[PATCH 1/2] cgroup: make sure a parent css isn't offlined before its children

[Tejun Heo]

There are three subsystem callbacks in css shutdown path -
css_offline(), css_released() and css_free().  Except for
css_released(), cgroup core didn't use to guarantee the order of
invocation.  css_offline() or css_free() could be called on a parent
css before its children.  This behavior is unexpected and led to
use-after-free in cpu controller.

This patch updates offline path so that a parent css is never offlined
before its children.  Each css keeps online_cnt which reaches zero iff
itself and all its children are offline and offline_css() is invoked
only after online_cnt reaches zero.

This fixes the reported cpu controller malfunction.  The next patch
will update css_free() handling.

Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Reported-by: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Link: http://lkml.kernel.org/g/5698A023.9070703@xxxxxxxxxx
Cc: Heiko Carstens <heiko.carstens@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
---
Hello, Christian.

Can you please verify whether this patch fixes the issue?

Thanks.

 include/linux/cgroup-defs.h |    6 ++++++
 kernel/cgroup.c             |   22 +++++++++++++++++-----
 2 files changed, 23 insertions(+), 5 deletions(-)

--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -127,6 +127,12 @@ struct cgroup_subsys_state {
 	 */
 	u64 serial_nr;
 
+	/*
+	 * Incremented by online self and children.  Used to guarantee that
+	 * parents are not offlined before their children.
+	 */
+	atomic_t online_cnt;
+
 	/* percpu_ref killing and RCU release */
 	struct rcu_head rcu_head;
 	struct work_struct destroy_work;
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4761,6 +4761,7 @@ static void init_and_link_css(struct cgr
 	INIT_LIST_HEAD(&css->sibling);
 	INIT_LIST_HEAD(&css->children);
 	css->serial_nr = css_serial_nr_next++;
+	atomic_set(&css->online_cnt, 0);
 
 	if (cgroup_parent(cgrp)) {
 		css->parent = cgroup_css(cgroup_parent(cgrp), ss);
@@ -4783,6 +4784,10 @@ static int online_css(struct cgroup_subs
 	if (!ret) {
 		css->flags |= CSS_ONLINE;
 		rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
+
+		atomic_inc(&css->online_cnt);
+		if (css->parent)
+			atomic_inc(&css->parent->online_cnt);
 	}
 	return ret;
 }
@@ -5020,10 +5025,15 @@ static void css_killed_work_fn(struct wo
 		container_of(work, struct cgroup_subsys_state, destroy_work);
 
 	mutex_lock(&cgroup_mutex);
-	offline_css(css);
-	mutex_unlock(&cgroup_mutex);
 
-	css_put(css);
+	do {
+		offline_css(css);
+		css_put(css);
+		/* @css can't go away while we're holding cgroup_mutex */
+		css = css->parent;
+	} while (css && atomic_dec_and_test(&css->online_cnt));
+
+	mutex_unlock(&cgroup_mutex);
 }
 
 /* css kill confirmation processing requires process context, bounce */
@@ -5032,8 +5042,10 @@ static void css_killed_ref_fn(struct per
 	struct cgroup_subsys_state *css =
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
-	INIT_WORK(&css->destroy_work, css_killed_work_fn);
-	queue_work(cgroup_destroy_wq, &css->destroy_work);
+	if (atomic_dec_and_test(&css->online_cnt)) {
+		INIT_WORK(&css->destroy_work, css_killed_work_fn);
+		queue_work(cgroup_destroy_wq, &css->destroy_work);
+	}
 }
 
 /**