offset,
>  		       uint64_t dst_offset, uint32_t byte_count,
>  		       struct dma_resv *resv,
>  		       struct dma_fence **fence,
> @@ -2282,7 +2285,7 @@ int amdgpu_copy_buffer(struct amdgpu_device *adev, uint64_t src_offset,
>  	max_bytes = adev->mman.buffer_funcs->copy_max_bytes;
>  	num_loops = DIV_ROUND_UP(byte_count, max_bytes);
>  	num_dw = ALIGN(num_loops * adev->mman.buffer_funcs->copy_num_dw, 8);
> -	r = amdgpu_ttm_prepare_job(adev, &adev->mman.move_entity, num_dw,
> +	r = amdgpu_ttm_prepare_job(adev, entity, num_dw,
>  				   resv, vm_needs_flush, &job,
>  				   AMDGPU_KERNEL_JOB_ID_TTM_COPY_BUFFER);
>  	if (r)
> @@ -2411,22 +2414,18 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
>  	return r;
>  }
>  
> -int amdgpu_fill_buffer(struct amdgpu_bo *bo,
> -			uint32_t src_data,
> -			struct dma_resv *resv,
> -			struct dma_fence **f,
> -			bool delayed,
> -			u64 k_job_id)
> +int amdgpu_fill_buffer(struct amdgpu_ttm_buffer_entity *entity,
> +		       struct amdgpu_bo *bo,
> +		       uint32_t src_data,
> +		       struct dma_resv *resv,
> +		       struct dma_fence **f,
> +		       u64 k_job_id)
>  {
>  	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
> -	struct amdgpu_ttm_buffer_entity *entity;
>  	struct dma_fence *fence = NULL;
>  	struct amdgpu_res_cursor dst;
>  	int r;
>  
> -	entity = delayed ? &adev->mman.clear_entity :
> -			   &adev->mman.move_entity;
> -
>  	if (!adev->mman.buffer_funcs_enabled) {
>  		dev_err(adev->dev,
>  			"Trying to clear memory with ring turned off.\n");
> @@ -2443,13 +2442,14 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo,
>  		/* Never fill more than 256MiB at once to avoid timeouts */
>  		cur_size = min(dst.size, 256ULL << 20);
>  
> -		r = amdgpu_ttm_map_buffer(adev, &adev->mman.default_entity,
> +		r = amdgpu_ttm_map_buffer(adev, entity,
>  					  &bo->tbo, bo->tbo.resource, &dst,
>  					  1, false, &cur_size, &to);
>  		if (r)
>  			goto error;
>  
> -		r = amdgpu_ttm_fill_mem(adev, entity, src_data, to, cur_size, resv,
> +		r = amdgpu_ttm_fill_mem(adev, entity,
> +					src_data, to, cur_size, resv,
>  					&next, true, k_job_id);
>  		if (r)
>  			goto error;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> index 41bbc25680a2..9288599c9c46 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> @@ -167,7 +167,9 @@ int amdgpu_ttm_init(struct amdgpu_device *adev);
>  void amdgpu_ttm_fini(struct amdgpu_device *adev);
>  void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev,
>  					bool enable);
> -int amdgpu_copy_buffer(struct amdgpu_device *adev, uint64_t src_offset,
> +int amdgpu_copy_buffer(struct amdgpu_device *adev,
> +		       struct amdgpu_ttm_buffer_entity *entity,
> +		       uint64_t src_offset,
>  		       uint64_t dst_offset, uint32_t byte_count,
>  		       struct dma_resv *resv,
>  		       struct dma_fence **fence,
> @@ -175,12 +177,12 @@ int amdgpu_copy_buffer(struct amdgpu_device *adev, uint64_t src_offset,
>  int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
>  			    struct dma_resv *resv,
>  			    struct dma_fence **fence);
> -int amdgpu_fill_buffer(struct amdgpu_bo *bo,
> -			uint32_t src_data,
> -			struct dma_resv *resv,
> -			struct dma_fence **fence,
> -			bool delayed,
> -			u64 k_job_id);
> +int amdgpu_fill_buffer(struct amdgpu_ttm_buffer_entity *entity,
> +		       struct amdgpu_bo *bo,
> +		       uint32_t src_data,
> +		       struct dma_resv *resv,
> +		       struct dma_fence **f,
> +		       u64 k_job_id);
>  
>  int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo);
>  void amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo);
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> index ade1d4068d29..9c76f1ba0e55 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> @@ -157,7 +157,8 @@ svm_migrate_copy_memory_gart(struct amdgpu_device *adev, dma_addr_t *sys,
>  			goto out_unlock;
>  		}
>  
> -		r = amdgpu_copy_buffer(adev, gart_s, gart_d, size * PAGE_SIZE,
> +		r = amdgpu_copy_buffer(adev, entity,
> +				       gart_s, gart_d, size * PAGE_SIZE,
>  				       NULL, &next, true, 0);
>  		if (r) {
>  			dev_err(adev->dev, "fail %d to copy memory\n", r);