sched_rt.c

		 * the caller to recalculate the next task
		 * in that case:
		 */
		if (double_lock_balance(this_rq, src_rq)) {
			struct task_struct *old_next = next;

			next = pick_next_task_rt(this_rq);
			if (next != old_next)
				ret = 1;
		}

		/*
		 * Are there still pullable RT tasks?
		 */
		if (src_rq->rt.rt_nr_running <= 1)
			goto skip;

		p = pick_next_highest_task_rt(src_rq, this_cpu);

		/*
		 * Do we have an RT task that preempts
		 * the to-be-scheduled task?
		 */
		if (p && (!next || (p->prio < next->prio))) {
			WARN_ON(p == src_rq->curr);
			WARN_ON(!p->se.on_rq);

			/*
			 * There's a chance that p is higher in priority
			 * than what's currently running on its cpu.
			 * This is just that p is wakeing up and hasn't
			 * had a chance to schedule. We only pull
			 * p if it is lower in priority than the
			 * current task on the run queue or
			 * this_rq next task is lower in prio than
			 * the current task on that rq.
			 */
			if (p->prio < src_rq->curr->prio ||
			    (next && next->prio < src_rq->curr->prio))
				goto skip;

			ret = 1;

			deactivate_task(src_rq, p, 0);
			set_task_cpu(p, this_cpu);
			activate_task(this_rq, p, 0);
			/*
			 * We continue with the search, just in
			 * case there's an even higher prio task
			 * in another runqueue. (low likelyhood
			 * but possible)
			 *
			 * Update next so that we won't pick a task
			 * on another cpu with a priority lower (or equal)
			 * than the one we just picked.
			 */
			next = p;

		}
 skip:
		spin_unlock(&src_rq->lock);
	}

	return ret;
}

static void pre_schedule_rt(struct rq *rq, struct task_struct *prev)
{
	/* Try to pull RT tasks here if we lower this rq's prio */
	if (unlikely(rt_task(prev)) && rq->rt.highest_prio > prev->prio)
		pull_rt_task(rq);
}

static void post_schedule_rt(struct rq *rq)
{
	/*
	 * If we have more than one rt_task queued, then
	 * see if we can push the other rt_tasks off to other CPUS.
	 * Note we may release the rq lock, and since
	 * the lock was owned by prev, we need to release it
	 * first via finish_lock_switch and then reaquire it here.
	 */
	if (unlikely(rq->rt.overloaded)) {
		spin_lock_irq(&rq->lock);
		push_rt_tasks(rq);
		spin_unlock_irq(&rq->lock);
	}
}

/*
 * If we are not running and we are not going to reschedule soon, we should
 * try to push tasks away now
 */
static void task_wake_up_rt(struct rq *rq, struct task_struct *p)
{
	if (!task_running(rq, p) &&
	    !test_tsk_need_resched(rq->curr) &&
	    rq->rt.overloaded)
		push_rt_tasks(rq);
}

static unsigned long
load_balance_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
		unsigned long max_load_move,
		struct sched_domain *sd, enum cpu_idle_type idle,
		int *all_pinned, int *this_best_prio)
{
	/* don't touch RT tasks */
	return 0;
}

static int
move_one_task_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
		 struct sched_domain *sd, enum cpu_idle_type idle)
{
	/* don't touch RT tasks */
	return 0;
}

static void set_cpus_allowed_rt(struct task_struct *p,
				const cpumask_t *new_mask)
{
	int weight = cpus_weight(*new_mask);

	BUG_ON(!rt_task(p));

	/*
	 * Update the migration status of the RQ if we have an RT task
	 * which is running AND changing its weight value.
	 */
	if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) {
		struct rq *rq = task_rq(p);

		if ((p->rt.nr_cpus_allowed <= 1) && (weight > 1)) {
			rq->rt.rt_nr_migratory++;
		} else if ((p->rt.nr_cpus_allowed > 1) && (weight <= 1)) {
			BUG_ON(!rq->rt.rt_nr_migratory);
			rq->rt.rt_nr_migratory--;
		}

		update_rt_migration(rq);

		if (unlikely(weight == 1 || p->rt.nr_cpus_allowed == 1))
			/*
			 * If either the new or old weight is a "1", we need
			 * to requeue to properly move between shared and
			 * exclusive queues.
			 */
			requeue_task_rt(rq, p);
	}

	p->cpus_allowed    = *new_mask;
	p->rt.nr_cpus_allowed = weight;
}

/* Assumes rq->lock is held */
static void join_domain_rt(struct rq *rq)
{
	if (rq->rt.overloaded)
		rt_set_overload(rq);

	cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio);
}

/* Assumes rq->lock is held */
static void leave_domain_rt(struct rq *rq)
{
	if (rq->rt.overloaded)
		rt_clear_overload(rq);

	cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_INVALID);
}

/*
 * When switch from the rt queue, we bring ourselves to a position
 * that we might want to pull RT tasks from other runqueues.
 */
static void switched_from_rt(struct rq *rq, struct task_struct *p,
			   int running)
{
	/*
	 * If there are other RT tasks then we will reschedule
	 * and the scheduling of the other RT tasks will handle
	 * the balancing. But if we are the last RT task
	 * we may need to handle the pulling of RT tasks
	 * now.
	 */
	if (!rq->rt.rt_nr_running)
		pull_rt_task(rq);
}
#endif /* CONFIG_SMP */

/*
 * When switching a task to RT, we may overload the runqueue
 * with RT tasks. In this case we try to push them off to
 * other runqueues.
 */
static void switched_to_rt(struct rq *rq, struct task_struct *p,
			   int running)
{
	int check_resched = 1;

	/*
	 * If we are already running, then there's nothing
	 * that needs to be done. But if we are not running
	 * we may need to preempt the current running task.
	 * If that current running task is also an RT task
	 * then see if we can move to another run queue.
	 */
	if (!running) {
#ifdef CONFIG_SMP
		if (rq->rt.overloaded && push_rt_task(rq) &&
		    /* Don't resched if we changed runqueues */
		    rq != task_rq(p))
			check_resched = 0;
#endif /* CONFIG_SMP */
		if (check_resched && p->prio < rq->curr->prio)
			resched_task(rq->curr);
	}
}

/*
 * Priority of the task has changed. This may cause
 * us to initiate a push or pull.
 */
static void prio_changed_rt(struct rq *rq, struct task_struct *p,
			    int oldprio, int running)
{
	if (running) {
#ifdef CONFIG_SMP
		/*
		 * If our priority decreases while running, we
		 * may need to pull tasks to this runqueue.
		 */
		if (oldprio < p->prio)
			pull_rt_task(rq);
		/*
		 * If there's a higher priority task waiting to run
		 * then reschedule. Note, the above pull_rt_task
		 * can release the rq lock and p could migrate.
		 * Only reschedule if p is still on the same runqueue.
		 */
		if (p->prio > rq->rt.highest_prio && rq->curr == p)
			resched_task(p);
#else
		/* For UP simply resched on drop of prio */
		if (oldprio < p->prio)
			resched_task(p);
#endif /* CONFIG_SMP */
	} else {
		/*
		 * This task is not running, but if it is
		 * greater than the current running task
		 * then reschedule.
		 */
		if (p->prio < rq->curr->prio)
			resched_task(rq->curr);
	}
}

static void watchdog(struct rq *rq, struct task_struct *p)
{
	unsigned long soft, hard;

	if (!p->signal)
		return;

	soft = p->signal->rlim[RLIMIT_RTTIME].rlim_cur;
	hard = p->signal->rlim[RLIMIT_RTTIME].rlim_max;

	if (soft != RLIM_INFINITY) {
		unsigned long next;

		p->rt.timeout++;
		next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ);
		if (p->rt.timeout > next)
			p->it_sched_expires = p->se.sum_exec_runtime;
	}
}

static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
{
	update_curr_rt(rq);

	watchdog(rq, p);

	/*
	 * RR tasks need a special form of timeslice management.
	 * FIFO tasks have no timeslices.
	 */
	if (p->policy != SCHED_RR)
		return;

	if (--p->rt.time_slice)
		return;

	p->rt.time_slice = DEF_TIMESLICE;

	/*
	 * Requeue to the end of queue if we are not the only element
	 * on the queue:
	 */
	if (p->rt.run_list.prev != p->rt.run_list.next) {
		requeue_task_rt(rq, p);
		set_tsk_need_resched(p);
	}
}

static void set_curr_task_rt(struct rq *rq)
{
	struct task_struct *p = rq->curr;

	p->se.exec_start = rq->clock;
}

static const struct sched_class rt_sched_class = {
	.next			= &fair_sched_class,
	.enqueue_task		= enqueue_task_rt,
	.dequeue_task		= dequeue_task_rt,
	.yield_task		= yield_task_rt,
#ifdef CONFIG_SMP
	.select_task_rq		= select_task_rq_rt,
#endif /* CONFIG_SMP */

	.check_preempt_curr	= check_preempt_curr_rt,

	.pick_next_task		= pick_next_task_rt,
	.put_prev_task		= put_prev_task_rt,

#ifdef CONFIG_SMP
	.load_balance		= load_balance_rt,
	.move_one_task		= move_one_task_rt,
	.set_cpus_allowed       = set_cpus_allowed_rt,
	.join_domain            = join_domain_rt,
	.leave_domain           = leave_domain_rt,
	.pre_schedule		= pre_schedule_rt,
	.post_schedule		= post_schedule_rt,
	.task_wake_up		= task_wake_up_rt,
	.switched_from		= switched_from_rt,
#endif

	.set_curr_task          = set_curr_task_rt,
	.task_tick		= task_tick_rt,

	.prio_changed		= prio_changed_rt,
	.switched_to		= switched_to_rt,
};