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

[Mike Kravetz]

On Wed, Sep 26, 2001 at 06:44:03PM +0200, Ingo Molnar wrote:
> +void __unwakeup_process(struct task_struct * p, long state)
> +{
> +	unsigned long flags;
> +
> +	spin_lock_irqsave(&runqueue_lock, flags);
> +	if (!p->has_cpu && (p != current) && task_on_runqueue(p)) {
> +		del_from_runqueue(p);
> +		p->state = state;
> +	}
> +	spin_unlock_irqrestore(&runqueue_lock, flags);
> +}

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?

-- 
Mike Kravetz                                  [e-mail]
IBM Linux Technology Center       (we're not at Sequent anymore)