Re: The O(1) scheduler breaks UML

[Davide Libenzi]

On Mon, 14 Jan 2002, Ingo Molnar wrote:

>
> On Sun, 13 Jan 2002, Davide Libenzi wrote:
>
> > > So, is it possible to enable IRQs across the call to _switch_to?
> >
> > Yes, this should work :
> >
> >     if (likely(prev != next)) {
> >         rq->nr_switches++;
> >         rq->curr = next;
> >         next->cpu = prev->cpu;
> >         spin_unlock_irq(&rq->lock);
> >         context_switch(prev, next);
> >     } else
> >         spin_unlock_irq(&rq->lock);
>
> this change is incredibly broken on SMP - eg. what protects 'prev' from
> being executed on another CPU prematurely. It's even broken on UP:
> interrupt context that changes current->need_resched needs to be aware of
> nonatomic context switches. See my previous mail.

yup, true. no more schedule_tail()

- Davide