Re: lockdep trace from posix timers

[Oleg Nesterov <oleg@redhat.com>]

On 08/20, Peter Zijlstra wrote:
>
> +static void __task_work_run(struct callback_head *tail)
>  {
> -	struct task_struct *task = current;
> -	struct callback_head *p, *q;
> -
> -	while (1) {
> -		raw_spin_lock_irq(&task->pi_lock);
> -		p = task->task_works;
> -		task->task_works = NULL;
> -		raw_spin_unlock_irq(&task->pi_lock);
> -
> -		if (unlikely(!p))
> -			return;
> -
> -		q = p->next; /* head */
> -		p->next = NULL; /* cut it */
> -		while (q) {
> -			p = q->next;
> -			q->func(q);
> -			q = p;
> +	struct callback_head **head = &current->task_works;
> +
> +	do {
> +		struct callback_head *work = xchg(head, NULL);
> +		while (work) {
> +			struct callback_head *next = ACCESS_ONCE(work->next);
> +
> +			WARN_ON_ONCE(work == &dead);
> +
> +			work->func(work);
> +			work = next;
>  		}
> -	}
> +	} while (cmpxchg(head, NULL, tail) != NULL);

Yes, we can add the explicit argument to __task_work_run(), but it can
check PF_EXITING instead, this looks simpler to me.

Note also your patch breaks fifo, but this is fixable.

Oleg.