more kernel hacking, the check_preempt_curr_rt() func

The following function in the linux kernel is a little confusing for me:

Code:

---

/*
 * Preempt the current task with a newly woken task if needed:
 */
static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p)
{
        if (p->prio < rq->curr->prio) {
            resched_task(rq->curr);
        }
}

---

So this means that the current thread, rq->curr will be preempted when resched_task(rq->curr) is called, but this happens when p have a LOWER prio then rq->curr? shouldn't it be the other way around? I mean 99 is highets prioirty and 0 is the lowest. Or have I missunderstood this?



Also why is prio used and not rt_prioirty?

If I understand it correct, p is the current task, so if p's priority is LOWER than the newly enabled-to-run priority, then reschedule.

--
Mats

Hmm, but confusing with the naming rq->curr, sounds like thats the current task?


And why isn't rt_priority used instead of prio?


So p is the current task that is being preempted? But isn't rq->curr the one being rescheduled??