On Tue, Jun 05, 2018 at 03:56:16PM +0200, Peter Zijlstra wrote: > On Tue, Jun 05, 2018 at 02:28:02PM +0100, Mark Rutland wrote: > > On Tue, Jun 05, 2018 at 02:16:23PM +0200, Peter Zijlstra wrote: > > > and simply using smp_mb__{before,after}_atomic for the full fence, its > > > exactly what they were made for. > > > > The snag is arch/alpha, whare we have: > > > > /* > > * To ensure dependency ordering is preserved for the _relaxed and > > * _release atomics, an smp_read_barrier_depends() is unconditionally > > * inserted into the _relaxed variants, which are used to build the > > * barriered versions. To avoid redundant back-to-back fences, we can > > * define the _acquire and _fence versions explicitly. > > */ > > #define __atomic_op_acquire(op, args...) op##_relaxed(args) > > #define __atomic_op_fence __atomic_op_release > > > > ... where alpha's smp_read_barrier_depends() is the same as > > smp_mb_after_atomic(). > > > > Since alpha's non-value-returning atomics do not have the > > smp_read_barrier_depends(), I can't just define an empty > > smp_mb_after_atomic(). > > > > Thoughts? > > Bah, of course there had to be a misfit.
Of course it had to be alpha. ;) > Something along these lines then: > > __atomic_acquire_fence > __atomic_release_fence > __atomic_mb_before > __atomic_mb_after Locally I've made this: __atomic_acquire_fence() __atomic_release_fence() __atomic_pre_fence() __atomic_post_fence() ... but I'm more than happy to rename however you prefer. Thanks, Mark.