sched_fair.c

/*
 * Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH)
 *
 *  Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
 *
 *  Interactivity improvements by Mike Galbraith
 *  (C) 2007 Mike Galbraith <efault@gmx.de>
 *
 *  Various enhancements by Dmitry Adamushko.
 *  (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com>
 *
 *  Group scheduling enhancements by Srivatsa Vaddagiri
 *  Copyright IBM Corporation, 2007
 *  Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
 *
 *  Scaled math optimizations by Thomas Gleixner
 *  Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
 *
 *  Adaptive scheduling granularity, math enhancements by Peter Zijlstra
 *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
 */

/*
 * Targeted preemption latency for CPU-bound tasks:
 * (default: 20ms * (1 + ilog(ncpus)), units: nanoseconds)
 *
 * NOTE: this latency value is not the same as the concept of
 * 'timeslice length' - timeslices in CFS are of variable length
 * and have no persistent notion like in traditional, time-slice
 * based scheduling concepts.
 *
 * (to see the precise effective timeslice length of your workload,
 *  run vmstat and monitor the context-switches (cs) field)
 */
unsigned int sysctl_sched_latency = 20000000ULL;

/*
 * Minimal preemption granularity for CPU-bound tasks:
 * (default: 4 msec * (1 + ilog(ncpus)), units: nanoseconds)
 */
unsigned int sysctl_sched_min_granularity = 4000000ULL;

/*
 * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
 */
static unsigned int sched_nr_latency = 5;

/*
 * After fork, child runs first. (default) If set to 0 then
 * parent will (try to) run first.
 */
const_debug unsigned int sysctl_sched_child_runs_first = 1;

/*
 * sys_sched_yield() compat mode
 *
 * This option switches the agressive yield implementation of the
 * old scheduler back on.
 */
unsigned int __read_mostly sysctl_sched_compat_yield;

/*
 * SCHED_BATCH wake-up granularity.
 * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds)
 *
 * This option delays the preemption effects of decoupled workloads
 * and reduces their over-scheduling. Synchronous workloads will still
 * have immediate wakeup/sleep latencies.
 */
unsigned int sysctl_sched_batch_wakeup_granularity = 10000000UL;

/*
 * SCHED_OTHER wake-up granularity.
 * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds)
 *
 * This option delays the preemption effects of decoupled workloads
 * and reduces their over-scheduling. Synchronous workloads will still
 * have immediate wakeup/sleep latencies.
 */
unsigned int sysctl_sched_wakeup_granularity = 10000000UL;

const_debug unsigned int sysctl_sched_migration_cost = 500000UL;

/**************************************************************
 * CFS operations on generic schedulable entities:
 */

#ifdef CONFIG_FAIR_GROUP_SCHED

/* cpu runqueue to which this cfs_rq is attached */
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
{
	return cfs_rq->rq;
}

/* An entity is a task if it doesn't "own" a runqueue */
#define entity_is_task(se)	(!se->my_q)

#else	/* CONFIG_FAIR_GROUP_SCHED */

static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
{
	return container_of(cfs_rq, struct rq, cfs);
}

#define entity_is_task(se)	1

#endif	/* CONFIG_FAIR_GROUP_SCHED */

static inline struct task_struct *task_of(struct sched_entity *se)
{
	return container_of(se, struct task_struct, se);
}


/**************************************************************
 * Scheduling class tree data structure manipulation methods:
 */

static inline u64 max_vruntime(u64 min_vruntime, u64 vruntime)
{
	s64 delta = (s64)(vruntime - min_vruntime);
	if (delta > 0)
		min_vruntime = vruntime;

	return min_vruntime;
}

static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
{
	s64 delta = (s64)(vruntime - min_vruntime);
	if (delta < 0)
		min_vruntime = vruntime;

	return min_vruntime;
}

static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	return se->vruntime - cfs_rq->min_vruntime;
}

/*
 * Enqueue an entity into the rb-tree:
 */
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
	struct rb_node *parent = NULL;
	struct sched_entity *entry;
	s64 key = entity_key(cfs_rq, se);
	int leftmost = 1;

	/*
	 * Find the right place in the rbtree:
	 */
	while (*link) {
		parent = *link;
		entry = rb_entry(parent, struct sched_entity, run_node);
		/*
		 * We dont care about collisions. Nodes with
		 * the same key stay together.
		 */
		if (key < entity_key(cfs_rq, entry)) {
			link = &parent->rb_left;
		} else {
			link = &parent->rb_right;
			leftmost = 0;
		}
	}

	/*
	 * Maintain a cache of leftmost tree entries (it is frequently
	 * used):
	 */
	if (leftmost)
		cfs_rq->rb_leftmost = &se->run_node;

	rb_link_node(&se->run_node, parent, link);
	rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
}

static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	if (cfs_rq->rb_leftmost == &se->run_node)
		cfs_rq->rb_leftmost = rb_next(&se->run_node);

	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
}

static inline struct rb_node *first_fair(struct cfs_rq *cfs_rq)
{
	return cfs_rq->rb_leftmost;
}

static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
{
	return rb_entry(first_fair(cfs_rq), struct sched_entity, run_node);
}

static inline struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
{
	struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
	struct sched_entity *se = NULL;
	struct rb_node *parent;

	while (*link) {
		parent = *link;
		se = rb_entry(parent, struct sched_entity, run_node);
		link = &parent->rb_right;
	}

	return se;
}

/**************************************************************
 * Scheduling class statistics methods:
 */

#ifdef CONFIG_SCHED_DEBUG
int sched_nr_latency_handler(struct ctl_table *table, int write,
		struct file *filp, void __user *buffer, size_t *lenp,
		loff_t *ppos)
{
	int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);

	if (ret || !write)
		return ret;

	sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency,
					sysctl_sched_min_granularity);

	return 0;
}
#endif

/*
 * The idea is to set a period in which each task runs once.
 *
 * When there are too many tasks (sysctl_sched_nr_latency) we have to stretch
 * this period because otherwise the slices get too small.
 *
 * p = (nr <= nl) ? l : l*nr/nl
 */
static u64 __sched_period(unsigned long nr_running)
{
	u64 period = sysctl_sched_latency;
	unsigned long nr_latency = sched_nr_latency;

	if (unlikely(nr_running > nr_latency)) {
		period = sysctl_sched_min_granularity;
		period *= nr_running;
	}

	return period;
}

/*
 * We calculate the wall-time slice from the period by taking a part
 * proportional to the weight.
 *
 * s = p*w/rw
 */
static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	u64 slice = __sched_period(cfs_rq->nr_running);

	slice *= se->load.weight;
	do_div(slice, cfs_rq->load.weight);

	return slice;
}

/*
 * We calculate the vruntime slice.
 *
 * vs = s/w = p/rw
 */
static u64 __sched_vslice(unsigned long rq_weight, unsigned long nr_running)
{
	u64 vslice = __sched_period(nr_running);

	vslice *= NICE_0_LOAD;
	do_div(vslice, rq_weight);

	return vslice;
}

static u64 sched_vslice(struct cfs_rq *cfs_rq)
{
	return __sched_vslice(cfs_rq->load.weight, cfs_rq->nr_running);
}

static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	return __sched_vslice(cfs_rq->load.weight + se->load.weight,
			cfs_rq->nr_running + 1);
}

/*
 * Update the current task's runtime statistics. Skip current tasks that
 * are not in our scheduling class.
 */
static inline void
__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
	      unsigned long delta_exec)
{
	unsigned long delta_exec_weighted;
	u64 vruntime;

	schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));

	curr->sum_exec_runtime += delta_exec;
	schedstat_add(cfs_rq, exec_clock, delta_exec);
	delta_exec_weighted = delta_exec;
	if (unlikely(curr->load.weight != NICE_0_LOAD)) {
		delta_exec_weighted = calc_delta_fair(delta_exec_weighted,
							&curr->load);
	}
	curr->vruntime += delta_exec_weighted;

	/*
	 * maintain cfs_rq->min_vruntime to be a monotonic increasing
	 * value tracking the leftmost vruntime in the tree.
	 */
	if (first_fair(cfs_rq)) {
		vruntime = min_vruntime(curr->vruntime,
				__pick_next_entity(cfs_rq)->vruntime);
	} else
		vruntime = curr->vruntime;

	cfs_rq->min_vruntime =
		max_vruntime(cfs_rq->min_vruntime, vruntime);
}

static void update_curr(struct cfs_rq *cfs_rq)
{
	struct sched_entity *curr = cfs_rq->curr;
	u64 now = rq_of(cfs_rq)->clock;
	unsigned long delta_exec;

	if (unlikely(!curr))
		return;

	/*
	 * Get the amount of time the current task was running
	 * since the last time we changed load (this cannot
	 * overflow on 32 bits):
	 */
	delta_exec = (unsigned long)(now - curr->exec_start);

	__update_curr(cfs_rq, curr, delta_exec);
	curr->exec_start = now;

	if (entity_is_task(curr)) {
		struct task_struct *curtask = task_of(curr);

		cpuacct_charge(curtask, delta_exec);
	}
}

static inline void
update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	schedstat_set(se->wait_start, rq_of(cfs_rq)->clock);
}

/*
 * Task is being enqueued - update stats:
 */
static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	/*
	 * Are we enqueueing a waiting task? (for current tasks
	 * a dequeue/enqueue event is a NOP)
	 */
	if (se != cfs_rq->curr)
		update_stats_wait_start(cfs_rq, se);
}

static void
update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	schedstat_set(se->wait_max, max(se->wait_max,
			rq_of(cfs_rq)->clock - se->wait_start));
	schedstat_set(se->wait_start, 0);
}

static inline void
update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	/*
	 * Mark the end of the wait period if dequeueing a
	 * waiting task:
	 */
	if (se != cfs_rq->curr)
		update_stats_wait_end(cfs_rq, se);
}

/*
 * We are picking a new current task - update its stats:
 */
static inline void
update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	/*
	 * We are starting a new run period:
	 */
	se->exec_start = rq_of(cfs_rq)->clock;
}

/**************************************************
 * Scheduling class queueing methods:
 */

static void
account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	update_load_add(&cfs_rq->load, se->load.weight);
	cfs_rq->nr_running++;
	se->on_rq = 1;
}

static void
account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	update_load_sub(&cfs_rq->load, se->load.weight);
	cfs_rq->nr_running--;
	se->on_rq = 0;
}

static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHEDSTATS
	if (se->sleep_start) {
		u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;

		if ((s64)delta < 0)
			delta = 0;

		if (unlikely(delta > se->sleep_max))
			se->sleep_max = delta;

		se->sleep_start = 0;
		se->sum_sleep_runtime += delta;
	}
	if (se->block_start) {
		u64 delta = rq_of(cfs_rq)->clock - se->block_start;

		if ((s64)delta < 0)
			delta = 0;

		if (unlikely(delta > se->block_max))
			se->block_max = delta;

		se->block_start = 0;
		se->sum_sleep_runtime += delta;

		/*
		 * Blocking time is in units of nanosecs, so shift by 20 to
		 * get a milliseconds-range estimation of the amount of
		 * time that the task spent sleeping:
		 */
		if (unlikely(prof_on == SLEEP_PROFILING)) {
			struct task_struct *tsk = task_of(se);

			profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
				     delta >> 20);
		}
	}
#endif
}

static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHED_DEBUG
	s64 d = se->vruntime - cfs_rq->min_vruntime;

	if (d < 0)
		d = -d;

	if (d > 3*sysctl_sched_latency)
		schedstat_inc(cfs_rq, nr_spread_over);
#endif
}

static void
place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
{
	u64 vruntime;

	vruntime = cfs_rq->min_vruntime;

	if (sched_feat(TREE_AVG)) {
		struct sched_entity *last = __pick_last_entity(cfs_rq);
		if (last) {
			vruntime += last->vruntime;
			vruntime >>= 1;
		}
	} else if (sched_feat(APPROX_AVG) && cfs_rq->nr_running)
		vruntime += sched_vslice(cfs_rq)/2;

	/*
	 * The 'current' period is already promised to the current tasks,
	 * however the extra weight of the new task will slow them down a
	 * little, place the new task so that it fits in the slot that
	 * stays open at the end.
	 */
	if (initial && sched_feat(START_DEBIT))
		vruntime += sched_vslice_add(cfs_rq, se);

	if (!initial) {
		/* sleeps upto a single latency don't count. */
		if (sched_feat(NEW_FAIR_SLEEPERS) && entity_is_task(se))
			vruntime -= sysctl_sched_latency;

		/* ensure we never gain time by being placed backwards. */
		vruntime = max_vruntime(se->vruntime, vruntime);
	}

	se->vruntime = vruntime;
}

static void
enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
{
	/*
	 * Update run-time statistics of the 'current'.
	 */
	update_curr(cfs_rq);

	if (wakeup) {
		place_entity(cfs_rq, se, 0);
		enqueue_sleeper(cfs_rq, se);
	}

	update_stats_enqueue(cfs_rq, se);
	check_spread(cfs_rq, se);
	if (se != cfs_rq->curr)
		__enqueue_entity(cfs_rq, se);
	account_entity_enqueue(cfs_rq, se);
}

static void
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
{
	/*
	 * Update run-time statistics of the 'current'.
	 */
	update_curr(cfs_rq);

	update_stats_dequeue(cfs_rq, se);
	if (sleep) {
#ifdef CONFIG_SCHEDSTATS
		if (entity_is_task(se)) {
			struct task_struct *tsk = task_of(se);

			if (tsk->state & TASK_INTERRUPTIBLE)
				se->sleep_start = rq_of(cfs_rq)->clock;
			if (tsk->state & TASK_UNINTERRUPTIBLE)
				se->block_start = rq_of(cfs_rq)->clock;
		}
#endif
	}

	if (se != cfs_rq->curr)
		__dequeue_entity(cfs_rq, se);
	account_entity_dequeue(cfs_rq, se);
}

/*
 * Preempt the current task with a newly woken task if needed:
 */
static void
check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
	unsigned long ideal_runtime, delta_exec;

	ideal_runtime = sched_slice(cfs_rq, curr);
	delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
	if (delta_exec > ideal_runtime)
		resched_task(rq_of(cfs_rq)->curr);
}

static void
set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	/* 'current' is not kept within the tree. */
	if (se->on_rq) {
		/*
		 * Any task has to be enqueued before it get to execute on
		 * a CPU. So account for the time it spent waiting on the
		 * runqueue.
		 */
		update_stats_wait_end(cfs_rq, se);
		__dequeue_entity(cfs_rq, se);
	}

	update_stats_curr_start(cfs_rq, se);
	cfs_rq->curr = se;
#ifdef CONFIG_SCHEDSTATS
	/*
	 * Track our maximum slice length, if the CPU's load is at
	 * least twice that of our own weight (i.e. dont track it
	 * when there are only lesser-weight tasks around):
	 */
	if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
		se->slice_max = max(se->slice_max,
			se->sum_exec_runtime - se->prev_sum_exec_runtime);
	}
#endif
	se->prev_sum_exec_runtime = se->sum_exec_runtime;
}

static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
	struct sched_entity *se = NULL;

	if (first_fair(cfs_rq)) {
		se = __pick_next_entity(cfs_rq);
		set_next_entity(cfs_rq, se);
	}

	return se;
}

static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
{
	/*
	 * If still on the runqueue then deactivate_task()
	 * was not called and update_curr() has to be done:
	 */
	if (prev->on_rq)
		update_curr(cfs_rq);

	check_spread(cfs_rq, prev);
	if (prev->on_rq) {
		update_stats_wait_start(cfs_rq, prev);
		/* Put 'current' back into the tree. */
		__enqueue_entity(cfs_rq, prev);
	}
	cfs_rq->curr = NULL;
}

static void
entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
{
	/*
	 * Update run-time statistics of the 'current'.
	 */
	update_curr(cfs_rq);

#ifdef CONFIG_SCHED_HRTICK
	/*
	 * queued ticks are scheduled to match the slice, so don't bother
	 * validating it and just reschedule.
	 */
	if (queued)
		return resched_task(rq_of(cfs_rq)->curr);
	/*
	 * don't let the period tick interfere with the hrtick preemption
	 */
	if (!sched_feat(DOUBLE_TICK) &&
			hrtimer_active(&rq_of(cfs_rq)->hrtick_timer))
		return;
#endif

	if (cfs_rq->nr_running > 1 || !sched_feat(WAKEUP_PREEMPT))
		check_preempt_tick(cfs_rq, curr);
}

/**************************************************
 * CFS operations on tasks:
 */

#ifdef CONFIG_FAIR_GROUP_SCHED

/* Walk up scheduling entities hierarchy */
#define for_each_sched_entity(se) \
		for (; se; se = se->parent)

static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
	return p->se.cfs_rq;
}

/* runqueue on which this entity is (to be) queued */
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
	return se->cfs_rq;
}

/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
	return grp->my_q;
}

/* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on
 * another cpu ('this_cpu')
 */
static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
	return cfs_rq->tg->cfs_rq[this_cpu];
}

/* Iterate thr' all leaf cfs_rq's on a runqueue */
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
	list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)

/* Do the two (enqueued) entities belong to the same group ? */
static inline int
is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
	if (se->cfs_rq == pse->cfs_rq)
		return 1;

	return 0;
}

static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
	return se->parent;
}

#define GROUP_IMBALANCE_PCT	20

#else	/* CONFIG_FAIR_GROUP_SCHED */

#define for_each_sched_entity(se) \
		for (; se; se = NULL)

static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
	return &task_rq(p)->cfs;
}

static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
	struct task_struct *p = task_of(se);
	struct rq *rq = task_rq(p);

	return &rq->cfs;
}

/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
	return NULL;
}

static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
	return &cpu_rq(this_cpu)->cfs;
}

#define for_each_leaf_cfs_rq(rq, cfs_rq) \
		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)

static inline int
is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
	return 1;
}

static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
	return NULL;
}

#endif	/* CONFIG_FAIR_GROUP_SCHED */

#ifdef CONFIG_SCHED_HRTICK
static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
	int requeue = rq->curr == p;
	struct sched_entity *se = &p->se;
	struct cfs_rq *cfs_rq = cfs_rq_of(se);

	WARN_ON(task_rq(p) != rq);

	if (hrtick_enabled(rq) && cfs_rq->nr_running > 1) {
		u64 slice = sched_slice(cfs_rq, se);
		u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime;
		s64 delta = slice - ran;

		if (delta < 0) {
			if (rq->curr == p)
				resched_task(p);
			return;
		}

		/*
		 * Don't schedule slices shorter than 10000ns, that just
		 * doesn't make sense. Rely on vruntime for fairness.
		 */
		if (!requeue)
			delta = max(10000LL, delta);

		hrtick_start(rq, delta, requeue);
	}
}
#else
static inline void
hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
}
#endif

/*
 * The enqueue_task method is called before nr_running is
 * increased. Here we update the fair scheduling stats and
 * then put the task into the rbtree:
 */
static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se = &p->se,
			    *topse = NULL;	/* Highest schedulable entity */
	int incload = 1;

	for_each_sched_entity(se) {
		topse = se;
		if (se->on_rq) {
			incload = 0;
			break;
		}
		cfs_rq = cfs_rq_of(se);
		enqueue_entity(cfs_rq, se, wakeup);
		wakeup = 1;
	}
	/* Increment cpu load if we just enqueued the first task of a group on
	 * 'rq->cpu'. 'topse' represents the group to which task 'p' belongs
	 * at the highest grouping level.
	 */
	if (incload)
		inc_cpu_load(rq, topse->load.weight);

	hrtick_start_fair(rq, rq->curr);
}

/*
 * The dequeue_task method is called before nr_running is
 * decreased. We remove the task from the rbtree and
 * update the fair scheduling stats:
 */
static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se = &p->se,
			    *topse = NULL; 	/* Highest schedulable entity */
	int decload = 1;

	for_each_sched_entity(se) {
		topse = se;
		cfs_rq = cfs_rq_of(se);
		dequeue_entity(cfs_rq, se, sleep);
		/* Don't dequeue parent if it has other entities besides us */
		if (cfs_rq->load.weight) {
			if (parent_entity(se))
				decload = 0;
			break;
		}
		sleep = 1;
	}
	/* Decrement cpu load if we just dequeued the last task of a group on
	 * 'rq->cpu'. 'topse' represents the group to which task 'p' belongs
	 * at the highest grouping level.
	 */
	if (decload)
		dec_cpu_load(rq, topse->load.weight);

	hrtick_start_fair(rq, rq->curr);
}

/*
 * sched_yield() support is very simple - we dequeue and enqueue.
 *
 * If compat_yield is turned on then we requeue to the end of the tree.
 */
static void yield_task_fair(struct rq *rq)
{
	struct task_struct *curr = rq->curr;
	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
	struct sched_entity *rightmost, *se = &curr->se;

	/*
	 * Are we the only task in the tree?
	 */
	if (unlikely(cfs_rq->nr_running == 1))
		return;

	if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
		__update_rq_clock(rq);
		/*
		 * Update run-time statistics of the 'current'.
		 */
		update_curr(cfs_rq);

		return;
	}
	/*
	 * Find the rightmost entry in the rbtree:
	 */
	rightmost = __pick_last_entity(cfs_rq);
	/*
	 * Already in the rightmost position?
	 */
	if (unlikely(rightmost->vruntime < se->vruntime))
		return;

	/*
	 * Minimally necessary key value to be last in the tree:
	 * Upon rescheduling, sched_class::put_prev_task() will place
	 * 'current' within the tree based on its new key value.
	 */
	se->vruntime = rightmost->vruntime + 1;
}

/*
 * wake_idle() will wake a task on an idle cpu if task->cpu is
 * not idle and an idle cpu is available.  The span of cpus to
 * search starts with cpus closest then further out as needed,
 * so we always favor a closer, idle cpu.
 *
 * Returns the CPU we should wake onto.
 */
#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
static int wake_idle(int cpu, struct task_struct *p)
{
	cpumask_t tmp;
	struct sched_domain *sd;
	int i;

	/*
	 * If it is idle, then it is the best cpu to run this task.
	 *
	 * This cpu is also the best, if it has more than one task already.
	 * Siblings must be also busy(in most cases) as they didn't already
	 * pickup the extra load from this cpu and hence we need not check
	 * sibling runqueue info. This will avoid the checks and cache miss
	 * penalities associated with that.
	 */
	if (idle_cpu(cpu) || cpu_rq(cpu)->nr_running > 1)
		return cpu;

	for_each_domain(cpu, sd) {
		if (sd->flags & SD_WAKE_IDLE) {
			cpus_and(tmp, sd->span, p->cpus_allowed);
			for_each_cpu_mask(i, tmp) {
				if (idle_cpu(i)) {
					if (i != task_cpu(p)) {
						schedstat_inc(p,
						       se.nr_wakeups_idle);
					}
					return i;
				}
			}
		} else {
			break;
		}
	}
	return cpu;
}
#else
static inline int wake_idle(int cpu, struct task_struct *p)
{
	return cpu;
}
#endif

#ifdef CONFIG_SMP
static int select_task_rq_fair(struct task_struct *p, int sync)
{
	int cpu, this_cpu;
	struct rq *rq;
	struct sched_domain *sd, *this_sd = NULL;
	int new_cpu;

	cpu      = task_cpu(p);
	rq       = task_rq(p);
	this_cpu = smp_processor_id();
	new_cpu  = cpu;

	if (cpu == this_cpu)
		goto out_set_cpu;

	for_each_domain(this_cpu, sd) {
		if (cpu_isset(cpu, sd->span)) {
			this_sd = sd;
			break;
		}
	}

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

	/*
	 * Check for affine wakeup and passive balancing possibilities.
	 */