linux-kernel - [PATCH 4.4 024/163] sched/cgroup: Fix/cleanup cgroup teardown/init

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20160503000509.336675366@linuxfoundation.org>
Date:	Mon,  2 May 2016 17:10:52 -0700
From:	Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:	linux-kernel@...r.kernel.org
Cc:	Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
	stable@...r.kernel.org, Tejun Heo <tj@...nel.org>,
	Kazuki Yamaguchi <k@....jp>,
	Niklas Cassel <niklas.cassel@...s.com>,
	"Peter Zijlstra (Intel)" <peterz@...radead.org>,
	Linus Torvalds <torvalds@...ux-foundation.org>,
	Thomas Gleixner <tglx@...utronix.de>,
	Ingo Molnar <mingo@...nel.org>
Subject: [PATCH 4.4 024/163] sched/cgroup: Fix/cleanup cgroup teardown/init

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

------------------

From: Peter Zijlstra <peterz@...radead.org>

commit 2f5177f0fd7e531b26d54633be62d1d4cb94621c upstream.

The CPU controller hasn't kept up with the various changes in the whole
cgroup initialization / destruction sequence, and commit:

  2e91fa7f6d45 ("cgroup: keep zombies associated with their original cgroups")

caused it to explode.

The reason for this is that zombies do not inhibit css_offline() from
being called, but do stall css_released(). Now we tear down the cfs_rq
structures on css_offline() but zombies can run after that, leading to
use-after-free issues.

The solution is to move the tear-down to css_released(), which
guarantees nobody (including no zombies) is still using our cgroup.

Furthermore, a few simple cleanups are possible too. There doesn't
appear to be any point to us using css_online() (anymore?) so fold that
in css_alloc().

And since cgroup code guarantees an RCU grace period between
css_released() and css_free() we can forgo using call_rcu() and free the
stuff immediately.

Suggested-by: Tejun Heo <tj@...nel.org>
Reported-by: Kazuki Yamaguchi <k@....jp>
Reported-by: Niklas Cassel <niklas.cassel@...s.com>
Tested-by: Niklas Cassel <niklas.cassel@...s.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Acked-by: Tejun Heo <tj@...nel.org>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Thomas Gleixner <tglx@...utronix.de>
Fixes: 2e91fa7f6d45 ("cgroup: keep zombies associated with their original cgroups")
Link: http://lkml.kernel.org/r/20160316152245.GY6344@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@...nel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>

---
 kernel/sched/core.c |   35 ++++++++++++++---------------------
 1 file changed, 14 insertions(+), 21 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7693,7 +7693,7 @@ void set_curr_task(int cpu, struct task_
 /* task_group_lock serializes the addition/removal of task groups */
 static DEFINE_SPINLOCK(task_group_lock);
 
-static void free_sched_group(struct task_group *tg)
+static void sched_free_group(struct task_group *tg)
 {
 	free_fair_sched_group(tg);
 	free_rt_sched_group(tg);
@@ -7719,7 +7719,7 @@ struct task_group *sched_create_group(st
 	return tg;
 
 err:
-	free_sched_group(tg);
+	sched_free_group(tg);
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -7739,17 +7739,16 @@ void sched_online_group(struct task_grou
 }
 
 /* rcu callback to free various structures associated with a task group */
-static void free_sched_group_rcu(struct rcu_head *rhp)
+static void sched_free_group_rcu(struct rcu_head *rhp)
 {
 	/* now it should be safe to free those cfs_rqs */
-	free_sched_group(container_of(rhp, struct task_group, rcu));
+	sched_free_group(container_of(rhp, struct task_group, rcu));
 }
 
-/* Destroy runqueue etc associated with a task group */
 void sched_destroy_group(struct task_group *tg)
 {
 	/* wait for possible concurrent references to cfs_rqs complete */
-	call_rcu(&tg->rcu, free_sched_group_rcu);
+	call_rcu(&tg->rcu, sched_free_group_rcu);
 }
 
 void sched_offline_group(struct task_group *tg)
@@ -8210,31 +8209,26 @@ cpu_cgroup_css_alloc(struct cgroup_subsy
 	if (IS_ERR(tg))
 		return ERR_PTR(-ENOMEM);
 
+	sched_online_group(tg, parent);
+
 	return &tg->css;
 }
 
-static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
+static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
 {
 	struct task_group *tg = css_tg(css);
-	struct task_group *parent = css_tg(css->parent);
 
-	if (parent)
-		sched_online_group(tg, parent);
-	return 0;
+	sched_offline_group(tg);
 }
 
 static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
 {
 	struct task_group *tg = css_tg(css);
 
-	sched_destroy_group(tg);
-}
-
-static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
-{
-	struct task_group *tg = css_tg(css);
-
-	sched_offline_group(tg);
+	/*
+	 * Relies on the RCU grace period between css_released() and this.
+	 */
+	sched_free_group(tg);
 }
 
 static void cpu_cgroup_fork(struct task_struct *task, void *private)
@@ -8594,9 +8588,8 @@ static struct cftype cpu_files[] = {
 
 struct cgroup_subsys cpu_cgrp_subsys = {
 	.css_alloc	= cpu_cgroup_css_alloc,
+	.css_released	= cpu_cgroup_css_released,
 	.css_free	= cpu_cgroup_css_free,
-	.css_online	= cpu_cgroup_css_online,
-	.css_offline	= cpu_cgroup_css_offline,
 	.fork		= cpu_cgroup_fork,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,