On Mon, Jun 30, 2014 at 8:01 PM, Austin Schuh <aus...@peloton-tech.com> wrote:
> On Fri, Jun 27, 2014 at 7:24 AM, Thomas Gleixner <t...@linutronix.de> wrote:
>> Completely untested patch below.
>
> By chance, I found this in my boot logs. I'll do some more startup
> testing tomorrow.
>
> Jun 30 19:54:40 vpc5 kernel: [ 0.670955] ------------[ cut here
> ]------------
> Jun 30 19:54:40 vpc5 kernel: [ 0.670962] WARNING: CPU: 0 PID: 4 at
> kernel/workqueue.c:1604 worker_enter_idle+0x65/0x16b()
> Jun 30 19:54:40 vpc5 kernel: [ 0.670970] Modules linked in:
> Jun 30 19:54:40 vpc5 kernel: [ 0.670973] CPU: 0 PID: 4 Comm:
> kworker/0:0 Not tainted 3.14.3-rt4abs+ #8
> Jun 30 19:54:40 vpc5 kernel: [ 0.670974] Hardware name: CompuLab
> Intense-PC/Intense-PC, BIOS CR_2.2.0.377 X64 04/10/2013
> Jun 30 19:54:40 vpc5 kernel: [ 0.670983] 0000000000000009
> ffff88040ce75de8 ffffffff81510faf 0000000000000002
> Jun 30 19:54:40 vpc5 kernel: [ 0.670985] 0000000000000000
> ffff88040ce75e28 ffffffff81042085 0000000000000001
> Jun 30 19:54:40 vpc5 kernel: [ 0.670987] ffffffff81057a60
> ffff88042d406900 ffff88042da63fc0 ffff88042da64030
> Jun 30 19:54:40 vpc5 kernel: [ 0.670988] Call Trace:
> Jun 30 19:54:40 vpc5 kernel: [ 0.670995] [<ffffffff81510faf>]
> dump_stack+0x4f/0x7c
> Jun 30 19:54:40 vpc5 kernel: [ 0.670999] [<ffffffff81042085>]
> warn_slowpath_common+0x81/0x9c
> Jun 30 19:54:40 vpc5 kernel: [ 0.671002] [<ffffffff81057a60>] ?
> worker_enter_idle+0x65/0x16b
> Jun 30 19:54:40 vpc5 kernel: [ 0.671005] [<ffffffff810420ba>]
> warn_slowpath_null+0x1a/0x1c
> Jun 30 19:54:40 vpc5 kernel: [ 0.671007] [<ffffffff81057a60>]
> worker_enter_idle+0x65/0x16b
> Jun 30 19:54:40 vpc5 kernel: [ 0.671010] [<ffffffff8105a0a9>]
> worker_thread+0x1b3/0x22b
> Jun 30 19:54:40 vpc5 kernel: [ 0.671013] [<ffffffff81059ef6>] ?
> rescuer_thread+0x293/0x293
> Jun 30 19:54:40 vpc5 kernel: [ 0.671015] [<ffffffff81059ef6>] ?
> rescuer_thread+0x293/0x293
> Jun 30 19:54:40 vpc5 kernel: [ 0.671018] [<ffffffff8105f7ab>]
> kthread+0xdc/0xe4
> Jun 30 19:54:40 vpc5 kernel: [ 0.671022] [<ffffffff8105f6cf>] ?
> flush_kthread_worker+0xe1/0xe1
> Jun 30 19:54:40 vpc5 kernel: [ 0.671025] [<ffffffff8151586c>]
> ret_from_fork+0x7c/0xb0
> Jun 30 19:54:40 vpc5 kernel: [ 0.671027] [<ffffffff8105f6cf>] ?
> flush_kthread_worker+0xe1/0xe1
> Jun 30 19:54:40 vpc5 kernel: [ 0.671029] ---[ end trace 0000000000000001
> ]---
Bug in my extra locking... Sorry for the noise. The second diff is a
cleaner way of destroying the workers.
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 8900da8..590cc26 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1567,10 +1602,16 @@ static void worker_enter_idle(struct worker *worker)
{
struct worker_pool *pool = worker->pool;
- if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) ||
- WARN_ON_ONCE(!list_empty(&worker->entry) &&
- (worker->hentry.next || worker->hentry.pprev)))
+ if (WARN_ON_ONCE(worker->flags & WORKER_IDLE)) return;
+
+ rt_lock_idle_list(pool);
+ if (WARN_ON_ONCE(!list_empty(&worker->entry) &&
+ (worker->hentry.next || worker->hentry.pprev))) {
+ rt_unlock_idle_list(pool);
return;
+ } else {
+ rt_unlock_idle_list(pool);
+ }
/* can't use worker_set_flags(), also called from start_worker() */
worker->flags |= WORKER_IDLE;
@@ -3584,8 +3637,14 @@ static void put_unbound_pool(struct worker_pool *pool)
mutex_lock(&pool->manager_mutex);
spin_lock_irq(&pool->lock);
- while ((worker = first_worker(pool)))
+ rt_lock_idle_list(pool);
+ while ((worker = first_worker(pool))) {
+ rt_unlock_idle_list(pool);
destroy_worker(worker);
+ rt_lock_idle_list(pool);
+ }
+ rt_unlock_idle_list(pool);
+
WARN_ON(pool->nr_workers || pool->nr_idle);
spin_unlock_irq(&pool->lock);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
