Re: [PATCH v3 08/28] drm/amdgpu: pass the entity to use to amdgpu_ttm_map_buffer

["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>

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

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 55 ++++++++++++++++---------
>  1 file changed, 35 insertions(+), 20 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> index 353682c0e8f0..3d850893b97f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -177,6 +177,7 @@ amdgpu_ttm_job_submit(struct amdgpu_device *adev, struct amdgpu_job *job, u32 nu
>  /**
>   * amdgpu_ttm_map_buffer - Map memory into the GART windows
>   * @adev: the device being used
> + * @entity: entity to run the window setup job
>   * @bo: buffer object to map
>   * @mem: memory object to map
>   * @mm_cur: range to map
> @@ -189,6 +190,7 @@ amdgpu_ttm_job_submit(struct amdgpu_device *adev, struct amdgpu_job *job, u32 nu
>   * the physical address for local memory.
>   */
>  static int amdgpu_ttm_map_buffer(struct amdgpu_device *adev,
> +				 struct amdgpu_ttm_buffer_entity *entity,
>  				 struct ttm_buffer_object *bo,
>  				 struct ttm_resource *mem,
>  				 struct amdgpu_res_cursor *mm_cur,
> @@ -235,7 +237,7 @@ static int amdgpu_ttm_map_buffer(struct amdgpu_device *adev,
>  	num_dw = ALIGN(adev->mman.buffer_funcs->copy_num_dw, 8);
>  	num_bytes = num_pages * 8 * AMDGPU_GPU_PAGES_IN_CPU_PAGE;
>  
> -	r = amdgpu_job_alloc_with_ib(adev, &adev->mman.default_entity.base,
> +	r = amdgpu_job_alloc_with_ib(adev, &entity->base,
>  				     AMDGPU_FENCE_OWNER_UNDEFINED,
>  				     num_dw * 4 + num_bytes,
>  				     AMDGPU_IB_POOL_DELAYED, &job,
> @@ -275,6 +277,7 @@ static int amdgpu_ttm_map_buffer(struct amdgpu_device *adev,
>  /**
>   * amdgpu_ttm_copy_mem_to_mem - Helper function for copy
>   * @adev: amdgpu device
> + * @entity: entity to run the jobs
>   * @src: buffer/address where to read from
>   * @dst: buffer/address where to write to
>   * @size: number of bytes to copy
> @@ -289,6 +292,7 @@ static int amdgpu_ttm_map_buffer(struct amdgpu_device *adev,
>   */
>  __attribute__((nonnull))
>  static int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
> +				      struct amdgpu_ttm_buffer_entity *entity,
>  				      const struct amdgpu_copy_mem *src,
>  				      const struct amdgpu_copy_mem *dst,
>  				      uint64_t size, bool tmz,
> @@ -320,12 +324,14 @@ static int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
>  		cur_size = min3(src_mm.size, dst_mm.size, 256ULL << 20);
>  
>  		/* Map src to window 0 and dst to window 1. */
> -		r = amdgpu_ttm_map_buffer(adev, src->bo, src->mem, &src_mm,
> +		r = amdgpu_ttm_map_buffer(adev, entity,
> +					  src->bo, src->mem, &src_mm,
>  					  0, tmz, &cur_size, &from);
>  		if (r)
>  			goto error;
>  
> -		r = amdgpu_ttm_map_buffer(adev, dst->bo, dst->mem, &dst_mm,
> +		r = amdgpu_ttm_map_buffer(adev, entity,
> +					  dst->bo, dst->mem, &dst_mm,
>  					  1, tmz, &cur_size, &to);
>  		if (r)
>  			goto error;
> @@ -394,7 +400,9 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
>  	src.offset = 0;
>  	dst.offset = 0;
>  
> -	r = amdgpu_ttm_copy_mem_to_mem(adev, &src, &dst,
> +	r = amdgpu_ttm_copy_mem_to_mem(adev,
> +				       &adev->mman.move_entity,
> +				       &src, &dst,
>  				       new_mem->size,
>  				       amdgpu_bo_encrypted(abo),
>  				       bo->base.resv, &fence);
> @@ -2220,17 +2228,16 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
>  }
>  
>  static int amdgpu_ttm_prepare_job(struct amdgpu_device *adev,
> +				  struct amdgpu_ttm_buffer_entity *entity,
>  				  unsigned int num_dw,
>  				  struct dma_resv *resv,
>  				  bool vm_needs_flush,
>  				  struct amdgpu_job **job,
> -				  bool delayed, u64 k_job_id)
> +				  u64 k_job_id)
>  {
>  	enum amdgpu_ib_pool_type pool = AMDGPU_IB_POOL_DELAYED;
>  	int r;
> -	struct drm_sched_entity *entity = delayed ? &adev->mman.clear_entity.base :
> -						    &adev->mman.move_entity.base;
> -	r = amdgpu_job_alloc_with_ib(adev, entity,
> +	r = amdgpu_job_alloc_with_ib(adev, &entity->base,
>  				     AMDGPU_FENCE_OWNER_UNDEFINED,
>  				     num_dw * 4, pool, job, k_job_id);
>  	if (r) {
> @@ -2275,8 +2282,8 @@ 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, num_dw,
> -				   resv, vm_needs_flush, &job, false,
> +	r = amdgpu_ttm_prepare_job(adev, &adev->mman.move_entity, num_dw,
> +				   resv, vm_needs_flush, &job,
>  				   AMDGPU_KERNEL_JOB_ID_TTM_COPY_BUFFER);
>  	if (r)
>  		goto error_free;
> @@ -2301,11 +2308,13 @@ int amdgpu_copy_buffer(struct amdgpu_device *adev, uint64_t src_offset,
>  	return r;
>  }
>  
> -static int amdgpu_ttm_fill_mem(struct amdgpu_device *adev, uint32_t src_data,
> +static int amdgpu_ttm_fill_mem(struct amdgpu_device *adev,
> +			       struct amdgpu_ttm_buffer_entity *entity,
> +			       uint32_t src_data,
>  			       uint64_t dst_addr, uint32_t byte_count,
>  			       struct dma_resv *resv,
>  			       struct dma_fence **fence,
> -			       bool vm_needs_flush, bool delayed,
> +			       bool vm_needs_flush,
>  			       u64 k_job_id)
>  {
>  	unsigned int num_loops, num_dw;
> @@ -2317,8 +2326,8 @@ static int amdgpu_ttm_fill_mem(struct amdgpu_device *adev, uint32_t src_data,
>  	max_bytes = adev->mman.buffer_funcs->fill_max_bytes;
>  	num_loops = DIV_ROUND_UP_ULL(byte_count, max_bytes);
>  	num_dw = ALIGN(num_loops * adev->mman.buffer_funcs->fill_num_dw, 8);
> -	r = amdgpu_ttm_prepare_job(adev, num_dw, resv, vm_needs_flush,
> -				   &job, delayed, k_job_id);
> +	r = amdgpu_ttm_prepare_job(adev, entity, num_dw, resv,
> +				   vm_needs_flush, &job, k_job_id);
>  	if (r)
>  		return r;
>  
> @@ -2379,13 +2388,14 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
>  		/* Never clear more than 256MiB at once to avoid timeouts */
>  		size = min(cursor.size, 256ULL << 20);
>  
> -		r = amdgpu_ttm_map_buffer(adev, &bo->tbo, bo->tbo.resource, &cursor,
> +		r = amdgpu_ttm_map_buffer(adev, &adev->mman.clear_entity,
> +					  &bo->tbo, bo->tbo.resource, &cursor,
>  					  1, false, &size, &addr);
>  		if (r)
>  			goto err;
>  
> -		r = amdgpu_ttm_fill_mem(adev, 0, addr, size, resv,
> -					&next, true, true,
> +		r = amdgpu_ttm_fill_mem(adev, &adev->mman.clear_entity, 0, addr, size, resv,
> +					&next, true,
>  					AMDGPU_KERNEL_JOB_ID_TTM_CLEAR_BUFFER);
>  		if (r)
>  			goto err;
> @@ -2409,10 +2419,14 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo,
>  			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");
> @@ -2429,13 +2443,14 @@ 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, &bo->tbo, bo->tbo.resource, &dst,
> +		r = amdgpu_ttm_map_buffer(adev, &adev->mman.default_entity,
> +					  &bo->tbo, bo->tbo.resource, &dst,
>  					  1, false, &cur_size, &to);
>  		if (r)
>  			goto error;
>  
> -		r = amdgpu_ttm_fill_mem(adev, src_data, to, cur_size, resv,
> -					&next, true, delayed, k_job_id);
> +		r = amdgpu_ttm_fill_mem(adev, entity, src_data, to, cur_size, resv,
> +					&next, true, k_job_id);
>  		if (r)
>  			goto error;
>