Messages in this thread | | | Date | Fri, 17 Jul 2015 05:40:40 -0700 | From | "Paul E. McKenney" <> | Subject | Re: [RFC PATCH v2] memory-barriers: remove smp_mb__after_unlock_lock() |
| |
On Fri, Jul 17, 2015 at 12:15:35PM +0200, Peter Zijlstra wrote: > On Fri, Jul 17, 2015 at 10:32:21AM +0100, Will Deacon wrote: > > @@ -158,9 +140,7 @@ void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) > > > > static inline void arch_spin_unlock(arch_spinlock_t *lock) > > { > > - SYNC_IO; > > - __asm__ __volatile__("# arch_spin_unlock\n\t" > > - PPC_RELEASE_BARRIER: : :"memory"); > > + smp_mb(); > > lock->slock = 0; > > } > > Should we then also make smp_store_release() use sync instead of lwsync > to keep it consistent?
Unless smp_store_release() needs to interact with MMIO accesses, it should still be able to be lwsync. This means that unlock-lock is a full barrier, but relase-acquire is not necessarily, which should be just fine.
Thanx, Paul
| |