Re: [PATCH v4 5/5] x86: drop mfence in favor of lock+addl

[Linus Torvalds]

On Wed, Jan 27, 2016 at 7:10 AM, Michael S. Tsirkin <mst@xxxxxxxxxx> wrote:
>
> -#define __smp_mb()     mb()
> +#define __smp_mb()     asm volatile("lock; addl $0,-4(%%esp)" ::: "memory", "cc")

So this doesn't look right for x86-64. Using %esp rather than %rsp.
How did that even work for you?

                Linus