On Mon, Jul 31, 2017 at 11:16:48AM -0400, Steven Rostedt wrote: > On Mon, 31 Jul 2017 17:04:11 +0200 > Peter Zijlstra <[email protected]> wrote: > > > Well, this is x86, its a NO-OP. The only reason to write barriers like > > Is it really a nop?
smp_wmb() is ever since we killed OOSTORE, and smp_rmb() is effectively (I don't think anybody uses PPRO_FENCE). The normal x86 TSO memory model doesn't need read or write barriers -- only weird and wonderful (broken) x86 bits do.
