Messages in this thread | | | Date | Tue, 23 Apr 2019 15:26:20 +0200 | From | Peter Zijlstra <> | Subject | Re: [PATCH] Documentation: atomic_t.txt: Explain ordering provided by smp_mb__{before,after}_atomic() |
| |
On Tue, Apr 23, 2019 at 06:21:16AM -0700, Paul E. McKenney wrote: > On Tue, Apr 23, 2019 at 02:17:15PM +0200, Peter Zijlstra wrote: > > On Sat, Apr 20, 2019 at 01:54:40AM -0700, Paul E. McKenney wrote: > > > 3. Make non-value-returning atomics provide full ordering. > > > This would of course need some benchmarking, but would be a > > > simple change to make and would eliminate a large class of > > > potential bugs. My guess is that the loss in performance > > > would be non-negligible, but who knows? > > > > Well, only for the architectures that have > > smp_mb__{before,after}_atomic() as barrier(), which are: ia64, mips, > > s390, sparc, x86 and xtense. > > The weakly ordered architectures would need to add the equivalent of > smp_mb() before and after, right? This might result in a more noticeable > loss of performance.
The weak archs already have: smp_mb__{before,after}_atomic() := smp_mb().
| |