Memory barriers and spin_unlock safety

Linus Torvalds torvalds at
Sat Mar 4 08:34:17 EST 2006

On Fri, 3 Mar 2006, David Howells wrote:
> I suspect, then, that x86_64 should not have an SFENCE for smp_wmb(), and that
> only io_wmb() should have that.

Indeed. I think smp_wmb() should be a compiler fence only on x86(-64), ie 
just compile to a "barrier()" (and not even that on UP, of course).


More information about the Linuxppc64-dev mailing list