sched_fair.c

Kernel code of linux kernel

	if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
		return 0;

	/*
	 * If sync wakeup then subtract the (maximum possible)
	 * effect of the currently running task from the load
	 * of the current CPU:
	 */
	if (sync) {
		tg = task_group(current);
		weight = current->se.load.weight;

		tl += effective_load(tg, this_cpu, -weight, -weight);
		load += effective_load(tg, prev_cpu, 0, -weight);
	}

	tg = task_group(p);
	weight = p->se.load.weight;

	balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <=
		imbalance*(load + effective_load(tg, prev_cpu, 0, weight));

	/*
	 * If the currently running task will sleep within
	 * a reasonable amount of time then attract this newly
	 * woken task:
	 */
	if (sync && balanced) {
		if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
		    p->se.avg_overlap < sysctl_sched_migration_cost)
			return 1;
	}

	schedstat_inc(p, se.nr_wakeups_affine_attempts);
	tl_per_task = cpu_avg_load_per_task(this_cpu);

	if ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) ||
			balanced) {
		/*
		 * This domain has SD_WAKE_AFFINE and
		 * p is cache cold in this domain, and
		 * there is no bad imbalance.
		 */
		schedstat_inc(this_sd, ttwu_move_affine);
		schedstat_inc(p, se.nr_wakeups_affine);

		return 1;
	}
	return 0;
}

static int select_task_rq_fair(struct task_struct *p, int sync)
{
	struct sched_domain *sd, *this_sd = NULL;
	int prev_cpu, this_cpu, new_cpu;
	unsigned long load, this_load;
	struct rq *rq, *this_rq;
	unsigned int imbalance;
	int idx;

	prev_cpu	= task_cpu(p);
	rq		= task_rq(p);
	this_cpu	= smp_processor_id();
	this_rq		= cpu_rq(this_cpu);
	new_cpu		= prev_cpu;

	/*
	 * 'this_sd' is the first domain that both
	 * this_cpu and prev_cpu are present in:
	 */
	for_each_domain(this_cpu, sd) {
		if (cpu_isset(prev_cpu, sd->span)) {
			this_sd = sd;
			break;
		}
	}

	if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
		goto out;

	/*
	 * Check for affine wakeup and passive balancing possibilities.
	 */
	if (!this_sd)
		goto out;

	idx = this_sd->wake_idx;

	imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;

	load = source_load(prev_cpu, idx);
	this_load = target_load(this_cpu, idx);

	if (wake_affine(rq, this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
				     load, this_load, imbalance))
		return this_cpu;

	if (prev_cpu == this_cpu)
		goto out;

	/*
	 * Start passive balancing when half the imbalance_pct
	 * limit is reached.
	 */
	if (this_sd->flags & SD_WAKE_BALANCE) {
		if (imbalance*this_load <= 100*load) {
			schedstat_inc(this_sd, ttwu_move_balance);
			schedstat_inc(p, se.nr_wakeups_passive);
			return this_cpu;
		}
	}

out:
	return wake_idle(new_cpu, p);
}
#endif /* CONFIG_SMP */

static unsigned long wakeup_gran(struct sched_entity *se)
{
	unsigned long gran = sysctl_sched_wakeup_granularity;

	/*
	 * More easily preempt - nice tasks, while not making it harder for
	 * + nice tasks.
	 */
	if (sched_feat(ASYM_GRAN))
		gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se);
	else
		gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se);

	return gran;
}

/*
 * Should 'se' preempt 'curr'.
 *
 *             |s1
 *        |s2
 *   |s3
 *         g
 *      |<--->|c
 *
 *  w(c, s1) = -1
 *  w(c, s2) =  0
 *  w(c, s3) =  1
 *
 */
static int
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
{
	s64 gran, vdiff = curr->vruntime - se->vruntime;

	if (vdiff < 0)
		return -1;

	gran = wakeup_gran(curr);
	if (vdiff > gran)
		return 1;

	return 0;
}

/* return depth at which a sched entity is present in the hierarchy */
static inline int depth_se(struct sched_entity *se)
{
	int depth = 0;

	for_each_sched_entity(se)
		depth++;

	return depth;
}

/*
 * Preempt the current task with a newly woken task if needed:
 */
static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
{
	struct task_struct *curr = rq->curr;
	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
	struct sched_entity *se = &curr->se, *pse = &p->se;
	int se_depth, pse_depth;

	if (unlikely(rt_prio(p->prio))) {
		update_rq_clock(rq);
		update_curr(cfs_rq);
		resched_task(curr);
		return;
	}

	if (unlikely(se == pse))
		return;

	cfs_rq_of(pse)->next = pse;

	/*
	 * Batch tasks do not preempt (their preemption is driven by
	 * the tick):
	 */
	if (unlikely(p->policy == SCHED_BATCH))
		return;

	if (!sched_feat(WAKEUP_PREEMPT))
		return;

	/*
	 * preemption test can be made between sibling entities who are in the
	 * same cfs_rq i.e who have a common parent. Walk up the hierarchy of
	 * both tasks until we find their ancestors who are siblings of common
	 * parent.
	 */

	/* First walk up until both entities are at same depth */
	se_depth = depth_se(se);
	pse_depth = depth_se(pse);

	while (se_depth > pse_depth) {
		se_depth--;
		se = parent_entity(se);
	}

	while (pse_depth > se_depth) {
		pse_depth--;
		pse = parent_entity(pse);
	}

	while (!is_same_group(se, pse)) {
		se = parent_entity(se);
		pse = parent_entity(pse);
	}

	if (wakeup_preempt_entity(se, pse) == 1)
		resched_task(curr);
}

static struct task_struct *pick_next_task_fair(struct rq *rq)
{
	struct task_struct *p;
	struct cfs_rq *cfs_rq = &rq->cfs;
	struct sched_entity *se;

	if (unlikely(!cfs_rq->nr_running))
		return NULL;

	do {
		se = pick_next_entity(cfs_rq);
		cfs_rq = group_cfs_rq(se);
	} while (cfs_rq);

	p = task_of(se);
	hrtick_start_fair(rq, p);

	return p;
}

/*
 * Account for a descheduled task:
 */
static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
{
	struct sched_entity *se = &prev->se;
	struct cfs_rq *cfs_rq;

	for_each_sched_entity(se) {
		cfs_rq = cfs_rq_of(se);
		put_prev_entity(cfs_rq, se);
	}
}

#ifdef CONFIG_SMP
/**************************************************
 * Fair scheduling class load-balancing methods:
 */

/*
 * Load-balancing iterator. Note: while the runqueue stays locked
 * during the whole iteration, the current task might be
 * dequeued so the iterator has to be dequeue-safe. Here we
 * achieve that by always pre-iterating before returning
 * the current task:
 */
static struct task_struct *
__load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
{
	struct task_struct *p = NULL;
	struct sched_entity *se;

	if (next == &cfs_rq->tasks)
		return NULL;

	/* Skip over entities that are not tasks */
	do {
		se = list_entry(next, struct sched_entity, group_node);
		next = next->next;
	} while (next != &cfs_rq->tasks && !entity_is_task(se));

	if (next == &cfs_rq->tasks)
		return NULL;

	cfs_rq->balance_iterator = next;

	if (entity_is_task(se))
		p = task_of(se);

	return p;
}

static struct task_struct *load_balance_start_fair(void *arg)
{
	struct cfs_rq *cfs_rq = arg;

	return __load_balance_iterator(cfs_rq, cfs_rq->tasks.next);
}

static struct task_struct *load_balance_next_fair(void *arg)
{
	struct cfs_rq *cfs_rq = arg;

	return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
}

static unsigned long
__load_balance_fair(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,
		struct cfs_rq *cfs_rq)
{
	struct rq_iterator cfs_rq_iterator;

	cfs_rq_iterator.start = load_balance_start_fair;
	cfs_rq_iterator.next = load_balance_next_fair;
	cfs_rq_iterator.arg = cfs_rq;

	return balance_tasks(this_rq, this_cpu, busiest,
			max_load_move, sd, idle, all_pinned,
			this_best_prio, &cfs_rq_iterator);
}

#ifdef CONFIG_FAIR_GROUP_SCHED
static unsigned long
load_balance_fair(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)
{
	long rem_load_move = max_load_move;
	int busiest_cpu = cpu_of(busiest);
	struct task_group *tg;

	rcu_read_lock();
	update_h_load(busiest_cpu);

	list_for_each_entry(tg, &task_groups, list) {
		struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu];
		unsigned long busiest_h_load = busiest_cfs_rq->h_load;
		unsigned long busiest_weight = busiest_cfs_rq->load.weight;
		u64 rem_load, moved_load;

		/*
		 * empty group
		 */
		if (!busiest_cfs_rq->task_weight)
			continue;

		rem_load = (u64)rem_load_move * busiest_weight;
		rem_load = div_u64(rem_load, busiest_h_load + 1);

		moved_load = __load_balance_fair(this_rq, this_cpu, busiest,
				rem_load, sd, idle, all_pinned, this_best_prio,
				tg->cfs_rq[busiest_cpu]);

		if (!moved_load)
			continue;

		moved_load *= busiest_h_load;
		moved_load = div_u64(moved_load, busiest_weight + 1);

		rem_load_move -= moved_load;
		if (rem_load_move < 0)
			break;
	}
	rcu_read_unlock();

	return max_load_move - rem_load_move;
}
#else
static unsigned long
load_balance_fair(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)
{
	return __load_balance_fair(this_rq, this_cpu, busiest,
			max_load_move, sd, idle, all_pinned,
			this_best_prio, &busiest->cfs);
}
#endif

static int
move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
		   struct sched_domain *sd, enum cpu_idle_type idle)
{
	struct cfs_rq *busy_cfs_rq;
	struct rq_iterator cfs_rq_iterator;

	cfs_rq_iterator.start = load_balance_start_fair;
	cfs_rq_iterator.next = load_balance_next_fair;

	for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
		/*
		 * pass busy_cfs_rq argument into
		 * load_balance_[start|next]_fair iterators
		 */
		cfs_rq_iterator.arg = busy_cfs_rq;
		if (iter_move_one_task(this_rq, this_cpu, busiest, sd, idle,
				       &cfs_rq_iterator))
		    return 1;
	}

	return 0;
}
#endif /* CONFIG_SMP */

/*
 * scheduler tick hitting a task of our scheduling class:
 */
static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se = &curr->se;

	for_each_sched_entity(se) {
		cfs_rq = cfs_rq_of(se);
		entity_tick(cfs_rq, se, queued);
	}
}

#define swap(a, b) do { typeof(a) tmp = (a); (a) = (b); (b) = tmp; } while (0)

/*
 * Share the fairness runtime between parent and child, thus the
 * total amount of pressure for CPU stays equal - new tasks
 * get a chance to run but frequent forkers are not allowed to
 * monopolize the CPU. Note: the parent runqueue is locked,
 * the child is not running yet.
 */
static void task_new_fair(struct rq *rq, struct task_struct *p)
{
	struct cfs_rq *cfs_rq = task_cfs_rq(p);
	struct sched_entity *se = &p->se, *curr = cfs_rq->curr;
	int this_cpu = smp_processor_id();

	sched_info_queued(p);

	update_curr(cfs_rq);
	place_entity(cfs_rq, se, 1);

	/* 'curr' will be NULL if the child belongs to a different group */
	if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) &&
			curr && curr->vruntime < se->vruntime) {
		/*
		 * Upon rescheduling, sched_class::put_prev_task() will place
		 * 'current' within the tree based on its new key value.
		 */
		swap(curr->vruntime, se->vruntime);
	}

	enqueue_task_fair(rq, p, 0);
	resched_task(rq->curr);
}

/*
 * Priority of the task has changed. Check to see if we preempt
 * the current task.
 */
static void prio_changed_fair(struct rq *rq, struct task_struct *p,
			      int oldprio, int running)
{
	/*
	 * Reschedule if we are currently running on this runqueue and
	 * our priority decreased, or if we are not currently running on
	 * this runqueue and our priority is higher than the current's
	 */
	if (running) {
		if (p->prio > oldprio)
			resched_task(rq->curr);
	} else
		check_preempt_curr(rq, p);
}

/*
 * We switched to the sched_fair class.
 */
static void switched_to_fair(struct rq *rq, struct task_struct *p,
			     int running)
{
	/*
	 * We were most likely switched from sched_rt, so
	 * kick off the schedule if running, otherwise just see
	 * if we can still preempt the current task.
	 */
	if (running)
		resched_task(rq->curr);
	else
		check_preempt_curr(rq, p);
}

/* Account for a task changing its policy or group.
 *
 * This routine is mostly called to set cfs_rq->curr field when a task
 * migrates between groups/classes.
 */
static void set_curr_task_fair(struct rq *rq)
{
	struct sched_entity *se = &rq->curr->se;

	for_each_sched_entity(se)
		set_next_entity(cfs_rq_of(se), se);
}

#ifdef CONFIG_FAIR_GROUP_SCHED
static void moved_group_fair(struct task_struct *p)
{
	struct cfs_rq *cfs_rq = task_cfs_rq(p);

	update_curr(cfs_rq);
	place_entity(cfs_rq, &p->se, 1);
}
#endif

/*
 * All the scheduling class methods:
 */
static const struct sched_class fair_sched_class = {
	.next			= &idle_sched_class,
	.enqueue_task		= enqueue_task_fair,
	.dequeue_task		= dequeue_task_fair,
	.yield_task		= yield_task_fair,
#ifdef CONFIG_SMP
	.select_task_rq		= select_task_rq_fair,
#endif /* CONFIG_SMP */

	.check_preempt_curr	= check_preempt_wakeup,

	.pick_next_task		= pick_next_task_fair,
	.put_prev_task		= put_prev_task_fair,

#ifdef CONFIG_SMP
	.load_balance		= load_balance_fair,
	.move_one_task		= move_one_task_fair,
#endif

	.set_curr_task          = set_curr_task_fair,
	.task_tick		= task_tick_fair,
	.task_new		= task_new_fair,

	.prio_changed		= prio_changed_fair,
	.switched_to		= switched_to_fair,

#ifdef CONFIG_FAIR_GROUP_SCHED
	.moved_group		= moved_group_fair,
#endif
};

#ifdef CONFIG_SCHED_DEBUG
static void print_cfs_stats(struct seq_file *m, int cpu)
{
	struct cfs_rq *cfs_rq;

	rcu_read_lock();
	for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
		print_cfs_rq(m, cpu, cfs_rq);
	rcu_read_unlock();
}
#endif