kernel/sched.c

/*
 *  kernel/sched.c
 *
 *  Kernel scheduler and related syscalls
 *
 *  Copyright (C) 1991-2002  Linus Torvalds
 *
 *  1996-12-23  Modified by Dave Grothe to fix bugs in semaphores and
 *		make semaphores SMP safe
 *  1998-11-19	Implemented schedule_timeout() and related stuff
 *		by Andrea Arcangeli
 *  2002-01-04	New ultra-scalable O(1) scheduler by Ingo Molnar:
 *		hybrid priority-list and round-robin design with
 *		an array-switch method of distributing timeslices
 *		and per-CPU runqueues.  Cleanups and useful suggestions
 *		by Davide Libenzi, preemptible kernel bits by Robert Love.
 *  2003-09-03	Interactivity tuning by Con Kolivas.
 *  2004-04-02	Scheduler domains code by Nick Piggin
 */

#include <linux/mm.h>
#include <linux/module.h>
#include <linux/nmi.h>
#include <linux/init.h>
#include <asm/uaccess.h>
#include <linux/highmem.h>
#include <linux/smp_lock.h>
#include <asm/mmu_context.h>
#include <linux/interrupt.h>
#include <linux/capability.h>
#include <linux/completion.h>
#include <linux/kernel_stat.h>
#include <linux/debug_locks.h>
#include <linux/security.h>
#include <linux/notifier.h>
#include <linux/profile.h>
#include <linux/freezer.h>
#include <linux/vmalloc.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
#include <linux/smp.h>
#include <linux/threads.h>
#include <linux/timer.h>
#include <linux/rcupdate.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/percpu.h>
#include <linux/kthread.h>
#include <linux/seq_file.h>
#include <linux/syscalls.h>
#include <linux/times.h>
#include <linux/tsacct_kern.h>
#include <linux/kprobes.h>
#include <linux/delayacct.h>
#include <linux/reciprocal_div.h>

#include <asm/tlb.h>
#include <asm/unistd.h>

/*
 * Scheduler clock - returns current time in nanosec units.
 * This is default implementation.
 * Architectures and sub-architectures can override this.
 */
unsigned long long __attribute__((weak)) sched_clock(void)
{
	return (unsigned long long)jiffies * (1000000000 / HZ);
}

/*
 * Convert user-nice values [ -20 ... 0 ... 19 ]
 * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
 * and back.
 */
#define NICE_TO_PRIO(nice)	(MAX_RT_PRIO + (nice) + 20)
#define PRIO_TO_NICE(prio)	((prio) - MAX_RT_PRIO - 20)
#define TASK_NICE(p)		PRIO_TO_NICE((p)->static_prio)

/*
 * 'User priority' is the nice value converted to something we
 * can work with better when scaling various scheduler parameters,
 * it's a [ 0 ... 39 ] range.
 */
#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))

/*
 * Some helpers for converting nanosecond timing to jiffy resolution
 */
#define NS_TO_JIFFIES(TIME)	((TIME) / (1000000000 / HZ))
#define JIFFIES_TO_NS(TIME)	((TIME) * (1000000000 / HZ))

/*
 * These are the 'tuning knobs' of the scheduler:
 *
 * Minimum timeslice is 5 msecs (or 1 jiffy, whichever is larger),
 * default timeslice is 100 msecs, maximum timeslice is 800 msecs.
 * Timeslices get refilled after they expire.
 */
#define MIN_TIMESLICE		max(5 * HZ / 1000, 1)
#define DEF_TIMESLICE		(100 * HZ / 1000)
#define ON_RUNQUEUE_WEIGHT	 30
#define CHILD_PENALTY		 95
#define PARENT_PENALTY		100
#define EXIT_WEIGHT		  3
#define PRIO_BONUS_RATIO	 25
#define MAX_BONUS		(MAX_USER_PRIO * PRIO_BONUS_RATIO / 100)
#define INTERACTIVE_DELTA	  2
#define MAX_SLEEP_AVG		(DEF_TIMESLICE * MAX_BONUS)
#define STARVATION_LIMIT	(MAX_SLEEP_AVG)
#define NS_MAX_SLEEP_AVG	(JIFFIES_TO_NS(MAX_SLEEP_AVG))

/*
 * If a task is 'interactive' then we reinsert it in the active
 * array after it has expired its current timeslice. (it will not
 * continue to run immediately, it will still roundrobin with
 * other interactive tasks.)
 *
 * This part scales the interactivity limit depending on niceness.
 *
 * We scale it linearly, offset by the INTERACTIVE_DELTA delta.
 * Here are a few examples of different nice levels:
 *
 *  TASK_INTERACTIVE(-20): [1,1,1,1,1,1,1,1,1,0,0]
 *  TASK_INTERACTIVE(-10): [1,1,1,1,1,1,1,0,0,0,0]
 *  TASK_INTERACTIVE(  0): [1,1,1,1,0,0,0,0,0,0,0]
 *  TASK_INTERACTIVE( 10): [1,1,0,0,0,0,0,0,0,0,0]
 *  TASK_INTERACTIVE( 19): [0,0,0,0,0,0,0,0,0,0,0]
 *
 * (the X axis represents the possible -5 ... 0 ... +5 dynamic
 *  priority range a task can explore, a value of '1' means the
 *  task is rated interactive.)
 *
 * Ie. nice +19 tasks can never get 'interactive' enough to be
 * reinserted into the active array. And only heavily CPU-hog nice -20
 * tasks will be expired. Default nice 0 tasks are somewhere between,
 * it takes some effort for them to get interactive, but it's not
 * too hard.
 */

#define CURRENT_BONUS(p) \
	(NS_TO_JIFFIES((p)->sleep_avg) * MAX_BONUS / \
		MAX_SLEEP_AVG)

#define GRANULARITY	(10 * HZ / 1000 ? : 1)

#ifdef CONFIG_SMP
#define TIMESLICE_GRANULARITY(p)	(GRANULARITY * \
		(1 << (((MAX_BONUS - CURRENT_BONUS(p)) ? : 1) - 1)) * \
			num_online_cpus())
#else
#define TIMESLICE_GRANULARITY(p)	(GRANULARITY * \
		(1 << (((MAX_BONUS - CURRENT_BONUS(p)) ? : 1) - 1)))
#endif

#define SCALE(v1,v1_max,v2_max) \
	(v1) * (v2_max) / (v1_max)

#define DELTA(p) \
	(SCALE(TASK_NICE(p) + 20, 40, MAX_BONUS) - 20 * MAX_BONUS / 40 + \
		INTERACTIVE_DELTA)

#define TASK_INTERACTIVE(p) \
	((p)->prio <= (p)->static_prio - DELTA(p))

#define INTERACTIVE_SLEEP(p) \
	(JIFFIES_TO_NS(MAX_SLEEP_AVG * \
		(MAX_BONUS / 2 + DELTA((p)) + 1) / MAX_BONUS - 1))

#define TASK_PREEMPTS_CURR(p, rq) \
	((p)->prio < (rq)->curr->prio)

#define SCALE_PRIO(x, prio) \
	max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO / 2), MIN_TIMESLICE)

static unsigned int static_prio_timeslice(int static_prio)
{
	if (static_prio < NICE_TO_PRIO(0))
		return SCALE_PRIO(DEF_TIMESLICE * 4, static_prio);
	else
		return SCALE_PRIO(DEF_TIMESLICE, static_prio);
}

#ifdef CONFIG_SMP
/*
 * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
 * Since cpu_power is a 'constant', we can use a reciprocal divide.
 */
static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load)
{
	return reciprocal_divide(load, sg->reciprocal_cpu_power);
}

/*
 * Each time a sched group cpu_power is changed,
 * we must compute its reciprocal value
 */
static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val)
{
	sg->__cpu_power += val;
	sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power);
}
#endif

/*
 * task_timeslice() scales user-nice values [ -20 ... 0 ... 19 ]
 * to time slice values: [800ms ... 100ms ... 5ms]
 *
 * The higher a thread's priority, the bigger timeslices
 * it gets during one round of execution. But even the lowest
 * priority thread gets MIN_TIMESLICE worth of execution time.
 */

static inline unsigned int task_timeslice(struct task_struct *p)
{
	return static_prio_timeslice(p->static_prio);
}

/*
 * These are the runqueue data structures:
 */

struct prio_array {
	unsigned int nr_active;
	DECLARE_BITMAP(bitmap, MAX_PRIO+1); /* include 1 bit for delimiter */
	struct list_head queue[MAX_PRIO];
};

/*
 * This is the main, per-CPU runqueue data structure.
 *
 * Locking rule: those places that want to lock multiple runqueues
 * (such as the load balancing or the thread migration code), lock
 * acquire operations must be ordered by ascending &runqueue.
 */
struct rq {
	spinlock_t lock;

	/*
	 * nr_running and cpu_load should be in the same cacheline because
	 * remote CPUs use both these fields when doing load calculation.
	 */
	unsigned long nr_running;
	unsigned long raw_weighted_load;
#ifdef CONFIG_SMP
	unsigned long cpu_load[3];
	unsigned char idle_at_tick;
#ifdef CONFIG_NO_HZ
	unsigned char in_nohz_recently;
#endif
#endif
	unsigned long long nr_switches;

	/*
	 * This is part of a global counter where only the total sum
	 * over all CPUs matters. A task can increase this counter on
	 * one CPU and if it got migrated afterwards it may decrease
	 * it on another CPU. Always updated under the runqueue lock:
	 */
	unsigned long nr_uninterruptible;

	unsigned long expired_timestamp;
	/* Cached timestamp set by update_cpu_clock() */
	unsigned long long most_recent_timestamp;
	struct task_struct *curr, *idle;
	unsigned long next_balance;
	struct mm_struct *prev_mm;
	struct prio_array *active, *expired, arrays[2];
	int best_expired_prio;
	atomic_t nr_iowait;

#ifdef CONFIG_SMP
	struct sched_domain *sd;

	/* For active balancing */
	int active_balance;
	int push_cpu;
	int cpu;		/* cpu of this runqueue */

	struct task_struct *migration_thread;
	struct list_head migration_queue;
#endif

#ifdef CONFIG_SCHEDSTATS
	/* latency stats */
	struct sched_info rq_sched_info;

	/* sys_sched_yield() stats */
	unsigned long yld_exp_empty;
	unsigned long yld_act_empty;
	unsigned long yld_both_empty;
	unsigned long yld_cnt;

	/* schedule() stats */
	unsigned long sched_switch;
	unsigned long sched_cnt;
	unsigned long sched_goidle;

	/* try_to_wake_up() stats */
	unsigned long ttwu_cnt;
	unsigned long ttwu_local;
#endif
	struct lock_class_key rq_lock_key;
};

static DEFINE_PER_CPU(struct rq, runqueues) ____cacheline_aligned_in_smp;
static DEFINE_MUTEX(sched_hotcpu_mutex);

static inline int cpu_of(struct rq *rq)
{
#ifdef CONFIG_SMP
	return rq->cpu;
#else
	return 0;
#endif
}

/*
 * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
 * See detach_destroy_domains: synchronize_sched for details.
 *
 * The domain tree of any CPU may only be accessed from within
 * preempt-disabled sections.
 */
#define for_each_domain(cpu, __sd) \
	for (__sd = rcu_dereference(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent)

#define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
#define this_rq()		(&__get_cpu_var(runqueues))
#define task_rq(p)		cpu_rq(task_cpu(p))
#define cpu_curr(cpu)		(cpu_rq(cpu)->curr)

#ifndef prepare_arch_switch
# define prepare_arch_switch(next)	do { } while (0)
#endif
#ifndef finish_arch_switch
# define finish_arch_switch(prev)	do { } while (0)
#endif

#ifndef __ARCH_WANT_UNLOCKED_CTXSW
static inline int task_running(struct rq *rq, struct task_struct *p)
{
	return rq->curr == p;
}

static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
{
}

static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_DEBUG_SPINLOCK
	/* this is a valid case when another task releases the spinlock */
	rq->lock.owner = current;
#endif
	/*
	 * If we are tracking spinlock dependencies then we have to
	 * fix up the runqueue lock - which gets 'carried over' from
	 * prev into current:
	 */
	spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);

	spin_unlock_irq(&rq->lock);
}

#else /* __ARCH_WANT_UNLOCKED_CTXSW */
static inline int task_running(struct rq *rq, struct task_struct *p)
{
#ifdef CONFIG_SMP
	return p->oncpu;
#else
	return rq->curr == p;
#endif
}

static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
{
#ifdef CONFIG_SMP
	/*
	 * We can optimise this out completely for !SMP, because the
	 * SMP rebalancing from interrupt is the only thing that cares
	 * here.
	 */
	next->oncpu = 1;
#endif
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
	spin_unlock_irq(&rq->lock);
#else
	spin_unlock(&rq->lock);
#endif
}

static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_SMP
	/*
	 * After ->oncpu is cleared, the task can be moved to a different CPU.
	 * We must ensure this doesn't happen until the switch is completely
	 * finished.
	 */
	smp_wmb();
	prev->oncpu = 0;
#endif
#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
	local_irq_enable();
#endif
}
#endif /* __ARCH_WANT_UNLOCKED_CTXSW */

/*
 * __task_rq_lock - lock the runqueue a given task resides on.
 * Must be called interrupts disabled.
 */
static inline struct rq *__task_rq_lock(struct task_struct *p)
	__acquires(rq->lock)
{
	struct rq *rq;

repeat_lock_task:
	rq = task_rq(p);
	spin_lock(&rq->lock);
	if (unlikely(rq != task_rq(p))) {
		spin_unlock(&rq->lock);
		goto repeat_lock_task;
	}
	return rq;
}

/*
 * task_rq_lock - lock the runqueue a given task resides on and disable
 * interrupts.  Note the ordering: we can safely lookup the task_rq without
 * explicitly disabling preemption.
 */
static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
	__acquires(rq->lock)
{
	struct rq *rq;

repeat_lock_task:
	local_irq_save(*flags);
	rq = task_rq(p);
	spin_lock(&rq->lock);
	if (unlikely(rq != task_rq(p))) {
		spin_unlock_irqrestore(&rq->lock, *flags);
		goto repeat_lock_task;
	}
	return rq;
}

static inline void __task_rq_unlock(struct rq *rq)
	__releases(rq->lock)
{
	spin_unlock(&rq->lock);
}

static inline void task_rq_unlock(struct rq *rq, unsigned long *flags)
	__releases(rq->lock)
{
	spin_unlock_irqrestore(&rq->lock, *flags);
}

#ifdef CONFIG_SCHEDSTATS
/*
 * bump this up when changing the output format or the meaning of an existing
 * format, so that tools can adapt (or abort)
 */
#define SCHEDSTAT_VERSION 14

static int show_schedstat(struct seq_file *seq, void *v)
{
	int cpu;

	seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
	seq_printf(seq, "timestamp %lu\n", jiffies);
	for_each_online_cpu(cpu) {
		struct rq *rq = cpu_rq(cpu);
#ifdef CONFIG_SMP
		struct sched_domain *sd;
		int dcnt = 0;
#endif

		/* runqueue-specific stats */
		seq_printf(seq,
		    "cpu%d %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu",
		    cpu, rq->yld_both_empty,
		    rq->yld_act_empty, rq->yld_exp_empty, rq->yld_cnt,
		    rq->sched_switch, rq->sched_cnt, rq->sched_goidle,
		    rq->ttwu_cnt, rq->ttwu_local,
		    rq->rq_sched_info.cpu_time,
		    rq->rq_sched_info.run_delay, rq->rq_sched_info.pcnt);

		seq_printf(seq, "\n");

#ifdef CONFIG_SMP
		/* domain-specific stats */
		preempt_disable();
		for_each_domain(cpu, sd) {
			enum idle_type itype;
			char mask_str[NR_CPUS];

			cpumask_scnprintf(mask_str, NR_CPUS, sd->span);
			seq_printf(seq, "domain%d %s", dcnt++, mask_str);
			for (itype = SCHED_IDLE; itype < MAX_IDLE_TYPES;
					itype++) {
				seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu "
						"%lu",
				    sd->lb_cnt[itype],
				    sd->lb_balanced[itype],
				    sd->lb_failed[itype],
				    sd->lb_imbalance[itype],
				    sd->lb_gained[itype],
				    sd->lb_hot_gained[itype],
				    sd->lb_nobusyq[itype],
				    sd->lb_nobusyg[itype]);
			}
			seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu %lu"
			    " %lu %lu %lu\n",
			    sd->alb_cnt, sd->alb_failed, sd->alb_pushed,
			    sd->sbe_cnt, sd->sbe_balanced, sd->sbe_pushed,
			    sd->sbf_cnt, sd->sbf_balanced, sd->sbf_pushed,
			    sd->ttwu_wake_remote, sd->ttwu_move_affine,
			    sd->ttwu_move_balance);
		}
		preempt_enable();
#endif
	}
	return 0;
}

static int schedstat_open(struct inode *inode, struct file *file)
{
	unsigned int size = PAGE_SIZE * (1 + num_online_cpus() / 32);
	char *buf = kmalloc(size, GFP_KERNEL);
	struct seq_file *m;
	int res;

	if (!buf)
		return -ENOMEM;
	res = single_open(file, show_schedstat, NULL);
	if (!res) {
		m = file->private_data;
		m->buf = buf;
		m->size = size;
	} else
		kfree(buf);
	return res;
}

const struct file_operations proc_schedstat_operations = {
	.open    = schedstat_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = single_release,
};

/*
 * Expects runqueue lock to be held for atomicity of update
 */
static inline void
rq_sched_info_arrive(struct rq *rq, unsigned long delta_jiffies)
{
	if (rq) {
		rq->rq_sched_info.run_delay += delta_jiffies;
		rq->rq_sched_info.pcnt++;
	}
}

/*
 * Expects runqueue lock to be held for atomicity of update
 */
static inline void
rq_sched_info_depart(struct rq *rq, unsigned long delta_jiffies)
{
	if (rq)
		rq->rq_sched_info.cpu_time += delta_jiffies;
}
# define schedstat_inc(rq, field)	do { (rq)->field++; } while (0)
# define schedstat_add(rq, field, amt)	do { (rq)->field += (amt); } while (0)
#else /* !CONFIG_SCHEDSTATS */
static inline void
rq_sched_info_arrive(struct rq *rq, unsigned long delta_jiffies)
{}
static inline void
rq_sched_info_depart(struct rq *rq, unsigned long delta_jiffies)
{}
# define schedstat_inc(rq, field)	do { } while (0)
# define schedstat_add(rq, field, amt)	do { } while (0)
#endif

/*
 * this_rq_lock - lock this runqueue and disable interrupts.
 */
static inline struct rq *this_rq_lock(void)
	__acquires(rq->lock)
{
	struct rq *rq;

	local_irq_disable();
	rq = this_rq();
	spin_lock(&rq->lock);

	return rq;
}

#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
/*
 * Called when a process is dequeued from the active array and given
 * the cpu.  We should note that with the exception of interactive
 * tasks, the expired queue will become the active queue after the active
 * queue is empty, without explicitly dequeuing and requeuing tasks in the
 * expired queue.  (Interactive tasks may be requeued directly to the
 * active queue, thus delaying tasks in the expired queue from running;
 * see scheduler_tick()).
 *
 * This function is only called from sched_info_arrive(), rather than
 * dequeue_task(). Even though a task may be queued and dequeued multiple
 * times as it is shuffled about, we're really interested in knowing how
 * long it was from the *first* time it was queued to the time that it
 * finally hit a cpu.
 */
static inline void sched_info_dequeued(struct task_struct *t)
{
	t->sched_info.last_queued = 0;
}

/*
 * Called when a task finally hits the cpu.  We can now calculate how
 * long it was waiting to run.  We also note when it began so that we
 * can keep stats on how long its timeslice is.
 */
static void sched_info_arrive(struct task_struct *t)
{
	unsigned long now = jiffies, delta_jiffies = 0;

	if (t->sched_info.last_queued)
		delta_jiffies = now - t->sched_info.last_queued;
	sched_info_dequeued(t);
	t->sched_info.run_delay += delta_jiffies;
	t->sched_info.last_arrival = now;
	t->sched_info.pcnt++;

	rq_sched_info_arrive(task_rq(t), delta_jiffies);
}

/*
 * Called when a process is queued into either the active or expired
 * array.  The time is noted and later used to determine how long we
 * had to wait for us to reach the cpu.  Since the expired queue will
 * become the active queue after active queue is empty, without dequeuing
 * and requeuing any tasks, we are interested in queuing to either. It
 * is unusual but not impossible for tasks to be dequeued and immediately
 * requeued in the same or another array: this can happen in sched_yield(),
 * set_user_nice(), and even load_balance() as it moves tasks from runqueue
 * to runqueue.
 *
 * This function is only called from enqueue_task(), but also only updates
 * the timestamp if it is already not set.  It's assumed that
 * sched_info_dequeued() will clear that stamp when appropriate.
 */
static inline void sched_info_queued(struct task_struct *t)
{
	if (unlikely(sched_info_on()))
		if (!t->sched_info.last_queued)
			t->sched_info.last_queued = jiffies;
}

/*
 * Called when a process ceases being the active-running process, either
 * voluntarily or involuntarily.  Now we can calculate how long we ran.
 */
static inline void sched_info_depart(struct task_struct *t)
{
	unsigned long delta_jiffies = jiffies - t->sched_info.last_arrival;

	t->sched_info.cpu_time += delta_jiffies;
	rq_sched_info_depart(task_rq(t), delta_jiffies);
}

/*
 * Called when tasks are switched involuntarily due, typically, to expiring
 * their time slice.  (This may also be called when switching to or from
 * the idle task.)  We are only called when prev != next.
 */
static inline void
__sched_info_switch(struct task_struct *prev, struct task_struct *next)
{
	struct rq *rq = task_rq(prev);

	/*
	 * prev now departs the cpu.  It's not interesting to record
	 * stats about how efficient we were at scheduling the idle
	 * process, however.
	 */
	if (prev != rq->idle)
		sched_info_depart(prev);

	if (next != rq->idle)
		sched_info_arrive(next);
}
static inline void
sched_info_switch(struct task_struct *prev, struct task_struct *next)
{
	if (unlikely(sched_info_on()))
		__sched_info_switch(prev, next);
}
#else
#define sched_info_queued(t)		do { } while (0)
#define sched_info_switch(t, next)	do { } while (0)
#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */

/*
 * Adding/removing a task to/from a priority array:
 */
static void dequeue_task(struct task_struct *p, struct prio_array *array)
{
	array->nr_active--;
	list_del(&p->run_list);
	if (list_empty(array->queue + p->prio))
		__clear_bit(p->prio, array->bitmap);
}

static void enqueue_task(struct task_struct *p, struct prio_array *array)
{
	sched_info_queued(p);
	list_add_tail(&p->run_list, array->queue + p->prio);
	__set_bit(p->prio, array->bitmap);
	array->nr_active++;
	p->array = array;
}

/*
 * Put task to the end of the run list without the overhead of dequeue
 * followed by enqueue.
 */
static void requeue_task(struct task_struct *p, struct prio_array *array)
{
	list_move_tail(&p->run_list, array->queue + p->prio);
}

static inline void
enqueue_task_head(struct task_struct *p, struct prio_array *array)
{
	list_add(&p->run_list, array->queue + p->prio);
	__set_bit(p->prio, array->bitmap);
	array->nr_active++;
	p->array = array;
}

/*
 * __normal_prio - return the priority that is based on the static
 * priority but is modified by bonuses/penalties.
 *
 * We scale the actual sleep average [0 .... MAX_SLEEP_AVG]
 * into the -5 ... 0 ... +5 bonus/penalty range.
 *
 * We use 25% of the full 0...39 priority range so that:
 *
 * 1) nice +19 interactive tasks do not preempt nice 0 CPU hogs.
 * 2) nice -20 CPU hogs do not get preempted by nice 0 tasks.
 *
 * Both properties are important to certain workloads.
 */

static inline int __normal_prio(struct task_struct *p)
{
	int bonus, prio;

	bonus = CURRENT_BONUS(p) - MAX_BONUS / 2;

	prio = p->static_prio - bonus;
	if (prio < MAX_RT_PRIO)
		prio = MAX_RT_PRIO;
	if (prio > MAX_PRIO-1)
		prio = MAX_PRIO-1;
	return prio;
}

/*
 * To aid in avoiding the subversion of "niceness" due to uneven distribution
 * of tasks with abnormal "nice" values across CPUs the contribution that
 * each task makes to its run queue's load is weighted according to its
 * scheduling class and "nice" value.  For SCHED_NORMAL tasks this is just a
 * scaled version of the new time slice allocation that they receive on time
 * slice expiry etc.
 */

/*
 * Assume: static_prio_timeslice(NICE_TO_PRIO(0)) == DEF_TIMESLICE
 * If static_prio_timeslice() is ever changed to break this assumption then
 * this code will need modification
 */
#define TIME_SLICE_NICE_ZERO DEF_TIMESLICE
#define LOAD_WEIGHT(lp) \
	(((lp) * SCHED_LOAD_SCALE) / TIME_SLICE_NICE_ZERO)
#define PRIO_TO_LOAD_WEIGHT(prio) \
	LOAD_WEIGHT(static_prio_timeslice(prio))
#define RTPRIO_TO_LOAD_WEIGHT(rp) \
	(PRIO_TO_LOAD_WEIGHT(MAX_RT_PRIO) + LOAD_WEIGHT(rp))

static void set_load_weight(struct task_struct *p)
{
	if (has_rt_policy(p)) {
#ifdef CONFIG_SMP
		if (p == task_rq(p)->migration_thread)
			/*
			 * The migration thread does the actual balancing.
			 * Giving its load any weight will skew balancing
			 * adversely.
			 */
			p->load_weight = 0;
		else
#endif
			p->load_weight = RTPRIO_TO_LOAD_WEIGHT(p->rt_priority);
	} else
		p->load_weight = PRIO_TO_LOAD_WEIGHT(p->static_prio);
}

static inline void
inc_raw_weighted_load(struct rq *rq, const struct task_struct *p)
{
	rq->raw_weighted_load += p->load_weight;
}

static inline void
dec_raw_weighted_load(struct rq *rq, const struct task_struct *p)
{
	rq->raw_weighted_load -= p->load_weight;
}

static inline void inc_nr_running(struct task_struct *p, struct rq *rq)
{
	rq->nr_running++;
	inc_raw_weighted_load(rq, p);
}

static inline void dec_nr_running(struct task_struct *p, struct rq *rq)
{
	rq->nr_running--;
	dec_raw_weighted_load(rq, p);
}

/*
 * Calculate the expected normal priority: i.e. priority
 * without taking RT-inheritance into account. Might be
 * boosted by interactivity modifiers. Changes upon fork,
 * setprio syscalls, and whenever the interactivity
 * estimator recalculates.
 */
static inline int normal_prio(struct task_struct *p)
{
	int prio;

	if (has_rt_policy(p))
		prio = MAX_RT_PRIO-1 - p->rt_priority;
	else
		prio = __normal_prio(p);
	return prio;
}

/*
 * Calculate the current priority, i.e. the priority
 * taken into account by the scheduler. This value might
 * be boosted by RT tasks, or might be boosted by
 * interactivity modifiers. Will be RT if the task got
 * RT-boosted. If not then it returns p->normal_prio.
 */
static int effective_prio(struct task_struct *p)
{
	p->normal_prio = normal_prio(p);
	/*
	 * If we are RT tasks or we were boosted to RT priority,
	 * keep the priority unchanged. Otherwise, update priority
	 * to the normal priority:
	 */
	if (!rt_prio(p->prio))
		return p->normal_prio;
	return p->prio;
}

/*
 * __activate_task - move a task to the runqueue.
 */
static void __activate_task(struct task_struct *p, struct rq *rq)
{
	struct prio_array *target = rq->active;

	if (batch_task(p))
		target = rq->expired;
	enqueue_task(p, target);
	inc_nr_running(p, rq);
}

/*
 * __activate_idle_task - move idle task to the _front_ of runqueue.
 */
static inline void __activate_idle_task(struct task_struct *p, struct rq *rq)
{
	enqueue_task_head(p, rq->active);
	inc_nr_running(p, rq);
}

/*
 * Recalculate p->normal_prio and p->prio after having slept,
 * updating the sleep-average too:
 */
static int recalc_task_prio(struct task_struct *p, unsigned long long now)
{
	/* Caller must always ensure 'now >= p->timestamp' */
	unsigned long sleep_time = now - p->timestamp;

	if (batch_task(p))
		sleep_time = 0;

	if (likely(sleep_time > 0)) {
		/*
		 * This ceiling is set to the lowest priority that would allow
		 * a task to be reinserted into the active array on timeslice
		 * completion.
		 */
		unsigned long ceiling = INTERACTIVE_SLEEP(p);

		if (p->mm && sleep_time > ceiling && p->sleep_avg < ceiling) {
			/*
			 * Prevents user tasks from achieving best priority
			 * with one single large enough sleep.
			 */
			p->sleep_avg = ceiling;
			/*
			 * Using INTERACTIVE_SLEEP() as a ceiling places a
			 * nice(0) task 1ms sleep away from promotion, and
			 * gives it 700ms to round-robin with no chance of
			 * being demoted.  This is more than generous, so
			 * mark this sleep as non-interactive to prevent the
			 * on-runqueue bonus logic from intervening should
			 * this task not receive cpu immediately.
			 */
			p->sleep_type = SLEEP_NONINTERACTIVE;
		} else {
			/*
			 * Tasks waking from uninterruptible sleep are
			 * limited in their sleep_avg rise as they
			 * are likely to be waiting on I/O
			 */
			if (p->sleep_type == SLEEP_NONINTERACTIVE && p->mm) {
				if (p->sleep_avg >= ceiling)
					sleep_time = 0;
				else if (p->sleep_avg + sleep_time >=
					 ceiling) {
						p->sleep_avg = ceiling;
						sleep_time = 0;
				}
			}

			/*
			 * This code gives a bonus to interactive tasks.
			 *
			 * The boost works by updating the 'average sleep time'
			 * value here, based on ->timestamp. The more time a
			 * task spends sleeping, the higher the average gets -
			 * and the higher the priority boost gets as well.
			 */
			p->sleep_avg += sleep_time;

		}
		if (p->sleep_avg > NS_MAX_SLEEP_AVG)
			p->sleep_avg = NS_MAX_SLEEP_AVG;
	}

	return effective_prio(p);
}

/*
 * activate_task - move a task to the runqueue and do priority recalculation
 *
 * Update all the scheduling statistics stuff. (sleep average
 * calculation, priority modifiers, etc.)
 */
static void activate_task(struct task_struct *p, struct rq *rq, int local)
{
	unsigned long long now;

	if (rt_task(p))
		goto out;

	now = sched_clock();
#ifdef CONFIG_SMP
	if (!local) {
		/* Compensate for drifting sched_clock */
		struct rq *this_rq = this_rq();
		now = (now - this_rq->most_recent_timestamp)
			+ rq->most_recent_timestamp;
	}
#endif

	/*
	 * Sleep 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)) {
		if (p->state == TASK_UNINTERRUPTIBLE)
			profile_hits(SLEEP_PROFILING, (void *)get_wchan(p),
				     (now - p->timestamp) >> 20);
	}

	p->prio = recalc_task_prio(p, now);

	/*
	 * This checks to make sure it's not an uninterruptible task
	 * that is now waking up.
	 */
	if (p->sleep_type == SLEEP_NORMAL) {
		/*
		 * Tasks which were woken up by interrupts (ie. hw events)
		 * are most likely of interactive nature. So we give them
		 * the credit of extending their sleep time to the period
		 * of time they spend on the runqueue, waiting for execution
		 * on a CPU, first time around:
		 */
		if (in_interrupt())
			p->sleep_type = SLEEP_INTERRUPTED;
		else {
			/*
			 * Normal first-time wakeups get a credit too for
			 * on-runqueue time, but it will be weighted down:
			 */
			p->sleep_type = SLEEP_INTERACTIVE;
		}
	}
	p->timestamp = now;
out:
	__activate_task(p, rq);
}

/*
 * deactivate_task - remove a task from the runqueue.
 */
static void deactivate_task(struct task_struct *p, struct rq *rq)
{
	dec_nr_running(p, rq);
	dequeue_task(p, p->array);
	p->array = NULL;
}

/*
 * resched_task - mark a task 'to be rescheduled now'.
 *
 * On UP this means the setting of the need_resched flag, on SMP it
 * might also involve a cross-CPU call to trigger the scheduler on
 * the target CPU.
 */
#ifdef CONFIG_SMP

#ifndef tsk_is_polling
#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
#endif

static void resched_task(struct task_struct *p)
{
	int cpu;

	assert_spin_locked(&task_rq(p)->lock);

	if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
		return;

	set_tsk_thread_flag(p, TIF_NEED_RESCHED);

	cpu = task_cpu(p);
	if (cpu == smp_processor_id())
		return;

	/* NEED_RESCHED must be visible before we test polling */
	smp_mb();
	if (!tsk_is_polling(p))
		smp_send_reschedule(cpu);
}

static void resched_cpu(int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long flags;

	if (!spin_trylock_irqsave(&rq->lock, flags))
		return;
	resched_task(cpu_curr(cpu));
	spin_unlock_irqrestore(&rq->lock, flags);
}
#else
static inline void resched_task(struct task_struct *p)
{
	assert_spin_locked(&task_rq(p)->lock);
	set_tsk_need_resched(p);
}
#endif

/**
 * task_curr - is this task currently executing on a CPU?
 * @p: the task in question.
 */
inline int task_curr(const struct task_struct *p)
{
	return cpu_curr(task_cpu(p)) == p;
}

/* Used instead of source_load when we know the type == 0 */
unsigned long weighted_cpuload(const int cpu)
{
	return cpu_rq(cpu)->raw_weighted_load;
}

#ifdef CONFIG_SMP
struct migration_req {
	struct list_head list;

	struct task_struct *task;
	int dest_cpu;

	struct completion done;
};

/*
 * The task's runqueue lock must be held.
 * Returns true if you have to wait for migration thread.
 */
static int
migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
{
	struct rq *rq = task_rq(p);

	/*
	 * If the task is not on a runqueue (and not running), then
	 * it is sufficient to simply update the task's cpu field.
	 */
	if (!p->array && !task_running(rq, p)) {
		set_task_cpu(p, dest_cpu);
		return 0;
	}

	init_completion(&req->done);
	req->task = p;
	req->dest_cpu = dest_cpu;
	list_add(&req->list, &rq->migration_queue);

	return 1;
}

/*
 * wait_task_inactive - wait for a thread to unschedule.
 *
 * The caller must ensure that the task *will* unschedule sometime soon,
 * else this function might spin for a *long* time. This function can't
 * be called with interrupts off, or it may introduce deadlock with
 * smp_call_function() if an IPI is sent by the same process we are
 * waiting to become inactive.
 */
void wait_task_inactive(struct task_struct *p)
{
	unsigned long flags;
	struct rq *rq;
	struct prio_array *array;
	int running;

repeat:
	/*
	 * We do the initial early heuristics without holding
	 * any task-queue locks at all. We'll only try to get
	 * the runqueue lock when things look like they will
	 * work out!
	 */
	rq = task_rq(p);

	/*
	 * If the task is actively running on another CPU
	 * still, just relax and busy-wait without holding
	 * any locks.
	 *
	 * NOTE! Since we don't hold any locks, it's not
	 * even sure that "rq" stays as the right runqueue!
	 * But we don't care, since "task_running()" will
	 * return false if the runqueue has changed and p
	 * is actually now running somewhere else!
	 */
	while (task_running(rq, p))
		cpu_relax();

	/*
	 * Ok, time to look more closely! We need the rq
	 * lock now, to be *sure*. If we're wrong, we'll
	 * just go back and repeat.
	 */
	rq = task_rq_lock(p, &flags);
	running = task_running(rq, p);
	array = p->array;
	task_rq_unlock(rq, &flags);

	/*
	 * Was it really running after all now that we
	 * checked with the proper locks actually held?
	 *
	 * Oops. Go back and try again..
	 */
	if (unlikely(running)) {
		cpu_relax();
		goto repeat;
	}

	/*
	 * It's not enough that it's not actively running,
	 * it must be off the runqueue _entirely_, and not
	 * preempted!
	 *
	 * So if it wa still runnable (but just not actively
	 * running right now), it's preempted, and we should
	 * yield - it could be a while.
	 */
	if (unlikely(array)) {
		yield();
		goto repeat;
	}

	/*
	 * Ahh, all good. It wasn't running, and it wasn't
	 * runnable, which means that it will never become
	 * running in the future either. We're all done!
	 */
}

/***
 * kick_process - kick a running thread to enter/exit the kernel
 * @p: the to-be-kicked thread
 *
 * Cause a process which is running on another CPU to enter
 * kernel-mode, without any delay. (to get signals handled.)
 *
 * NOTE: this function doesnt have to take the runqueue lock,
 * because all it wants to ensure is that the remote task enters
 * the kernel. If the IPI races and the task has been migrated
 * to another CPU then no harm is done and the purpose has been
 * achieved as well.
 */
void kick_process(struct task_struct *p)
{
	int cpu;

	preempt_disable();
	cpu = task_cpu(p);
	if ((cpu != smp_processor_id()) && task_curr(p))
		smp_send_reschedule(cpu);
	preempt_enable();
}

/*
 * Return a low guess at the load of a migration-source cpu weighted
 * according to the scheduling class and "nice" value.
 *
 * We want to under-estimate the load of migration sources, to
 * balance conservatively.
 */
static inline unsigned long source_load(int cpu, int type)
{
	struct rq *rq = cpu_rq(cpu);

	if (type == 0)
		return rq->raw_weighted_load;

	return min(rq->cpu_load[type-1], rq->raw_weighted_load);
}

/*
 * Return a high guess at the load of a migration-target cpu weighted
 * according to the scheduling class and "nice" value.
 */
static inline unsigned long target_load(int cpu, int type)
{
	struct rq *rq = cpu_rq(cpu);

	if (type == 0)
		return rq->raw_weighted_load;

	return max(rq->cpu_load[type-1], rq->raw_weighted_load);
}

/*
 * Return the average load per task on the cpu's run queue
 */
static inline unsigned long cpu_avg_load_per_task(int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long n = rq->nr_running;

	return n ? rq->raw_weighted_load / n : SCHED_LOAD_SCALE;
}

/*
 * find_idlest_group finds and returns the least busy CPU group within the
 * domain.
 */
static struct sched_group *
find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
{
	struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups;
	unsigned long min_load = ULONG_MAX, this_load = 0;
	int load_idx = sd->forkexec_idx;
	int imbalance = 100 + (sd->imbalance_pct-100)/2;

	do {
		unsigned long load, avg_load;
		int local_group;
		int i;

		/* Skip over this group if it has no CPUs allowed */
		if (!cpus_intersects(group->cpumask, p->cpus_allowed))
			goto nextgroup;

		local_group = cpu_isset(this_cpu, group->cpumask);

		/* Tally up the load of all CPUs in the group */
		avg_load = 0;

		for_each_cpu_mask(i, group->cpumask) {
			/* Bias balancing toward cpus of our domain */
			if (local_group)
				load = source_load(i, load_idx);
			else
				load = target_load(i, load_idx);

			avg_load += load;
		}

		/* Adjust by relative CPU power of the group */
		avg_load = sg_div_cpu_power(group,
				avg_load * SCHED_LOAD_SCALE);

		if (local_group) {
			this_load = avg_load;
			this = group;
		} else if (avg_load < min_load) {
			min_load = avg_load;
			idlest = group;
		}
nextgroup:
		group = group->next;
	} while (group != sd->groups);

	if (!idlest || 100*this_load < imbalance*min_load)
		return NULL;
	return idlest;
}

/*
 * find_idlest_cpu - find the idlest cpu among the cpus in group.
 */
static int
find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
{
	cpumask_t tmp;
	unsigned long load, min_load = ULONG_MAX;
	int idlest = -1;
	int i;

	/* Traverse only the allowed CPUs */
	cpus_and(tmp, group->cpumask, p->cpus_allowed);

	for_each_cpu_mask(i, tmp) {
		load = weighted_cpuload(i);

		if (load < min_load || (load == min_load && i == this_cpu)) {
			min_load = load;
			idlest = i;
		}
	}

	return idlest;
}

/*
 * sched_balance_self: balance the current task (running on cpu) in domains
 * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
 * SD_BALANCE_EXEC.
 *
 * Balance, ie. select the least loaded group.
 *
 * Returns the target CPU number, or the same CPU if no balancing is needed.
 *
 * preempt must be disabled.
 */
static int sched_balance_self(int cpu, int flag)
{
	struct task_struct *t = current;
	struct sched_domain *tmp, *sd = NULL;

	for_each_domain(cpu, tmp) {
 		/*
 	 	 * If power savings logic is enabled for a domain, stop there.
 	 	 */
		if (tmp->flags & SD_POWERSAVINGS_BALANCE)
			break;
		if (tmp->flags & flag)
			sd = tmp;
	}

	while (sd) {
		cpumask_t span;
		struct sched_group *group;
		int new_cpu, weight;

		if (!(sd->flags & flag)) {
			sd = sd->child;
			continue;
		}

		span = sd->span;
		group = find_idlest_group(sd, t, cpu);
		if (!group) {
			sd = sd->child;
			continue;
		}

		new_cpu = find_idlest_cpu(group, t, cpu);
		if (new_cpu == -1 || new_cpu == cpu) {
			/* Now try balancing at a lower domain level of cpu */
			sd = sd->child;
			continue;
		}

		/* Now try balancing at a lower domain level of new_cpu */
		cpu = new_cpu;
		sd = NULL;
		weight = cpus_weight(span);
		for_each_domain(cpu, tmp) {
			if (weight <= cpus_weight(tmp->span))
				break;
			if (tmp->flags & flag)
				sd = tmp;
		}
		/* while loop will break here if sd == NULL */
	}

	return cpu;
}

#endif /* CONFIG_SMP */

/*
 * 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))
					return i;
			}
		}
		else
			break;
	}
	return cpu;
}
#else
static inline int wake_idle(int cpu, struct task_struct *p)
{
	return cpu;
}
#endif

/***
 * try_to_wake_up - wake up a thread
 * @p: the to-be-woken-up thread
 * @state: the mask of task states that can be woken
 * @sync: do a synchronous wakeup?
 *
 * Put it on the run-queue if it's not already there. The "current"
 * thread is always on the run-queue (except when the actual
 * re-schedule is in progress), and as such you're allowed to do
 * the simpler "current->state = TASK_RUNNING" to mark yourself
 * runnable without the overhead of this.
 *
 * returns failure only if the task is already active.
 */
static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
{
	int cpu, this_cpu, success = 0;
	unsigned long flags;
	long old_state;
	struct rq *rq;
#ifdef CONFIG_SMP
	struct sched_domain *sd, *this_sd = NULL;
	unsigned long load, this_load;
	int new_cpu;
#endif

	rq = task_rq_lock(p, &flags);
	old_state = p->state;
	if (!(old_state & state))
		goto out;

	if (p->array)
		goto out_running;

	cpu = task_cpu(p);
	this_cpu = smp_processor_id();

#ifdef CONFIG_SMP
	if (unlikely(task_running(rq, p)))
		goto out_activate;

	new_cpu = cpu;

	schedstat_inc(rq, ttwu_cnt);
	if (cpu == this_cpu) {
		schedstat_inc(rq, ttwu_local);
		goto out_set_cpu;
	}

	for_each_domain(this_cpu, sd) {
		if (cpu_isset(cpu, sd->span)) {
			schedstat_inc(sd, ttwu_wake_remote);
			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.
	 */
	if (this_sd) {
		int idx = this_sd->wake_idx;
		unsigned int imbalance;

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

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

		new_cpu = this_cpu; /* Wake to this CPU if we can */

		if (this_sd->flags & SD_WAKE_AFFINE) {
			unsigned long tl = this_load;
			unsigned long tl_per_task;

			tl_per_task = cpu_avg_load_per_task(this_cpu);

			/*
			 * If sync wakeup then subtract the (maximum possible)
			 * effect of the currently running task from the load
			 * of the current CPU:
			 */
			if (sync)
				tl -= current->load_weight;

			if ((tl <= load &&
				tl + target_load(cpu, idx) <= tl_per_task) ||
				100*(tl + p->load_weight) <= imbalance*load) {
				/*
				 * 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);
				goto out_set_cpu;
			}
		}

		/*
		 * 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);
				goto out_set_cpu;
			}
		}
	}

	new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
out_set_cpu:
	new_cpu = wake_idle(new_cpu, p);
	if (new_cpu != cpu) {
		set_task_cpu(p, new_cpu);
		task_rq_unlock(rq, &flags);
		/* might preempt at this point */
		rq = task_rq_lock(p, &flags);
		old_state = p->state;
		if (!(old_state & state))
			goto out;
		if (p->array)
			goto out_running;

		this_cpu = smp_processor_id();
		cpu = task_cpu(p);
	}

out_activate:
#endif /* CONFIG_SMP */
	if (old_state == TASK_UNINTERRUPTIBLE) {
		rq->nr_uninterruptible--;
		/*
		 * Tasks on involuntary sleep don't earn
		 * sleep_avg beyond just interactive state.
		 */
		p->sleep_type = SLEEP_NONINTERACTIVE;
	} else

	/*
	 * Tasks that have marked their sleep as noninteractive get
	 * woken up with their sleep average not weighted in an
	 * interactive way.
	 */
		if (old_state & TASK_NONINTERACTIVE)
			p->sleep_type = SLEEP_NONINTERACTIVE;


	activate_task(p, rq, cpu == this_cpu);
	/*
	 * Sync wakeups (i.e. those types of wakeups where the waker
	 * has indicated that it will leave the CPU in short order)
	 * don't trigger a preemption, if the woken up task will run on
	 * this cpu. (in this case the 'I will reschedule' promise of
	 * the waker guarantees that the freshly woken up task is going
	 * to be considered on this CPU.)
	 */
	if (!sync || cpu != this_cpu) {
		if (TASK_PREEMPTS_CURR(p, rq))
			resched_task(rq->curr);
	}
	success = 1;

out_running:
	p->state = TASK_RUNNING;
out:
	task_rq_unlock(rq, &flags);

	return success;
}

int fastcall wake_up_process(struct task_struct *p)
{
	return try_to_wake_up(p, TASK_STOPPED | TASK_TRACED |
				 TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0);
}
EXPORT_SYMBOL(wake_up_process);

int fastcall wake_up_state(struct task_struct *p, unsigned int state)
{
	return try_to_wake_up(p, state, 0);
}

static void task_running_tick(struct rq *rq, struct task_struct *p);
/*
 * Perform scheduler related setup for a newly forked process p.
 * p is forked by current.
 */
void fastcall sched_fork(struct task_struct *p, int clone_flags)
{
	int cpu = get_cpu();

#ifdef CONFIG_SMP
	cpu = sched_balance_self(cpu, SD_BALANCE_FORK);
#endif
	set_task_cpu(p, cpu);

	/*
	 * We mark the process as running here, but have not actually
	 * inserted it onto the runqueue yet. This guarantees that
	 * nobody will actually run it, and a signal or other external
	 * event cannot wake it up and insert it on the runqueue either.
	 */
	p->state = TASK_RUNNING;

	/*
	 * Make sure we do not leak PI boosting priority to the child:
	 */
	p->prio = current->normal_prio;

	INIT_LIST_HEAD(&p->run_list);
	p->array = NULL;
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
	if (unlikely(sched_info_on()))
		memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
	p->oncpu = 0;
#endif
#ifdef CONFIG_PREEMPT
	/* Want to start with kernel preemption disabled. */
	task_thread_info(p)->preempt_count = 1;
#endif
	/*
	 * Share the timeslice between parent and child, thus the
	 * total amount of pending timeslices in the system doesn't change,
	 * resulting in more scheduling fairness.
	 */
	local_irq_disable();
	p->time_slice = (current->time_slice + 1) >> 1;
	/*
	 * The remainder of the first timeslice might be recovered by
	 * the parent if the child exits early enough.
	 */
	p->first_time_slice = 1;
	current->time_slice >>= 1;
	p->timestamp = sched_clock();
	if (unlikely(!current->time_slice)) {
		/*
		 * This case is rare, it happens when the parent has only
		 * a single jiffy left from its timeslice. Taking the
		 * runqueue lock is not a problem.
		 */
		current->time_slice = 1;
		task_running_tick(cpu_rq(cpu), current);
	}
	local_irq_enable();
	put_cpu();
}

/*
 * wake_up_new_task - wake up a newly created task for the first time.
 *
 * This function will do some initial scheduler statistics housekeeping
 * that must be done for every newly created context, then puts the task
 * on the runqueue and wakes it.
 */
void fastcall wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
{
	struct rq *rq, *this_rq;
	unsigned long flags;
	int this_cpu, cpu;

	rq = task_rq_lock(p, &flags);
	BUG_ON(p->state != TASK_RUNNING);
	this_cpu = smp_processor_id();
	cpu = task_cpu(p);

	/*
	 * We decrease the sleep average of forking parents
	 * and children as well, to keep max-interactive tasks
	 * from forking tasks that are max-interactive. The parent
	 * (current) is done further down, under its lock.
	 */
	p->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(p) *
		CHILD_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS);

	p->prio = effective_prio(p);

	if (likely(cpu == this_cpu)) {
		if (!(clone_flags & CLONE_VM)) {
			/*
			 * The VM isn't cloned, so we're in a good position to
			 * do child-runs-first in anticipation of an exec. This
			 * usually avoids a lot of COW overhead.
			 */
			if (unlikely(!current->array))
				__activate_task(p, rq);
			else {
				p->prio = current->prio;
				p->normal_prio = current->normal_prio;
				list_add_tail(&p->run_list, &current->run_list);
				p->array = current->array;
				p->array->nr_active++;
				inc_nr_running(p, rq);
			}
			set_need_resched();
		} else
			/* Run child last */
			__activate_task(p, rq);
		/*
		 * We skip the following code due to cpu == this_cpu
	 	 *
		 *   task_rq_unlock(rq, &flags);
		 *   this_rq = task_rq_lock(current, &flags);
		 */
		this_rq = rq;
	} else {
		this_rq = cpu_rq(this_cpu);

		/*
		 * Not the local CPU - must adjust timestamp. This should
		 * get optimised away in the !CONFIG_SMP case.
		 */
		p->timestamp = (p->timestamp - this_rq->most_recent_timestamp)
					+ rq->most_recent_timestamp;
		__activate_task(p, rq);
		if (TASK_PREEMPTS_CURR(p, rq))
			resched_task(rq->curr);

		/*
		 * Parent and child are on different CPUs, now get the
		 * parent runqueue to update the parent's ->sleep_avg:
		 */
		task_rq_unlock(rq, &flags);
		this_rq = task_rq_lock(current, &flags);
	}
	current->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(current) *
		PARENT_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS);
	task_rq_unlock(this_rq, &flags);
}

/*
 * Potentially available exiting-child timeslices are
 * retrieved here - this way the parent does not get
 * penalized for creating too many threads.
 *
 * (this cannot be used to 'generate' timeslices
 * artificially, because any timeslice recovered here
 * was given away by the parent in the first place.)
 */
void fastcall sched_exit(struct task_struct *p)
{
	unsigned long flags;
	struct rq *rq;

	/*
	 * If the child was a (relative-) CPU hog then decrease
	 * the sleep_avg of the parent as well.
	 */
	rq = task_rq_lock(p->parent, &flags);
	if (p->first_time_slice && task_cpu(p) == task_cpu(p->parent)) {
		p->parent->time_slice += p->time_slice;
		if (unlikely(p->parent->time_slice > task_timeslice(p)))
			p->parent->time_slice = task_timeslice(p);
	}
	if (p->sleep_avg < p->parent->sleep_avg)
		p->parent->sleep_avg = p->parent->sleep_avg /
		(EXIT_WEIGHT + 1) * EXIT_WEIGHT + p->sleep_avg /
		(EXIT_WEIGHT + 1);
	task_rq_unlock(rq, &flags);
}

/**
 * prepare_task_switch - prepare to switch tasks
 * @rq: the runqueue preparing to switch
 * @next: the task we are going to switch to.
 *
 * This is called with the rq lock held and interrupts off. It must
 * be paired with a subsequent finish_task_switch after the context
 * switch.
 *
 * prepare_task_switch sets up locking and calls architecture specific
 * hooks.
 */
static inline void prepare_task_switch(struct rq *rq, struct task_struct *next)
{
	prepare_lock_switch(rq, next);
	prepare_arch_switch(next);
}

/**
 * finish_task_switch - clean up after a task-switch
 * @rq: runqueue associated with task-switch
 * @prev: the thread we just switched away from.
 *
 * finish_task_switch must be called after the context switch, paired
 * with a prepare_task_switch call before the context switch.
 * finish_task_switch will reconcile locking set up by prepare_task_switch,
 * and do any other architecture-specific cleanup actions.
 *
 * Note that we may have delayed dropping an mm in context_switch(). If
 * so, we finish that here outside of the runqueue lock.  (Doing it
 * with the lock held can cause deadlocks; see schedule() for
 * details.)
 */
static inline void finish_task_switch(struct rq *rq, struct task_struct *prev)
	__releases(rq->lock)
{
	struct mm_struct *mm = rq->prev_mm;
	long prev_state;

	rq->prev_mm = NULL;

	/*
	 * A task struct has one reference for the use as "current".
	 * If a task dies, then it sets TASK_DEAD in tsk->state and calls
	 * schedule one last time. The schedule call will never return, and
	 * the scheduled task must drop that reference.
	 * The test for TASK_DEAD must occur while the runqueue locks are
	 * still held, otherwise prev could be scheduled on another cpu, die
	 * there before we look at prev->state, and then the reference would
	 * be dropped twice.
	 *		Manfred Spraul <manfred@colorfullife.com>
	 */
	prev_state = prev->state;
	finish_arch_switch(prev);
	finish_lock_switch(rq, prev);
	if (mm)
		mmdrop(mm);
	if (unlikely(prev_state == TASK_DEAD)) {
		/*
		 * Remove function-return probe instances associated with this
		 * task and put them back on the free list.
	 	 */
		kprobe_flush_task(prev);
		put_task_struct(prev);
	}
}

/**
 * schedule_tail - first thing a freshly forked thread must call.
 * @prev: the thread we just switched away from.
 */
asmlinkage void schedule_tail(struct task_struct *prev)
	__releases(rq->lock)
{
	struct rq *rq = this_rq();

	finish_task_switch(rq, prev);
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
	/* In this case, finish_task_switch does not reenable preemption */
	preempt_enable();
#endif
	if (current->set_child_tid)
		put_user(current->pid, current->set_child_tid);
}

/*
 * context_switch - switch to the new MM and the new
 * thread's register state.
 */
static inline struct task_struct *
context_switch(struct rq *rq, struct task_struct *prev,
	       struct task_struct *next)
{
	struct mm_struct *mm = next->mm;
	struct mm_struct *oldmm = prev->active_mm;

	/*
	 * For paravirt, this is coupled with an exit in switch_to to
	 * combine the page table reload and the switch backend into
	 * one hypercall.
	 */
	arch_enter_lazy_cpu_mode();

	if (!mm) {
		next->active_mm = oldmm;
		atomic_inc(&oldmm->mm_count);
		enter_lazy_tlb(oldmm, next);
	} else
		switch_mm(oldmm, mm, next);

	if (!prev->mm) {
		prev->active_mm = NULL;
		WARN_ON(rq->prev_mm);
		rq->prev_mm = oldmm;
	}
	/*
	 * Since the runqueue lock will be released by the next
	 * task (which is an invalid locking op but in the case
	 * of the scheduler it's an obvious special-case), so we
	 * do an early lockdep release here:
	 */
#ifndef __ARCH_WANT_UNLOCKED_CTXSW
	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
#endif

	/* Here we just switch the register state and the stack. */
	switch_to(prev, next, prev);

	return prev;
}

/*
 * nr_running, nr_uninterruptible and nr_context_switches:
 *
 * externally visible scheduler statistics: current number of runnable
 * threads, current number of uninterruptible-sleeping threads, total
 * number of context switches performed since bootup.
 */
unsigned long nr_running(void)
{
	unsigned long i, sum = 0;

	for_each_online_cpu(i)
		sum += cpu_rq(i)->nr_running;

	return sum;
}

unsigned long nr_uninterruptible(void)
{
	unsigned long i, sum = 0;

	for_each_possible_cpu(i)
		sum += cpu_rq(i)->nr_uninterruptible;

	/*
	 * Since we read the counters lockless, it might be slightly
	 * inaccurate. Do not allow it to go below zero though:
	 */
	if (unlikely((long)sum < 0))
		sum = 0;

	return sum;
}

unsigned long long nr_context_switches(void)
{
	int i;
	unsigned long long sum = 0;

	for_each_possible_cpu(i)
		sum += cpu_rq(i)->nr_switches;

	return sum;
}

unsigned long nr_iowait(void)
{
	unsigned long i, sum = 0;

	for_each_possible_cpu(i)
		sum += atomic_read(&cpu_rq(i)->nr_iowait);

	return sum;
}

unsigned long nr_active(void)
{
	unsigned long i, running = 0, uninterruptible = 0;

	for_each_online_cpu(i) {
		running += cpu_rq(i)->nr_running;
		uninterruptible += cpu_rq(i)->nr_uninterruptible;
	}

	if (unlikely((long)uninterruptible < 0))
		uninterruptible = 0;

	return running + uninterruptible;
}

#ifdef CONFIG_SMP

/*
 * Is this task likely cache-hot:
 */
static inline int
task_hot(struct task_struct *p, unsigned long long now, struct sched_domain *sd)
{
	return (long long)(now - p->last_ran) < (long long)sd->cache_hot_time;
}

/*
 * double_rq_lock - safely lock two runqueues
 *
 * Note this does not disable interrupts like task_rq_lock,
 * you need to do so manually before calling.
 */
static void double_rq_lock(struct rq *rq1, struct rq *rq2)
	__acquires(rq1->lock)
	__acquires(rq2->lock)
{
	BUG_ON(!irqs_disabled());
	if (rq1 == rq2) {
		spin_lock(&rq1->lock);
		__acquire(rq2->lock);	/* Fake it out ;) */
	} else {
		if (rq1 < rq2) {
			spin_lock(&rq1->lock);
			spin_lock(&rq2->lock);
		} else {
			spin_lock(&rq2->lock);
			spin_lock(&rq1->lock);
		}
	}
}

/*
 * double_rq_unlock - safely unlock two runqueues
 *
 * Note this does not restore interrupts like task_rq_unlock,
 * you need to do so manually after calling.
 */
static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
	__releases(rq1->lock)
	__releases(rq2->lock)
{
	spin_unlock(&rq1->lock);
	if (rq1 != rq2)
		spin_unlock(&rq2->lock);
	else
		__release(rq2->lock);
}

/*
 * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
 */
static void double_lock_balance(struct rq *this_rq, struct rq *busiest)
	__releases(this_rq->lock)
	__acquires(busiest->lock)
	__acquires(this_rq->lock)
{
	if (unlikely(!irqs_disabled())) {
		/* printk() doesn't work good under rq->lock */
		spin_unlock(&this_rq->lock);
		BUG_ON(1);
	}
	if (unlikely(!spin_trylock(&busiest->lock))) {
		if (busiest < this_rq) {
			spin_unlock(&this_rq->lock);
			spin_lock(&busiest->lock);
			spin_lock(&this_rq->lock);
		} else
			spin_lock(&busiest->lock);
	}
}

/*
 * If dest_cpu is allowed for this process, migrate the task to it.
 * This is accomplished by forcing the cpu_allowed mask to only
 * allow dest_cpu, which will force the cpu onto dest_cpu.  Then
 * the cpu_allowed mask is restored.
 */
static void sched_migrate_task(struct task_struct *p, int dest_cpu)
{
	struct migration_req req;
	unsigned long flags;
	struct rq *rq;

	rq = task_rq_lock(p, &flags);
	if (!cpu_isset(dest_cpu, p->cpus_allowed)
	    || unlikely(cpu_is_offline(dest_cpu)))
		goto out;

	/* force the process onto the specified CPU */
	if (migrate_task(p, dest_cpu, &req)) {
		/* Need to wait for migration thread (might exit: take ref). */
		struct task_struct *mt = rq->migration_thread;

		get_task_struct(mt);
		task_rq_unlock(rq, &flags);
		wake_up_process(mt);
		put_task_struct(mt);
		wait_for_completion(&req.done);

		return;
	}
out:
	task_rq_unlock(rq, &flags);
}

/*
 * sched_exec - execve() is a valuable balancing opportunity, because at
 * this point the task has the smallest effective memory and cache footprint.
 */
void sched_exec(void)
{
	int new_cpu, this_cpu = get_cpu();
	new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC);
	put_cpu();
	if (new_cpu != this_cpu)
		sched_migrate_task(current, new_cpu);
}

/*
 * pull_task - move a task from a remote runqueue to the local runqueue.
 * Both runqueues must be locked.
 */
static void pull_task(struct rq *src_rq, struct prio_array *src_array,
		      struct task_struct *p, struct rq *this_rq,
		      struct prio_array *this_array, int this_cpu)
{
	dequeue_task(p, src_array);
	dec_nr_running(p, src_rq);
	set_task_cpu(p, this_cpu);
	inc_nr_running(p, this_rq);
	enqueue_task(p, this_array);
	p->timestamp = (p->timestamp - src_rq->most_recent_timestamp)
				+ this_rq->most_recent_timestamp;
	/*
	 * Note that idle threads have a prio of MAX_PRIO, for this test
	 * to be always true for them.
	 */
	if (TASK_PREEMPTS_CURR(p, this_rq))
		resched_task(this_rq->curr);
}

/*
 * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
 */
static
int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
		     struct sched_domain *sd, enum idle_type idle,
		     int *all_pinned)
{
	/*
	 * We do not migrate tasks that are:
	 * 1) running (obviously), or
	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
	 * 3) are cache-hot on their current CPU.
	 */
	if (!cpu_isset(this_cpu, p->cpus_allowed))
		return 0;
	*all_pinned = 0;

	if (task_running(rq, p))
		return 0;

	/*
	 * Aggressive migration if:
	 * 1) task is cache cold, or
	 * 2) too many balance attempts have failed.
	 */

	if (sd->nr_balance_failed > sd->cache_nice_tries) {
#ifdef CONFIG_SCHEDSTATS
		if (task_hot(p, rq->most_recent_timestamp, sd))
			schedstat_inc(sd, lb_hot_gained[idle]);
#endif
		return 1;
	}

	if (task_hot(p, rq->most_recent_timestamp, sd))
		return 0;
	return 1;
}

#define rq_best_prio(rq) min((rq)->curr->prio, (rq)->best_expired_prio)

/*
 * move_tasks tries to move up to max_nr_move tasks and max_load_move weighted
 * load from busiest to this_rq, as part of a balancing operation within
 * "domain". Returns the number of tasks moved.
 *
 * Called with both runqueues locked.
 */
static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
		      unsigned long max_nr_move, unsigned long max_load_move,
		      struct sched_domain *sd, enum idle_type idle,
		      int *all_pinned)
{
	int idx, pulled = 0, pinned = 0, this_best_prio, best_prio,
	    best_prio_seen, skip_for_load;
	struct prio_array *array, *dst_array;
	struct list_head *head, *curr;
	struct task_struct *tmp;
	long rem_load_move;

	if (max_nr_move == 0 || max_load_move == 0)
		goto out;

	rem_load_move = max_load_move;
	pinned = 1;
	this_best_prio = rq_best_prio(this_rq);
	best_prio = rq_best_prio(busiest);
	/*
	 * Enable handling of the case where there is more than one task
	 * with the best priority.   If the current running task is one
	 * of those with prio==best_prio we know it won't be moved
	 * and therefore it's safe to override the skip (based on load) of
	 * any task we find with that prio.
	 */
	best_prio_seen = best_prio == busiest->curr->prio;

	/*
	 * We first consider expired tasks. Those will likely not be
	 * executed in the near future, and they are most likely to
	 * be cache-cold, thus switching CPUs has the least effect
	 * on them.
	 */
	if (busiest->expired->nr_active) {
		array = busiest->expired;
		dst_array = this_rq->expired;
	} else {
		array = busiest->active;
		dst_array = this_rq->active;
	}

new_array:
	/* Start searching at priority 0: */
	idx = 0;
skip_bitmap:
	if (!idx)
		idx = sched_find_first_bit(array->bitmap);
	else
		idx = find_next_bit(array->bitmap, MAX_PRIO, idx);
	if (idx >= MAX_PRIO) {
		if (array == busiest->expired && busiest->active->nr_active) {
			array = busiest->active;
			dst_array = this_rq->active;
			goto new_array;
		}
		goto out;
	}

	head = array->queue + idx;
	curr = head->prev;
skip_queue:
	tmp = list_entry(curr, struct task_struct, run_list);

	curr = curr->prev;

	/*
	 * To help distribute high priority tasks accross CPUs we don't
	 * skip a task if it will be the highest priority task (i.e. smallest
	 * prio value) on its new queue regardless of its load weight
	 */
	skip_for_load = tmp->load_weight > rem_load_move;
	if (skip_for_load && idx < this_best_prio)
		skip_for_load = !best_prio_seen && idx == best_prio;
	if (skip_for_load ||
	    !can_migrate_task(tmp, busiest, this_cpu, sd, idle, &pinned)) {

		best_prio_seen |= idx == best_prio;
		if (curr != head)
			goto skip_queue;
		idx++;
		goto skip_bitmap;
	}

	pull_task(busiest, array, tmp, this_rq, dst_array, this_cpu);
	pulled++;
	rem_load_move -= tmp->load_weight;

	/*
	 * We only want to steal up to the prescribed number of tasks
	 * and the prescribed amount of weighted load.
	 */
	if (pulled < max_nr_move && rem_load_move > 0) {
		if (idx < this_best_prio)
			this_best_prio = idx;
		if (curr != head)
			goto skip_queue;
		idx++;
		goto skip_bitmap;
	}
out:
	/*
	 * Right now, this is the only place pull_task() is called,
	 * so we can safely collect pull_task() stats here rather than
	 * inside pull_task().
	 */
	schedstat_add(sd, lb_gained[idle], pulled);

	if (all_pinned)
		*all_pinned = pinned;
	return pulled;
}

/*
 * find_busiest_group finds and returns the busiest CPU group within the
 * domain. It calculates and returns the amount of weighted load which
 * should be moved to restore balance via the imbalance parameter.
 */
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
		   unsigned long *imbalance, enum idle_type idle, int *sd_idle,
		   cpumask_t *cpus, int *balance)
{
	struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
	unsigned long max_load, avg_load, total_load, this_load, total_pwr;
	unsigned long max_pull;
	unsigned long busiest_load_per_task, busiest_nr_running;
	unsigned long this_load_per_task, this_nr_running;
	int load_idx;
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
	int power_savings_balance = 1;
	unsigned long leader_nr_running = 0, min_load_per_task = 0;
	unsigned long min_nr_running = ULONG_MAX;
	struct sched_group *group_min = NULL, *group_leader = NULL;
#endif

	max_load = this_load = total_load = total_pwr = 0;
	busiest_load_per_task = busiest_nr_running = 0;
	this_load_per_task = this_nr_running = 0;
	if (idle == NOT_IDLE)
		load_idx = sd->busy_idx;
	else if (idle == NEWLY_IDLE)
		load_idx = sd->newidle_idx;
	else
		load_idx = sd->idle_idx;

	do {
		unsigned long load, group_capacity;
		int local_group;
		int i;
		unsigned int balance_cpu = -1, first_idle_cpu = 0;
		unsigned long sum_nr_running, sum_weighted_load;

		local_group = cpu_isset(this_cpu, group->cpumask);

		if (local_group)
			balance_cpu = first_cpu(group->cpumask);

		/* Tally up the load of all CPUs in the group */
		sum_weighted_load = sum_nr_running = avg_load = 0;

		for_each_cpu_mask(i, group->cpumask) {
			struct rq *rq;

			if (!cpu_isset(i, *cpus))
				continue;

			rq = cpu_rq(i);

			if (*sd_idle && !idle_cpu(i))
				*sd_idle = 0;

			/* Bias balancing toward cpus of our domain */
			if (local_group) {
				if (idle_cpu(i) && !first_idle_cpu) {
					first_idle_cpu = 1;
					balance_cpu = i;
				}

				load = target_load(i, load_idx);
			} else
				load = source_load(i, load_idx);

			avg_load += load;
			sum_nr_running += rq->nr_running;
			sum_weighted_load += rq->raw_weighted_load;
		}

		/*
		 * First idle cpu or the first cpu(busiest) in this sched group
		 * is eligible for doing load balancing at this and above
		 * domains.
		 */
		if (local_group && balance_cpu != this_cpu && balance) {
			*balance = 0;
			goto ret;
		}

		total_load += avg_load;
		total_pwr += group->__cpu_power;

		/* Adjust by relative CPU power of the group */
		avg_load = sg_div_cpu_power(group,
				avg_load * SCHED_LOAD_SCALE);

		group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;

		if (local_group) {
			this_load = avg_load;
			this = group;
			this_nr_running = sum_nr_running;
			this_load_per_task = sum_weighted_load;
		} else if (avg_load > max_load &&
			   sum_nr_running > group_capacity) {
			max_load = avg_load;
			busiest = group;
			busiest_nr_running = sum_nr_running;
			busiest_load_per_task = sum_weighted_load;
		}

#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
		/*
		 * Busy processors will not participate in power savings
		 * balance.
		 */
 		if (idle == NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
 			goto group_next;

		/*
		 * If the local group is idle or completely loaded
		 * no need to do power savings balance at this domain
		 */
		if (local_group && (this_nr_running >= group_capacity ||
				    !this_nr_running))
			power_savings_balance = 0;

 		/*
		 * If a group is already running at full capacity or idle,
		 * don't include that group in power savings calculations
 		 */
 		if (!power_savings_balance || sum_nr_running >= group_capacity
		    || !sum_nr_running)
 			goto group_next;

 		/*
		 * Calculate the group which has the least non-idle load.
 		 * This is the group from where we need to pick up the load
 		 * for saving power
 		 */
 		if ((sum_nr_running < min_nr_running) ||
 		    (sum_nr_running == min_nr_running &&
		     first_cpu(group->cpumask) <
		     first_cpu(group_min->cpumask))) {
 			group_min = group;
 			min_nr_running = sum_nr_running;
			min_load_per_task = sum_weighted_load /
						sum_nr_running;
 		}

 		/*
		 * Calculate the group which is almost near its
 		 * capacity but still has some space to pick up some load
 		 * from other group and save more power
 		 */
 		if (sum_nr_running <= group_capacity - 1) {
 			if (sum_nr_running > leader_nr_running ||
 			    (sum_nr_running == leader_nr_running &&
 			     first_cpu(group->cpumask) >
 			      first_cpu(group_leader->cpumask))) {
 				group_leader = group;
 				leader_nr_running = sum_nr_running;
 			}
		}
group_next:
#endif
		group = group->next;
	} while (group != sd->groups);

	if (!busiest || this_load >= max_load || busiest_nr_running == 0)
		goto out_balanced;

	avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr;

	if (this_load >= avg_load ||
			100*max_load <= sd->imbalance_pct*this_load)
		goto out_balanced;

	busiest_load_per_task /= busiest_nr_running;
	/*
	 * We're trying to get all the cpus to the average_load, so we don't
	 * want to push ourselves above the average load, nor do we wish to
	 * reduce the max loaded cpu below the average load, as either of these
	 * actions would just result in more rebalancing later, and ping-pong
	 * tasks around. Thus we look for the minimum possible imbalance.
	 * Negative imbalances (*we* are more loaded than anyone else) will
	 * be counted as no imbalance for these purposes -- we can't fix that
	 * by pulling tasks to us.  Be careful of negative numbers as they'll
	 * appear as very large values with unsigned longs.
	 */
	if (max_load <= busiest_load_per_task)
		goto out_balanced;

	/*
	 * In the presence of smp nice balancing, certain scenarios can have
	 * max load less than avg load(as we skip the groups at or below
	 * its cpu_power, while calculating max_load..)
	 */
	if (max_load < avg_load) {
		*imbalance = 0;
		goto small_imbalance;
	}

	/* Don't want to pull so many tasks that a group would go idle */
	max_pull = min(max_load - avg_load, max_load - busiest_load_per_task);

	/* How much load to actually move to equalise the imbalance */
	*imbalance = min(max_pull * busiest->__cpu_power,
				(avg_load - this_load) * this->__cpu_power)
			/ SCHED_LOAD_SCALE;

	/*
	 * if *imbalance is less than the average load per runnable task
	 * there is no gaurantee that any tasks will be moved so we'll have
	 * a think about bumping its value to force at least one task to be
	 * moved
	 */
	if (*imbalance < busiest_load_per_task) {
		unsigned long tmp, pwr_now, pwr_move;
		unsigned int imbn;

small_imbalance:
		pwr_move = pwr_now = 0;
		imbn = 2;
		if (this_nr_running) {
			this_load_per_task /= this_nr_running;
			if (busiest_load_per_task > this_load_per_task)
				imbn = 1;
		} else
			this_load_per_task = SCHED_LOAD_SCALE;

		if (max_load - this_load >= busiest_load_per_task * imbn) {
			*imbalance = busiest_load_per_task;
			return busiest;
		}

		/*
		 * OK, we don't have enough imbalance to justify moving tasks,
		 * however we may be able to increase total CPU power used by
		 * moving them.
		 */

		pwr_now += busiest->__cpu_power *
				min(busiest_load_per_task, max_load);
		pwr_now += this->__cpu_power *
				min(this_load_per_task, this_load);
		pwr_now /= SCHED_LOAD_SCALE;

		/* Amount of load we'd subtract */
		tmp = sg_div_cpu_power(busiest,
				busiest_load_per_task * SCHED_LOAD_SCALE);
		if (max_load > tmp)
			pwr_move += busiest->__cpu_power *
				min(busiest_load_per_task, max_load - tmp);

		/* Amount of load we'd add */
		if (max_load * busiest->__cpu_power <
				busiest_load_per_task * SCHED_LOAD_SCALE)
			tmp = sg_div_cpu_power(this,
					max_load * busiest->__cpu_power);
		else
			tmp = sg_div_cpu_power(this,
				busiest_load_per_task * SCHED_LOAD_SCALE);
		pwr_move += this->__cpu_power *
				min(this_load_per_task, this_load + tmp);
		pwr_move /= SCHED_LOAD_SCALE;

		/* Move if we gain throughput */
		if (pwr_move <= pwr_now)
			goto out_balanced;

		*imbalance = busiest_load_per_task;
	}

	return busiest;

out_balanced:
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
	if (idle == NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
		goto ret;

	if (this == group_leader && group_leader != group_min) {
		*imbalance = min_load_per_task;
		return group_min;
	}
#endif
ret:
	*imbalance = 0;
	return NULL;
}

/*
 * find_busiest_queue - find the busiest runqueue among the cpus in group.
 */
static struct rq *
find_busiest_queue(struct sched_group *group, enum idle_type idle,
		   unsigned long imbalance, cpumask_t *cpus)
{
	struct rq *busiest = NULL, *rq;
	unsigned long max_load = 0;
	int i;

	for_each_cpu_mask(i, group->cpumask) {

		if (!cpu_isset(i, *cpus))
			continue;

		rq = cpu_rq(i);

		if (rq->nr_running == 1 && rq->raw_weighted_load > imbalance)
			continue;

		if (rq->raw_weighted_load > max_load) {
			max_load = rq->raw_weighted_load;
			busiest = rq;
		}
	}

	return busiest;
}

/*
 * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
 * so long as it is large enough.
 */
#define MAX_PINNED_INTERVAL	512

static inline unsigned long minus_1_or_zero(unsigned long n)
{
	return n > 0 ? n - 1 : 0;
}

/*
 * Check this_cpu to ensure it is balanced within domain. Attempt to move
 * tasks if there is an imbalance.
 */
static int load_balance(int this_cpu, struct rq *this_rq,
			struct sched_domain *sd, enum idle_type idle,
			int *balance)
{
	int nr_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
	struct sched_group *group;
	unsigned long imbalance;
	struct rq *busiest;
	cpumask_t cpus = CPU_MASK_ALL;
	unsigned long flags;

	/*
	 * When power savings policy is enabled for the parent domain, idle
	 * sibling can pick up load irrespective of busy siblings. In this case,
	 * let the state of idle sibling percolate up as IDLE, instead of
	 * portraying it as NOT_IDLE.
	 */
	if (idle != NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
		sd_idle = 1;

	schedstat_inc(sd, lb_cnt[idle]);

redo:
	group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
				   &cpus, balance);

	if (*balance == 0)
		goto out_balanced;

	if (!group) {
		schedstat_inc(sd, lb_nobusyg[idle]);
		goto out_balanced;
	}

	busiest = find_busiest_queue(group, idle, imbalance, &cpus);
	if (!busiest) {
		schedstat_inc(sd, lb_nobusyq[idle]);
		goto out_balanced;
	}

	BUG_ON(busiest == this_rq);

	schedstat_add(sd, lb_imbalance[idle], imbalance);

	nr_moved = 0;
	if (busiest->nr_running > 1) {
		/*
		 * Attempt to move tasks. If find_busiest_group has found
		 * an imbalance but busiest->nr_running <= 1, the group is
		 * still unbalanced. nr_moved simply stays zero, so it is
		 * correctly treated as an imbalance.
		 */
		local_irq_save(flags);
		double_rq_lock(this_rq, busiest);
		nr_moved = move_tasks(this_rq, this_cpu, busiest,
				      minus_1_or_zero(busiest->nr_running),
				      imbalance, sd, idle, &all_pinned);
		double_rq_unlock(this_rq, busiest);
		local_irq_restore(flags);

		/*
		 * some other cpu did the load balance for us.
		 */
		if (nr_moved && this_cpu != smp_processor_id())
			resched_cpu(this_cpu);

		/* All tasks on this runqueue were pinned by CPU affinity */
		if (unlikely(all_pinned)) {
			cpu_clear(cpu_of(busiest), cpus);
			if (!cpus_empty(cpus))
				goto redo;
			goto out_balanced;
		}
	}

	if (!nr_moved) {
		schedstat_inc(sd, lb_failed[idle]);
		sd->nr_balance_failed++;

		if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {

			spin_lock_irqsave(&busiest->lock, flags);

			/* don't kick the migration_thread, if the curr
			 * task on busiest cpu can't be moved to this_cpu
			 */
			if (!cpu_isset(this_cpu, busiest->curr->cpus_allowed)) {
				spin_unlock_irqrestore(&busiest->lock, flags);
				all_pinned = 1;
				goto out_one_pinned;
			}

			if (!busiest->active_balance) {
				busiest->active_balance = 1;
				busiest->push_cpu = this_cpu;
				active_balance = 1;
			}
			spin_unlock_irqrestore(&busiest->lock, flags);
			if (active_balance)
				wake_up_process(busiest->migration_thread);

			/*
			 * We've kicked active balancing, reset the failure
			 * counter.
			 */
			sd->nr_balance_failed = sd->cache_nice_tries+1;
		}
	} else
		sd->nr_balance_failed = 0;

	if (likely(!active_balance)) {
		/* We were unbalanced, so reset the balancing interval */
		sd->balance_interval = sd->min_interval;
	} else {
		/*
		 * If we've begun active balancing, start to back off. This
		 * case may not be covered by the all_pinned logic if there
		 * is only 1 task on the busy runqueue (because we don't call
		 * move_tasks).
		 */
		if (sd->balance_interval < sd->max_interval)
			sd->balance_interval *= 2;
	}

	if (!nr_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
		return -1;
	return nr_moved;

out_balanced:
	schedstat_inc(sd, lb_balanced[idle]);

	sd->nr_balance_failed = 0;

out_one_pinned:
	/* tune up the balancing interval */
	if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
			(sd->balance_interval < sd->max_interval))
		sd->balance_interval *= 2;

	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
		return -1;
	return 0;
}

/*
 * Check this_cpu to ensure it is balanced within domain. Attempt to move
 * tasks if there is an imbalance.
 *
 * Called from schedule when this_rq is about to become idle (NEWLY_IDLE).
 * this_rq is locked.
 */
static int
load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
{
	struct sched_group *group;
	struct rq *busiest = NULL;
	unsigned long imbalance;
	int nr_moved = 0;
	int sd_idle = 0;
	cpumask_t cpus = CPU_MASK_ALL;

	/*
	 * When power savings policy is enabled for the parent domain, idle
	 * sibling can pick up load irrespective of busy siblings. In this case,
	 * let the state of idle sibling percolate up as IDLE, instead of
	 * portraying it as NOT_IDLE.
	 */
	if (sd->flags & SD_SHARE_CPUPOWER &&
	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
		sd_idle = 1;

	schedstat_inc(sd, lb_cnt[NEWLY_IDLE]);
redo:
	group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE,
				   &sd_idle, &cpus, NULL);
	if (!group) {
		schedstat_inc(sd, lb_nobusyg[NEWLY_IDLE]);
		goto out_balanced;
	}

	busiest = find_busiest_queue(group, NEWLY_IDLE, imbalance,
				&cpus);
	if (!busiest) {
		schedstat_inc(sd, lb_nobusyq[NEWLY_IDLE]);
		goto out_balanced;
	}

	BUG_ON(busiest == this_rq);

	schedstat_add(sd, lb_imbalance[NEWLY_IDLE], imbalance);

	nr_moved = 0;
	if (busiest->nr_running > 1) {
		/* Attempt to move tasks */
		double_lock_balance(this_rq, busiest);
		nr_moved = move_tasks(this_rq, this_cpu, busiest,
					minus_1_or_zero(busiest->nr_running),
					imbalance, sd, NEWLY_IDLE, NULL);
		spin_unlock(&busiest->lock);

		if (!nr_moved) {
			cpu_clear(cpu_of(busiest), cpus);
			if (!cpus_empty(cpus))
				goto redo;
		}
	}

	if (!nr_moved) {
		schedstat_inc(sd, lb_failed[NEWLY_IDLE]);
		if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
		    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
			return -1;
	} else
		sd->nr_balance_failed = 0;

	return nr_moved;

out_balanced:
	schedstat_inc(sd, lb_balanced[NEWLY_IDLE]);
	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
		return -1;
	sd->nr_balance_failed = 0;

	return 0;
}

/*
 * idle_balance is called by schedule() if this_cpu is about to become
 * idle. Attempts to pull tasks from other CPUs.
 */
static void idle_balance(int this_cpu, struct rq *this_rq)
{
	struct sched_domain *sd;
	int pulled_task = 0;
	unsigned long next_balance = jiffies + 60 *  HZ;

	for_each_domain(this_cpu, sd) {
		unsigned long interval;

		if (!(sd->flags & SD_LOAD_BALANCE))
			continue;

		if (sd->flags & SD_BALANCE_NEWIDLE)
			/* If we've pulled tasks over stop searching: */
			pulled_task = load_balance_newidle(this_cpu,
								this_rq, sd);

		interval = msecs_to_jiffies(sd->balance_interval);
		if (time_after(next_balance, sd->last_balance + interval))
			next_balance = sd->last_balance + interval;
		if (pulled_task)
			break;
	}
	if (!pulled_task)
		/*
		 * We are going idle. next_balance may be set based on
		 * a busy processor. So reset next_balance.
		 */
		this_rq->next_balance = next_balance;
}

/*
 * active_load_balance is run by migration threads. It pushes running tasks
 * off the busiest CPU onto idle CPUs. It requires at least 1 task to be
 * running on each physical CPU where possible, and avoids physical /
 * logical imbalances.
 *
 * Called with busiest_rq locked.
 */
static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
{
	int target_cpu = busiest_rq->push_cpu;
	struct sched_domain *sd;
	struct rq *target_rq;

	/* Is there any task to move? */
	if (busiest_rq->nr_running <= 1)
		return;

	target_rq = cpu_rq(target_cpu);

	/*
	 * This condition is "impossible", if it occurs
	 * we need to fix it.  Originally reported by
	 * Bjorn Helgaas on a 128-cpu setup.
	 */
	BUG_ON(busiest_rq == target_rq);

	/* move a task from busiest_rq to target_rq */
	double_lock_balance(busiest_rq, target_rq);

	/* Search for an sd spanning us and the target CPU. */
	for_each_domain(target_cpu, sd) {
		if ((sd->flags & SD_LOAD_BALANCE) &&
		    cpu_isset(busiest_cpu, sd->span))
				break;
	}

	if (likely(sd)) {
		schedstat_inc(sd, alb_cnt);

		if (move_tasks(target_rq, target_cpu, busiest_rq, 1,
			       RTPRIO_TO_LOAD_WEIGHT(100), sd, SCHED_IDLE,
			       NULL))
			schedstat_inc(sd, alb_pushed);
		else
			schedstat_inc(sd, alb_failed);
	}
	spin_unlock(&target_rq->lock);
}

static void update_load(struct rq *this_rq)
{
	unsigned long this_load;
	unsigned int i, scale;

	this_load = this_rq->raw_weighted_load;

	/* Update our load: */
	for (i = 0, scale = 1; i < 3; i++, scale += scale) {
		unsigned long old_load, new_load;

		/* scale is effectively 1 << i now, and >> i divides by scale */

		old_load = this_rq->cpu_load[i];
		new_load = this_load;
		/*
		 * Round up the averaging division if load is increasing. This
		 * prevents us from getting stuck on 9 if the load is 10, for
		 * example.
		 */
		if (new_load > old_load)
			new_load += scale-1;
		this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
	}
}

#ifdef CONFIG_NO_HZ
static struct {
	atomic_t load_balancer;
	cpumask_t  cpu_mask;
} nohz ____cacheline_aligned = {
	.load_balancer = ATOMIC_INIT(-1),
	.cpu_mask = CPU_MASK_NONE,
};

/*
 * This routine will try to nominate the ilb (idle load balancing)
 * owner among the cpus whose ticks are stopped. ilb owner will do the idle
 * load balancing on behalf of all those cpus. If all the cpus in the system
 * go into this tickless mode, then there will be no ilb owner (as there is
 * no need for one) and all the cpus will sleep till the next wakeup event
 * arrives...
 *
 * For the ilb owner, tick is not stopped. And this tick will be used
 * for idle load balancing. ilb owner will still be part of
 * nohz.cpu_mask..
 *
 * While stopping the tick, this cpu will become the ilb owner if there
 * is no other owner. And will be the owner till that cpu becomes busy
 * or if all cpus in the system stop their ticks at which point
 * there is no need for ilb owner.
 *
 * When the ilb owner becomes busy, it nominates another owner, during the
 * next busy scheduler_tick()
 */
int select_nohz_load_balancer(int stop_tick)
{
	int cpu = smp_processor_id();

	if (stop_tick) {
		cpu_set(cpu, nohz.cpu_mask);
		cpu_rq(cpu)->in_nohz_recently = 1;

		/*
		 * If we are going offline and still the leader, give up!
		 */
		if (cpu_is_offline(cpu) &&
		    atomic_read(&nohz.load_balancer) == cpu) {
			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
				BUG();
			return 0;
		}

		/* time for ilb owner also to sleep */
		if (cpus_weight(nohz.cpu_mask) == num_online_cpus()) {
			if (atomic_read(&nohz.load_balancer) == cpu)
				atomic_set(&nohz.load_balancer, -1);
			return 0;
		}

		if (atomic_read(&nohz.load_balancer) == -1) {
			/* make me the ilb owner */
			if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1)
				return 1;
		} else if (atomic_read(&nohz.load_balancer) == cpu)
			return 1;
	} else {
		if (!cpu_isset(cpu, nohz.cpu_mask))
			return 0;

		cpu_clear(cpu, nohz.cpu_mask);

		if (atomic_read(&nohz.load_balancer) == cpu)
			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
				BUG();
	}
	return 0;
}
#endif

static DEFINE_SPINLOCK(balancing);

/*
 * It checks each scheduling domain to see if it is due to be balanced,
 * and initiates a balancing operation if so.
 *
 * Balancing parameters are set up in arch_init_sched_domains.
 */
static inline void rebalance_domains(int cpu, enum idle_type idle)
{
	int balance = 1;
	struct rq *rq = cpu_rq(cpu);
	unsigned long interval;
	struct sched_domain *sd;
	/* Earliest time when we have to do rebalance again */
	unsigned long next_balance = jiffies + 60*HZ;

	for_each_domain(cpu, sd) {
		if (!(sd->flags & SD_LOAD_BALANCE))
			continue;

		interval = sd->balance_interval;
		if (idle != SCHED_IDLE)
			interval *= sd->busy_factor;

		/* scale ms to jiffies */
		interval = msecs_to_jiffies(interval);
		if (unlikely(!interval))
			interval = 1;

		if (sd->flags & SD_SERIALIZE) {
			if (!spin_trylock(&balancing))
				goto out;
		}

		if (time_after_eq(jiffies, sd->last_balance + interval)) {
			if (load_balance(cpu, rq, sd, idle, &balance)) {
				/*
				 * We've pulled tasks over so either we're no
				 * longer idle, or one of our SMT siblings is
				 * not idle.
				 */
				idle = NOT_IDLE;
			}
			sd->last_balance = jiffies;
		}
		if (sd->flags & SD_SERIALIZE)
			spin_unlock(&balancing);
out:
		if (time_after(next_balance, sd->last_balance + interval))
			next_balance = sd->last_balance + interval;

		/*
		 * Stop the load balance at this level. There is another
		 * CPU in our sched group which is doing load balancing more
		 * actively.
		 */
		if (!balance)
			break;
	}
	rq->next_balance = next_balance;
}

/*
 * run_rebalance_domains is triggered when needed from the scheduler tick.
 * In CONFIG_NO_HZ case, the idle load balance owner will do the
 * rebalancing for all the cpus for whom scheduler ticks are stopped.
 */
static void run_rebalance_domains(struct softirq_action *h)
{
	int local_cpu = smp_processor_id();
	struct rq *local_rq = cpu_rq(local_cpu);
	enum idle_type idle = local_rq->idle_at_tick ? SCHED_IDLE : NOT_IDLE;

	rebalance_domains(local_cpu, idle);

#ifdef CONFIG_NO_HZ
	/*
	 * If this cpu is the owner for idle load balancing, then do the
	 * balancing on behalf of the other idle cpus whose ticks are
	 * stopped.
	 */
	if (local_rq->idle_at_tick &&
	    atomic_read(&nohz.load_balancer) == local_cpu) {
		cpumask_t cpus = nohz.cpu_mask;
		struct rq *rq;
		int balance_cpu;

		cpu_clear(local_cpu, cpus);
		for_each_cpu_mask(balance_cpu, cpus) {
			/*
			 * If this cpu gets work to do, stop the load balancing
			 * work being done for other cpus. Next load
			 * balancing owner will pick it up.
			 */
			if (need_resched())
				break;

			rebalance_domains(balance_cpu, SCHED_IDLE);

			rq = cpu_rq(balance_cpu);
			if (time_after(local_rq->next_balance, rq->next_balance))
				local_rq->next_balance = rq->next_balance;
		}
	}
#endif
}

/*
 * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
 *
 * In case of CONFIG_NO_HZ, this is the place where we nominate a new
 * idle load balancing owner or decide to stop the periodic load balancing,
 * if the whole system is idle.
 */
static inline void trigger_load_balance(int cpu)
{
	struct rq *rq = cpu_rq(cpu);
#ifdef CONFIG_NO_HZ
	/*
	 * If we were in the nohz mode recently and busy at the current
	 * scheduler tick, then check if we need to nominate new idle
	 * load balancer.
	 */
	if (rq->in_nohz_recently && !rq->idle_at_tick) {
		rq->in_nohz_recently = 0;

		if (atomic_read(&nohz.load_balancer) == cpu) {
			cpu_clear(cpu, nohz.cpu_mask);
			atomic_set(&nohz.load_balancer, -1);
		}

		if (atomic_read(&nohz.load_balancer) == -1) {
			/*
			 * simple selection for now: Nominate the
			 * first cpu in the nohz list to be the next
			 * ilb owner.
			 *
			 * TBD: Traverse the sched domains and nominate
			 * the nearest cpu in the nohz.cpu_mask.
			 */
			int ilb = first_cpu(nohz.cpu_mask);

			if (ilb != NR_CPUS)
				resched_cpu(ilb);
		}
	}

	/*
	 * If this cpu is idle and doing idle load balancing for all the
	 * cpus with ticks stopped, is it time for that to stop?
	 */
	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu &&
	    cpus_weight(nohz.cpu_mask) == num_online_cpus()) {
		resched_cpu(cpu);
		return;
	}

	/*
	 * If this cpu is idle and the idle load balancing is done by
	 * someone else, then no need raise the SCHED_SOFTIRQ
	 */
	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu &&
	    cpu_isset(cpu, nohz.cpu_mask))
		return;
#endif
	if (time_after_eq(jiffies, rq->next_balance))
		raise_softirq(SCHED_SOFTIRQ);
}
#else
/*
 * on UP we do not need to balance between CPUs:
 */
static inline void idle_balance(int cpu, struct rq *rq)
{
}
#endif

DEFINE_PER_CPU(struct kernel_stat, kstat);

EXPORT_PER_CPU_SYMBOL(kstat);

/*
 * This is called on clock ticks and on context switches.
 * Bank in p->sched_time the ns elapsed since the last tick or switch.
 */
static inline void
update_cpu_clock(struct task_struct *p, struct rq *rq, unsigned long long now)
{
	p->sched_time += now - p->last_ran;
	p->last_ran = rq->most_recent_timestamp = now;
}

/*
 * Return current->sched_time plus any more ns on the sched_clock
 * that have not yet been banked.
 */
unsigned long long current_sched_time(const struct task_struct *p)
{
	unsigned long long ns;
	unsigned long flags;

	local_irq_save(flags);
	ns = p->sched_time + sched_clock() -