On Fri, Feb 12, 2016 at 04:22:29PM -0500, Waiman Long wrote:
> >>+ smp_cond_acquire(!p->on_cpu || !(p->state& state));
> >>+ if (!(p->state& state)) {
> >>+ success = 0;
> >>+ goto out;
> >>+ }
> >This doesn't make sense, if we managed to get here, p->on_rq must be
> >false, which means the other side is already in the middle of
> >schedule().
> Yes, you are right. It is my bad that I miss the on_rq check earlier. Just
> scrap the last patch.No worries, that is tricky code :-)
