Re: [PATCH v2 03/20] drm/amdgpu: remove direct_submit arg from amdgpu_copy_buffer

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

On 11/13/25 17:05, Pierre-Eric Pelloux-Prayer wrote:
> It was always false.
> 
> Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
> Reviewed-by: Christian König <christian.koenig@amd.com>

Please push to amd-staging-drm-next.

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c |  2 +-
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c       | 20 +++++++------------
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h       |  2 +-
>  drivers/gpu/drm/amd/amdkfd/kfd_migrate.c      |  2 +-
>  4 files changed, 10 insertions(+), 16 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> index 199693369c7c..02c2479a8840 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> @@ -39,7 +39,7 @@ static int amdgpu_benchmark_do_move(struct amdgpu_device *adev, unsigned size,
>  	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,
> -				       false, false, 0);
> +				       false, 0);
>  		if (r)
>  			goto exit_do_move;
>  		r = dma_fence_wait(fence, false);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> index 3b46a24a8c48..c985f57fa227 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -354,7 +354,7 @@ static int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
>  		}
>  
>  		r = amdgpu_copy_buffer(ring, from, to, cur_size, resv,
> -				       &next, false, true, copy_flags);
> +				       &next, true, copy_flags);
>  		if (r)
>  			goto error;
>  
> @@ -2211,16 +2211,13 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
>  }
>  
>  static int amdgpu_ttm_prepare_job(struct amdgpu_device *adev,
> -				  bool direct_submit,
>  				  unsigned int num_dw,
>  				  struct dma_resv *resv,
>  				  bool vm_needs_flush,
>  				  struct amdgpu_job **job,
>  				  bool delayed, u64 k_job_id)
>  {
> -	enum amdgpu_ib_pool_type pool = direct_submit ?
> -		AMDGPU_IB_POOL_DIRECT :
> -		AMDGPU_IB_POOL_DELAYED;
> +	enum amdgpu_ib_pool_type pool = AMDGPU_IB_POOL_DELAYED;
>  	int r;
>  	struct drm_sched_entity *entity = delayed ? &adev->mman.low_pr :
>  						    &adev->mman.high_pr;
> @@ -2246,7 +2243,7 @@ static int amdgpu_ttm_prepare_job(struct amdgpu_device *adev,
>  int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
>  		       uint64_t dst_offset, uint32_t byte_count,
>  		       struct dma_resv *resv,
> -		       struct dma_fence **fence, bool direct_submit,
> +		       struct dma_fence **fence,
>  		       bool vm_needs_flush, uint32_t copy_flags)
>  {
>  	struct amdgpu_device *adev = ring->adev;
> @@ -2256,7 +2253,7 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
>  	unsigned int i;
>  	int r;
>  
> -	if (!direct_submit && !ring->sched.ready) {
> +	if (!ring->sched.ready) {
>  		dev_err(adev->dev,
>  			"Trying to move memory with ring turned off.\n");
>  		return -EINVAL;
> @@ -2265,7 +2262,7 @@ 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, direct_submit, num_dw,
> +	r = amdgpu_ttm_prepare_job(adev, num_dw,
>  				   resv, vm_needs_flush, &job, false,
>  				   AMDGPU_KERNEL_JOB_ID_TTM_COPY_BUFFER);
>  	if (r)
> @@ -2283,10 +2280,7 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
>  
>  	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
>  	WARN_ON(job->ibs[0].length_dw > num_dw);
> -	if (direct_submit)
> -		r = amdgpu_job_submit_direct(job, ring, fence);
> -	else
> -		*fence = amdgpu_job_submit(job);
> +	*fence = amdgpu_job_submit(job);
>  	if (r)
>  		goto error_free;
>  
> @@ -2315,7 +2309,7 @@ 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, false, num_dw, resv, vm_needs_flush,
> +	r = amdgpu_ttm_prepare_job(adev, num_dw, resv, vm_needs_flush,
>  				   &job, delayed, k_job_id);
>  	if (r)
>  		return r;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> index 577ee04ce0bf..50e40380fe95 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> @@ -166,7 +166,7 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev,
>  int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
>  		       uint64_t dst_offset, uint32_t byte_count,
>  		       struct dma_resv *resv,
> -		       struct dma_fence **fence, bool direct_submit,
> +		       struct dma_fence **fence,
>  		       bool vm_needs_flush, uint32_t copy_flags);
>  int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
>  			    struct dma_resv *resv,
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> index 46c84fc60af1..378af0b2aaa9 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> @@ -153,7 +153,7 @@ svm_migrate_copy_memory_gart(struct amdgpu_device *adev, dma_addr_t *sys,
>  		}
>  
>  		r = amdgpu_copy_buffer(ring, gart_s, gart_d, size * PAGE_SIZE,
> -				       NULL, &next, false, true, 0);
> +				       NULL, &next, true, 0);
>  		if (r) {
>  			dev_err(adev->dev, "fail %d to copy memory\n", r);
>  			goto out_unlock;