Re: [RFC][PATCH 0/5] Getting rid of smp_mb__before_spinlock

2017-06-09 Thread Will Deacon
On Wed, Jun 07, 2017 at 06:15:01PM +0200, Peter Zijlstra wrote: > There was a thread on this somewhere about a year ago, I finally remembered to > finish this :-) > > This series removes two smp_mb__before_spinlock() (ab)users and converts the > scheduler to use smp_mb__after_spinlock(), which pro

[RFC][PATCH 0/5] Getting rid of smp_mb__before_spinlock

2017-06-07 Thread Peter Zijlstra
There was a thread on this somewhere about a year ago, I finally remembered to finish this :-) This series removes two smp_mb__before_spinlock() (ab)users and converts the scheduler to use smp_mb__after_spinlock(), which provides more guarantees with the same amount of barriers.