Messages in this thread | | | Date | Tue, 1 Sep 2015 18:38:12 +0200 | From | Peter Zijlstra <> | Subject | Re: futex atomic vs ordering constraints |
| |
On Fri, Aug 28, 2015 at 06:33:06PM -0700, Davidlohr Bueso wrote: > On Wed, 2015-08-26 at 20:16 +0200, Peter Zijlstra wrote: > > Of course, if anything else prior to futex_atomic_op_inuser() implies an > > (RCsc) RELEASE or stronger the primitive can do without providing > > anything itself. > > > > This turns out to be the case, a successful get_futex_key() implies a > > full memory barrier; recent: 1d0dcb3ad9d3 ("futex: Implement lockless > > wakeups"). > > Hmm while it is certainly true that get_futex_key() implies a full > barrier, I don't see why you're referring to the recent wake_q stuff;
D'oh, because I'm a sheep or so. I meant:
b0c29f79ecea (futexes: Avoid taking the hb->lock if there's nothing to wake up)
| |