Re: lockdep trace from posix timers

[Oleg Nesterov <oleg@redhat.com>]

On 08/21, Oleg Nesterov wrote:
>
> > task_work_add(struct task_struct *task, struct callback_head *twork, bool notify)
> > {
> > 	do {
> > 		twork->next = ACCESS_ONCE(task->task_works);
> > 		if (unlikely(twork->next == TWORK_EXITED))
> > 			return -ESRCH;
> > 	} while (cmp_xchg(&task->task_works, twork->next, twork));
>           ^^^^^^^^^^^^^^^
>
> while (!cmp_xchg(...))

and _cancel can be simplified a bit.

OK, I actually tested the code below, seems to work.

Peter, if you think it can work for you and if you agree with
the implementation I will be happy to send the patch.

The only change outside of task_work.c is that exit_task_work()
should call task_work_run() unconditionally.

As for cmp_xchg below... Of course it is not strictly needed.
But otoh, personally I'd like to have this helper (probably
renamed) somewhere in include/linux. Perhaps this is just me,
but cmpxchg() always confuses me, and most users only need
success_or_not from cmpxchg.

Oleg.


#define cmp_xchg(ptr, _old, new)	\
({					\
	__typeof__(_old) old = (_old);	\
	cmpxchg(ptr, old, new) == old;	\
})

#define TWORK_EXITED	((struct callback_head*)1)

int
task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
{
	do {
		work->next = ACCESS_ONCE(task->task_works);
		if (unlikely(work->next == TWORK_EXITED))
			return -ESRCH;
	} while (!cmp_xchg(&task->task_works, work->next, work));

	/* test_and_set_bit() implies mb(), see tracehook_notify_resume(). */
	if (notify)
		set_notify_resume(task);
	return 0;
}

struct callback_head *
task_work_cancel(struct task_struct *task, task_work_func_t func)
{
	struct callback_head **pprev = &task->task_works;
	struct callback_head *work = NULL;
	unsigned long flags;

	raw_spin_lock_irqsave(&task->pi_lock, flags);
	if (likely(*pprev != TWORK_EXITED)) {
		while ((work = *pprev)) {
			read_barrier_depends();
			if (work->func != func)
				pprev = &work->next;
			else if (cmp_xchg(pprev, work, work->next))
				break;
		}
	}
	raw_spin_unlock_irqrestore(&task->pi_lock, flags);

	return work;
}

void task_work_run(void)
{
	struct task_struct *task = current;
	struct callback_head *work, *head, *next;

	for (;;) {
		raw_spin_lock_irq(&task->pi_lock);
		do {
			work = ACCESS_ONCE(task->task_works);
			head = !work && (task->flags & PF_EXITING) ?
				TWORK_EXITED : NULL;
		} while (!cmp_xchg(&task->task_works, work, head));
		raw_spin_unlock_irq(&task->pi_lock);

		if (!work)
			break;

#if PETERZ_WONT_ARGUE_AGAINST_FIFO_TOO_MUCH
		head = NULL;
		do {
			next = work->next;
			work->next = head;
			head = work;
			work = next;
		} while (work);

		work = head;
#endif
		do {
			next = work->next;
			work->func(work);
			work = next;
			cond_resched();
		} while (work);
	}
}