From efa2a039afc3eac43e529e02bb47df62042a504c Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 18 Apr 2014 11:04:16 -0400 Subject: [PATCH] workqueue: make rescuer_thread() empty wq->maydays list before exiting commit 4d595b866d2c653dc90a492b9973a834eabfa354 upstream. After a @pwq is scheduled for emergency execution, other workers may consume the affectd work items before the rescuer gets to them. This means that a workqueue many have pwqs queued on @wq->maydays list while not having any work item pending or in-flight. If destroy_workqueue() executes in such condition, the rescuer may exit without emptying @wq->maydays. This currently doesn't cause any actual harm. destroy_workqueue() can safely destroy all the involved data structures whether @wq->maydays is populated or not as nobody access the list once the rescuer exits. However, this is nasty and makes future development difficult. Let's update rescuer_thread() so that it empties @wq->maydays after seeing should_stop to guarantee that the list is empty on rescuer exit. tj: Updated comment and patch description. Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- kernel/workqueue.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 8b5ef62..b6a3941 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2397,6 +2397,7 @@ static int rescuer_thread(void *__rescuer) struct worker *rescuer = __rescuer; struct workqueue_struct *wq = rescuer->rescue_wq; struct list_head *scheduled = &rescuer->scheduled; + bool should_stop; set_user_nice(current, RESCUER_NICE_LEVEL); @@ -2408,11 +2409,15 @@ static int rescuer_thread(void *__rescuer) repeat: set_current_state(TASK_INTERRUPTIBLE); - if (kthread_should_stop()) { - __set_current_state(TASK_RUNNING); - rescuer->task->flags &= ~PF_WQ_WORKER; - return 0; - } + /* + * By the time the rescuer is requested to stop, the workqueue + * shouldn't have any work pending, but @wq->maydays may still have + * pwq(s) queued. This can happen by non-rescuer workers consuming + * all the work items before the rescuer got to them. Go through + * @wq->maydays processing before acting on should_stop so that the + * list is always empty on exit. + */ + should_stop = kthread_should_stop(); /* see whether any pwq is asking for help */ spin_lock_irq(&wq_mayday_lock); @@ -2464,6 +2469,12 @@ repeat: spin_unlock_irq(&wq_mayday_lock); + if (should_stop) { + __set_current_state(TASK_RUNNING); + rescuer->task->flags &= ~PF_WQ_WORKER; + return 0; + } + /* rescuers should never participate in concurrency management */ WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); schedule(); -- 2.7.4