Re: [PATCH 2/3] workqueue: not allow recursion run_workqueue

[Frederic Weisbecker <fweisbec@gmail.com>]

On Thu, Jan 22, 2009 at 05:14:24PM +0800, Lai Jiangshan wrote:
> 1) lockdep will complain when recursion run_workqueue
> 2) works is not run orderly when recursion run_workqueue
> 
> 3) BUG!
>    We use recursion run_workqueue to hidden deadlock when
>    keventd trying to flush its own queue.
> 
>    It's bug. When flush_workqueue()(nested in a work callback)returns,
>    the workqueue is not really flushed, the sequence statement of
>    this work callback will do some thing bad.
> 
>    So we should not allow workqueue trying to flush its own queue.
> 
> 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;
> +	BUG_ON(cwq->thread == current);

Hi Lai,

BUG_ON seems perhaps a bit too much for such case. The system
will run in an endless loop because of a mistake that will not have
necessarily a fatal end.
WARN_ON should be enough (plus the warn that lockdep will raise
too in this case).

Thanks.
Frederic.

 
> -		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;
>  }
>