sched_rt.c

	 * There appears to be other cpus that can accept
	 * current and none to run 'p', so lets reschedule
	 * to try and push current away:
	 */
	requeue_task_rt(rq, p, 1);
	resched_task(rq->curr);
}

#endif /* CONFIG_SMP */

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

#ifdef CONFIG_SMP
	/*
	 * If:
	 *
	 * - the newly woken task is of equal priority to the current task
	 * - the newly woken task is non-migratable while current is migratable
	 * - current will be preempted on the next reschedule
	 *
	 * we should check to see if current can readily move to a different
	 * cpu.  If so, we will reschedule to allow the push logic to try
	 * to move current somewhere else, making room for our non-migratable
	 * task.
	 */
	if (p->prio == rq->curr->prio && !need_resched())
		check_preempt_equal_prio(rq, p);
#endif
}

static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
						   struct rt_rq *rt_rq)
{
	struct rt_prio_array *array = &rt_rq->active;
	struct sched_rt_entity *next = NULL;
	struct list_head *queue;
	int idx;

	idx = sched_find_first_bit(array->bitmap);
	BUG_ON(idx >= MAX_RT_PRIO);

	queue = array->queue + idx;
	next = list_entry(queue->next, struct sched_rt_entity, run_list);

	return next;
}

static struct task_struct *_pick_next_task_rt(struct rq *rq)
{
	struct sched_rt_entity *rt_se;
	struct task_struct *p;
	struct rt_rq *rt_rq;

	rt_rq = &rq->rt;

	if (unlikely(!rt_rq->rt_nr_running))
		return NULL;

	if (rt_rq_throttled(rt_rq))
		return NULL;

	do {
		rt_se = pick_next_rt_entity(rq, rt_rq);
		BUG_ON(!rt_se);
		rt_rq = group_rt_rq(rt_se);
	} while (rt_rq);

	p = rt_task_of(rt_se);
	p->se.exec_start = rq->clock;

	return p;
}

static struct task_struct *pick_next_task_rt(struct rq *rq)
{
	struct task_struct *p = _pick_next_task_rt(rq);

	/* The running task is never eligible for pushing */
	if (p)
		dequeue_pushable_task(rq, p);

#ifdef CONFIG_SMP
	/*
	 * We detect this state here so that we can avoid taking the RQ
	 * lock again later if there is no need to push
	 */
	rq->post_schedule = has_pushable_tasks(rq);
#endif

	return p;
}

static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
{
	update_curr_rt(rq);
	p->se.exec_start = 0;

	/*
	 * The previous task needs to be made eligible for pushing
	 * if it is still active
	 */
	if (p->se.on_rq && p->rt.nr_cpus_allowed > 1)
		enqueue_pushable_task(rq, p);
}

#ifdef CONFIG_SMP

/* Only try algorithms three times */
#define RT_MAX_TRIES 3

static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep);

static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
{
	if (!task_running(rq, p) &&
	    (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) &&
	    (p->rt.nr_cpus_allowed > 1))
		return 1;
	return 0;
}

/* Return the second highest RT task, NULL otherwise */
static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
{
	struct task_struct *next = NULL;
	struct sched_rt_entity *rt_se;
	struct rt_prio_array *array;
	struct rt_rq *rt_rq;
	int idx;

	for_each_leaf_rt_rq(rt_rq, rq) {
		array = &rt_rq->active;
		idx = sched_find_first_bit(array->bitmap);
 next_idx:
		if (idx >= MAX_RT_PRIO)
			continue;
		if (next && next->prio < idx)
			continue;
		list_for_each_entry(rt_se, array->queue + idx, run_list) {
			struct task_struct *p;

			if (!rt_entity_is_task(rt_se))
				continue;

			p = rt_task_of(rt_se);
			if (pick_rt_task(rq, p, cpu)) {
				next = p;
				break;
			}
		}
		if (!next) {
			idx = find_next_bit(array->bitmap, MAX_RT_PRIO, idx+1);
			goto next_idx;
		}
	}

	return next;
}

static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);

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 */

	/*
	 * 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 (!cpumask_test_cpu(this_cpu, lowest_mask))
		this_cpu = -1; /* Skip this_cpu opt if not among lowest */

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

			/*
			 * "this_cpu" is cheaper to preempt than a
			 * remote processor.
			 */
			if (this_cpu != -1 &&
			    cpumask_test_cpu(this_cpu, sched_domain_span(sd)))
				return this_cpu;

			best_cpu = cpumask_first_and(lowest_mask,
						     sched_domain_span(sd));
			if (best_cpu < nr_cpu_ids)
				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.
	 */
	if (this_cpu != -1)
		return this_cpu;

	cpu = cpumask_any(lowest_mask);
	if (cpu < nr_cpu_ids)
		return cpu;
	return -1;
}

/* 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)) {

				raw_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;
}

static struct task_struct *pick_next_pushable_task(struct rq *rq)
{
	struct task_struct *p;

	if (!has_pushable_tasks(rq))
		return NULL;

	p = plist_first_entry(&rq->rt.pushable_tasks,
			      struct task_struct, pushable_tasks);

	BUG_ON(rq->cpu != task_cpu(p));
	BUG_ON(task_current(rq, p));
	BUG_ON(p->rt.nr_cpus_allowed <= 1);

	BUG_ON(!p->se.on_rq);
	BUG_ON(!rt_task(p));

	return p;
}

/*
 * 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;

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

	next_task = pick_next_pushable_task(rq);
	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 migrated.
		 *
		 * We need to make sure that the task is still on the same
		 * run-queue and is also still the next task eligible for
		 * pushing.
		 */
		task = pick_next_pushable_task(rq);
		if (task_cpu(next_task) == rq->cpu && task == next_task) {
			/*
			 * If we get here, the task hasnt moved at all, but
			 * it has failed to push.  We will not try again,
			 * since the other cpus will pull from us when they
			 * are ready.
			 */
			dequeue_pushable_task(rq, next_task);
			goto out;
		}

		if (!task)
			/* No more tasks, just exit */
			goto out;

		/*
		 * Something has shifted, try again.
		 */
		put_task_struct(next_task);
		next_task = task;
		goto retry;
	}

	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);

out:
	put_task_struct(next_task);

	return 1;
}

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);

		/*
		 * Don't bother taking the src_rq->lock if the next highest
		 * task is known to be lower-priority than our current task.
		 * This may look racy, but if this value is about to go
		 * logically higher, the src_rq will push this task away.
		 * And if its going logically lower, we do not care
		 */
		if (src_rq->rt.highest_prio.next >=
		    this_rq->rt.highest_prio.curr)
			continue;

		/*
		 * 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)
{
	push_rt_tasks(rq);
}

/*
 * If we are not running and we are not going to reschedule soon, we should
 * try to push tasks away now
 */
static void task_woken_rt(struct rq *rq, struct task_struct *p)
{
	if (!task_running(rq, p) &&
	    !test_tsk_need_resched(rq->curr) &&
	    has_pushable_tasks(rq) &&
	    rt_task(rq->curr) &&
	    rq->curr->prio < p->prio &&
	    p->rt.nr_cpus_allowed > 1)
		push_rt_tasks(rq);
}

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 (!task_current(rq, p)) {
			/*
			 * Make sure we dequeue this task from the pushable list
			 * before going further.  It will either remain off of
			 * the list because we are no longer pushable, or it
			 * will be requeued.
			 */
			if (p->rt.nr_cpus_allowed > 1)
				dequeue_pushable_task(rq, p);

			/*
			 * Requeue if our weight is changing and still > 1
			 */
			if (weight > 1)
				enqueue_pushable_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->rt);
	}

	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)
		zalloc_cpumask_var_node(&per_cpu(local_cpu_mask, i),
					GFP_KERNEL, cpu_to_node(i));
}
#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;

	/* max may change after cur was read, this will be fixed next tick */
	soft = task_rlimit(p, RLIMIT_RTTIME);
	hard = task_rlimit_max(p, RLIMIT_RTTIME);

	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;

	/* The running task is never eligible for pushing */
	dequeue_pushable_task(rq, p);
}

static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
{
	/*
	 * Time slice is 0 for SCHED_FIFO tasks
	 */
	if (task->policy == SCHED_RR)
		return DEF_TIMESLICE;
	else
		return 0;
}

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,

	.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_woken		= task_woken_rt,
	.switched_from		= switched_from_rt,
#endif

	.set_curr_task          = set_curr_task_rt,
	.task_tick		= task_tick_rt,

	.get_rr_interval	= get_rr_interval_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 */