[~shefty/rdma-dev.git] / kernel / sched / core.c

/*
 *  kernel/sched/core.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/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 <linux/binfmts.h>
#include <linux/context_tracking.h>

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

#include "sched.h"
#include "../workqueue_sched.h"
#include "../smpboot.h"

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

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);
        }
}

DEFINE_MUTEX(sched_domains_mutex);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);

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

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);
}

/*
 * Debugging: various feature bits
 */

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

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

#undef SCHED_FEAT

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

static const char * const sched_feat_names[] = {
#include "features.h"
};

#undef SCHED_FEAT

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

        for (i = 0; i < __SCHED_FEAT_NR; 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;
}

#ifdef HAVE_JUMP_LABEL

#define jump_label_key__true  STATIC_KEY_INIT_TRUE
#define jump_label_key__false STATIC_KEY_INIT_FALSE

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

struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
#include "features.h"
};

#undef SCHED_FEAT

static void sched_feat_disable(int i)
{
        if (static_key_enabled(&sched_feat_keys[i]))
                static_key_slow_dec(&sched_feat_keys[i]);
}

static void sched_feat_enable(int i)
{
        if (!static_key_enabled(&sched_feat_keys[i]))
                static_key_slow_inc(&sched_feat_keys[i]);
}
#else
static void sched_feat_disable(int i) { };
static void sched_feat_enable(int i) { };
#endif /* HAVE_JUMP_LABEL */

static int sched_feat_set(char *cmp)
{
        int i;
        int neg = 0;

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

        for (i = 0; i < __SCHED_FEAT_NR; i++) {
                if (strcmp(cmp, sched_feat_names[i]) == 0) {
                        if (neg) {
                                sysctl_sched_features &= ~(1UL << i);
                                sched_feat_disable(i);
                        } else {
                                sysctl_sched_features |= (1UL << i);
                                sched_feat_enable(i);
                        }
                        break;
                }
        }

        return i;
}

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 i;

        if (cnt > 63)
                cnt = 63;

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

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

        i = sched_feat_set(cmp);
        if (i == __SCHED_FEAT_NR)
                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 /* CONFIG_SCHED_DEBUG */

/*
 * 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;

__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;



/*
 * __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.
 */

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
 */
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
 */
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) 0
#endif

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);
}

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)
{
        int cpu = smp_processor_id();
        return idle_cpu(cpu) && test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu));
}

#else /* CONFIG_NO_HZ */

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

#endif /* CONFIG_NO_HZ */

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;
        }
}

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

#if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
                        (defined(CONFIG_SMP) || defined(CONFIG_CFS_BANDWIDTH)))
/*
 * 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.
 */
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;
}

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

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);
}

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);
}

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);
}

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_key_false((&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
}

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);
}

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;
}

static ATOMIC_NOTIFIER_HEAD(task_migration_notifier);

void register_task_migration_notifier(struct notifier_block *n)
{
        atomic_notifier_chain_register(&task_migration_notifier, n);
}

#ifdef CONFIG_SMP
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) {
                struct task_migration_notifier tmn;

                if (p->sched_class->migrate_task_rq)
                        p->sched_class->migrate_task_rq(p, new_cpu);
                p->se.nr_migrations++;
                perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);

                tmn.task = p;
                tmn.from_cpu = task_cpu(p);
                tmn.to_cpu = new_cpu;

                atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn);
        }

        __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)
{
        const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu));
        enum { cpuset, possible, fail } state = cpuset;
        int dest_cpu;

        /* Look for allowed, online CPU in same node. */
        for_each_cpu(dest_cpu, nodemask) {
                if (!cpu_online(dest_cpu))
                        continue;
                if (!cpu_active(dest_cpu))
                        continue;
                if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
                        return dest_cpu;
        }

        for (;;) {
                /* Any allowed, online CPU? */
                for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) {
                        if (!cpu_online(dest_cpu))
                                continue;
                        if (!cpu_active(dest_cpu))
                                continue;
                        goto out;
                }

                switch (state) {
                case cpuset:
                        /* No more Mr. Nice Guy. */
                        cpuset_cpus_allowed_fallback(p);
                        state = possible;
                        break;

                case possible:
                        do_set_cpus_allowed(p, cpu_possible_mask);
                        state = fail;
                        break;

                case fail:
                        BUG();
                        break;
                }
        }

out:
        if (state != cpuset) {
                /*
                 * 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_sched("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);
}

bool cpus_share_cache(int this_cpu, int that_cpu)
{
        return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
}
#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) && !cpus_share_cache(smp_processor_id(), cpu)) {
                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)
                cpu_relax();
        /*
         * 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);

        BUG_ON(rq != this_rq());
        BUG_ON(p == current);
        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_ALL, 0);
}
EXPORT_SYMBOL(wake_up_process);

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

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

/*
 * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
 * removed when useful for applications beyond shares distribution (e.g.
 * load-balance).
 */
#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
        p->se.avg.runnable_avg_period = 0;
        p->se.avg.runnable_avg_sum = 0;
#endif
#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

#ifdef CONFIG_NUMA_BALANCING
        if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
                p->mm->numa_next_scan = jiffies;
                p->mm->numa_next_reset = jiffies;
                p->mm->numa_scan_seq = 0;
        }

        p->node_stamp = 0ULL;
        p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
        p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0;
        p->numa_scan_period = sysctl_numa_balancing_scan_delay;
        p->numa_work.next = &p->numa_work;
#endif /* CONFIG_NUMA_BALANCING */
}

#ifdef CONFIG_NUMA_BALANCING
#ifdef CONFIG_SCHED_DEBUG
void set_numabalancing_state(bool enabled)
{
        if (enabled)
                sched_feat_set("NUMA");
        else
                sched_feat_set("NO_NUMA");
}
#else
__read_mostly bool numabalancing_enabled;

void set_numabalancing_state(bool enabled)
{
        numabalancing_enabled = enabled;
}
#endif /* CONFIG_SCHED_DEBUG */
#endif /* CONFIG_NUMA_BALANCING */

/*
 * 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)
{
        trace_sched_switch(prev, 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);
}

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

        rq->prev_mm = NULL;

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

        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

        context_tracking_task_switch(prev, next);
        /* 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 the new update time.
         */
        smp_rmb();

        /*
         * If the folding window started, make sure we start writing in the
         * next idle-delta.
         */
        if (!time_before(jiffies, calc_load_update))
                idx++;

        return idx & 1;
}

static inline int calc_load_read_idx(void)
{
        return calc_load_idx & 1;
}

void calc_load_enter_idle(void)
{
        struct rq *this_rq = this_rq();
        long delta;

        /*
         * We're going into NOHZ mode, if there's any pending delta, fold it
         * into the pending idle delta.
         */
        delta = calc_load_fold_active(this_rq);
        if (delta) {
                int idx = calc_load_write_idx();
                atomic_long_add(delta, &calc_load_idle[idx]);
        }
}

void calc_load_exit_idle(void)
{
        struct rq *this_rq = this_rq();

        /*
         * If we're still before the sample window, we're done.
         */
        if (time_before(jiffies, this_rq->calc_load_update))
                return;

        /*
         * We woke inside or after the sample window, this means we're already
         * accounted through the nohz accounting, so skip the entire deal and
         * sync up for the next window.
         */
        this_rq->calc_load_update = calc_load_update;
        if (time_before(jiffies, this_rq->calc_load_update + 10))
                this_rq->calc_load_update += LOAD_FREQ;
}

static long calc_load_fold_idle(void)
{
        int idx = calc_load_read_idx();
        long delta = 0;

        if (atomic_long_read(&calc_load_idle[idx]))
                delta = atomic_long_xchg(&calc_load_idle[idx], 0);

        return delta;
}

/**
 * fixed_power_int - compute: x^n, in O(log n) time
 *
 * @x:         base of the power
 * @frac_bits: fractional bits of @x
 * @n:         power to raise @x to.
 *
 * By exploiting the relation between the definition of the natural power
 * function: x^n := x*x*...*x (x multiplied by itself for n times), and
 * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
 * (where: n_i \elem {0, 1}, the binary vector representing n),
 * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
 * of course trivially computable in O(log_2 n), the length of our binary
 * vector.
 */
static unsigned long
fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
{
        unsigned long result = 1UL << frac_bits;

        if (n) for (;;) {
                if (n & 1) {
                        result *= x;
                        result += 1UL << (frac_bits - 1);
                        result >>= frac_bits;
                }
                n >>= 1;
                if (!n)
                        break;
                x *= x;
                x += 1UL << (frac_bits - 1);
                x >>= frac_bits;
        }

        return result;
}

/*
 * a1 = a0 * e + a * (1 - e)
 *
 * a2 = a1 * e + a * (1 - e)
 *    = (a0 * e + a * (1 - e)) * e + a * (1 - e)
 *    = a0 * e^2 + a * (1 - e) * (1 + e)
 *
 * a3 = a2 * e + a * (1 - e)
 *    = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
 *    = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
 *
 *  ...
 *
 * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
 *    = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
 *    = a0 * e^n + a * (1 - e^n)
 *
 * [1] application of the geometric series:
 *
 *              n         1 - x^(n+1)
 *     S_n := \Sum x^i = -------------
 *             i=0          1 - x
 */
static unsigned long
calc_load_n(unsigned long load, unsigned long exp,
            unsigned long active, unsigned int n)
{

        return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
}

/*
 * NO_HZ can leave us missing all per-cpu ticks calling
 * calc_load_account_active(), but since an idle CPU folds its delta into
 * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold
 * in the pending idle delta if our idle period crossed a load cycle boundary.
 *
 * Once we've updated the global active value, we need to apply the exponential
 * weights adjusted to the number of cycles missed.
 */
static void calc_global_nohz(void)
{
        long delta, active, n;

        if (!time_before(jiffies, calc_load_update + 10)) {
                /*
                 * Catch-up, fold however many we are behind still
                 */
                delta = jiffies - calc_load_update - 10;
                n = 1 + (delta / LOAD_FREQ);

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

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

                calc_load_update += n * LOAD_FREQ;
        }

        /*
         * Flip the idle index...
         *
         * Make sure we first write the new time then flip the index, so that
         * calc_load_write_idx() will see the new time when it reads the new
         * index, this avoids a double flip messing things up.
         */
        smp_wmb();
        calc_load_idx++;
}
#else /* !CONFIG_NO_HZ */

static inline long calc_load_fold_idle(void) { return 0; }
static inline void calc_global_nohz(void) { }

#endif /* CONFIG_NO_HZ */

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

        if (time_before(jiffies, calc_load_update + 10))
                return;

        /*
         * Fold the 'old' idle-delta to include all NO_HZ cpus.
         */
        delta = calc_load_fold_idle();
        if (delta)
                atomic_long_add(delta, &calc_load_tasks);

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

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

        calc_load_update += LOAD_FREQ;

        /*
         * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.
         */
        calc_global_nohz();
}

/*
 * Called from update_cpu_load() to periodically update this CPU's
 * active count.
 */
static void calc_load_account_active(struct rq *this_rq)
{
        long delta;

        if (time_before(jiffies, this_rq->calc_load_update))
                return;

        delta  = calc_load_fold_active(this_rq);
        if (delta)
                atomic_long_add(delta, &calc_load_tasks);

        this_rq->calc_load_update += LOAD_FREQ;
}

/*
 * End of global load-average stuff
 */

/*
 * The exact cpuload at various idx values, calculated at every tick would be
 * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
 *
 * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
 * on nth tick when cpu may be busy, then we have:
 * load = ((2^idx - 1) / 2^idx)^(n-1) * load
 * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
 *
 * decay_load_missed() below does efficient calculation of
 * load = ((2^idx - 1) / 2^idx)^(n-1) * load
 * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
 *
 * The calculation is approximated on a 128 point scale.
 * degrade_zero_ticks is the number of ticks after which load at any
 * particular idx is approximated to be zero.
 * degrade_factor is a precomputed table, a row for each load idx.
 * Each column corresponds to degradation factor for a power of two ticks,
 * based on 128 point scale.
 * Example:
 * row 2, col 3 (=12) says that the degradation at load idx 2 after
 * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
 *
 * With this power of 2 load factors, we can degrade the load n times
 * by looking at 1 bits in n and doing as many mult/shift instead of
 * n mult/shifts needed by the exact degradation.
 */
#define DEGRADE_SHIFT           7
static const unsigned char
                degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
static const unsigned char
                degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
                                        {0, 0, 0, 0, 0, 0, 0, 0},
                                        {64, 32, 8, 0, 0, 0, 0, 0},
                                        {96, 72, 40, 12, 1, 0, 0},
                                        {112, 98, 75, 43, 15, 1, 0},
                                        {120, 112, 98, 76, 45, 16, 2} };

/*
 * Update cpu_load for any missed ticks, due to tickless idle. The backlog
 * would be when CPU is idle and so we just decay the old load without
 * adding any new load.
 */
static unsigned long
decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
{
        int j = 0;

        if (!missed_updates)
                return load;

        if (missed_updates >= degrade_zero_ticks[idx])
                return 0;

        if (idx == 1)
                return load >> missed_updates;

        while (missed_updates) {
                if (missed_updates % 2)
                        load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT;

                missed_updates >>= 1;
                j++;
        }
        return load;
}

/*
 * Update rq->cpu_load[] statistics. This function is usually called every
 * scheduler tick (TICK_NSEC). With tickless idle this will not be called
 * every tick. We fix it up based on jiffies.
 */
static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
                              unsigned long pending_updates)
{
        int i, scale;

        this_rq->nr_load_updates++;

        /* Update our load: */
        this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
        for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
                unsigned long old_load, new_load;

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

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

                this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
        }

        sched_avg_update(this_rq);
}

#ifdef CONFIG_NO_HZ
/*
 * There is no sane way to deal with nohz on smp when using jiffies because the
 * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
 * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
 *
 * Therefore we cannot use the delta approach from the regular tick since that
 * would seriously skew the load calculation. However we'll make do for those
 * updates happening while idle (nohz_idle_balance) or coming out of idle
 * (tick_nohz_idle_exit).
 *
 * This means we might still be one tick off for nohz periods.
 */

/*
 * Called from nohz_idle_balance() to update the load ratings before doing the
 * idle balance.
 */
void update_idle_cpu_load(struct rq *this_rq)
{
        unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
        unsigned long load = this_rq->load.weight;
        unsigned long pending_updates;

        /*
         * bail if there's load or we're actually up-to-date.
         */
        if (load || curr_jiffies == this_rq->last_load_update_tick)
                return;

        pending_updates = curr_jiffies - this_rq->last_load_update_tick;
        this_rq->last_load_update_tick = curr_jiffies;

        __update_cpu_load(this_rq, load, pending_updates);
}

/*
 * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
 */
void update_cpu_load_nohz(void)
{
        struct rq *this_rq = this_rq();
        unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
        unsigned long pending_updates;

        if (curr_jiffies == this_rq->last_load_update_tick)
                return;

        raw_spin_lock(&this_rq->lock);
        pending_updates = curr_jiffies - this_rq->last_load_update_tick;
        if (pending_updates) {
                this_rq->last_load_update_tick = curr_jiffies;
                /*
                 * We were idle, this means load 0, the current load might be
                 * !0 due to remote wakeups and the sort.
                 */
                __update_cpu_load(this_rq, 0, pending_updates);
        }
        raw_spin_unlock(&this_rq->lock);
}
#endif /* CONFIG_NO_HZ */

/*
 * Called from scheduler_tick()
 */
static void update_cpu_load_active(struct rq *this_rq)
{
        /*
         * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
         */
        this_rq->last_load_update_tick = jiffies;
        __update_cpu_load(this_rq, this_rq->load.weight, 1);

        calc_load_account_active(this_rq);
}

#ifdef CONFIG_SMP

/*
 * sched_exec - execve() is a valuable balancing opportunity, because at
 * this point the task has the smallest effective memory and cache footprint.
 */
void sched_exec(void)
{
        struct task_struct *p = current;
        unsigned long flags;
        int dest_cpu;

        raw_spin_lock_irqsave(&p->pi_lock, flags);
        dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0);
        if (dest_cpu == smp_processor_id())
                goto unlock;

        if (likely(cpu_active(dest_cpu))) {
                struct migration_arg arg = { p, dest_cpu };

                raw_spin_unlock_irqrestore(&p->pi_lock, flags);
                stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
                return;
        }
unlock:
        raw_spin_unlock_irqrestore(&p->pi_lock, flags);
}

#endif

DEFINE_PER_CPU(struct kernel_stat, kstat);
DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat);

EXPORT_PER_CPU_SYMBOL(kstat);
EXPORT_PER_CPU_SYMBOL(kernel_cpustat);

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

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

        return ns;
}

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

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

        return ns;
}

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

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

        return ns;
}

/*
 * This function gets called by the timer code, with HZ frequency.
 * We call it with interrupts disabled.
 */
void scheduler_tick(void)
{
        int cpu = smp_processor_id();
        struct rq *rq = cpu_rq(cpu);
        struct task_struct *curr = rq->curr;

        sched_clock_tick();

        raw_spin_lock(&rq->lock);
        update_rq_clock(rq);
        update_cpu_load_active(rq);
        curr->sched_class->task_tick(rq, curr, 0);
        raw_spin_unlock(&rq->lock);

        perf_event_task_tick();

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

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

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

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

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

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

#endif

/*
 * Print scheduling while atomic bug:
 */
static noinline void __schedule_bug(struct task_struct *prev)
{
        if (oops_in_progress)
                return;

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

        debug_show_held_locks(prev);
        print_modules();
        if (irqs_disabled())
                print_irqtrace_events(prev);
        dump_stack();
        add_taint(TAINT_WARN);
}

/*
 * Various schedule()-time debugging checks and statistics:
 */
static inline void schedule_debug(struct task_struct *prev)
{
        /*
         * Test if we are atomic. Since do_exit() needs to call into
         * schedule() atomically, we ignore that path for now.
         * Otherwise, whine if we are scheduling when we should not be.
         */
        if (unlikely(in_atomic_preempt_off() && !prev->exit_state))
                __schedule_bug(prev);
        rcu_sleep_check();

        profile_hit(SCHED_PROFILING, __builtin_return_address(0));

        schedstat_inc(this_rq(), sched_count);
}

static void put_prev_task(struct rq *rq, struct task_struct *prev)
{
        if (prev->on_rq || rq->skip_clock_update < 0)
                update_rq_clock(rq);
        prev->sched_class->put_prev_task(rq, prev);
}

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

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

        for_each_class(class) {
                p = class->pick_next_task(rq);
                if (p)
                        return p;
        }

        BUG(); /* the idle class will always have a runnable task */
}

/*
 * __schedule() is the main scheduler function.
 *
 * The main means of driving the scheduler and thus entering this function are:
 *
 *   1. Explicit blocking: mutex, semaphore, waitqueue, etc.
 *
 *   2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return
 *      paths. For example, see arch/x86/entry_64.S.
 *
 *      To drive preemption between tasks, the scheduler sets the flag in timer
 *      interrupt handler scheduler_tick().
 *
 *   3. Wakeups don't really cause entry into schedule(). They add a
 *      task to the run-queue and that's it.
 *
 *      Now, if the new task added to the run-queue preempts the current
 *      task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
 *      called on the nearest possible occasion:
 *
 *       - If the kernel is preemptible (CONFIG_PREEMPT=y):
 *
 *         - in syscall or exception context, at the next outmost
 *           preempt_enable(). (this might be as soon as the wake_up()'s
 *           spin_unlock()!)
 *
 *         - in IRQ context, return from interrupt-handler to
 *           preemptible context
 *
 *       - If the kernel is not preemptible (CONFIG_PREEMPT is not set)
 *         then at the next:
 *
 *          - cond_resched() call
 *          - explicit schedule() call
 *          - return from syscall or exception to user-space
 *          - return from interrupt-handler to user-space
 */
static void __sched __schedule(void)
{
        struct task_struct *prev, *next;
        unsigned long *switch_count;
        struct rq *rq;
        int cpu;

need_resched:
        preempt_disable();
        cpu = smp_processor_id();
        rq = cpu_rq(cpu);
        rcu_note_context_switch(cpu);
        prev = rq->curr;

        schedule_debug(prev);

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

        raw_spin_lock_irq(&rq->lock);

        switch_count = &prev->nivcsw;
        if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
                if (unlikely(signal_pending_state(prev->state, prev))) {
                        prev->state = TASK_RUNNING;
                } else {
                        deactivate_task(rq, prev, DEQUEUE_SLEEP);
                        prev->on_rq = 0;

                        /*
                         * If a worker went to sleep, notify and ask workqueue
                         * whether it wants to wake up a task to maintain
                         * concurrency.
                         */
                        if (prev->flags & PF_WQ_WORKER) {
                                struct task_struct *to_wakeup;

                                to_wakeup = wq_worker_sleeping(prev, cpu);
                                if (to_wakeup)
                                        try_to_wake_up_local(to_wakeup);
                        }
                }
                switch_count = &prev->nvcsw;
        }

        pre_schedule(rq, prev);

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

        put_prev_task(rq, prev);
        next = pick_next_task(rq);
        clear_tsk_need_resched(prev);
        rq->skip_clock_update = 0;

        if (likely(prev != next)) {
                rq->nr_switches++;
                rq->curr = next;
                ++*switch_count;

                context_switch(rq, prev, next); /* unlocks the rq */
                /*
                 * The context switch have flipped the stack from under us
                 * and restored the local variables which were saved when
                 * this task called schedule() in the past. prev == current
                 * is still correct, but it can be moved to another cpu/rq.
                 */
                cpu = smp_processor_id();
                rq = cpu_rq(cpu);
        } else
                raw_spin_unlock_irq(&rq->lock);

        post_schedule(rq);

        sched_preempt_enable_no_resched();
        if (need_resched())
                goto need_resched;
}

static inline void sched_submit_work(struct task_struct *tsk)
{
        if (!tsk->state || tsk_is_pi_blocked(tsk))
                return;
        /*
         * If we are going to sleep and we have plugged IO queued,
         * make sure to submit it to avoid deadlocks.
         */
        if (blk_needs_flush_plug(tsk))
                blk_schedule_flush_plug(tsk);
}

asmlinkage void __sched schedule(void)
{
        struct task_struct *tsk = current;

        sched_submit_work(tsk);
        __schedule();
}
EXPORT_SYMBOL(schedule);

#ifdef CONFIG_CONTEXT_TRACKING
asmlinkage void __sched schedule_user(void)
{
        /*
         * If we come here after a random call to set_need_resched(),
         * or we have been woken up remotely but the IPI has not yet arrived,
         * we haven't yet exited the RCU idle mode. Do it here manually until
         * we find a better solution.
         */
        user_exit();
        schedule();
        user_enter();
}
#endif

/**
 * schedule_preempt_disabled - called with preemption disabled
 *
 * Returns with preemption disabled. Note: preempt_count must be 1
 */
void __sched schedule_preempt_disabled(void)
{
        sched_preempt_enable_no_resched();
        schedule();
        preempt_disable();
}

#ifdef CONFIG_MUTEX_SPIN_ON_OWNER

static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
{
        if (lock->owner != owner)
                return false;

        /*
         * Ensure we emit the owner->on_cpu, dereference _after_ checking
         * lock->owner still matches owner, if that fails, owner might
         * point to free()d memory, if it still matches, the rcu_read_lock()
         * ensures the memory stays valid.
         */
        barrier();

        return owner->on_cpu;
}

/*
 * Look out! "owner" is an entirely speculative pointer
 * access and not reliable.
 */
int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
{
        if (!sched_feat(OWNER_SPIN))
                return 0;

        rcu_read_lock();
        while (owner_running(lock, owner)) {
                if (need_resched())
                        break;

                arch_mutex_cpu_relax();
        }
        rcu_read_unlock();

        /*
         * We break out the loop above on need_resched() and when the
         * owner changed, which is a sign for heavy contention. Return
         * success only when lock->owner is NULL.
         */
        return lock->owner == NULL;
}
#endif

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

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

        do {
                add_preempt_count_notrace(PREEMPT_ACTIVE);
                __schedule();
                sub_preempt_count_notrace(PREEMPT_ACTIVE);

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

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

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

        user_exit();
        do {
                add_preempt_count(PREEMPT_ACTIVE);
                local_irq_enable();
                __schedule();
                local_irq_disable();
                sub_preempt_count(PREEMPT_ACTIVE);

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

#endif /* CONFIG_PREEMPT */

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

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

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

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

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

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

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

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

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

        if (unlikely(!q))
                return;

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

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

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

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

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

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

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

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

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

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

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

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

/**
 * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
 * @x:  holds the state of this particular completion
 * @timeout:  timeout value in jiffies
 *
 * This waits for either a completion of a specific task to be signaled or for a
 * specified timeout to expire. The timeout is in jiffies. It is not
 * interruptible.
 *
 * The return value is 0 if timed out, and positive (at least 1, or number of
 * jiffies left till timeout) if completed.
 */
unsigned long __sched
wait_for_completion_timeout(struct completion *x, unsigned long timeout)
{
        return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_for_completion_timeout);

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

/**
 * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
 * @x:  holds the state of this particular completion
 * @timeout:  timeout value in jiffies
 *
 * This waits for either a completion of a specific task to be signaled or for a
 * specified timeout to expire. It is interruptible. The timeout is in jiffies.
 *
 * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
 * positive (at least 1, or number of jiffies left till timeout) if completed.
 */
long __sched
wait_for_completion_interruptible_timeout(struct completion *x,
                                          unsigned long timeout)
{
        return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);

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

/**
 * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable))
 * @x:  holds the state of this particular completion
 * @timeout:  timeout value in jiffies
 *
 * This waits for either a completion of a specific task to be
 * signaled or for a specified timeout to expire. It can be
 * interrupted by a kill signal. The timeout is in jiffies.
 *
 * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
 * positive (at least 1, or number of jiffies left till timeout) if completed.
 */
long __sched
wait_for_completion_killable_timeout(struct completion *x,
                                     unsigned long timeout)
{
        return wait_for_common(x, timeout, TASK_KILLABLE);
}
EXPORT_SYMBOL(wait_for_completion_killable_timeout);

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

        spin_lock_irqsave(&x->wait.lock, flags);
        if (!x->done)
                ret = 0;
        else
                x->done--;
        spin_unlock_irqrestore(&x->wait.lock, flags);
        return ret;
}
EXPORT_SYMBOL(try_wait_for_completion);

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

        spin_lock_irqsave(&x->wait.lock, flags);
        if (!x->done)
                ret = 0;
        spin_unlock_irqrestore(&x->wait.lock, flags);
        return ret;
}
EXPORT_SYMBOL(completion_done);

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

        init_waitqueue_entry(&wait, current);

        __set_current_state(state);

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

        return timeout;
}

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

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

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

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

#ifdef CONFIG_RT_MUTEXES

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

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

        rq = __task_rq_lock(p);

        /*
         * Idle task boosting is a nono in general. There is one
         * exception, when PREEMPT_RT and NOHZ is active:
         *
         * The idle task calls get_next_timer_interrupt() and holds
         * the timer wheel base->lock on the CPU and another CPU wants
         * to access the timer (probably to cancel it). We can safely
         * ignore the boosting request, as the idle CPU runs this code
         * with interrupts disabled and will complete the lock
         * protected section without being interrupted. So there is no
         * real need to boost.
         */
        if (unlikely(p == rq->idle)) {
                WARN_ON(p != rq->curr);
                WARN_ON(p->pi_blocked_on);
                goto out_unlock;
        }

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

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

        p->prio = prio;

        if (running)
                p->sched_class->set_curr_task(rq);
        if (on_rq)
                enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);

        check_class_changed(rq, p, prev_class, oldprio);
out_unlock:
        __task_rq_unlock(rq);
}
#endif
void set_user_nice(struct task_struct *p, long nice)
{
        int old_prio, delta, on_rq;
        unsigned long flags;
        struct rq *rq;

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

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

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

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

        return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
                capable(CAP_SYS_NICE));
}

#ifdef __ARCH_WANT_SYS_NICE

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

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

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

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

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

        set_user_nice(current, nice);
        return 0;
}

#endif

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

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

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

        if (rq->curr != rq->idle)
                return 0;

        if (rq->nr_running)
                return 0;

#ifdef CONFIG_SMP
        if (!llist_empty(&rq->wake_list))
                return 0;
#endif

        return 1;
}

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

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

/* Actually do priority change: must hold rq lock. */
static void
__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
{
        p->policy = policy;
        p->rt_priority = prio;
        p->normal_prio = normal_prio(p);
        /* we are holding p->pi_lock already */
        p->prio = rt_mutex_getprio(p);
        if (rt_prio(p->prio))
                p->sched_class = &rt_sched_class;
        else
                p->sched_class = &fair_sched_class;
        set_load_weight(p);
}

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

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

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

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

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

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

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

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

                        /* can't increase priority */
                        if (param->sched_priority > p->rt_priority &&
                            param->sched_priority > rlim_rtprio)
                                return -EPERM;
                }

                /*
                 * Treat SCHED_IDLE as nice 20. Only allow a switch to
                 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
                 */
                if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
                        if (!can_nice(p, TASK_NICE(p)))
                                return -EPERM;
                }

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

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

        if (user) {
                retval = security_task_setscheduler(p);
                if (retval)
                        return retval;
        }

        /*
         * make sure no PI-waiters arrive (or leave) while we are
         * changing the priority of the task:
         *
         * To be able to change p->policy safely, the appropriate
         * runqueue lock must be held.
         */
        rq = task_rq_lock(p, &flags);

        /*
         * Changing the policy of the stop threads its a very bad idea
         */
        if (p == rq->stop) {
                task_rq_unlock(rq, p, &flags);
                return -EINVAL;
        }

        /*
         * If not changing anything there's no need to proceed further:
         */
        if (unlikely(policy == p->policy && (!rt_policy(policy) ||
                        param->sched_priority == p->rt_priority))) {
                task_rq_unlock(rq, p, &flags);
                return 0;
        }

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

        /* recheck policy now with rq lock held */
        if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
                policy = oldpolicy = -1;
                task_rq_unlock(rq, p, &flags);
                goto recheck;
        }
        on_rq = p->on_rq;
        running = task_current(rq, p);
        if (on_rq)
                dequeue_task(rq, p, 0);
        if (running)
                p->sched_class->put_prev_task(rq, p);

        p->sched_reset_on_fork = reset_on_fork;

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

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

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

        rt_mutex_adjust_pi(p);

        return 0;
}

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

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

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

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

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

        return retval;
}

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

        return do_sched_setscheduler(pid, policy, param);
}

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

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

        if (pid < 0)
                return -EINVAL;

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

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

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

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

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

        lp.sched_priority = p->rt_priority;
        rcu_read_unlock();

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

        return retval;

out_unlock:
        rcu_read_unlock();
        return retval;
}

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

        get_online_cpus();
        rcu_read_lock();

        p = find_process_by_pid(pid);
        if (!p) {
                rcu_read_unlock();
                put_online_cpus();
                return -ESRCH;
        }

        /* Prevent p going away */
        get_task_struct(p);
        rcu_read_unlock();

        if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
                retval = -ENOMEM;
                goto out_put_task;
        }
        if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
                retval = -ENOMEM;
                goto out_free_cpus_allowed;
        }
        retval = -EPERM;
        if (!check_same_owner(p)) {
                rcu_read_lock();
                if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
                        rcu_read_unlock();
                        goto out_unlock;
                }
                rcu_read_unlock();
        }

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

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

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

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

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

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

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

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

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

        get_online_cpus();
        rcu_read_lock();

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

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

        raw_spin_lock_irqsave(&p->pi_lock, flags);
        cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);
        raw_spin_unlock_irqrestore(&p->pi_lock, flags);

out_unlock:
        rcu_read_unlock();
        put_online_cpus();

        return retval;
}

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

        if ((len * BITS_PER_BYTE) < nr_cpu_ids)
                return -EINVAL;
        if (len & (sizeof(unsigned long)-1))
                return -EINVAL;

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

        ret = sched_getaffinity(pid, mask);
        if (ret == 0) {
                size_t retlen = min_t(size_t, len, cpumask_size());

                if (copy_to_user(user_mask_ptr, mask, retlen))
                        ret = -EFAULT;
                else
                        ret = retlen;
        }
        free_cpumask_var(mask);

        return ret;
}

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

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

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

        schedule();

        return 0;
}

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

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

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

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

        lockdep_assert_held(lock);

        if (spin_needbreak(lock) || resched) {
      &