Re: [PATCH v3] barriers: introduce smp_mb__release_acquire and update documentation

2016-01-28 Thread Will Deacon
On Wed, Jan 27, 2016 at 03:00:11PM -0800, Paul E. McKenney wrote: > On Wed, Jan 27, 2016 at 06:39:23PM +, Will Deacon wrote: > > On Wed, Jan 27, 2016 at 07:25:51PM +0100, Peter Zijlstra wrote: > > > On Wed, Jan 27, 2016 at 06:22:04PM +, Will Deacon wrote: > > > > As much as we'd like to liv

Re: [PATCH v3] barriers: introduce smp_mb__release_acquire and update documentation

2016-01-28 Thread Will Deacon
On Thu, Jan 28, 2016 at 10:46:23AM +0800, Boqun Feng wrote: > On Wed, Jan 27, 2016 at 06:22:04PM +, Will Deacon wrote: > > As much as we'd like to live in a world where RELEASE -> ACQUIRE is > > always cheaply ordered and can be used to construct UNLOCK -> LOCK > > definitions with similar guar

Re: [PATCH v3] barriers: introduce smp_mb__release_acquire and update documentation

2016-01-27 Thread Boqun Feng
On Wed, Jan 27, 2016 at 06:22:04PM +, Will Deacon wrote: > As much as we'd like to live in a world where RELEASE -> ACQUIRE is > always cheaply ordered and can be used to construct UNLOCK -> LOCK > definitions with similar guarantees, the grim reality is that this isn't > even possible on x86 (

Re: [PATCH v3] barriers: introduce smp_mb__release_acquire and update documentation

2016-01-27 Thread Paul E. McKenney
On Wed, Jan 27, 2016 at 06:39:23PM +, Will Deacon wrote: > On Wed, Jan 27, 2016 at 07:25:51PM +0100, Peter Zijlstra wrote: > > On Wed, Jan 27, 2016 at 06:22:04PM +, Will Deacon wrote: > > > As much as we'd like to live in a world where RELEASE -> ACQUIRE is > > > always cheaply ordered and

Re: [PATCH v3] barriers: introduce smp_mb__release_acquire and update documentation

2016-01-27 Thread Will Deacon
On Wed, Jan 27, 2016 at 07:25:51PM +0100, Peter Zijlstra wrote: > On Wed, Jan 27, 2016 at 06:22:04PM +, Will Deacon wrote: > > As much as we'd like to live in a world where RELEASE -> ACQUIRE is > > always cheaply ordered and can be used to construct UNLOCK -> LOCK > > definitions with similar

[PATCH v3] barriers: introduce smp_mb__release_acquire and update documentation

2016-01-27 Thread Will Deacon
As much as we'd like to live in a world where RELEASE -> ACQUIRE is always cheaply ordered and can be used to construct UNLOCK -> LOCK definitions with similar guarantees, the grim reality is that this isn't even possible on x86 (thanks to Paul for bringing us crashing down to Earth). This patch h

Re: [PATCH v3] barriers: introduce smp_mb__release_acquire and update documentation

2016-01-27 Thread Peter Zijlstra
On Wed, Jan 27, 2016 at 06:22:04PM +, Will Deacon wrote: > As much as we'd like to live in a world where RELEASE -> ACQUIRE is > always cheaply ordered and can be used to construct UNLOCK -> LOCK > definitions with similar guarantees, the grim reality is that this isn't > even possible on x86 (