diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c22eecb..4a7fb40 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -98,6 +98,14 @@
 			   lockdep_is_held(&cgroup_mutex),		\
 			   "cgroup_mutex or RCU read lock required");
 
+#ifdef CONFIG_LOCKDEP
+#define cgroup_assert_mutex_or_root_locked()				\
+	WARN_ON_ONCE(debug_locks && (!lockdep_is_held(&cgroup_mutex) &&	\
+				     !lockdep_is_held(&cgroup_root_mutex)))
+#else
+#define cgroup_assert_mutex_or_root_locked()	do { } while (0)
+#endif
+
 /*
  * cgroup destruction makes heavy use of work items and there can be a lot
  * of concurrent destructions.  Use a separate workqueue so that cgroup
@@ -237,14 +245,15 @@
 /**
  * for_each_subsys - iterate all loaded cgroup subsystems
  * @ss: the iteration cursor
- * @i: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
+ * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
  *
- * Should be called under cgroup_mutex.
+ * Iterates through all loaded subsystems.  Should be called under
+ * cgroup_mutex or cgroup_root_mutex.
  */
-#define for_each_subsys(ss, i)						\
-	for ((i) = 0; (i) < CGROUP_SUBSYS_COUNT; (i)++)			\
-		if (({ lockdep_assert_held(&cgroup_mutex);		\
-		       !((ss) = cgroup_subsys[i]); })) { }		\
+#define for_each_subsys(ss, ssid)					\
+	for (({ cgroup_assert_mutex_or_root_locked(); (ssid) = 0; });	\
+	     (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)			\
+		if (!((ss) = cgroup_subsys[(ssid)])) { }		\
 		else
 
 /**
@@ -4592,6 +4601,7 @@
 	cgroup_init_cftsets(ss);
 
 	mutex_lock(&cgroup_mutex);
+	mutex_lock(&cgroup_root_mutex);
 	cgroup_subsys[ss->subsys_id] = ss;
 
 	/*
@@ -4641,10 +4651,12 @@
 		goto err_unload;
 
 	/* success! */
+	mutex_unlock(&cgroup_root_mutex);
 	mutex_unlock(&cgroup_mutex);
 	return 0;
 
 err_unload:
+	mutex_unlock(&cgroup_root_mutex);
 	mutex_unlock(&cgroup_mutex);
 	/* @ss can't be mounted here as try_module_get() would fail */
 	cgroup_unload_subsys(ss);
@@ -4674,6 +4686,7 @@
 	BUG_ON(ss->root != &cgroup_dummy_root);
 
 	mutex_lock(&cgroup_mutex);
+	mutex_lock(&cgroup_root_mutex);
 
 	offline_css(cgroup_css(cgroup_dummy_top, ss));
 
@@ -4708,6 +4721,7 @@
 	ss->css_free(cgroup_css(cgroup_dummy_top, ss));
 	RCU_INIT_POINTER(cgroup_dummy_top->subsys[ss->subsys_id], NULL);
 
+	mutex_unlock(&cgroup_root_mutex);
 	mutex_unlock(&cgroup_mutex);
 }
 EXPORT_SYMBOL_GPL(cgroup_unload_subsys);