sched_rt.c

Kernel code of linux kernel

static inline
void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
	rt_rq->rt_nr_running++;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
	if (rt_se_prio(rt_se) < rt_rq->highest_prio) {
#ifdef CONFIG_SMP
		struct rq *rq = rq_of_rt_rq(rt_rq);
#endif

		rt_rq->highest_prio = rt_se_prio(rt_se);
#ifdef CONFIG_SMP
		if (rq->online)
			cpupri_set(&rq->rd->cpupri, rq->cpu,
				   rt_se_prio(rt_se));
#endif
	}
#endif
#ifdef CONFIG_SMP
	if (rt_se->nr_cpus_allowed > 1) {
		struct rq *rq = rq_of_rt_rq(rt_rq);

		rq->rt.rt_nr_migratory++;
	}

	update_rt_migration(rq_of_rt_rq(rt_rq));
#endif
#ifdef CONFIG_RT_GROUP_SCHED
	if (rt_se_boosted(rt_se))
		rt_rq->rt_nr_boosted++;

	if (rt_rq->tg)
		start_rt_bandwidth(&rt_rq->tg->rt_bandwidth);
#else
	start_rt_bandwidth(&def_rt_bandwidth);
#endif
}

static inline
void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
#ifdef CONFIG_SMP
	int highest_prio = rt_rq->highest_prio;
#endif

	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
	WARN_ON(!rt_rq->rt_nr_running);
	rt_rq->rt_nr_running--;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
	if (rt_rq->rt_nr_running) {
		struct rt_prio_array *array;

		WARN_ON(rt_se_prio(rt_se) < rt_rq->highest_prio);
		if (rt_se_prio(rt_se) == rt_rq->highest_prio) {
			/* recalculate */
			array = &rt_rq->active;
			rt_rq->highest_prio =
				sched_find_first_bit(array->bitmap);
		} /* otherwise leave rq->highest prio alone */
	} else
		rt_rq->highest_prio = MAX_RT_PRIO;
#endif
#ifdef CONFIG_SMP
	if (rt_se->nr_cpus_allowed > 1) {
		struct rq *rq = rq_of_rt_rq(rt_rq);
		rq->rt.rt_nr_migratory--;
	}

	if (rt_rq->highest_prio != highest_prio) {
		struct rq *rq = rq_of_rt_rq(rt_rq);

		if (rq->online)
			cpupri_set(&rq->rd->cpupri, rq->cpu,
				   rt_rq->highest_prio);
	}

	update_rt_migration(rq_of_rt_rq(rt_rq));
#endif /* CONFIG_SMP */
#ifdef CONFIG_RT_GROUP_SCHED
	if (rt_se_boosted(rt_se))
		rt_rq->rt_nr_boosted--;

	WARN_ON(!rt_rq->rt_nr_running && rt_rq->rt_nr_boosted);
#endif
}

static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
{
	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
	struct rt_prio_array *array = &rt_rq->active;
	struct rt_rq *group_rq = group_rt_rq(rt_se);
	struct list_head *queue = array->queue + rt_se_prio(rt_se);

	/*
	 * Don't enqueue the group if its throttled, or when empty.
	 * The latter is a consequence of the former when a child group
	 * get throttled and the current group doesn't have any other
	 * active members.
	 */
	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
		return;

	list_add_tail(&rt_se->run_list, queue);
	__set_bit(rt_se_prio(rt_se), array->bitmap);

	inc_rt_tasks(rt_se, rt_rq);
}

static void __dequeue_rt_entity(struct sched_rt_entity *rt_se)
{
	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
	struct rt_prio_array *array = &rt_rq->active;

	list_del_init(&rt_se->run_list);
	if (list_empty(array->queue + rt_se_prio(rt_se)))
		__clear_bit(rt_se_prio(rt_se), array->bitmap);

	dec_rt_tasks(rt_se, rt_rq);
}

/*
 * Because the prio of an upper entry depends on the lower
 * entries, we must remove entries top - down.
 */
static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
{
	struct sched_rt_entity *back = NULL;

	for_each_sched_rt_entity(rt_se) {
		rt_se->back = back;
		back = rt_se;
	}

	for (rt_se = back; rt_se; rt_se = rt_se->back) {
		if (on_rt_rq(rt_se))
			__dequeue_rt_entity(rt_se);
	}
}

static void enqueue_rt_entity(struct sched_rt_entity *rt_se)
{
	dequeue_rt_stack(rt_se);
	for_each_sched_rt_entity(rt_se)
		__enqueue_rt_entity(rt_se);
}

static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
{
	dequeue_rt_stack(rt_se);

	for_each_sched_rt_entity(rt_se) {
		struct rt_rq *rt_rq = group_rt_rq(rt_se);

		if (rt_rq && rt_rq->rt_nr_running)
			__enqueue_rt_entity(rt_se);
	}
}

/*
 * Adding/removing a task to/from a priority array:
 */
static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
{
	struct sched_rt_entity *rt_se = &p->rt;

	if (wakeup)
		rt_se->timeout = 0;

	enqueue_rt_entity(rt_se);

	inc_cpu_load(rq, p->se.load.weight);
}

static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
{
	struct sched_rt_entity *rt_se = &p->rt;

	update_curr_rt(rq);
	dequeue_rt_entity(rt_se);

	dec_cpu_load(rq, p->se.load.weight);
}

/*
 * Put task to the end of the run list without the overhead of dequeue
 * followed by enqueue.
 */
static void
requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int head)
{
	if (on_rt_rq(rt_se)) {
		struct rt_prio_array *array = &rt_rq->active;
		struct list_head *queue = array->queue + rt_se_prio(rt_se);

		if (head)
			list_move(&rt_se->run_list, queue);
		else
			list_move_tail(&rt_se->run_list, queue);
	}
}

static void requeue_task_rt(struct rq *rq, struct task_struct *p, int head)
{
	struct sched_rt_entity *rt_se = &p->rt;
	struct rt_rq *rt_rq;

	for_each_sched_rt_entity(rt_se) {
		rt_rq = rt_rq_of_se(rt_se);
		requeue_rt_entity(rt_rq, rt_se, head);
	}
}

static void yield_task_rt(struct rq *rq)
{
	requeue_task_rt(rq, rq->curr, 0);
}

#ifdef CONFIG_SMP
static int find_lowest_rq(struct task_struct *task);

static int select_task_rq_rt(struct task_struct *p, int sync)
{
	struct rq *rq = task_rq(p);

	/*
	 * If the current task is an RT task, then
	 * try to see if we can wake this RT task up on another
	 * runqueue. Otherwise simply start this RT task
	 * on its current runqueue.
	 *
	 * We want to avoid overloading runqueues. Even if
	 * the RT task is of higher priority than the current RT task.
	 * RT tasks behave differently than other tasks. If
	 * one gets preempted, we try to push it off to another queue.
	 * So trying to keep a preempting RT task on the same
	 * cache hot CPU will force the running RT task to
	 * a cold CPU. So we waste all the cache for the lower
	 * RT task in hopes of saving some of a RT task
	 * that is just being woken and probably will have
	 * cold cache anyway.
	 */
	if (unlikely(rt_task(rq->curr)) &&
	    (p->rt.nr_cpus_allowed > 1)) {
		int cpu = find_lowest_rq(p);

		return (cpu == -1) ? task_cpu(p) : cpu;
	}

	/*
	 * Otherwise, just let it ride on the affined RQ and the
	 * post-schedule router will push the preempted task away
	 */
	return task_cpu(p);
}

static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
{
	cpumask_t mask;

	if (rq->curr->rt.nr_cpus_allowed == 1)
		return;

	if (p->rt.nr_cpus_allowed != 1
	    && cpupri_find(&rq->rd->cpupri, p, &mask))
		return;

	if (!cpupri_find(&rq->rd->cpupri, rq->curr, &mask))
		return;

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

#ifdef CONFIG_SMP

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

static int double_lock_balance(struct rq *this_rq, struct rq *busiest);
static void double_unlock_balance(struct rq *this_rq, struct rq *busiest);

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 || cpu_isset(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 = 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_t, local_cpu_mask);

static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
{
	int first;

	/* "this_cpu" is cheaper to preempt than a remote processor */
	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;
	cpumask_t *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.
	 */
	cpus_and(*lowest_mask, *lowest_mask, cpu_active_map);

	/*
	 * 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 (cpu_isset(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;

			cpus_and(domain_mask, sd->span, *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);