diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
index 33e47a43ae321bded79822cfb03318c79a155211..345305235349c0c40a1812e6555900cfbea6b187 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
@@ -39,7 +39,8 @@ static int amdgpu_benchmark_do_move(struct amdgpu_device *adev, unsigned size,
 	start_jiffies = jiffies;
 	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, saddr, daddr, size, NULL, &fence,
+				       false);
 		if (r)
 			goto exit_do_move;
 		r = fence_wait(fence, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
index 05a53f4fc3349e8b5075d56e37c45dcc5da49cf7..b827c75e95deb1295f6ec14a5a781fc6b922939c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
@@ -111,7 +111,7 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 		amdgpu_bo_kunmap(gtt_obj[i]);
 
 		r = amdgpu_copy_buffer(ring, gtt_addr, vram_addr,
-				       size, NULL, &fence);
+				       size, NULL, &fence, false);
 
 		if (r) {
 			DRM_ERROR("Failed GTT->VRAM copy %d\n", i);
@@ -156,7 +156,7 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 		amdgpu_bo_kunmap(vram_obj);
 
 		r = amdgpu_copy_buffer(ring, vram_addr, gtt_addr,
-				       size, NULL, &fence);
+				       size, NULL, &fence, false);
 
 		if (r) {
 			DRM_ERROR("Failed VRAM->GTT copy %d\n", i);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 783a9703c1607df60e85254d7461cac6e04868d0..bdc76e28a2405f51a8ea8ca96a5c49be53e4255c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -282,7 +282,7 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 
 	r = amdgpu_copy_buffer(ring, old_start, new_start,
 			       new_mem->num_pages * PAGE_SIZE, /* bytes */
-			       bo->resv, &fence);
+			       bo->resv, &fence, false);
 	if (r)
 		return r;
 
@@ -1143,7 +1143,7 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring,
 		       uint64_t dst_offset,
 		       uint32_t byte_count,
 		       struct reservation_object *resv,
-		       struct fence **fence)
+		       struct fence **fence, bool direct_submit)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_job *job;
@@ -1187,12 +1187,21 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring,
 
 	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
 	WARN_ON(job->ibs[0].length_dw > num_dw);
-	r = amdgpu_job_submit(job, ring, &adev->mman.entity,
-			      AMDGPU_FENCE_OWNER_UNDEFINED, fence);
-	if (r)
-		goto error_free;
+	if (direct_submit) {
+		r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs,
+				       NULL, NULL, fence);
+		job->fence = fence_get(*fence);
+		if (r)
+			DRM_ERROR("Error scheduling IBs (%d)\n", r);
+		amdgpu_job_free(job);
+	} else {
+		r = amdgpu_job_submit(job, ring, &adev->mman.entity,
+				      AMDGPU_FENCE_OWNER_UNDEFINED, fence);
+		if (r)
+			goto error_free;
+	}
 
-	return 0;
+	return r;
 
 error_free:
 	amdgpu_job_free(job);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 8927e0e5012aa249deb68f0a69691cb21f10555e..4d39276053092ba5484a3db234e1b50eaad97248 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -68,7 +68,7 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring,
 		       uint64_t dst_offset,
 		       uint32_t byte_count,
 		       struct reservation_object *resv,
-		       struct fence **fence);
+		       struct fence **fence, bool direct_submit);
 int amdgpu_fill_buffer(struct amdgpu_bo *bo,
 			uint32_t src_data,
 			struct reservation_object *resv,