sched, cputime: Cleanups related to task_times()

[linux-2.6.git] / kernel / sched.c

/*
 *  kernel/sched.c
 *
 *  Kernel scheduler and related syscalls
 *
 *  Copyright (C) 1991-2002  Linus Torvalds
 *
 *  1996-12-23  Modified by Dave Grothe to fix bugs in semaphores and
 *              make semaphores SMP safe
 *  1998-11-19  Implemented schedule_timeout() and related stuff
 *              by Andrea Arcangeli
 *  2002-01-04  New ultra-scalable O(1) scheduler by Ingo Molnar:
 *              hybrid priority-list and round-robin design with
 *              an array-switch method of distributing timeslices
 *              and per-CPU runqueues.  Cleanups and useful suggestions
 *              by Davide Libenzi, preemptible kernel bits by Robert Love.
 *  2003-09-03  Interactivity tuning by Con Kolivas.
 *  2004-04-02  Scheduler domains code by Nick Piggin
 *  2007-04-15  Work begun on replacing all interactivity tuning with a
 *              fair scheduling design by Con Kolivas.
 *  2007-05-05  Load balancing (smp-nice) and other improvements
 *              by Peter Williams
 *  2007-05-06  Interactivity improvements to CFS by Mike Galbraith
 *  2007-07-01  Group scheduling enhancements by Srivatsa Vaddagiri
 *  2007-11-29  RT balancing improvements by Steven Rostedt, Gregory Haskins,
 *              Thomas Gleixner, Mike Kravetz
 */

#include <linux/mm.h>
#include <linux/module.h>
#include <linux/nmi.h>
#include <linux/init.h>
#include <linux/uaccess.h>
#include <linux/highmem.h>
#include <linux/smp_lock.h>
#include <asm/mmu_context.h>
#include <linux/interrupt.h>
#include <linux/capability.h>
#include <linux/completion.h>
#include <linux/kernel_stat.h>
#include <linux/debug_locks.h>
#include <linux/perf_event.h>
#include <linux/security.h>
#include <linux/notifier.h>
#include <linux/profile.h>
#include <linux/freezer.h>
#include <linux/vmalloc.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
#include <linux/pid_namespace.h>
#include <linux/smp.h>
#include <linux/threads.h>
#include <linux/timer.h>
#include <linux/rcupdate.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/percpu.h>
#include <linux/kthread.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/sysctl.h>
#include <linux/syscalls.h>
#include <linux/times.h>
#include <linux/tsacct_kern.h>
#include <linux/kprobes.h>
#include <linux/delayacct.h>
#include <linux/unistd.h>
#include <linux/pagemap.h>
#include <linux/hrtimer.h>
#include <linux/tick.h>
#include <linux/debugfs.h>
#include <linux/ctype.h>
#include <linux/ftrace.h>

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

#include "sched_cpupri.h"

#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>

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

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

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

#define NICE_0_LOAD             SCHED_LOAD_SCALE
#define NICE_0_SHIFT            SCHED_LOAD_SHIFT

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

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

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

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

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

struct rt_bandwidth {
        /* nests inside the rq lock: */
        spinlock_t              rt_runtime_lock;
        ktime_t                 rt_period;
        u64                     rt_runtime;
        struct hrtimer          rt_period_timer;
};

static struct rt_bandwidth def_rt_bandwidth;

static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);

static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
{
        struct rt_bandwidth *rt_b =
                container_of(timer, struct rt_bandwidth, rt_period_timer);
        ktime_t now;
        int overrun;
        int idle = 0;

        for (;;) {
                now = hrtimer_cb_get_time(timer);
                overrun = hrtimer_forward(timer, now, rt_b->rt_period);

                if (!overrun)
                        break;

                idle = do_sched_rt_period_timer(rt_b, overrun);
        }

        return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
}

static
void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
{
        rt_b->rt_period = ns_to_ktime(period);
        rt_b->rt_runtime = runtime;

        spin_lock_init(&rt_b->rt_runtime_lock);

        hrtimer_init(&rt_b->rt_period_timer,
                        CLOCK_MONOTONIC, HRTIMER_MODE_REL);
        rt_b->rt_period_timer.function = sched_rt_period_timer;
}

static inline int rt_bandwidth_enabled(void)
{
        return sysctl_sched_rt_runtime >= 0;
}

static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
{
        ktime_t now;

        if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
                return;

        if (hrtimer_active(&rt_b->rt_period_timer))
                return;

        spin_lock(&rt_b->rt_runtime_lock);
        for (;;) {
                unsigned long delta;
                ktime_t soft, hard;

                if (hrtimer_active(&rt_b->rt_period_timer))
                        break;

                now = hrtimer_cb_get_time(&rt_b->rt_period_timer);
                hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period);

                soft = hrtimer_get_softexpires(&rt_b->rt_period_timer);
                hard = hrtimer_get_expires(&rt_b->rt_period_timer);
                delta = ktime_to_ns(ktime_sub(hard, soft));
                __hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta,
                                HRTIMER_MODE_ABS_PINNED, 0);
        }
        spin_unlock(&rt_b->rt_runtime_lock);
}

#ifdef CONFIG_RT_GROUP_SCHED
static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
{
        hrtimer_cancel(&rt_b->rt_period_timer);
}
#endif

/*
 * sched_domains_mutex serializes calls to arch_init_sched_domains,
 * detach_destroy_domains and partition_sched_domains.
 */
static DEFINE_MUTEX(sched_domains_mutex);

#ifdef CONFIG_GROUP_SCHED

#include <linux/cgroup.h>

struct cfs_rq;

static LIST_HEAD(task_groups);

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

#ifdef CONFIG_USER_SCHED
        uid_t uid;
#endif

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

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

        struct rt_bandwidth rt_bandwidth;
#endif

        struct rcu_head rcu;
        struct list_head list;

        struct task_group *parent;
        struct list_head siblings;
        struct list_head children;
};

#ifdef CONFIG_USER_SCHED

/* Helper function to pass uid information to create_sched_user() */
void set_tg_uid(struct user_struct *user)
{
        user->tg->uid = user->uid;
}

/*
 * Root task group.
 *      Every UID task group (including init_task_group aka UID-0) will
 *      be a child to this group.
 */
struct task_group root_task_group;

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

#ifdef CONFIG_RT_GROUP_SCHED
static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
#endif /* CONFIG_RT_GROUP_SCHED */
#else /* !CONFIG_USER_SCHED */
#define root_task_group init_task_group
#endif /* CONFIG_USER_SCHED */

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

#ifdef CONFIG_FAIR_GROUP_SCHED

#ifdef CONFIG_SMP
static int root_task_group_empty(void)
{
        return list_empty(&root_task_group.children);
}
#endif

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

/*
 * A weight of 0 or 1 can cause arithmetics problems.
 * A weight of a cfs_rq is the sum of weights of which entities
 * are queued on this cfs_rq, so a weight of a entity should not be
 * too large, so as the shares value of a task group.
 * (The default weight is 1024 - so there's no practical
 *  limitation from this.)
 */
#define MIN_SHARES      2
#define MAX_SHARES      (1UL << 18)

static int init_task_group_load = INIT_TASK_GROUP_LOAD;
#endif

/* Default task group.
 *      Every task in system belong to this group at bootup.
 */
struct task_group init_task_group;

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

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

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

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

#else

static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
static inline struct task_group *task_group(struct task_struct *p)
{
        return NULL;
}

#endif  /* CONFIG_GROUP_SCHED */

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

        u64 exec_clock;
        u64 min_vruntime;

        struct rb_root tasks_timeline;
        struct rb_node *rb_leftmost;

        struct list_head tasks;
        struct list_head *balance_iterator;

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

        unsigned int nr_spread_over;

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

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

#ifdef CONFIG_SMP
        /*
         * the part of load.weight contributed by tasks
         */
        unsigned long task_weight;

        /*
         *   h_load = weight * f(tg)
         *
         * Where f(tg) is the recursive weight fraction assigned to
         * this group.
         */
        unsigned long h_load;

        /*
         * this cpu's part of tg->shares
         */
        unsigned long shares;

        /*
         * load.weight at the time we set shares
         */
        unsigned long rq_weight;
#endif
#endif
};

/* Real-Time classes' related field in a runqueue: */
struct rt_rq {
        struct rt_prio_array active;
        unsigned long rt_nr_running;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
        struct {
                int curr; /* highest queued rt task prio */
#ifdef CONFIG_SMP
                int next; /* next highest */
#endif
        } highest_prio;
#endif
#ifdef CONFIG_SMP
        unsigned long rt_nr_migratory;
        unsigned long rt_nr_total;
        int overloaded;
        struct plist_head pushable_tasks;
#endif
        int rt_throttled;
        u64 rt_time;
        u64 rt_runtime;
        /* Nests inside the rq lock: */
        spinlock_t rt_runtime_lock;

#ifdef CONFIG_RT_GROUP_SCHED
        unsigned long rt_nr_boosted;

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

#ifdef CONFIG_SMP

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

        /*
         * The "RT overload" flag: it gets set if a CPU has more than
         * one runnable RT task.
         */
        cpumask_var_t rto_mask;
        atomic_t rto_count;
#ifdef CONFIG_SMP
        struct cpupri cpupri;
#endif
};

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

#endif

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

        /*
         * nr_running and cpu_load should be in the same cacheline because
         * remote CPUs use both these fields when doing load calculation.
         */
        unsigned long nr_running;
        #define CPU_LOAD_IDX_MAX 5
        unsigned long cpu_load[CPU_LOAD_IDX_MAX];
#ifdef CONFIG_NO_HZ
        unsigned char in_nohz_recently;
#endif
        /* capture load from *all* tasks on this cpu: */
        struct load_weight load;
        unsigned long nr_load_updates;
        u64 nr_switches;

        struct cfs_rq cfs;
        struct rt_rq rt;

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

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

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

        u64 clock;

        atomic_t nr_iowait;

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

        unsigned char idle_at_tick;
        /* For active balancing */
        int post_schedule;
        int active_balance;
        int push_cpu;
        /* cpu of this runqueue: */
        int cpu;
        int online;

        unsigned long avg_load_per_task;

        struct task_struct *migration_thread;
        struct list_head migration_queue;

        u64 rt_avg;
        u64 age_stamp;
        u64 idle_stamp;
        u64 avg_idle;
#endif

        /* calc_load related fields */
        unsigned long calc_load_update;
        long calc_load_active;

#ifdef CONFIG_SCHED_HRTICK
#ifdef CONFIG_SMP
        int hrtick_csd_pending;
        struct call_single_data hrtick_csd;
#endif
        struct hrtimer hrtick_timer;
#endif

#ifdef CONFIG_SCHEDSTATS
        /* latency stats */
        struct sched_info rq_sched_info;
        unsigned long long rq_cpu_time;
        /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */

        /* sys_sched_yield() stats */
        unsigned int yld_count;

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

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

        /* BKL stats */
        unsigned int bkl_count;
#endif
};

static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);

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

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

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

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

inline void update_rq_clock(struct rq *rq)
{
        rq->clock = sched_clock_cpu(cpu_of(rq));
}

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

/**
 * runqueue_is_locked
 * @cpu: the processor in question.
 *
 * Returns true if the current cpu runqueue is locked.
 * This interface allows printk to be called with the runqueue lock
 * held and know whether or not it is OK to wake up the klogd.
 */
int runqueue_is_locked(int cpu)
{
        return spin_is_locked(&cpu_rq(cpu)->lock);
}

/*
 * Debugging: various feature bits
 */

#define SCHED_FEAT(name, enabled)       \
        __SCHED_FEAT_##name ,

enum {
#include "sched_features.h"
};

#undef SCHED_FEAT

#define SCHED_FEAT(name, enabled)       \
        (1UL << __SCHED_FEAT_##name) * enabled |

const_debug unsigned int sysctl_sched_features =
#include "sched_features.h"
        0;

#undef SCHED_FEAT

#ifdef CONFIG_SCHED_DEBUG
#define SCHED_FEAT(name, enabled)       \
        #name ,

static __read_mostly char *sched_feat_names[] = {
#include "sched_features.h"
        NULL
};

#undef SCHED_FEAT

static int sched_feat_show(struct seq_file *m, void *v)
{
        int i;

        for (i = 0; sched_feat_names[i]; i++) {
                if (!(sysctl_sched_features & (1UL << i)))
                        seq_puts(m, "NO_");
                seq_printf(m, "%s ", sched_feat_names[i]);
        }
        seq_puts(m, "\n");

        return 0;
}

static ssize_t
sched_feat_write(struct file *filp, const char __user *ubuf,
                size_t cnt, loff_t *ppos)
{
        char buf[64];
        char *cmp = buf;
        int neg = 0;
        int i;

        if (cnt > 63)
                cnt = 63;

        if (copy_from_user(&buf, ubuf, cnt))
                return -EFAULT;

        buf[cnt] = 0;

        if (strncmp(buf, "NO_", 3) == 0) {
                neg = 1;
                cmp += 3;
        }

        for (i = 0; sched_feat_names[i]; i++) {
                int len = strlen(sched_feat_names[i]);

                if (strncmp(cmp, sched_feat_names[i], len) == 0) {
                        if (neg)
                                sysctl_sched_features &= ~(1UL << i);
                        else
                                sysctl_sched_features |= (1UL << i);
                        break;
                }
        }

        if (!sched_feat_names[i])
                return -EINVAL;

        *ppos += cnt;

        return cnt;
}

static int sched_feat_open(struct inode *inode, struct file *filp)
{
        return single_open(filp, sched_feat_show, NULL);
}

static const struct file_operations sched_feat_fops = {
        .open           = sched_feat_open,
        .write          = sched_feat_write,
        .read           = seq_read,
        .llseek         = seq_lseek,
        .release        = single_release,
};

static __init int sched_init_debug(void)
{
        debugfs_create_file("sched_features", 0644, NULL, NULL,
                        &sched_feat_fops);

        return 0;
}
late_initcall(sched_init_debug);

#endif

#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))

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

/*
 * ratelimit for updating the group shares.
 * default: 0.25ms
 */
unsigned int sysctl_sched_shares_ratelimit = 250000;

/*
 * Inject some fuzzyness into changing the per-cpu group shares
 * this avoids remote rq-locks at the expense of fairness.
 * default: 4
 */
unsigned int sysctl_sched_shares_thresh = 4;

/*
 * period over which we average the RT time consumption, measured
 * in ms.
 *
 * default: 1s
 */
const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;

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

static __read_mostly int scheduler_running;

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

static inline u64 global_rt_period(void)
{
        return (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
}

static inline u64 global_rt_runtime(void)
{
        if (sysctl_sched_rt_runtime < 0)
                return RUNTIME_INF;

        return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
}

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

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

#ifndef __ARCH_WANT_UNLOCKED_CTXSW
static inline int task_running(struct rq *rq, struct task_struct *p)
{
        return task_current(rq, p);
}

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

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

        spin_unlock_irq(&rq->lock);
}

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

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

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

/*
 * __task_rq_lock - lock the runqueue a given task resides on.
 * Must be called interrupts disabled.
 */
static inline struct rq *__task_rq_lock(struct task_struct *p)
        __acquires(rq->lock)
{
        for (;;) {
                struct rq *rq = task_rq(p);
                spin_lock(&rq->lock);
                if (likely(rq == task_rq(p)))
                        return rq;
                spin_unlock(&rq->lock);
        }
}

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

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

void task_rq_unlock_wait(struct task_struct *p)
{
        struct rq *rq = task_rq(p);

        smp_mb(); /* spin-unlock-wait is not a full memory barrier */
        spin_unlock_wait(&rq->lock);
}

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

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

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

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

        return rq;
}

#ifdef CONFIG_SCHED_HRTICK
/*
 * Use HR-timers to deliver accurate preemption points.
 *
 * Its all a bit involved since we cannot program an hrt while holding the
 * rq->lock. So what we do is store a state in in rq->hrtick_* and ask for a
 * reschedule event.
 *
 * When we get rescheduled we reprogram the hrtick_timer outside of the
 * rq->lock.
 */

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

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

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

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

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

        return HRTIMER_NORESTART;
}

#ifdef CONFIG_SMP
/*
 * called from hardirq (IPI) context
 */
static void __hrtick_start(void *arg)
{
        struct rq *rq = arg;

        spin_lock(&rq->lock);
        hrtimer_restart(&rq->hrtick_timer);
        rq->hrtick_csd_pending = 0;
        spin_unlock(&rq->lock);
}

/*
 * Called to set the hrtick timer state.
 *
 * called with rq->lock held and irqs disabled
 */
static void hrtick_start(struct rq *rq, u64 delay)
{
        struct hrtimer *timer = &rq->hrtick_timer;
        ktime_t time = ktime_add_ns(timer->base->get_time(), delay);

        hrtimer_set_expires(timer, time);

        if (rq == this_rq()) {
                hrtimer_restart(timer);
        } else if (!rq->hrtick_csd_pending) {
                __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
                rq->hrtick_csd_pending = 1;
        }
}

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

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

        return NOTIFY_DONE;
}

static __init void init_hrtick(void)
{
        hotcpu_notifier(hotplug_hrtick, 0);
}
#else
/*
 * Called to set the hrtick timer state.
 *
 * called with rq->lock held and irqs disabled
 */
static void hrtick_start(struct rq *rq, u64 delay)
{
        __hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
                        HRTIMER_MODE_REL_PINNED, 0);
}

static inline void init_hrtick(void)
{
}
#endif /* CONFIG_SMP */

static void init_rq_hrtick(struct rq *rq)
{
#ifdef CONFIG_SMP
        rq->hrtick_csd_pending = 0;

        rq->hrtick_csd.flags = 0;
        rq->hrtick_csd.func = __hrtick_start;
        rq->hrtick_csd.info = rq;
#endif

        hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
        rq->hrtick_timer.function = hrtick;
}
#else   /* CONFIG_SCHED_HRTICK */
static inline void hrtick_clear(struct rq *rq)
{
}

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

static inline void init_hrtick(void)
{
}
#endif  /* CONFIG_SCHED_HRTICK */

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

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

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

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

        if (test_tsk_need_resched(p))
                return;

        set_tsk_need_resched(p);

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

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

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

        if (!spin_trylock_irqsave(&rq->lock, flags))
                return;
        resched_task(cpu_curr(cpu));
        spin_unlock_irqrestore(&rq->lock, flags);
}

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

        if (cpu == smp_processor_id())
                return;

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

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

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

static u64 sched_avg_period(void)
{
        return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
}

static void sched_avg_update(struct rq *rq)
{
        s64 period = sched_avg_period();

        while ((s64)(rq->clock - rq->age_stamp) > period) {
                rq->age_stamp += period;
                rq->rt_avg /= 2;
        }
}

static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
{
        rq->rt_avg += rt_delta;
        sched_avg_update(rq);
}

#else /* !CONFIG_SMP */
static void resched_task(struct task_struct *p)
{
        assert_spin_locked(&task_rq(p)->lock);
        set_tsk_need_resched(p);
}

static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
{
}
#endif /* CONFIG_SMP */

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

#define WMULT_SHIFT     32

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

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

        if (!lw->inv_weight) {
                if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST))
                        lw->inv_weight = 1;
                else
                        lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)
                                / (lw->weight+1);
        }

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

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

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

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

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

#define WEIGHT_IDLEPRIO                3
#define WMULT_IDLEPRIO         1431655765

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

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

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

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

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

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

/* Time spent by the tasks of the cpu accounting group executing in ... */
enum cpuacct_stat_index {
        CPUACCT_STAT_USER,      /* ... user mode */
        CPUACCT_STAT_SYSTEM,    /* ... kernel mode */

        CPUACCT_STAT_NSTATS,
};

#ifdef CONFIG_CGROUP_CPUACCT
static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
static void cpuacct_update_stats(struct task_struct *tsk,
                enum cpuacct_stat_index idx, cputime_t val);
#else
static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
static inline void cpuacct_update_stats(struct task_struct *tsk,
                enum cpuacct_stat_index idx, cputime_t val) {}
#endif

static inline void inc_cpu_load(struct rq *rq, unsigned long load)
{
        update_load_add(&rq->load, load);
}

static inline void dec_cpu_load(struct rq *rq, unsigned long load)
{
        update_load_sub(&rq->load, load);
}

#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(CONFIG_RT_GROUP_SCHED)
typedef int (*tg_visitor)(struct task_group *, void *);

/*
 * Iterate the full tree, calling @down when first entering a node and @up when
 * leaving it for the final time.
 */
static int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
{
        struct task_group *parent, *child;
        int ret;

        rcu_read_lock();
        parent = &root_task_group;
down:
        ret = (*down)(parent, data);
        if (ret)
                goto out_unlock;
        list_for_each_entry_rcu(child, &parent->children, siblings) {
                parent = child;
                goto down;

up:
                continue;
        }
        ret = (*up)(parent, data);
        if (ret)
                goto out_unlock;

        child = parent;
        parent = parent->parent;
        if (parent)
                goto up;
out_unlock:
        rcu_read_unlock();

        return ret;
}

static int tg_nop(struct task_group *tg, void *data)
{
        return 0;
}
#endif

#ifdef CONFIG_SMP
/* Used instead of source_load when we know the type == 0 */
static unsigned long weighted_cpuload(const int cpu)
{
        return cpu_rq(cpu)->load.weight;
}

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

        if (type == 0 || !sched_feat(LB_BIAS))
                return total;

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

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

        if (type == 0 || !sched_feat(LB_BIAS))
                return total;

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

static struct sched_group *group_of(int cpu)
{
        struct sched_domain *sd = rcu_dereference(cpu_rq(cpu)->sd);

        if (!sd)
                return NULL;

        return sd->groups;
}

static unsigned long power_of(int cpu)
{
        struct sched_group *group = group_of(cpu);

        if (!group)
                return SCHED_LOAD_SCALE;

        return group->cpu_power;
}

static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);

static unsigned long cpu_avg_load_per_task(int cpu)
{
        struct rq *rq = cpu_rq(cpu);
        unsigned long nr_running = ACCESS_ONCE(rq->nr_running);

        if (nr_running)
                rq->avg_load_per_task = rq->load.weight / nr_running;
        else
                rq->avg_load_per_task = 0;

        return rq->avg_load_per_task;
}

#ifdef CONFIG_FAIR_GROUP_SCHED

static __read_mostly unsigned long *update_shares_data;

static void __set_se_shares(struct sched_entity *se, unsigned long shares);

/*
 * Calculate and set the cpu's group shares.
 */
static void update_group_shares_cpu(struct task_group *tg, int cpu,
                                    unsigned long sd_shares,
                                    unsigned long sd_rq_weight,
                                    unsigned long *usd_rq_weight)
{
        unsigned long shares, rq_weight;
        int boost = 0;

        rq_weight = usd_rq_weight[cpu];
        if (!rq_weight) {
                boost = 1;
                rq_weight = NICE_0_LOAD;
        }

        /*
         *             \Sum_j shares_j * rq_weight_i
         * shares_i =  -----------------------------
         *                  \Sum_j rq_weight_j
         */
        shares = (sd_shares * rq_weight) / sd_rq_weight;
        shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);

        if (abs(shares - tg->se[cpu]->load.weight) >
                        sysctl_sched_shares_thresh) {
                struct rq *rq = cpu_rq(cpu);
                unsigned long flags;

                spin_lock_irqsave(&rq->lock, flags);
                tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight;
                tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
                __set_se_shares(tg->se[cpu], shares);
                spin_unlock_irqrestore(&rq->lock, flags);
        }
}

/*
 * Re-compute the task group their per cpu shares over the given domain.
 * This needs to be done in a bottom-up fashion because the rq weight of a
 * parent group depends on the shares of its child groups.
 */
static int tg_shares_up(struct task_group *tg, void *data)
{
        unsigned long weight, rq_weight = 0, shares = 0;
        unsigned long *usd_rq_weight;
        struct sched_domain *sd = data;
        unsigned long flags;
        int i;

        if (!tg->se[0])
                return 0;

        local_irq_save(flags);
        usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id());

        for_each_cpu(i, sched_domain_span(sd)) {
                weight = tg->cfs_rq[i]->load.weight;
                usd_rq_weight[i] = weight;

                /*
                 * If there are currently no tasks on the cpu pretend there
                 * is one of average load so that when a new task gets to
                 * run here it will not get delayed by group starvation.
                 */
                if (!weight)
                        weight = NICE_0_LOAD;

                rq_weight += weight;
                shares += tg->cfs_rq[i]->shares;
        }

        if ((!shares && rq_weight) || shares > tg->shares)
                shares = tg->shares;

        if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE))
                shares = tg->shares;

        for_each_cpu(i, sched_domain_span(sd))
                update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight);

        local_irq_restore(flags);

        return 0;
}

/*
 * Compute the cpu's hierarchical load factor for each task group.
 * This needs to be done in a top-down fashion because the load of a child
 * group is a fraction of its parents load.
 */
static int tg_load_down(struct task_group *tg, void *data)
{
        unsigned long load;
        long cpu = (long)data;

        if (!tg->parent) {
                load = cpu_rq(cpu)->load.weight;
        } else {
                load = tg->parent->cfs_rq[cpu]->h_load;
                load *= tg->cfs_rq[cpu]->shares;
                load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
        }

        tg->cfs_rq[cpu]->h_load = load;

        return 0;
}

static void update_shares(struct sched_domain *sd)
{
        s64 elapsed;
        u64 now;

        if (root_task_group_empty())
                return;

        now = cpu_clock(raw_smp_processor_id());
        elapsed = now - sd->last_update;

        if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
                sd->last_update = now;
                walk_tg_tree(tg_nop, tg_shares_up, sd);
        }
}

static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
{
        if (root_task_group_empty())
                return;

        spin_unlock(&rq->lock);
        update_shares(sd);
        spin_lock(&rq->lock);
}

static void update_h_load(long cpu)
{
        if (root_task_group_empty())
                return;

        walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
}

#else

static inline void update_shares(struct sched_domain *sd)
{
}

static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)
{
}

#endif

#ifdef CONFIG_PREEMPT

static void double_rq_lock(struct rq *rq1, struct rq *rq2);

/*
 * fair double_lock_balance: Safely acquires both rq->locks in a fair
 * way at the expense of forcing extra atomic operations in all
 * invocations.  This assures that the double_lock is acquired using the
 * same underlying policy as the spinlock_t on this architecture, which
 * reduces latency compared to the unfair variant below.  However, it
 * also adds more overhead and therefore may reduce throughput.
 */
static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
        __releases(this_rq->lock)
        __acquires(busiest->lock)
        __acquires(this_rq->lock)
{
        spin_unlock(&this_rq->lock);
        double_rq_lock(this_rq, busiest);

        return 1;
}

#else
/*
 * Unfair double_lock_balance: Optimizes throughput at the expense of
 * latency by eliminating extra atomic operations when the locks are
 * already in proper order on entry.  This favors lower cpu-ids and will
 * grant the double lock to lower cpus over higher ids under contention,
 * regardless of entry order into the function.
 */
static int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
        __releases(this_rq->lock)
        __acquires(busiest->lock)
        __acquires(this_rq->lock)
{
        int ret = 0;

        if (unlikely(!spin_trylock(&busiest->lock))) {
                if (busiest < this_rq) {
                        spin_unlock(&this_rq->lock);
                        spin_lock(&busiest->lock);
                        spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
                        ret = 1;
                } else
                        spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
        }
        return ret;
}

#endif /* CONFIG_PREEMPT */

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

        return _double_lock_balance(this_rq, busiest);
}

static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
        __releases(busiest->lock)
{
        spin_unlock(&busiest->lock);
        lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
}
#endif

#ifdef CONFIG_FAIR_GROUP_SCHED
static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
{
#ifdef CONFIG_SMP
        cfs_rq->shares = shares;
#endif
}
#endif

static void calc_load_account_active(struct rq *this_rq);

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

#define sched_class_highest (&rt_sched_class)
#define for_each_class(class) \
   for (class = sched_class_highest; class; class = class->next)

static void inc_nr_running(struct rq *rq)
{
        rq->nr_running++;
}

static void dec_nr_running(struct rq *rq)
{
        rq->nr_running--;
}

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

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

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

static void update_avg(u64 *avg, u64 sample)
{
        s64 diff = sample - *avg;
        *avg += diff >> 3;
}

static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
{
        if (wakeup)
                p->se.start_runtime = p->se.sum_exec_runtime;

        sched_info_queued(p);
        p->sched_class->enqueue_task(rq, p, wakeup);
        p->se.on_rq = 1;
}

static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
{
        if (sleep) {
                if (p->se.last_wakeup) {
                        update_avg(&p->se.avg_overlap,
                                p->se.sum_exec_runtime - p->se.last_wakeup);
                        p->se.last_wakeup = 0;
                } else {
                        update_avg(&p->se.avg_wakeup,
                                sysctl_sched_wakeup_granularity);
                }
        }

        sched_info_dequeued(p);
        p->sched_class->dequeue_task(rq, p, sleep);
        p->se.on_rq = 0;
}

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

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

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

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

/*
 * activate_task - move a task to the runqueue.
 */
static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
{
        if (task_contributes_to_load(p))
                rq->nr_uninterruptible--;

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

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

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

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

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

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

/**
 * kthread_bind - bind a just-created kthread to a cpu.
 * @p: thread created by kthread_create().
 * @cpu: cpu (might not be online, must be possible) for @k to run on.
 *
 * Description: This function is equivalent to set_cpus_allowed(),
 * except that @cpu doesn't need to be online, and the thread must be
 * stopped (i.e., just returned from kthread_create()).
 *
 * Function lives here instead of kthread.c because it messes with
 * scheduler internals which require locking.
 */
void kthread_bind(struct task_struct *p, unsigned int cpu)
{
        struct rq *rq = cpu_rq(cpu);
        unsigned long flags;

        /* Must have done schedule() in kthread() before we set_task_cpu */
        if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
                WARN_ON(1);
                return;
        }

        spin_lock_irqsave(&rq->lock, flags);
        update_rq_clock(rq);
        set_task_cpu(p, cpu);
        p->cpus_allowed = cpumask_of_cpu(cpu);
        p->rt.nr_cpus_allowed = 1;
        p->flags |= PF_THREAD_BOUND;
        spin_unlock_irqrestore(&rq->lock, flags);
}
EXPORT_SYMBOL(kthread_bind);

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

        /*
         * Buddy candidates are cache hot:
         */
        if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
                        (&p->se == cfs_rq_of(&p->se)->next ||
                         &p->se == cfs_rq_of(&p->se)->last))
                return 1;

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

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

        delta = now - p->se.exec_start;

        return delta < (s64)sysctl_sched_migration_cost;
}


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

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

        trace_sched_migrate_task(p, new_cpu);

#ifdef CONFIG_SCHEDSTATS
        if (p->se.wait_start)
                p->se.wait_start -= clock_offset;
        if (p->se.sleep_start)
                p->se.sleep_start -= clock_offset;
        if (p->se.block_start)
                p->se.block_start -= clock_offset;
#endif
        if (old_cpu != new_cpu) {
                p->se.nr_migrations++;
#ifdef CONFIG_SCHEDSTATS
                if (task_hot(p, old_rq->clock, NULL))
                        schedstat_inc(p, se.nr_forced2_migrations);
#endif
                perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS,
                                     1, 1, NULL, 0);
        }
        p->se.vruntime -= old_cfsrq->min_vruntime -
                                         new_cfsrq->min_vruntime;

        __set_task_cpu(p, new_cpu);
}

struct migration_req {
        struct list_head list;

        struct task_struct *task;
        int dest_cpu;

        struct completion done;
};

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

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

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

        return 1;
}

/*
 * wait_task_context_switch -   wait for a thread to complete at least one
 *                              context switch.
 *
 * @p must not be current.
 */
void wait_task_context_switch(struct task_struct *p)
{
        unsigned long nvcsw, nivcsw, flags;
        int running;
        struct rq *rq;

        nvcsw   = p->nvcsw;
        nivcsw  = p->nivcsw;
        for (;;) {
                /*
                 * The runqueue is assigned before the actual context
                 * switch. We need to take the runqueue lock.
                 *
                 * We could check initially without the lock but it is
                 * very likely that we need to take the lock in every
                 * iteration.
                 */
                rq = task_rq_lock(p, &flags);
                running = task_running(rq, p);
                task_rq_unlock(rq, &flags);

                if (likely(!running))
                        break;
                /*
                 * The switch count is incremented before the actual
                 * context switch. We thus wait for two switches to be
                 * sure at least one completed.
                 */
                if ((p->nvcsw - nvcsw) > 1)
                        break;
                if ((p->nivcsw - nivcsw) > 1)
                        break;

                cpu_relax();
        }
}

/*
 * wait_task_inactive - wait for a thread to unschedule.
 *
 * If @match_state is nonzero, it's the @p->state value just checked and
 * not expected to change.  If it changes, i.e. @p might have woken up,
 * then return zero.  When we succeed in waiting for @p to be off its CPU,
 * we return a positive number (its total switch count).  If a second call
 * a short while later returns the same number, the caller can be sure that
 * @p has remained unscheduled the whole time.
 *
 * 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.
 */
unsigned long wait_task_inactive(struct task_struct *p, long match_state)
{
        unsigned long flags;
        int running, on_rq;
        unsigned long ncsw;
        struct rq *rq;

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

                /*
                 * If the task is actively running on another CPU
                 * still, just relax and busy-wait without holding
                 * any locks.
                 *
                 * NOTE! Since we don't hold any locks, it's not
                 * even sure that "rq" stays as the right runqueue!
                 * But we don't care, since "task_running()" will
                 * return false if the runqueue has changed and p
                 * is actually now running somewhere else!
                 */
                while (task_running(rq, p)) {
                        if (match_state && unlikely(p->state != match_state))
                                return 0;
                        cpu_relax();
                }

                /*
                 * Ok, time to look more closely! We need the rq
                 * lock now, to be *sure*. If we're wrong, we'll
                 * just go back and repeat.
                 */
                rq = task_rq_lock(p, &flags);
                trace_sched_wait_task(rq, p);
                running = task_running(rq, p);
                on_rq = p->se.on_rq;
                ncsw = 0;
                if (!match_state || p->state == match_state)
                        ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
                task_rq_unlock(rq, &flags);

                /*
                 * If it changed from the expected state, bail out now.
                 */
                if (unlikely(!ncsw))
                        break;

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

                /*
                 * It's not enough that it's not actively running,
                 * it must be off the runqueue _entirely_, and not
                 * preempted!
                 *
                 * So if it was still runnable (but just not actively
                 * running right now), it's preempted, and we should
                 * yield - it could be a while.
                 */
                if (unlikely(on_rq)) {
                        schedule_timeout_uninterruptible(1);
                        continue;
                }

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

        return ncsw;
}

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

        preempt_disable();
        cpu = task_cpu(p);
        if ((cpu != smp_processor_id()) && task_curr(p))
                smp_send_reschedule(cpu);
        preempt_enable();
}
EXPORT_SYMBOL_GPL(kick_process);
#endif /* CONFIG_SMP */

/**
 * task_oncpu_function_call - call a function on the cpu on which a task runs
 * @p:          the task to evaluate
 * @func:       the function to be called
 * @info:       the function call argument
 *
 * Calls the function @func when the task is currently running. This might
 * be on the current CPU, which just calls the function directly
 */
void task_oncpu_function_call(struct task_struct *p,
                              void (*func) (void *info), void *info)
{
        int cpu;

        preempt_disable();
        cpu = task_cpu(p);
        if (task_curr(p))
                smp_call_function_single(cpu, func, info, 1);
        preempt_enable();
}

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

        if (!sched_feat(SYNC_WAKEUPS))
                wake_flags &= ~WF_SYNC;

        this_cpu = get_cpu();

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

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

        cpu = task_cpu(p);
        orig_cpu = cpu;

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

        /*
         * In order to handle concurrent wakeups and release the rq->lock
         * we put the task in TASK_WAKING state.
         *
         * First fix up the nr_uninterruptible count:
         */
        if (task_contributes_to_load(p))
                rq->nr_uninterruptible--;
        p->state = TASK_WAKING;
        task_rq_unlock(rq, &flags);

        cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
        if (cpu != orig_cpu) {
                local_irq_save(flags);
                rq = cpu_rq(cpu);
                update_rq_clock(rq);
                set_task_cpu(p, cpu);
                local_irq_restore(flags);
        }
        rq = task_rq_lock(p, &flags);

        WARN_ON(p->state != TASK_WAKING);
        cpu = task_cpu(p);

#ifdef CONFIG_SCHEDSTATS
        schedstat_inc(rq, ttwu_count);
        if (cpu == this_cpu)
                schedstat_inc(rq, ttwu_local);
        else {
                struct sched_domain *sd;
                for_each_domain(this_cpu, sd) {
                        if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
                                schedstat_inc(sd, ttwu_wake_remote);
                                break;
                        }
                }
        }
#endif /* CONFIG_SCHEDSTATS */

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

        /*
         * Only attribute actual wakeups done by this task.
         */
        if (!in_interrupt()) {
                struct sched_entity *se = &current->se;
                u64 sample = se->sum_exec_runtime;

                if (se->last_wakeup)
                        sample -= se->last_wakeup;
                else
                        sample -= se->start_runtime;
                update_avg(&se->avg_wakeup, sample);

                se->last_wakeup = se->sum_exec_runtime;
        }

out_running:
        trace_sched_wakeup(rq, p, success);
        check_preempt_curr(rq, p, wake_flags);

        p->state = TASK_RUNNING;
#ifdef CONFIG_SMP
        if (p->sched_class->task_wake_up)
                p->sched_class->task_wake_up(rq, p);

        if (unlikely(rq->idle_stamp)) {
                u64 delta = rq->clock - rq->idle_stamp;
                u64 max = 2*sysctl_sched_migration_cost;

                if (delta > max)
                        rq->avg_idle = max;
                else
                        update_avg(&rq->avg_idle, delta);
                rq->idle_stamp = 0;
        }
#endif
out:
        task_rq_unlock(rq, &flags);
        put_cpu();

        return success;
}

/**
 * wake_up_process - Wake up a specific process
 * @p: The process to be woken up.
 *
 * Attempt to wake up the nominated process and move it to the set of runnable
 * processes.  Returns 1 if the process was woken up, 0 if it was already
 * running.
 *
 * It may be assumed that this function implies a write memory barrier before
 * changing the task state if and only if any tasks are woken up.
 */
int wake_up_process(struct task_struct *p)
{
        return try_to_wake_up(p, TASK_ALL, 0);
}
EXPORT_SYMBOL(wake_up_process);

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

/*
 * Perform scheduler related setup for a newly forked process p.
 * p is forked by current.
 *
 * __sched_fork() is basic setup used by init_idle() too:
 */
static void __sched_fork(struct task_struct *p)
{
        p->se.exec_start                = 0;
        p->se.sum_exec_runtime          = 0;
        p->se.prev_sum_exec_runtime     = 0;
        p->se.nr_migrations             = 0;
        p->se.last_wakeup               = 0;
        p->se.avg_overlap               = 0;
        p->se.start_runtime             = 0;
        p->se.avg_wakeup                = sysctl_sched_wakeup_granularity;
        p->se.avg_running               = 0;

#ifdef CONFIG_SCHEDSTATS
        p->se.wait_start                        = 0;
        p->se.wait_max                          = 0;
        p->se.wait_count                        = 0;
        p->se.wait_sum                          = 0;

        p->se.sleep_start                       = 0;
        p->se.sleep_max                         = 0;
        p->se.sum_sleep_runtime                 = 0;

        p->se.block_start                       = 0;
        p->se.block_max                         = 0;
        p->se.exec_max                          = 0;
        p->se.slice_max                         = 0;

        p->se.nr_migrations_cold                = 0;
        p->se.nr_failed_migrations_affine       = 0;
        p->se.nr_failed_migrations_running      = 0;
        p->se.nr_failed_migrations_hot          = 0;
        p->se.nr_forced_migrations              = 0;
        p->se.nr_forced2_migrations             = 0;

        p->se.nr_wakeups                        = 0;
        p->se.nr_wakeups_sync                   = 0;
        p->se.nr_wakeups_migrate                = 0;
        p->se.nr_wakeups_local                  = 0;
        p->se.nr_wakeups_remote                 = 0;
        p->se.nr_wakeups_affine                 = 0;
        p->se.nr_wakeups_affine_attempts        = 0;
        p->se.nr_wakeups_passive                = 0;
        p->se.nr_wakeups_idle                   = 0;

#endif

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

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

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

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

        __sched_fork(p);

        /*
         * Revert to default priority/policy on fork if requested.
         */
        if (unlikely(p->sched_reset_on_fork)) {
                if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) {
                        p->policy = SCHED_NORMAL;
                        p->normal_prio = p->static_prio;
                }

                if (PRIO_TO_NICE(p->static_prio) < 0) {
                        p->static_prio = NICE_TO_PRIO(0);
                        p->normal_prio = p->static_prio;
                        set_load_weight(p);
                }

                /*
                 * We don't need the reset flag anymore after the fork. It has
                 * fulfilled its duty:
                 */
                p->sched_reset_on_fork = 0;
        }

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

        if (!rt_prio(p->prio))
                p->sched_class = &fair_sched_class;

#ifdef CONFIG_SMP
        cpu = p->sched_class->select_task_rq(p, SD_BALANCE_FORK, 0);
#endif
        local_irq_save(flags);
        update_rq_clock(cpu_rq(cpu));
        set_task_cpu(p, cpu);
        local_irq_restore(flags);

#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
        if (likely(sched_info_on()))
                memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
        p->oncpu = 0;
#endif
#ifdef CONFIG_PREEMPT
        /* Want to start with kernel preemption disabled. */
        task_thread_info(p)->preempt_count = 1;
#endif
        plist_node_init(&p->pushable_tasks, MAX_PRIO);

        put_cpu();
}

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

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

        if (!p->sched_class->task_new || !current->se.on_rq) {
                activate_task(rq, p, 0);
        } else {
                /*
                 * Let the scheduling class do new task startup
                 * management (if any):
                 */
                p->sched_class->task_new(rq, p);
                inc_nr_running(rq);
        }
        trace_sched_wakeup_new(rq, p, 1);
        check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
        if (p->sched_class->task_wake_up)
                p->sched_class->task_wake_up(rq, p);
#endif
        task_rq_unlock(rq, &flags);
}

#ifdef CONFIG_PREEMPT_NOTIFIERS

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

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

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

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

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

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

#else /* !CONFIG_PREEMPT_NOTIFIERS */

static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
}

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

#endif /* CONFIG_PREEMPT_NOTIFIERS */

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

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

        rq->prev_mm = NULL;

        /*
         * A task struct has one reference for the use as "current".
         * If a task dies, then it sets TASK_DEAD in tsk->state and calls
         * schedule one last time. The schedule call will never return, and
         * the scheduled task must drop that reference.
         * The test for TASK_DEAD must occur while the runqueue locks are
         * still held, otherwise prev could be scheduled on another cpu, die
         * there before we look at prev->state, and then the reference would
         * be dropped twice.
         *              Manfred Spraul <manfred@colorfullife.com>
         */
        prev_state = prev->state;
        finish_arch_switch(prev);
        perf_event_task_sched_in(current, cpu_of(rq));
        finish_lock_switch(rq, prev);

        fire_sched_in_preempt_notifiers(current);
        if (mm)
                mmdrop(mm);
        if (unlikely(prev_state == TASK_DEAD)) {
                /*
                 * Remove function-return probe instances associated with this
                 * task and put them back on the free list.
                 */
                kprobe_flush_task(prev);
                put_task_struct(prev);
        }
}

#ifdef CONFIG_SMP

/* assumes rq->lock is held */
static inline void pre_schedule(struct rq *rq, struct task_struct *prev)
{
        if (prev->sched_class->pre_schedule)
                prev->sched_class->pre_schedule(rq, prev);
}

/* rq->lock is NOT held, but preemption is disabled */
static inline void post_schedule(struct rq *rq)
{
        if (rq->post_schedule) {
                unsigned long flags;

                spin_lock_irqsave(&rq->lock, flags);
                if (rq->curr->sched_class->post_schedule)
                        rq->curr->sched_class->post_schedule(rq);
                spin_unlock_irqrestore(&rq->lock, flags);

                rq->post_schedule = 0;
        }
}

#else

static inline void pre_schedule(struct rq *rq, struct task_struct *p)
{
}

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

#endif

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

        finish_task_switch(rq, prev);

        /*
         * FIXME: do we need to worry about rq being invalidated by the
         * task_switch?
         */
        post_schedule(rq);

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

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

        prepare_task_switch(rq, prev, next);
        trace_sched_switch(rq, prev, next);
        mm = next->mm;
        oldmm = prev->active_mm;
        /*
         * For paravirt, this is coupled with an exit in switch_to to
         * combine the page table reload and the switch backend into
         * one hypercall.
         */
        arch_start_context_switch(prev);

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

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

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

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

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

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

        return sum;
}

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

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

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

        return sum;
}

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

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

        return sum;
}

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

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

        return sum;
}

unsigned long nr_iowait_cpu(void)
{
        struct rq *this = this_rq();
        return atomic_read(&this->nr_iowait);
}

unsigned long this_cpu_load(void)
{
        struct rq *this = this_rq();
        return this->cpu_load[0];
}


/* Variables and functions for calc_load */
static atomic_long_t calc_load_tasks;
static unsigned long calc_load_update;
unsigned long avenrun[3];
EXPORT_SYMBOL(avenrun);

/**
 * get_avenrun - get the load average array
 * @loads:      pointer to dest load array
 * @offset:     offset to add
 * @shift:      shift count to shift the result left
 *
 * These values are estimates at best, so no need for locking.
 */
void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
{
        loads[0] = (avenrun[0] + offset) << shift;
        loads[1] = (avenrun[1] + offset) << shift;
        loads[2] = (avenrun[2] + offset) << shift;
}

static unsigned long
calc_load(unsigned long load, unsigned long exp, unsigned long active)
{
        load *= exp;
        load += active * (FIXED_1 - exp);
        return load >> FSHIFT;
}

/*
 * calc_load - update the avenrun load estimates 10 ticks after the
 * CPUs have updated calc_load_tasks.
 */
void calc_global_load(void)
{
        unsigned long upd = calc_load_update + 10;
        long active;

        if (time_before(jiffies, upd))
                return;

        active = atomic_long_read(&calc_load_tasks);
        active = active > 0 ? active * FIXED_1 : 0;

        avenrun[0] = calc_load(avenrun[0], EXP_1, active);
        avenrun[1] = calc_load(avenrun[1], EXP_5, active);
        avenrun[2] = calc_load(avenrun[2], EXP_15, active);

        calc_load_update += LOAD_FREQ;
}

/*
 * Either called from update_cpu_load() or from a cpu going idle
 */
static void calc_load_account_active(struct rq *this_rq)
{
        long nr_active, delta;

        nr_active = this_rq->nr_running;
        nr_active += (long) this_rq->nr_uninterruptible;

        if (nr_active != this_rq->calc_load_active) {
                delta = nr_active - this_rq->calc_load_active;
                this_rq->calc_load_active = nr_active;
                atomic_long_add(delta, &calc_load_tasks);
        }
}

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

        this_rq->nr_load_updates++;

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

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

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

        if (time_after_eq(jiffies, this_rq->calc_load_update)) {
                this_rq->calc_load_update += LOAD_FREQ;
                calc_load_account_active(this_rq);
        }
}

#ifdef CONFIG_SMP

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

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

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

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

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

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

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

/*
 * sched_exec - execve() is a valuable balancing opportunity, because at
 * this point the task has the smallest effective memory and cache footprint.
 */
void sched_exec(void)
{
        int new_cpu, this_cpu = get_cpu();
        new_cpu = current->sched_class->select_task_rq(current, SD_BALANCE_EXEC, 0);
        put_cpu();
        if (new_cpu != this_cpu)
                sched_migrate_task(current, new_cpu);
}

/*
 * pull_task - move a task from a remote runqueue to the local runqueue.
 * Both runqueues must be locked.
 */
static void pull_task(struct rq *src_rq, struct task_struct *p,
                      struct rq *this_rq, int this_cpu)
{
        deactivate_task(src_rq, p, 0);
        set_task_cpu(p, this_cpu);
        activate_task(this_rq, p, 0);
        /*
         * Note that idle threads have a prio of MAX_PRIO, for this test
         * to be always true for them.
         */
        check_preempt_curr(this_rq, p, 0);
}

/*
 * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
 */
static
int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
                     struct sched_domain *sd, enum cpu_idle_type idle,
                     int *all_pinned)
{
        int tsk_cache_hot = 0;
        /*
         * 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 (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) {
                schedstat_inc(p, se.nr_failed_migrations_affine);
                return 0;
        }
        *all_pinned = 0;

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

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

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

        if (tsk_cache_hot) {
                schedstat_inc(p, se.nr_failed_migrations_hot);
                return 0;
        }
        return 1;
}

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

        if (max_load_move == 0)
                goto out;

        pinned = 1;

        /*
         * Start the load-balancing iterator:
         */
        p = iterator->start(iterator->arg);
next:
        if (!p || loops++ > sysctl_sched_nr_migrate)
                goto out;

        if ((p->se.load.weight >> 1) > rem_load_move ||
            !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
                p = iterator->next(iterator->arg);
                goto next;
        }

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

#ifdef CONFIG_PREEMPT
        /*
         * NEWIDLE balancing is a source of latency, so preemptible kernels
         * will stop after the first task is pulled to minimize the critical
         * section.
         */
        if (idle == CPU_NEWLY_IDLE)
                goto out;
#endif

        /*
         * We only want to steal up to the prescribed amount of weighted load.
         */
        if (rem_load_move > 0) {
                if (p->prio < *this_best_prio)
                        *this_best_prio = p->prio;
                p = iterator->next(iterator->arg);
                goto next;
        }
out:
        /*
         * Right now, this is one of only two places pull_task() is called,
         * so we can safely collect pull_task() stats here rather than
         * inside pull_task().
         */
        schedstat_add(sd, lb_gained[idle], pulled);

        if (all_pinned)
                *all_pinned = pinned;

        return max_load_move - rem_load_move;
}

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

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

#ifdef CONFIG_PREEMPT
                /*
                 * NEWIDLE balancing is a source of latency, so preemptible
                 * kernels will stop after the first task is pulled to minimize
                 * the critical section.
                 */
                if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
                        break;
#endif
        } while (class && max_load_move > total_load_moved);

        return total_load_moved > 0;
}

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

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

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

        return 0;
}

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

        for_each_class(class) {
                if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle))
                        return 1;
        }

        return 0;
}
/********** Helpers for find_busiest_group ************************/
/*
 * sd_lb_stats - Structure to store the statistics of a sched_domain
 *              during load balancing.
 */
struct sd_lb_stats {
        struct sched_group *busiest; /* Busiest group in this sd */
        struct sched_group *this;  /* Local group in this sd */
        unsigned long total_load;  /* Total load of all groups in sd */
        unsigned long total_pwr;   /*   Total power of all groups in sd */
        unsigned long avg_load;    /* Average load across all groups in sd */

        /** Statistics of this group */
        unsigned long this_load;
        unsigned long this_load_per_task;
        unsigned long this_nr_running;

        /* Statistics of the busiest group */
        unsigned long max_load;
        unsigned long busiest_load_per_task;
        unsigned long busiest_nr_running;

        int group_imb; /* Is there imbalance in this sd */
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
        int power_savings_balance; /* Is powersave balance needed for this sd */
        struct sched_group *group_min; /* Least loaded group in sd */
        struct sched_group *group_leader; /* Group which relieves group_min */
        unsigned long min_load_per_task; /* load_per_task in group_min */
        unsigned long leader_nr_running; /* Nr running of group_leader */
        unsigned long min_nr_running; /* Nr running of group_min */
#endif
};

/*
 * sg_lb_stats - stats of a sched_group required for load_balancing
 */
struct sg_lb_stats {
        unsigned long avg_load; /*Avg load across the CPUs of the group */
        unsigned long group_load; /* Total load over the CPUs of the group */
        unsigned long sum_nr_running; /* Nr tasks running in the group */
        unsigned long sum_weighted_load; /* Weighted load of group's tasks */
        unsigned long group_capacity;
        int group_imb; /* Is there an imbalance in the group ? */
};

/**
 * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
 * @group: The group whose first cpu is to be returned.
 */
static inline unsigned int group_first_cpu(struct sched_group *group)
{
        return cpumask_first(sched_group_cpus(group));
}

/**
 * get_sd_load_idx - Obtain the load index for a given sched domain.
 * @sd: The sched_domain whose load_idx is to be obtained.
 * @idle: The Idle status of the CPU for whose sd load_icx is obtained.
 */
static inline int get_sd_load_idx(struct sched_domain *sd,
                                        enum cpu_idle_type idle)
{
        int load_idx;

        switch (idle) {
        case CPU_NOT_IDLE:
                load_idx = sd->busy_idx;
                break;

        case CPU_NEWLY_IDLE:
                load_idx = sd->newidle_idx;
                break;
        default:
                load_idx = sd->idle_idx;
                break;
        }

        return load_idx;
}


#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
/**
 * init_sd_power_savings_stats - Initialize power savings statistics for
 * the given sched_domain, during load balancing.
 *
 * @sd: Sched domain whose power-savings statistics are to be initialized.
 * @sds: Variable containing the statistics for sd.
 * @idle: Idle status of the CPU at which we're performing load-balancing.
 */
static inline void init_sd_power_savings_stats(struct sched_domain *sd,
        struct sd_lb_stats *sds, enum cpu_idle_type idle)
{
        /*
         * Busy processors will not participate in power savings
         * balance.
         */
        if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
                sds->power_savings_balance = 0;
        else {
                sds->power_savings_balance = 1;
                sds->min_nr_running = ULONG_MAX;
                sds->leader_nr_running = 0;
        }
}

/**
 * update_sd_power_savings_stats - Update the power saving stats for a
 * sched_domain while performing load balancing.
 *
 * @group: sched_group belonging to the sched_domain under consideration.
 * @sds: Variable containing the statistics of the sched_domain
 * @local_group: Does group contain the CPU for which we're performing
 *              load balancing ?
 * @sgs: Variable containing the statistics of the group.
 */
static inline void update_sd_power_savings_stats(struct sched_group *group,
        struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
{

        if (!sds->power_savings_balance)
                return;

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

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

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

        /*
         * Calculate the group which is almost near its
         * capacity but still has some space to pick up some load
         * from other group and save more power
         */
        if (sgs->sum_nr_running + 1 > sgs->group_capacity)
                return;

        if (sgs->sum_nr_running > sds->leader_nr_running ||
            (sgs->sum_nr_running == sds->leader_nr_running &&
             group_first_cpu(group) < group_first_cpu(sds->group_leader))) {
                sds->group_leader = group;
                sds->leader_nr_running = sgs->sum_nr_running;
        }
}

/**
 * check_power_save_busiest_group - see if there is potential for some power-savings balance
 * @sds: Variable containing the statistics of the sched_domain
 *      under consideration.
 * @this_cpu: Cpu at which we're currently performing load-balancing.
 * @imbalance: Variable to store the imbalance.
 *
 * Description:
 * Check if we have potential to perform some power-savings balance.
 * If yes, set the busiest group to be the least loaded group in the
 * sched_domain, so that it's CPUs can be put to idle.
 *
 * Returns 1 if there is potential to perform power-savings balance.
 * Else returns 0.
 */
static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
                                        int this_cpu, unsigned long *imbalance)
{
        if (!sds->power_savings_balance)
                return 0;

        if (sds->this != sds->group_leader ||
                        sds->group_leader == sds->group_min)
                return 0;

        *imbalance = sds->min_load_per_task;
        sds->busiest = sds->group_min;

        return 1;

}
#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
static inline void init_sd_power_savings_stats(struct sched_domain *sd,
        struct sd_lb_stats *sds, enum cpu_idle_type idle)
{
        return;
}

static inline void update_sd_power_savings_stats(struct sched_group *group,
        struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
{
        return;
}

static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
                                        int this_cpu, unsigned long *imbalance)
{
        return 0;
}
#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */


unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu)
{
        return SCHED_LOAD_SCALE;
}

unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu)
{
        return default_scale_freq_power(sd, cpu);
}

unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
{
        unsigned long weight = cpumask_weight(sched_domain_span(sd));
        unsigned long smt_gain = sd->smt_gain;

        smt_gain /= weight;

        return smt_gain;
}

unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
{
        return default_scale_smt_power(sd, cpu);
}

unsigned long scale_rt_power(int cpu)
{
        struct rq *rq = cpu_rq(cpu);
        u64 total, available;

        sched_avg_update(rq);

        total = sched_avg_period() + (rq->clock - rq->age_stamp);
        available = total - rq->rt_avg;

        if (unlikely((s64)total < SCHED_LOAD_SCALE))
                total = SCHED_LOAD_SCALE;

        total >>= SCHED_LOAD_SHIFT;

        return div_u64(available, total);
}

static void update_cpu_power(struct sched_domain *sd, int cpu)
{
        unsigned long weight = cpumask_weight(sched_domain_span(sd));
        unsigned long power = SCHED_LOAD_SCALE;
        struct sched_group *sdg = sd->groups;

        if (sched_feat(ARCH_POWER))
                power *= arch_scale_freq_power(sd, cpu);
        else
                power *= default_scale_freq_power(sd, cpu);

        power >>= SCHED_LOAD_SHIFT;

        if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
                if (sched_feat(ARCH_POWER))
                        power *= arch_scale_smt_power(sd, cpu);
                else
                        power *= default_scale_smt_power(sd, cpu);

                power >>= SCHED_LOAD_SHIFT;
        }

        power *= scale_rt_power(cpu);
        power >>= SCHED_LOAD_SHIFT;

        if (!power)
                power = 1;

        sdg->cpu_power = power;
}

static void update_group_power(struct sched_domain *sd, int cpu)
{
        struct sched_domain *child = sd->child;
        struct sched_group *group, *sdg = sd->groups;
        unsigned long power;

        if (!child) {
                update_cpu_power(sd, cpu);
                return;
        }

        power = 0;

        group = child->groups;
        do {
                power += group->cpu_power;
                group = group->next;
        } while (group != child->groups);

        sdg->cpu_power = power;
}

/**
 * update_sg_lb_stats - Update sched_group's statistics for load balancing.
 * @sd: The sched_domain whose statistics are to be updated.
 * @group: sched_group whose statistics are to be updated.
 * @this_cpu: Cpu for which load balance is currently performed.
 * @idle: Idle status of this_cpu
 * @load_idx: Load index of sched_domain of this_cpu for load calc.
 * @sd_idle: Idle status of the sched_domain containing group.
 * @local_group: Does group contain this_cpu.
 * @cpus: Set of cpus considered for load balancing.
 * @balance: Should we balance.
 * @sgs: variable to hold the statistics for this group.
 */
static inline void update_sg_lb_stats(struct sched_domain *sd,
                        struct sched_group *group, int this_cpu,
                        enum cpu_idle_type idle, int load_idx, int *sd_idle,
                        int local_group, const struct cpumask *cpus,
                        int *balance, struct sg_lb_stats *sgs)
{
        unsigned long load, max_cpu_load, min_cpu_load;
        int i;
        unsigned int balance_cpu = -1, first_idle_cpu = 0;
        unsigned long sum_avg_load_per_task;
        unsigned long avg_load_per_task;

        if (local_group) {
                balance_cpu = group_first_cpu(group);
                if (balance_cpu == this_cpu)
                        update_group_power(sd, this_cpu);
        }

        /* Tally up the load of all CPUs in the group */
        sum_avg_load_per_task = avg_load_per_task = 0;
        max_cpu_load = 0;
        min_cpu_load = ~0UL;

        for_each_cpu_and(i, sched_group_cpus(group), cpus) {
                struct rq *rq = cpu_rq(i);

                if (*sd_idle && rq->nr_running)
                        *sd_idle = 0;

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

                        load = target_load(i, load_idx);
                } else {
                        load = source_load(i, load_idx);
                        if (load > max_cpu_load)
                                max_cpu_load = load;
                        if (min_cpu_load > load)
                                min_cpu_load = load;
                }

                sgs->group_load += load;
                sgs->sum_nr_running += rq->nr_running;
                sgs->sum_weighted_load += weighted_cpuload(i);

                sum_avg_load_per_task += cpu_avg_load_per_task(i);
        }

        /*
         * First idle cpu or the first cpu(busiest) in this sched group
         * is eligible for doing load balancing at this and above
         * domains. In the newly idle case, we will allow all the cpu's
         * to do the newly idle load balance.
         */
        if (idle != CPU_NEWLY_IDLE && local_group &&
            balance_cpu != this_cpu && balance) {
                *balance = 0;
                return;
        }

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


        /*
         * Consider the group unbalanced when the imbalance is larger
         * than the average weight of two tasks.
         *
         * APZ: with cgroup the avg task weight can vary wildly and
         *      might not be a suitable number - should we keep a
         *      normalized nr_running number somewhere that negates
         *      the hierarchy?
         */
        avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
                group->cpu_power;

        if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
                sgs->group_imb = 1;

        sgs->group_capacity =
                DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
}

/**
 * update_sd_lb_stats - Update sched_group's statistics for load balancing.
 * @sd: sched_domain whose statistics are to be updated.
 * @this_cpu: Cpu for which load balance is currently performed.
 * @idle: Idle status of this_cpu
 * @sd_idle: Idle status of the sched_domain containing group.
 * @cpus: Set of cpus considered for load balancing.
 * @balance: Should we balance.
 * @sds: variable to hold the statistics for this sched_domain.
 */
static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
                        enum cpu_idle_type idle, int *sd_idle,
                        const struct cpumask *cpus, int *balance,
                        struct sd_lb_stats *sds)
{
        struct sched_domain *child = sd->child;
        struct sched_group *group = sd->groups;
        struct sg_lb_stats sgs;
        int load_idx, prefer_sibling = 0;

        if (child && child->flags & SD_PREFER_SIBLING)
                prefer_sibling = 1;

        init_sd_power_savings_stats(sd, sds, idle);
        load_idx = get_sd_load_idx(sd, idle);

        do {
                int local_group;

                local_group = cpumask_test_cpu(this_cpu,
                                               sched_group_cpus(group));
                memset(&sgs, 0, sizeof(sgs));
                update_sg_lb_stats(sd, group, this_cpu, idle, load_idx, sd_idle,
                                local_group, cpus, balance, &sgs);

                if (local_group && balance && !(*balance))
                        return;

                sds->total_load += sgs.group_load;
                sds->total_pwr += group->cpu_power;

                /*
                 * In case the child domain prefers tasks go to siblings
                 * first, lower the group capacity to one so that we'll try
                 * and move all the excess tasks away.
                 */
                if (prefer_sibling)
                        sgs.group_capacity = min(sgs.group_capacity, 1UL);

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

                update_sd_power_savings_stats(group, sds, local_group, &sgs);
                group = group->next;
        } while (group != sd->groups);
}

/**
 * fix_small_imbalance - Calculate the minor imbalance that exists
 *                      amongst the groups of a sched_domain, during
 *                      load balancing.
 * @sds: Statistics of the sched_domain whose imbalance is to be calculated.
 * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
 * @imbalance: Variable to store the imbalance.
 */
static inline void fix_small_imbalance(struct sd_lb_stats *sds,
                                int this_cpu, unsigned long *imbalance)
{
        unsigned long tmp, pwr_now = 0, pwr_move = 0;
        unsigned int imbn = 2;

        if (sds->this_nr_running) {
                sds->this_load_per_task /= sds->this_nr_running;
                if (sds->busiest_load_per_task >
                                sds->this_load_per_task)
                        imbn = 1;
        } else
                sds->this_load_per_task =
                        cpu_avg_load_per_task(this_cpu);

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

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

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

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

        /* Move if we gain throughput */
        if (pwr_move > pwr_now)
                *imbalance = sds->busiest_load_per_task;
}

/**
 * calculate_imbalance - Calculate the amount of imbalance present within the
 *                       groups of a given sched_domain during load balance.
 * @sds: statistics of the sched_domain whose imbalance is to be calculated.
 * @this_cpu: Cpu for which currently load balance is being performed.
 * @imbalance: The variable to store the imbalance.
 */
static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
                unsigned long *imbalance)
{
        unsigned long max_pull;
        /*
         * In the presence of smp nice balancing, certain scenarios can have
         * max load less than avg load(as we skip the groups at or below
         * its cpu_power, while calculating max_load..)
         */
        if (sds->max_load < sds->avg_load) {
                *imbalance = 0;
                return fix_small_imbalance(sds, this_cpu, imbalance);
        }

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

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

        /*
         * if *imbalance is less than the average load per runnable task
         * there is no gaurantee that any tasks will be moved so we'll have
         * a think about bumping its value to force at least one task to be
         * moved
         */
        if (*imbalance < sds->busiest_load_per_task)
                return fix_small_imbalance(sds, this_cpu, imbalance);

}
/******* find_busiest_group() helpers end here *********************/

/**
 * find_busiest_group - Returns the busiest group within the sched_domain
 * if there is an imbalance. If there isn't an imbalance, and
 * the user has opted for power-savings, it returns a group whose
 * CPUs can be put to idle by rebalancing those tasks elsewhere, if
 * such a group exists.
 *
 * Also calculates the amount of weighted load which should be moved
 * to restore balance.
 *
 * @sd: The sched_domain whose busiest group is to be returned.
 * @this_cpu: The cpu for which load balancing is currently being performed.
 * @imbalance: Variable which stores amount of weighted load which should
 *              be moved to restore balance/put a group to idle.
 * @idle: The idle status of this_cpu.
 * @sd_idle: The idleness of sd
 * @cpus: The set of CPUs under consideration for load-balancing.
 * @balance: Pointer to a variable indicating if this_cpu
 *      is the appropriate cpu to perform load balancing at this_level.
 *
 * Returns:     - the busiest group if imbalance exists.
 *              - If no imbalance and user has opted for power-savings balance,
 *                 return the least loaded group whose CPUs can be
 *                 put to idle by rebalancing its tasks onto our group.
 */
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
                   unsigned long *imbalance, enum cpu_idle_type idle,
                   int *sd_idle, const struct cpumask *cpus, int *balance)
{
        struct sd_lb_stats sds;

        memset(&sds, 0, sizeof(sds));

        /*
         * Compute the various statistics relavent for load balancing at
         * this level.
         */
        update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus,
                                        balance, &sds);

        /* Cases where imbalance does not exist from POV of this_cpu */
        /* 1) this_cpu is not the appropriate cpu to perform load balancing
         *    at this level.
         * 2) There is no busy sibling group to pull from.
         * 3) This group is the busiest group.
         * 4) This group is more busy than the avg busieness at this
         *    sched_domain.
         * 5) The imbalance is within the specified limit.
         * 6) Any rebalance would lead to ping-pong
         */
        if (balance && !(*balance))
                goto ret;

        if (!sds.busiest || sds.busiest_nr_running == 0)
                goto out_balanced;

        if (sds.this_load >= sds.max_load)
                goto out_balanced;

        sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;

        if (sds.this_load >= sds.avg_load)
                goto out_balanced;

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

        sds.busiest_load_per_task /= sds.busiest_nr_running;
        if (sds.group_imb)
                sds.busiest_load_per_task =
                        min(sds.busiest_load_per_task, sds.avg_load);

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

        /* Looks like there is an imbalance. Compute it */
        calculate_imbalance(&sds, this_cpu, imbalance);
        return sds.busiest;

out_balanced:
        /*
         * There is no obvious imbalance. But check if we can do some balancing
         * to save power.
         */
        if (check_power_save_busiest_group(&sds, this_cpu, imbalance))
                return sds.busiest;
ret:
        *imbalance = 0;
        return NULL;
}

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

        for_each_cpu(i, sched_group_cpus(group)) {
                unsigned long power = power_of(i);
                unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
                unsigned long wl;

                if (!cpumask_test_cpu(i, cpus))
                        continue;

                rq = cpu_rq(i);
                wl = weighted_cpuload(i) * SCHED_LOAD_SCALE;
                wl /= power;

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

                if (wl > max_load) {
                        max_load = wl;
                        busiest = rq;
                }
        }

        return busiest;
}

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

/* Working cpumask for load_balance and load_balance_newidle. */
static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);

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

        cpumask_copy(cpus, cpu_online_mask);

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

        schedstat_inc(sd, lb_count[idle]);

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

        if (*balance == 0)
                goto out_balanced;

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

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

        BUG_ON(busiest == this_rq);

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

        ld_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. ld_moved simply stays zero, so it is
                 * correctly treated as an imbalance.
                 */
                local_irq_save(flags);
                double_rq_lock(this_rq, busiest);
                ld_moved = move_tasks(this_rq, this_cpu, busiest,
                                      imbalance, sd, idle, &all_pinned);
                double_rq_unlock(this_rq, busiest);
                local_irq_restore(flags);

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

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

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

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

                        spin_lock_irqsave(&busiest->lock, flags);

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

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

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

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

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

        goto out;

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

        sd->nr_balance_failed = 0;

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

        if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
            !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
                ld_moved = -1;
        else
                ld_moved = 0;
out:
        if (ld_moved)
                update_shares(sd);
        return ld_moved;
}

/*
 * 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 (CPU_NEWLY_IDLE).
 * this_rq is locked.
 */
static int
load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
{
        struct sched_group *group;
        struct rq *busiest = NULL;
        unsigned long imbalance;
        int ld_moved = 0;
        int sd_idle = 0;
        int all_pinned = 0;
        struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);

        cpumask_copy(cpus, cpu_online_mask);

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

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

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

        BUG_ON(busiest == this_rq);

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

        ld_moved = 0;
        if (busiest->nr_running > 1) {
                /* Attempt to move tasks */
                double_lock_balance(this_rq, busiest);
                /* this_rq->clock is already updated */
                update_rq_clock(busiest);
                ld_moved = move_tasks(this_rq, this_cpu, busiest,
                                        imbalance, sd, CPU_NEWLY_IDLE,
                                        &all_pinned);
                double_unlock_balance(this_rq, busiest);

                if (unlikely(all_pinned)) {
                        cpumask_clear_cpu(cpu_of(busiest), cpus);
                        if (!cpumask_empty(cpus))
                                goto redo;
                }
        }

        if (!ld_moved) {
                int active_balance = 0;

                schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]);
                if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
                    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
                        return -1;

                if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
                        return -1;

                if (sd->nr_balance_failed++ < 2)
                        return -1;

                /*
                 * The only task running in a non-idle cpu can be moved to this
                 * cpu in an attempt to completely freeup the other CPU
                 * package. The same method used to move task in load_balance()
                 * have been extended for load_balance_newidle() to speedup
                 * consolidation at sched_mc=POWERSAVINGS_BALANCE_WAKEUP (2)
                 *
                 * The package power saving logic comes from
                 * find_busiest_group().  If there are no imbalance, then
                 * f_b_g() will return NULL.  However when sched_mc={1,2} then
                 * f_b_g() will select a group from which a running task may be
                 * pulled to this cpu in order to make the other package idle.
                 * If there is no opportunity to make a package idle and if
                 * there are no imbalance, then f_b_g() will return NULL and no
                 * action will be taken in load_balance_newidle().
                 *
                 * Under normal task pull operation due to imbalance, there
                 * will be more than one task in the source run queue and
                 * move_tasks() will succeed.  ld_moved will be true and this
                 * active balance code will not be triggered.
                 */

                /* Lock busiest in correct order while this_rq is held */
                double_lock_balance(this_rq, busiest);

                /*
                 * don't kick the migration_thread, if the curr
                 * task on busiest cpu can't be moved to this_cpu
                 */
                if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
                        double_unlock_balance(this_rq, busiest);
                        all_pinned = 1;
                        return ld_moved;
                }

                if (!busiest->active_balance) {
                        busiest->active_balance = 1;
                        busiest->push_cpu = this_cpu;
                        active_balance = 1;
                }

                double_unlock_balance(this_rq, busiest);
                /*
                 * Should not call ttwu while holding a rq->lock
                 */
                spin_unlock(&this_rq->lock);
                if (active_balance)
                        wake_up_process(busiest->migration_thread);
                spin_lock(&this_rq->lock);

        } else
                sd->nr_balance_failed = 0;

        update_shares_locked(this_rq, sd);
        return ld_moved;

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

        return 0;
}

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

        this_rq->idle_stamp = this_rq->clock;

        if (this_rq->avg_idle < sysctl_sched_migration_cost)
                return;

        for_each_domain(this_cpu, sd) {
                unsigned long interval;

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

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

                interval = msecs_to_jiffies(sd->balance_interval);
                if (time_after(next_balance, sd->last_balance + interval))
                        next_balance = sd->last_balance + interval;
                if (pulled_task) {
                        this_rq->idle_stamp = 0;
                        break;
                }
        }
        if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
                /*
                 * We are going idle. next_balance may be set based on
                 * a busy processor. So reset next_balance.
                 */
                this_rq->next_balance = next_balance;
        }
}

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

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

        target_rq = cpu_rq(target_cpu);

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

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

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

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

                if (move_one_task(target_rq, target_cpu, busiest_rq,
                                  sd, CPU_IDLE))
                        schedstat_inc(sd, alb_pushed);
                else
                        schedstat_inc(sd, alb_failed);
        }
        double_unlock_balance(busiest_rq, target_rq);
}

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

int get_nohz_load_balancer(void)
{
        return atomic_read(&nohz.load_balancer);
}

#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
/**
 * lowest_flag_domain - Return lowest sched_domain containing flag.
 * @cpu:        The cpu whose lowest level of sched domain is to
 *              be returned.
 * @flag:       The flag to check for the lowest sched_domain
 *              for the given cpu.
 *
 * Returns the lowest sched_domain of a cpu which contains the given flag.
 */
static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
{
        struct sched_domain *sd;

        for_each_domain(cpu, sd)
                if (sd && (sd->flags & flag))
                        break;

        return sd;
}

/**
 * for_each_flag_domain - Iterates over sched_domains containing the flag.
 * @cpu:        The cpu whose domains we're iterating over.
 * @sd:         variable holding the value of the power_savings_sd
 *              for cpu.
 * @flag:       The flag to filter the sched_domains to be iterated.
 *
 * Iterates over all the scheduler domains for a given cpu that has the 'flag'
 * set, starting from the lowest sched_domain to the highest.
 */
#define for_each_flag_domain(cpu, sd, flag) \
        for (sd = lowest_flag_domain(cpu, flag); \
                (sd && (sd->flags & flag)); sd = sd->parent)

/**
 * is_semi_idle_group - Checks if the given sched_group is semi-idle.
 * @ilb_group:  group to be checked for semi-idleness
 *
 * Returns:     1 if the group is semi-idle. 0 otherwise.
 *
 * We define a sched_group to be semi idle if it has atleast one idle-CPU
 * and atleast one non-idle CPU. This helper function checks if the given
 * sched_group is semi-idle or not.
 */
static inline int is_semi_idle_group(struct sched_group *ilb_group)
{
        cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask,
                                        sched_group_cpus(ilb_group));

        /*
         * A sched_group is semi-idle when it has atleast one busy cpu
         * and atleast one idle cpu.
         */
        if (cpumask_empty(nohz.ilb_grp_nohz_mask))
                return 0;

        if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group)))
                return 0;

        return 1;
}
/**
 * find_new_ilb - Finds the optimum idle load balancer for nomination.
 * @cpu:        The cpu which is nominating a new idle_load_balancer.
 *
 * Returns:     Returns the id of the idle load balancer if it exists,
 *              Else, returns >= nr_cpu_ids.
 *
 * This algorithm picks the idle load balancer such that it belongs to a
 * semi-idle powersavings sched_domain. The idea is to try and avoid
 * completely idle packages/cores just for the purpose of idle load balancing
 * when there are other idle cpu's which are better suited for that job.
 */
static int find_new_ilb(int cpu)
{
        struct sched_domain *sd;
        struct sched_group *ilb_group;

        /*
         * Have idle load balancer selection from semi-idle packages only
         * when power-aware load balancing is enabled
         */
        if (!(sched_smt_power_savings || sched_mc_power_savings))
                goto out_done;

        /*
         * Optimize for the case when we have no idle CPUs or only one
         * idle CPU. Don't walk the sched_domain hierarchy in such cases
         */
        if (cpumask_weight(nohz.cpu_mask) < 2)
                goto out_done;

        for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) {
                ilb_group = sd->groups;

                do {
                        if (is_semi_idle_group(ilb_group))
                                return cpumask_first(nohz.ilb_grp_nohz_mask);

                        ilb_group = ilb_group->next;

                } while (ilb_group != sd->groups);
        }

out_done:
        return cpumask_first(nohz.cpu_mask);
}
#else /*  (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
static inline int find_new_ilb(int call_cpu)
{
        return cpumask_first(nohz.cpu_mask);
}
#endif

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

        if (stop_tick) {
                cpu_rq(cpu)->in_nohz_recently = 1;

                if (!cpu_active(cpu)) {
                        if (atomic_read(&nohz.load_balancer) != cpu)
                                return 0;

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

                        return 0;
                }

                cpumask_set_cpu(cpu, nohz.cpu_mask);

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

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

                        if (!(sched_smt_power_savings ||
                                                sched_mc_power_savings))
                                return 1;
                        /*
                         * Check to see if there is a more power-efficient
                         * ilb.
                         */
                        new_ilb = find_new_ilb(cpu);
                        if (new_ilb < nr_cpu_ids && new_ilb != cpu) {
                                atomic_set(&nohz.load_balancer, -1);
                                resched_cpu(new_ilb);
                                return 0;
                        }
                        return 1;
                }
        } else {
                if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
                        return 0;

                cpumask_clear_cpu(cpu, nohz.cpu_mask);

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

static DEFINE_SPINLOCK(balancing);

/*
 * It checks each scheduling domain to see if it is due to be balanced,
 * and initiates a balancing operation if so.
 *
 * Balancing parameters are set up in arch_init_sched_domains.
 */
static void rebalance_domains(int cpu, enum cpu_idle_type idle)
{
        int balance = 1;
        struct rq *rq = cpu_rq(cpu);
        unsigned long interval;
        struct sched_domain *sd;
        /* Earliest time when we have to do rebalance again */
        unsigned long next_balance = jiffies + 60*HZ;
        int update_next_balance = 0;
        int need_serialize;

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

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

                /* scale ms to jiffies */
                interval = msecs_to_jiffies(interval);
                if (unlikely(!interval))
                        interval = 1;
                if (interval > HZ*NR_CPUS/10)
                        interval = HZ*NR_CPUS/10;

                need_serialize = sd->flags & SD_SERIALIZE;

                if (need_serialize) {
                        if (!spin_trylock(&balancing))
                                goto out;
                }

                if (time_after_eq(jiffies, sd->last_balance + interval)) {
                        if (load_balance(cpu, rq, sd, idle, &balance)) {
                                /*
                                 * We've pulled tasks over so either we're no
                                 * longer idle, or one of our SMT siblings is
                                 * not idle.
                                 */
                                idle = CPU_NOT_IDLE;
                        }
                        sd->last_balance = jiffies;
                }
                if (need_serialize)
                        spin_unlock(&balancing);
out:
                if (time_after(next_balance, sd->last_balance + interval)) {
                        next_balance = sd->last_balance + interval;
                        update_next_balance = 1;
                }

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

        /*
         * next_balance will be updated only when there is a need.
         * When the cpu is attached to null domain for ex, it will not be
         * updated.
         */
        if (likely(update_next_balance))
                rq->next_balance = next_balance;
}

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

        rebalance_domains(this_cpu, idle);

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

                for_each_cpu(balance_cpu, nohz.cpu_mask) {
                        if (balance_cpu == this_cpu)
                                continue;

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

                        rebalance_domains(balance_cpu, CPU_IDLE);

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

static inline int on_null_domain(int cpu)
{
        return !rcu_dereference(cpu_rq(cpu)->sd);
}

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

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

                if (atomic_read(&nohz.load_balancer) == -1) {
                        int ilb = find_new_ilb(cpu);

                        if (ilb < nr_cpu_ids)
                                resched_cpu(ilb);
                }
        }

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

        /*
         * If this cpu is idle and the idle load balancing is done by
         * someone else, then no need raise the SCHED_SOFTIRQ
         */
        if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu &&
            cpumask_test_cpu(cpu, nohz.cpu_mask))
                return;
#endif
        /* Don't need to rebalance while attached to NULL domain */
        if (time_after_eq(jiffies, rq->next_balance) &&
            likely(!on_null_domain(cpu)))
                raise_softirq(SCHED_SOFTIRQ);
}

#else   /* CONFIG_SMP */

/*
 * on UP we do not need to balance between CPUs:
 */
static inline void idle_balance(int cpu, struct rq *rq)
{
}

#endif

DEFINE_PER_CPU(struct kernel_stat, kstat);

EXPORT_PER_CPU_SYMBOL(kstat);

/*
 * Return any ns on the sched_clock that have not yet been accounted in
 * @p in case that task is currently running.
 *
 * Called with task_rq_lock() held on @rq.
 */
static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
{
        u64 ns = 0;

        if (task_current(rq, p)) {
                update_rq_clock(rq);
                ns = rq->clock - p->se.exec_start;
                if ((s64)ns < 0)
                        ns = 0;
        }

        return ns;
}

unsigned long long task_delta_exec(struct task_struct *p)
{
        unsigned long flags;
        struct rq *rq;
        u64 ns = 0;

        rq = task_rq_lock(p, &flags);
        ns = do_task_delta_exec(p, rq);
        task_rq_unlock(rq, &flags);

        return ns;
}

/*
 * Return accounted runtime for the task.
 * In case the task is currently running, return the runtime plus current's
 * pending runtime that have not been accounted yet.
 */
unsigned long long task_sched_runtime(struct task_struct *p)
{
        unsigned long flags;
        struct rq *rq;
        u64 ns = 0;

        rq = task_rq_lock(p, &flags);
        ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq);
        task_rq_unlock(rq, &flags);

        return ns;
}

/*
 * Return sum_exec_runtime for the thread group.
 * In case the task is currently running, return the sum plus current's
 * pending runtime that have not been accounted yet.
 *
 * Note that the thread group might have other running tasks as well,
 * so the return value not includes other pending runtime that other
 * running tasks might have.
 */
unsigned long long thread_group_sched_runtime(struct task_struct *p)
{
        struct task_cputime totals;
        unsigned long flags;
        struct rq *rq;
        u64 ns;

        rq = task_rq_lock(p, &flags);
        thread_group_cputime(p, &totals);
        ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq);
        task_rq_unlock(rq, &flags);

        return ns;
}

/*
 * Account user cpu time to a process.
 * @p: the process that the cpu time gets accounted to
 * @cputime: the cpu time spent in user space since the last update
 * @cputime_scaled: cputime scaled by cpu frequency
 */
void account_user_time(struct task_struct *p, cputime_t cputime,
                       cputime_t cputime_scaled)
{
        struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
        cputime64_t tmp;

        /* Add user time to process. */
        p->utime = cputime_add(p->utime, cputime);
        p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
        account_group_user_time(p, cputime);

        /* Add user time to cpustat. */
        tmp = cputime_to_cputime64(cputime);
        if (TASK_NICE(p) > 0)
                cpustat->nice = cputime64_add(cpustat->nice, tmp);
        else
                cpustat->user = cputime64_add(cpustat->user, tmp);

        cpuacct_update_stats(p, CPUACCT_STAT_USER, cputime);
        /* Account for user time used */
        acct_update_integrals(p);
}

/*
 * Account guest cpu time to a process.
 * @p: the process that the cpu time gets accounted to
 * @cputime: the cpu time spent in virtual machine since the last update
 * @cputime_scaled: cputime scaled by cpu frequency
 */
static void account_guest_time(struct task_struct *p, cputime_t cputime,
                               cputime_t cputime_scaled)
{
        cputime64_t tmp;
        struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;

        tmp = cputime_to_cputime64(cputime);

        /* Add guest time to process. */
        p->utime = cputime_add(p->utime, cputime);
        p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
        account_group_user_time(p, cputime);
        p->gtime = cputime_add(p->gtime, cputime);

        /* Add guest time to cpustat. */
        if (TASK_NICE(p) > 0) {
                cpustat->nice = cputime64_add(cpustat->nice, tmp);
                cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp);
        } else {
                cpustat->user = cputime64_add(cpustat->user, tmp);
                cpustat->guest = cputime64_add(cpustat->guest, tmp);
        }
}

/*
 * Account system cpu time to a process.
 * @p: the process that the cpu time gets accounted to
 * @hardirq_offset: the offset to subtract from hardirq_count()
 * @cputime: the cpu time spent in kernel space since the last update
 * @cputime_scaled: cputime scaled by cpu frequency
 */
void account_system_time(struct task_struct *p, int hardirq_offset,
                         cputime_t cputime, cputime_t cputime_scaled)
{
        struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
        cputime64_t tmp;

        if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
                account_guest_time(p, cputime, cputime_scaled);
                return;
        }

        /* Add system time to process. */
        p->stime = cputime_add(p->stime, cputime);
        p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
        account_group_system_time(p, cputime);

        /* Add system time to cpustat. */
        tmp = cputime_to_cputime64(cputime);
        if (hardirq_count() - hardirq_offset)
                cpustat->irq = cputime64_add(cpustat->irq, tmp);
        else if (softirq_count())
                cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
        else
                cpustat->system = cputime64_add(cpustat->system, tmp);

        cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);

        /* Account for system time used */
        acct_update_integrals(p);
}

/*
 * Account for involuntary wait time.
 * @steal: the cpu time spent in involuntary wait
 */
void account_steal_time(cputime_t cputime)
{
        struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
        cputime64_t cputime64 = cputime_to_cputime64(cputime);

        cpustat->steal = cputime64_add(cpustat->steal, cputime64);
}

/*
 * Account for idle time.
 * @cputime: the cpu time spent in idle wait
 */
void account_idle_time(cputime_t cputime)
{
        struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
        cputime64_t cputime64 = cputime_to_cputime64(cputime);
        struct rq *rq = this_rq();

        if (atomic_read(&rq->nr_iowait) > 0)
                cpustat->iowait = cputime64_add(cpustat->iowait, cputime64);
        else
                cpustat->idle = cputime64_add(cpustat->idle, cputime64);
}

#ifndef CONFIG_VIRT_CPU_ACCOUNTING

/*
 * Account a single tick of cpu time.
 * @p: the process that the cpu time gets accounted to
 * @user_tick: indicates if the tick is a user or a system tick
 */
void account_process_tick(struct task_struct *p, int user_tick)
{
        cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
        struct rq *rq = this_rq();

        if (user_tick)
                account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
        else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
                account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
                                    one_jiffy_scaled);
        else
                account_idle_time(cputime_one_jiffy);
}

/*
 * Account multiple ticks of steal time.
 * @p: the process from which the cpu time has been stolen
 * @ticks: number of stolen ticks
 */
void account_steal_ticks(unsigned long ticks)
{
        account_steal_time(jiffies_to_cputime(ticks));
}

/*
 * Account multiple ticks of idle time.
 * @ticks: number of stolen ticks
 */
void account_idle_ticks(unsigned long ticks)
{
        account_idle_time(jiffies_to_cputime(ticks));
}

#endif

/*
 * Use precise platform statistics if available:
 */
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
        *ut = p->utime;
        *st = p->stime;
}
#else

#ifndef nsecs_to_cputime
# define nsecs_to_cputime(__nsecs)      nsecs_to_jiffies(__nsecs)
#endif

void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
        cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime);

        /*
         * Use CFS's precise accounting:
         */
        rtime = nsecs_to_cputime(p->se.sum_exec_runtime);

        if (total) {
                u64 temp;

                temp = (u64)(rtime * utime);
                do_div(temp, total);
                utime = (cputime_t)temp;
        } else
                utime = rtime;

        /*
         * Compare with previous values, to keep monotonicity:
         */
        p->prev_utime = max(p->prev_utime, utime);
        p->prev_stime = max(p->prev_stime, cputime_sub(rtime, p->prev_utime));

        *ut = p->prev_utime;
        *st = p->prev_stime;
}
#endif

/*
 * 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(void)
{
        int cpu = smp_processor_id();
        struct rq *rq = cpu_rq(cpu);
        struct task_struct *curr = rq->curr;

        sched_clock_tick();

        spin_lock(&rq->lock);
        update_rq_clock(rq);
        update_cpu_load(rq);
        curr->sched_class->task_tick(rq, curr, 0);
        spin_unlock(&rq->lock);

        perf_event_task_tick(curr, cpu);

#ifdef CONFIG_SMP
        rq->idle_at_tick = idle_cpu(cpu);
        trigger_load_balance(rq, cpu);
#endif
}

notrace unsigned long get_parent_ip(unsigned long addr)
{
        if (in_lock_functions(addr)) {
                addr = CALLER_ADDR2;
                if (in_lock_functions(addr))
                        addr = CALLER_ADDR3;
        }
        return addr;
}

#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
                                defined(CONFIG_PREEMPT_TRACER))

void __kprobes add_preempt_count(int val)
{
#ifdef CONFIG_DEBUG_PREEMPT
        /*
         * Underflow?
         */
        if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
                return;
#endif
        preempt_count() += val;
#ifdef CONFIG_DEBUG_PREEMPT
        /*
         * Spinlock count overflowing soon?
         */
        DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
                                PREEMPT_MASK - 10);
#endif
        if (preempt_count() == val)
                trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
}
EXPORT_SYMBOL(add_preempt_count);

void __kprobes sub_preempt_count(int val)
{
#ifdef CONFIG_DEBUG_PREEMPT
        /*
         * Underflow?
         */
        if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
                return;
        /*
         * Is the spinlock portion underflowing?
         */
        if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
                        !(preempt_count() & PREEMPT_MASK)))
                return;
#endif

        if (preempt_count() == val)
                trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
        preempt_count() -= val;
}
EXPORT_SYMBOL(sub_preempt_count);

#endif

/*
 * Print scheduling while atomic bug:
 */
static noinline void __schedule_bug(struct task_struct *prev)
{
        struct pt_regs *regs = get_irq_regs();

        printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
                prev->comm, prev->pid, preempt_count());

        debug_show_held_locks(prev);
        print_modules();
        if (irqs_disabled())
                print_irqtrace_events(prev);

        if (regs)
                show_regs(regs);
        else
                dump_stack();
}

/*
 * Various schedule()-time debugging checks and statistics:
 */
static inline void schedule_debug(struct task_struct *prev)
{
        /*
         * 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 (unlikely(in_atomic_preempt_off() && !prev->exit_state))
                __schedule_bug(prev);

        profile_hit(SCHED_PROFILING, __builtin_return_address(0));

        schedstat_inc(this_rq(), sched_count);
#ifdef CONFIG_SCHEDSTATS
        if (unlikely(prev->lock_depth >= 0)) {
                schedstat_inc(this_rq(), bkl_count);
                schedstat_inc(prev, sched_info.bkl_count);
        }
#endif
}

static void put_prev_task(struct rq *rq, struct task_struct *p)
{
        u64 runtime = p->se.sum_exec_runtime - p->se.prev_sum_exec_runtime;

        update_avg(&p->se.avg_running, runtime);

        if (p->state == TASK_RUNNING) {
                /*
                 * In order to avoid avg_overlap growing stale when we are
                 * indeed overlapping and hence not getting put to sleep, grow
                 * the avg_overlap on preemption.
                 *
                 * We use the average preemption runtime because that
                 * correlates to the amount of cache footprint a task can
                 * build up.
                 */
                runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
                update_avg(&p->se.avg_overlap, runtime);
        } else {
                update_avg(&p->se.avg_running, 0);
        }
        p->sched_class->put_prev_task(rq, p);
}

/*
 * Pick up the highest-prio task:
 */
static inline struct task_struct *
pick_next_task(struct rq *rq)
{
        const struct sched_class *class;
        struct task_struct *p;

        /*
         * Optimization: we know that if all tasks are in
         * the fair class we can call that function directly:
         */
        if (likely(rq->nr_running == rq->cfs.nr_running)) {
                p = fair_sched_class.pick_next_task(rq);
                if (likely(p))
                        return p;
        }

        class = sched_class_highest;
        for ( ; ; ) {
                p = class->pick_next_task(rq);
                if (p)
                        return p;
                /*
                 * Will never be NULL as the idle class always
                 * returns a non-NULL p:
                 */
                class = class->next;
        }
}

/*
 * schedule() is the main scheduler function.
 */
asmlinkage void __sched schedule(void)
{
        struct task_struct *prev, *next;
        unsigned long *switch_count;
        struct rq *rq;
        int cpu;

need_resched:
        preempt_disable();
        cpu = smp_processor_id();
        rq = cpu_rq(cpu);
        rcu_sched_qs(cpu);
        prev = rq->curr;
        switch_count = &prev->nivcsw;

        release_kernel_lock(prev);
need_resched_nonpreemptible:

        schedule_debug(prev);

        if (sched_feat(HRTICK))
                hrtick_clear(rq);

        spin_lock_irq(&rq->lock);
        update_rq_clock(rq);
        clear_tsk_need_resched(prev);

        if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
                if (unlikely(signal_pending_state(prev->state, prev)))
                        prev->state = TASK_RUNNING;
                else
                        deactivate_task(rq, prev, 1);
                switch_count = &prev->nvcsw;
        }

        pre_schedule(rq, prev);

        if (unlikely(!rq->nr_running))
                idle_balance(cpu, rq);

        put_prev_task(rq, prev);
        next = pick_next_task(rq);

        if (likely(prev != next)) {
                sched_info_switch(prev, next);
                perf_event_task_sched_out(prev, next, cpu);

                rq->nr_switches++;
                rq->curr = next;
                ++*switch_count;

                context_switch(rq, prev, next); /* unlocks the rq */
                /*
                 * the context switch might have flipped the stack from under
                 * us, hence refresh the local variables.
                 */
                cpu = smp_processor_id();
                rq = cpu_rq(cpu);
        } else
                spin_unlock_irq(&rq->lock);

        post_schedule(rq);

        if (unlikely(reacquire_kernel_lock(current) < 0))
                goto need_resched_nonpreemptible;

        preempt_enable_no_resched();
        if (need_resched())
                goto need_resched;
}
EXPORT_SYMBOL(schedule);

#ifdef CONFIG_SMP
/*
 * Look out! "owner" is an entirely speculative pointer
 * access and not reliable.
 */
int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
{
        unsigned int cpu;
        struct rq *rq;

        if (!sched_feat(OWNER_SPIN))
                return 0;

#ifdef CONFIG_DEBUG_PAGEALLOC
        /*
         * Need to access the cpu field knowing that
         * DEBUG_PAGEALLOC could have unmapped it if
         * the mutex owner just released it and exited.
         */
        if (probe_kernel_address(&owner->cpu, cpu))
                goto out;
#else
        cpu = owner->cpu;
#endif

        /*
         * Even if the access succeeded (likely case),
         * the cpu field may no longer be valid.
         */
        if (cpu >= nr_cpumask_bits)
                goto out;

        /*
         * We need to validate that we can do a
         * get_cpu() and that we have the percpu area.
         */
        if (!cpu_online(cpu))
                goto out;

        rq = cpu_rq(cpu);

        for (;;) {
                /*
                 * Owner changed, break to re-assess state.
                 */
                if (lock->owner != owner)
                        break;

                /*
                 * Is that owner really running on that cpu?
                 */
                if (task_thread_info(rq->curr) != owner || need_resched())
                        return 0;

                cpu_relax();
        }
out:
        return 1;
}
#endif

#ifdef CONFIG_PREEMPT
/*
 * this is the entry point to schedule() from in-kernel preemption
 * off of preempt_enable. Kernel preemptions off return from interrupt
 * occur there and call schedule directly.
 */
asmlinkage void __sched preempt_schedule(void)
{
        struct thread_info *ti = current_thread_info();

        /*
         * If there is a non-zero preempt_count or interrupts are disabled,
         * we do not want to preempt the current task. Just return..
         */
        if (likely(ti->preempt_count || irqs_disabled()))
                return;

        do {
                add_preempt_count(PREEMPT_ACTIVE);
                schedule();
                sub_preempt_count(PREEMPT_ACTIVE);

                /*
                 * Check again in case we missed a preemption opportunity
                 * between schedule and now.
                 */
                barrier();
        } while (need_resched());
}
EXPORT_SYMBOL(preempt_schedule);

/*
 * this is the entry point to schedule() from kernel preemption
 * off of irq context.
 * Note, that this is called and return with irqs disabled. This will
 * protect us against recursive calling from irq.
 */
asmlinkage void __sched preempt_schedule_irq(void)
{
        struct thread_info *ti = current_thread_info();

        /* Catch callers which need to be fixed */
        BUG_ON(ti->preempt_count || !irqs_disabled());

        do {
                add_preempt_count(PREEMPT_ACTIVE);
                local_irq_enable();
                schedule();
                local_irq_disable();
                sub_preempt_count(PREEMPT_ACTIVE);

                /*
                 * Check again in case we missed a preemption opportunity
                 * between schedule and now.
                 */
                barrier();
        } while (need_resched());
}

#endif /* CONFIG_PREEMPT */

int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
                          void *key)
{
        return try_to_wake_up(curr->private, mode, wake_flags);
}
EXPORT_SYMBOL(default_wake_function);

/*
 * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
 * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
 * number) then we wake all the non-exclusive tasks and one exclusive task.
 *
 * There are circumstances in which we can try to wake a task which has already
 * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
 * zero in this (rare) case, and we handle it by continuing to scan the queue.
 */
static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
                        int nr_exclusive, int wake_flags, void *key)
{
        wait_queue_t *curr, *next;

        list_for_each_entry_safe(curr, next, &q->task_list, task_list) {
                unsigned flags = curr->flags;

                if (curr->func(curr, mode, wake_flags, key) &&
                                (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
                        break;
        }
}

/**
 * __wake_up - wake up threads blocked on a waitqueue.
 * @q: the waitqueue
 * @mode: which threads
 * @nr_exclusive: how many wake-one or wake-many threads to wake up
 * @key: is directly passed to the wakeup function
 *
 * It may be assumed that this function implies a write memory barrier before
 * changing the task state if and only if any tasks are woken up.
 */
void __wake_up(wait_queue_head_t *q, unsigned int mode,
                        int nr_exclusive, void *key)
{
        unsigned long flags;

        spin_lock_irqsave(&q->lock, flags);
        __wake_up_common(q, mode, nr_exclusive, 0, key);
        spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(__wake_up);

/*
 * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
 */
void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
{
        __wake_up_common(q, mode, 1, 0, NULL);
}

void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
{
        __wake_up_common(q, mode, 1, 0, key);
}

/**
 * __wake_up_sync_key - wake up threads blocked on a waitqueue.
 * @q: the waitqueue
 * @mode: which threads
 * @nr_exclusive: how many wake-one or wake-many threads to wake up
 * @key: opaque value to be passed to wakeup targets
 *
 * The sync wakeup differs that the waker knows that it will schedule
 * away soon, so while the target thread will be woken up, it will not
 * be migrated to another CPU - ie. the two threads are 'synchronized'
 * with each other. This can prevent needless bouncing between CPUs.
 *
 * On UP it can prevent extra preemption.
 *
 * It may be assumed that this function implies a write memory barrier before
 * changing the task state if and only if any tasks are woken up.
 */
void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
                        int nr_exclusive, void *key)
{
        unsigned long flags;
        int wake_flags = WF_SYNC;

        if (unlikely(!q))
                return;

        if (unlikely(!nr_exclusive))
                wake_flags = 0;

        spin_lock_irqsave(&q->lock, flags);
        __wake_up_common(q, mode, nr_exclusive, wake_flags, key);
        spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL_GPL(__wake_up_sync_key);

/*
 * __wake_up_sync - see __wake_up_sync_key()
 */
void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
{
        __wake_up_sync_key(q, mode, nr_exclusive, NULL);
}
EXPORT_SYMBOL_GPL(__wake_up_sync);      /* For internal use only */

/**
 * complete: - signals a single thread waiting on this completion
 * @x:  holds the state of this particular completion
 *
 * This will wake up a single thread waiting on this completion. Threads will be
 * awakened in the same order in which they were queued.
 *
 * See also complete_all(), wait_for_completion() and related routines.
 *
 * It may be assumed that this function implies a write memory barrier before
 * changing the task state if and only if any tasks are woken up.
 */
void complete(struct completion *x)
{
        unsigned long flags;

        spin_lock_irqsave(&x->wait.lock, flags);
        x->done++;
        __wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL);
        spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete);

/**
 * complete_all: - signals all threads waiting on this completion
 * @x:  holds the state of this particular completion
 *
 * This will wake up all threads waiting on this particular completion event.
 *
 * It may be assumed that this function implies a write memory barrier before
 * changing the task state if and only if any tasks are woken up.
 */
void complete_all(struct completion *x)
{
        unsigned long flags;

        spin_lock_irqsave(&x->wait.lock, flags);
        x->done += UINT_MAX/2;
        __wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL);
        spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete_all);

static inline long __sched
do_wait_for_common(struct completion *x, long timeout, int state)
{
        if (!x->done) {
                DECLARE_WAITQUEUE(wait, current);

                wait.flags |= WQ_FLAG_EXCLUSIVE;
                __add_wait_queue_tail(&x->wait, &wait);
                do {
                        if (signal_pending_state(state, current)) {
                                timeout = -ERESTARTSYS;
                                break;
                        }
                        __set_current_state(state);
                        spin_unlock_irq(&x->wait.lock);
                        timeout = schedule_timeout(timeout);
                        spin_lock_irq(&x->wait.lock);
                } while (!x->done && timeout);
                __remove_wait_queue(&x->wait, &wait);
                if (!x->done)
                        return timeout;
        }
        x->done--;
        return timeout ?: 1;
}

static long __sched
wait_for_common(struct completion *x, long timeout, int state)
{
        might_sleep();

        spin_lock_irq(&x->wait.lock);
        timeout = do_wait_for_common(x, timeout, state);
        spin_unlock_irq(&x->wait.lock);
        return timeout;
}

/**
 * wait_for_completion: - waits for completion of a task
 * @x:  holds the state of this particular completion
 *
 * This waits to be signaled for completion of a specific task. It is NOT
 * interruptible and there is no timeout.
 *
 * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
 * and interrupt capability. Also see complete().
 */
void __sched wait_for_completion(struct completion *x)
{
        wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_for_completion);

/**
 * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
 * @x:  holds the state of this particular completion
 * @timeout:  timeout value in jiffies
 *
 * This waits for either a completion of a specific task to be signaled or for a
 * specified timeout to expire. The timeout is in jiffies. It is not
 * interruptible.
 */
unsigned long __sched
wait_for_completion_timeout(struct completion *x, unsigned long timeout)
{
        return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_for_completion_timeout);

/**
 * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
 * @x:  holds the state of this particular completion
 *
 * This waits for completion of a specific task to be signaled. It is
 * interruptible.
 */
int __sched wait_for_completion_interruptible(struct completion *x)
{
        long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
        if (t == -ERESTARTSYS)
                return t;
        return 0;
}
EXPORT_SYMBOL(wait_for_completion_interruptible);

/**
 * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
 * @x:  holds the state of this particular completion
 * @timeout:  timeout value in jiffies
 *
 * This waits for either a completion of a specific task to be signaled or for a
 * specified timeout to expire. It is interruptible. The timeout is in jiffies.
 */
unsigned long __sched
wait_for_completion_interruptible_timeout(struct completion *x,
                                          unsigned long timeout)
{
        return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);

/**
 * wait_for_completion_killable: - waits for completion of a task (killable)
 * @x:  holds the state of this particular completion
 *
 * This waits to be signaled for completion of a specific task. It can be
 * interrupted by a kill signal.
 */
int __sched wait_for_completion_killable(struct completion *x)
{
        long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
        if (t == -ERESTARTSYS)
                return t;
        return 0;
}
EXPORT_SYMBOL(wait_for_completion_killable);

/**
 *      try_wait_for_completion - try to decrement a completion without blocking
 *      @x:     completion structure
 *
 *      Returns: 0 if a decrement cannot be done without blocking
 *               1 if a decrement succeeded.
 *
 *      If a completion is being used as a counting completion,
 *      attempt to decrement the counter without blocking. This
 *      enables us to avoid waiting if the resource the completion
 *      is protecting is not available.
 */
bool try_wait_for_completion(struct completion *x)
{
        int ret = 1;

        spin_lock_irq(&x->wait.lock);
        if (!x->done)
                ret = 0;
        else
                x->done--;
        spin_unlock_irq(&x->wait.lock);
        return ret;
}
EXPORT_SYMBOL(try_wait_for_completion);

/**
 *      completion_done - Test to see if a completion has any waiters
 *      @x:     completion structure
 *
 *      Returns: 0 if there are waiters (wait_for_completion() in progress)
 *               1 if there are no waiters.
 *
 */
bool completion_done(struct completion *x)
{
        int ret = 1;

        spin_lock_irq(&x->wait.lock);
        if (!x->done)
                ret = 0;
        spin_unlock_irq(&x->wait.lock);
        return ret;
}
EXPORT_SYMBOL(completion_done);

static long __sched
sleep_on_common(wait_queue_head_t *q, int state, long timeout)
{
        unsigned long flags;
        wait_queue_t wait;

        init_waitqueue_entry(&wait, current);

        __set_current_state(state);

        spin_lock_irqsave(&q->lock, flags);
        __add_wait_queue(q, &wait);
        spin_unlock(&q->lock);
        timeout = schedule_timeout(timeout);
        spin_lock_irq(&q->lock);
        __remove_wait_queue(q, &wait);
        spin_unlock_irqrestore(&q->lock, flags);

        return timeout;
}

void __sched interruptible_sleep_on(wait_queue_head_t *q)
{
        sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
}
EXPORT_SYMBOL(interruptible_sleep_on);

long __sched
interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
{
        return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout);
}
EXPORT_SYMBOL(interruptible_sleep_on_timeout);

void __sched sleep_on(wait_queue_head_t *q)
{
        sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
}
EXPORT_SYMBOL(sleep_on);

long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
{
        return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout);
}
EXPORT_SYMBOL(sleep_on_timeout);

#ifdef CONFIG_RT_MUTEXES

/*
 * rt_mutex_setprio - set the current priority of a task
 * @p: task
 * @prio: prio value (kernel-internal form)
 *
 * This function changes the 'effective' priority of a task. It does
 * not touch ->normal_prio like __setscheduler().
 *
 * Used by the rt_mutex code to implement priority inheritance logic.
 */
void rt_mutex_setprio(struct task_struct *p, int prio)
{
        unsigned long flags;
        int oldprio, on_rq, running;
        struct rq *rq;
        const struct sched_class *prev_class = p->sched_class;

        BUG_ON(prio < 0 || prio > MAX_PRIO);

        rq = task_rq_lock(p, &flags);
        update_rq_clock(rq);

        oldprio = p->prio;
        on_rq = p->se.on_rq;
        running = task_current(rq, p);
        if (on_rq)
                dequeue_task(rq, p, 0);
        if (running)
                p->sched_class->put_prev_task(rq, p);

        if (rt_prio(prio))
                p->sched_class = &rt_sched_class;
        else
                p->sched_class = &fair_sched_class;

        p->prio = prio;

        if (running)
                p->sched_class->set_curr_task(rq);
        if (on_rq) {
                enqueue_task(rq, p, 0);

                check_class_changed(rq, p, prev_class, oldprio, running);
        }
        task_rq_unlock(rq, &flags);
}

#endif

void set_user_nice(struct task_struct *p, long nice)
{
        int old_prio, delta, on_rq;
        unsigned long flags;
        struct rq *rq;

        if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
                return;
        /*
         * We have to be careful, if called from sys_setpriority(),
         * the task might be in the middle of scheduling on another CPU.
         */
        rq = task_rq_lock(p, &flags);
        update_rq_clock(rq);
        /*
         * The RT priorities are set via sched_setscheduler(), but we still
         * allow the 'normal' nice value to be set - but as expected
         * it wont have any effect on scheduling until the task is
         * SCHED_FIFO/SCHED_RR:
         */
        if (task_has_rt_policy(p)) {
                p->static_prio = NICE_TO_PRIO(nice);
                goto out_unlock;
        }
        on_rq = p->se.on_rq;
        if (on_rq)
                dequeue_task(rq, p, 0);

        p->static_prio = NICE_TO_PRIO(nice);
        set_load_weight(p);
        old_prio = p->prio;
        p->prio = effective_prio(p);
        delta = p->prio - old_prio;

        if (on_rq) {
                enqueue_task(rq, p, 0);
                /*
                 * If the task increased its priority or is running and
                 * lowered its priority, then reschedule its CPU:
                 */
                if (delta < 0 || (delta > 0 && task_running(rq, p)))
                        resched_task(rq->curr);
        }
out_unlock:
        task_rq_unlock(rq, &flags);
}
EXPORT_SYMBOL(set_user_nice);

/*
 * can_nice - check if a task can reduce its nice value
 * @p: task
 * @nice: nice value
 */
int can_nice(const struct task_struct *p, const int nice)
{
        /* convert nice value [19,-20] to rlimit style value [1,40] */
        int nice_rlim = 20 - nice;

        return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur ||
                capable(CAP_SYS_NICE));
}

#ifdef __ARCH_WANT_SYS_NICE

/*
 * sys_nice - change the priority of the current process.
 * @increment: priority increment
 *
 * sys_setpriority is a more generic, but much slower function that
 * does similar things.
 */
SYSCALL_DEFINE1(nice, int, increment)
{
        long nice, retval;

        /*
         * Setpriority might change our priority at the same moment.
         * We don't have to worry. Conceptually one call occurs first
         * and we have a single winner.
         */
        if (increment < -40)
                increment = -40;
        if (increment > 40)
                increment = 40;

        nice = TASK_NICE(current) + increment;
        if (nice < -20)
                nice = -20;
        if (nice > 19)
                nice = 19;

        if (increment < 0 && !can_nice(current, nice))
                return -EPERM;

        retval = security_task_setnice(current, nice);
        if (retval)
                return retval;

        set_user_nice(current, nice);
        return 0;
}

#endif

/**
 * task_prio - return the priority value of a given task.
 * @p: the task in question.
 *
 * This is the priority value as seen by users in /proc.
 * RT tasks are offset by -200. Normal tasks are centered
 * around 0, value goes from -16 to +15.
 */
int task_prio(const struct task_struct *p)
{
        return p->prio - MAX_RT_PRIO;
}

/**
 * task_nice - return the nice value of a given task.
 * @p: the task in question.
 */
int task_nice(const struct task_struct *p)
{
        return TASK_NICE(p);
}
EXPORT_SYMBOL(task_nice);

/**
 * idle_cpu - is a given cpu idle currently?
 * @cpu: the processor in question.
 */
int idle_cpu(int cpu)
{
        return cpu_curr(cpu) == cpu_rq(cpu)->idle;
}

/**
 * idle_task - return the idle task for a given cpu.
 * @cpu: the processor in question.
 */
struct task_struct *idle_task(int cpu)
{
        return cpu_rq(cpu)->idle;
}

/**
 * find_process_by_pid - find a process with a matching PID value.
 * @pid: the pid in question.
 */
static struct task_struct *find_process_by_pid(pid_t pid)
{
        return pid ? find_task_by_vpid(pid) : current;
}

/* Actually do priority change: must hold rq lock. */
static void
__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
{
        BUG_ON(p->se.on_rq);

        p->policy = policy;
        p->rt_priority = prio;
        p->normal_prio = normal_prio(p);
        /* we are holding p->pi_lock already */
        p->prio = rt_mutex_getprio(p);
        if (rt_prio(p->prio))
                p->sched_class = &rt_sched_class;
        else
                p->sched_class = &fair_sched_class;
        set_load_weight(p);
}

/*
 * check the target process has a UID that matches the current process's
 */
static bool check_same_owner(struct task_struct *p)
{
        const struct cred *cred = current_cred(), *pcred;
        bool match;

        rcu_read_lock();
        pcred = __task_cred(p);
        match = (cred->euid == pcred->euid ||
                 cred->euid == pcred->uid);
        rcu_read_unlock();
        return match;
}

static int __sched_setscheduler(struct task_struct *p, int policy,
                                struct sched_param *param, bool user)
{
        int retval, oldprio, oldpolicy = -1, on_rq, running;
        unsigned long flags;
        const struct sched_class *prev_class = p->sched_class;
        struct rq *rq;
        int reset_on_fork;

        /* may grab non-irq protected spin_locks */
        BUG_ON(in_interrupt());
recheck:
        /* double check policy once rq lock held */
        if (policy < 0) {
                reset_on_fork = p->sched_reset_on_fork;
                policy = oldpolicy = p->policy;
        } else {
                reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
                policy &= ~SCHED_RESET_ON_FORK;

                if (policy != SCHED_FIFO && policy != SCHED_RR &&
                                policy != SCHED_NORMAL && policy != SCHED_BATCH &&
                                policy != SCHED_IDLE)
                        return -EINVAL;
        }

        /*
         * Valid priorities for SCHED_FIFO and SCHED_RR are
         * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
         * SCHED_BATCH and SCHED_IDLE is 0.
         */
        if (param->sched_priority < 0 ||
            (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
            (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
                return -EINVAL;
        if (rt_policy(policy) != (param->sched_priority != 0))
                return -EINVAL;

        /*
         * Allow unprivileged RT tasks to decrease priority:
         */
        if (user && !capable(CAP_SYS_NICE)) {
                if (rt_policy(policy)) {
                        unsigned long rlim_rtprio;

                        if (!lock_task_sighand(p, &flags))
                                return -ESRCH;
                        rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur;
                        unlock_task_sighand(p, &flags);

                        /* can't set/change the rt policy */
                        if (policy != p->policy && !rlim_rtprio)
                                return -EPERM;

                        /* can't increase priority */
                        if (param->sched_priority > p->rt_priority &&
                            param->sched_priority > rlim_rtprio)
                                return -EPERM;
                }
                /*
                 * Like positive nice levels, dont allow tasks to
                 * move out of SCHED_IDLE either:
                 */
                if (p->policy == SCHED_IDLE && policy != SCHED_IDLE)
                        return -EPERM;

                /* can't change other user's priorities */
                if (!check_same_owner(p))
                        return -EPERM;

                /* Normal users shall not reset the sched_reset_on_fork flag */
                if (p->sched_reset_on_fork && !reset_on_fork)
                        return -EPERM;
        }

        if (user) {
#ifdef CONFIG_RT_GROUP_SCHED
                /*
                 * Do not allow realtime tasks into groups that have no runtime
                 * assigned.
                 */
                if (rt_bandwidth_enabled() && rt_policy(policy) &&
                                task_group(p)->rt_bandwidth.rt_runtime == 0)
                        return -EPERM;
#endif

                retval = security_task_setscheduler(p, policy, param);
                if (retval)
                        return retval;
        }

        /*
         * make sure no PI-waiters arrive (or leave) while we are
         * changing the priority of the task:
         */
        spin_lock_irqsave(&p->pi_lock, flags);
        /*
         * To be able to change p->policy safely, the apropriate
         * runqueue lock must be held.
         */
        rq = __task_rq_lock(p);
        /* recheck policy now with rq lock held */
        if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
                policy = oldpolicy = -1;
                __task_rq_unlock(rq);
                spin_unlock_irqrestore(&p->pi_lock, flags);
                goto recheck;
        }
        update_rq_clock(rq);
        on_rq = p->se.on_rq;
        running = task_current(rq, p);
        if (on_rq)
                deactivate_task(rq, p, 0);
        if (running)
                p->sched_class->put_prev_task(rq, p);

        p->sched_reset_on_fork = reset_on_fork;

        oldprio = p->prio;
        __setscheduler(rq, p, policy, param->sched_priority);

        if (running)
                p->sched_class->set_curr_task(rq);
        if (on_rq) {
                activate_task(rq, p, 0);

                check_class_changed(rq, p, prev_class, oldprio, running);
        }
        __task_rq_unlock(rq);
        spin_unlock_irqrestore(&p->pi_lock, flags);

        rt_mutex_adjust_pi(p);

        return 0;
}

/**
 * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
 * @p: the task in question.
 * @policy: new policy.
 * @param: structure containing the new RT priority.
 *
 * NOTE that the task may be already dead.
 */
int sched_setscheduler(struct task_struct *p, int policy,
                       struct sched_param *param)
{
        return __sched_setscheduler(p, policy, param, true);
}
EXPORT_SYMBOL_GPL(sched_setscheduler);

/**
 * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
 * @p: the task in question.
 * @policy: new policy.
 * @param: structure containing the new RT priority.
 *
 * Just like sched_setscheduler, only don't bother checking if the
 * current context has permission.  For example, this is needed in
 * stop_machine(): we create temporary high priority worker threads,
 * but our caller might not have that capability.
 */
int sched_setscheduler_nocheck(struct task_struct *p, int policy,
                               struct sched_param *param)
{
        return __sched_setscheduler(p, policy, param, false);
}

static int
do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
{
        struct sched_param lparam;
        struct task_struct *p;
        int retval;

        if (!param || pid < 0)
                return -EINVAL;
        if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
                return -EFAULT;

        rcu_read_lock();
        retval = -ESRCH;
        p = find_process_by_pid(pid);
        if (p != NULL)
                retval = sched_setscheduler(p, policy, &lparam);
        rcu_read_unlock();

        return retval;
}

/**
 * sys_sched_setscheduler - set/change the scheduler policy and RT priority
 * @pid: the pid in question.
 * @policy: new policy.
 * @param: structure containing the new RT priority.
 */
SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
                struct sched_param __user *, param)
{
        /* negative values for policy are not valid */
        if (policy < 0)
                return -EINVAL;

        return do_sched_setscheduler(pid, policy, param);
}

/**
 * sys_sched_setparam - set/change the RT priority of a thread
 * @pid: the pid in question.
 * @param: structure containing the new RT priority.
 */
SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
{
        return do_sched_setscheduler(pid, -1, param);
}

/**
 * sys_sched_getscheduler - get the policy (scheduling class) of a thread
 * @pid: the pid in question.
 */
SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
{
        struct task_struct *p;
        int retval;

        if (pid < 0)
                return -EINVAL;

        retval = -ESRCH;
        read_lock(&tasklist_lock);
        p = find_process_by_pid(pid);
        if (p) {
                retval = security_task_getscheduler(p);
                if (!retval)
                        retval = p->policy
                                | (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0);
        }
        read_unlock(&tasklist_lock);
        return retval;
}

/**
 * sys_sched_getparam - get the RT priority of a thread
 * @pid: the pid in question.
 * @param: structure containing the RT priority.
 */
SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
{
        struct sched_param lp;
        struct task_struct *p;
        int retval;

        if (!param || pid < 0)
                return -EINVAL;

        read_lock(&tasklist_lock);
        p = find_process_by_pid(pid);
        retval = -ESRCH;
        if (!p)
                goto out_unlock;

        retval = security_task_getscheduler(p);
        if (retval)
                goto out_unlock;

        lp.sched_priority = p->rt_priority;
        read_unlock(&tasklist_lock);

        /*
         * This one might sleep, we cannot do it with a spinlock held ...
         */
        retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;

        return retval;

out_unlock:
        read_unlock(&tasklist_lock);
        return retval;
}

long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
{
        cpumask_var_t cpus_allowed, new_mask;
        struct task_struct *p;
        int retval;

        get_online_cpus();
        read_lock(&tasklist_lock);

        p = find_process_by_pid(pid);
        if (!p) {
                read_unlock(&tasklist_lock);
                put_online_cpus();
                return -ESRCH;
        }

        /*
         * It is not safe to call set_cpus_allowed with the
         * tasklist_lock held. We will bump the task_struct's
         * usage count and then drop tasklist_lock.
         */
        get_task_struct(p);
        read_unlock(&tasklist_lock);

        if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
                retval = -ENOMEM;
                goto out_put_task;
        }
        if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
                retval = -ENOMEM;
                goto out_free_cpus_allowed;
        }
        retval = -EPERM;
        if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
                goto out_unlock;

        retval = security_task_setscheduler(p, 0, NULL);
        if (retval)
                goto out_unlock;

        cpuset_cpus_allowed(p, cpus_allowed);
        cpumask_and(new_mask, in_mask, cpus_allowed);
 again:
        retval = set_cpus_allowed_ptr(p, new_mask);

        if (!retval) {
                cpuset_cpus_allowed(p, cpus_allowed);
                if (!cpumask_subset(new_mask, cpus_allowed)) {
                        /*
                         * We must have raced with a concurrent cpuset
                         * update. Just reset the cpus_allowed to the
                         * cpuset's cpus_allowed
                         */
                        cpumask_copy(new_mask, cpus_allowed);
                        goto again;
                }
        }
out_unlock:
        free_cpumask_var(new_mask);
out_free_cpus_allowed:
        free_cpumask_var(cpus_allowed);
out_put_task:
        put_task_struct(p);
        put_online_cpus();
        return retval;
}

static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
                             struct cpumask *new_mask)
{
        if (len < cpumask_size())
                cpumask_clear(new_mask);
        else if (len > cpumask_size())
                len = cpumask_size();

        return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
}

/**
 * sys_sched_setaffinity - set the cpu affinity of a process
 * @pid: pid of the process
 * @len: length in bytes of the bitmask pointed to by user_mask_ptr
 * @user_mask_ptr: user-space pointer to the new cpu mask
 */
SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
                unsigned long __user *, user_mask_ptr)
{
        cpumask_var_t new_mask;
        int retval;

        if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
                return -ENOMEM;

        retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
        if (retval == 0)
                retval = sched_setaffinity(pid, new_mask);
        free_cpumask_var(new_mask);
        return retval;
}

long sched_getaffinity(pid_t pid, struct cpumask *mask)
{
        struct task_struct *p;
        int retval;

        get_online_cpus();
        read_lock(&tasklist_lock);

        retval = -ESRCH;
        p = find_process_by_pid(pid);
        if (!p)
                goto out_unlock;

        retval = security_task_getscheduler(p);
        if (retval)
                goto out_unlock;

        cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);

out_unlock:
        read_unlock(&tasklist_lock);
        put_online_cpus();

        return retval;
}

/**
 * sys_sched_getaffinity - get the cpu affinity of a process
 * @pid: pid of the process
 * @len: length in bytes of the bitmask pointed to by user_mask_ptr
 * @user_mask_ptr: user-space pointer to hold the current cpu mask
 */
SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
                unsigned long __user *, user_mask_ptr)
{
        int ret;
        cpumask_var_t mask;

        if (len < cpumask_size())
                return -EINVAL;

        if (!alloc_cpumask_var(&mask, GFP_KERNEL))
                return -ENOMEM;

        ret = sched_getaffinity(pid, mask);
        if (ret == 0) {
                if (copy_to_user(user_mask_ptr, mask, cpumask_size()))
                        ret = -EFAULT;
                else
                        ret = cpumask_size();
        }
        free_cpumask_var(mask);

        return ret;
}

/**
 * sys_sched_yield - yield the current processor to other threads.
 *
 * This function yields the current CPU to other tasks. If there are no
 * other threads running on this CPU then this function will return.
 */
SYSCALL_DEFINE0(sched_yield)
{
        struct rq *rq = this_rq_lock();

        schedstat_inc(rq, yld_count);
        current->sched_class->yield_task(rq);

        /*
         * Since we are going to call schedule() anyway, there's
         * no need to preempt or enable interrupts:
         */
        __release(rq->lock);
        spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
        _raw_spin_unlock(&rq->lock);
        preempt_enable_no_resched();

        schedule();

        return 0;
}

static inline int should_resched(void)
{
        return need_resched() && !(preempt_count() & PREEMPT_ACTIVE);
}

static void __cond_resched(void)
{
        add_preempt_count(PREEMPT_ACTIVE);
        schedule();
        sub_preempt_count(PREEMPT_ACTIVE);
}

int __sched _cond_resched(void)
{
        if (should_resched()) {
                __cond_resched();
                return 1;
        }
        return 0;
}
EXPORT_SYMBOL(_cond_resched);

/*
 * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
 * call schedule, and on return reacquire the lock.
 *
 * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
 * operations here to prevent schedule() from being called twice (once via
 * spin_unlock(), once by hand).
 */
int __cond_resched_lock(spinlock_t *lock)
{
        int resched = should_resched();
        int ret = 0;

        lockdep_assert_held(lock);

        if (spin_needbreak(lock) || resched) {
                spin_unlock(lock);
                if (resched)
                        __cond_resched();
                else
                        cpu_relax();
                ret = 1;
                spin_lock(lock);
        }
        return ret;
}
EXPORT_SYMBOL(__cond_resched_lock);

int __sched __cond_resched_softirq(void)
{
        BUG_ON(!in_softirq());

        if (should_resched()) {
                local_bh_enable();
                __cond_resched();
                local_bh_disable();
                return 1;
        }
        return 0;
}
EXPORT_SYMBOL(__cond_resched_softirq);

/**
 * yield - yield the current processor to other threads.
 *
 * This is a shortcut for kernel-space yielding - it marks the
 * thread runnable and calls sys_sched_yield().
 */
void __sched yield(void)
{
        set_current_state(TASK_RUNNING);
        sys_sched_yield();
}
EXPORT_SYMBOL(yield);

/*
 * This task is about to go to sleep on IO. Increment rq->nr_iowait so
 * that process accounting knows that this is a task in IO wait state.
 */
void __sched io_schedule(void)
{
        struct rq *rq = raw_rq();

        delayacct_blkio_start();
        atomic_inc(&rq->nr_iowait);
        current->in_iowait = 1;
        schedule();
        current->in_iowait = 0;
        atomic_dec(&rq->nr_iowait);
        delayacct_blkio_end();
}
EXPORT_SYMBOL(io_schedule);

long __sched io_schedule_timeout(long timeout)
{
        struct rq *rq = raw_rq();
        long ret;

        delayacct_blkio_start();
        atomic_inc(&rq->nr_iowait);
        current->in_iowait = 1;
        ret = schedule_timeout(timeout);
        current->in_iowait = 0;
        atomic_dec(&rq->nr_iowait);
        delayacct_blkio_end();
        return ret;
}

/**
 * sys_sched_get_priority_max - return maximum RT priority.
 * @policy: scheduling class.
 *
 * this syscall returns the maximum rt_priority that can be used
 * by a given scheduling class.
 */
SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
{
        int ret = -EINVAL;

        switch (policy) {
        case SCHED_FIFO:
        case SCHED_RR:
                ret = MAX_USER_RT_PRIO-1;
                break;
        case SCHED_NORMAL:
        case SCHED_BATCH:
        case SCHED_IDLE:
                ret = 0;
                break;
        }
        return ret;
}

/**
 * sys_sched_get_priority_min - return minimum RT priority.
 * @policy: scheduling class.
 *
 * this syscall returns the minimum rt_priority that can be used
 * by a given scheduling class.
 */
SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
{
        int ret = -EINVAL;

        switch (policy) {
        case SCHED_FIFO:
        case SCHED_RR:
                ret = 1;
                break;
        case SCHED_NORMAL:
        case SCHED_BATCH:
        case SCHED_IDLE:
                ret = 0;
        }
        return ret;
}

/**
 * sys_sched_rr_get_interval - return the default timeslice of a process.
 * @pid: pid of the process.
 * @interval: userspace pointer to the timeslice value.
 *
 * this syscall writes the default timeslice value of a given process
 * into the user-space timespec buffer. A value of '0' means infinity.
 */
SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
                struct timespec __user *, interval)
{
        struct task_struct *p;
        unsigned int time_slice;
        int retval;
        struct timespec t;

        if (pid < 0)
                return -EINVAL;

        retval = -ESRCH;
        read_lock(&tasklist_lock);
        p = find_process_by_pid(pid);
        if (!p)
                goto out_unlock;

        retval = security_task_getscheduler(p);
        if (retval)
                goto out_unlock;

        time_slice = p->sched_class->get_rr_interval(p);

        read_unlock(&tasklist_lock);
        jiffies_to_timespec(time_slice, &t);
        retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
        return retval;

out_unlock:
        read_unlock(&tasklist_lock);
        return retval;
}

static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;

void sched_show_task(struct task_struct *p)
{
        unsigned long free = 0;
        unsigned state;

        state = p->state ? __ffs(p->state) + 1 : 0;
        printk(KERN_INFO "%-13.13s %c", p->comm,
                state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
#if BITS_PER_LONG == 32
        if (state == TASK_RUNNING)
                printk(KERN_CONT " running  ");
        else
                printk(KERN_CONT " %08lx ", thread_saved_pc(p));
#else
        if (state == TASK_RUNNING)
                printk(KERN_CONT "  running task    ");
        else
                printk(KERN_CONT " %016lx ", thread_saved_pc(p));
#endif
#ifdef CONFIG_DEBUG_STACK_USAGE
        free = stack_not_used(p);
#endif
        printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
                task_pid_nr(p), task_pid_nr(p->real_parent),
                (unsigned long)task_thread_info(p)->flags);

        show_stack(p, NULL);
}

void show_state_filter(unsigned long state_filter)
{
        struct task_struct *g, *p;

#if BITS_PER_LONG == 32
        printk(KERN_INFO
                "  task                PC stack   pid father\n");
#else
        printk(KERN_INFO
                "  task                        PC stack   pid father\n");
#endif
     &nbs