[RFC] virtio: use mandatory barriers for remote processor vdevs

[Ohad Ben-Cohen]

On Sat, Dec 3, 2011 at 1:09 AM, Benjamin Herrenschmidt
<benh at kernel.crashing.org> wrote:
> Have you measured the impact of using normal barriers (non-SMP ones)
> like we use on normal HW drivers unconditionally ?
>
> IE. If the difference is small enough I'd say just go for it and avoid
> the bloat.

I agree.

MST wanted to give this a try this week. If all goes well and there's
no unreasonable regression, we'd just switch to mandatory barriers.

Ohad.