Re: futex code and barriers

From: Jiri Kosina
Date: Tue Apr 29 2008 - 09:00:37 EST


On Tue, 29 Apr 2008, Peter Zijlstra wrote:

> While looking through the futex code I stumbled upon the following bit:
> kernel/futex.c:
> /* add_wait_queue is the barrier after __set_current_state. */
> __set_current_state(TASK_INTERRUPTIBLE);
> add_wait_queue(&q.waiters, &wait);
> However,
> void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
> {
> unsigned long flags;
>
> wait->flags &= ~WQ_FLAG_EXCLUSIVE;
> spin_lock_irqsave(&q->lock, flags);
> __add_wait_queue(q, wait);
> spin_unlock_irqrestore(&q->lock, flags);
> }
[ ... ]
> Non of which implies a full barrier.

Well I am probably missing the point, but what about the lock and unlock
of the spinlock?

--
Jiri Kosina
SUSE Labs

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/