Messages in this thread | | | Date | Wed, 16 Sep 2015 11:01:52 +0200 | From | Peter Zijlstra <> | Subject | Re: [PATCH -tip 2/3] sched/wake_q: Relax to acquire semantics |
| |
On Tue, Sep 15, 2015 at 12:49:46PM -0700, Davidlohr Bueso wrote: > On Tue, 15 Sep 2015, Peter Zijlstra wrote: > > >>Secondly, the wake queues are not concurrent, they're in context, so I > >>don't see ordering matter at all. The only reason its a cmpxchg() is > >>because there is the (small) possibility of two contexts wanting to wake > >>the same task, and we use task_struct storage for the queue. > > > >I don't think we need _any_ barriers here, unless we have concurrent > >users of the wake queues (or want to allow any, do we?). > > Exactly, the queues are not concurent and do not need barriers, but some of > our callers do expect them.
Ah, that is what you were saying. In that case, I think we should remove all our barriers and make them explicit in the callers where needed.
| |