sched_rt.c

	if ((this_cpu != -1) && cpu_isset(this_cpu, *mask))
		return this_cpu;

	first = first_cpu(*mask);
	if (first != NR_CPUS)
		return first;

	return -1;
}

static int find_lowest_rq(struct task_struct *task)
{
	struct sched_domain *sd;
	struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
	int this_cpu = smp_processor_id();
	int cpu      = task_cpu(task);

	if (task->rt.nr_cpus_allowed == 1)
		return -1; /* No other targets possible */

	if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
		return -1; /* No targets found */

	/*
	 * Only consider CPUs that are usable for migration.
	 * I guess we might want to change cpupri_find() to ignore those
	 * in the first place.
	 */
	cpumask_and(lowest_mask, lowest_mask, cpu_active_mask);

	/*
	 * At this point we have built a mask of cpus representing the
	 * lowest priority tasks in the system.  Now we want to elect
	 * the best one based on our affinity and topology.
	 *
	 * We prioritize the last cpu that the task executed on since
	 * it is most likely cache-hot in that location.
	 */
	if (cpumask_test_cpu(cpu, lowest_mask))
		return cpu;

	/*
	 * Otherwise, we consult the sched_domains span maps to figure
	 * out which cpu is logically closest to our hot cache data.
	 */
	if (this_cpu == cpu)
		this_cpu = -1; /* Skip this_cpu opt if the same */

	for_each_domain(cpu, sd) {
		if (sd->flags & SD_WAKE_AFFINE) {
			cpumask_t domain_mask;
			int       best_cpu;

			cpumask_and(&domain_mask, sched_domain_span(sd),
				    lowest_mask);

			best_cpu = pick_optimal_cpu(this_cpu,
						    &domain_mask);
			if (best_cpu != -1)
				return best_cpu;
		}
	}

	/*
	 * And finally, if there were no matches within the domains
	 * just give the caller *something* to work with from the compatible
	 * locations.
	 */
	return pick_optimal_cpu(this_cpu, lowest_mask);
}

/* Will lock the rq it finds */
static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
{
	struct rq *lowest_rq = NULL;
	int tries;
	int cpu;

	for (tries = 0; tries < RT_MAX_TRIES; tries++) {
		cpu = find_lowest_rq(task);

		if ((cpu == -1) || (cpu == rq->cpu))
			break;

		lowest_rq = cpu_rq(cpu);

		/* if the prio of this runqueue changed, try again */
		if (double_lock_balance(rq, lowest_rq)) {
			/*
			 * We had to unlock the run queue. In
			 * the mean time, task could have
			 * migrated already or had its affinity changed.
			 * Also make sure that it wasn't scheduled on its rq.
			 */
			if (unlikely(task_rq(task) != rq ||
				     !cpumask_test_cpu(lowest_rq->cpu,
						       &task->cpus_allowed) ||
				     task_running(rq, task) ||
				     !task->se.on_rq)) {

				spin_unlock(&lowest_rq->lock);
				lowest_rq = NULL;
				break;
			}
		}

		/* If this rq is still suitable use it. */
		if (lowest_rq->rt.highest_prio.curr > task->prio)
			break;

		/* try again */
		double_unlock_balance(rq, lowest_rq);
		lowest_rq = NULL;
	}

	return lowest_rq;
}

/*
 * If the current CPU has more than one RT task, see if the non
 * running task can migrate over to a CPU that is running a task
 * of lesser priority.
 */
static int push_rt_task(struct rq *rq)
{
	struct task_struct *next_task;
	struct rq *lowest_rq;
	int ret = 0;
	int paranoid = RT_MAX_TRIES;

	if (!rq->rt.overloaded)
		return 0;

	next_task = pick_next_highest_task_rt(rq, -1);
	if (!next_task)
		return 0;

 retry:
	if (unlikely(next_task == rq->curr)) {
		WARN_ON(1);
		return 0;
	}

	/*
	 * It's possible that the next_task slipped in of
	 * higher priority than current. If that's the case
	 * just reschedule current.
	 */
	if (unlikely(next_task->prio < rq->curr->prio)) {
		resched_task(rq->curr);
		return 0;
	}

	/* We might release rq lock */
	get_task_struct(next_task);

	/* find_lock_lowest_rq locks the rq if found */
	lowest_rq = find_lock_lowest_rq(next_task, rq);
	if (!lowest_rq) {
		struct task_struct *task;
		/*
		 * find lock_lowest_rq releases rq->lock
		 * so it is possible that next_task has changed.
		 * If it has, then try again.
		 */
		task = pick_next_highest_task_rt(rq, -1);
		if (unlikely(task != next_task) && task && paranoid--) {
			put_task_struct(next_task);
			next_task = task;
			goto retry;
		}
		goto out;
	}

	deactivate_task(rq, next_task, 0);
	set_task_cpu(next_task, lowest_rq->cpu);
	activate_task(lowest_rq, next_task, 0);

	resched_task(lowest_rq->curr);

	double_unlock_balance(rq, lowest_rq);

	ret = 1;
out:
	put_task_struct(next_task);

	return ret;
}

/*
 * TODO: Currently we just use the second highest prio task on
 *       the queue, and stop when it can't migrate (or there's
 *       no more RT tasks).  There may be a case where a lower
 *       priority RT task has a different affinity than the
 *       higher RT task. In this case the lower RT task could
 *       possibly be able to migrate where as the higher priority
 *       RT task could not.  We currently ignore this issue.
 *       Enhancements are welcome!
 */
static void push_rt_tasks(struct rq *rq)
{
	/* push_rt_task will return true if it moved an RT */
	while (push_rt_task(rq))
		;
}

static int pull_rt_task(struct rq *this_rq)
{
	int this_cpu = this_rq->cpu, ret = 0, cpu;
	struct task_struct *p;
	struct rq *src_rq;

	if (likely(!rt_overloaded(this_rq)))
		return 0;

	for_each_cpu(cpu, this_rq->rd->rto_mask) {
		if (this_cpu == cpu)
			continue;

		src_rq = cpu_rq(cpu);
		/*
		 * We can potentially drop this_rq's lock in
		 * double_lock_balance, and another CPU could
		 * alter this_rq
		 */
		double_lock_balance(this_rq, src_rq);

		/*
		 * 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 && (p->prio < this_rq->rt.highest_prio.curr)) {
			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
			 */
			if (p->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)
			 */
		}
 skip:
		double_unlock_balance(this_rq, src_rq);
	}

	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.curr > 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 struct cpumask *new_mask)
{
	int weight = cpumask_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);
	}

	cpumask_copy(&p->cpus_allowed, new_mask);
	p->rt.nr_cpus_allowed = weight;
}

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

	__enable_runtime(rq);

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

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

	__disable_runtime(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);
}

static inline void init_sched_rt_class(void)
{
	unsigned int i;

	for_each_possible_cpu(i)
		alloc_cpumask_var(&per_cpu(local_cpu_mask, i), GFP_KERNEL);
}
#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.curr && 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->cputime_expires.sched_exp = 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, 0);
		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,

	.check_preempt_curr	= check_preempt_curr_rt,

	.pick_next_task		= pick_next_task_rt,
	.put_prev_task		= put_prev_task_rt,

#ifdef CONFIG_SMP
	.select_task_rq		= select_task_rq_rt,

	.load_balance		= load_balance_rt,
	.move_one_task		= move_one_task_rt,
	.set_cpus_allowed       = set_cpus_allowed_rt,
	.rq_online              = rq_online_rt,
	.rq_offline             = rq_offline_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,
};

#ifdef CONFIG_SCHED_DEBUG
extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);

static void print_rt_stats(struct seq_file *m, int cpu)
{
	struct rt_rq *rt_rq;

	rcu_read_lock();
	for_each_leaf_rt_rq(rt_rq, cpu_rq(cpu))
		print_rt_rq(m, cpu, rt_rq);
	rcu_read_unlock();
}
#endif /* CONFIG_SCHED_DEBUG */