On Tue, Nov 24, 2015 at 01:54:23PM +0800, Herbert Xu wrote:
> diff --git a/include/linux/wait.h b/include/linux/wait.h
> index 1e1bf9f..bd1157f 100644
> --- a/include/linux/wait.h
> +++ b/include/linux/wait.h
> @@ -107,6 +107,50 @@ static inline int waitqueue_active(wait_queue_head_t *q)
> return !list_empty(&q->task_list);
> }
>
> +/**
> + * wq_has_sleeper - check if there are any waiting processes
> + * @wq: wait queue head
> + *
> + * Returns true if wq has waiting processes
> + *
> + * The purpose of the wq_has_sleeper and sock_poll_wait is to wrap the memory
> + * barrier call. They were added due to the race found within the tcp code.
> + *
> + * Consider following tcp code paths:
> + *
> + * CPU1 CPU2
> + *
> + * sys_select receive packet
> + * ... ...
> + * __add_wait_queue update tp->rcv_nxt
> + * ... ...
> + * tp->rcv_nxt check sock_def_readable
> + * ... {
> + * schedule rcu_read_lock();
> + * wq = rcu_dereference(sk->sk_wq);
> + * if (wq && waitqueue_active(&wq->wait))
> + * wake_up_interruptible(&wq->wait)
> + * ...
> + * }
> + *
> + * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay
> + * in its cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1
> + * could then endup calling schedule and sleep forever if there are no more
> + * data on the socket.
> + *
Would be easier to refer to the comment that now adorns
waitqueue_active().
> + */
> +static inline bool wq_has_sleeper(wait_queue_head_t *wq)
> +{
> + /* We need to be sure we are in sync with the
broken comment style.
> + * add_wait_queue modifications to the wait queue.
> + *
> + * This memory barrier should be paired with one on the
> + * waiting side.
> + */
> + smp_mb();
> + return waitqueue_active(wq);
> +}
> +
> extern void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait);
> extern void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t
> *wait);
> extern void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait);
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
