lkml.org 
[lkml]   [2009]   [Feb]   [9]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH 2/3] workqueue: not allow recursion run_workqueue
On 02/06, Lai Jiangshan wrote:
>
> 1) lockdep will complain when recursion run_workqueue()
> 2) The recursive implement of run_workqueue() makes flush_workqueue()
> and it's doc are inconsistent. It may hide deadlock and other bugs.
> 3) recursion run_workqueue() will poison cwq->current_work,
> but flush_work() and __cancel_work_timer() ...etc. need
> reliable cwq->current_work.

I think this change is good. If we still have users which call flush
from work->func() they should be fixed, imho.

And while I knew this recursive flush is bad, I didn't realize how
bad it is until Lai spelled this. Thanks.

Acked-by: Oleg Nesterov <oleg@redhat.com>

> Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
> ---
> diff --git a/kernel/workqueue.c b/kernel/workqueue.c
> index 2f44583..1129cde 100644
> --- a/kernel/workqueue.c
> +++ b/kernel/workqueue.c
> @@ -48,8 +48,6 @@ struct cpu_workqueue_struct {
>
> struct workqueue_struct *wq;
> struct task_struct *thread;
> -
> - int run_depth; /* Detect run_workqueue() recursion depth */
> } ____cacheline_aligned;
>
> /*
> @@ -262,13 +260,6 @@ EXPORT_SYMBOL_GPL(queue_delayed_work_on);
> static void run_workqueue(struct cpu_workqueue_struct *cwq)
> {
> spin_lock_irq(&cwq->lock);
> - cwq->run_depth++;
> - if (cwq->run_depth > 3) {
> - /* morton gets to eat his hat */
> - printk("%s: recursion depth exceeded: %d\n",
> - __func__, cwq->run_depth);
> - dump_stack();
> - }
> while (!list_empty(&cwq->worklist)) {
> struct work_struct *work = list_entry(cwq->worklist.next,
> struct work_struct, entry);
> @@ -311,7 +302,6 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq)
> spin_lock_irq(&cwq->lock);
> cwq->current_work = NULL;
> }
> - cwq->run_depth--;
> spin_unlock_irq(&cwq->lock);
> }
>
> @@ -368,29 +358,20 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
>
> static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
> {
> - int active;
> + int active = 0;
> + struct wq_barrier barr;
>
> - if (cwq->thread == current) {
> - /*
> - * Probably keventd trying to flush its own queue. So simply run
> - * it by hand rather than deadlocking.
> - */
> - run_workqueue(cwq);
> - active = 1;
> - } else {
> - struct wq_barrier barr;
> + WARN_ON(cwq->thread == current);
>
> - active = 0;
> - spin_lock_irq(&cwq->lock);
> - if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
> - insert_wq_barrier(cwq, &barr, &cwq->worklist);
> - active = 1;
> - }
> - spin_unlock_irq(&cwq->lock);
> -
> - if (active)
> - wait_for_completion(&barr.done);
> + spin_lock_irq(&cwq->lock);
> + if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
> + insert_wq_barrier(cwq, &barr, &cwq->worklist);
> + active = 1;
> }
> + spin_unlock_irq(&cwq->lock);
> +
> + if (active)
> + wait_for_completion(&barr.done);
>
> return active;
> }
>



\
 
 \ /
  Last update: 2009-02-09 20:21    [W:0.122 / U:0.020 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site