Re: [PATCH v2 08/20] drm/amdgpu: allocate multiple move entities

[Felix Kuehling <felix.kuehling@amd.com>]

On 2025-11-13 11:05, Pierre-Eric Pelloux-Prayer wrote:
> No functional change for now, as we always use entity 0.
>
> Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>

Acked-by: Felix Kuehling <felix.kuehling@amd.com>


> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c  |  9 +++--
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c  | 48 +++++++++++++++---------
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h  |  3 +-
>   drivers/gpu/drm/amd/amdkfd/kfd_migrate.c |  2 +-
>   4 files changed, 39 insertions(+), 23 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> index e73dcfed5338..2713dd51ab9a 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> @@ -686,9 +686,10 @@ void amdgpu_gmc_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
>   	 * translation. Avoid this by doing the invalidation from the SDMA
>   	 * itself at least for GART.
>   	 */
> -	mutex_lock(&adev->mman.move_entity.gart_window_lock);
>   	for (i = 0; i < adev->mman.num_clear_entities; i++)
>   		mutex_lock(&adev->mman.clear_entities[i].gart_window_lock);
> +	for (i = 0; i < adev->mman.num_move_entities; i++)
> +		mutex_lock(&adev->mman.move_entities[i].gart_window_lock);
>   	r = amdgpu_job_alloc_with_ib(ring->adev, &adev->mman.default_entity.base,
>   				     AMDGPU_FENCE_OWNER_UNDEFINED,
>   				     16 * 4, AMDGPU_IB_POOL_IMMEDIATE,
> @@ -701,7 +702,8 @@ void amdgpu_gmc_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
>   	job->ibs->ptr[job->ibs->length_dw++] = ring->funcs->nop;
>   	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
>   	fence = amdgpu_job_submit(job);
> -	mutex_unlock(&adev->mman.move_entity.gart_window_lock);
> +	for (i = 0; i < adev->mman.num_move_entities; i++)
> +		mutex_unlock(&adev->mman.move_entities[i].gart_window_lock);
>   	for (i = 0; i < adev->mman.num_clear_entities; i++)
>   		mutex_unlock(&adev->mman.clear_entities[i].gart_window_lock);
>   
> @@ -711,7 +713,8 @@ void amdgpu_gmc_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
>   	return;
>   
>   error_alloc:
> -	mutex_unlock(&adev->mman.move_entity.gart_window_lock);
> +	for (i = 0; i < adev->mman.num_move_entities; i++)
> +		mutex_unlock(&adev->mman.move_entities[i].gart_window_lock);
>   	for (i = 0; i < adev->mman.num_clear_entities; i++)
>   		mutex_unlock(&adev->mman.clear_entities[i].gart_window_lock);
>   	dev_err(adev->dev, "Error flushing GPU TLB using the SDMA (%d)!\n", r);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> index 2f305ad32080..e1f0567fd2d5 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -401,7 +401,7 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
>   	dst.offset = 0;
>   
>   	r = amdgpu_ttm_copy_mem_to_mem(adev,
> -				       &adev->mman.move_entity,
> +				       &adev->mman.move_entities[0],
>   				       &src, &dst,
>   				       new_mem->size,
>   				       amdgpu_bo_encrypted(abo),
> @@ -414,7 +414,7 @@ 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(&adev->mman.move_entity,
> +		r = amdgpu_fill_buffer(&adev->mman.move_entities[0],
>   				       abo, 0, NULL, &wipe_fence,
>   				       AMDGPU_KERNEL_JOB_ID_MOVE_BLIT);
>   		if (r) {
> @@ -2167,10 +2167,11 @@ u32 amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
>   	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
>   	uint64_t size;
>   	int r, i, j;
> -	u32 num_clear_entities, windows, w;
> +	u32 num_clear_entities, num_move_entities, windows, w;
>   
>   	num_clear_entities = adev->sdma.num_instances;
> -	windows = adev->gmc.is_app_apu ? 0 : (2 + num_clear_entities);
> +	num_move_entities = MIN(adev->sdma.num_instances, TTM_NUM_MOVE_FENCES);
> +	windows = adev->gmc.is_app_apu ? 0 : (2 * num_move_entities + num_clear_entities);
>   
>   	if (!adev->mman.initialized || amdgpu_in_reset(adev) ||
>   	    adev->mman.buffer_funcs_enabled == enable || adev->gmc.is_app_apu)
> @@ -2186,20 +2187,25 @@ u32 amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
>   					  DRM_SCHED_PRIORITY_KERNEL, &sched,
>   					  1, NULL);
>   		if (r) {
> -			dev_err(adev->dev,
> -				"Failed setting up TTM BO eviction entity (%d)\n",
> +			dev_err(adev->dev, "Failed setting up entity (%d)\n",
>   				r);
>   			return 0;
>   		}
>   
> -		r = drm_sched_entity_init(&adev->mman.move_entity.base,
> -					  DRM_SCHED_PRIORITY_NORMAL, &sched,
> -					  1, NULL);
> -		if (r) {
> -			dev_err(adev->dev,
> -				"Failed setting up TTM BO move entity (%d)\n",
> -				r);
> -			goto error_free_entity;
> +		adev->mman.num_move_entities = num_move_entities;
> +		for (i = 0; i < num_move_entities; i++) {
> +			r = drm_sched_entity_init(&adev->mman.move_entities[i].base,
> +						  DRM_SCHED_PRIORITY_NORMAL, &sched,
> +						  1, NULL);
> +			if (r) {
> +				dev_err(adev->dev,
> +					"Failed setting up TTM BO move entities (%d)\n",
> +					r);
> +				for (j = 0; j < i; j++)
> +					drm_sched_entity_destroy(
> +						&adev->mman.move_entities[j].base);
> +				goto error_free_entity;
> +			}
>   		}
>   
>   		adev->mman.num_clear_entities = num_clear_entities;
> @@ -2214,6 +2220,9 @@ u32 amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
>   						  DRM_SCHED_PRIORITY_NORMAL, &sched,
>   						  1, NULL);
>   			if (r) {
> +				for (j = 0; j < num_move_entities; j++)
> +					drm_sched_entity_destroy(
> +						&adev->mman.move_entities[j].base);
>   				for (j = 0; j < i; j++)
>   					drm_sched_entity_destroy(
>   						&adev->mman.clear_entities[j].base);
> @@ -2225,9 +2234,11 @@ u32 amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
>   		/* Statically assign GART windows to each entity. */
>   		w = 0;
>   		mutex_init(&adev->mman.default_entity.gart_window_lock);
> -		adev->mman.move_entity.gart_window_id0 = w++;
> -		adev->mman.move_entity.gart_window_id1 = w++;
> -		mutex_init(&adev->mman.move_entity.gart_window_lock);
> +		for (i = 0; i < num_move_entities; i++) {
> +			adev->mman.move_entities[i].gart_window_id0 = w++;
> +			adev->mman.move_entities[i].gart_window_id1 = w++;
> +			mutex_init(&adev->mman.move_entities[i].gart_window_lock);
> +		}
>   		for (i = 0; i < num_clear_entities; i++) {
>   			/* Clearing entities don't use id0 */
>   			adev->mman.clear_entities[i].gart_window_id1 = w++;
> @@ -2236,7 +2247,8 @@ u32 amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
>   		WARN_ON(w != windows);
>   	} else {
>   		drm_sched_entity_destroy(&adev->mman.default_entity.base);
> -		drm_sched_entity_destroy(&adev->mman.move_entity.base);
> +		for (i = 0; i < num_move_entities; i++)
> +			drm_sched_entity_destroy(&adev->mman.move_entities[i].base);
>   		for (i = 0; i < num_clear_entities; i++)
>   			drm_sched_entity_destroy(&adev->mman.clear_entities[i].base);
>   		for (i = 0; i < TTM_NUM_MOVE_FENCES; i++) {
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> index 797f851a4578..9d4891e86675 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> @@ -72,9 +72,10 @@ struct amdgpu_mman {
>   	struct mutex				gtt_window_lock;
>   
>   	struct amdgpu_ttm_buffer_entity default_entity; /* has no gart windows */
> -	struct amdgpu_ttm_buffer_entity move_entity;
>   	struct amdgpu_ttm_buffer_entity *clear_entities;
>   	u32 num_clear_entities;
> +	struct amdgpu_ttm_buffer_entity move_entities[TTM_NUM_MOVE_FENCES];
> +	u32 num_move_entities;
>   
>   	struct amdgpu_vram_mgr vram_mgr;
>   	struct amdgpu_gtt_mgr gtt_mgr;
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> index bc47fc362a17..943c3438c7ee 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> @@ -136,7 +136,7 @@ svm_migrate_copy_memory_gart(struct amdgpu_device *adev, dma_addr_t *sys,
>   	u64 size;
>   	int r;
>   
> -	entity = &adev->mman.move_entity;
> +	entity = &adev->mman.move_entities[0];
>   
>   	mutex_lock(&entity->gart_window_lock);
>