diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
index 1beae5b..2fb299a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
@@ -40,7 +40,7 @@ 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, false);
 		if (r)
 			goto exit_do_move;
 		r = dma_fence_wait(fence, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 8ee6965..c34cf2c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -535,7 +535,7 @@ int amdgpu_bo_backup_to_shadow(struct amdgpu_device *adev,
 
 	r = amdgpu_copy_buffer(ring, bo_addr, shadow_addr,
 			       amdgpu_bo_size(bo), resv, fence,
-			       direct);
+			       direct, false);
 	if (!r)
 		amdgpu_bo_fence(bo, *fence, true);
 
@@ -588,7 +588,7 @@ int amdgpu_bo_restore_from_shadow(struct amdgpu_device *adev,
 
 	r = amdgpu_copy_buffer(ring, shadow_addr, bo_addr,
 			       amdgpu_bo_size(bo), resv, fence,
-			       direct);
+			       direct, false);
 	if (!r)
 		amdgpu_bo_fence(bo, *fence, true);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
index 15510da..d02e611 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, false);
+				       size, NULL, &fence, false, 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, false);
+				       size, NULL, &fence, false, 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 c9b131b..8c5f75d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -318,7 +318,7 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 
 		r = amdgpu_copy_buffer(ring, old_start, new_start,
 				       cur_pages * PAGE_SIZE,
-				       bo->resv, &next, false);
+				       bo->resv, &next, false, false);
 		if (r)
 			goto error;
 
@@ -1256,12 +1256,11 @@ int amdgpu_mmap(struct file *filp, struct vm_area_struct *vma)
 	return ttm_bo_mmap(filp, vma, &adev->mman.bdev);
 }
 
-int amdgpu_copy_buffer(struct amdgpu_ring *ring,
-		       uint64_t src_offset,
-		       uint64_t dst_offset,
-		       uint32_t byte_count,
+int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
+		       uint64_t dst_offset, uint32_t byte_count,
 		       struct reservation_object *resv,
-		       struct dma_fence **fence, bool direct_submit)
+		       struct dma_fence **fence, bool direct_submit,
+		       bool vm_needs_flush)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_job *job;
@@ -1283,6 +1282,7 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 
+	job->vm_needs_flush = vm_needs_flush;
 	if (resv) {
 		r = amdgpu_sync_resv(adev, &job->sync, resv,
 				     AMDGPU_FENCE_OWNER_UNDEFINED);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 6bdede8..cd5bbfa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -61,12 +61,11 @@ int amdgpu_gtt_mgr_alloc(struct ttm_mem_type_manager *man,
 			 const struct ttm_place *place,
 			 struct ttm_mem_reg *mem);
 
-int amdgpu_copy_buffer(struct amdgpu_ring *ring,
-		       uint64_t src_offset,
-		       uint64_t dst_offset,
-		       uint32_t byte_count,
+int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
+		       uint64_t dst_offset, uint32_t byte_count,
 		       struct reservation_object *resv,
-		       struct dma_fence **fence, bool direct_submit);
+		       struct dma_fence **fence, bool direct_submit,
+		       bool vm_needs_flush);
 int amdgpu_fill_buffer(struct amdgpu_bo *bo,
 			uint32_t src_data,
 			struct reservation_object *resv,