Re: [RFC][PATCH 2/3] sched, workqueue: Move WQ-sleeper wakeup

[Tejun Heo <tj@kernel.org>]

Hello, Peter.

On Wed, Jun 22, 2011 at 01:34:46AM +0200, Peter Zijlstra wrote:
> -/**
>   * wake_up_process - Wake up a specific process
>   * @p: The process to be woken up.
>   *
> @@ -4215,6 +4181,19 @@ static inline void sched_submit_work(voi
>  
>  	if (tsk->state && !(preempt_count() & PREEMPT_ACTIVE)) {
>  		/*
> +		 * If a worker went to sleep, notify and ask workqueue
> +		 * whether it wants to wake up a task to maintain
> +		 * concurrency.
> +		 */
> +		if (tsk->flags & PF_WQ_WORKER) {
> +			struct task_struct *to_wakeup;
> +
> +			to_wakeup = wq_worker_sleeping(tsk, smp_processor_id());
> +			if (to_wakeup)
> +				wake_up_process(to_wakeup);
> +		}
> +
> +		/*

Preemption could still be enabled here, right?  What prevents
preemtion kicking after wq_worker_sleeping() and do it again thus
breaking nr_running tracking.

>  		 * If we are going to sleep and we have plugged IO
>  		 * queued, make sure to submit it to avoid deadlocks.
>  		 */
> @@ -4256,19 +4235,6 @@ asmlinkage void __sched schedule(void)
>  		} else {
>  			deactivate_task(rq, prev, DEQUEUE_SLEEP);
>  			prev->on_rq = 0;
> -
> -			/*
> -			 * If a worker went to sleep, notify and ask workqueue
> -			 * whether it wants to wake up a task to maintain
> -			 * concurrency.
> -			 */
> -			if (prev->flags & PF_WQ_WORKER) {
> -				struct task_struct *to_wakeup;
> -
> -				to_wakeup = wq_worker_sleeping(prev, cpu);
> -				if (to_wakeup)
> -					try_to_wake_up_local(to_wakeup);
> -			}

Similarly, the if the 'if {}' part of the above if/else is taken, the
task never goes to sleep and nr_running will again be broken.

-- 
tejun