cgroups: use simple wait in css_release()

To avoid:
|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:914
|in_atomic(): 1, irqs_disabled(): 0, pid: 92, name: rcuc/11
|2 locks held by rcuc/11/92:
| #0:  (rcu_callback){......}, at: [<ffffffff810e037e>] rcu_cpu_kthread+0x3de/0x940
| #1:  (rcu_read_lock_sched){......}, at: [<ffffffff81328390>] percpu_ref_call_confirm_rcu+0x0/0xd0
|Preemption disabled at:[<ffffffff813284e2>] percpu_ref_switch_to_atomic_rcu+0x82/0xc0
|CPU: 11 PID: 92 Comm: rcuc/11 Not tainted 3.18.7-rt0+ #1
| ffff8802398cdf80 ffff880235f0bc28 ffffffff815b3a12 0000000000000000
| 0000000000000000 ffff880235f0bc48 ffffffff8109aa16 0000000000000000
| ffff8802398cdf80 ffff880235f0bc78 ffffffff815b8dd4 000000000000df80
|Call Trace:
| [<ffffffff815b3a12>] dump_stack+0x4f/0x7c
| [<ffffffff8109aa16>] __might_sleep+0x116/0x190
| [<ffffffff815b8dd4>] rt_spin_lock+0x24/0x60
| [<ffffffff8108d2cd>] queue_work_on+0x6d/0x1d0
| [<ffffffff8110c881>] css_release+0x81/0x90
| [<ffffffff8132844e>] percpu_ref_call_confirm_rcu+0xbe/0xd0
| [<ffffffff813284e2>] percpu_ref_switch_to_atomic_rcu+0x82/0xc0
| [<ffffffff810e03e5>] rcu_cpu_kthread+0x445/0x940
| [<ffffffff81098a2d>] smpboot_thread_fn+0x18d/0x2d0
| [<ffffffff810948d8>] kthread+0xe8/0x100
| [<ffffffff815b9c3c>] ret_from_fork+0x7c/0xb0

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index b9cb94c3102a402539368cee3016d81b1cc173f9..3bd502178b986665257cc8478d5fc614c542b449 100644 (file)
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -22,6 +22,7 @@
 #include <linux/seq_file.h>
 #include <linux/kernfs.h>
 #include <linux/wait.h>
+#include <linux/work-simple.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -91,6 +92,7 @@ struct cgroup_subsys_state {
        /* percpu_ref killing and RCU release */
        struct rcu_head rcu_head;
        struct work_struct destroy_work;
+       struct swork_event destroy_swork;
 };
 
 /* bits in struct cgroup_subsys_state flags field */

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 29a7b2cc593e3f50a425f1dbbf187d5d1fb4542f..e86d1032d8742221d69d3f5975891c846bdf34d6 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4424,10 +4424,10 @@ static void css_free_rcu_fn(struct rcu_head *rcu_head)
        queue_work(cgroup_destroy_wq, &css->destroy_work);
 }
 
-static void css_release_work_fn(struct work_struct *work)
+static void css_release_work_fn(struct swork_event *sev)
 {
        struct cgroup_subsys_state *css =
-               container_of(work, struct cgroup_subsys_state, destroy_work);
+               container_of(sev, struct cgroup_subsys_state, destroy_swork);
        struct cgroup_subsys *ss = css->ss;
        struct cgroup *cgrp = css->cgroup;
 
@@ -4466,8 +4466,8 @@ static void css_release(struct percpu_ref *ref)
        struct cgroup_subsys_state *css =
                container_of(ref, struct cgroup_subsys_state, refcnt);
 
-       INIT_WORK(&css->destroy_work, css_release_work_fn);
-       queue_work(cgroup_destroy_wq, &css->destroy_work);
+       INIT_SWORK(&css->destroy_swork, css_release_work_fn);
+       swork_queue(&css->destroy_swork);
 }
 
 static void init_and_link_css(struct cgroup_subsys_state *css,
@@ -5068,6 +5068,7 @@ static int __init cgroup_wq_init(void)
         */
        cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
        BUG_ON(!cgroup_destroy_wq);
+       BUG_ON(swork_get());
 
        /*
         * Used to destroy pidlists and separate to serve as flush domain.