Re: [PATCH v3 04/28] drm/amdgpu: remove the ring param from ttm functions

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

On 11/21/25 11:12, Pierre-Eric Pelloux-Prayer wrote:
> With the removal of the direct_submit argument, the ring param
> becomes useless: the jobs are always submitted to buffer_funcs_ring.
> 
> Some functions are getting an amdgpu_device argument since they
> were getting it from the ring arg.
> 
> 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_ttm.c       | 46 ++++++++++---------
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h       |  2 +-
>  drivers/gpu/drm/amd/amdkfd/kfd_migrate.c      |  2 +-
>  4 files changed, 27 insertions(+), 26 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> index 02c2479a8840..3636b757c974 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> @@ -37,8 +37,7 @@ 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(adev, saddr, daddr, size, NULL, &fence,
>  				       false, 0);
>  		if (r)
>  			goto exit_do_move;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> index 071afbacb3d2..d54b57078946 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -164,11 +164,11 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
>  
>  /**
>   * amdgpu_ttm_map_buffer - Map memory into the GART windows
> + * @adev: the device being used
>   * @bo: buffer object to map
>   * @mem: memory object to map
>   * @mm_cur: range to map
>   * @window: which GART window to use
> - * @ring: DMA ring to use for the copy
>   * @tmz: if we should setup a TMZ enabled mapping
>   * @size: in number of bytes to map, out number of bytes mapped
>   * @addr: resulting address inside the MC address space
> @@ -176,15 +176,16 @@ 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 amdgpu_device *adev,
> +				 struct ttm_buffer_object *bo,

Using this should work as well:

struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);

Not a must have, but is more defensive and saves an extra parameter.

Apart from that the patch looks good to me.

Regards,
Christian.

>  				 struct ttm_resource *mem,
>  				 struct amdgpu_res_cursor *mm_cur,
> -				 unsigned int window, struct amdgpu_ring *ring,
> +				 unsigned int window,
>  				 bool tmz, uint64_t *size, uint64_t *addr)
>  {
> -	struct amdgpu_device *adev = ring->adev;
>  	unsigned int offset, num_pages, num_dw, num_bytes;
>  	uint64_t src_addr, dst_addr;
> +	struct amdgpu_ring *ring;
>  	struct amdgpu_job *job;
>  	void *cpu_addr;
>  	uint64_t flags;
> @@ -239,6 +240,7 @@ static int amdgpu_ttm_map_buffer(struct ttm_buffer_object *bo,
>  	amdgpu_emit_copy_buffer(adev, &job->ibs[0], src_addr,
>  				dst_addr, num_bytes, 0);
>  
> +	ring = adev->mman.buffer_funcs_ring;
>  	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
>  	WARN_ON(job->ibs[0].length_dw > num_dw);
>  
> @@ -286,7 +288,6 @@ static int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
>  				      struct dma_resv *resv,
>  				      struct dma_fence **f)
>  {
> -	struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
>  	struct amdgpu_res_cursor src_mm, dst_mm;
>  	struct dma_fence *fence = NULL;
>  	int r = 0;
> @@ -312,13 +313,13 @@ 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,
> -					  0, ring, tmz, &cur_size, &from);
> +		r = amdgpu_ttm_map_buffer(adev, src->bo, src->mem, &src_mm,
> +					  0, tmz, &cur_size, &from);
>  		if (r)
>  			goto error;
>  
> -		r = amdgpu_ttm_map_buffer(dst->bo, dst->mem, &dst_mm,
> -					  1, ring, tmz, &cur_size, &to);
> +		r = amdgpu_ttm_map_buffer(adev, dst->bo, dst->mem, &dst_mm,
> +					  1, tmz, &cur_size, &to);
>  		if (r)
>  			goto error;
>  
> @@ -345,7 +346,7 @@ 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(adev, from, to, cur_size, resv,
>  				       &next, true, copy_flags);
>  		if (r)
>  			goto error;
> @@ -2232,19 +2233,21 @@ 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_device *adev, uint64_t src_offset,
>  		       uint64_t dst_offset, uint32_t byte_count,
>  		       struct dma_resv *resv,
>  		       struct dma_fence **fence,
>  		       bool vm_needs_flush, uint32_t copy_flags)
>  {
> -	struct amdgpu_device *adev = ring->adev;
>  	unsigned int num_loops, num_dw;
> +	struct amdgpu_ring *ring;
>  	struct amdgpu_job *job;
>  	uint32_t max_bytes;
>  	unsigned int i;
>  	int r;
>  
> +	ring = adev->mman.buffer_funcs_ring;
> +
>  	if (!ring->sched.ready) {
>  		dev_err(adev->dev,
>  			"Trying to move memory with ring turned off.\n");
> @@ -2284,15 +2287,15 @@ 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_device *adev, 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,
>  			       u64 k_job_id)
>  {
> -	struct amdgpu_device *adev = ring->adev;
>  	unsigned int num_loops, num_dw;
> +	struct amdgpu_ring *ring;
>  	struct amdgpu_job *job;
>  	uint32_t max_bytes;
>  	unsigned int i;
> @@ -2316,6 +2319,7 @@ static int amdgpu_ttm_fill_mem(struct amdgpu_ring *ring, uint32_t src_data,
>  		byte_count -= cur_size;
>  	}
>  
> +	ring = adev->mman.buffer_funcs_ring;
>  	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
>  	WARN_ON(job->ibs[0].length_dw > num_dw);
>  	*fence = amdgpu_job_submit(job);
> @@ -2338,7 +2342,6 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
>  			    struct dma_fence **fence)
>  {
>  	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
> -	struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
>  	struct amdgpu_res_cursor cursor;
>  	u64 addr;
>  	int r = 0;
> @@ -2366,12 +2369,12 @@ 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,
> -					  1, ring, false, &size, &addr);
> +		r = amdgpu_ttm_map_buffer(adev, &bo->tbo, bo->tbo.resource, &cursor,
> +					  1, false, &size, &addr);
>  		if (r)
>  			goto err;
>  
> -		r = amdgpu_ttm_fill_mem(ring, 0, addr, size, resv,
> +		r = amdgpu_ttm_fill_mem(adev, 0, addr, size, resv,
>  					&next, true, true,
>  					AMDGPU_KERNEL_JOB_ID_TTM_CLEAR_BUFFER);
>  		if (r)
> @@ -2396,7 +2399,6 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo,
>  			u64 k_job_id)
>  {
>  	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
> -	struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
>  	struct dma_fence *fence = NULL;
>  	struct amdgpu_res_cursor dst;
>  	int r;
> @@ -2417,12 +2419,12 @@ 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,
> -					  1, ring, false, &cur_size, &to);
> +		r = amdgpu_ttm_map_buffer(adev, &bo->tbo, bo->tbo.resource, &dst,
> +					  1, false, &cur_size, &to);
>  		if (r)
>  			goto error;
>  
> -		r = amdgpu_ttm_fill_mem(ring, src_data, to, cur_size, resv,
> +		r = amdgpu_ttm_fill_mem(adev, src_data, to, cur_size, resv,
>  					&next, true, delayed, 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 50e40380fe95..76e00a6510c6 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> @@ -163,7 +163,7 @@ 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_device *adev, uint64_t src_offset,
>  		       uint64_t dst_offset, uint32_t byte_count,
>  		       struct dma_resv *resv,
>  		       struct dma_fence **fence,
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> index 378af0b2aaa9..0ad44acb08f2 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> @@ -152,7 +152,7 @@ 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(adev, gart_s, gart_d, size * PAGE_SIZE,
>  				       NULL, &next, true, 0);
>  		if (r) {
>  			dev_err(adev->dev, "fail %d to copy memory\n", r);