Re: [patch] softirq performance fixes, cleanups, 2.4.10.

[Ingo Molnar]

On Wed, 26 Sep 2001, Mike Kravetz wrote:

> > +	if (!p->has_cpu && (p != current) && task_on_runqueue(p)) {

> Is it really possible for a task to be 'current' without having
> 'has_cpu' set?  If so, then don't you need to compare p to 'current'
> on all CPUs since 'current' is CPU specific?

you are correct that the check is redundant on SMP, but ->has_cpu is not
set on UP kernels, so the 'current' check is needed there. I did not want
to introduce yet another #if CONFIG_SMP ifdef.

	Ingo