Re: [PATCH v2 05/20] drm/amdgpu: pass the entity to use to ttm functions

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

On 11/13/25 17:05, 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>
> ---
>  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       | 75 +++++++++++--------
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h       | 16 ++--
>  drivers/gpu/drm/amd/amdkfd/kfd_migrate.c      |  3 +-
>  5 files changed, 60 insertions(+), 41 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> index 02c2479a8840..b59040a8771f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> @@ -38,7 +38,8 @@ static int amdgpu_benchmark_do_move(struct amdgpu_device *adev, unsigned size,
>  	stime = ktime_get();
>  	for (i = 0; i < n; i++) {
>  		struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
> -		r = amdgpu_copy_buffer(ring, saddr, daddr, size, NULL, &fence,
> +		r = amdgpu_copy_buffer(ring, &adev->mman.default_entity.base,
> +				       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 e08f58de4b17..c06c132a753c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> @@ -1321,8 +1321,8 @@ 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 42d448cd6a6d..c8d59ca2b3bd 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -164,6 +164,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
>  
>  /**
>   * amdgpu_ttm_map_buffer - Map memory into the GART windows
> + * @entity: entity to run the window setup job
>   * @bo: buffer object to map
>   * @mem: memory object to map
>   * @mm_cur: range to map
> @@ -176,7 +177,8 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
>   * Setup one of the GART windows to access a specific piece of memory or return
>   * the physical address for local memory.
>   */
> -static int amdgpu_ttm_map_buffer(struct ttm_buffer_object *bo,
> +static int amdgpu_ttm_map_buffer(struct drm_sched_entity *entity,
> +				 struct ttm_buffer_object *bo,


Probably better to split this patch into multiple patches.

One which changes amdgpu_ttm_map_buffer() and then another one or two for the higher level copy_buffer and fill_buffer functions.

>  				 struct ttm_resource *mem,
>  				 struct amdgpu_res_cursor *mm_cur,
>  				 unsigned int window, struct amdgpu_ring *ring,
> @@ -224,7 +226,7 @@ static int amdgpu_ttm_map_buffer(struct ttm_buffer_object *bo,
>  	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,
>  				     AMDGPU_FENCE_OWNER_UNDEFINED,
>  				     num_dw * 4 + num_bytes,
>  				     AMDGPU_IB_POOL_DELAYED, &job,
> @@ -274,6 +276,7 @@ static int amdgpu_ttm_map_buffer(struct ttm_buffer_object *bo,
>  /**
>   * 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
> @@ -288,6 +291,7 @@ static int amdgpu_ttm_map_buffer(struct ttm_buffer_object *bo,
>   */
>  __attribute__((nonnull))
>  static int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
> +				      struct drm_sched_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(src->bo, src->mem, &src_mm,
> +		r = amdgpu_ttm_map_buffer(entity,
> +					  src->bo, src->mem, &src_mm,
>  					  0, ring, tmz, &cur_size, &from);
>  		if (r)
>  			goto error;
>  
> -		r = amdgpu_ttm_map_buffer(dst->bo, dst->mem, &dst_mm,
> +		r = amdgpu_ttm_map_buffer(entity,
> +					  dst->bo, dst->mem, &dst_mm,
>  					  1, ring, tmz, &cur_size, &to);
>  		if (r)
>  			goto error;
> @@ -353,7 +359,7 @@ static int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
>  							     write_compress_disable));
>  		}
>  
> -		r = amdgpu_copy_buffer(ring, from, to, cur_size, resv,
> +		r = amdgpu_copy_buffer(ring, entity, from, to, cur_size, resv,
>  				       &next, true, copy_flags);
>  		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.base,
> +				       &src, &dst,
>  				       new_mem->size,
>  				       amdgpu_bo_encrypted(abo),
>  				       bo->base.resv, &fence);
> @@ -406,8 +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) {
> @@ -2223,16 +2232,15 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
>  }
>  
>  static int amdgpu_ttm_prepare_job(struct amdgpu_device *adev,
> +				  struct drm_sched_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,
>  				     AMDGPU_FENCE_OWNER_UNDEFINED,
>  				     num_dw * 4, pool, job, k_job_id);
> @@ -2252,7 +2260,9 @@ static int amdgpu_ttm_prepare_job(struct amdgpu_device *adev,
>  						   DMA_RESV_USAGE_BOOKKEEP);
>  }
>  
> -int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
> +int amdgpu_copy_buffer(struct amdgpu_ring *ring,
> +		       struct drm_sched_entity *entity,
> +		       uint64_t src_offset,
>  		       uint64_t dst_offset, uint32_t byte_count,
>  		       struct dma_resv *resv,
>  		       struct dma_fence **fence,
> @@ -2274,8 +2284,8 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, 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, entity, num_dw,
> +				   resv, vm_needs_flush, &job,
>  				   AMDGPU_KERNEL_JOB_ID_TTM_COPY_BUFFER);
>  	if (r)
>  		return r;
> @@ -2304,11 +2314,13 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
>  	return r;
>  }
>  
> -static int amdgpu_ttm_fill_mem(struct amdgpu_ring *ring, uint32_t src_data,
> +static int amdgpu_ttm_fill_mem(struct amdgpu_ring *ring,
> +			       struct drm_sched_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)
>  {
>  	struct amdgpu_device *adev = ring->adev;
> @@ -2321,8 +2333,8 @@ static int amdgpu_ttm_fill_mem(struct amdgpu_ring *ring, 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;
>  
> @@ -2386,13 +2398,14 @@ 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(&bo->tbo, bo->tbo.resource, &cursor,
> +		r = amdgpu_ttm_map_buffer(&adev->mman.clear_entity.base,
> +					  &bo->tbo, bo->tbo.resource, &cursor,
>  					  1, ring, false, &size, &addr);
>  		if (r)
>  			goto err;
>  
> -		r = amdgpu_ttm_fill_mem(ring, 0, addr, size, resv,
> -					&next, true, true,
> +		r = amdgpu_ttm_fill_mem(ring, &adev->mman.clear_entity.base, 0, addr, size, resv,
> +					&next, true,
>  					AMDGPU_KERNEL_JOB_ID_TTM_CLEAR_BUFFER);
>  		if (r)
>  			goto err;
> @@ -2408,12 +2421,12 @@ 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_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_ring *ring = adev->mman.buffer_funcs_ring;
> @@ -2437,13 +2450,15 @@ 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(&bo->tbo, bo->tbo.resource, &dst,
> +		r = amdgpu_ttm_map_buffer(&entity->base,
> +					  &bo->tbo, bo->tbo.resource, &dst,
>  					  1, ring, false, &cur_size, &to);
>  		if (r)
>  			goto error;
>  
> -		r = amdgpu_ttm_fill_mem(ring, src_data, to, cur_size, resv,
> -					&next, true, delayed, k_job_id);
> +		r = amdgpu_ttm_fill_mem(ring, &entity->base,
> +					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 d2295d6c2b67..e1655f86a016 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_ring *ring, uint64_t src_offset,
> +int amdgpu_copy_buffer(struct amdgpu_ring *ring,
> +		       struct drm_sched_entity *entity,

If I'm not completely mistaken you should be able to drop the ring argument since that can be determined from the entity.

Apart from that looks rather good to me.

Regards,
Christian.

> +		       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_ring *ring, 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_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 d74ff6e90590..09756132fa1b 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(ring, gart_s, gart_d, size * PAGE_SIZE,
> +		r = amdgpu_copy_buffer(ring, &entity->base,
> +				       gart_s, gart_d, size * PAGE_SIZE,
>  				       NULL, &next, true, 0);
>  		if (r) {
>  			dev_err(adev->dev, "fail %d to copy memory\n", r);