cgroups: remove events before destroying subsystem state objects

Events should be removed after rmdir of cgroup directory, but before
destroying subsystem state objects.  Let's take reference to cgroup
directory dentry to do that.
Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hioryu@jp.fujitsu.com>
Cc: Paul Menage <menage@google.com>
Acked-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: Dan Malek <dan@embeddedalley.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/cgroup.h

@@ -396,9 +396,6 @@ struct cftype {
 	 * closes the eventfd or on cgroup removing.
 	 * This callback must be implemented, if you want provide
 	 * notification functionality.
-	 *
-	 * Be careful. It can be called after destroy(), so you have
-	 * to keep all nesessary data, until all events are removed.
 	 */
 	int (*unregister_event)(struct cgroup *cgrp, struct cftype *cft,
 			struct eventfd_ctx *eventfd);

kernel/cgroup.c

@@ -2994,6 +2994,7 @@ static void cgroup_event_remove(struct work_struct *work)
 
 	eventfd_ctx_put(event->eventfd);
 	kfree(event);
+	dput(cgrp->dentry);
 }
 
 /*
@@ -3114,6 +3115,13 @@ static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft,
 		goto fail;
 	}
 
+	/*
+	 * Events should be removed after rmdir of cgroup directory, but before
+	 * destroying subsystem state objects. Let's take reference to cgroup
+	 * directory dentry to do that.
+	 */
+	dget(cgrp->dentry);
+
 	spin_lock(&cgrp->event_list_lock);
 	list_add(&event->list, &cgrp->event_list);
 	spin_unlock(&cgrp->event_list_lock);

mm/memcontrol.c

@@ -3361,12 +3361,6 @@ static int mem_cgroup_register_event(struct cgroup *cgrp, struct cftype *cft,
 		}
 	}
 
-	/*
-	 * We need to increment refcnt to be sure that all thresholds
-	 * will be unregistered before calling __mem_cgroup_free()
-	 */
-	mem_cgroup_get(memcg);
-
 	if (type == _MEM)
 		rcu_assign_pointer(memcg->thresholds, thresholds_new);
 	else
@@ -3460,9 +3454,6 @@ assign:
 	/* To be sure that nobody uses thresholds before freeing it */
 	synchronize_rcu();
 
-	for (i = 0; i < thresholds->size - size; i++)
-		mem_cgroup_put(memcg);
-
 	kfree(thresholds);
 unlock:
 	mutex_unlock(&memcg->thresholds_lock);