Re: [PATCH v7 5/6] MCS Lock: allow architectures to hook in to contended paths

2014-01-20 Thread Peter Zijlstra
On Thu, Jan 16, 2014 at 04:08:31PM -0800, Tim Chen wrote: > +#ifndef arch_mcs_spin_lock_contended > +/* > + * Using smp_load_acquire() provides a memory barrier that ensures > + * subsequent operations happen after the lock is acquired. > + */ > +#define arch_mcs_spin_lock_contended(l)

Re: [PATCH v7 5/6] MCS Lock: allow architectures to hook in to contended paths

2014-01-19 Thread Paul E. McKenney
On Thu, Jan 16, 2014 at 04:08:31PM -0800, Tim Chen wrote: > When contended, architectures may be able to reduce the polling overhead > in ways which aren't expressible using a simple relax() primitive. > > This patch allows architectures to hook into the mcs_{lock,unlock} > functions for the conte