[PATCH 3.16.y-ckt 056/129] cgroup: make sure a parent css isn't offlined before its children

From: Luis Henriques
Date: Fri Feb 26 2016 - 05:56:42 EST


3.16.7-ckt25 -stable review patch. If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Tejun Heo <tj@xxxxxxxxxx>

commit aa226ff4a1ce79f229c6b7a4c0a14e17fececd01 upstream.

There are three subsystem callbacks in css shutdown path -
css_offline(), css_released() and css_free(). Except for
css_released(), cgroup core didn't 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 bugs in cpu and
memory 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 memory controller bug and allows the fix for cpu
controller.

Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Reported-and-tested-by: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Reported-by: Brian Christiansen <brian.o.christiansen@xxxxxxxxx>
Link: http://lkml.kernel.org/g/5698A023.9070703@xxxxxxxxxx
Link: http://lkml.kernel.org/g/CAKB58ikDkzc8REt31WBkD99+hxNzjK4+FBmhkgS+NVrC9vjMSg@xxxxxxxxxxxxxx
Cc: Heiko Carstens <heiko.carstens@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
[ luis: backported to 3.16:
- file rename: cgroup-defs.h -> cgroup.h
- adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@xxxxxxxxxxxxx>
---
include/linux/cgroup.h | 6 ++++++
kernel/cgroup.c | 22 +++++++++++++++++-----
2 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 8a111dd42d7a..c2d312de22f8 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -88,6 +88,12 @@ 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;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 58fd665d1217..660a21884771 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4278,6 +4278,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
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);
@@ -4300,6 +4301,10 @@ static int online_css(struct cgroup_subsys_state *css)
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;
}
@@ -4524,10 +4529,15 @@ static void css_killed_work_fn(struct work_struct *work)
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 */
@@ -4536,8 +4546,10 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
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);
+ }
}

/**