sched/cputime: Fix steal time accounting vs. CPU hotplug

[pandora-kernel.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 <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/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/stop_machine.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 <linux/slab.h>
#include <linux/init_task.h>

#include <asm/tlb.h>
#include <asm/irq_regs.h>
#include <asm/mutex.h>
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#endif

#include "sched_cpupri.h"
#include "workqueue_sched.h"
#include "sched_autogroup.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 (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: */
        raw_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;

        raw_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_bandwidth_timer(struct hrtimer *period_timer, ktime_t period)
{
        unsigned long delta;
        ktime_t soft, hard, now;

        for (;;) {
                if (hrtimer_active(period_timer))
                        break;

                now = hrtimer_cb_get_time(period_timer);
                hrtimer_forward(period_timer, now, period);

                soft = hrtimer_get_softexpires(period_timer);
                hard = hrtimer_get_expires(period_timer);
                delta = ktime_to_ns(ktime_sub(hard, soft));
                __hrtimer_start_range_ns(period_timer, soft, delta,
                                         HRTIMER_MODE_ABS_PINNED, 0);
        }
}

static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
{
        if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
                return;

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

        raw_spin_lock(&rt_b->rt_runtime_lock);
        start_bandwidth_timer(&rt_b->rt_period_timer, rt_b->rt_period);
        raw_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 init_sched_domains,
 * detach_destroy_domains and partition_sched_domains.
 */
static DEFINE_MUTEX(sched_domains_mutex);

#ifdef CONFIG_CGROUP_SCHED

#include <linux/cgroup.h>

struct cfs_rq;

static LIST_HEAD(task_groups);

struct cfs_bandwidth {
#ifdef CONFIG_CFS_BANDWIDTH
        raw_spinlock_t lock;
        ktime_t period;
        u64 quota, runtime;
        s64 hierarchal_quota;
        u64 runtime_expires;

        int idle, timer_active;
        struct hrtimer period_timer, slack_timer;
        struct list_head throttled_cfs_rq;

        /* statistics */
        int nr_periods, nr_throttled;
        u64 throttled_time;
#endif
};

/* task group related information */
struct task_group {
        struct cgroup_subsys_state css;

#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;

        atomic_t load_weight;
#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_SCHED_AUTOGROUP
        struct autogroup *autogroup;
#endif

        struct cfs_bandwidth cfs_bandwidth;
};

/* task_group_lock serializes the addition/removal of task groups */
static DEFINE_SPINLOCK(task_group_lock);

#ifdef CONFIG_FAIR_GROUP_SCHED

# define ROOT_TASK_GROUP_LOAD   NICE_0_LOAD

/*
 * 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      (1UL <<  1)
#define MAX_SHARES      (1UL << 18)

static int root_task_group_load = ROOT_TASK_GROUP_LOAD;
#endif

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

#endif  /* CONFIG_CGROUP_SCHED */

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

        u64 exec_clock;
        u64 min_vruntime;
#ifndef CONFIG_64BIT
        u64 min_vruntime_copy;
#endif

        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, *skip;

#ifdef  CONFIG_SCHED_DEBUG
        unsigned int nr_spread_over;
#endif

#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.
         */
        int on_list;
        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;

        /*
         * Maintaining per-cpu shares distribution for group scheduling
         *
         * load_stamp is the last time we updated the load average
         * load_last is the last time we updated the load average and saw load
         * load_unacc_exec_time is currently unaccounted execution time
         */
        u64 load_avg;
        u64 load_period;
        u64 load_stamp, load_last, load_unacc_exec_time;

        unsigned long load_contribution;
#endif
#ifdef CONFIG_CFS_BANDWIDTH
        int runtime_enabled;
        u64 runtime_expires;
        s64 runtime_remaining;

        u64 throttled_timestamp;
        int throttled, throttle_count;
        struct list_head throttled_list;
#endif
#endif
};

#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_CFS_BANDWIDTH
static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
{
        return &tg->cfs_bandwidth;
}

static inline u64 default_cfs_period(void);
static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun);
static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b);

static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
{
        struct cfs_bandwidth *cfs_b =
                container_of(timer, struct cfs_bandwidth, slack_timer);
        do_sched_cfs_slack_timer(cfs_b);

        return HRTIMER_NORESTART;
}

static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
{
        struct cfs_bandwidth *cfs_b =
                container_of(timer, struct cfs_bandwidth, period_timer);
        ktime_t now;
        int overrun;
        int idle = 0;

        for (;;) {
                now = hrtimer_cb_get_time(timer);
                overrun = hrtimer_forward(timer, now, cfs_b->period);

                if (!overrun)
                        break;

                idle = do_sched_cfs_period_timer(cfs_b, overrun);
        }

        return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
}

static void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
        raw_spin_lock_init(&cfs_b->lock);
        cfs_b->runtime = 0;
        cfs_b->quota = RUNTIME_INF;
        cfs_b->period = ns_to_ktime(default_cfs_period());

        INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
        hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
        cfs_b->period_timer.function = sched_cfs_period_timer;
        hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
        cfs_b->slack_timer.function = sched_cfs_slack_timer;
}

static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
        cfs_rq->runtime_enabled = 0;
        INIT_LIST_HEAD(&cfs_rq->throttled_list);
}

/* requires cfs_b->lock, may release to reprogram timer */
static void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
        /*
         * The timer may be active because we're trying to set a new bandwidth
         * period or because we're racing with the tear-down path
         * (timer_active==0 becomes visible before the hrtimer call-back
         * terminates).  In either case we ensure that it's re-programmed
         */
        while (unlikely(hrtimer_active(&cfs_b->period_timer))) {
                raw_spin_unlock(&cfs_b->lock);
                /* ensure cfs_b->lock is available while we wait */
                hrtimer_cancel(&cfs_b->period_timer);

                raw_spin_lock(&cfs_b->lock);
                /* if someone else restarted the timer then we're done */
                if (cfs_b->timer_active)
                        return;
        }

        cfs_b->timer_active = 1;
        start_bandwidth_timer(&cfs_b->period_timer, cfs_b->period);
}

static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
        hrtimer_cancel(&cfs_b->period_timer);
        hrtimer_cancel(&cfs_b->slack_timer);
}
#else
static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
static void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}

static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
{
        return NULL;
}
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */

/* 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: */
        raw_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;
#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;
        atomic_t rto_count;
        struct rcu_head rcu;
        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;
        struct cpupri cpupri;
};

/*
 * 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 /* CONFIG_SMP */

/*
 * 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: */
        raw_spinlock_t lock;

        /*
         * nr_running and cpu_load should be in the same cacheline because
         * remote CPUs use both these fields when doing load calculation.
         */
        unsigned long nr_running;
        #define CPU_LOAD_IDX_MAX 5
        unsigned long cpu_load[CPU_LOAD_IDX_MAX];
        unsigned long last_load_update_tick;
#ifdef CONFIG_NO_HZ
        u64 nohz_stamp;
        unsigned char nohz_balance_kick;
#endif
        int skip_clock_update;

        /* 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, *stop;
        unsigned long next_balance;
        struct mm_struct *prev_mm;

        u64 clock;
        u64 clock_task;

        atomic_t nr_iowait;

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

        unsigned long cpu_power;

        unsigned char idle_balance;
        /* For active balancing */
        int post_schedule;
        int active_balance;
        int push_cpu;
        struct cpu_stop_work active_balance_work;
        /* cpu of this runqueue: */
        int cpu;
        int online;

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

#ifdef CONFIG_IRQ_TIME_ACCOUNTING
        u64 prev_irq_time;
#endif
#ifdef CONFIG_PARAVIRT
        u64 prev_steal_time;
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
        u64 prev_steal_time_rq;
#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;
#endif

#ifdef CONFIG_SMP
        struct llist_head wake_list;
#endif
};

static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);


static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);

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

#define rcu_dereference_check_sched_domain(p) \
        rcu_dereference_check((p), \
                              lockdep_is_held(&sched_domains_mutex))

/*
 * 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_check_sched_domain(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))

#ifdef CONFIG_CGROUP_SCHED

/*
 * Return the group to which this tasks belongs.
 *
 * We cannot use task_subsys_state() and friends because the cgroup
 * subsystem changes that value before the cgroup_subsys::attach() method
 * is called, therefore we cannot pin it and might observe the wrong value.
 *
 * The same is true for autogroup's p->signal->autogroup->tg, the autogroup
 * core changes this before calling sched_move_task().
 *
 * Instead we use a 'copy' which is updated from sched_move_task() while
 * holding both task_struct::pi_lock and rq::lock.
 */
static inline struct task_group *task_group(struct task_struct *p)
{
        return p->sched_task_group;
}

/* 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 /* CONFIG_CGROUP_SCHED */

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_CGROUP_SCHED */

static void update_rq_clock_task(struct rq *rq, s64 delta);

static void update_rq_clock(struct rq *rq)
{
        s64 delta;

        if (rq->skip_clock_update > 0)
                return;

        delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
        rq->clock += delta;
        update_rq_clock_task(rq, delta);
}

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

/**
 * runqueue_is_locked - Returns true if the current cpu runqueue is locked
 * @cpu: the processor in question.
 *
 * 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 raw_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;
        int neg = 0;
        int i;

        if (cnt > 63)
                cnt = 63;

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

        buf[cnt] = 0;
        cmp = strstrip(buf);

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

        for (i = 0; sched_feat_names[i]; i++) {
                if (strcmp(cmp, sched_feat_names[i]) == 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;

/*
 * 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;
}

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

#ifndef __ARCH_WANT_UNLOCKED_CTXSW
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->on_cpu = 1;
#endif
}

static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_SMP
        /*
         * After ->on_cpu is cleared, the task can be moved to a different CPU.
         * We must ensure this doesn't happen until the switch is completely
         * finished.
         *
         * Pairs with the control dependency and rmb in try_to_wake_up().
         */
        smp_mb();
        prev->on_cpu = 0;
#endif
#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_);

        raw_spin_unlock_irq(&rq->lock);
}

#else /* __ARCH_WANT_UNLOCKED_CTXSW */
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->on_cpu = 1;
#endif
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
        raw_spin_unlock_irq(&rq->lock);
#else
        raw_spin_unlock(&rq->lock);
#endif
}

static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_SMP
        /*
         * After ->on_cpu 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->on_cpu = 0;
#endif
#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
        local_irq_enable();
#endif
}
#endif /* __ARCH_WANT_UNLOCKED_CTXSW */

/*
 * __task_rq_lock - lock the rq @p resides on.
 */
static inline struct rq *__task_rq_lock(struct task_struct *p)
        __acquires(rq->lock)
{
        struct rq *rq;

        lockdep_assert_held(&p->pi_lock);

        for (;;) {
                rq = task_rq(p);
                raw_spin_lock(&rq->lock);
                if (likely(rq == task_rq(p)))
                        return rq;
                raw_spin_unlock(&rq->lock);
        }
}

/*
 * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
 */
static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
        __acquires(p->pi_lock)
        __acquires(rq->lock)
{
        struct rq *rq;

        for (;;) {
                raw_spin_lock_irqsave(&p->pi_lock, *flags);
                rq = task_rq(p);
                raw_spin_lock(&rq->lock);
                if (likely(rq == task_rq(p)))
                        return rq;
                raw_spin_unlock(&rq->lock);
                raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
        }
}

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

static inline void
task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags)
        __releases(rq->lock)
        __releases(p->pi_lock)
{
        raw_spin_unlock(&rq->lock);
        raw_spin_unlock_irqrestore(&p->pi_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();
        raw_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());

        raw_spin_lock(&rq->lock);
        update_rq_clock(rq);
        rq->curr->sched_class->task_tick(rq, rq->curr, 1);
        raw_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;

        raw_spin_lock(&rq->lock);
        hrtimer_restart(&rq->hrtick_timer);
        rq->hrtick_csd_pending = 0;
        raw_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_raw_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 (!raw_spin_trylock_irqsave(&rq->lock, flags))
                return;
        resched_task(cpu_curr(cpu));
        raw_spin_unlock_irqrestore(&rq->lock, flags);
}

#ifdef CONFIG_NO_HZ
/*
 * In the semi idle case, use the nearest busy cpu for migrating timers
 * from an idle cpu.  This is good for power-savings.
 *
 * We don't do similar optimization for completely idle system, as
 * selecting an idle cpu will add more delays to the timers than intended
 * (as that cpu's timer base may not be uptodate wrt jiffies etc).
 */
int get_nohz_timer_target(void)
{
        int cpu = smp_processor_id();
        int i;
        struct sched_domain *sd;

        rcu_read_lock();
        for_each_domain(cpu, sd) {
                for_each_cpu(i, sched_domain_span(sd)) {
                        if (!idle_cpu(i)) {
                                cpu = i;
                                goto unlock;
                        }
                }
        }
unlock:
        rcu_read_unlock();
        return cpu;
}
/*
 * 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);
}

static inline bool got_nohz_idle_kick(void)
{
        return idle_cpu(smp_processor_id()) && this_rq()->nohz_balance_kick;
}

#else /* CONFIG_NO_HZ */

static inline bool got_nohz_idle_kick(void)
{
        return false;
}

#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) {
                /*
                 * Inline assembly required to prevent the compiler
                 * optimising this loop into a divmod call.
                 * See __iter_div_u64_rem() for another example of this.
                 */
                asm("" : "+rm" (rq->age_stamp));
                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_raw_spin_locked(&task_rq(p)->lock);
        set_tsk_need_resched(p);
}

static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
{
}

static void sched_avg_update(struct rq *rq)
{
}
#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;

        /*
         * weight can be less than 2^SCHED_LOAD_RESOLUTION for task group sched
         * entities since MIN_SHARES = 2. Treat weight as 1 if less than
         * 2^SCHED_LOAD_RESOLUTION.
         */
        if (likely(weight > (1UL << SCHED_LOAD_RESOLUTION)))
                tmp = (u64)delta_exec * scale_load_down(weight);
        else
                tmp = (u64)delta_exec;

        if (!lw->inv_weight) {
                unsigned long w = scale_load_down(lw->weight);

                if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
                        lw->inv_weight = 1;
                else if (unlikely(!w))
                        lw->inv_weight = WMULT_CONST;
                else
                        lw->inv_weight = WMULT_CONST / w;
        }

        /*
         * 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;
}

static inline void update_load_set(struct load_weight *lw, unsigned long w)
{
        lw->weight = w;
        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,
};

/* 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_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
                        (defined(CONFIG_SMP) || defined(CONFIG_CFS_BANDWIDTH)))
typedef int (*tg_visitor)(struct task_group *, void *);

/*
 * Iterate task_group tree rooted at *from, calling @down when first entering a
 * node and @up when leaving it for the final time.
 *
 * Caller must hold rcu_lock or sufficient equivalent.
 */
static int walk_tg_tree_from(struct task_group *from,
                             tg_visitor down, tg_visitor up, void *data)
{
        struct task_group *parent, *child;
        int ret;

        parent = from;

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

up:
                continue;
        }
        ret = (*up)(parent, data);
        if (ret || parent == from)
                goto out;

        child = parent;
        parent = parent->parent;
        if (parent)
                goto up;
out:
        return ret;
}

/*
 * Iterate the full tree, calling @down when first entering a node and @up when
 * leaving it for the final time.
 *
 * Caller must hold rcu_lock or sufficient equivalent.
 */

static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
{
        return walk_tg_tree_from(&root_task_group, down, up, data);
}

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 unsigned long power_of(int cpu)
{
        return cpu_rq(cpu)->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)
                return rq->load.weight / nr_running;

        return 0;
}

#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)
{
        raw_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(!raw_spin_trylock(&busiest->lock))) {
                if (busiest < this_rq) {
                        raw_spin_unlock(&this_rq->lock);
                        raw_spin_lock(&busiest->lock);
                        raw_spin_lock_nested(&this_rq->lock,
                                              SINGLE_DEPTH_NESTING);
                        ret = 1;
                } else
                        raw_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 */
                raw_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)
{
        raw_spin_unlock(&busiest->lock);
        lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
}

/*
 * 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) {
                raw_spin_lock(&rq1->lock);
                __acquire(rq2->lock);   /* Fake it out ;) */
        } else {
                if (rq1 < rq2) {
                        raw_spin_lock(&rq1->lock);
                        raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
                } else {
                        raw_spin_lock(&rq2->lock);
                        raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
                }
        }
}

/*
 * 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)
{
        raw_spin_unlock(&rq1->lock);
        if (rq1 != rq2)
                raw_spin_unlock(&rq2->lock);
        else
                __release(rq2->lock);
}

#else /* 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());
        BUG_ON(rq1 != rq2);
        raw_spin_lock(&rq1->lock);
        __acquire(rq2->lock);   /* Fake it out ;) */
}

/*
 * 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)
{
        BUG_ON(rq1 != rq2);
        raw_spin_unlock(&rq1->lock);
        __release(rq2->lock);
}

#endif

static void update_sysctl(void);
static int get_update_sysctl_factor(void);
static void update_idle_cpu_load(struct rq *this_rq);

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
         * successfully 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 const struct sched_class rt_sched_class;

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

#include "sched_stats.h"

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)
{
        int prio = p->static_prio - MAX_RT_PRIO;
        struct load_weight *load = &p->se.load;

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

        load->weight = scale_load(prio_to_weight[prio]);
        load->inv_weight = prio_to_wmult[prio];
}

static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
{
        update_rq_clock(rq);
        sched_info_queued(p);
        p->sched_class->enqueue_task(rq, p, flags);
}

static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
{
        update_rq_clock(rq);
        sched_info_dequeued(p);
        p->sched_class->dequeue_task(rq, p, flags);
}

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

        enqueue_task(rq, p, flags);
}

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

        dequeue_task(rq, p, flags);
}

#ifdef CONFIG_IRQ_TIME_ACCOUNTING

/*
 * There are no locks covering percpu hardirq/softirq time.
 * They are only modified in account_system_vtime, on corresponding CPU
 * with interrupts disabled. So, writes are safe.
 * They are read and saved off onto struct rq in update_rq_clock().
 * This may result in other CPU reading this CPU's irq time and can
 * race with irq/account_system_vtime on this CPU. We would either get old
 * or new value with a side effect of accounting a slice of irq time to wrong
 * task when irq is in progress while we read rq->clock. That is a worthy
 * compromise in place of having locks on each irq in account_system_time.
 */
static DEFINE_PER_CPU(u64, cpu_hardirq_time);
static DEFINE_PER_CPU(u64, cpu_softirq_time);

static DEFINE_PER_CPU(u64, irq_start_time);
static int sched_clock_irqtime;

void enable_sched_clock_irqtime(void)
{
        sched_clock_irqtime = 1;
}

void disable_sched_clock_irqtime(void)
{
        sched_clock_irqtime = 0;
}

#ifndef CONFIG_64BIT
static DEFINE_PER_CPU(seqcount_t, irq_time_seq);

static inline void irq_time_write_begin(void)
{
        __this_cpu_inc(irq_time_seq.sequence);
        smp_wmb();
}

static inline void irq_time_write_end(void)
{
        smp_wmb();
        __this_cpu_inc(irq_time_seq.sequence);
}

static inline u64 irq_time_read(int cpu)
{
        u64 irq_time;
        unsigned seq;

        do {
                seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
                irq_time = per_cpu(cpu_softirq_time, cpu) +
                           per_cpu(cpu_hardirq_time, cpu);
        } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));

        return irq_time;
}
#else /* CONFIG_64BIT */
static inline void irq_time_write_begin(void)
{
}

static inline void irq_time_write_end(void)
{
}

static inline u64 irq_time_read(int cpu)
{
        return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
}
#endif /* CONFIG_64BIT */

/*
 * Called before incrementing preempt_count on {soft,}irq_enter
 * and before decrementing preempt_count on {soft,}irq_exit.
 */
void account_system_vtime(struct task_struct *curr)
{
        unsigned long flags;
        s64 delta;
        int cpu;

        if (!sched_clock_irqtime)
                return;

        local_irq_save(flags);

        cpu = smp_processor_id();
        delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
        __this_cpu_add(irq_start_time, delta);

        irq_time_write_begin();
        /*
         * We do not account for softirq time from ksoftirqd here.
         * We want to continue accounting softirq time to ksoftirqd thread
         * in that case, so as not to confuse scheduler with a special task
         * that do not consume any time, but still wants to run.
         */
        if (hardirq_count())
                __this_cpu_add(cpu_hardirq_time, delta);
        else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
                __this_cpu_add(cpu_softirq_time, delta);

        irq_time_write_end();
        local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(account_system_vtime);

#endif /* CONFIG_IRQ_TIME_ACCOUNTING */

static inline void account_reset_rq(struct rq *rq)
{
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
        rq->prev_irq_time = 0;
#endif
#ifdef CONFIG_PARAVIRT
        rq->prev_steal_time = 0;
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
        rq->prev_steal_time_rq = 0;
#endif
}

#ifdef CONFIG_PARAVIRT
static inline u64 steal_ticks(u64 steal)
{
        if (unlikely(steal > NSEC_PER_SEC))
                return div_u64(steal, TICK_NSEC);

        return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
}
#endif

static void update_rq_clock_task(struct rq *rq, s64 delta)
{
/*
 * In theory, the compile should just see 0 here, and optimize out the call
 * to sched_rt_avg_update. But I don't trust it...
 */
#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
        s64 steal = 0, irq_delta = 0;
#endif
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
        irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;

        /*
         * Since irq_time is only updated on {soft,}irq_exit, we might run into
         * this case when a previous update_rq_clock() happened inside a
         * {soft,}irq region.
         *
         * When this happens, we stop ->clock_task and only update the
         * prev_irq_time stamp to account for the part that fit, so that a next
         * update will consume the rest. This ensures ->clock_task is
         * monotonic.
         *
         * It does however cause some slight miss-attribution of {soft,}irq
         * time, a more accurate solution would be to update the irq_time using
         * the current rq->clock timestamp, except that would require using
         * atomic ops.
         */
        if (irq_delta > delta)
                irq_delta = delta;

        rq->prev_irq_time += irq_delta;
        delta -= irq_delta;
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
        if (static_branch((&paravirt_steal_rq_enabled))) {
                u64 st;

                steal = paravirt_steal_clock(cpu_of(rq));
                steal -= rq->prev_steal_time_rq;

                if (unlikely(steal > delta))
                        steal = delta;

                st = steal_ticks(steal);
                steal = st * TICK_NSEC;

                rq->prev_steal_time_rq += steal;

                delta -= steal;
        }
#endif

        rq->clock_task += delta;

#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
        if ((irq_delta + steal) && sched_feat(NONTASK_POWER))
                sched_rt_avg_update(rq, irq_delta + steal);
#endif
}

#ifdef CONFIG_IRQ_TIME_ACCOUNTING
static int irqtime_account_hi_update(void)
{
        struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
        unsigned long flags;
        u64 latest_ns;
        int ret = 0;

        local_irq_save(flags);
        latest_ns = this_cpu_read(cpu_hardirq_time);
        if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq))
                ret = 1;
        local_irq_restore(flags);
        return ret;
}

static int irqtime_account_si_update(void)
{
        struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
        unsigned long flags;
        u64 latest_ns;
        int ret = 0;

        local_irq_save(flags);
        latest_ns = this_cpu_read(cpu_softirq_time);
        if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq))
                ret = 1;
        local_irq_restore(flags);
        return ret;
}

#else /* CONFIG_IRQ_TIME_ACCOUNTING */

#define sched_clock_irqtime     (0)

#endif

#ifdef CONFIG_SMP
static void unthrottle_offline_cfs_rqs(struct rq *rq);
#endif

#include "sched_idletask.c"
#include "sched_fair.c"
#include "sched_rt.c"
#include "sched_autogroup.c"
#include "sched_stoptask.c"
#ifdef CONFIG_SCHED_DEBUG
# include "sched_debug.c"
#endif

void sched_set_stop_task(int cpu, struct task_struct *stop)
{
        struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
        struct task_struct *old_stop = cpu_rq(cpu)->stop;

        if (stop) {
                /*
                 * Make it appear like a SCHED_FIFO task, its something
                 * userspace knows about and won't get confused about.
                 *
                 * Also, it will make PI more or less work without too
                 * much confusion -- but then, stop work should not
                 * rely on PI working anyway.
                 */
                sched_setscheduler_nocheck(stop, SCHED_FIFO, &param);

                stop->sched_class = &stop_sched_class;
        }

        cpu_rq(cpu)->stop = stop;

        if (old_stop) {
                /*
                 * Reset it back to a normal scheduling class so that
                 * it can die in pieces.
                 */
                old_stop->sched_class = &rt_sched_class;
        }
}

/*
 * __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;
}

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

static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
{
        const struct sched_class *class;

        if (p->sched_class == rq->curr->sched_class) {
                rq->curr->sched_class->check_preempt_curr(rq, p, flags);
        } else {
                for_each_class(class) {
                        if (class == rq->curr->sched_class)
                                break;
                        if (class == p->sched_class) {
                                resched_task(rq->curr);
                                break;
                        }
                }
        }

        /*
         * A queue event has occurred, and we're going to schedule.  In
         * this case, we can save a useless back to back clock update.
         */
        if (rq->curr->on_rq && test_tsk_need_resched(rq->curr))
                rq->skip_clock_update = 1;
}

#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;

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

        if (unlikely(p->policy == SCHED_IDLE))
                return 0;

        /*
         * 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 (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)
{
#ifdef CONFIG_SCHED_DEBUG
        /*
         * We should never call set_task_cpu() on a blocked task,
         * ttwu() will sort out the placement.
         */
        WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
                        !(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));

#ifdef CONFIG_LOCKDEP
        /*
         * The caller should hold either p->pi_lock or rq->lock, when changing
         * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
         *
         * sched_move_task() holds both and thus holding either pins the cgroup,
         * see task_group().
         *
         * Furthermore, all task_rq users should acquire both locks, see
         * task_rq_lock().
         */
        WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
                                      lockdep_is_held(&task_rq(p)->lock)));
#endif
#endif

        trace_sched_migrate_task(p, new_cpu);

        if (task_cpu(p) != new_cpu) {
                p->se.nr_migrations++;
                perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
        }

        __set_task_cpu(p, new_cpu);
}

struct migration_arg {
        struct task_struct *task;
        int dest_cpu;
};

static int migration_cpu_stop(void *data);

/*
 * 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(p);
                running = task_running(rq, p);
                on_rq = p->on_rq;
                ncsw = 0;
                if (!match_state || p->state == match_state)
                        ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
                task_rq_unlock(rq, p, &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)) {
                        ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ);

                        set_current_state(TASK_UNINTERRUPTIBLE);
                        schedule_hrtimeout(&to, HRTIMER_MODE_REL);
                        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 doesn't 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 */

#ifdef CONFIG_SMP
/*
 * ->cpus_allowed is protected by both rq->lock and p->pi_lock
 */
static int select_fallback_rq(int cpu, struct task_struct *p)
{
        int dest_cpu;
        const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu));

        /* Look for allowed, online CPU in same node. */
        for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask)
                if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
                        return dest_cpu;

        /* Any allowed, online CPU? */
        dest_cpu = cpumask_any_and(tsk_cpus_allowed(p), cpu_active_mask);
        if (dest_cpu < nr_cpu_ids)
                return dest_cpu;

        /* No more Mr. Nice Guy. */
        dest_cpu = cpuset_cpus_allowed_fallback(p);
        /*
         * Don't tell them about moving exiting tasks or
         * kernel threads (both mm NULL), since they never
         * leave kernel.
         */
        if (p->mm && printk_ratelimit()) {
                printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n",
                                task_pid_nr(p), p->comm, cpu);
        }

        return dest_cpu;
}

/*
 * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
 */
static inline
int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
{
        int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);

        /*
         * In order not to call set_task_cpu() on a blocking task we need
         * to rely on ttwu() to place the task on a valid ->cpus_allowed
         * cpu.
         *
         * Since this is common to all placement strategies, this lives here.
         *
         * [ this allows ->select_task() to simply return task_cpu(p) and
         *   not worry about this generic constraint ]
         */
        if (unlikely(!cpumask_test_cpu(cpu, tsk_cpus_allowed(p)) ||
                     !cpu_online(cpu)))
                cpu = select_fallback_rq(task_cpu(p), p);

        return cpu;
}

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

static void
ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
{
#ifdef CONFIG_SCHEDSTATS
        struct rq *rq = this_rq();

#ifdef CONFIG_SMP
        int this_cpu = smp_processor_id();

        if (cpu == this_cpu) {
                schedstat_inc(rq, ttwu_local);
                schedstat_inc(p, se.statistics.nr_wakeups_local);
        } else {
                struct sched_domain *sd;

                schedstat_inc(p, se.statistics.nr_wakeups_remote);
                rcu_read_lock();
                for_each_domain(this_cpu, sd) {
                        if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
                                schedstat_inc(sd, ttwu_wake_remote);
                                break;
                        }
                }
                rcu_read_unlock();
        }

        if (wake_flags & WF_MIGRATED)
                schedstat_inc(p, se.statistics.nr_wakeups_migrate);

#endif /* CONFIG_SMP */

        schedstat_inc(rq, ttwu_count);
        schedstat_inc(p, se.statistics.nr_wakeups);

        if (wake_flags & WF_SYNC)
                schedstat_inc(p, se.statistics.nr_wakeups_sync);

#endif /* CONFIG_SCHEDSTATS */
}

static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
{
        activate_task(rq, p, en_flags);
        p->on_rq = 1;

        /* if a worker is waking up, notify workqueue */
        if (p->flags & PF_WQ_WORKER)
                wq_worker_waking_up(p, cpu_of(rq));
}

/*
 * Mark the task runnable and perform wakeup-preemption.
 */
static void
ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
{
        trace_sched_wakeup(p, true);
        check_preempt_curr(rq, p, wake_flags);

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

        if (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
}

static void
ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags)
{
#ifdef CONFIG_SMP
        if (p->sched_contributes_to_load)
                rq->nr_uninterruptible--;
#endif

        ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING);
        ttwu_do_wakeup(rq, p, wake_flags);
}

/*
 * Called in case the task @p isn't fully descheduled from its runqueue,
 * in this case we must do a remote wakeup. Its a 'light' wakeup though,
 * since all we need to do is flip p->state to TASK_RUNNING, since
 * the task is still ->on_rq.
 */
static int ttwu_remote(struct task_struct *p, int wake_flags)
{
        struct rq *rq;
        int ret = 0;

        rq = __task_rq_lock(p);
        if (p->on_rq) {
                ttwu_do_wakeup(rq, p, wake_flags);
                ret = 1;
        }
        __task_rq_unlock(rq);

        return ret;
}

#ifdef CONFIG_SMP
static void sched_ttwu_pending(void)
{
        struct rq *rq = this_rq();
        struct llist_node *llist = llist_del_all(&rq->wake_list);
        struct task_struct *p;

        raw_spin_lock(&rq->lock);

        while (llist) {
                p = llist_entry(llist, struct task_struct, wake_entry);
                llist = llist_next(llist);
                ttwu_do_activate(rq, p, 0);
        }

        raw_spin_unlock(&rq->lock);
}

void scheduler_ipi(void)
{
        if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick())
                return;

        /*
         * Not all reschedule IPI handlers call irq_enter/irq_exit, since
         * traditionally all their work was done from the interrupt return
         * path. Now that we actually do some work, we need to make sure
         * we do call them.
         *
         * Some archs already do call them, luckily irq_enter/exit nest
         * properly.
         *
         * Arguably we should visit all archs and update all handlers,
         * however a fair share of IPIs are still resched only so this would
         * somewhat pessimize the simple resched case.
         */
        irq_enter();
        sched_ttwu_pending();

        /*
         * Check if someone kicked us for doing the nohz idle load balance.
         */
        if (unlikely(got_nohz_idle_kick() && !need_resched())) {
                this_rq()->idle_balance = 1;
                raise_softirq_irqoff(SCHED_SOFTIRQ);
        }
        irq_exit();
}

static void ttwu_queue_remote(struct task_struct *p, int cpu)
{
        if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list))
                smp_send_reschedule(cpu);
}

#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
static int ttwu_activate_remote(struct task_struct *p, int wake_flags)
{
        struct rq *rq;
        int ret = 0;

        rq = __task_rq_lock(p);
        if (p->on_cpu) {
                ttwu_activate(rq, p, ENQUEUE_WAKEUP);
                ttwu_do_wakeup(rq, p, wake_flags);
                ret = 1;
        }
        __task_rq_unlock(rq);

        return ret;

}
#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
#endif /* CONFIG_SMP */

static void ttwu_queue(struct task_struct *p, int cpu)
{
        struct rq *rq = cpu_rq(cpu);

#if defined(CONFIG_SMP)
        if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) {
                sched_clock_cpu(cpu); /* sync clocks x-cpu */
                ttwu_queue_remote(p, cpu);
                return;
        }
#endif

        raw_spin_lock(&rq->lock);
        ttwu_do_activate(rq, p, 0);
        raw_spin_unlock(&rq->lock);
}

/**
 * try_to_wake_up - wake up a thread
 * @p: the thread to be awakened
 * @state: the mask of task states that can be woken
 * @wake_flags: wake modifier flags (WF_*)
 *
 * 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 %true if @p was woken up, %false if it was already running
 * or @state didn't match @p's state.
 */
static int
try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
{
        unsigned long flags;
        int cpu, success = 0;

        smp_wmb();
        raw_spin_lock_irqsave(&p->pi_lock, flags);
        if (!(p->state & state))
                goto out;

        success = 1; /* we're going to change ->state */
        cpu = task_cpu(p);

        if (p->on_rq && ttwu_remote(p, wake_flags))
                goto stat;

#ifdef CONFIG_SMP
        /*
         * If the owning (remote) cpu is still in the middle of schedule() with
         * this task as prev, wait until its done referencing the task.
         */
        while (p->on_cpu) {
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
                /*
                 * In case the architecture enables interrupts in
                 * context_switch(), we cannot busy wait, since that
                 * would lead to deadlocks when an interrupt hits and
                 * tries to wake up @prev. So bail and do a complete
                 * remote wakeup.
                 */
                if (ttwu_activate_remote(p, wake_flags))
                        goto stat;
#else
                cpu_relax();
#endif
        }
        /*
         * Pairs with the smp_wmb() in finish_lock_switch().
         */
        smp_rmb();

        p->sched_contributes_to_load = !!task_contributes_to_load(p);
        p->state = TASK_WAKING;

        if (p->sched_class->task_waking)
                p->sched_class->task_waking(p);

        cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
        if (task_cpu(p) != cpu) {
                wake_flags |= WF_MIGRATED;
                set_task_cpu(p, cpu);
        }
#endif /* CONFIG_SMP */

        ttwu_queue(p, cpu);
stat:
        ttwu_stat(p, cpu, wake_flags);
out:
        raw_spin_unlock_irqrestore(&p->pi_lock, flags);

        return success;
}

/**
 * try_to_wake_up_local - try to wake up a local task with rq lock held
 * @p: the thread to be awakened
 *
 * Put @p on the run-queue if it's not already there. The caller must
 * ensure that this_rq() is locked, @p is bound to this_rq() and not
 * the current task.
 */
static void try_to_wake_up_local(struct task_struct *p)
{
        struct rq *rq = task_rq(p);

        if (WARN_ON_ONCE(rq != this_rq()) ||
            WARN_ON_ONCE(p == current))
                return;

        lockdep_assert_held(&rq->lock);

        if (!raw_spin_trylock(&p->pi_lock)) {
                raw_spin_unlock(&rq->lock);
                raw_spin_lock(&p->pi_lock);
                raw_spin_lock(&rq->lock);
        }

        if (!(p->state & TASK_NORMAL))
                goto out;

        if (!p->on_rq)
                ttwu_activate(rq, p, ENQUEUE_WAKEUP);

        ttwu_do_wakeup(rq, p, 0);
        ttwu_stat(p, smp_processor_id(), 0);
out:
        raw_spin_unlock(&p->pi_lock);
}

/**
 * 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_NORMAL, 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->on_rq                        = 0;

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

#ifdef CONFIG_SCHEDSTATS
        memset(&p->se.statistics, 0, sizeof(p->se.statistics));
#endif

        INIT_LIST_HEAD(&p->rt.run_list);

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

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

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

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

        /*
         * Revert to default priority/policy on fork if requested.
         */
        if (unlikely(p->sched_reset_on_fork)) {
                if (task_has_rt_policy(p)) {
                        p->policy = SCHED_NORMAL;
                        p->static_prio = NICE_TO_PRIO(0);
                        p->rt_priority = 0;
                } else if (PRIO_TO_NICE(p->static_prio) < 0)
                        p->static_prio = NICE_TO_PRIO(0);

                p->prio = p->normal_prio = __normal_prio(p);
                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;
        }

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

        if (p->sched_class->task_fork)
                p->sched_class->task_fork(p);

        /*
         * The child is not yet in the pid-hash so no cgroup attach races,
         * and the cgroup is pinned to this child due to cgroup_fork()
         * is ran before sched_fork().
         *
         * Silence PROVE_RCU.
         */
        raw_spin_lock_irqsave(&p->pi_lock, flags);
        set_task_cpu(p, cpu);
        raw_spin_unlock_irqrestore(&p->pi_lock, 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)
        p->on_cpu = 0;
#endif
#ifdef CONFIG_PREEMPT_COUNT
        /* Want to start with kernel preemption disabled. */
        task_thread_info(p)->preempt_count = 1;
#endif
#ifdef CONFIG_SMP
        plist_node_init(&p->pushable_tasks, MAX_PRIO);
#endif

        put_cpu();
}

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

        raw_spin_lock_irqsave(&p->pi_lock, flags);
#ifdef CONFIG_SMP
        /*
         * Fork balancing, do it here and not earlier because:
         *  - cpus_allowed can change in the fork path
         *  - any previously selected cpu might disappear through hotplug
         */
        set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0));
#endif

        rq = __task_rq_lock(p);
        activate_task(rq, p, 0);
        p->on_rq = 1;
        trace_sched_wakeup_new(p, true);
        check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
        if (p->sched_class->task_woken)
                p->sched_class->task_woken(rq, p);
#endif
        task_rq_unlock(rq, p, &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)
{
        sched_info_switch(prev, next);
        perf_event_task_sched_out(prev, next);
        fire_sched_out_preempt_notifiers(prev, next);
        prepare_lock_switch(rq, next);
        prepare_arch_switch(next);
        trace_sched_switch(prev, 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.
         *
         * We must observe prev->state before clearing prev->on_cpu (in
         * finish_lock_switch), otherwise a concurrent wakeup can get prev
         * running on another CPU and we could rave with its RUNNING -> DEAD
         * transition, resulting in a double drop.
         */
        prev_state = prev->state;
        finish_arch_switch(prev);
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
        local_irq_disable();
#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
        perf_event_task_sched_in(prev, current);
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
        local_irq_enable();
#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
        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;

                raw_spin_lock_irqsave(&rq->lock, flags);
                if (rq->curr->sched_class->post_schedule)
                        rq->curr->sched_class->post_schedule(rq);
                raw_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);

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

        if (!prev->mm) {
                prev->active_mm = NULL;
                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(int cpu)
{
        struct rq *this = cpu_rq(cpu);
        return atomic_read(&this->nr_iowait);
}

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


/*
 * Global load-average calculations
 *
 * We take a distributed and async approach to calculating the global load-avg
 * in order to minimize overhead.
 *
 * The global load average is an exponentially decaying average of nr_running +
 * nr_uninterruptible.
 *
 * Once every LOAD_FREQ:
 *
 *   nr_active = 0;
 *   for_each_possible_cpu(cpu)
 *      nr_active += cpu_of(cpu)->nr_running + cpu_of(cpu)->nr_uninterruptible;
 *
 *   avenrun[n] = avenrun[0] * exp_n + nr_active * (1 - exp_n)
 *
 * Due to a number of reasons the above turns in the mess below:
 *
 *  - for_each_possible_cpu() is prohibitively expensive on machines with
 *    serious number of cpus, therefore we need to take a distributed approach
 *    to calculating nr_active.
 *
 *        \Sum_i x_i(t) = \Sum_i x_i(t) - x_i(t_0) | x_i(t_0) := 0
 *                      = \Sum_i { \Sum_j=1 x_i(t_j) - x_i(t_j-1) }
 *
 *    So assuming nr_active := 0 when we start out -- true per definition, we
 *    can simply take per-cpu deltas and fold those into a global accumulate
 *    to obtain the same result. See calc_load_fold_active().
 *
 *    Furthermore, in order to avoid synchronizing all per-cpu delta folding
 *    across the machine, we assume 10 ticks is sufficient time for every
 *    cpu to have completed this task.
 *
 *    This places an upper-bound on the IRQ-off latency of the machine. Then
 *    again, being late doesn't loose the delta, just wrecks the sample.
 *
 *  - cpu_rq()->nr_uninterruptible isn't accurately tracked per-cpu because
 *    this would add another cross-cpu cacheline miss and atomic operation
 *    to the wakeup path. Instead we increment on whatever cpu the task ran
 *    when it went into uninterruptible state and decrement on whatever cpu
 *    did the wakeup. This means that only the sum of nr_uninterruptible over
 *    all cpus yields the correct result.
 *
 *  This covers the NO_HZ=n code, for extra head-aches, see the comment below.
 */

/* 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); /* should be removed */

/**
 * 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 long calc_load_fold_active(struct rq *this_rq)
{
        long nr_active, delta = 0;

        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;
        }

        return delta;
}

/*
 * a1 = a0 * e + a * (1 - e)
 */
static unsigned long
calc_load(unsigned long load, unsigned long exp, unsigned long active)
{
        load *= exp;
        load += active * (FIXED_1 - exp);
        load += 1UL << (FSHIFT - 1);
        return load >> FSHIFT;
}

#ifdef CONFIG_NO_HZ
/*
 * Handle NO_HZ for the global load-average.
 *
 * Since the above described distributed algorithm to compute the global
 * load-average relies on per-cpu sampling from the tick, it is affected by
 * NO_HZ.
 *
 * The basic idea is to fold the nr_active delta into a global idle-delta upon
 * entering NO_HZ state such that we can include this as an 'extra' cpu delta
 * when we read the global state.
 *
 * Obviously reality has to ruin such a delightfully simple scheme:
 *
 *  - When we go NO_HZ idle during the window, we can negate our sample
 *    contribution, causing under-accounting.
 *
 *    We avoid this by keeping two idle-delta counters and flipping them
 *    when the window starts, thus separating old and new NO_HZ load.
 *
 *    The only trick is the slight shift in index flip for read vs write.
 *
 *        0s            5s            10s           15s
 *          +10           +10           +10           +10
 *        |-|-----------|-|-----------|-|-----------|-|
 *    r:0 0 1           1 0           0 1           1 0
 *    w:0 1 1           0 0           1 1           0 0
 *
 *    This ensures we'll fold the old idle contribution in this window while
 *    accumlating the new one.
 *
 *  - When we wake up from NO_HZ idle during the window, we push up our
 *    contribution, since we effectively move our sample point to a known
 *    busy state.
 *
 *    This is solved by pushing the window forward, and thus skipping the
 *    sample, for this cpu (effectively using the idle-delta for this cpu which
 *    was in effect at the time the window opened). This also solves the issue
 *    of having to deal with a cpu having been in NOHZ idle for multiple
 *    LOAD_FREQ intervals.
 *
 * When making the ILB scale, we should try to pull this in as well.
 */
static atomic_long_t calc_load_idle[2];
static int calc_load_idx;

static inline int calc_load_write_idx(void)
{
        int idx = calc_load_idx;

        /*
         * See calc_global_nohz(), if we observe the new index, we also
         * need to observe