1 files changed, 23 insertions, 15 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 78ab08e8f..ae1609e73 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -53,10 +53,8 @@ vc4_free_hang_state(struct drm_device *dev, struct vc4_hang_state *state)
 {
 	unsigned int i;
 
-	mutex_lock(&dev->struct_mutex);
 	for (i = 0; i < state->user_state.bo_count; i++)
-		drm_gem_object_unreference(state->bo[i]);
-	mutex_unlock(&dev->struct_mutex);
+		drm_gem_object_unreference_unlocked(state->bo[i]);
 
 	kfree(state);
 }
@@ -473,6 +471,11 @@ vc4_update_bo_seqnos(struct vc4_exec_info *exec, uint64_t seqno)
 	list_for_each_entry(bo, &exec->unref_list, unref_head) {
 		bo->seqno = seqno;
 	}
+
+	for (i = 0; i < exec->rcl_write_bo_count; i++) {
+		bo = to_vc4_bo(&exec->rcl_write_bo[i]->base);
+		bo->write_seqno = seqno;
+	}
 }
 
 /* Queues a struct vc4_exec_info for execution.  If no job is
@@ -536,8 +539,8 @@ vc4_cl_lookup_bos(struct drm_device *dev,
 		return -EINVAL;
 	}
 
-	exec->bo = kcalloc(exec->bo_count, sizeof(struct drm_gem_cma_object *),
-			   GFP_KERNEL);
+	exec->bo = drm_calloc_large(exec->bo_count,
+				    sizeof(struct drm_gem_cma_object *));
 	if (!exec->bo) {
 		DRM_ERROR("Failed to allocate validated BO pointers\n");
 		return -ENOMEM;
@@ -610,7 +613,7 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec)
 	 * read the contents back for validation, and I think the
 	 * bo->vaddr is uncached access.
 	 */
-	temp = kmalloc(temp_size, GFP_KERNEL);
+	temp = drm_malloc_ab(temp_size, 1);
 	if (!temp) {
 		DRM_ERROR("Failed to allocate storage for copying "
 			  "in bin/render CLs.\n");
@@ -675,9 +678,17 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec)
 		goto fail;
 
 	ret = vc4_validate_shader_recs(dev, exec);
+	if (ret)
+		goto fail;
+
+	/* Block waiting on any previous rendering into the CS's VBO,
+	 * IB, or textures, so that pixels are actually written by the
+	 * time we try to read them.
+	 */
+	ret = vc4_wait_for_seqno(dev, exec->bin_dep_seqno, ~0ull, true);
 
 fail:
-	kfree(temp);
+	drm_free_large(temp);
 	return ret;
 }
 
@@ -687,21 +698,18 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec)
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	unsigned i;
 
-	/* Need the struct lock for drm_gem_object_unreference(). */
-	mutex_lock(&dev->struct_mutex);
 	if (exec->bo) {
 		for (i = 0; i < exec->bo_count; i++)
-			drm_gem_object_unreference(&exec->bo[i]->base);
-		kfree(exec->bo);
+			drm_gem_object_unreference_unlocked(&exec->bo[i]->base);
+		drm_free_large(exec->bo);
 	}
 
 	while (!list_empty(&exec->unref_list)) {
 		struct vc4_bo *bo = list_first_entry(&exec->unref_list,
 						     struct vc4_bo, unref_head);
 		list_del(&bo->unref_head);
-		drm_gem_object_unreference(&bo->base.base);
+		drm_gem_object_unreference_unlocked(&bo->base.base);
 	}
-	mutex_unlock(&dev->struct_mutex);
 
 	mutex_lock(&vc4->power_lock);
 	if (--vc4->power_refcount == 0)
@@ -947,8 +955,8 @@ vc4_gem_destroy(struct drm_device *dev)
 		vc4->overflow_mem = NULL;
 	}
 
-	vc4_bo_cache_destroy(dev);
-
 	if (vc4->hang_state)
 		vc4_free_hang_state(dev, vc4->hang_state);
+
+	vc4_bo_cache_destroy(dev);
 }