/*
 *  kernel/sched/core.c
 *
 *  Core kernel scheduler code and related syscalls
 *
 *  Copyright (C) 1991-2002  Linus Torvalds
 */
#include "sched.h"

#include <linux/nospec.h>

#include <linux/kcov.h>

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

#include "../workqueue_internal.h"
#include "../smpboot.h"

#include "pelt.h"

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

DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);

#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL)
/*
 * Debugging: various feature bits
 *
 * If SCHED_DEBUG is disabled, each compilation unit has its own copy of
 * sysctl_sched_features, defined in sched.h, to allow constants propagation
 * at compile time and compiler optimization based on features default.
 */
#define SCHED_FEAT(name, enabled)       \
        (1UL << __SCHED_FEAT_##name) * enabled |
const_debug unsigned int sysctl_sched_features =
#include "features.h"
        0;
#undef SCHED_FEAT
#endif

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

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

__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.
 */
struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
        __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) && !task_on_rq_migrating(p))) {
                        rq_pin_lock(rq, rf);
                        return rq;
                }
                raw_spin_unlock(&rq->lock);

                while (unlikely(task_on_rq_migrating(p)))
                        cpu_relax();
        }
}

/*
 * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
 */
struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
        __acquires(p->pi_lock)
        __acquires(rq->lock)
{
        struct rq *rq;

        for (;;) {
                raw_spin_lock_irqsave(&p->pi_lock, rf->flags);
                rq = task_rq(p);
                raw_spin_lock(&rq->lock);
                /*
                 *      move_queued_task()              task_rq_lock()
                 *
                 *      ACQUIRE (rq->lock)
                 *      [S] ->on_rq = MIGRATING         [L] rq = task_rq()
                 *      WMB (__set_task_cpu())          ACQUIRE (rq->lock);
                 *      [S] ->cpu = new_cpu             [L] task_rq()
                 *                                      [L] ->on_rq
                 *      RELEASE (rq->lock)
                 *
                 * If we observe the old CPU in task_rq_lock, the acquire of
                 * the old rq->lock will fully serialize against the stores.
                 *
                 * If we observe the new CPU in task_rq_lock, the acquire will
                 * pair with the WMB to ensure we must then also see migrating.
                 */
                if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
                        rq_pin_lock(rq, rf);
                        return rq;
                }
                raw_spin_unlock(&rq->lock);
                raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);

                while (unlikely(task_on_rq_migrating(p)))
                        cpu_relax();
        }
}

/*
 * RQ-clock updating methods:
 */

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

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

                rq->prev_steal_time_rq += steal;
                delta -= steal;
        }
#endif

        rq->clock_task += delta;

#ifdef HAVE_SCHED_AVG_IRQ
        if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
                update_irq_load_avg(rq, irq_delta + steal);
#endif
}

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

        lockdep_assert_held(&rq->lock);

        if (rq->clock_update_flags & RQCF_ACT_SKIP)
                return;

#ifdef CONFIG_SCHED_DEBUG
        if (sched_feat(WARN_DOUBLE_CLOCK))
                SCHED_WARN_ON(rq->clock_update_flags & RQCF_UPDATED);
        rq->clock_update_flags |= RQCF_UPDATED;
#endif

        delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
        if (delta < 0)
                return;
        rq->clock += delta;
        update_rq_clock_task(rq, delta);
}


#ifdef CONFIG_SCHED_HRTICK
/*
 * Use HR-timers to deliver accurate preemption points.
 */

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);
        struct rq_flags rf;

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

        rq_lock(rq, &rf);
        update_rq_clock(rq);
        rq->curr->sched_class->task_tick(rq, rq->curr, 1);
        rq_unlock(rq, &rf);

        return HRTIMER_NORESTART;
}

#ifdef CONFIG_SMP

static void __hrtick_restart(struct rq *rq)
{
        struct hrtimer *timer = &rq->hrtick_timer;

        hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
}

/*
 * called from hardirq (IPI) context
 */
static void __hrtick_start(void *arg)
{
        struct rq *rq = arg;
        struct rq_flags rf;

        rq_lock(rq, &rf);
        __hrtick_restart(rq);
        rq->hrtick_csd_pending = 0;
        rq_unlock(rq, &rf);
}

/*
 * 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;
        s64 delta;

        /*
         * Don't schedule slices shorter than 10000ns, that just
         * doesn't make sense and can cause timer DoS.
         */
        delta = max_t(s64, delay, 10000LL);
        time = ktime_add_ns(timer->base->get_time(), delta);

        hrtimer_set_expires(timer, time);

        if (rq == this_rq()) {
                __hrtick_restart(rq);
        } else if (!rq->hrtick_csd_pending) {
                smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
                rq->hrtick_csd_pending = 1;
        }
}

#else
/*
 * Called to set the hrtick timer state.
 *
 * called with rq->lock held and irqs disabled
 */
void hrtick_start(struct rq *rq, u64 delay)
{
        /*
         * Don't schedule slices shorter than 10000ns, that just
         * doesn't make sense. Rely on vruntime for fairness.
         */
        delay = max_t(u64, delay, 10000LL);
        hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
                      HRTIMER_MODE_REL_PINNED);
}
#endif /* CONFIG_SMP */

static void hrtick_rq_init(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 hrtick_rq_init(struct rq *rq)
{
}
#endif  /* CONFIG_SCHED_HRTICK */

/*
 * cmpxchg based fetch_or, macro so it works for different integer types
 */
#define fetch_or(ptr, mask)                                             \
        ({                                                              \
                typeof(ptr) _ptr = (ptr);                               \
                typeof(mask) _mask = (mask);                            \
                typeof(*_ptr) _old, _val = *_ptr;                       \
                                                                        \
                for (;;) {                                              \
                        _old = cmpxchg(_ptr, _val, _val | _mask);       \
                        if (_old == _val)                               \
                                break;                                  \
                        _val = _old;                                    \
                }                                                       \
        _old;                                                           \
})

#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
/*
 * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
 * this avoids any races wrt polling state changes and thereby avoids
 * spurious IPIs.
 */
static bool set_nr_and_not_polling(struct task_struct *p)
{
        struct thread_info *ti = task_thread_info(p);
        return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);
}

/*
 * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set.
 *
 * If this returns true, then the idle task promises to call
 * sched_ttwu_pending() and reschedule soon.
 */
static bool set_nr_if_polling(struct task_struct *p)
{
        struct thread_info *ti = task_thread_info(p);
        typeof(ti->flags) old, val = READ_ONCE(ti->flags);

        for (;;) {
                if (!(val & _TIF_POLLING_NRFLAG))
                        return false;
                if (val & _TIF_NEED_RESCHED)
                        return true;
                old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED);
                if (old == val)
                        break;
                val = old;
        }
        return true;
}

#else
static bool set_nr_and_not_polling(struct task_struct *p)
{
        set_tsk_need_resched(p);
        return true;
}

#ifdef CONFIG_SMP
static bool set_nr_if_polling(struct task_struct *p)
{
        return false;
}
#endif
#endif

void wake_q_add(struct wake_q_head *head, struct task_struct *task)
{
        struct wake_q_node *node = &task->wake_q;

        /*
         * Atomically grab the task, if ->wake_q is !nil already it means
         * its already queued (either by us or someone else) and will get the
         * wakeup due to that.
         *
         * This cmpxchg() executes a full barrier, which pairs with the full
         * barrier executed by the wakeup in wake_up_q().
         */
        if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
                return;

        get_task_struct(task);

        /*
         * The head is context local, there can be no concurrency.
         */
        *head->lastp = node;
        head->lastp = &node->next;
}

void wake_up_q(struct wake_q_head *head)
{
        struct wake_q_node *node = head->first;

        while (node != WAKE_Q_TAIL) {
                struct task_struct *task;

                task = container_of(node, struct task_struct, wake_q);
                BUG_ON(!task);
                /* Task can safely be re-inserted now: */
                node = node->next;
                task->wake_q.next = NULL;

                /*
                 * wake_up_process() executes a full barrier, which pairs with
                 * the queueing in wake_q_add() so as not to miss wakeups.
                 */
                wake_up_process(task);
                put_task_struct(task);
        }
}

/*
 * resched_curr - mark rq's current 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.
 */
void resched_curr(struct rq *rq)
{
        struct task_struct *curr = rq->curr;
        int cpu;

        lockdep_assert_held(&rq->lock);

        if (test_tsk_need_resched(curr))
                return;

        cpu = cpu_of(rq);

        if (cpu == smp_processor_id()) {
                set_tsk_need_resched(curr);
                set_preempt_need_resched();
                return;
        }

        if (set_nr_and_not_polling(curr))
                smp_send_reschedule(cpu);
        else
                trace_sched_wake_idle_without_ipi(cpu);
}

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

        raw_spin_lock_irqsave(&rq->lock, flags);
        if (cpu_online(cpu) || cpu == smp_processor_id())
                resched_curr(rq);
        raw_spin_unlock_irqrestore(&rq->lock, flags);
}

#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ_COMMON
/*
 * 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 i, cpu = smp_processor_id();
        struct sched_domain *sd;

        if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER))
                return cpu;

        rcu_read_lock();
        for_each_domain(cpu, sd) {
                for_each_cpu(i, sched_domain_span(sd)) {
                        if (cpu == i)
                                continue;

                        if (!idle_cpu(i) && housekeeping_cpu(i, HK_FLAG_TIMER)) {
                                cpu = i;
                                goto unlock;
                        }
                }
        }

        if (!housekeeping_cpu(cpu, HK_FLAG_TIMER))
                cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
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.
 */
static void wake_up_idle_cpu(int cpu)
{
        struct rq *rq = cpu_rq(cpu);

        if (cpu == smp_processor_id())
                return;

        if (set_nr_and_not_polling(rq->idle))
                smp_send_reschedule(cpu);
        else
                trace_sched_wake_idle_without_ipi(cpu);
}

static bool wake_up_full_nohz_cpu(int cpu)
{
        /*
         * We just need the target to call irq_exit() and re-evaluate
         * the next tick. The nohz full kick at least implies that.
         * If needed we can still optimize that later with an
         * empty IRQ.
         */
        if (cpu_is_offline(cpu))
                return true;  /* Don't try to wake offline CPUs. */
        if (tick_nohz_full_cpu(cpu)) {
                if (cpu != smp_processor_id() ||
                    tick_nohz_tick_stopped())
                        tick_nohz_full_kick_cpu(cpu);
                return true;
        }

        return false;
}

/*
 * Wake up the specified CPU.  If the CPU is going offline, it is the
 * caller's responsibility to deal with the lost wakeup, for example,
 * by hooking into the CPU_DEAD notifier like timers and hrtimers do.
 */
void wake_up_nohz_cpu(int cpu)
{
        if (!wake_up_full_nohz_cpu(cpu))
                wake_up_idle_cpu(cpu);
}

static inline bool got_nohz_idle_kick(void)
{
        int cpu = smp_processor_id();

        if (!(atomic_read(nohz_flags(cpu)) & NOHZ_KICK_MASK))
                return false;

        if (idle_cpu(cpu) && !need_resched())
                return true;

        /*
         * We can't run Idle Load Balance on this CPU for this time so we
         * cancel it and clear NOHZ_BALANCE_KICK
         */
        atomic_andnot(NOHZ_KICK_MASK, nohz_flags(cpu));
        return false;
}

#else /* CONFIG_NO_HZ_COMMON */

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

#endif /* CONFIG_NO_HZ_COMMON */

#ifdef CONFIG_NO_HZ_FULL
bool sched_can_stop_tick(struct rq *rq)
{
        int fifo_nr_running;

        /* Deadline tasks, even if single, need the tick */
        if (rq->dl.dl_nr_running)
                return false;

        /*
         * If there are more than one RR tasks, we need the tick to effect the
         * actual RR behaviour.
         */
        if (rq->rt.rr_nr_running) {
                if (rq->rt.rr_nr_running == 1)
                        return true;
                else
                        return false;
        }

        /*
         * If there's no RR tasks, but FIFO tasks, we can skip the tick, no
         * forced preemption between FIFO tasks.
         */
        fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running;
        if (fifo_nr_running)
                return true;

        /*
         * If there are no DL,RR/FIFO tasks, there must only be CFS tasks left;
         * if there's more than one we need the tick for involuntary
         * preemption.
         */
        if (rq->nr_running > 1)
                return false;

        return true;
}
#endif /* CONFIG_NO_HZ_FULL */
#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, bool update_load)
{
        int prio = p->static_prio - MAX_RT_PRIO;
        struct load_weight *load = &p->se.load;

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

        /*
         * SCHED_OTHER tasks have to update their load when changing their
         * weight
         */
        if (update_load && p->sched_class == &fair_sched_class) {
                reweight_task(p, prio);
        } else {
                load->weight = scale_load(sched_prio_to_weight[prio]);
                load->inv_weight = sched_prio_to_wmult[prio];
        }
}

static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
{
        if (!(flags & ENQUEUE_NOCLOCK))
                update_rq_clock(rq);

        if (!(flags & ENQUEUE_RESTORE))
                sched_info_queued(rq, p);

        p->sched_class->enqueue_task(rq, p, flags);
}

static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
{
        if (!(flags & DEQUEUE_NOCLOCK))
                update_rq_clock(rq);

        if (!(flags & DEQUEUE_SAVE))
                sched_info_dequeued(rq, 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);
}

/*
 * __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_dl_policy(p))
                prio = MAX_DL_PRIO-1;
        else 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.
 *
 * Return: 1 if the task is currently executing. 0 otherwise.
 */
inline int task_curr(const struct task_struct *p)
{
        return cpu_curr(task_cpu(p)) == p;
}

/*
 * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock,
 * use the balance_callback list if you want balancing.
 *
 * this means any call to check_class_changed() must be followed by a call to
 * balance_callback().
 */
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 || dl_task(p))
                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_curr(rq);
                                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 (task_on_rq_queued(rq->curr) && test_tsk_need_resched(rq->curr))
                rq_clock_skip_update(rq);
}

#ifdef CONFIG_SMP

static inline bool is_per_cpu_kthread(struct task_struct *p)
{
        if (!(p->flags & PF_KTHREAD))
                return false;

        if (p->nr_cpus_allowed != 1)
                return false;

        return true;
}

/*
 * Per-CPU kthreads are allowed to run on !actie && online CPUs, see
 * __set_cpus_allowed_ptr() and select_fallback_rq().
 */
static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
{
        if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
                return false;

        if (is_per_cpu_kthread(p))
                return cpu_online(cpu);

        return cpu_active(cpu);
}

/*
 * This is how migration works:
 *
 * 1) we invoke migration_cpu_stop() on the target CPU using
 *    stop_one_cpu().
 * 2) stopper starts to run (implicitly forcing the migrated thread
 *    off the CPU)
 * 3) it checks whether the migrated task is still in the wrong runqueue.
 * 4) if it's in the wrong runqueue then the migration thread removes
 *    it and puts it into the right queue.
 * 5) stopper completes and stop_one_cpu() returns and the migration
 *    is done.
 */

/*
 * move_queued_task - move a queued task to new rq.
 *
 * Returns (locked) new rq. Old rq's lock is released.
 */
static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
                                   struct task_struct *p, int new_cpu)
{
        lockdep_assert_held(&rq->lock);

        p->on_rq = TASK_ON_RQ_MIGRATING;
        dequeue_task(rq, p, DEQUEUE_NOCLOCK);
        set_task_cpu(p, new_cpu);
        rq_unlock(rq, rf);

        rq = cpu_rq(new_cpu);

        rq_lock(rq, rf);
        BUG_ON(task_cpu(p) != new_cpu);
        enqueue_task(rq, p, 0);
        p->on_rq = TASK_ON_RQ_QUEUED;
        check_preempt_curr(rq, p, 0);

        return rq;
}

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

/*
 * Move (not current) task off this CPU, onto the destination CPU. We're doing
 * this because either it can't run here any more (set_cpus_allowed()
 * away from this CPU, or CPU going down), or because we're
 * attempting to rebalance this task on exec (sched_exec).
 *
 * So we race with normal scheduler movements, but that's OK, as long
 * as the task is no longer on this CPU.
 */
static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
                                 struct task_struct *p, int dest_cpu)
{
        /* Affinity changed (again). */
        if (!is_cpu_allowed(p, dest_cpu))
                return rq;

        update_rq_clock(rq);
        rq = move_queued_task(rq, rf, p, dest_cpu);

        return rq;
}

/*
 * migration_cpu_stop - this will be executed by a highprio stopper thread
 * and performs thread migration by bumping thread off CPU then
 * 'pushing' onto another runqueue.
 */
static int migration_cpu_stop(void *data)
{
        struct migration_arg *arg = data;
        struct task_struct *p = arg->task;
        struct rq *rq = this_rq();
        struct rq_flags rf;

        /*
         * The original target CPU might have gone down and we might
         * be on another CPU but it doesn't matter.
         */
        local_irq_disable();
        /*
         * We need to explicitly wake pending tasks before running
         * __migrate_task() such that we will not miss enforcing cpus_allowed
         * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
         */
        sched_ttwu_pending();

        raw_spin_lock(&p->pi_lock);
        rq_lock(rq, &rf);
        /*
         * If task_rq(p) != rq, it cannot be migrated here, because we're
         * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
         * we're holding p->pi_lock.
         */
        if (task_rq(p) == rq) {
                if (task_on_rq_queued(p))
                        rq = __migrate_task(rq, &rf, p, arg->dest_cpu);
                else
                        p->wake_cpu = arg->dest_cpu;
        }
        rq_unlock(rq, &rf);
        raw_spin_unlock(&p->pi_lock);

        local_irq_enable();
        return 0;
}

/*

 * sched_class::set_cpus_allowed must do the below, but is not required to
 * actually call this function.
 */
void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask)
{
        cpumask_copy(&p->cpus_allowed, new_mask);
        p->nr_cpus_allowed = cpumask_weight(new_mask);
}

void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
{
        struct rq *rq = task_rq(p);
        bool queued, running;

        lockdep_assert_held(&p->pi_lock);

        queued = task_on_rq_queued(p);
        running = task_current(rq, p);

        if (queued) {
                /*
                 * Because __kthread_bind() calls this on blocked tasks without
                 * holding rq->lock.
                 */
                lockdep_assert_held(&rq->lock);
                dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
        }
        if (running)
                put_prev_task(rq, p);

        p->sched_class->set_cpus_allowed(p, new_mask);

        if (queued)
                enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
        if (running)
                set_curr_task(rq, p);
}

/*
 * Change a given task's CPU affinity. Migrate the thread to a
 * proper CPU and schedule it away if the CPU it's executing on
 * is removed from the allowed bitmask.
 *
 * NOTE: the caller must have a valid reference to the task, the
 * task must not exit() & deallocate itself prematurely. The
 * call is not atomic; no spinlocks may be held.
 */
static int __set_cpus_allowed_ptr(struct task_struct *p,
                                  const struct cpumask *new_mask, bool check)
{
        const struct cpumask *cpu_valid_mask = cpu_active_mask;
        unsigned int dest_cpu;
        struct rq_flags rf;
        struct rq *rq;
        int ret = 0;

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

        if (p->flags & PF_KTHREAD) {
                /*
                 * Kernel threads are allowed on online && !active CPUs
                 */
                cpu_valid_mask = cpu_online_mask;
        }

        /*
         * Must re-check here, to close a race against __kthread_bind(),
         * sched_setaffinity() is not guaranteed to observe the flag.
         */
        if (check && (p->flags & PF_NO_SETAFFINITY)) {
                ret = -EINVAL;
                goto out;
        }

        if (cpumask_equal(&p->cpus_allowed, new_mask))
                goto out;

        if (!cpumask_intersects(new_mask, cpu_valid_mask)) {
                ret = -EINVAL;
                goto out;
        }

        do_set_cpus_allowed(p, new_mask);

        if (p->flags & PF_KTHREAD) {
                /*
                 * For kernel threads that do indeed end up on online &&
                 * !active we want to ensure they are strict per-CPU threads.
                 */
                WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) &&
                        !cpumask_intersects(new_mask, cpu_active_mask) &&
                        p->nr_cpus_allowed != 1);
        }

        /* Can the task run on the task's current CPU? If so, we're done */
        if (cpumask_test_cpu(task_cpu(p), new_mask))
                goto out;

        dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
        if (task_running(rq, p) || p->state == TASK_WAKING) {
                struct migration_arg arg = { p, dest_cpu };
                /* Need help from migration thread: drop lock and wait. */
                task_rq_unlock(rq, p, &rf);
                stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
                tlb_migrate_finish(p->mm);
                return 0;
        } else if (task_on_rq_queued(p)) {
                /*
                 * OK, since we're going to drop the lock immediately
                 * afterwards anyway.
                 */
                rq = move_queued_task(rq, &rf, p, dest_cpu);
        }
out:
        task_rq_unlock(rq, p, &rf);

        return ret;
}

int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
{
        return __set_cpus_allowed_ptr(p, new_mask, false);
}
EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);

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 &&
                        !p->on_rq);

        /*
         * Migrating fair class task must have p->on_rq = TASK_ON_RQ_MIGRATING,
         * because schedstat_wait_{start,end} rebase migrating task's wait_start
         * time relying on p->on_rq.
         */
        WARN_ON_ONCE(p->state == TASK_RUNNING &&
                     p->sched_class == &fair_sched_class &&
                     (p->on_rq && !task_on_rq_migrating(p)));

#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
        /*
         * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
         */
        WARN_ON_ONCE(!cpu_online(new_cpu));
#endif

        trace_sched_migrate_task(p, new_cpu);

        if (task_cpu(p) != new_cpu) {
                if (p->sched_class->migrate_task_rq)
                        p->sched_class->migrate_task_rq(p, new_cpu);
                p->se.nr_migrations++;
                rseq_migrate(p);
                perf_event_task_migrate(p);
        }

        __set_task_cpu(p, new_cpu);
}

#ifdef CONFIG_NUMA_BALANCING
static void __migrate_swap_task(struct task_struct *p, int cpu)
{
        if (task_on_rq_queued(p)) {
                struct rq *src_rq, *dst_rq;
                struct rq_flags srf, drf;

                src_rq = task_rq(p);
                dst_rq = cpu_rq(cpu);

                rq_pin_lock(src_rq, &srf);
                rq_pin_lock(dst_rq, &drf);

                p->on_rq = TASK_ON_RQ_MIGRATING;
                deactivate_task(src_rq, p, 0);
                set_task_cpu(p, cpu);
                activate_task(dst_rq, p, 0);
                p->on_rq = TASK_ON_RQ_QUEUED;
                check_preempt_curr(dst_rq, p, 0);

                rq_unpin_lock(dst_rq, &drf);
                rq_unpin_lock(src_rq, &srf);

        } else {
                /*
                 * Task isn't running anymore; make it appear like we migrated
                 * it before it went to sleep. This means on wakeup we make the
                 * previous CPU our target instead of where it really is.
                 */
                p->wake_cpu = cpu;
        }
}

struct migration_swap_arg {
        struct task_struct *src_task, *dst_task;
        int src_cpu, dst_cpu;
};

static int migrate_swap_stop(void *data)
{
        struct migration_swap_arg *arg = data;
        struct rq *src_rq, *dst_rq;
        int ret = -EAGAIN;

        if (!cpu_active(arg->src_cpu) || !cpu_active(arg->dst_cpu))
                return -EAGAIN;

        src_rq = cpu_rq(arg->src_cpu);
        dst_rq = cpu_rq(arg->dst_cpu);

        double_raw_lock(&arg->src_task->pi_lock,
                        &arg->dst_task->pi_lock);
        double_rq_lock(src_rq, dst_rq);

        if (task_cpu(arg->dst_task) != arg->dst_cpu)
                goto unlock;

        if (task_cpu(arg->src_task) != arg->src_cpu)
                goto unlock;

        if (!cpumask_test_cpu(arg->dst_cpu, &arg->src_task->cpus_allowed))
                goto unlock;

        if (!cpumask_test_cpu(arg->src_cpu, &arg->dst_task->cpus_allowed))
                goto unlock;

        __migrate_swap_task(arg->src_task, arg->dst_cpu);
        __migrate_swap_task(arg->dst_task, arg->src_cpu);

        ret = 0;

unlock:
        double_rq_unlock(src_rq, dst_rq);
        raw_spin_unlock(&arg->dst_task->pi_lock);
        raw_spin_unlock(&arg->src_task->pi_lock);

        return ret;
}

/*
 * Cross migrate two tasks
 */
int migrate_swap(struct task_struct *cur, struct task_struct *p,
                int target_cpu, int curr_cpu)
{
        struct migration_swap_arg arg;
        int ret = -EINVAL;

        arg = (struct migration_swap_arg){
                .src_task = cur,
                .src_cpu = curr_cpu,
                .dst_task = p,
                .dst_cpu = target_cpu,
        };

        if (arg.src_cpu == arg.dst_cpu)
                goto out;

        /*
         * These three tests are all lockless; this is OK since all of them
         * will be re-checked with proper locks held further down the line.
         */
        if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu))
                goto out;

        if (!cpumask_test_cpu(arg.dst_cpu, &arg.src_task->cpus_allowed))
                goto out;

        if (!cpumask_test_cpu(arg.src_cpu, &arg.dst_task->cpus_allowed))
                goto out;

        trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu);
        ret = stop_two_cpus(arg.dst_cpu, arg.src_cpu, migrate_swap_stop, &arg);

out:
        return ret;
}
#endif /* CONFIG_NUMA_BALANCING */

/*
 * 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)
{
        int running, queued;
        struct rq_flags rf;
        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, &rf);
                trace_sched_wait_task(p);
                running = task_running(rq, p);
                queued = task_on_rq_queued(p);
                ncsw = 0;
                if (!match_state || p->state == match_state)
                        ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
                task_rq_unlock(rq, p, &rf);

                /*
                 * 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(queued)) {
                        ktime_t to = 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);

/*
 * ->cpus_allowed is protected by both rq->lock and p->pi_lock
 *
 * A few notes on cpu_active vs cpu_online:
 *
 *  - cpu_active must be a subset of cpu_online
 *
 *  - on CPU-up we allow per-CPU kthreads on the online && !active CPU,
 *    see __set_cpus_allowed_ptr(). At this point the newly online
 *    CPU isn't yet part of the sched domains, and balancing will not
 *    see it.
 *
 *  - on CPU-down we clear cpu_active() to mask the sched domains and
 *    avoid the load balancer to place new tasks on the to be removed
 *    CPU. Existing tasks will remain running there and will be taken
 *    off.
 *
 * This means that fallback selection must not select !active CPUs.
 * And can assume that any active CPU must be online. Conversely
 * select_task_rq() below may allow selection of !active CPUs in order
 * to satisfy the above rules.
 */
static int select_fallback_rq(int cpu, struct task_struct *p)
{
        int nid = cpu_to_node(cpu);
        const struct cpumask *nodemask = NULL;
        enum { cpuset, possible, fail } state = cpuset;
        int dest_cpu;

        /*
         * If the node that the CPU is on has been offlined, cpu_to_node()
         * will return -1. There is no CPU on the node, and we should
         * select the CPU on the other node.
         */
        if (nid != -1) {
                nodemask = cpumask_of_node(nid);

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

        for (;;) {
                /* Any allowed, online CPU? */
                for_each_cpu(dest_cpu, &p->cpus_allowed) {
                        if (!is_cpu_allowed(p, dest_cpu))
                                continue;

                        goto out;
                }

                /* No more Mr. Nice Guy. */
                switch (state) {
                case cpuset:
                        if (IS_ENABLED(CONFIG_CPUSETS)) {
                                cpuset_cpus_allowed_fallback(p);
                                state = possible;
                                break;
                        }
                        /* Fall-through */
                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_deferred("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 cpu, int sd_flags, int wake_flags)
{
        lockdep_assert_held(&p->pi_lock);

        if (p->nr_cpus_allowed > 1)
                cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
        else
                cpu = cpumask_any(&p->cpus_allowed);

        /*
         * 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(!is_cpu_allowed(p, 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;
}

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;
        }
}

#else

static inline int __set_cpus_allowed_ptr(struct task_struct *p,
                                         const struct cpumask *new_mask, bool check)
{
        return set_cpus_allowed_ptr(p, new_mask);
}

#endif /* CONFIG_SMP */

static void
ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
{
        struct rq *rq;

        if (!schedstat_enabled())
                return;

        rq = this_rq();

#ifdef CONFIG_SMP
        if (cpu == rq->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(rq->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);
}

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

        /* If a worker is waking up, notify the 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,
                           struct rq_flags *rf)
{
        check_preempt_curr(rq, p, wake_flags);
        p->state = TASK_RUNNING;
        trace_sched_wakeup(p);

#ifdef CONFIG_SMP
        if (p->sched_class->task_woken) {
                /*
                 * Our task @p is fully woken up and running; so its safe to
                 * drop the rq->lock, hereafter rq is only used for statistics.
                 */
                rq_unpin_lock(rq, rf);
                p->sched_class->task_woken(rq, p);
                rq_repin_lock(rq, rf);
        }

        if (rq->idle_stamp) {
                u64 delta = rq_clock(rq) - rq->idle_stamp;
                u64 max = 2*rq->max_idle_balance_cost;

                update_avg(&rq->avg_idle, delta);

                if (rq->avg_idle > max)
                        rq->avg_idle = max;

                rq->idle_stamp = 0;
        }
#endif
}

static void
ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
                 struct rq_flags *rf)
{
        int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;

        lockdep_assert_held(&rq->lock);

#ifdef CONFIG_SMP
        if (p->sched_contributes_to_load)
                rq->nr_uninterruptible--;

        if (wake_flags & WF_MIGRATED)
                en_flags |= ENQUEUE_MIGRATED;
#endif

        ttwu_activate(rq, p, en_flags);
        ttwu_do_wakeup(rq, p, wake_flags, rf);
}

/*
 * 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_flags rf;
        struct rq *rq;
        int ret = 0;

        rq = __task_rq_lock(p, &rf);
        if (task_on_rq_queued(p)) {
                /* check_preempt_curr() may use rq clock */
                update_rq_clock(rq);
                ttwu_do_wakeup(rq, p, wake_flags, &rf);
                ret = 1;
        }
        __task_rq_unlock(rq, &rf);

        return ret;
}

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

        if (!llist)
                return;

        rq_lock_irqsave(rq, &rf);
        update_rq_clock(rq);

        llist_for_each_entry_safe(p, t, llist, wake_entry)
                ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);

        rq_unlock_irqrestore(rq, &rf);
}

void scheduler_ipi(void)
{
        /*
         * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting
         * TIF_NEED_RESCHED remotely (for the first time) will also send
         * this IPI.
         */
        preempt_fold_need_resched();

        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())) {
                this_rq()->idle_balance = 1;
                raise_softirq_irqoff(SCHED_SOFTIRQ);
        }
        irq_exit();
}

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

        p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);

        if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) {
                if (!set_nr_if_polling(rq->idle))
                        smp_send_reschedule(cpu);
                else
                        trace_sched_wake_idle_without_ipi(cpu);
        }
}

void wake_up_if_idle(int cpu)
{
        struct rq *rq = cpu_rq(cpu);
        struct rq_flags rf;

        rcu_read_lock();

        if (!is_idle_task(rcu_dereference(rq->curr)))
                goto out;

        if (set_nr_if_polling(rq->idle)) {
                trace_sched_wake_idle_without_ipi(cpu);
        } else {
                rq_lock_irqsave(rq, &rf);
                if (is_idle_task(rq->curr))
                        smp_send_reschedule(cpu);
                /* Else CPU is not idle, do nothing here: */
                rq_unlock_irqrestore(rq, &rf);
        }

out:
        rcu_read_unlock();
}

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, int wake_flags)
{
        struct rq *rq = cpu_rq(cpu);
        struct rq_flags rf;

#if defined(CONFIG_SMP)
        if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
                sched_clock_cpu(cpu); /* Sync clocks across CPUs */
                ttwu_queue_remote(p, cpu, wake_flags);
                return;
        }
#endif

        rq_lock(rq, &rf);
        update_rq_clock(rq);
        ttwu_do_activate(rq, p, wake_flags, &rf);
        rq_unlock(rq, &rf);
}

/*
 * Notes on Program-Order guarantees on SMP systems.
 *
 *  MIGRATION
 *
 * The basic program-order guarantee on SMP systems is that when a task [t]
 * migrates, all its activity on its old CPU [c0] happens-before any subsequent
 * execution on its new CPU [c1].
 *
 * For migration (of runnable tasks) this is provided by the following means:
 *
 *  A) UNLOCK of the rq(c0)->lock scheduling out task t
 *  B) migration for t is required to synchronize *both* rq(c0)->lock and
 *     rq(c1)->lock (if not at the same time, then in that order).
 *  C) LOCK of the rq(c1)->lock scheduling in task
 *
 * Release/acquire chaining guarantees that B happens after A and C after B.
 * Note: the CPU doing B need not be c0 or c1
 *
 * Example:
 *
 *   CPU0            CPU1            CPU2
 *
 *   LOCK rq(0)->lock
 *   sched-out X
 *   sched-in Y
 *   UNLOCK rq(0)->lock
 *
 *                                   LOCK rq(0)->lock // orders against CPU0
 *                                   dequeue X
 *                                   UNLOCK rq(0)->lock
 *
 *                                   LOCK rq(1)->lock
 *                                   enqueue X
 *                                   UNLOCK rq(1)->lock
 *
 *                   LOCK rq(1)->lock // orders against CPU2
 *                   sched-out Z
 *                   sched-in X
 *                   UNLOCK rq(1)->lock
 *
 *
 *  BLOCKING -- aka. SLEEP + WAKEUP
 *
 * For blocking we (obviously) need to provide the same guarantee as for
 * migration. However the means are completely different as there is no lock
 * chain to provide order. Instead we do:
 *
 *   1) smp_store_release(X->on_cpu, 0)
 *   2) smp_cond_load_acquire(!X->on_cpu)
 *
 * Example:
 *
 *   CPU0 (schedule)  CPU1 (try_to_wake_up) CPU2 (schedule)
 *
 *   LOCK rq(0)->lock LOCK X->pi_lock
 *   dequeue X
 *   sched-out X
 *   smp_store_release(X->on_cpu, 0);
 *
 *                    smp_cond_load_acquire(&X->on_cpu, !VAL);
 *                    X->state = WAKING
 *                    set_task_cpu(X,2)
 *
 *                    LOCK rq(2)->lock
 *                    enqueue X
 *                    X->state = RUNNING
 *                    UNLOCK rq(2)->lock
 *
 *                                          LOCK rq(2)->lock // orders against CPU1
 *                                          sched-out Z
 *                                          sched-in X
 *                                          UNLOCK rq(2)->lock
 *
 *                    UNLOCK X->pi_lock
 *   UNLOCK rq(0)->lock
 *
 *
 * However, for wakeups there is a second guarantee we must provide, namely we
 * must ensure that CONDITION=1 done by the caller can not be reordered with
 * accesses to the task state; see try_to_wake_up() and set_current_state().
 */

/**
 * 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_*)
 *
 * If (@state & @p->state) @p->state = TASK_RUNNING.
 *
 * If the task was not queued/runnable, also place it back on a runqueue.
 *
 * Atomic against schedule() which would dequeue a task, also see
 * set_current_state().
 *
 * This function executes a full memory barrier before accessing the task
 * state; see set_current_state().
 *
 * Return: %true if @p->state changes (an actual wakeup was done),
 *         %false otherwise.
 */
static int
try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
{
        unsigned long flags;
        int cpu, success = 0;

        /*
         * If we are going to wake up a thread waiting for CONDITION we
         * need to ensure that CONDITION=1 done by the caller can not be
         * reordered with p->state check below. This pairs with mb() in
         * set_current_state() the waiting thread does.
         */
        raw_spin_lock_irqsave(&p->pi_lock, flags);
        smp_mb__after_spinlock();
        if (!(p->state & state))
                goto out;

        trace_sched_waking(p);

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

        /*
         * Ensure we load p->on_rq _after_ p->state, otherwise it would
         * be possible to, falsely, observe p->on_rq == 0 and get stuck
         * in smp_cond_load_acquire() below.
         *
         * sched_ttwu_pending()                 try_to_wake_up()
         *   STORE p->on_rq = 1                   LOAD p->state
         *   UNLOCK rq->lock
         *
         * __schedule() (switch to task 'p')
         *   LOCK rq->lock                        smp_rmb();
         *   smp_mb__after_spinlock();
         *   UNLOCK rq->lock
         *
         * [task p]
         *   STORE p->state = UNINTERRUPTIBLE     LOAD p->on_rq
         *
         * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
         * __schedule().  See the comment for smp_mb__after_spinlock().
         */
        smp_rmb();
        if (p->on_rq && ttwu_remote(p, wake_flags))
                goto stat;

#ifdef CONFIG_SMP
        /*
         * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
         * possible to, falsely, observe p->on_cpu == 0.
         *
         * One must be running (->on_cpu == 1) in order to remove oneself

         * from the runqueue.
         *
         * __schedule() (switch to task 'p')    try_to_wake_up()
         *   STORE p->on_cpu = 1                  LOAD p->on_rq
         *   UNLOCK rq->lock
         *
         * __schedule() (put 'p' to sleep)
         *   LOCK rq->lock                        smp_rmb();
         *   smp_mb__after_spinlock();
         *   STORE p->on_rq = 0                   LOAD p->on_cpu
         *
         * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
         * __schedule().  See the comment for smp_mb__after_spinlock().
         */
        smp_rmb();

        /*
         * If the owning (remote) CPU is still in the middle of schedule() with
         * this task as prev, wait until its done referencing the task.
         *
         * Pairs with the smp_store_release() in finish_task().
         *
         * This ensures that tasks getting woken will be fully ordered against
         * their previous state and preserve Program Order.
         */
        smp_cond_load_acquire(&p->on_cpu, !VAL);

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

        if (p->in_iowait) {
                delayacct_blkio_end(p);
                atomic_dec(&task_rq(p)->nr_iowait);
        }

        cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
        if (task_cpu(p) != cpu) {
                wake_flags |= WF_MIGRATED;
                set_task_cpu(p, cpu);
        }

#else /* CONFIG_SMP */

        if (p->in_iowait) {
                delayacct_blkio_end(p);
                atomic_dec(&task_rq(p)->nr_iowait);
        }

#endif /* CONFIG_SMP */

        ttwu_queue(p, cpu, wake_flags);
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
 * @rf: request-queue flags for pinning
 *
 * 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_flags *rf)
{
        struct rq *rq = task_rq(p);

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

        lockdep_assert_held(&rq->lock);

        if (!raw_spin_trylock(&p->pi_lock)) {
                /*
                 * This is OK, because current is on_cpu, which avoids it being
                 * picked for load-balance and preemption/IRQs are still
                 * disabled avoiding further scheduler activity on it and we've
                 * not yet picked a replacement task.
                 */
                rq_unlock(rq, rf);
                raw_spin_lock(&p->pi_lock);
                rq_relock(rq, rf);
        }

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

        trace_sched_waking(p);

        if (!task_on_rq_queued(p)) {
                if (p->in_iowait) {
                        delayacct_blkio_end(p);
                        atomic_dec(&rq->nr_iowait);
                }
                ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
        }

        ttwu_do_wakeup(rq, p, 0, rf);
        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.
 *
 * Return: 1 if the process was woken up, 0 if it was already running.
 *
 * This function executes a full memory barrier before accessing the task state.
 */
int wake_up_process(struct task_struct *p)
{
        return try_to_wake_up(p, TASK_NORMAL, 0);
}
EXPORT_SYMBOL(wake_up_process);

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

/*
 * Perform scheduler related setup for a newly forked process p.
 * p is forked by current.
 *
 * __sched_fork() is basic setup used by init_idle() too:
 */
static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
{
        p->on_rq                        = 0;

        p->se.on_rq                     = 0;
        p->se.exec_start                = 0;
        p->se.sum_exec_runtime          = 0;
        p->se.prev_sum_exec_runtime     = 0;
        p->se.nr_migrations             = 0;
        p->se.vruntime                  = 0;
        INIT_LIST_HEAD(&p->se.group_node);

#ifdef CONFIG_FAIR_GROUP_SCHED
        p->se.cfs_rq                    = NULL;
#endif

#ifdef CONFIG_SCHEDSTATS
        /* Even if schedstat is disabled, there should not be garbage */
        memset(&p->se.statistics, 0, sizeof(p->se.statistics));
#endif

        RB_CLEAR_NODE(&p->dl.rb_node);
        init_dl_task_timer(&p->dl);
        init_dl_inactive_task_timer(&p->dl);
        __dl_clear_params(p);

        INIT_LIST_HEAD(&p->rt.run_list);
        p->rt.timeout           = 0;
        p->rt.time_slice        = sched_rr_timeslice;
        p->rt.on_rq             = 0;
        p->rt.on_list           = 0;

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

        init_numa_balancing(clone_flags, p);
}

DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);

#ifdef CONFIG_NUMA_BALANCING

void set_numabalancing_state(bool enabled)
{
        if (enabled)
                static_branch_enable(&sched_numa_balancing);
        else
                static_branch_disable(&sched_numa_balancing);
}

#ifdef CONFIG_PROC_SYSCTL
int sysctl_numa_balancing(struct ctl_table *table, int write,
                         void __user *buffer, size_t *lenp, loff_t *ppos)
{
        struct ctl_table t;
        int err;
        int state = static_branch_likely(&sched_numa_balancing);

        if (write && !capable(CAP_SYS_ADMIN))
                return -EPERM;

        t = *table;
        t.data = &state;
        err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
        if (err < 0)
                return err;
        if (write)
                set_numabalancing_state(state);
        return err;
}
#endif
#endif

#ifdef CONFIG_SCHEDSTATS

DEFINE_STATIC_KEY_FALSE(sched_schedstats);
static bool __initdata __sched_schedstats = false;

static void set_schedstats(bool enabled)
{
        if (enabled)
                static_branch_enable(&sched_schedstats);
        else
                static_branch_disable(&sched_schedstats);
}

void force_schedstat_enabled(void)
{
        if (!schedstat_enabled()) {
                pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n");
                static_branch_enable(&sched_schedstats);
        }
}

static int __init setup_schedstats(char *str)
{
        int ret = 0;
        if (!str)
                goto out;

        /*
         * This code is called before jump labels have been set up, so we can't
         * change the static branch directly just yet.  Instead set a temporary
         * variable so init_schedstats() can do it later.
         */
        if (!strcmp(str, "enable")) {
                __sched_schedstats = true;
                ret = 1;
        } else if (!strcmp(str, "disable")) {
                __sched_schedstats = false;
                ret = 1;
        }
out:
        if (!ret)
                pr_warn("Unable to parse schedstats=\n");

        return ret;
}
__setup("schedstats=", setup_schedstats);

static void __init init_schedstats(void)
{
        set_schedstats(__sched_schedstats);
}

#ifdef CONFIG_PROC_SYSCTL
int sysctl_schedstats(struct ctl_table *table, int write,
                         void __user *buffer, size_t *lenp, loff_t *ppos)
{
        struct ctl_table t;
        int err;
        int state = static_branch_likely(&sched_schedstats);

        if (write && !capable(CAP_SYS_ADMIN))
                return -EPERM;

        t = *table;
        t.data = &state;
        err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
        if (err < 0)
                return err;
        if (write)
                set_schedstats(state);
        return err;
}
#endif /* CONFIG_PROC_SYSCTL */
#else  /* !CONFIG_SCHEDSTATS */
static inline void init_schedstats(void) {}
#endif /* CONFIG_SCHEDSTATS */

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

        __sched_fork(clone_flags, p);
        /*
         * We mark the process as NEW 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_NEW;

        /*
         * 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_dl_policy(p) || 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, false);

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

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

        init_entity_runnable_average(&p->se);

        /*
         * 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);
        /*
         * We're setting the CPU for the first time, we don't migrate,
         * so use __set_task_cpu().
         */
        __set_task_cpu(p, smp_processor_id());
        if (p->sched_class->task_fork)
                p->sched_class->task_fork(p);
        raw_spin_unlock_irqrestore(&p->pi_lock, flags);

#ifdef CONFIG_SCHED_INFO
        if (likely(sched_info_on()))
                memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
#if defined(CONFIG_SMP)
        p->on_cpu = 0;
#endif
        init_task_preempt_count(p);
#ifdef CONFIG_SMP
        plist_node_init(&p->pushable_tasks, MAX_PRIO);
        RB_CLEAR_NODE(&p->pushable_dl_tasks);
#endif
        return 0;
}

unsigned long to_ratio(u64 period, u64 runtime)
{
        if (runtime == RUNTIME_INF)
                return BW_UNIT;

        /*
         * Doing this here saves a lot of checks in all
         * the calling paths, and returning zero seems
         * safe for them anyway.
         */
        if (period == 0)
                return 0;

        return div64_u64(runtime << BW_SHIFT, period);
}

/*
 * 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)
{
        struct rq_flags rf;
        struct rq *rq;

        raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
        p->state = TASK_RUNNING;
#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
         *
         * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
         * as we're not fully set-up yet.
         */
        p->recent_used_cpu = task_cpu(p);
        __set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif
        rq = __task_rq_lock(p, &rf);
        update_rq_clock(rq);
        post_init_entity_util_avg(&p->se);

        activate_task(rq, p, ENQUEUE_NOCLOCK);
        p->on_rq = TASK_ON_RQ_QUEUED;
        trace_sched_wakeup_new(p);
        check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
        if (p->sched_class->task_woken) {
                /*
                 * Nothing relies on rq->lock after this, so its fine to
                 * drop it.
                 */
                rq_unpin_lock(rq, &rf);
                p->sched_class->task_woken(rq, p);
                rq_repin_lock(rq, &rf);
        }
#endif
        task_rq_unlock(rq, p, &rf);
}

#ifdef CONFIG_PREEMPT_NOTIFIERS

static DEFINE_STATIC_KEY_FALSE(preempt_notifier_key);

void preempt_notifier_inc(void)
{
        static_branch_inc(&preempt_notifier_key);
}
EXPORT_SYMBOL_GPL(preempt_notifier_inc);

void preempt_notifier_dec(void)
{
        static_branch_dec(&preempt_notifier_key);
}
EXPORT_SYMBOL_GPL(preempt_notifier_dec);

/**
 * preempt_notifier_register - tell me when current is being preempted & rescheduled
 * @notifier: notifier struct to register
 */
void preempt_notifier_register(struct preempt_notifier *notifier)
{
        if (!static_branch_unlikely(&preempt_notifier_key))
                WARN(1, "registering preempt_notifier while notifiers disabled\n");

        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 *not* 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;

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

static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
        if (static_branch_unlikely(&preempt_notifier_key))
                __fire_sched_in_preempt_notifiers(curr);
}

static void
__fire_sched_out_preempt_notifiers(struct task_struct *curr,
                                   struct task_struct *next)
{
        struct preempt_notifier *notifier;

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

static __always_inline void
fire_sched_out_preempt_notifiers(struct task_struct *curr,
                                 struct task_struct *next)
{
        if (static_branch_unlikely(&preempt_notifier_key))
                __fire_sched_out_preempt_notifiers(curr, next);
}

#else /* !CONFIG_PREEMPT_NOTIFIERS */

static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
}

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

#endif /* CONFIG_PREEMPT_NOTIFIERS */

static inline void prepare_task(struct task_struct *next)
{
#ifdef CONFIG_SMP
        /*
         * Claim the task as running, we do this before switching to it
         * such that any running task will have this set.
         */
        next->on_cpu = 1;
#endif
}

static inline void finish_task(struct task_struct *prev)
{
#ifdef CONFIG_SMP
        /*
         * After ->on_cpu is cleared, the task can be moved to a different CPU.
         * We must ensure this doesn't happen until the switch is completely
         * finished.
         *
         * In particular, the load of prev->state in finish_task_switch() must
         * happen before this.
         *
         * Pairs with the smp_cond_load_acquire() in try_to_wake_up().
         */
        smp_store_release(&prev->on_cpu, 0);
#endif
}

static inline void
prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf)
{
        /*
         * 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:
         */
        rq_unpin_lock(rq, rf);
        spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
#ifdef CONFIG_DEBUG_SPINLOCK
        /* this is a valid case when another task releases the spinlock */
        rq->lock.owner = next;
#endif
}

static inline void finish_lock_switch(struct rq *rq)
{
        /*
         * If we are tracking spinlock dependencies then we have to
         * fix up the runqueue lock - which gets 'carried over' from
         * prev into current:
         */
        spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
        raw_spin_unlock_irq(&rq->lock);
}

/*
 * NOP if the arch has not defined these:
 */

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

#ifndef finish_arch_post_lock_switch
# define finish_arch_post_lock_switch() do { } while (0)
#endif

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

/**
 * finish_task_switch - clean up after a 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.)
 *
 * 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 we need to recalculate this_rq
 * because prev may have moved to another CPU.
 */
static struct rq *finish_task_switch(struct task_struct *prev)
        __releases(rq->lock)
{
        struct rq *rq = this_rq();
        struct mm_struct *mm = rq->prev_mm;
        long prev_state;

        /*
         * The previous task will have left us with a preempt_count of 2
         * because it left us after:
         *
         *      schedule()
         *        preempt_disable();                    // 1
         *        __schedule()
         *          raw_spin_lock_irq(&rq->lock)        // 2
         *
         * Also, see FORK_PREEMPT_COUNT.
         */
        if (WARN_ONCE(preempt_count() != 2*PREEMPT_DISABLE_OFFSET,
                      "corrupted preempt_count: %s/%d/0x%x\n",
                      current->comm, current->pid, preempt_count()))
                preempt_count_set(FORK_PREEMPT_COUNT);

        rq->prev_mm = NULL;

        /*
         * A task struct has one reference for the use as "current".
         * If a task dies, then it sets TASK_DEAD in tsk->state and calls
         * schedule one last time. The schedule call will never return, and
         * the scheduled task must drop that reference.
         *
         * We must observe prev->state before clearing prev->on_cpu (in
         * finish_task), otherwise a concurrent wakeup can get prev
         * running on another CPU and we could rave with its RUNNING -> DEAD
         * transition, resulting in a double drop.
         */
        prev_state = prev->state;
        vtime_task_switch(prev);
        perf_event_task_sched_in(prev, current);
        finish_task(prev);
        finish_lock_switch(rq);
        finish_arch_post_lock_switch();
        kcov_finish_switch(current);

        fire_sched_in_preempt_notifiers(current);
        /*
         * When switching through a kernel thread, the loop in
         * membarrier_{private,global}_expedited() may have observed that
         * kernel thread and not issued an IPI. It is therefore possible to
         * schedule between user->kernel->user threads without passing though
         * switch_mm(). Membarrier requires a barrier after storing to
         * rq->curr, before returning to userspace, so provide them here:
         *
         * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly
         *   provided by mmdrop(),
         * - a sync_core for SYNC_CORE.
         */
        if (mm) {
                membarrier_mm_sync_core_before_usermode(mm);
                mmdrop(mm);
        }
        if (unlikely(prev_state == TASK_DEAD)) {
                if (prev->sched_class->task_dead)
                        prev->sched_class->task_dead(prev);

                /*
                 * Remove function-return probe instances associated with this
                 * task and put them back on the free list.
                 */
                kprobe_flush_task(prev);

                /* Task is done with its stack. */
                put_task_stack(prev);

                put_task_struct(prev);
        }

        tick_nohz_task_switch();
        return rq;
}

#ifdef CONFIG_SMP

/* rq->lock is NOT held, but preemption is disabled */
static void __balance_callback(struct rq *rq)
{
        struct callback_head *head, *next;
        void (*func)(struct rq *rq);
        unsigned long flags;

        raw_spin_lock_irqsave(&rq->lock, flags);
        head = rq->balance_callback;
        rq->balance_callback = NULL;
        while (head) {
                func = (void (*)(struct rq *))head->func;
                next = head->next;
                head->next = NULL;
                head = next;

                func(rq);
        }
        raw_spin_unlock_irqrestore(&rq->lock, flags);
}

static inline void balance_callback(struct rq *rq)
{
        if (unlikely(rq->balance_callback))
                __balance_callback(rq);
}

#else

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

#endif

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

        /*
         * New tasks start with FORK_PREEMPT_COUNT, see there and
         * finish_task_switch() for details.
         *
         * finish_task_switch() will drop rq->lock() and lower preempt_count
         * and the preempt_enable() will end up enabling preemption (on
         * PREEMPT_COUNT kernels).
         */

        rq = finish_task_switch(prev);
        balance_callback(rq);
        preempt_enable();

        if (current->set_child_tid)
                put_user(task_pid_vnr(current), current->set_child_tid);

        calculate_sigpending();
}

/*
 * context_switch - switch to the new MM and the new thread's register state.
 */
static __always_inline struct rq *
context_switch(struct rq *rq, struct task_struct *prev,
               struct task_struct *next, struct rq_flags *rf)
{
        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 is non-NULL, we pass through switch_mm(). If mm is
         * NULL, we will pass through mmdrop() in finish_task_switch().
         * Both of these contain the full memory barrier required by
         * membarrier after storing to rq->curr, before returning to
         * user-space.
         */
        if (!mm) {
                next->active_mm = oldmm;
                mmgrab(oldmm);
                enter_lazy_tlb(oldmm, next);
        } else
                switch_mm_irqs_off(oldmm, mm, next);

        if (!prev->mm) {
                prev->active_mm = NULL;
                rq->prev_mm = oldmm;
        }

        rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);

        prepare_lock_switch(rq, next, rf);

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

        return finish_task_switch(prev);
}

/*
 * nr_running and nr_context_switches:
 *
 * externally visible scheduler statistics: current number of runnable
 * 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;
}

/*
 * Check if only the current task is running on the CPU.
 *
 * Caution: this function does not check that the caller has disabled
 * preemption, thus the result might have a time-of-check-to-time-of-use
 * race.  The caller is responsible to use it correctly, for example:
 *
 * - from a non-preemptable section (of course)
 *
 * - from a thread that is bound to a single CPU
 *
 * - in a loop with very short iterations (e.g. a polling loop)
 */
bool single_task_running(void)
{
        return raw_rq()->nr_running == 1;
}
EXPORT_SYMBOL(single_task_running);

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;
}

/*
 * IO-wait accounting, and how its mostly bollocks (on SMP).
 *
 * The idea behind IO-wait account is to account the idle time that we could
 * have spend running if it were not for IO. That is, if we were to improve the
 * storage performance, we'd have a proportional reduction in IO-wait time.
 *
 * This all works nicely on UP, where, when a task blocks on IO, we account
 * idle time as IO-wait, because if the storage were faster, it could've been
 * running and we'd not be idle.
 *
 * This has been extended to SMP, by doing the same for each CPU. This however
 * is broken.
 *
 * Imagine for instance the case where two tasks block on one CPU, only the one
 * CPU will have IO-wait accounted, while the other has regular idle. Even
 * though, if the storage were faster, both could've ran at the same time,
 * utilising both CPUs.
 *
 * This means, that when looking globally, the current IO-wait accounting on
 * SMP is a lower bound, by reason of under accounting.
 *
 * Worse, since the numbers are provided per CPU, they are sometimes
 * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly
 * associated with any one particular CPU, it can wake to another CPU than it
 * blocked on. This means the per CPU IO-wait number is meaningless.
 *
 * Task CPU affinities can make all that even more 'interesting'.
 */

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;
}

/*
 * Consumers of these two interfaces, like for example the cpufreq menu
 * governor are using nonsensical data. Boosting frequency for a CPU that has
 * IO-wait which might not even end up running the task when it does become
 * runnable.
 */

unsigned long nr_iowait_cpu(int cpu)
{
        struct rq *this = cpu_rq(cpu);
        return atomic_read(&this->nr_iowait);
}

void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
{
        struct rq *rq = this_rq();
        *nr_waiters = atomic_read(&rq->nr_iowait);
        *load = rq->load.weight;
}

#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, task_cpu(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);

/*
 * The function fair_sched_class.update_curr accesses the struct curr
 * and its field curr->exec_start; when called from task_sched_runtime(),
 * we observe a high rate of cache misses in practice.
 * Prefetching this data results in improved performance.
 */
static inline void prefetch_curr_exec_start(struct task_struct *p)
{
#ifdef CONFIG_FAIR_GROUP_SCHED
        struct sched_entity *curr = (&p->se)->cfs_rq->curr;
#else
        struct sched_entity *curr = (&task_rq(p)->cfs)->curr;
#endif
        prefetch(curr);
        prefetch(&curr->exec_start);
}

/*
 * 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)
{
        struct rq_flags rf;
        struct rq *rq;
        u64 ns;

#if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
        /*
         * 64-bit doesn't need locks to atomically read a 64-bit value.
         * So we have a optimization chance when the task's delta_exec is 0.
         * Reading ->on_cpu is racy, but this is ok.
         *
         * If we race with it leaving CPU, we'll take a lock. So we're correct.
         * If we race with it entering CPU, unaccounted time is 0. This is
         * indistinguishable from the read occurring a few cycles earlier.
         * If we see ->on_cpu without ->on_rq, the task is leaving, and has
         * been accounted, so we're correct here as well.
         */
        if (!p->on_cpu || !task_on_rq_queued(p))
                return p->se.sum_exec_runtime;
#endif

        rq = task_rq_lock(p, &rf);
        /*
         * Must be ->curr _and_ ->on_rq.  If dequeued, we would
         * project cycles that may never be accounted to this
         * thread, breaking clock_gettime().
         */
        if (task_current(rq, p) && task_on_rq_queued(p)) {
                prefetch_curr_exec_start(p);
                update_rq_clock(rq);
                p->sched_class->update_curr(rq);
        }
        ns = p->se.sum_exec_runtime;
        task_rq_unlock(rq, p, &rf);

        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;
        struct rq_flags rf;

        sched_clock_tick();

        rq_lock(rq, &rf);

        update_rq_clock(rq);
        curr->sched_class->task_tick(rq, curr, 0);
        cpu_load_update_active(rq);
        calc_global_load_tick(rq);

        rq_unlock(rq, &rf);

        perf_event_task_tick();

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

#ifdef CONFIG_NO_HZ_FULL

struct tick_work {
        int                     cpu;
        struct delayed_work     work;
};

static struct tick_work __percpu *tick_work_cpu;

static void sched_tick_remote(struct work_struct *work)
{
        struct delayed_work *dwork = to_delayed_work(work);
        struct tick_work *twork = container_of(dwork, struct tick_work, work);
        int cpu = twork->cpu;
        struct rq *rq = cpu_rq(cpu);
        struct task_struct *curr;
        struct rq_flags rf;
        u64 delta;

        /*
         * Handle the tick only if it appears the remote CPU is running in full
         * dynticks mode. The check is racy by nature, but missing a tick or
         * having one too much is no big deal because the scheduler tick updates
         * statistics and checks timeslices in a time-independent way, regardless
         * of when exactly it is running.
         */
        if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu))
                goto out_requeue;

        rq_lock_irq(rq, &rf);
        curr = rq->curr;
        if (is_idle_task(curr))
                goto out_unlock;

        update_rq_clock(rq);
        delta = rq_clock_task(rq) - curr->se.exec_start;

        /*
         * Make sure the next tick runs within a reasonable
         * amount of time.
         */
        WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
        curr->sched_class->task_tick(rq, curr, 0);

out_unlock:
        rq_unlock_irq(rq, &rf);

out_requeue:
        /*
         * Run the remote tick once per second (1Hz). This arbitrary
         * frequency is large enough to avoid overload but short enough
         * to keep scheduler internal stats reasonably up to date.
         */
        queue_delayed_work(system_unbound_wq, dwork, HZ);
}

static void sched_tick_start(int cpu)
{
        struct tick_work *twork;

        if (housekeeping_cpu(cpu, HK_FLAG_TICK))
                return;

        WARN_ON_ONCE(!tick_work_cpu);

        twork = per_cpu_ptr(tick_work_cpu, cpu);
        twork->cpu = cpu;
        INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
        queue_delayed_work(system_unbound_wq, &twork->work, HZ);
}

#ifdef CONFIG_HOTPLUG_CPU
static void sched_tick_stop(int cpu)
{
        struct tick_work *twork;

        if (housekeeping_cpu(cpu, HK_FLAG_TICK))
                return;

        WARN_ON_ONCE(!tick_work_cpu);

        twork = per_cpu_ptr(tick_work_cpu, cpu);
        cancel_delayed_work_sync(&twork->work);
}
#endif /* CONFIG_HOTPLUG_CPU */

int __init sched_tick_offload_init(void)
{
        tick_work_cpu = alloc_percpu(struct tick_work);
        BUG_ON(!tick_work_cpu);

        return 0;
}

#else /* !CONFIG_NO_HZ_FULL */
static inline void sched_tick_start(int cpu) { }
static inline void sched_tick_stop(int cpu) { }
#endif

#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
                                defined(CONFIG_TRACE_PREEMPT_TOGGLE))
/*
 * If the value passed in is equal to the current preempt count
 * then we just disabled preemption. Start timing the latency.
 */
static inline void preempt_latency_start(int val)
{
        if (preempt_count() == val) {
                unsigned long ip = get_lock_parent_ip();
#ifdef CONFIG_DEBUG_PREEMPT
                current->preempt_disable_ip = ip;
#endif
                trace_preempt_off(CALLER_ADDR0, ip);
        }
}

void preempt_count_add(int val)
{
#ifdef CONFIG_DEBUG_PREEMPT
        /*
         * Underflow?
         */
        if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
                return;
#endif
        __preempt_count_add(val);
#ifdef CONFIG_DEBUG_PREEMPT
        /*
         * Spinlock count overflowing soon?
         */
        DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
                                PREEMPT_MASK - 10);
#endif
        preempt_latency_start(val);
}
EXPORT_SYMBOL(preempt_count_add);
NOKPROBE_SYMBOL(preempt_count_add);

/*
 * If the value passed in equals to the current preempt count
 * then we just enabled preemption. Stop timing the latency.
 */
static inline void preempt_latency_stop(int val)
{
        if (preempt_count() == val)
                trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
}

void preempt_count_sub(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

        preempt_latency_stop(val);
        __preempt_count_sub(val);
}
EXPORT_SYMBOL(preempt_count_sub);
NOKPROBE_SYMBOL(preempt_count_sub);

#else
static inline void preempt_latency_start(int val) { }
static inline void preempt_latency_stop(int val) { }
#endif

static inline unsigned long get_preempt_disable_ip(struct task_struct *p)
{
#ifdef CONFIG_DEBUG_PREEMPT
        return p->preempt_disable_ip;
#else
        return 0;
#endif
}

/*
 * Print scheduling while atomic bug:
 */
static noinline void __schedule_bug(struct task_struct *prev)
{
        /* Save this before calling printk(), since that will clobber it */
        unsigned long preempt_disable_ip = get_preempt_disable_ip(current);

        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);
        if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
            && in_atomic_preempt_off()) {
                pr_err("Preemption disabled at:");
                print_ip_sym(preempt_disable_ip);
                pr_cont("\n");
        }
        if (panic_on_warn)
                panic("scheduling while atomic\n");

        dump_stack();
        add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
}

/*
 * Various schedule()-time debugging checks and statistics:
 */
static inline void schedule_debug(struct task_struct *prev)
{
#ifdef CONFIG_SCHED_STACK_END_CHECK
        if (task_stack_end_corrupted(prev))
                panic("corrupted stack end detected inside scheduler\n");
#endif

        if (unlikely(in_atomic_preempt_off())) {
                __schedule_bug(prev);
                preempt_count_set(PREEMPT_DISABLED);
        }
        rcu_sleep_check();

        profile_hit(SCHED_PROFILING, __builtin_return_address(0));

        schedstat_inc(this_rq()->sched_count);
}

/*
 * Pick up the highest-prio task:
 */
static inline struct task_struct *
pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
        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, but only if the @prev task wasn't of a
         * higher scheduling class, because otherwise those loose the
         * opportunity to pull in more work from other CPUs.
         */
        if (likely((prev->sched_class == &idle_sched_class ||
                    prev->sched_class == &fair_sched_class) &&
                   rq->nr_running == rq->cfs.h_nr_running)) {

                p = fair_sched_class.pick_next_task(rq, prev, rf);
                if (unlikely(p == RETRY_TASK))
                        goto again;

                /* Assumes fair_sched_class->next == idle_sched_class */
                if (unlikely(!p))
                        p = idle_sched_class.pick_next_task(rq, prev, rf);

                return p;
        }

again:
        for_each_class(class) {
                p = class->pick_next_task(rq, prev, rf);
                if (p) {
                        if (unlikely(p == RETRY_TASK))
                                goto again;
                        return p;
                }
        }

        /* The idle class should always have a runnable task: */
        BUG();
}

/*
 * __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
 *
 * WARNING: must be called with preemption disabled!
 */
static void __sched notrace __schedule(bool preempt)
{
        struct task_struct *prev, *next;
        unsigned long *switch_count;
        struct rq_flags rf;
        struct rq *rq;
        int cpu;

        cpu = smp_processor_id();
        rq = cpu_rq(cpu);
        prev = rq->curr;

        schedule_debug(prev);

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

        local_irq_disable();
        rcu_note_context_switch(preempt);

        /*
         * Make sure that signal_pending_state()->signal_pending() below
         * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
         * done by the caller to avoid the race with signal_wake_up().
         *
         * The membarrier system call requires a full memory barrier
         * after coming from user-space, before storing to rq->curr.
         */
        rq_lock(rq, &rf);
        smp_mb__after_spinlock();

        /* Promote REQ to ACT */
        rq->clock_update_flags <<= 1;
        update_rq_clock(rq);

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

                        if (prev->in_iowait) {
                                atomic_inc(&rq->nr_iowait);
                                delayacct_blkio_start();
                        }

                        /*
                         * 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);
                                if (to_wakeup)
                                        try_to_wake_up_local(to_wakeup, &rf);
                        }
                }
                switch_count = &prev->nvcsw;
        }

        next = pick_next_task(rq, prev, &rf);
        clear_tsk_need_resched(prev);
        clear_preempt_need_resched();

        if (likely(prev != next)) {
                rq->nr_switches++;
                rq->curr = next;
                /*
                 * The membarrier system call requires each architecture
                 * to have a full memory barrier after updating
                 * rq->curr, before returning to user-space.
                 *
                 * Here are the schemes providing that barrier on the
                 * various architectures:
                 * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC.
                 *   switch_mm() rely on membarrier_arch_switch_mm() on PowerPC.
                 * - finish_lock_switch() for weakly-ordered
                 *   architectures where spin_unlock is a full barrier,
                 * - switch_to() for arm64 (weakly-ordered, spin_unlock
                 *   is a RELEASE barrier),
                 */
                ++*switch_count;

                trace_sched_switch(preempt, prev, next);

                /* Also unlocks the rq: */
                rq = context_switch(rq, prev, next, &rf);
        } else {
                rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
                rq_unlock_irq(rq, &rf);
        }

        balance_callback(rq);
}

void __noreturn do_task_dead(void)
{
        /* Causes final put_task_struct in finish_task_switch(): */
        set_special_state(TASK_DEAD);

        /* Tell freezer to ignore us: */
        current->flags |= PF_NOFREEZE;

        __schedule(false);
        BUG();

        /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
        for (;;)
                cpu_relax();
}

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

        sched_submit_work(tsk);
        do {
                preempt_disable();
                __schedule(false);
                sched_preempt_enable_no_resched();
        } while (need_resched());
}
EXPORT_SYMBOL(schedule);

/*
 * synchronize_rcu_tasks() makes sure that no task is stuck in preempted
 * state (have scheduled out non-voluntarily) by making sure that all
 * tasks have either left the run queue or have gone into user space.
 * As idle tasks do not do either, they must not ever be preempted
 * (schedule out non-voluntarily).
 *
 * schedule_idle() is similar to schedule_preempt_disable() except that it
 * never enables preemption because it does not call sched_submit_work().
 */
void __sched schedule_idle(void)
{
        /*
         * As this skips calling sched_submit_work(), which the idle task does
         * regardless because that function is a nop when the task is in a
         * TASK_RUNNING state, make sure this isn't used someplace that the
         * current task can be in any other state. Note, idle is always in the
         * TASK_RUNNING state.
         */
        WARN_ON_ONCE(current->state);
        do {
                __schedule(false);
        } while (need_resched());
}

#ifdef CONFIG_CONTEXT_TRACKING
asmlinkage __visible 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.
         *
         * NB: There are buggy callers of this function.  Ideally we
         * should warn if prev_state != CONTEXT_USER, but that will trigger
         * too frequently to make sense yet.
         */
        enum ctx_state prev_state = exception_enter();
        schedule();
        exception_exit(prev_state);
}
#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();
}

static void __sched notrace preempt_schedule_common(void)
{
        do {
                /*
                 * Because the function tracer can trace preempt_count_sub()
                 * and it also uses preempt_enable/disable_notrace(), if
                 * NEED_RESCHED is set, the preempt_enable_notrace() called
                 * by the function tracer will call this function again and
                 * cause infinite recursion.
                 *
                 * Preemption must be disabled here before the function
                 * tracer can trace. Break up preempt_disable() into two
                 * calls. One to disable preemption without fear of being
                 * traced. The other to still record the preemption latency,
                 * which can also be traced by the function tracer.
                 */
                preempt_disable_notrace();
                preempt_latency_start(1);
                __schedule(true);
                preempt_latency_stop(1);
                preempt_enable_no_resched_notrace();

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

#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 __visible void __sched notrace preempt_schedule(void)
{
        /*
         * 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(!preemptible()))
                return;

        preempt_schedule_common();
}
NOKPROBE_SYMBOL(preempt_schedule);
EXPORT_SYMBOL(preempt_schedule);

/**
 * preempt_schedule_notrace - preempt_schedule called by tracing
 *
 * The tracing infrastructure uses preempt_enable_notrace to prevent
 * recursion and tracing preempt enabling caused by the tracing
 * infrastructure itself. But as tracing can happen in areas coming
 * from userspace or just about to enter userspace, a preempt enable
 * can occur before user_exit() is called. This will cause the scheduler
 * to be called when the system is still in usermode.
 *
 * To prevent this, the preempt_enable_notrace will use this function
 * instead of preempt_schedule() to exit user context if needed before
 * calling the scheduler.
 */
asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
{
        enum ctx_state prev_ctx;

        if (likely(!preemptible()))
                return;

        do {
                /*
                 * Because the function tracer can trace preempt_count_sub()
                 * and it also uses preempt_enable/disable_notrace(), if
                 * NEED_RESCHED is set, the preempt_enable_notrace() called
                 * by the function tracer will call this function again and
                 * cause infinite recursion.
                 *
                 * Preemption must be disabled here before the function
                 * tracer can trace. Break up preempt_disable() into two
                 * calls. One to disable preemption without fear of being
                 * traced. The other to still record the preemption latency,
                 * which can also be traced by the function tracer.
                 */
                preempt_disable_notrace();
                preempt_latency_start(1);
                /*
                 * Needs preempt disabled in case user_exit() is traced
                 * and the tracer calls preempt_enable_notrace() causing
                 * an infinite recursion.
                 */
                prev_ctx = exception_enter();
                __schedule(true);
                exception_exit(prev_ctx);

                preempt_latency_stop(1);
                preempt_enable_no_resched_notrace();
        } while (need_resched());
}
EXPORT_SYMBOL_GPL(preempt_schedule_notrace);

#endif /* CONFIG_PREEMPT */

/*
 * 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 __visible void __sched preempt_schedule_irq(void)
{
        enum ctx_state prev_state;

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

        prev_state = exception_enter();

        do {
                preempt_disable();
                local_irq_enable();
                __schedule(true);
                local_irq_disable();
                sched_preempt_enable_no_resched();
        } while (need_resched());

        exception_exit(prev_state);
}

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

#ifdef CONFIG_RT_MUTEXES

static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
{
        if (pi_task)
                prio = min(prio, pi_task->prio);

        return prio;
}

static inline int rt_effective_prio(struct task_struct *p, int prio)
{
        struct task_struct *pi_task = rt_mutex_get_top_task(p);

        return __rt_effective_prio(pi_task, prio);
}

/*
 * rt_mutex_setprio - set the current priority of a task
 * @p: task to boost
 * @pi_task: donor task
 *
 * 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. Call site only calls if the priority of the task changed.
 */
void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
{
        int prio, oldprio, queued, running, queue_flag =
                DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
        const struct sched_class *prev_class;
        struct rq_flags rf;
        struct rq *rq;

        /* XXX used to be waiter->prio, not waiter->task->prio */
        prio = __rt_effective_prio(pi_task, p->normal_prio);

        /*
         * If nothing changed; bail early.
         */
        if (p->pi_top_task == pi_task && prio == p->prio && !dl_prio(prio))
                return;

        rq = __task_rq_lock(p, &rf);
        update_rq_clock(rq);
        /*
         * Set under pi_lock && rq->lock, such that the value can be used under
         * either lock.
         *
         * Note that there is loads of tricky to make this pointer cache work
         * right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to
         * ensure a task is de-boosted (pi_task is set to NULL) before the
         * task is allowed to run again (and can exit). This ensures the pointer
         * points to a blocked task -- which guaratees the task is present.
         */
        p->pi_top_task = pi_task;

        /*
         * For FIFO/RR we only need to set prio, if that matches we're done.
         */
        if (prio == p->prio && !dl_prio(prio))
                goto out_unlock;

        /*
         * 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, pi_task);
        oldprio = p->prio;

        if (oldprio == prio)
                queue_flag &= ~DEQUEUE_MOVE;

        prev_class = p->sched_class;
        queued = task_on_rq_queued(p);
        running = task_current(rq, p);
        if (queued)
                dequeue_task(rq, p, queue_flag);
        if (running)
                put_prev_task(rq, p);

        /*
         * Boosting condition are:
         * 1. -rt task is running and holds mutex A
         *      --> -dl task blocks on mutex A
         *
         * 2. -dl task is running and holds mutex A
         *      --> -dl task blocks on mutex A and could preempt the
         *          running task
         */
        if (dl_prio(prio)) {
                if (!dl_prio(p->normal_prio) ||
                    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
                        p->dl.dl_boosted = 1;
                        queue_flag |= ENQUEUE_REPLENISH;
                } else
                        p->dl.dl_boosted = 0;
                p->sched_class = &dl_sched_class;
        } else if (rt_prio(prio)) {
                if (dl_prio(oldprio))
                        p->dl.dl_boosted = 0;
                if (oldprio < prio)
                        queue_flag |= ENQUEUE_HEAD;
                p->sched_class = &rt_sched_class;
        } else {
                if (dl_prio(oldprio))
                        p->dl.dl_boosted = 0;
                if (rt_prio(oldprio))
                        p->rt.timeout = 0;
                p->sched_class = &fair_sched_class;
        }

        p->prio = prio;

        if (queued)
                enqueue_task(rq, p, queue_flag);
        if (running)
                set_curr_task(rq, p);

        check_class_changed(rq, p, prev_class, oldprio);
out_unlock:
        /* Avoid rq from going away on us: */
        preempt_disable();
        __task_rq_unlock(rq, &rf);

        balance_callback(rq);
        preempt_enable();
}
#else
static inline int rt_effective_prio(struct task_struct *p, int prio)
{
        return prio;
}
#endif

void set_user_nice(struct task_struct *p, long nice)
{
        bool queued, running;
        int old_prio, delta;
        struct rq_flags rf;
        struct rq *rq;

        if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
                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, &rf);
        update_rq_clock(rq);

        /*
         * The RT priorities are set via sched_setscheduler(), but we still
         * allow the 'normal' nice value to be set - but as expected
         * it wont have any effect on scheduling until the task is
         * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR:
         */
        if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
                p->static_prio = NICE_TO_PRIO(nice);
                goto out_unlock;
        }
        queued = task_on_rq_queued(p);
        running = task_current(rq, p);
        if (queued)
                dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
        if (running)
                put_prev_task(rq, p);

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

        if (queued) {
                enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
                /*
                 * 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_curr(rq);
        }
        if (running)
                set_curr_task(rq, p);
out_unlock:
        task_rq_unlock(rq, p, &rf);
}
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 = nice_to_rlimit(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.
         */
        increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH);
        nice = task_nice(current) + increment;

        nice = clamp_val(nice, MIN_NICE, MAX_NICE);
        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.
 *
 * Return: 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;
}

/**
 * idle_cpu - is a given CPU idle currently?
 * @cpu: the processor in question.
 *
 * Return: 1 if the CPU is currently idle. 0 otherwise.
 */
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))