In case the fill job depends on a previous fence, the caller can now pass it to make sure the ordering of the jobs is correct.
Signed-off-by: Pierre-Eric Pelloux-Prayer pierre-eric.pelloux-prayer@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 22 ++++++++++++++++------ drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 1 + 3 files changed, 18 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index e7b2cae031b3..be3532134e46 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1322,7 +1322,7 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) goto out;
r = amdgpu_fill_buffer(&adev->mman.clear_entities[0], abo, 0, &bo->base._resv, - &fence, AMDGPU_KERNEL_JOB_ID_CLEAR_ON_RELEASE); + &fence, NULL, 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 1b3945513157..b94ac16c785b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -173,6 +173,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo, * @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 + * @dep: optional dependency * * Setup one of the GART windows to access a specific piece of memory or return * the physical address for local memory. @@ -182,7 +183,8 @@ static int amdgpu_ttm_map_buffer(struct drm_sched_entity *entity, struct ttm_resource *mem, struct amdgpu_res_cursor *mm_cur, unsigned int window, struct amdgpu_ring *ring, - bool tmz, uint64_t *size, uint64_t *addr) + bool tmz, uint64_t *size, uint64_t *addr, + struct dma_fence *dep) { struct amdgpu_device *adev = ring->adev; unsigned int offset, num_pages, num_dw, num_bytes; @@ -234,6 +236,9 @@ static int amdgpu_ttm_map_buffer(struct drm_sched_entity *entity, if (r) return r;
+ if (dep) + drm_sched_job_add_dependency(&job->base, dma_fence_get(dep)); + src_addr = num_dw * 4; src_addr += job->ibs[0].gpu_addr;
@@ -326,13 +331,15 @@ static int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev, /* Map src to window 0 and dst to window 1. */ r = amdgpu_ttm_map_buffer(&entity->base, src->bo, src->mem, &src_mm, - entity->gart_window_id0, ring, tmz, &cur_size, &from); + entity->gart_window_id0, ring, tmz, &cur_size, &from, + NULL); if (r) goto error;
r = amdgpu_ttm_map_buffer(&entity->base, dst->bo, dst->mem, &dst_mm, - entity->gart_window_id1, ring, tmz, &cur_size, &to); + entity->gart_window_id1, ring, tmz, &cur_size, &to, + NULL); if (r) goto error;
@@ -415,7 +422,7 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo, struct dma_fence *wipe_fence = NULL;
r = amdgpu_fill_buffer(&adev->mman.move_entities[0], - abo, 0, NULL, &wipe_fence, + abo, 0, NULL, &wipe_fence, fence, AMDGPU_KERNEL_JOB_ID_MOVE_BLIT); if (r) { goto error; @@ -2443,7 +2450,8 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
r = amdgpu_ttm_map_buffer(&entity->base, &bo->tbo, bo->tbo.resource, &cursor, - entity->gart_window_id1, ring, false, &size, &addr); + entity->gart_window_id1, ring, false, &size, &addr, + NULL); if (r) goto err;
@@ -2469,6 +2477,7 @@ int amdgpu_fill_buffer(struct amdgpu_ttm_entity *entity, uint32_t src_data, struct dma_resv *resv, struct dma_fence **f, + struct dma_fence *dependency, u64 k_job_id) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); @@ -2496,7 +2505,8 @@ int amdgpu_fill_buffer(struct amdgpu_ttm_entity *entity, r = amdgpu_ttm_map_buffer(&entity->base, &bo->tbo, bo->tbo.resource, &dst, entity->gart_window_id1, ring, false, - &cur_size, &to); + &cur_size, &to, + dependency); 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 2874f054e869..9dd2a76a5641 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -186,6 +186,7 @@ int amdgpu_fill_buffer(struct amdgpu_ttm_entity *entity, uint32_t src_data, struct dma_resv *resv, struct dma_fence **f, + struct dma_fence *dependency, u64 k_job_id);
int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo);