/*
 *  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 <linux/pagemap.h>
#include <asm/mmu_context.h>
#include <linux/interrupt.h>
#include <linux/completion.h>
#include <linux/kernel_stat.h>
#include <linux/security.h>
#include <linux/notifier.h>
#include <linux/profile.h>
#include <linux/suspend.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
#include <linux/smp.h>
#include <linux/timer.h>
#include <linux/rcupdate.h>
#include <linux/cpu.h>
#include <linux/percpu.h>
#include <linux/kthread.h>
#include <linux/seq_file.h>
#include <linux/times.h>
#include <linux/kprobes.h>
#include <asm/tlb.h>

#include <asm/unistd.h>

#ifdef CONFIG_NUMA
#define cpu_to_node_mask(cpu) node_to_cpumask(cpu_to_node(cpu))
#else
#define cpu_to_node_mask(cpu) (cpu_online_map)
#endif

/*
 * 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))

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

/*
 * 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))
#define CREDIT_LIMIT            100

/*
 * 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)

#ifdef CONFIG_SMP
#define TIMESLICE_GRANULARITY(p)        (MIN_TIMESLICE * \
                (1 << (((MAX_BONUS - CURRENT_BONUS(p)) ? : 1) - 1)) * \
                        num_online_cpus())
#else
#define TIMESLICE_GRANULARITY(p)        (MIN_TIMESLICE * \
                (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), 40, MAX_BONUS) + 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 HIGH_CREDIT(p) \
        ((p)->interactive_credit > CREDIT_LIMIT)

#define LOW_CREDIT(p) \
        ((p)->interactive_credit < -CREDIT_LIMIT)

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

/*
 * 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.
 */

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

static unsigned int task_timeslice(task_t *p)
{
        if (p->static_prio < NICE_TO_PRIO(0))
                return SCALE_PRIO(DEF_TIMESLICE*4, p->static_prio);
        else
                return SCALE_PRIO(DEF_TIMESLICE, p->static_prio);
}
#define task_hot(p, now, sd) ((long long) ((now) - (p)->last_ran)       \
                                < (long long) (sd)->cache_hot_time)

enum idle_type
{
        IDLE,
        NOT_IDLE,
        NEWLY_IDLE,
        MAX_IDLE_TYPES
};

struct sched_domain;

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

#define BITMAP_SIZE ((((MAX_PRIO+1+7)/8)+sizeof(long)-1)/sizeof(long))

typedef struct runqueue runqueue_t;

struct prio_array {
        unsigned int nr_active;
        unsigned long bitmap[BITMAP_SIZE];
        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 runqueue {
        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;
#ifdef CONFIG_SMP
        unsigned long cpu_load;
        unsigned int irq_pct;
        int irq_quantum;
        u64 prev_irq_ticks;
#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 switch_timestamp;
        unsigned long long timestamp_last_tick;
        task_t *curr, *idle;
        struct mm_struct *prev_mm;
        prio_array_t *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;

        task_t *migration_thread;
        struct list_head migration_queue;
        int cpu;
#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_noswitch;
        unsigned long sched_switch;
        unsigned long sched_cnt;
        unsigned long sched_goidle;

        /* pull_task() stats */
        unsigned long pt_gained[MAX_IDLE_TYPES];
        unsigned long pt_lost[MAX_IDLE_TYPES];

        /* active_load_balance() stats */
        unsigned long alb_cnt;
        unsigned long alb_lost;
        unsigned long alb_gained;
        unsigned long alb_failed;

        /* try_to_wake_up() stats */
        unsigned long ttwu_cnt;
        unsigned long ttwu_attempts;
        unsigned long ttwu_moved;

        /* wake_up_new_task() stats */
        unsigned long wunt_cnt;
        unsigned long wunt_moved;

        /* sched_migrate_task() stats */
        unsigned long smt_cnt;

        /* sched_balance_exec() stats */
        unsigned long sbe_cnt;
#endif
};

static DEFINE_PER_CPU(struct runqueue, runqueues);

/*
 * sched-domains (multiprocessor balancing) declarations:
 */
#ifdef CONFIG_SMP
#define SCHED_LOAD_SCALE        128UL   /* increase resolution of load */

#define SD_BALANCE_NEWIDLE      1       /* Balance when about to become idle */
#define SD_BALANCE_EXEC         2       /* Balance on exec */
#define SD_WAKE_IDLE            4       /* Wake to idle CPU on task wakeup */
#define SD_WAKE_AFFINE          8       /* Wake task to waking CPU */
#define SD_WAKE_BALANCE         16      /* Perform balancing at task wakeup */
#define SD_SHARE_CPUPOWER       32      /* Domain members share cpu power */

struct sched_group {
        struct sched_group *next;       /* Must be a circular list */
        cpumask_t cpumask;

        /*
         * CPU power of this group, SCHED_LOAD_SCALE being max power for a
         * single CPU. This is read only (except for setup, hotplug CPU).
         */
        unsigned long cpu_power;
};

struct sched_domain {
        /* These fields must be setup */
        struct sched_domain *parent;    /* top domain must be null terminated */
        struct sched_group *groups;     /* the balancing groups of the domain */
        cpumask_t span;                 /* span of all CPUs in this domain */
        unsigned long min_interval;     /* Minimum balance interval ms */
        unsigned long max_interval;     /* Maximum balance interval ms */
        unsigned int busy_factor;       /* less balancing by factor if busy */
        unsigned int imbalance_pct;     /* No balance until over watermark */
        unsigned long long cache_hot_time; /* Task considered cache hot (ns) */
        unsigned int cache_nice_tries;  /* Leave cache hot tasks for # tries */
        unsigned int per_cpu_gain;      /* CPU % gained by adding domain cpus */
        int flags;                      /* See SD_* */

        /* Runtime fields. */
        unsigned long last_balance;     /* init to jiffies. units in jiffies */
        unsigned int balance_interval;  /* initialise to 1. units in ms. */
        unsigned int nr_balance_failed; /* initialise to 0 */

#ifdef CONFIG_SCHEDSTATS
        /* load_balance() stats */
        unsigned long lb_cnt[MAX_IDLE_TYPES];
        unsigned long lb_failed[MAX_IDLE_TYPES];
        unsigned long lb_imbalance[MAX_IDLE_TYPES];
        unsigned long lb_nobusyg[MAX_IDLE_TYPES];
        unsigned long lb_nobusyq[MAX_IDLE_TYPES];

        /* sched_balance_exec() stats */
        unsigned long sbe_attempts;
        unsigned long sbe_pushed;

        /* try_to_wake_up() stats */
        unsigned long ttwu_wake_affine;
        unsigned long ttwu_wake_balance;
#endif
};

#ifndef ARCH_HAS_SCHED_TUNE
#ifdef CONFIG_SCHED_SMT
#define ARCH_HAS_SCHED_WAKE_IDLE
/* Common values for SMT siblings */
#define SD_SIBLING_INIT (struct sched_domain) {         \
        .span                   = CPU_MASK_NONE,        \
        .parent                 = NULL,                 \
        .groups                 = NULL,                 \
        .min_interval           = 1,                    \
        .max_interval           = 2,                    \
        .busy_factor            = 8,                    \
        .imbalance_pct          = 110,                  \
        .cache_hot_time         = 0,                    \
        .cache_nice_tries       = 0,                    \
        .per_cpu_gain           = 25,                   \
        .flags                  = SD_BALANCE_NEWIDLE    \
                                | SD_BALANCE_EXEC       \
                                | SD_WAKE_AFFINE        \
                                | SD_WAKE_IDLE          \
                                | SD_SHARE_CPUPOWER,    \
        .last_balance           = jiffies,              \
        .balance_interval       = 1,                    \
        .nr_balance_failed      = 0,                    \
}
#endif

/* Common values for CPUs */
#define SD_CPU_INIT (struct sched_domain) {             \
        .span                   = CPU_MASK_NONE,        \
        .parent                 = NULL,                 \
        .groups                 = NULL,                 \
        .min_interval           = 1,                    \
        .max_interval           = 4,                    \
        .busy_factor            = 64,                   \
        .imbalance_pct          = 125,                  \
        .cache_hot_time         = cache_decay_ticks*1000000 ? : (5*1000000/2),\
        .cache_nice_tries       = 1,                    \
        .per_cpu_gain           = 100,                  \
        .flags                  = SD_BALANCE_NEWIDLE    \
                                | SD_BALANCE_EXEC       \
                                | SD_WAKE_AFFINE        \
                                | SD_WAKE_BALANCE,      \
        .last_balance           = jiffies,              \
        .balance_interval       = 1,                    \
        .nr_balance_failed      = 0,                    \
}

#ifdef CONFIG_SCHED_MC
#ifndef SD_MC_INIT
/* for now its same as SD_CPU_INIT.
 * TBD: Tune Domain parameters!
 */
#define SD_MC_INIT   SD_CPU_INIT
#endif
#endif

/* Arch can override this macro in processor.h */
#if defined(CONFIG_NUMA) && !defined(SD_NODE_INIT)
#define SD_NODE_INIT (struct sched_domain) {            \
        .span                   = CPU_MASK_NONE,        \
        .parent                 = NULL,                 \
        .groups                 = NULL,                 \
        .min_interval           = 8,                    \
        .max_interval           = 32,                   \
        .busy_factor            = 32,                   \
        .imbalance_pct          = 125,                  \
        .cache_hot_time         = (10*1000000),         \
        .cache_nice_tries       = 1,                    \
        .per_cpu_gain           = 100,                  \
        .flags                  = SD_BALANCE_EXEC       \
                                | SD_WAKE_BALANCE,      \
        .last_balance           = jiffies,              \
        .balance_interval       = 1,                    \
        .nr_balance_failed      = 0,                    \
}
#endif
#endif /* ARCH_HAS_SCHED_TUNE */
#endif


#define for_each_domain(cpu, domain) \
        for (domain = cpu_rq(cpu)->sd; domain; domain = domain->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)

/*
 * Default context-switch locking:
 */
#ifndef prepare_arch_switch
# define prepare_arch_switch(rq, next)  do { } while (0)
# define finish_arch_switch(rq, next)   spin_unlock_irq(&(rq)->lock)
# define task_running(rq, p)            ((rq)->curr == (p))
#endif

/*
 * 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 inline runqueue_t *task_rq_lock(task_t *p, unsigned long *flags)
{
        struct runqueue *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(runqueue_t *rq, unsigned long *flags)
{
        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 10

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

        seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
        seq_printf(seq, "timestamp %lu\n", jiffies);
        for_each_online_cpu(cpu) {
                runqueue_t *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 "
                    "%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_noswitch,
                    rq->sched_switch, rq->sched_cnt, rq->sched_goidle,
                    rq->alb_cnt, rq->alb_gained, rq->alb_lost,
                    rq->alb_failed,
                    rq->ttwu_cnt, rq->ttwu_moved, rq->ttwu_attempts,
                    rq->wunt_cnt, rq->wunt_moved,
                    rq->smt_cnt, rq->sbe_cnt, rq->rq_sched_info.cpu_time,
                    rq->rq_sched_info.run_delay, rq->rq_sched_info.pcnt);

                for (itype = IDLE; itype < MAX_IDLE_TYPES; itype++)
                        seq_printf(seq, " %lu %lu", rq->pt_gained[itype],
                                                    rq->pt_lost[itype]);
                seq_printf(seq, "\n");

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

                        cpumask_scnprintf(mask_str, NR_CPUS, sd->span);
                        seq_printf(seq, "domain%d %s", dcnt++, mask_str);
                        for (itype = IDLE; itype < MAX_IDLE_TYPES; itype++) {
                                seq_printf(seq, " %lu %lu %lu %lu %lu",
                                    sd->lb_cnt[itype],
                                    sd->lb_failed[itype],
                                    sd->lb_imbalance[itype],
                                    sd->lb_nobusyq[itype],
                                    sd->lb_nobusyg[itype]);
                        }
                        seq_printf(seq, " %lu %lu %lu %lu\n",
                            sd->sbe_pushed, sd->sbe_attempts,
                            sd->ttwu_wake_affine, sd->ttwu_wake_balance);
                }
#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;
}

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

# define schedstat_inc(rq, field)       rq->field++;
# define schedstat_add(rq, field, amt)  rq->field += amt;
#else /* !CONFIG_SCHEDSTATS */
# define schedstat_inc(rq, field)       do { } while (0);
# define schedstat_add(rq, field, amt)  do { } while (0);
#endif

/*
 * rq_lock - lock a given runqueue and disable interrupts.
 */
static inline runqueue_t *this_rq_lock(void)
{
        runqueue_t *rq;

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

        return rq;
}

static inline void rq_unlock(runqueue_t *rq)
{
        spin_unlock_irq(&rq->lock);
}

#ifdef CONFIG_SCHEDSTATS
/*
 * 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(task_t *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 inline void sched_info_arrive(task_t *t)
{
        unsigned long now = jiffies, diff = 0;
        struct runqueue *rq = task_rq(t);

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

        if (!rq)
                return;

        rq->rq_sched_info.run_delay += diff;
        rq->rq_sched_info.pcnt++;
}

/*
 * 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(task_t *t)
{
        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(task_t *t)
{
        struct runqueue *rq = task_rq(t);
        unsigned long diff = jiffies - t->sched_info.last_arrival;

        t->sched_info.cpu_time += diff;

        if (rq)
                rq->rq_sched_info.cpu_time += diff;
}

/*
 * 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(task_t *prev, task_t *next)
{
        struct runqueue *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);
}
#else
#define sched_info_queued(t)            do { } while (0)
#define sched_info_switch(t, next)      do { } while (0)
#endif /* CONFIG_SCHEDSTATS */

/*
 * Adding/removing a task to/from a priority array:
 */
static void dequeue_task(struct task_struct *p, prio_array_t *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, prio_array_t *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;
}

/*
 * Used by the migration code - we pull tasks from the head of the
 * remote queue so we want these tasks to show up at the head of the
 * local queue:
 */
static inline void enqueue_task_head(struct task_struct *p, prio_array_t *array)
{
        list_add(&p->run_list, array->queue + p->prio);
        __set_bit(p->prio, array->bitmap);
        array->nr_active++;
        p->array = array;
}

/*
 * effective_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 int effective_prio(task_t *p)
{
        int bonus, prio;

        if (rt_task(p))
                return p->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;
}

/*
 * __activate_task - move a task to the runqueue.
 */
static inline void __activate_task(task_t *p, runqueue_t *rq)
{
        enqueue_task(p, rq->active);
        rq->nr_running++;
}

/*
 * __activate_idle_task - move idle task to the _front_ of runqueue.
 */
static inline void __activate_idle_task(task_t *p, runqueue_t *rq)
{
        enqueue_task_head(p, rq->active);
        rq->nr_running++;
}

static void recalc_task_prio(task_t *p, unsigned long long now)
{
        unsigned long long __sleep_time = now - p->timestamp;
        unsigned long sleep_time;

        if (__sleep_time > NS_MAX_SLEEP_AVG)
                sleep_time = NS_MAX_SLEEP_AVG;
        else
                sleep_time = (unsigned long)__sleep_time;

        if (likely(sleep_time > 0)) {
                /*
                 * User tasks that sleep a long time are categorised as
                 * idle and will get just interactive status to stay active &
                 * prevent them suddenly becoming cpu hogs and starving
                 * other processes.
                 */
                if (p->mm && p->activated != -1 &&
                        sleep_time > INTERACTIVE_SLEEP(p)) {
                                p->sleep_avg = JIFFIES_TO_NS(MAX_SLEEP_AVG -
                                                DEF_TIMESLICE);
                                if (!HIGH_CREDIT(p))
                                        p->interactive_credit++;
                } else {
                        /*
                         * The lower the sleep avg a task has the more
                         * rapidly it will rise with sleep time.
                         */
                        sleep_time *= (MAX_BONUS - CURRENT_BONUS(p)) ? : 1;

                        /*
                         * Tasks with low interactive_credit are limited to
                         * one timeslice worth of sleep avg bonus.
                         */
                        if (LOW_CREDIT(p) &&
                            sleep_time > JIFFIES_TO_NS(task_timeslice(p)))
                                sleep_time = JIFFIES_TO_NS(task_timeslice(p));

                        /*
                         * Non high_credit tasks waking from uninterruptible
                         * sleep are limited in their sleep_avg rise as they
                         * are likely to be cpu hogs waiting on I/O
                         */
                        if (p->activated == -1 && !HIGH_CREDIT(p) && p->mm) {
                                if (p->sleep_avg >= INTERACTIVE_SLEEP(p))
                                        sleep_time = 0;
                                else if (p->sleep_avg + sleep_time >=
                                                INTERACTIVE_SLEEP(p)) {
                                        p->sleep_avg = INTERACTIVE_SLEEP(p);
                                        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;
                                if (!HIGH_CREDIT(p))
                                        p->interactive_credit++;
                        }
                }
        }

        p->prio = 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(task_t *p, runqueue_t *rq, int local)
{
        unsigned long long now;

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

        recalc_task_prio(p, now);

        /*
         * This checks to make sure it's not an uninterruptible task
         * that is now waking up.
         */
        if (!p->activated) {
                /*
                 * 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->activated = 2;
                else {
                        /*
                         * Normal first-time wakeups get a credit too for
                         * on-runqueue time, but it will be weighted down:
                         */
                        p->activated = 1;
                }
        }
        p->timestamp = now;

        __activate_task(p, rq);
}

/*
 * deactivate_task - remove a task from the runqueue.
 */
static void deactivate_task(struct task_struct *p, runqueue_t *rq)
{
        rq->nr_running--;
        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
static void resched_task(task_t *p)
{
        int need_resched, nrpolling;

        BUG_ON(!spin_is_locked(&task_rq(p)->lock));

        /* minimise the chance of sending an interrupt to poll_idle() */
        nrpolling = test_tsk_thread_flag(p,TIF_POLLING_NRFLAG);
        need_resched = test_and_set_tsk_thread_flag(p,TIF_NEED_RESCHED);
        nrpolling |= test_tsk_thread_flag(p,TIF_POLLING_NRFLAG);

        if (!need_resched && !nrpolling && (task_cpu(p) != smp_processor_id()))
                smp_send_reschedule(task_cpu(p));
}
#else
static inline void resched_task(task_t *p)
{
        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 task_t *p)
{
        return cpu_curr(task_cpu(p)) == p;
}

int wake_balance=1;

#ifdef CONFIG_SMP

#define LOWLAT_ENABLED()                (wake_balance == 2)

enum request_type {
        REQ_MOVE_TASK,
        REQ_SET_DOMAIN,
};

typedef struct {
        struct list_head list;
        enum request_type type;

        /* For REQ_MOVE_TASK */
        task_t *task;
        int dest_cpu;

        /* For REQ_SET_DOMAIN */
        struct sched_domain *sd;

        struct completion done;
} migration_req_t;

/*
 * The task's runqueue lock must be held.
 * Returns true if you have to wait for migration thread.
 */

static int migrate_task(task_t *p, int dest_cpu, migration_req_t *req)
{
        runqueue_t *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->type = REQ_MOVE_TASK;
        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(task_t * p)
{
        unsigned long flags;
        runqueue_t *rq;
        int preempted;

repeat:
        rq = task_rq_lock(p, &flags);
        /* Must be off runqueue entirely, not preempted. */
        if (unlikely(p->array || task_running(rq, p))) {
                /* If it's preempted, we yield.  It could be a while. */
                preempted = !task_running(rq, p);
                task_rq_unlock(rq, &flags);
                cpu_relax();
                if (preempted)
                        yield();
                goto repeat;
        }
        task_rq_unlock(rq, &flags);
}

/***
 * 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.)
 */
void kick_process(task_t *p)
{
        int cpu;

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

static unsigned long current_load(runqueue_t *rq)
{
        unsigned long load = rq->nr_running * SCHED_LOAD_SCALE;

        if (LOWLAT_ENABLED())
                load += (SCHED_LOAD_SCALE * rq->irq_pct) / 100;
        return load;
}

/*
 * Return a low guess at the load of a migration-source cpu.
 *
 * We want to under-estimate the load of migration sources, to
 * balance conservatively.
 */
static inline unsigned long source_load(int cpu)
{
        runqueue_t *rq = cpu_rq(cpu);

        return min(rq->cpu_load, current_load(rq));
}

/*
 * Return a high guess at the load of a migration-target cpu
 */
static inline unsigned long target_load(int cpu)
{
        runqueue_t *rq = cpu_rq(cpu);

        return max(rq->cpu_load, current_load(rq));
}

#endif

/*
 * wake_idle() is useful especially on SMT architectures to wake a
 * task onto an idle sibling if we would otherwise wake it onto a
 * busy sibling.
 *
 * Returns the CPU we should wake onto.
 */
#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
static int wake_idle(int cpu, task_t *p)
{
        cpumask_t tmp;
        runqueue_t *rq = cpu_rq(cpu);
        struct sched_domain *sd;
        int i;
        unsigned long load = current_load(rq) + SCHED_LOAD_SCALE;

        if (LOWLAT_ENABLED()) {
                if (idle_cpu(cpu))
                        load -= SCHED_LOAD_SCALE;
                if (load <= SCHED_LOAD_SCALE)
                        return cpu;
        } else if (idle_cpu(cpu)) {
                return cpu;
        }

        sd = rq->sd;
        if (!(sd->flags & SD_WAKE_IDLE) && !LOWLAT_ENABLED())
                return cpu;

        cpus_and(tmp, sd->span, p->cpus_allowed);

        for_each_cpu_mask(i, tmp) {
                if (LOWLAT_ENABLED()) {
                        unsigned long l = current_load(cpu_rq(i))
                                                        + SCHED_LOAD_SCALE;

                        if (idle_cpu(i))
                                l -= SCHED_LOAD_SCALE;
                        if (l <= SCHED_LOAD_SCALE)
                                return i;
                        if (l < load) {
                                cpu = i;
                                load = l;
                        }
                } else if (idle_cpu(i)) {
                        return i;
                }
        }

        return cpu;
}
#else
static inline int wake_idle(int cpu, task_t *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(task_t * p, unsigned int state, int sync)
{
        int cpu, this_cpu, success = 0;
        unsigned long flags;
        long old_state;
        runqueue_t *rq;
#ifdef CONFIG_SMP
        unsigned long load, this_load;
        struct sched_domain *sd;
        int new_cpu;
#endif

        rq = task_rq_lock(p, &flags);
        schedstat_inc(rq, ttwu_cnt);
        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;

        if (!wake_balance)
                goto out_set_cpu;

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

        load = source_load(cpu);
        this_load = target_load(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)
                this_load -= SCHED_LOAD_SCALE;

        /* Don't pull the task off an idle CPU to a busy one */
        if (load < SCHED_LOAD_SCALE/2 && this_load > SCHED_LOAD_SCALE/2)
                goto out_set_cpu;

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

        /*
         * Scan domains for affine wakeup and passive balancing
         * possibilities.
         */
        for_each_domain(this_cpu, sd) {
                unsigned int imbalance;
                /*
                 * Start passive balancing when half the imbalance_pct
                 * limit is reached.
                 */
                imbalance = sd->imbalance_pct + (sd->imbalance_pct - 100) / 2;

                if ((sd->flags & SD_WAKE_AFFINE) &&
                                !task_hot(p, rq->timestamp_last_tick, sd)) {
                        /*
                         * This domain has SD_WAKE_AFFINE and p is cache cold
                         * in this domain.
                         */
                        if (cpu_isset(cpu, sd->span)) {
                                schedstat_inc(sd, ttwu_wake_affine);
                                goto out_set_cpu;
                        }
                } else if ((sd->flags & SD_WAKE_BALANCE) &&
                                imbalance*this_load <= 100*load) {
                        /*
                         * This domain has SD_WAKE_BALANCE and there is
                         * an imbalance.
                         */
                        if (cpu_isset(cpu, sd->span)) {
                                schedstat_inc(sd, ttwu_wake_balance);
                                goto out_set_cpu;
                        }
                }
        }

        new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
out_set_cpu:
        schedstat_inc(rq, ttwu_attempts);
        new_cpu = wake_idle(new_cpu, p);
        if (new_cpu != cpu && cpu_isset(new_cpu, p->cpus_allowed)) {
                schedstat_inc(rq, ttwu_moved);
                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->activated = -1;
        }

        /*
         * 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.)
         */
        activate_task(p, rq, cpu == 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(task_t * 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(task_t *p, unsigned int state)
{
        return try_to_wake_up(p, state, 0);
}

#ifdef CONFIG_SMP
static int find_idlest_cpu(struct task_struct *p, int this_cpu,
                           struct sched_domain *sd);
#endif

/*
 * Perform scheduler related setup for a newly forked process p.
 * p is forked by current.
 */
void fastcall sched_fork(task_t *p)
{
        /*
         * 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;
        INIT_LIST_HEAD(&p->run_list);
        p->array = NULL;
        spin_lock_init(&p->switch_lock);
#ifdef CONFIG_SCHEDSTATS
        memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
#ifdef CONFIG_PREEMPT
        /*
         * During context-switch we hold precisely one spinlock, which
         * schedule_tail drops. (in the common case it's this_rq()->lock,
         * but it also can be p->switch_lock.) So we compensate with a count
         * of 1. Also, we want to start with kernel preemption disabled.
         */
        p->thread_info->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 creator if the child exits early enough.
         */
        p->first_time_slice = current->pid;
        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;
                preempt_disable();
                scheduler_tick(0, 0);
                local_irq_enable();
                preempt_enable();
        } else
                local_irq_enable();
}

/*
 * 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(task_t * p, unsigned long clone_flags)
{
        unsigned long flags;
        int this_cpu, cpu;
        runqueue_t *rq, *this_rq;

        rq = task_rq_lock(p, &flags);
        cpu = task_cpu(p);
        this_cpu = smp_processor_id();

        BUG_ON(p->state != TASK_RUNNING);

        schedstat_inc(rq, wunt_cnt);
        /*
         * 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->interactive_credit = 0;

        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;
                                list_add_tail(&p->run_list, &current->run_list);
                                p->array = current->array;
                                p->array->nr_active++;
                                rq->nr_running++;
                        }
                        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->timestamp_last_tick)
                                        + rq->timestamp_last_tick;
                __activate_task(p, rq);
                if (TASK_PREEMPTS_CURR(p, rq))
                        resched_task(rq->curr);

                schedstat_inc(rq, wunt_moved);
                /*
                 * 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 creator 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(task_t * p)
{
        unsigned long flags;
        runqueue_t *rq;
        struct task_struct* creator = NULL;

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

                        if (p->sleep_avg < creator->sleep_avg)
                                creator->sleep_avg = creator->sleep_avg /
                (EXIT_WEIGHT + 1) * EXIT_WEIGHT + p->sleep_avg /
                (EXIT_WEIGHT + 1);
        task_rq_unlock(rq, &flags);
                }
        }
}

/**
 * finish_task_switch - clean up after a task-switch
 * @prev: the thread we just switched away from.
 *
 * We enter this with the runqueue still locked, and finish_arch_switch()
 * will unlock it along with doing 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(task_t *prev)
{
        runqueue_t *rq = this_rq();
        struct mm_struct *mm = rq->prev_mm;
        unsigned long prev_task_flags;

        rq->prev_mm = NULL;

        /*
         * A task struct has one reference for the use as "current".
         * If a task dies, then it sets EXIT_ZOMBIE in tsk->exit_state and
         * calls schedule one last time. The schedule call will never return,
         * and the scheduled task must drop that reference.
         * The test for EXIT_ZOMBIE 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_task_flags = prev->flags;
        finish_arch_switch(rq, prev);
        if (mm)
                mmdrop(mm);
        if (unlikely(prev_task_flags & PF_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(task_t *prev)
{
        finish_task_switch(prev);

        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
task_t * context_switch(runqueue_t *rq, task_t *prev, task_t *next)
{
        struct mm_struct *mm = next->mm;
        struct mm_struct *oldmm = prev->active_mm;

        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;
                WARN_ON(rq->prev_mm);
                rq->prev_mm = oldmm;
        }

        /* 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_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)
{
        unsigned long long i, sum = 0;

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

        return sum;
}

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

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

        return sum;
}

/* cpus with isolated domains */
cpumask_t __devinitdata cpu_isolated_map = CPU_MASK_NONE;

#ifdef CONFIG_SMP

/*
 * double_rq_lock - safely lock two runqueues
 *
 * We must take them in cpu order to match code in
 * dependent_sleeper and wake_dependent_sleeper.
 *
 * Note this does not disable interrupts like task_rq_lock,
 * you need to do so manually before calling.
 */
static void double_rq_lock(runqueue_t *rq1, runqueue_t *rq2)
{
        if (rq1 == rq2)
                spin_lock(&rq1->lock);
        else {
                if (rq1->cpu < rq2->cpu) {
                        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(runqueue_t *rq1, runqueue_t *rq2)
{
        spin_unlock(&rq1->lock);
        if (rq1 != rq2)
                spin_unlock(&rq2->lock);
}

/*
 * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
 */
static void double_lock_balance(runqueue_t *this_rq, runqueue_t *busiest)
{
        if (unlikely(!spin_trylock(&busiest->lock))) {
                if (busiest->cpu < this_rq->cpu) {
                        spin_unlock(&this_rq->lock);
                        spin_lock(&busiest->lock);
                        spin_lock(&this_rq->lock);
                } else
                        spin_lock(&busiest->lock);
        }
}

/*
 * find_idlest_cpu - find the least busy runqueue.
 */
static int find_idlest_cpu(struct task_struct *p, int this_cpu,
                           struct sched_domain *sd)
{
        unsigned long load, min_load, this_load;
        int i, min_cpu;
        cpumask_t mask;

        min_cpu = UINT_MAX;
        min_load = ULONG_MAX;

        cpus_and(mask, sd->span, p->cpus_allowed);

        for_each_cpu_mask(i, mask) {
                load = target_load(i);

                if (load < min_load) {
                        min_cpu = i;
                        min_load = load;

                        /* break out early on an idle CPU: */
                        if (!min_load)
                                break;
                }
        }

        /* add +1 to account for the new task */
        this_load = source_load(this_cpu) + SCHED_LOAD_SCALE;

        /*
         * Would with the addition of the new task to the
         * current CPU there be an imbalance between this
         * CPU and the idlest CPU?
         *
         * Use half of the balancing threshold - new-context is
         * a good opportunity to balance.
         */
        if (min_load*(100 + (sd->imbalance_pct-100)/2) < this_load*100)
                return min_cpu;

        return this_cpu;
}

/*
 * 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(task_t *p, int dest_cpu)
{
        migration_req_t req;
        runqueue_t *rq;
        unsigned long flags;

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

        schedstat_inc(rq, smt_cnt);
        /* 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(): find the highest-level, exec-balance-capable
 * domain and try to migrate the task to the least loaded CPU.
 *
 * execve() is a valuable balancing opportunity, because at this point
 * the task has the smallest effective memory and cache footprint.
 */
void sched_exec(void)
{
        struct sched_domain *tmp, *sd = NULL;
        int new_cpu, this_cpu = get_cpu();

        schedstat_inc(this_rq(), sbe_cnt);
        /* Prefer the current CPU if there's only this task running */
        if (this_rq()->nr_running <= 1)
                goto out;

        for_each_domain(this_cpu, tmp)
                if (tmp->flags & SD_BALANCE_EXEC)
                        sd = tmp;

        if (sd) {
                schedstat_inc(sd, sbe_attempts);
                new_cpu = find_idlest_cpu(current, this_cpu, sd);
                if (new_cpu != this_cpu) {
                        schedstat_inc(sd, sbe_pushed);
                        put_cpu();
                        sched_migrate_task(current, new_cpu);
                        return;
                }
        }
out:
        put_cpu();
}

/*
 * pull_task - move a task from a remote runqueue to the local runqueue.
 * Both runqueues must be locked.
 */
static inline
void pull_task(runqueue_t *src_rq, prio_array_t *src_array, task_t *p,
               runqueue_t *this_rq, prio_array_t *this_array, int this_cpu)
{
        dequeue_task(p, src_array);
        src_rq->nr_running--;
        set_task_cpu(p, this_cpu);
        this_rq->nr_running++;
        enqueue_task(p, this_array);
        p->timestamp = (p->timestamp - src_rq->timestamp_last_tick)
                                + this_rq->timestamp_last_tick;
        /*
         * 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 inline
int can_migrate_task(task_t *p, runqueue_t *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 (task_running(rq, p))
                return 0;
        if (!cpu_isset(this_cpu, p->cpus_allowed))
                return 0;

        *all_pinned = 0;

        /* Aggressive migration if we've failed balancing */
        if (idle == NEWLY_IDLE ||
                        sd->nr_balance_failed < sd->cache_nice_tries) {
                if (task_hot(p, rq->timestamp_last_tick, sd))
                        return 0;
        }

        return 1;
}

/*
 * move_tasks tries to move up to max_nr_move tasks 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(runqueue_t *this_rq, int this_cpu, runqueue_t *busiest,
                      unsigned long max_nr_move, struct sched_domain *sd,
                      enum idle_type idle, int *all_pinned)
{
        prio_array_t *array, *dst_array;
        struct list_head *head, *curr;
        int idx, pulled = 0, pinned = 0;
        task_t *tmp;

        if (max_nr_move <= 0 || busiest->nr_running <= 1)
                goto out;

        pinned=1;

        /*
         * 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, task_t, run_list);

        curr = curr->prev;

        if (!can_migrate_task(tmp, busiest, this_cpu, sd, idle, &pinned)) {
                if (curr != head)
                        goto skip_queue;
                idx++;
                goto skip_bitmap;
        }

        /*
         * 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_inc(this_rq, pt_gained[idle]);
        schedstat_inc(busiest, pt_lost[idle]);

        pull_task(busiest, array, tmp, this_rq, dst_array, this_cpu);
        pulled++;

        /* We only want to steal up to the prescribed number of tasks. */
        if (pulled < max_nr_move) {
                if (curr != head)
                        goto skip_queue;
                idx++;
                goto skip_bitmap;
        }
out:
        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 number of tasks 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)
{
        struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
        unsigned long max_load, avg_load, total_load, this_load, total_pwr;

        max_load = this_load = total_load = total_pwr = 0;

        do {
                unsigned long load;
                int local_group;
                int i, nr_cpus = 0;

                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 = target_load(i);
                        else
                                load = source_load(i);

                        nr_cpus++;

                        avg_load += load;
                }

                if (!nr_cpus)
                        goto nextgroup;

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

                /* Adjust by relative CPU power of the group */
                avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;

                if (local_group) {
                        this_load = avg_load;
                        this = group;
                        goto nextgroup;
                } else if (avg_load > max_load) {
                        max_load = avg_load;
                        busiest = group;
                }
nextgroup:
                group = group->next;
        } while (group != sd->groups);

        if (!busiest || this_load >= max_load)
                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;

        /*
         * 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.
         */
        *imbalance = min(max_load - avg_load, avg_load - this_load);

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

        if (*imbalance < SCHED_LOAD_SCALE - 1) {
                unsigned long pwr_now = 0, pwr_move = 0;
                unsigned long tmp;

                if (max_load - this_load >= SCHED_LOAD_SCALE*2) {
                        *imbalance = 1;
                        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(SCHED_LOAD_SCALE, max_load);
                pwr_now += this->cpu_power*min(SCHED_LOAD_SCALE, this_load);
                pwr_now /= SCHED_LOAD_SCALE;

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

                /* Amount of load we'd add */
                tmp = SCHED_LOAD_SCALE*SCHED_LOAD_SCALE/this->cpu_power;
                if (max_load < tmp)
                        tmp = max_load;
                pwr_move += this->cpu_power*min(SCHED_LOAD_SCALE, this_load + tmp);
                pwr_move /= SCHED_LOAD_SCALE;

                /* Move if we gain another 8th of a CPU worth of throughput */
                if (pwr_move < pwr_now + SCHED_LOAD_SCALE / 8)
                        goto out_balanced;

                *imbalance = 1;
                return busiest;
        }

        /* Get rid of the scaling factor, rounding down as we divide */
        *imbalance = (*imbalance + 1) / SCHED_LOAD_SCALE;

        return busiest;

out_balanced:
        *imbalance = 0;
        return NULL;
}

/*
 * find_busiest_queue - find the busiest runqueue among the cpus in group.
 */
static runqueue_t *find_busiest_queue(struct sched_group *group)
{
        unsigned long load, max_load = 0;
        runqueue_t *busiest = NULL;
        int i;

        for_each_cpu_mask(i, group->cpumask) {
                load = source_load(i);

                if (load > max_load) {
                        max_load = load;
                        busiest = cpu_rq(i);
                }
        }

        return busiest;
}

/*
 * Check this_cpu to ensure it is balanced within domain. Attempt to move
 * tasks if there is an imbalance.
 *
 * Called with this_rq unlocked.
 */
static int load_balance(int this_cpu, runqueue_t *this_rq,
                        struct sched_domain *sd, enum idle_type idle)
{
        struct sched_group *group;
        runqueue_t *busiest;
        unsigned long imbalance;
        int nr_moved, all_pinned=0;

        spin_lock(&this_rq->lock);
        schedstat_inc(sd, lb_cnt[idle]);

        group = find_busiest_group(sd, this_cpu, &imbalance, idle);
        if (!group) {
                schedstat_inc(sd, lb_nobusyg[idle]);
                goto out_balanced;
        }

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

        /*
         * This should be "impossible", but since load
         * balancing is inherently racy and statistical,
         * it could happen in theory.
         */
        if (unlikely(busiest == this_rq)) {
                WARN_ON(1);
                goto out_balanced;
        }

        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.
                 */
                double_lock_balance(this_rq, busiest);
                nr_moved = move_tasks(this_rq, this_cpu, busiest,
                                                imbalance, sd, idle,
                                                &all_pinned);
                spin_unlock(&busiest->lock);

                /* All tasks on this runqueue were pinned by CPU affinity */
                if (unlikely(all_pinned))
                        goto out_balanced;
        }

        spin_unlock(&this_rq->lock);

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

                if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
                        int wake = 0;

                        spin_lock(&busiest->lock);
                        if (!busiest->active_balance) {
                                busiest->active_balance = 1;
                                busiest->push_cpu = this_cpu;
                                wake = 1;
                        }
                        spin_unlock(&busiest->lock);
                        if (wake)
                                wake_up_process(busiest->migration_thread);

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

        /* We were unbalanced, so reset the balancing interval */
        sd->balance_interval = sd->min_interval;

        return nr_moved;

out_balanced:
        spin_unlock(&this_rq->lock);

        sd->nr_balance_failed = 0;
        /* tune up the balancing interval */
        if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
                        (sd->balance_interval < sd->max_interval))
                sd->balance_interval *= 2;
        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, runqueue_t *this_rq,
                                struct sched_domain *sd)
{
        struct sched_group *group;
        runqueue_t *busiest = NULL;
        unsigned long imbalance;
        int nr_moved = 0;

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

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

        /* Attempt to move tasks */
        double_lock_balance(this_rq, busiest);

        schedstat_add(sd, lb_imbalance[NEWLY_IDLE], imbalance);
        nr_moved = move_tasks(this_rq, this_cpu, busiest,
                        imbalance, sd, NEWLY_IDLE, NULL);
        if (!nr_moved) {
                schedstat_inc(sd, lb_failed[NEWLY_IDLE]);
        } else
                sd->nr_balance_failed = 0;

        spin_unlock(&busiest->lock);
        return nr_moved;

out_balanced:
        schedstat_inc(sd, lb_balanced[NEWLY_IDLE]);
        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 inline void idle_balance(int this_cpu, runqueue_t *this_rq)
{
        struct sched_domain *sd;

        for_each_domain(this_cpu, sd) {
                if (sd->flags & SD_BALANCE_NEWIDLE) {
                        if (load_balance_newidle(this_cpu, this_rq, sd)) {
                                /* We've pulled tasks over so stop searching */
                                break;
                        }
                }
        }
}

/*
 * active_load_balance is run by migration threads. It pushes a running
 * task off the cpu. It can be required to correctly have at least 1 task
 * running on each physical CPU where possible, and not have a physical /
 * logical imbalance.
 *
 * Called with busiest locked.
 */
static void active_load_balance(runqueue_t *busiest, int busiest_cpu)
{
        struct sched_domain *sd;
        runqueue_t *target_rq;
        int target_cpu = busiest->push_cpu;

        schedstat_inc(busiest, alb_cnt);
        if (busiest->nr_running <= 1)
                return;

        target_rq = cpu_rq(target_cpu);

        /*
         * This condition is "impossible", but since load
         * balancing is inherently a bit racy and statistical,
         * it can trigger.. Reported by Bjorn Helgaas on a
         * 128-cpu setup.
         */
        BUG_ON(busiest == target_rq);

        double_lock_balance(busiest, target_rq);

        for_each_domain(target_cpu, sd)
                if (cpu_isset(busiest_cpu, sd->span))
                                break;

        if (unlikely(sd == NULL))
                goto out;

        if (move_tasks(target_rq, target_cpu, busiest, 1, sd, IDLE, NULL)) {
                schedstat_inc(busiest, alb_lost);
                schedstat_inc(target_rq, alb_gained);
        } else {
                schedstat_inc(busiest, alb_failed);
        }
out:
        spin_unlock(&target_rq->lock);
}

/*
 * rebalance_tick will get called every timer tick, on every CPU.
 *
 * 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.
 */

/* Don't have all balancing operations going off at once */
#define CPU_OFFSET(cpu) (HZ * cpu / NR_CPUS)

#define IRQ_QUANTUM     (HZ / 10)

static void rebalance_tick(int this_cpu, runqueue_t *this_rq,
                           enum idle_type idle)
{
        unsigned long old_load, this_load;
        unsigned long j = jiffies + CPU_OFFSET(this_cpu);
        struct sched_domain *sd;

        if (unlikely(--this_rq->irq_quantum <= 0)) {
                struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
                u64 irq_ticks = cpustat->irq + cpustat->softirq;
                unsigned int ticks = irq_ticks - this_rq->prev_irq_ticks;
                unsigned int pct = (ticks * 100) / IRQ_QUANTUM;

                this_rq->irq_pct = (this_rq->irq_pct + pct) / 2;
                this_rq->prev_irq_ticks = irq_ticks;
                this_rq->irq_quantum = IRQ_QUANTUM;
        }

        /* Update our load */
        old_load = this_rq->cpu_load;
        this_load = current_load(this_rq);
        /*
         * 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 (this_load > old_load)
                old_load++;
        this_rq->cpu_load = (old_load + this_load) / 2;

        /*
         * Isolated cpus don't get load-balanced.
         */
        if (cpu_isset(this_cpu, cpu_isolated_map))
                return;

        for_each_domain(this_cpu, sd) {
                unsigned long interval = sd->balance_interval;

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

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

                if (j - sd->last_balance >= interval) {
                        if (load_balance(this_cpu, this_rq, sd, idle)) {
                                /* We've pulled tasks over so no longer idle */
                                idle = NOT_IDLE;
                        }
                        sd->last_balance += interval;
                }
        }
}
#else
/*
 * on UP we do not need to balance between CPUs:
 */
static inline void rebalance_tick(int cpu, runqueue_t *rq, enum idle_type idle)
{
}
static inline void idle_balance(int cpu, runqueue_t *rq)
{
}
#endif

static inline int wake_priority_sleeper(runqueue_t *rq)
{
        int ret = 0;
#ifdef CONFIG_SCHED_SMT
        spin_lock(&rq->lock);
        /*
         * If an SMT sibling task has been put to sleep for priority
         * reasons reschedule the idle task to see if it can now run.
         */
        if (rq->nr_running) {
                resched_task(rq->idle);
                ret = 1;
        }
        spin_unlock(&rq->lock);
#endif
        return ret;
}

DEFINE_PER_CPU(struct kernel_stat, kstat);

EXPORT_PER_CPU_SYMBOL(kstat);

/*
 * We place interactive tasks back into the active array, if possible.
 *
 * To guarantee that this does not starve expired tasks we ignore the
 * interactivity of a task if the first expired task had to wait more
 * than a 'reasonable' amount of time. This deadline timeout is
 * load-dependent, as the frequency of array switched decreases with
 * increasing number of running tasks. We also ignore the interactivity
 * if a better static_prio task has expired:
 */
#define EXPIRED_STARVING(rq) \
        ((STARVATION_LIMIT && \
          (jiffies - (rq)->switch_timestamp > STARVATION_LIMIT)) || \
         ((rq)->curr->static_prio > (rq)->best_expired_prio))

/*
 * This function gets called by the timer code, with HZ frequency.
 * We call it with interrupts disabled.
 *
 * It also gets called by the fork code, when changing the parent's
 * timeslices.
 */
void scheduler_tick(int user_ticks, int sys_ticks)
{
        int cpu = smp_processor_id();
        struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
        runqueue_t *rq = this_rq();
        task_t *p = current;

        rq->timestamp_last_tick = sched_clock();

        if (rcu_pending(cpu))
                rcu_check_callbacks(cpu, user_ticks);

        /* note: this timer irq context must be accounted for as well */
        if (hardirq_count() - HARDIRQ_OFFSET) {
                cpustat->irq += sys_ticks;
                sys_ticks = 0;
        } else if (softirq_count()) {
                cpustat->softirq += sys_ticks;
                sys_ticks = 0;
        }

        if (p == rq->idle) {
                if (atomic_read(&rq->nr_iowait) > 0)
                        cpustat->iowait += sys_ticks;
                else
                        cpustat->idle += sys_ticks;
                if (wake_priority_sleeper(rq))
                        goto out;
                rebalance_tick(cpu, rq, IDLE);
                return;
        }
        if (TASK_NICE(p) > 0)
                cpustat->nice += user_ticks;
        else
                cpustat->user += user_ticks;
        cpustat->system += sys_ticks;

        /* Task might have expired already, but not scheduled off yet */
        if (p->array != rq->active) {
                set_tsk_need_resched(p);
                goto out;
        }
        spin_lock(&rq->lock);
        /*
         * The task was running during this tick - update the
         * time slice counter. Note: we do not update a thread's
         * priority until it either goes to sleep or uses up its
         * timeslice. This makes it possible for interactive tasks
         * to use up their timeslices at their highest priority levels.
         */
        if (rt_task(p)) {
                /*
                 * RR tasks need a special form of timeslice management.
                 * FIFO tasks have no timeslices.
                 */
                if ((p->policy == SCHED_RR) && !--p->time_slice) {
                        p->time_slice = task_timeslice(p);
                        p->first_time_slice = 0;
                        set_tsk_need_resched(p);

                        /* put it at the end of the queue: */
                        dequeue_task(p, rq->active);
                        enqueue_task(p, rq->active);
                }
                goto out_unlock;
        }
        if (!--p->time_slice) {
                dequeue_task(p, rq->active);
                set_tsk_need_resched(p);
                p->prio = effective_prio(p);
                p->time_slice = task_timeslice(p);
                p->first_time_slice = 0;

                if (!TASK_INTERACTIVE(p) || EXPIRED_STARVING(rq)) {
                        enqueue_task(p, rq->expired);
                        if (p->static_prio < rq->best_expired_prio)
                                rq->best_expired_prio = p->static_prio;
                } else
                        enqueue_task(p, rq->active);
        } else {
                /*
                 * Prevent a too long timeslice allowing a task to monopolize
                 * the CPU. We do this by splitting up the timeslice into
                 * smaller pieces.
                 *
                 * Note: this does not mean the task's timeslices expire or
                 * get lost in any way, they just might be preempted by
                 * another task of equal priority. (one with higher
                 * priority would have preempted this task already.) We
                 * requeue this task to the end of the list on this priority
                 * level, which is in essence a round-robin of tasks with
                 * equal priority.
                 *
                 * This only applies to tasks in the interactive
                 * delta range with at least TIMESLICE_GRANULARITY to requeue.
                 */
                if (TASK_INTERACTIVE(p) && !((task_timeslice(p) -
                        p->time_slice) % TIMESLICE_GRANULARITY(p)) &&
                        (p->time_slice >= TIMESLICE_GRANULARITY(p)) &&
                        (p->array == rq->active)) {

                        dequeue_task(p, rq->active);
                        set_tsk_need_resched(p);
                        p->prio = effective_prio(p);
                        enqueue_task(p, rq->active);
                }
        }
out_unlock:
        spin_unlock(&rq->lock);
out:
        rebalance_tick(cpu, rq, NOT_IDLE);
}

#ifdef CONFIG_SCHED_SMT
static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
{
        struct sched_domain *sd = this_rq->sd;
        cpumask_t sibling_map;
        int i;

        if (!(sd->flags & SD_SHARE_CPUPOWER))
                return;

        /*
         * Unlock the current runqueue because we have to lock in
         * CPU order to avoid deadlocks. Caller knows that we might
         * unlock. We keep IRQs disabled.
         */
        spin_unlock(&this_rq->lock);

        sibling_map = sd->span;

        for_each_cpu_mask(i, sibling_map)
                spin_lock(&cpu_rq(i)->lock);
        /*
         * We clear this CPU from the mask. This both simplifies the
         * inner loop and keps this_rq locked when we exit:
         */
        cpu_clear(this_cpu, sibling_map);

        for_each_cpu_mask(i, sibling_map) {
                runqueue_t *smt_rq = cpu_rq(i);

                /*
                 * If an SMT sibling task is sleeping due to priority
                 * reasons wake it up now.
                 */
                if (smt_rq->curr == smt_rq->idle && smt_rq->nr_running)
                        resched_task(smt_rq->idle);
        }

        for_each_cpu_mask(i, sibling_map)
                spin_unlock(&cpu_rq(i)->lock);
        /*
         * We exit with this_cpu's rq still held and IRQs
         * still disabled:
         */
}

static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
{
        struct sched_domain *sd = this_rq->sd;
        cpumask_t sibling_map;
        prio_array_t *array;
        int ret = 0, i;
        task_t *p;

        if (!(sd->flags & SD_SHARE_CPUPOWER))
                return 0;

        /*
         * The same locking rules and details apply as for
         * wake_sleeping_dependent():
         */
        spin_unlock(&this_rq->lock);
        sibling_map = sd->span;
        for_each_cpu_mask(i, sibling_map)
                spin_lock(&cpu_rq(i)->lock);
        cpu_clear(this_cpu, sibling_map);

        /*
         * Establish next task to be run - it might have gone away because
         * we released the runqueue lock above:
         */
        if (!this_rq->nr_running)
                goto out_unlock;
        array = this_rq->active;
        if (!array->nr_active)
                array = this_rq->expired;
        BUG_ON(!array->nr_active);

        p = list_entry(array->queue[sched_find_first_bit(array->bitmap)].next,
                task_t, run_list);

        for_each_cpu_mask(i, sibling_map) {
                runqueue_t *smt_rq = cpu_rq(i);
                task_t *smt_curr = smt_rq->curr;

                /*
                 * If a user task with lower static priority than the
                 * running task on the SMT sibling is trying to schedule,
                 * delay it till there is proportionately less timeslice
                 * left of the sibling task to prevent a lower priority
                 * task from using an unfair proportion of the
                 * physical cpu's resources. -ck
                 */
                if (((smt_curr->time_slice * (100 - sd->per_cpu_gain) / 100) >
                        task_timeslice(p) || rt_task(smt_curr)) &&
                        p->mm && smt_curr->mm && !rt_task(p))
                                ret = 1;

                /*
                 * Reschedule a lower priority task on the SMT sibling,
                 * or wake it up if it has been put to sleep for priority
                 * reasons.
                 */
                if ((((p->time_slice * (100 - sd->per_cpu_gain) / 100) >
                        task_timeslice(smt_curr) || rt_task(p)) &&
                        smt_curr->mm && p->mm && !rt_task(smt_curr)) ||
                        (smt_curr == smt_rq->idle && smt_rq->nr_running))
                                resched_task(smt_curr);
        }
out_unlock:
        for_each_cpu_mask(i, sibling_map)
                spin_unlock(&cpu_rq(i)->lock);
        return ret;
}
#else
static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
{
}

static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
{
        return 0;
}
#endif

/*
 * schedule() is the main scheduler function.
 */
asmlinkage void __sched schedule(void)
{
        long *switch_count;
        task_t *prev, *next;
        runqueue_t *rq;
        prio_array_t *array;
        struct list_head *queue;
        unsigned long long now;
        unsigned long run_time;
        int cpu, idx;

        //WARN_ON(system_state == SYSTEM_BOOTING);
        /*
         * Test if we are atomic.  Since do_exit() needs to call into
         * schedule() atomically, we ignore that path for now.
         * Otherwise, whine if we are scheduling when we should not be.
         */
        if (likely(!(current->exit_state & (EXIT_DEAD | EXIT_ZOMBIE)))) {
                if (unlikely(in_atomic())) {
                        printk(KERN_ERR "bad: scheduling while atomic!\n");
                        dump_stack();
                }
        }

need_resched:
        preempt_disable();
        prev = current;
        rq = this_rq();

        /*
         * The idle thread is not allowed to schedule!
         * Remove this check after it has been exercised a bit.
         */
        if (unlikely(current == rq->idle) && current->state != TASK_RUNNING) {
                printk(KERN_ERR "bad: scheduling from the idle thread!\n");
                dump_stack();
        }

        release_kernel_lock(prev);
        schedstat_inc(rq, sched_cnt);
        now = sched_clock();
        if (likely(now - prev->timestamp < NS_MAX_SLEEP_AVG))
                run_time = now - prev->timestamp;
        else
                run_time = NS_MAX_SLEEP_AVG;

        /*
         * Tasks with interactive credits get charged less run_time
         * at high sleep_avg to delay them losing their interactive
         * status
         */
        if (HIGH_CREDIT(prev))
                run_time /= (CURRENT_BONUS(prev) ? : 1);

        spin_lock_irq(&rq->lock);

        if (unlikely(current->flags & PF_DEAD))
                current->