sched_rt.c

Kernel code of linux kernel

/*
 * Real-Time Scheduling Class (mapped to the SCHED_FIFO and SCHED_RR
 * policies)
 */

#ifdef CONFIG_SMP

static inline int rt_overloaded(struct rq *rq)
{
	return atomic_read(&rq->rd->rto_count);
}

static inline void rt_set_overload(struct rq *rq)
{
	if (!rq->online)
		return;

	cpu_set(rq->cpu, rq->rd->rto_mask);
	/*
	 * Make sure the mask is visible before we set
	 * the overload count. That is checked to determine
	 * if we should look at the mask. It would be a shame
	 * if we looked at the mask, but the mask was not
	 * updated yet.
	 */
	wmb();
	atomic_inc(&rq->rd->rto_count);
}

static inline void rt_clear_overload(struct rq *rq)
{
	if (!rq->online)
		return;

	/* the order here really doesn't matter */
	atomic_dec(&rq->rd->rto_count);
	cpu_clear(rq->cpu, rq->rd->rto_mask);
}

static void update_rt_migration(struct rq *rq)
{
	if (rq->rt.rt_nr_migratory && (rq->rt.rt_nr_running > 1)) {
		if (!rq->rt.overloaded) {
			rt_set_overload(rq);
			rq->rt.overloaded = 1;
		}
	} else if (rq->rt.overloaded) {
		rt_clear_overload(rq);
		rq->rt.overloaded = 0;
	}
}
#endif /* CONFIG_SMP */

static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
{
	return container_of(rt_se, struct task_struct, rt);
}

static inline int on_rt_rq(struct sched_rt_entity *rt_se)
{
	return !list_empty(&rt_se->run_list);
}

#ifdef CONFIG_RT_GROUP_SCHED

static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
{
	if (!rt_rq->tg)
		return RUNTIME_INF;

	return rt_rq->rt_runtime;
}

static inline u64 sched_rt_period(struct rt_rq *rt_rq)
{
	return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period);
}

#define for_each_leaf_rt_rq(rt_rq, rq) \
	list_for_each_entry(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)

static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
	return rt_rq->rq;
}

static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
{
	return rt_se->rt_rq;
}

#define for_each_sched_rt_entity(rt_se) \
	for (; rt_se; rt_se = rt_se->parent)

static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
{
	return rt_se->my_q;
}

static void enqueue_rt_entity(struct sched_rt_entity *rt_se);
static void dequeue_rt_entity(struct sched_rt_entity *rt_se);

static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
{
	struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
	struct sched_rt_entity *rt_se = rt_rq->rt_se;

	if (rt_rq->rt_nr_running) {
		if (rt_se && !on_rt_rq(rt_se))
			enqueue_rt_entity(rt_se);
		if (rt_rq->highest_prio < curr->prio)
			resched_task(curr);
	}
}

static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
{
	struct sched_rt_entity *rt_se = rt_rq->rt_se;

	if (rt_se && on_rt_rq(rt_se))
		dequeue_rt_entity(rt_se);
}

static inline int rt_rq_throttled(struct rt_rq *rt_rq)
{
	return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
}

static int rt_se_boosted(struct sched_rt_entity *rt_se)
{
	struct rt_rq *rt_rq = group_rt_rq(rt_se);
	struct task_struct *p;

	if (rt_rq)
		return !!rt_rq->rt_nr_boosted;

	p = rt_task_of(rt_se);
	return p->prio != p->normal_prio;
}

#ifdef CONFIG_SMP
static inline cpumask_t sched_rt_period_mask(void)
{
	return cpu_rq(smp_processor_id())->rd->span;
}
#else
static inline cpumask_t sched_rt_period_mask(void)
{
	return cpu_online_map;
}
#endif

static inline
struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
{
	return container_of(rt_b, struct task_group, rt_bandwidth)->rt_rq[cpu];
}

static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
{
	return &rt_rq->tg->rt_bandwidth;
}

#else /* !CONFIG_RT_GROUP_SCHED */

static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
{
	return rt_rq->rt_runtime;
}

static inline u64 sched_rt_period(struct rt_rq *rt_rq)
{
	return ktime_to_ns(def_rt_bandwidth.rt_period);
}

#define for_each_leaf_rt_rq(rt_rq, rq) \
	for (rt_rq = &rq->rt; rt_rq; rt_rq = NULL)

static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
	return container_of(rt_rq, struct rq, rt);
}

static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
{
	struct task_struct *p = rt_task_of(rt_se);
	struct rq *rq = task_rq(p);

	return &rq->rt;
}

#define for_each_sched_rt_entity(rt_se) \
	for (; rt_se; rt_se = NULL)

static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
{
	return NULL;
}

static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
{
	if (rt_rq->rt_nr_running)
		resched_task(rq_of_rt_rq(rt_rq)->curr);
}

static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
{
}

static inline int rt_rq_throttled(struct rt_rq *rt_rq)
{
	return rt_rq->rt_throttled;
}

static inline cpumask_t sched_rt_period_mask(void)
{
	return cpu_online_map;
}

static inline
struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
{
	return &cpu_rq(cpu)->rt;
}

static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
{
	return &def_rt_bandwidth;
}

#endif /* CONFIG_RT_GROUP_SCHED */

#ifdef CONFIG_SMP
static int do_balance_runtime(struct rt_rq *rt_rq)
{
	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
	struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
	int i, weight, more = 0;
	u64 rt_period;

	weight = cpus_weight(rd->span);

	spin_lock(&rt_b->rt_runtime_lock);
	rt_period = ktime_to_ns(rt_b->rt_period);
	for_each_cpu_mask_nr(i, rd->span) {
		struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
		s64 diff;

		if (iter == rt_rq)
			continue;

		spin_lock(&iter->rt_runtime_lock);
		if (iter->rt_runtime == RUNTIME_INF)
			goto next;

		diff = iter->rt_runtime - iter->rt_time;
		if (diff > 0) {
			diff = div_u64((u64)diff, weight);
			if (rt_rq->rt_runtime + diff > rt_period)
				diff = rt_period - rt_rq->rt_runtime;
			iter->rt_runtime -= diff;
			rt_rq->rt_runtime += diff;
			more = 1;
			if (rt_rq->rt_runtime == rt_period) {
				spin_unlock(&iter->rt_runtime_lock);
				break;
			}
		}
next:
		spin_unlock(&iter->rt_runtime_lock);
	}
	spin_unlock(&rt_b->rt_runtime_lock);

	return more;
}

static void __disable_runtime(struct rq *rq)
{
	struct root_domain *rd = rq->rd;
	struct rt_rq *rt_rq;

	if (unlikely(!scheduler_running))
		return;

	for_each_leaf_rt_rq(rt_rq, rq) {
		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
		s64 want;
		int i;

		spin_lock(&rt_b->rt_runtime_lock);
		spin_lock(&rt_rq->rt_runtime_lock);
		if (rt_rq->rt_runtime == RUNTIME_INF ||
				rt_rq->rt_runtime == rt_b->rt_runtime)
			goto balanced;
		spin_unlock(&rt_rq->rt_runtime_lock);

		want = rt_b->rt_runtime - rt_rq->rt_runtime;

		for_each_cpu_mask(i, rd->span) {
			struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
			s64 diff;

			if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF)
				continue;

			spin_lock(&iter->rt_runtime_lock);
			if (want > 0) {
				diff = min_t(s64, iter->rt_runtime, want);
				iter->rt_runtime -= diff;
				want -= diff;
			} else {
				iter->rt_runtime -= want;
				want -= want;
			}
			spin_unlock(&iter->rt_runtime_lock);

			if (!want)
				break;
		}

		spin_lock(&rt_rq->rt_runtime_lock);
		BUG_ON(want);
balanced:
		rt_rq->rt_runtime = RUNTIME_INF;
		spin_unlock(&rt_rq->rt_runtime_lock);
		spin_unlock(&rt_b->rt_runtime_lock);
	}
}

static void disable_runtime(struct rq *rq)
{
	unsigned long flags;

	spin_lock_irqsave(&rq->lock, flags);
	__disable_runtime(rq);
	spin_unlock_irqrestore(&rq->lock, flags);
}

static void __enable_runtime(struct rq *rq)
{
	struct rt_rq *rt_rq;

	if (unlikely(!scheduler_running))
		return;

	for_each_leaf_rt_rq(rt_rq, rq) {
		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);

		spin_lock(&rt_b->rt_runtime_lock);
		spin_lock(&rt_rq->rt_runtime_lock);
		rt_rq->rt_runtime = rt_b->rt_runtime;
		rt_rq->rt_time = 0;
		rt_rq->rt_throttled = 0;
		spin_unlock(&rt_rq->rt_runtime_lock);
		spin_unlock(&rt_b->rt_runtime_lock);
	}
}

static void enable_runtime(struct rq *rq)
{
	unsigned long flags;

	spin_lock_irqsave(&rq->lock, flags);
	__enable_runtime(rq);
	spin_unlock_irqrestore(&rq->lock, flags);
}

static int balance_runtime(struct rt_rq *rt_rq)
{
	int more = 0;

	if (rt_rq->rt_time > rt_rq->rt_runtime) {
		spin_unlock(&rt_rq->rt_runtime_lock);
		more = do_balance_runtime(rt_rq);
		spin_lock(&rt_rq->rt_runtime_lock);
	}

	return more;
}
#else /* !CONFIG_SMP */
static inline int balance_runtime(struct rt_rq *rt_rq)
{
	return 0;
}
#endif /* CONFIG_SMP */

static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
{
	int i, idle = 1;
	cpumask_t span;

	if (rt_b->rt_runtime == RUNTIME_INF)
		return 1;

	span = sched_rt_period_mask();
	for_each_cpu_mask(i, span) {
		int enqueue = 0;
		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
		struct rq *rq = rq_of_rt_rq(rt_rq);

		spin_lock(&rq->lock);
		if (rt_rq->rt_time) {
			u64 runtime;

			spin_lock(&rt_rq->rt_runtime_lock);
			if (rt_rq->rt_throttled)
				balance_runtime(rt_rq);
			runtime = rt_rq->rt_runtime;
			rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime);
			if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
				rt_rq->rt_throttled = 0;
				enqueue = 1;
			}
			if (rt_rq->rt_time || rt_rq->rt_nr_running)
				idle = 0;
			spin_unlock(&rt_rq->rt_runtime_lock);
		} else if (rt_rq->rt_nr_running)
			idle = 0;

		if (enqueue)
			sched_rt_rq_enqueue(rt_rq);
		spin_unlock(&rq->lock);
	}

	return idle;
}

static inline int rt_se_prio(struct sched_rt_entity *rt_se)
{
#ifdef CONFIG_RT_GROUP_SCHED
	struct rt_rq *rt_rq = group_rt_rq(rt_se);

	if (rt_rq)
		return rt_rq->highest_prio;
#endif

	return rt_task_of(rt_se)->prio;
}

static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
{
	u64 runtime = sched_rt_runtime(rt_rq);

	if (rt_rq->rt_throttled)
		return rt_rq_throttled(rt_rq);

	if (sched_rt_runtime(rt_rq) >= sched_rt_period(rt_rq))
		return 0;

	balance_runtime(rt_rq);
	runtime = sched_rt_runtime(rt_rq);
	if (runtime == RUNTIME_INF)
		return 0;

	if (rt_rq->rt_time > runtime) {
		rt_rq->rt_throttled = 1;
		if (rt_rq_throttled(rt_rq)) {
			sched_rt_rq_dequeue(rt_rq);
			return 1;
		}
	}

	return 0;
}

/*
 * Update the current task's runtime statistics. Skip current tasks that
 * are not in our scheduling class.
 */
static void update_curr_rt(struct rq *rq)
{
	struct task_struct *curr = rq->curr;
	struct sched_rt_entity *rt_se = &curr->rt;
	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
	u64 delta_exec;

	if (!task_has_rt_policy(curr))
		return;

	delta_exec = rq->clock - curr->se.exec_start;
	if (unlikely((s64)delta_exec < 0))
		delta_exec = 0;

	schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec));

	curr->se.sum_exec_runtime += delta_exec;
	curr->se.exec_start = rq->clock;
	cpuacct_charge(curr, delta_exec);

	for_each_sched_rt_entity(rt_se) {
		rt_rq = rt_rq_of_se(rt_se);

		spin_lock(&rt_rq->rt_runtime_lock);
		if (sched_rt_runtime(rt_rq) != RUNTIME_INF) {
			rt_rq->rt_time += delta_exec;
			if (sched_rt_runtime_exceeded(rt_rq))
				resched_task(curr);
		}
		spin_unlock(&rt_rq->rt_runtime_lock);
	}
}