[PATCH 4.2.y-ckt 025/273] cgroup: make sure a parent css isn't offlined before its children

Kamal Mostafa kamal at canonical.com
Mon Mar 7 22:46:56 UTC 2016


4.2.8-ckt5 -stable review patch.  If anyone has any objections, please let me know.

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

From: Tejun Heo <tj at kernel.org>

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 at kernel.org>
Reported-and-tested-by: Christian Borntraeger <borntraeger at de.ibm.com>
Reported-by: Brian Christiansen <brian.o.christiansen at gmail.com>
Link: http://lkml.kernel.org/g/5698A023.9070703@de.ibm.com
Link: http://lkml.kernel.org/g/CAKB58ikDkzc8REt31WBkD99+hxNzjK4+FBmhkgS+NVrC9vjMSg@mail.gmail.com
Cc: Heiko Carstens <heiko.carstens at de.ibm.com>
Cc: Peter Zijlstra <peterz at infradead.org>
Signed-off-by: Kamal Mostafa <kamal at canonical.com>
---
 include/linux/cgroup-defs.h |  6 ++++++
 kernel/cgroup.c             | 22 +++++++++++++++++-----
 2 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 430c876..1f847d5 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -117,6 +117,12 @@ 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 fe6f855..42a4920 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4564,6 +4564,7 @@ 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);
@@ -4586,6 +4587,10 @@ 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;
 }
@@ -4823,10 +4828,15 @@ 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 */
@@ -4835,8 +4845,10 @@ 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);
+	}
 }
 
 /**
-- 
2.7.0





More information about the kernel-team mailing list