/*
 *  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
 *  2007-04-15  Work begun on replacing all interactivity tuning with a
 *              fair scheduling design by Con Kolivas.
 *  2007-05-05  Load balancing (smp-nice) and other improvements
 *              by Peter Williams
 *  2007-05-06  Interactivity improvements to CFS by Mike Galbraith
 *  2007-07-01  Group scheduling enhancements by Srivatsa Vaddagiri
 *  2007-11-29  RT balancing improvements by Steven Rostedt, Gregory Haskins,
 *              Thomas Gleixner, Mike Kravetz
 */

#include <linux/mm.h>
#include <linux/module.h>
#include <linux/nmi.h>
#include <linux/init.h>
#include <linux/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/pid_namespace.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/sysctl.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 <linux/unistd.h>
#include <linux/pagemap.h>
#include <linux/hrtimer.h>

#include <asm/tlb.h>
#include <asm/irq_regs.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 * (NSEC_PER_SEC / 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))

/*
 * Helpers for converting nanosecond timing to jiffy resolution
 */
#define NS_TO_JIFFIES(TIME)     ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))

#define NICE_0_LOAD             SCHED_LOAD_SCALE
#define NICE_0_SHIFT            SCHED_LOAD_SHIFT

/*
 * These are the 'tuning knobs' of the scheduler:
 *
 * default timeslice is 100 msecs (used only for SCHED_RR tasks).
 * Timeslices get refilled after they expire.
 */
#define DEF_TIMESLICE           (100 * HZ / 1000)

#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

static inline int rt_policy(int policy)
{
        if (unlikely(policy == SCHED_FIFO) || unlikely(policy == SCHED_RR))
                return 1;
        return 0;
}

static inline int task_has_rt_policy(struct task_struct *p)
{
        return rt_policy(p->policy);
}

/*
 * This is the priority-queue data structure of the RT scheduling class:
 */
struct rt_prio_array {
        DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */
        struct list_head queue[MAX_RT_PRIO];
};

#ifdef CONFIG_GROUP_SCHED

#include <linux/cgroup.h>

struct cfs_rq;

static LIST_HEAD(task_groups);

/* task group related information */
struct task_group {
#ifdef CONFIG_CGROUP_SCHED
        struct cgroup_subsys_state css;
#endif

#ifdef CONFIG_FAIR_GROUP_SCHED
        /* schedulable entities of this group on each cpu */
        struct sched_entity **se;
        /* runqueue "owned" by this group on each cpu */
        struct cfs_rq **cfs_rq;
        unsigned long shares;
#endif

#ifdef CONFIG_RT_GROUP_SCHED
        struct sched_rt_entity **rt_se;
        struct rt_rq **rt_rq;

        u64 rt_runtime;
#endif

        struct rcu_head rcu;
        struct list_head list;
};

#ifdef CONFIG_FAIR_GROUP_SCHED
/* Default task group's sched entity on each cpu */
static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
/* Default task group's cfs_rq on each cpu */
static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;

static struct sched_entity *init_sched_entity_p[NR_CPUS];
static struct cfs_rq *init_cfs_rq_p[NR_CPUS];
#endif

#ifdef CONFIG_RT_GROUP_SCHED
static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;

static struct sched_rt_entity *init_sched_rt_entity_p[NR_CPUS];
static struct rt_rq *init_rt_rq_p[NR_CPUS];
#endif

/* task_group_lock serializes add/remove of task groups and also changes to
 * a task group's cpu shares.
 */
static DEFINE_SPINLOCK(task_group_lock);

/* doms_cur_mutex serializes access to doms_cur[] array */
static DEFINE_MUTEX(doms_cur_mutex);

#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_USER_SCHED
# define INIT_TASK_GROUP_LOAD   (2*NICE_0_LOAD)
#else
# define INIT_TASK_GROUP_LOAD   NICE_0_LOAD
#endif

static int init_task_group_load = INIT_TASK_GROUP_LOAD;
#endif

/* Default task group.
 *      Every task in system belong to this group at bootup.
 */
struct task_group init_task_group = {
#ifdef CONFIG_FAIR_GROUP_SCHED
        .se     = init_sched_entity_p,
        .cfs_rq = init_cfs_rq_p,
#endif

#ifdef CONFIG_RT_GROUP_SCHED
        .rt_se  = init_sched_rt_entity_p,
        .rt_rq  = init_rt_rq_p,
#endif
};

/* return group to which a task belongs */
static inline struct task_group *task_group(struct task_struct *p)
{
        struct task_group *tg;

#ifdef CONFIG_USER_SCHED
        tg = p->user->tg;
#elif defined(CONFIG_CGROUP_SCHED)
        tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
                                struct task_group, css);
#else
        tg = &init_task_group;
#endif
        return tg;
}

/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
{
#ifdef CONFIG_FAIR_GROUP_SCHED
        p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
        p->se.parent = task_group(p)->se[cpu];
#endif

#ifdef CONFIG_RT_GROUP_SCHED
        p->rt.rt_rq  = task_group(p)->rt_rq[cpu];
        p->rt.parent = task_group(p)->rt_se[cpu];
#endif
}

static inline void lock_doms_cur(void)
{
        mutex_lock(&doms_cur_mutex);
}

static inline void unlock_doms_cur(void)
{
        mutex_unlock(&doms_cur_mutex);
}

#else

static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
static inline void lock_doms_cur(void) { }
static inline void unlock_doms_cur(void) { }

#endif  /* CONFIG_GROUP_SCHED */

/* CFS-related fields in a runqueue */
struct cfs_rq {
        struct load_weight load;
        unsigned long nr_running;

        u64 exec_clock;
        u64 min_vruntime;

        struct rb_root tasks_timeline;
        struct rb_node *rb_leftmost;
        struct rb_node *rb_load_balance_curr;
        /* 'curr' points to currently running entity on this cfs_rq.
         * It is set to NULL otherwise (i.e when none are currently running).
         */
        struct sched_entity *curr, *next;

        unsigned long nr_spread_over;

#ifdef CONFIG_FAIR_GROUP_SCHED
        struct rq *rq;  /* cpu runqueue to which this cfs_rq is attached */

        /*
         * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
         * a hierarchy). Non-leaf lrqs hold other higher schedulable entities
         * (like users, containers etc.)
         *
         * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
         * list is used during load balance.
         */
        struct list_head leaf_cfs_rq_list;
        struct task_group *tg;  /* group that "owns" this runqueue */
#endif
};

/* Real-Time classes' related field in a runqueue: */
struct rt_rq {
        struct rt_prio_array active;
        unsigned long rt_nr_running;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
        int highest_prio; /* highest queued rt task prio */
#endif
#ifdef CONFIG_SMP
        unsigned long rt_nr_migratory;
        int overloaded;
#endif
        int rt_throttled;
        u64 rt_time;

#ifdef CONFIG_RT_GROUP_SCHED
        unsigned long rt_nr_boosted;

        struct rq *rq;
        struct list_head leaf_rt_rq_list;
        struct task_group *tg;
        struct sched_rt_entity *rt_se;
#endif
};

#ifdef CONFIG_SMP

/*
 * We add the notion of a root-domain which will be used to define per-domain
 * variables. Each exclusive cpuset essentially defines an island domain by
 * fully partitioning the member cpus from any other cpuset. Whenever a new
 * exclusive cpuset is created, we also create and attach a new root-domain
 * object.
 *
 */
struct root_domain {
        atomic_t refcount;
        cpumask_t span;
        cpumask_t online;

        /*
         * The "RT overload" flag: it gets set if a CPU has more than
         * one runnable RT task.
         */
        cpumask_t rto_mask;
        atomic_t rto_count;
};

/*
 * By default the system creates a single root-domain with all cpus as
 * members (mimicking the global state we have today).
 */
static struct root_domain def_root_domain;

#endif

/*
 * 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 {
        /* runqueue lock: */
        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;
        #define CPU_LOAD_IDX_MAX 5
        unsigned long cpu_load[CPU_LOAD_IDX_MAX];
        unsigned char idle_at_tick;
#ifdef CONFIG_NO_HZ
        unsigned char in_nohz_recently;
#endif
        /* capture load from *all* tasks on this cpu: */
        struct load_weight load;
        unsigned long nr_load_updates;
        u64 nr_switches;

        struct cfs_rq cfs;
        struct rt_rq rt;
        u64 rt_period_expire;
        int rt_throttled;

#ifdef CONFIG_FAIR_GROUP_SCHED
        /* list of leaf cfs_rq on this cpu: */
        struct list_head leaf_cfs_rq_list;
#endif
#ifdef CONFIG_RT_GROUP_SCHED
        struct list_head leaf_rt_rq_list;
#endif

        /*
         * 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;

        struct task_struct *curr, *idle;
        unsigned long next_balance;
        struct mm_struct *prev_mm;

        u64 clock, prev_clock_raw;
        s64 clock_max_delta;

        unsigned int clock_warps, clock_overflows, clock_underflows;
        u64 idle_clock;
        unsigned int clock_deep_idle_events;
        u64 tick_timestamp;

        atomic_t nr_iowait;

#ifdef CONFIG_SMP
        struct root_domain *rd;
        struct sched_domain *sd;

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

        struct task_struct *migration_thread;
        struct list_head migration_queue;
#endif

#ifdef CONFIG_SCHED_HRTICK
        unsigned long hrtick_flags;
        ktime_t hrtick_expire;
        struct hrtimer hrtick_timer;
#endif

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

        /* sys_sched_yield() stats */
        unsigned int yld_exp_empty;
        unsigned int yld_act_empty;
        unsigned int yld_both_empty;
        unsigned int yld_count;

        /* schedule() stats */
        unsigned int sched_switch;
        unsigned int sched_count;
        unsigned int sched_goidle;

        /* try_to_wake_up() stats */
        unsigned int ttwu_count;
        unsigned int ttwu_local;

        /* BKL stats */
        unsigned int bkl_count;
#endif
        struct lock_class_key rq_lock_key;
};

static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);

static inline void check_preempt_curr(struct rq *rq, struct task_struct *p)
{
        rq->curr->sched_class->check_preempt_curr(rq, p);
}

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

/*
 * Update the per-runqueue clock, as finegrained as the platform can give
 * us, but without assuming monotonicity, etc.:
 */
static void __update_rq_clock(struct rq *rq)
{
        u64 prev_raw = rq->prev_clock_raw;
        u64 now = sched_clock();
        s64 delta = now - prev_raw;
        u64 clock = rq->clock;

#ifdef CONFIG_SCHED_DEBUG
        WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
#endif
        /*
         * Protect against sched_clock() occasionally going backwards:
         */
        if (unlikely(delta < 0)) {
                clock++;
                rq->clock_warps++;
        } else {
                /*
                 * Catch too large forward jumps too:
                 */
                if (unlikely(clock + delta > rq->tick_timestamp + TICK_NSEC)) {
                        if (clock < rq->tick_timestamp + TICK_NSEC)
                                clock = rq->tick_timestamp + TICK_NSEC;
                        else
                                clock++;
                        rq->clock_overflows++;
                } else {
                        if (unlikely(delta > rq->clock_max_delta))
                                rq->clock_max_delta = delta;
                        clock += delta;
                }
        }

        rq->prev_clock_raw = now;
        rq->clock = clock;
}

static void update_rq_clock(struct rq *rq)
{
        if (likely(smp_processor_id() == cpu_of(rq)))
                __update_rq_clock(rq);
}

/*
 * 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)

unsigned long rt_needs_cpu(int cpu)
{
        struct rq *rq = cpu_rq(cpu);
        u64 delta;

        if (!rq->rt_throttled)
                return 0;

        if (rq->clock > rq->rt_period_expire)
                return 1;

        delta = rq->rt_period_expire - rq->clock;
        do_div(delta, NSEC_PER_SEC / HZ);

        return (unsigned long)delta;
}

/*
 * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
 */
#ifdef CONFIG_SCHED_DEBUG
# define const_debug __read_mostly
#else
# define const_debug static const
#endif

/*
 * Debugging: various feature bits
 */
enum {
        SCHED_FEAT_NEW_FAIR_SLEEPERS    = 1,
        SCHED_FEAT_WAKEUP_PREEMPT       = 2,
        SCHED_FEAT_START_DEBIT          = 4,
        SCHED_FEAT_HRTICK               = 8,
        SCHED_FEAT_DOUBLE_TICK          = 16,
};

const_debug unsigned int sysctl_sched_features =
                SCHED_FEAT_NEW_FAIR_SLEEPERS    * 1 |
                SCHED_FEAT_WAKEUP_PREEMPT       * 1 |
                SCHED_FEAT_START_DEBIT          * 1 |
                SCHED_FEAT_HRTICK               * 1 |
                SCHED_FEAT_DOUBLE_TICK          * 0;

#define sched_feat(x) (sysctl_sched_features & SCHED_FEAT_##x)

/*
 * Number of tasks to iterate in a single balance run.
 * Limited because this is done with IRQs disabled.
 */
const_debug unsigned int sysctl_sched_nr_migrate = 32;

/*
 * period over which we measure -rt task cpu usage in us.
 * default: 1s
 */
unsigned int sysctl_sched_rt_period = 1000000;

static __read_mostly int scheduler_running;

/*
 * part of the period that we allow rt tasks to run in us.
 * default: 0.95s
 */
int sysctl_sched_rt_runtime = 950000;

/*
 * single value that denotes runtime == period, ie unlimited time.
 */
#define RUNTIME_INF     ((u64)~0ULL)

/*
 * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
 * clock constructed from sched_clock():
 */
unsigned long long cpu_clock(int cpu)
{
        unsigned long long now;
        unsigned long flags;
        struct rq *rq;

        /*
         * Only call sched_clock() if the scheduler has already been
         * initialized (some code might call cpu_clock() very early):
         */
        if (unlikely(!scheduler_running))
                return 0;

        local_irq_save(flags);
        rq = cpu_rq(cpu);
        update_rq_clock(rq);
        now = rq->clock;
        local_irq_restore(flags);

        return now;
}
EXPORT_SYMBOL_GPL(cpu_clock);

#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

static inline int task_current(struct rq *rq, struct task_struct *p)
{
        return rq->curr == p;
}

#ifndef __ARCH_WANT_UNLOCKED_CTXSW
static inline int task_running(struct rq *rq, struct task_struct *p)
{
        return task_current(rq, 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 task_current(rq, 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)
{
        for (;;) {
                struct rq *rq = task_rq(p);
                spin_lock(&rq->lock);
                if (likely(rq == task_rq(p)))
                        return rq;
                spin_unlock(&rq->lock);
        }
}

/*
 * 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;

        for (;;) {
                local_irq_save(*flags);
                rq = task_rq(p);
                spin_lock(&rq->lock);
                if (likely(rq == task_rq(p)))
                        return rq;
                spin_unlock_irqrestore(&rq->lock, *flags);
        }
}

static 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);
}

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

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

        return rq;
}

/*
 * We are going deep-idle (irqs are disabled):
 */
void sched_clock_idle_sleep_event(void)
{
        struct rq *rq = cpu_rq(smp_processor_id());

        spin_lock(&rq->lock);
        __update_rq_clock(rq);
        spin_unlock(&rq->lock);
        rq->clock_deep_idle_events++;
}
EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);

/*
 * We just idled delta nanoseconds (called with irqs disabled):
 */
void sched_clock_idle_wakeup_event(u64 delta_ns)
{
        struct rq *rq = cpu_rq(smp_processor_id());
        u64 now = sched_clock();

        rq->idle_clock += delta_ns;
        /*
         * Override the previous timestamp and ignore all
         * sched_clock() deltas that occured while we idled,
         * and use the PM-provided delta_ns to advance the
         * rq clock:
         */
        spin_lock(&rq->lock);
        rq->prev_clock_raw = now;
        rq->clock += delta_ns;
        spin_unlock(&rq->lock);
        touch_softlockup_watchdog();
}
EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);

static void __resched_task(struct task_struct *p, int tif_bit);

static inline void resched_task(struct task_struct *p)
{
        __resched_task(p, TIF_NEED_RESCHED);
}

#ifdef CONFIG_SCHED_HRTICK
/*
 * Use HR-timers to deliver accurate preemption points.
 *
 * Its all a bit involved since we cannot program an hrt while holding the
 * rq->lock. So what we do is store a state in in rq->hrtick_* and ask for a
 * reschedule event.
 *
 * When we get rescheduled we reprogram the hrtick_timer outside of the
 * rq->lock.
 */
static inline void resched_hrt(struct task_struct *p)
{
        __resched_task(p, TIF_HRTICK_RESCHED);
}

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

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

enum {
        HRTICK_SET,             /* re-programm hrtick_timer */
        HRTICK_RESET,           /* not a new slice */
        HRTICK_BLOCK,           /* stop hrtick operations */
};

/*
 * Use hrtick when:
 *  - enabled by features
 *  - hrtimer is actually high res
 */
static inline int hrtick_enabled(struct rq *rq)
{
        if (!sched_feat(HRTICK))
                return 0;
        if (unlikely(test_bit(HRTICK_BLOCK, &rq->hrtick_flags)))
                return 0;
        return hrtimer_is_hres_active(&rq->hrtick_timer);
}

/*
 * Called to set the hrtick timer state.
 *
 * called with rq->lock held and irqs disabled
 */
static void hrtick_start(struct rq *rq, u64 delay, int reset)
{
        assert_spin_locked(&rq->lock);

        /*
         * preempt at: now + delay
         */
        rq->hrtick_expire =
                ktime_add_ns(rq->hrtick_timer.base->get_time(), delay);
        /*
         * indicate we need to program the timer
         */
        __set_bit(HRTICK_SET, &rq->hrtick_flags);
        if (reset)
                __set_bit(HRTICK_RESET, &rq->hrtick_flags);

        /*
         * New slices are called from the schedule path and don't need a
         * forced reschedule.
         */
        if (reset)
                resched_hrt(rq->curr);
}

static void hrtick_clear(struct rq *rq)
{
        if (hrtimer_active(&rq->hrtick_timer))
                hrtimer_cancel(&rq->hrtick_timer);
}

/*
 * Update the timer from the possible pending state.
 */
static void hrtick_set(struct rq *rq)
{
        ktime_t time;
        int set, reset;
        unsigned long flags;

        WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());

        spin_lock_irqsave(&rq->lock, flags);
        set = __test_and_clear_bit(HRTICK_SET, &rq->hrtick_flags);
        reset = __test_and_clear_bit(HRTICK_RESET, &rq->hrtick_flags);
        time = rq->hrtick_expire;
        clear_thread_flag(TIF_HRTICK_RESCHED);
        spin_unlock_irqrestore(&rq->lock, flags);

        if (set) {
                hrtimer_start(&rq->hrtick_timer, time, HRTIMER_MODE_ABS);
                if (reset && !hrtimer_active(&rq->hrtick_timer))
                        resched_rq(rq);
        } else
                hrtick_clear(rq);
}

/*
 * High-resolution timer tick.
 * Runs from hardirq context with interrupts disabled.
 */
static enum hrtimer_restart hrtick(struct hrtimer *timer)
{
        struct rq *rq = container_of(timer, struct rq, hrtick_timer);

        WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());

        spin_lock(&rq->lock);
        __update_rq_clock(rq);
        rq->curr->sched_class->task_tick(rq, rq->curr, 1);
        spin_unlock(&rq->lock);

        return HRTIMER_NORESTART;
}

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

        spin_lock_irqsave(&rq->lock, flags);
        rq->hrtick_flags = 0;
        __set_bit(HRTICK_BLOCK, &rq->hrtick_flags);
        spin_unlock_irqrestore(&rq->lock, flags);

        hrtick_clear(rq);
}

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

        spin_lock_irqsave(&rq->lock, flags);
        __clear_bit(HRTICK_BLOCK, &rq->hrtick_flags);
        spin_unlock_irqrestore(&rq->lock, flags);
}

static int
hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu)
{

        int cpu = (int)(long)hcpu;

        switch (action) {
        case CPU_UP_CANCELED:
        case CPU_UP_CANCELED_FROZEN:
        case CPU_DOWN_PREPARE:
        case CPU_DOWN_PREPARE_FROZEN:
        case CPU_DEAD:
        case CPU_DEAD_FROZEN:
                hotplug_hrtick_disable(cpu);
                return NOTIFY_OK;

        case CPU_UP_PREPARE:
        case CPU_UP_PREPARE_FROZEN:
        case CPU_DOWN_FAILED:
        case CPU_DOWN_FAILED_FROZEN:
        case CPU_ONLINE:
        case CPU_ONLINE_FROZEN:
                hotplug_hrtick_enable(cpu);
                return NOTIFY_OK;
        }

        return NOTIFY_DONE;
}

static void init_hrtick(void)
{
        hotcpu_notifier(hotplug_hrtick, 0);
}

static void init_rq_hrtick(struct rq *rq)
{
        rq->hrtick_flags = 0;
        hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
        rq->hrtick_timer.function = hrtick;
        rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
}

void hrtick_resched(void)
{
        struct rq *rq;
        unsigned long flags;

        if (!test_thread_flag(TIF_HRTICK_RESCHED))
                return;

        local_irq_save(flags);
        rq = cpu_rq(smp_processor_id());
        hrtick_set(rq);
        local_irq_restore(flags);
}
#else
static inline void hrtick_clear(struct rq *rq)
{
}

static inline void hrtick_set(struct rq *rq)
{
}

static inline void init_rq_hrtick(struct rq *rq)
{
}

void hrtick_resched(void)
{
}

static inline void init_hrtick(void)
{
}
#endif

/*
 * 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 tif_bit)
{
        int cpu;

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

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

        set_tsk_thread_flag(p, tif_bit);

        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);
}

#ifdef CONFIG_NO_HZ
/*
 * When add_timer_on() enqueues a timer into the timer wheel of an
 * idle CPU then this timer might expire before the next timer event
 * which is scheduled to wake up that CPU. In case of a completely
 * idle system the next event might even be infinite time into the
 * future. wake_up_idle_cpu() ensures that the CPU is woken up and
 * leaves the inner idle loop so the newly added timer is taken into
 * account when the CPU goes back to idle and evaluates the timer
 * wheel for the next timer event.
 */
void wake_up_idle_cpu(int cpu)
{
        struct rq *rq = cpu_rq(cpu);

        if (cpu == smp_processor_id())
                return;

        /*
         * This is safe, as this function is called with the timer
         * wheel base lock of (cpu) held. When the CPU is on the way
         * to idle and has not yet set rq->curr to idle then it will
         * be serialized on the timer wheel base lock and take the new
         * timer into account automatically.
         */
        if (rq->curr != rq->idle)
                return;

        /*
         * We can set TIF_RESCHED on the idle task of the other CPU
         * lockless. The worst case is that the other CPU runs the
         * idle task through an additional NOOP schedule()
         */
        set_tsk_thread_flag(rq->idle, TIF_NEED_RESCHED);

        /* NEED_RESCHED must be visible before we test polling */
        smp_mb();
        if (!tsk_is_polling(rq->idle))
                smp_send_reschedule(cpu);
}
#endif

#else
static void __resched_task(struct task_struct *p, int tif_bit)
{
        assert_spin_locked(&task_rq(p)->lock);
        set_tsk_thread_flag(p, tif_bit);
}
#endif

#if BITS_PER_LONG == 32
# define WMULT_CONST    (~0UL)
#else
# define WMULT_CONST    (1UL << 32)
#endif

#define WMULT_SHIFT     32

/*
 * Shift right and round:
 */
#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))

static unsigned long
calc_delta_mine(unsigned long delta_exec, unsigned long weight,
                struct load_weight *lw)
{
        u64 tmp;

        if (unlikely(!lw->inv_weight))
                lw->inv_weight = (WMULT_CONST-lw->weight/2) / (lw->weight+1);

        tmp = (u64)delta_exec * weight;
        /*
         * Check whether we'd overflow the 64-bit multiplication:
         */
        if (unlikely(tmp > WMULT_CONST))
                tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
                        WMULT_SHIFT/2);
        else
                tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);

        return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
}

static inline unsigned long
calc_delta_fair(unsigned long delta_exec, struct load_weight *lw)
{
        return calc_delta_mine(delta_exec, NICE_0_LOAD, lw);
}

static inline void update_load_add(struct load_weight *lw, unsigned long inc)
{
        lw->weight += inc;
        lw->inv_weight = 0;
}

static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
{
        lw->weight -= dec;
        lw->inv_weight = 0;
}

/*
 * 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.
 */

#define WEIGHT_IDLEPRIO         2
#define WMULT_IDLEPRIO          (1 << 31)

/*
 * Nice levels are multiplicative, with a gentle 10% change for every
 * nice level changed. I.e. when a CPU-bound task goes from nice 0 to
 * nice 1, it will get ~10% less CPU time than another CPU-bound task
 * that remained on nice 0.
 *
 * The "10% effect" is relative and cumulative: from _any_ nice level,
 * if you go up 1 level, it's -10% CPU usage, if you go down 1 level
 * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
 * If a task goes up by ~10% and another task goes down by ~10% then
 * the relative distance between them is ~25%.)
 */
static const int prio_to_weight[40] = {
 /* -20 */     88761,     71755,     56483,     46273,     36291,
 /* -15 */     29154,     23254,     18705,     14949,     11916,
 /* -10 */      9548,      7620,      6100,      4904,      3906,
 /*  -5 */      3121,      2501,      1991,      1586,      1277,
 /*   0 */      1024,       820,       655,       526,       423,
 /*   5 */       335,       272,       215,       172,       137,
 /*  10 */       110,        87,        70,        56,        45,
 /*  15 */        36,        29,        23,        18,        15,
};

/*
 * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated.
 *
 * In cases where the weight does not change often, we can use the
 * precalculated inverse to speed up arithmetics by turning divisions
 * into multiplications:
 */
static const u32 prio_to_wmult[40] = {
 /* -20 */     48388,     59856,     76040,     92818,    118348,
 /* -15 */    147320,    184698,    229616,    287308,    360437,
 /* -10 */    449829,    563644,    704093,    875809,   1099582,
 /*  -5 */   1376151,   1717300,   2157191,   2708050,   3363326,
 /*   0 */   4194304,   5237765,   6557202,   8165337,  10153587,
 /*   5 */  12820798,  15790321,  19976592,  24970740,  31350126,
 /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
 /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
};

static void activate_task(struct rq *rq, struct task_struct *p, int wakeup);

/*
 * runqueue iterator, to support SMP load-balancing between different
 * scheduling classes, without having to expose their internal data
 * structures to the load-balancing proper:
 */
struct rq_iterator {
        void *arg;
        struct task_struct *(*start)(void *);
        struct task_struct *(*next)(void *);
};

#ifdef CONFIG_SMP
static unsigned long
balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
              unsigned long max_load_move, struct sched_domain *sd,
              enum cpu_idle_type idle, int *all_pinned,
              int *this_best_prio, struct rq_iterator *iterator);

static int
iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
                   struct sched_domain *sd, enum cpu_idle_type idle,
                   struct rq_iterator *iterator);
#endif

#ifdef CONFIG_CGROUP_CPUACCT
static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
#else
static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
#endif

#ifdef CONFIG_SMP
static unsigned long source_load(int cpu, int type);
static unsigned long target_load(int cpu, int type);
static unsigned long cpu_avg_load_per_task(int cpu);
static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
#endif /* CONFIG_SMP */

#include "sched_stats.h"
#include "sched_idletask.c"
#include "sched_fair.c"
#include "sched_rt.c"
#ifdef CONFIG_SCHED_DEBUG
# include "sched_debug.c"
#endif

#define sched_class_highest (&rt_sched_class)

static inline void inc_load(struct rq *rq, const struct task_struct *p)
{
        update_load_add(&rq->load, p->se.load.weight);
}

static inline void dec_load(struct rq *rq, const struct task_struct *p)
{
        update_load_sub(&rq->load, p->se.load.weight);
}

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

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

static void set_load_weight(struct task_struct *p)
{
        if (task_has_rt_policy(p)) {
                p->se.load.weight = prio_to_weight[0] * 2;
                p->se.load.inv_weight = prio_to_wmult[0] >> 1;
                return;
        }

        /*
         * SCHED_IDLE tasks get minimal weight:
         */
        if (p->policy == SCHED_IDLE) {
                p->se.load.weight = WEIGHT_IDLEPRIO;
                p->se.load.inv_weight = WMULT_IDLEPRIO;
                return;
        }

        p->se.load.weight = prio_to_weight[p->static_prio - MAX_RT_PRIO];
        p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO];
}

static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
{
        sched_info_queued(p);
        p->sched_class->enqueue_task(rq, p, wakeup);
        p->se.on_rq = 1;
}

static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
{
        p->sched_class->dequeue_task(rq, p, sleep);
        p->se.on_rq = 0;
}

/*
 * __normal_prio - return the priority that is based on the static prio
 */
static inline int __normal_prio(struct task_struct *p)
{
        return p->static_prio;
}

/*
 * 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 (task_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 rq *rq, struct task_struct *p, int wakeup)
{
        if (task_contributes_to_load(p))
                rq->nr_uninterruptible--;

        enqueue_task(rq, p, wakeup);
        inc_nr_running(p, rq);
}

/*
 * deactivate_task - remove a task from the runqueue.
 */
static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
{
        if (task_contributes_to_load(p))
                rq->nr_uninterruptible++;

        dequeue_task(rq, p, sleep);
        dec_nr_running(p, rq);
}

/**
 * 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)->load.weight;
}

static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
{
        set_task_rq(p, cpu);
#ifdef CONFIG_SMP
        /*
         * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
         * successfuly executed on another CPU. We must ensure that updates of
         * per-task data have been completed by this moment.
         */
        smp_wmb();
        task_thread_info(p)->cpu = cpu;
#endif
}

static inline void check_class_changed(struct rq *rq, struct task_struct *p,
                                       const struct sched_class *prev_class,
                                       int oldprio, int running)
{
        if (prev_class != p->sched_class) {
                if (prev_class->switched_from)
                        prev_class->switched_from(rq, p, running);
                p->sched_class->switched_to(rq, p, running);
        } else
                p->sched_class->prio_changed(rq, p, oldprio, running);
}

#ifdef CONFIG_SMP

/*
 * Is this task likely cache-hot:
 */
static int
task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
{
        s64 delta;

        /*
         * Buddy candidates are cache hot:
         */
        if (&p->se == cfs_rq_of(&p->se)->next)
                return 1;

        if (p->sched_class != &fair_sched_class)
                return 0;

        if (sysctl_sched_migration_cost == -1)
                return 1;
        if (sysctl_sched_migration_cost == 0)
                return 0;

        delta = now - p->se.exec_start;

        return delta < (s64)sysctl_sched_migration_cost;
}


void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
{
        int old_cpu = task_cpu(p);
        struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu);
        struct cfs_rq *old_cfsrq = task_cfs_rq(p),
                      *new_cfsrq = cpu_cfs_rq(old_cfsrq, new_cpu);
        u64 clock_offset;

        clock_offset = old_rq->clock - new_rq->clock;

#ifdef CONFIG_SCHEDSTATS
        if (p->se.wait_start)
                p->se.wait_start -= clock_offset;
        if (p->se.sleep_start)
                p->se.sleep_start -= clock_offset;
        if (p->se.block_start)
                p->se.block_start -= clock_offset;
        if (old_cpu != new_cpu) {
                schedstat_inc(p, se.nr_migrations);
                if (task_hot(p, old_rq->clock, NULL))
                        schedstat_inc(p, se.nr_forced2_migrations);
        }
#endif
        p->se.vruntime -= old_cfsrq->min_vruntime -
                                         new_cfsrq->min_vruntime;

        __set_task_cpu(p, new_cpu);
}

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->se.on_rq && !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;
        int running, on_rq;
        struct rq *rq;

        for (;;) {
                /*
                 * 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);
                on_rq = p->se.on_rq;
                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();
                        continue;
                }

                /*
                 * 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(on_rq)) {
                        schedule_timeout_uninterruptible(1);
                        continue;
                }

                /*
                 * 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!
                 */
                break;
        }
}

/***
 * 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 unsigned long source_load(int cpu, int type)
{
        struct rq *rq = cpu_rq(cpu);
        unsigned long total = weighted_cpuload(cpu);

        if (type == 0)
                return total;

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

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

        if (type == 0)
                return total;

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

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

        return n ? total / 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))
                        continue;

                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;
                }
        } while (group = group->next, 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 */

/***
 * 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, orig_cpu, this_cpu, success = 0;
        unsigned long flags;
        long old_state;
        struct rq *rq;

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

        if (p->se.on_rq)
                goto out_running;

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

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

        cpu = p->sched_class->select_task_rq(p, sync);
        if (cpu != orig_cpu) {
                set_task_cpu(p, 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->se.on_rq)
                        goto out_running;

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

#ifdef CONFIG_SCHEDSTATS
        schedstat_inc(rq, ttwu_count);
        if (cpu == this_cpu)
                schedstat_inc(rq, ttwu_local);
        else {
                struct sched_domain *sd;
                for_each_domain(this_cpu, sd) {
                        if (cpu_isset(cpu, sd->span)) {
                                schedstat_inc(sd, ttwu_wake_remote);
                                break;
                        }
                }
        }
#endif

out_activate:
#endif /* CONFIG_SMP */
        schedstat_inc(p, se.nr_wakeups);
        if (sync)
                schedstat_inc(p, se.nr_wakeups_sync);
        if (orig_cpu != cpu)
                schedstat_inc(p, se.nr_wakeups_migrate);
        if (cpu == this_cpu)
                schedstat_inc(p, se.nr_wakeups_local);
        else
                schedstat_inc(p, se.nr_wakeups_remote);
        update_rq_clock(rq);
        activate_task(rq, p, 1);
        success = 1;

out_running:
        check_preempt_curr(rq, p);

        p->state = TASK_RUNNING;
#ifdef CONFIG_SMP
        if (p->sched_class->task_wake_up)
                p->sched_class->task_wake_up(rq, p);
#endif
out:
        task_rq_unlock(rq, &flags);

        return success;
}

int wake_up_process(struct task_struct *p)
{
        return try_to_wake_up(p, TASK_ALL, 0);
}
EXPORT_SYMBOL(wake_up_process);

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

/*
 * Perform scheduler related setup for a newly forked process p.
 * p is forked by current.
 *
 * __sched_fork() is basic setup used by init_idle() too:
 */
static void __sched_fork(struct task_struct *p)
{

        p->se.exec_start                = 0;
        p->se.sum_exec_runtime          = 0;
        p->se.prev_sum_exec_runtime     = 0;
        p->se.last_wakeup               = 0;
        p->se.avg_overlap               = 0;

#ifdef CONFIG_SCHEDSTATS
        p->se.wait_start                = 0;
        p->se.sum_sleep_runtime         = 0;
        p->se.sleep_start               = 0;
        p->se.block_start               = 0;
        p->se.sleep_max                 = 0;
        p->se.block_max                 = 0;
        p->se.exec_max                  = 0;
        p->se.slice_max                 = 0;
        p->se.wait_max                  = 0;
#endif

        INIT_LIST_HEAD(&p->rt.run_list);
        p->se.on_rq = 0;

#ifdef CONFIG_PREEMPT_NOTIFIERS
        INIT_HLIST_HEAD(&p->preempt_notifiers);
#endif

        /*
         * 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;
}

/*
 * fork()/clone()-time setup:
 */
void sched_fork(struct task_struct *p, int clone_flags)
{
        int cpu = get_cpu();

        __sched_fork(p);

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

        /*
         * Make sure we do not leak PI boosting priority to the child:
         */
        p->prio = current->normal_prio;
        if (!rt_prio(p->prio))
                p->sched_class = &fair_sched_class;

#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
        if (likely(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
        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 wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
{
        unsigned long flags;
        struct rq *rq;

        rq = task_rq_lock(p, &flags);
        BUG_ON(p->state != TASK_RUNNING);
        update_rq_clock(rq);

        p->prio = effective_prio(p);

        if (!p->sched_class->task_new || !current->se.on_rq) {
                activate_task(rq, p, 0);
        } else {
                /*
                 * Let the scheduling class do new task startup
                 * management (if any):
                 */
                p->sched_class->task_new(rq, p);
                inc_nr_running(p, rq);
        }
        check_preempt_curr(rq, p);
#ifdef CONFIG_SMP
        if (p->sched_class->task_wake_up)
                p->sched_class->task_wake_up(rq, p);
#endif
        task_rq_unlock(rq, &flags);
}

#ifdef CONFIG_PREEMPT_NOTIFIERS

/**
 * preempt_notifier_register - tell me when current is being being preempted & rescheduled
 * @notifier: notifier struct to register
 */
void preempt_notifier_register(struct preempt_notifier *notifier)
{
        hlist_add_head(&notifier->link, &current->preempt_notifiers);
}
EXPORT_SYMBOL_GPL(preempt_notifier_register);

/**
 * preempt_notifier_unregister - no longer interested in preemption notifications
 * @notifier: notifier struct to unregister
 *
 * This is safe to call from within a preemption notifier.
 */
void preempt_notifier_unregister(struct preempt_notifier *notifier)
{
        hlist_del(&notifier->link);
}
EXPORT_SYMBOL_GPL(preempt_notifier_unregister);

static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
        struct preempt_notifier *notifier;
        struct hlist_node *node;

        hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
                notifier->ops->sched_in(notifier, raw_smp_processor_id());
}

static void
fire_sched_out_preempt_notifiers(struct task_struct *curr,
                                 struct task_struct *next)
{
        struct preempt_notifier *notifier;
        struct hlist_node *node;

        hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
                notifier->ops->sched_out(notifier, next);
}

#else

static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
}

static void
fire_sched_out_preempt_notifiers(struct task_struct *curr,
                                 struct task_struct *next)
{
}

#endif

/**
 * prepare_task_switch - prepare to switch tasks
 * @rq: the runqueue preparing to switch
 * @prev: the current task that is being switched out
 * @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 *prev,
                    struct task_struct *next)
{
        fire_sched_out_preempt_notifiers(prev, 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 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);
#ifdef CONFIG_SMP
        if (current->sched_class->post_schedule)
                current->sched_class->post_schedule(rq);
#endif

        fire_sched_in_preempt_notifiers(current);
        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(task_pid_vnr(current), current->set_child_tid);
}

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

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

        if (unlikely(!prev->mm)) {
                prev->active_mm = NULL;
                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);

        barrier();
        /*
         * this_rq must be evaluated again because prev may have moved
         * CPUs since it called schedule(), thus the 'rq' on its stack
         * frame will be invalid.
         */
        finish_task_switch(this_rq(), 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;
}

/*
 * Update rq->cpu_load[] statistics. This function is usually called every
 * scheduler tick (TICK_NSEC).
 */
static void update_cpu_load(struct rq *this_rq)
{
        unsigned long this_load = this_rq->load.weight;
        int i, scale;

        this_rq->nr_load_updates++;

        /* Update our load: */
        for (i = 0, scale = 1; i < CPU_LOAD_IDX_MAX; 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_SMP

/*
 * 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);
                }
        }
        update_rq_clock(rq1);
        update_rq_clock(rq2);
}

/*
 * 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 int double_lock_balance(struct rq *this_rq, struct rq *busiest)
        __releases(this_rq->lock)
        __acquires(busiest->lock)
        __acquires(this_rq->lock)
{
        int ret = 0;

        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);
                        ret = 1;
                } else
                        spin_lock(&busiest->lock);
        }
        return ret;
}

/*
 * 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 task_struct *p,
                      struct rq *this_rq, int this_cpu)
{
        deactivate_task(src_rq, p, 0);
        set_task_cpu(p, this_cpu);
        activate_task(this_rq, p, 0);
        /*
         * Note that idle threads have a prio of MAX_PRIO, for this test
         * to be always true for them.
         */
        check_preempt_curr(this_rq, p);
}

/*
 * 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 cpu_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)) {
                schedstat_inc(p, se.nr_failed_migrations_affine);
                return 0;
        }
        *all_pinned = 0;

        if (task_running(rq, p)) {
                schedstat_inc(p, se.nr_failed_migrations_running);
                return 0;
        }

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

        if (!task_hot(p, rq->clock, sd) ||
                        sd->nr_balance_failed > sd->cache_nice_tries) {
#ifdef CONFIG_SCHEDSTATS
                if (task_hot(p, rq->clock, sd)) {
                        schedstat_inc(sd, lb_hot_gained[idle]);
                        schedstat_inc(p, se.nr_forced_migrations);
                }
#endif
                return 1;
        }

        if (task_hot(p, rq->clock, sd)) {
                schedstat_inc(p, se.nr_failed_migrations_hot);
                return 0;
        }
        return 1;
}

static unsigned long
balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
              unsigned long max_load_move, struct sched_domain *sd,
              enum cpu_idle_type idle, int *all_pinned,
              int *this_best_prio, struct rq_iterator *iterator)
{
        int loops = 0, pulled = 0, pinned = 0, skip_for_load;
        struct task_struct *p;
        long rem_load_move = max_load_move;

        if (max_load_move == 0)
                goto out;

        pinned = 1;

        /*
         * Start the load-balancing iterator:
         */
        p = iterator->start(iterator->arg);
next:
        if (!p || loops++ > sysctl_sched_nr_migrate)
                goto out;
        /*
         * To help distribute high priority tasks across 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 = (p->se.load.weight >> 1) > rem_load_move +
                                                         SCHED_LOAD_SCALE_FUZZ;
        if ((skip_for_load && p->prio >= *this_best_prio) ||
            !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
                p = iterator->next(iterator->arg);
                goto next;
        }

        pull_task(busiest, p, this_rq, this_cpu);
        pulled++;
        rem_load_move -= p->se.load.weight;

        /*
         * We only want to steal up to the prescribed amount of weighted load.
         */
        if (rem_load_move > 0) {
                if (p->prio < *this_best_prio)
                        *this_best_prio = p->prio;
                p = iterator->next(iterator->arg);
                goto next;
        }
out:
        /*
         * Right now, this is one of only two places 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 max_load_move - rem_load_move;
}

/*
 * move_tasks tries to move up to max_load_move weighted load from busiest to
 * this_rq, as part of a balancing operation within domain "sd".
 * Returns 1 if successful and 0 otherwise.
 *
 * Called with both runqueues locked.
 */
static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
                      unsigned long max_load_move,
                      struct sched_domain *sd, enum cpu_idle_type idle,
                      int *all_pinned)
{
        const struct sched_class *class = sched_class_highest;
        unsigned long total_load_moved = 0;
        int this_best_prio = this_rq->curr->prio;

        do {
                total_load_moved +=
                        class->load_balance(this_rq, this_cpu, busiest,
                                max_load_move - total_load_moved,
                                sd, idle, all_pinned, &this_best_prio);
                class = class->next;
        } while (class && max_load_move > total_load_moved);

        return total_load_moved > 0;
}

static int
iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
                   struct sched_domain *sd, enum cpu_idle_type idle,
                   struct rq_iterator *iterator)
{
        struct task_struct *p = iterator->start(iterator->arg);
        int pinned = 0;

        while (p) {
                if (can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
                        pull_task(busiest, p, this_rq, this_cpu);
                        /*
                         * Right now, this is only the second place pull_task()
                         * is called, so we can safely collect pull_task()
                         * stats here rather than inside pull_task().
                         */
                        schedstat_inc(sd, lb_gained[idle]);

                        return 1;
                }
                p = iterator->next(iterator->arg);
        }

        return 0;
}

/*
 * move_one_task tries to move exactly one task from busiest to this_rq, as
 * part of active balancing operations within "domain".
 * Returns 1 if successful and 0 otherwise.
 *
 * Called with both runqueues locked.
 */
static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
                         struct sched_domain *sd, enum cpu_idle_type idle)
{
        const struct sched_class *class;

        for (class = sched_class_highest; class; class = class->next)
                if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle))
                        return 1;

        return 0;
}

/*
 * 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 cpu_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, group_imb = 0;
#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 == CPU_NOT_IDLE)
                load_idx = sd->busy_idx;
        else if (idle == CPU_NEWLY_IDLE)
                load_idx = sd->newidle_idx;
        else
                load_idx = sd->idle_idx;

        do {
                unsigned long load, group_capacity, max_cpu_load, min_cpu_load;
                int local_group;
                int i;
                int __group_imb = 0;
                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;
                max_cpu_load = 0;
                min_cpu_load = ~0UL;

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

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

                        rq = cpu_rq(i);

                        if (*sd_idle && rq->nr_running)
                                *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);
                                if (load > max_cpu_load)
                                        max_cpu_load = load;
                                if (min_cpu_load > load)
                                        min_cpu_load = load;
                        }

                        avg_load += load;
                        sum_nr_running += rq->nr_running;
                        sum_weighted_load += weighted_cpuload(i);
                }

                /*
                 * First idle cpu or the first cpu(busiest) in this sched group
                 * is eligible for doing load balancing at this and above
                 * domains. In the newly idle case, we will allow all the cpu's
                 * to do the newly idle load balance.
                 */
                if (idle != CPU_NEWLY_IDLE && 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);

                if ((max_cpu_load - min_cpu_load) > SCHED_LOAD_SCALE)
                        __group_imb = 1;

                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 || __group_imb)) {
                        max_load = avg_load;
                        busiest = group;
                        busiest_nr_running = sum_nr_running;
                        busiest_load_per_task = sum_weighted_load;
                        group_imb = __group_imb;
                }

#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
                /*
                 * Busy processors will not participate in power savings
                 * balance.
                 */
                if (idle == CPU_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;
        if (group_imb)
                busiest_load_per_task = min(busiest_load_per_task, avg_load);

        /*
         * 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 + SCHED_LOAD_SCALE_FUZZ >=
                                        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);