Messages in this thread | | | Date | Wed, 10 Oct 2012 16:02:49 +0200 | From | Andi Kleen <> | Subject | Re: [REPOST] RFC: sched: Prevent wakeup to enter critical section needlessly |
| |
> wait_event: > > prepare_to_wait(wq) // takes wq->lock > > if (!CONDITION) > schedule(); > > Now, > > CONDITION = 1; > wake_up(wq); > > at least need the full mb() before lits_empty().
You're right, but it would probably only matter for inlining with LTO (if the LTO compiler ever decides to do that)
Without that a call should be always enough barrier in practice.
So yes I would add the mb, but most likely it will not make much difference. Just make sure to comment it.
-Andi
| |