xref: /device/soc/rockchip/common/sdk_linux/kernel/sched/core.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 *  kernel/sched/core.c
 *
 *  Core kernel scheduler code and related syscalls
 *
 *  Copyright (C) 1991-2002  Linus Torvalds
 */
#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>
#undef CREATE_TRACE_POINTS

#include "sched.h"

#include <linux/nospec.h>

#include <linux/kcov.h>
#include <linux/scs.h>
#include <linux/irq.h>
#include <linux/delay.h>

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

#include "../workqueue_internal.h"
#include "../../io_uring/io-wq.h"
#include "../smpboot.h"

#include "pelt.h"
#include "smp.h"
#include "walt.h"
#include "rtg/rtg.h"

/*
 * Export tracepoints that act as a bare tracehook (ie: have no trace event
 * associated with them) to allow external modules to probe them.
 */
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_cfs_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_thermal_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_waking);
#ifdef CONFIG_SCHEDSTATS
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_stat_sleep);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_stat_wait);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_stat_iowait);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_stat_blocked);
#endif

DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);

#ifdef CONFIG_SCHED_DEBUG
/*
 * 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;

/*
 * Serialization rules
 *
 * Lock order
 *
 *   p->pi_lock
 *     rq->lock
 *       hrtimer_cpu_base->lock (hrtimer_start() for bandwidth controls)
 *
 *  rq1->lock
 *    rq2->lock  where: rq1 < rq2
 *
 * Regular state
 *
 * Normal scheduling state is serialized by rq->lock. __schedule() takes the
 * local CPU's rq->lock, it optionally removes the task from the runqueue and
 * always looks at the local rq data structures to find the most elegible task
 * to run next.
 *
 * Task enqueue is also under rq->lock, possibly taken from another CPU.
 * Wakeups from another LLC domain might use an IPI to transfer the enqueue to
 * the local CPU to avoid bouncing the runqueue state around [ see
 * ttwu_queue_wakelist() ]
 *
 * Task wakeup, specifically wakeups that involve migration, are horribly
 * complicated to avoid having to take two rq->locks.
 *
 * Special state
 *
 * System-calls and anything external will use task_rq_lock() which acquires
 * both p->pi_lock and rq->lock. As a consequence the state they change is
 * stable while holding either lock
 *
 *  - sched_setaffinity()/
 *    set_cpus_allowed_ptr():    p->cpus_ptr, p->nr_cpus_allowed
 *  - set_user_nice():        p->se.load, p->*prio
 *  - __sched_setscheduler():    p->sched_class, p->policy, p->*prio,
 *                p->se.load, p->rt_priority,
 *                p->dl.dl_{runtime, deadline, period, flags, bw, density}
 *  - sched_setnuma():        p->numa_preferred_nid
 *  - sched_move_task()/
 *    cpu_cgroup_fork():    p->sched_task_group
 *  - uclamp_update_active()    p->uclamp*
 *
 * p->state <- TASK_*
 *
 *   is changed locklessly using set_current_state(), __set_current_state() or
 *   set_special_state(), see their respective comments, or by
 *   try_to_wake_up(). This latter uses p->pi_lock to serialize against
 *   concurrent self.
 *
 * p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }:
 *
 *   is set by activate_task() and cleared by deactivate_task(), under
 *   rq->lock. Non-zero indicates the task is runnable, the special
 *   ON_RQ_MIGRATING state is used for migration without holding both
 *   rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
 *
 * p->on_cpu <- { 0, 1 }
 *
 *   is set by prepare_task() and cleared by finish_task() such that it will be
 *   set before p is scheduled-in and cleared after p is scheduled-out, both
 *   under rq->lock. Non-zero indicates the task is running on its CPU.
 *
 *   [ The astute reader will observe that it is possible for two tasks on one
 *     CPU to have ->on_cpu = 1 at the same time. ]
 *
 * task_cpu(p): is changed by set_task_cpu(), the rules are:
 *
 *  - Don't call set_task_cpu() on a blocked task:
 *
 *    We don't care what CPU we're not running on, this simplifies hotplug,
 *    the CPU assignment of blocked tasks isn't required to be valid.
 *
 *  - for try_to_wake_up(), called under p->pi_lock:
 *
 *    This allows try_to_wake_up() to only take one rq->lock, see its comment.
 *
 *  - for migration called under rq->lock:
 *    [ see task_on_rq_migrating() in task_rq_lock() ]
 *
 *    o move_queued_task()
 *    o detach_task()
 *
 *  - for migration called under double_rq_lock()
 *
 *    o __migrate_swap_task()
 *    o push_rt_task() / pull_rt_task()
 *    o push_dl_task() / pull_dl_task()
 *    o dl_task_offline_migration()
 *
 */

/*
 * __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 address
         * dependency headed by '[L] rq = task_rq()' and the acquire
         * will pair with the WMB to ensure we 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...
     */
    s64 __maybe_unused steal = 0, irq_delta = 0;

#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 CONFIG_HAVE_SCHED_AVG_IRQ
    if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) {
        update_irq_load_avg(rq, irq_delta + steal);
    }
#endif
    update_rq_clock_pelt(rq, delta);
}

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);
}

static inline void rq_csd_init(struct rq *rq, struct __call_single_data *csd,
                               smp_call_func_t func)
{
    csd->flags = 0;
    csd->func = func;
    csd->info = rq;
}

#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;
    ktime_t time = rq->hrtick_time;

    hrtimer_start(timer, time, HRTIMER_MODE_ABS_PINNED_HARD);
}

/*
 * 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_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;
    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);
    rq->hrtick_time = ktime_add_ns(timer->base->get_time(), delta);

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

#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_HARD);
}

#endif /* CONFIG_SMP */

static void hrtick_rq_init(struct rq *rq)
{
#ifdef CONFIG_SMP
    rq_csd_init(rq, &rq->hrtick_csd, __hrtick_start);
#endif
    hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
    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

static bool __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.
     *
     * In order to ensure that a pending wakeup will observe our pending
     * state, even in the failed case, an explicit smp_mb() must be used.
     */
    smp_mb__before_atomic();
    if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL))) {
        return false;
    }

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

/**
 * wake_q_add() - queue a wakeup for 'later' waking.
 * @head: the wake_q_head to add @task to
 * @task: the task to queue for 'later' wakeup
 *
 * Queue a task for later wakeup, most likely by the wake_up_q() call in the
 * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
 * instantly.
 *
 * This function must be used as-if it were wake_up_process(); IOW the task
 * must be ready to be woken at this location.
 */
void wake_q_add(struct wake_q_head *head, struct task_struct *task)
{
    if (__wake_q_add(head, task)) {
        get_task_struct(task);
    }
}

/**
 * wake_q_add_safe() - safely queue a wakeup for 'later' waking.
 * @head: the wake_q_head to add @task to
 * @task: the task to queue for 'later' wakeup
 *
 * Queue a task for later wakeup, most likely by the wake_up_q() call in the
 * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
 * instantly.
 *
 * This function must be used as-if it were wake_up_process(); IOW the task
 * must be ready to be woken at this location.
 *
 * This function is essentially a task-safe equivalent to wake_q_add(). Callers
 * that already hold reference to @task can call the 'safe' version and trust
 * wake_q to do the right thing depending whether or not the @task is already
 * queued for wakeup.
 */
void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task)
{
    if (!__wake_q_add(head, task)) {
        put_task_struct(task);
    }
}

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(), default_cpu = -1;
    struct sched_domain *sd;

    if (housekeeping_cpu(cpu, HK_FLAG_TIMER) && cpu_active(cpu)) {
        if (!idle_cpu(cpu)) {
            return cpu;
        }
        default_cpu = cpu;
    }

    rcu_read_lock();
    for_each_domain(cpu, sd)
    {
        for_each_cpu_and(i, sched_domain_span(sd),
                         housekeeping_cpumask(HK_FLAG_TIMER))
        {
            if (cpu == i) {
                continue;
            }

            if (!idle_cpu(i)) {
                cpu = i;
                goto unlock;
            }
        }
    }

    if (default_cpu == -1) {
        for_each_cpu_and(i, cpu_active_mask,
                         housekeeping_cpumask(HK_FLAG_TIMER))
        {
            if (cpu == i) {
                continue;
            }

            if (!idle_cpu(i)) {
                cpu = i;
                goto unlock;
            }
        }

        /* no active, not-idle, housekpeeing CPU found. */
        default_cpu = cpumask_any(cpu_active_mask);
        if (unlikely(default_cpu >= nr_cpu_ids)) {
            goto unlock;
        }
    }

    cpu = default_cpu;
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 void nohz_csd_func(void *info)
{
    struct rq *rq = info;
    int cpu = cpu_of(rq);
    unsigned int flags;

    /*
     * Release the rq::nohz_csd.
     */
    flags = atomic_fetch_andnot(NOHZ_KICK_MASK, nohz_flags(cpu));
    WARN_ON(!(flags & NOHZ_KICK_MASK));

    rq->idle_balance = idle_cpu(cpu);
    if (rq->idle_balance && !need_resched()) {
        rq->nohz_idle_balance = flags;
        raise_softirq_irqoff(SCHED_SOFTIRQ);
    }
}

#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 = !(READ_ONCE(p->state) & TASK_NEW);
    int prio = p->static_prio - MAX_RT_PRIO;
    struct load_weight *load = &p->se.load;

    /*
     * SCHED_IDLE tasks get minimal weight:
     */
    if (task_has_idle_policy(p)) {
        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];
    }
}

#ifdef CONFIG_SCHED_LATENCY_NICE
static void set_latency_weight(struct task_struct *p)
{
    p->se.latency_weight = sched_latency_to_weight[p->latency_prio];
}

static void __setscheduler_latency(struct task_struct *p,
                                   const struct sched_attr *attr)
{
    if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE) {
        p->latency_prio = NICE_TO_LATENCY(attr->sched_latency_nice);
        set_latency_weight(p);
    }
}

static int latency_nice_validate(struct task_struct *p, bool user,
                                 const struct sched_attr *attr)
{
    if (attr->sched_latency_nice > MAX_LATENCY_NICE) {
        return -EINVAL;
    }
    if (attr->sched_latency_nice < MIN_LATENCY_NICE) {
        return -EINVAL;
    }
    /* Use the same security checks as NICE */
    if (user && attr->sched_latency_nice < LATENCY_TO_NICE(p->latency_prio) &&
        !capable(CAP_SYS_NICE)) {
        return -EPERM;
    }

    return 0;
}
#else
static void __setscheduler_latency(struct task_struct *p,
                                   const struct sched_attr *attr)
{
}

static inline int latency_nice_validate(struct task_struct *p, bool user,
                                        const struct sched_attr *attr)
{
    return -EOPNOTSUPP;
}
#endif

#ifdef CONFIG_UCLAMP_TASK
/*
 * Serializes updates of utilization clamp values
 *
 * The (slow-path) user-space triggers utilization clamp value updates which
 * can require updates on (fast-path) scheduler's data structures used to
 * support enqueue/dequeue operations.
 * While the per-CPU rq lock protects fast-path update operations, user-space
 * requests are serialized using a mutex to reduce the risk of conflicting
 * updates or API abuses.
 */
static DEFINE_MUTEX(uclamp_mutex);

/* Max allowed minimum utilization */
unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;

/* Max allowed maximum utilization */
unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;

/*
 * By default RT tasks run at the maximum performance point/capacity of the
 * system. Uclamp enforces this by always setting UCLAMP_MIN of RT tasks to
 * SCHED_CAPACITY_SCALE.
 *
 * This knob allows admins to change the default behavior when uclamp is being
 * used. In battery powered devices, particularly, running at the maximum
 * capacity and frequency will increase energy consumption and shorten the
 * battery life.
 *
 * This knob only affects RT tasks that their uclamp_se->user_defined == false.
 *
 * This knob will not override the system default sched_util_clamp_min defined
 * above.
 */
unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE;

/* All clamps are required to be less or equal than these values */
static struct uclamp_se uclamp_default[UCLAMP_CNT];

/*
 * This static key is used to reduce the uclamp overhead in the fast path. It
 * primarily disables the call to uclamp_rq_{inc, dec}() in
 * enqueue/dequeue_task().
 *
 * This allows users to continue to enable uclamp in their kernel config with
 * minimum uclamp overhead in the fast path.
 *
 * As soon as userspace modifies any of the uclamp knobs, the static key is
 * enabled, since we have an actual users that make use of uclamp
 * functionality.
 *
 * The knobs that would enable this static key are:
 *
 *   * A task modifying its uclamp value with sched_setattr().
 *   * An admin modifying the sysctl_sched_uclamp_{min, max} via procfs.
 *   * An admin modifying the cgroup cpu.uclamp.{min, max}
 */
DEFINE_STATIC_KEY_FALSE(sched_uclamp_used);

/* Integer rounded range for each bucket */
#define UCLAMP_BUCKET_DELTA                                                    \
    DIV_ROUND_CLOSEST(SCHED_CAPACITY_SCALE, UCLAMP_BUCKETS)

#define cycle_each_clamp_id(clamp_id)                                            \
    for ((clamp_id) = 0; (clamp_id) < UCLAMP_CNT; (clamp_id)++)

static inline unsigned int uclamp_bucket_id(unsigned int clamp_value)
{
    return min_t(unsigned int, clamp_value / UCLAMP_BUCKET_DELTA,
                 UCLAMP_BUCKETS - 1);
}

static inline unsigned int uclamp_none(enum uclamp_id clamp_id)
{
    if (clamp_id == UCLAMP_MIN) {
        return 0;
    }
    return SCHED_CAPACITY_SCALE;
}

static inline void uclamp_se_set(struct uclamp_se *uc_se, unsigned int value,
                                 bool user_defined)
{
    uc_se->value = value;
    uc_se->bucket_id = uclamp_bucket_id(value);
    uc_se->user_defined = user_defined;
}

static inline unsigned int uclamp_idle_value(struct rq *rq,
                                             enum uclamp_id clamp_id,
                                             unsigned int clamp_value)
{
    /*
     * Avoid blocked utilization pushing up the frequency when we go
     * idle (which drops the max-clamp) by retaining the last known
     * max-clamp.
     */
    if (clamp_id == UCLAMP_MAX) {
        rq->uclamp_flags |= UCLAMP_FLAG_IDLE;
        return clamp_value;
    }

    return uclamp_none(UCLAMP_MIN);
}

static inline void uclamp_idle_reset(struct rq *rq, enum uclamp_id clamp_id,
                                     unsigned int clamp_value)
{
    /* Reset max-clamp retention only on idle exit */
    if (!(rq->uclamp_flags & UCLAMP_FLAG_IDLE)) {
        return;
    }

    WRITE_ONCE(rq->uclamp[clamp_id].value, clamp_value);
}

static inline unsigned int uclamp_rq_max_value(struct rq *rq,
                                               enum uclamp_id clamp_id,
                                               unsigned int clamp_value)
{
    struct uclamp_bucket *bucket = rq->uclamp[clamp_id].bucket;
    int bucket_id = UCLAMP_BUCKETS - 1;

    /*
     * Since both min and max clamps are max aggregated, find the
     * top most bucket with tasks in.
     */
    for (; bucket_id >= 0; bucket_id--) {
        if (!bucket[bucket_id].tasks) {
            continue;
        }
        return bucket[bucket_id].value;
    }

    /* No tasks -- default clamp values */
    return uclamp_idle_value(rq, clamp_id, clamp_value);
}

static void __uclamp_update_util_min_rt_default(struct task_struct *p)
{
    unsigned int default_util_min;
    struct uclamp_se *uc_se;

    lockdep_assert_held(&p->pi_lock);

    uc_se = &p->uclamp_req[UCLAMP_MIN];

    /* Only sync if user didn't override the default */
    if (uc_se->user_defined) {
        return;
    }

    default_util_min = sysctl_sched_uclamp_util_min_rt_default;
    uclamp_se_set(uc_se, default_util_min, false);
}

static void uclamp_update_util_min_rt_default(struct task_struct *p)
{
    struct rq_flags rf;
    struct rq *rq;

    if (!rt_task(p)) {
        return;
    }

    /* Protect updates to p->uclamp_* */
    rq = task_rq_lock(p, &rf);
    __uclamp_update_util_min_rt_default(p);
    task_rq_unlock(rq, p, &rf);
}

static void uclamp_sync_util_min_rt_default(void)
{
    struct task_struct *g, *p;

    /*
     * copy_process()            sysctl_uclamp
     *                      uclamp_min_rt = X;
     *   write_lock(&tasklist_lock)          read_lock(&tasklist_lock)
     *   // link thread              smp_mb__after_spinlock()
     *   write_unlock(&tasklist_lock)      read_unlock(&tasklist_lock);
     *   sched_post_fork()              for_each_process_thread()
     *     __uclamp_sync_rt()            __uclamp_sync_rt()
     *
     * Ensures that either sched_post_fork() will observe the new
     * uclamp_min_rt or for_each_process_thread() will observe the new
     * task.
     */
    read_lock(&tasklist_lock);
    smp_mb__after_spinlock();
    read_unlock(&tasklist_lock);

    rcu_read_lock();
    for_each_process_thread(g, p) uclamp_update_util_min_rt_default(p);
    rcu_read_unlock();
}

static inline struct uclamp_se uclamp_tg_restrict(struct task_struct *p,
                                                  enum uclamp_id clamp_id)
{
    /* Copy by value as we could modify it */
    struct uclamp_se uc_req = p->uclamp_req[clamp_id];
#ifdef CONFIG_UCLAMP_TASK_GROUP
    unsigned int tg_min, tg_max, value;

    /*
     * Tasks in autogroups or root task group will be
     * restricted by system defaults.
     */
    if (task_group_is_autogroup(task_group(p))) {
        return uc_req;
    }
    if (task_group(p) == &root_task_group) {
        return uc_req;
    }

    tg_min = task_group(p)->uclamp[UCLAMP_MIN].value;
    tg_max = task_group(p)->uclamp[UCLAMP_MAX].value;
    value = uc_req.value;
    value = clamp(value, tg_min, tg_max);
    uclamp_se_set(&uc_req, value, false);
#endif

    return uc_req;
}

/*
 * The effective clamp bucket index of a task depends on, by increasing
 * priority:
 * - the task specific clamp value, when explicitly requested from userspace
 * - the task group effective clamp value, for tasks not either in the root
 *   group or in an autogroup
 * - the system default clamp value, defined by the sysadmin
 */
static inline struct uclamp_se uclamp_eff_get(struct task_struct *p,
                                              enum uclamp_id clamp_id)
{
    struct uclamp_se uc_req = uclamp_tg_restrict(p, clamp_id);
    struct uclamp_se uc_max = uclamp_default[clamp_id];

    /* System default restrictions always apply */
    if (unlikely(uc_req.value > uc_max.value)) {
        return uc_max;
    }

    return uc_req;
}

unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id)
{
    struct uclamp_se uc_eff;

    /* Task currently refcounted: use back-annotated (effective) value */
    if (p->uclamp[clamp_id].active) {
        return (unsigned long)p->uclamp[clamp_id].value;
    }

    uc_eff = uclamp_eff_get(p, clamp_id);

    return (unsigned long)uc_eff.value;
}

/*
 * When a task is enqueued on a rq, the clamp bucket currently defined by the
 * task's uclamp::bucket_id is refcounted on that rq. This also immediately
 * updates the rq's clamp value if required.
 *
 * Tasks can have a task-specific value requested from user-space, track
 * within each bucket the maximum value for tasks refcounted in it.
 * This "local max aggregation" allows to track the exact "requested" value
 * for each bucket when all its RUNNABLE tasks require the same clamp.
 */
static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p,
                                    enum uclamp_id clamp_id)
{
    struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id];
    struct uclamp_se *uc_se = &p->uclamp[clamp_id];
    struct uclamp_bucket *bucket;

    lockdep_assert_held(&rq->lock);

    /* Update task effective clamp */
    p->uclamp[clamp_id] = uclamp_eff_get(p, clamp_id);

    bucket = &uc_rq->bucket[uc_se->bucket_id];
    bucket->tasks++;
    uc_se->active = true;

    uclamp_idle_reset(rq, clamp_id, uc_se->value);

    /*
     * Local max aggregation: rq buckets always track the max
     * "requested" clamp value of its RUNNABLE tasks.
     */
    if (bucket->tasks == 1 || uc_se->value > bucket->value) {
        bucket->value = uc_se->value;
    }

    if (uc_se->value > READ_ONCE(uc_rq->value)) {
        WRITE_ONCE(uc_rq->value, uc_se->value);
    }
}

/*
 * When a task is dequeued from a rq, the clamp bucket refcounted by the task
 * is released. If this is the last task reference counting the rq's max
 * active clamp value, then the rq's clamp value is updated.
 *
 * Both refcounted tasks and rq's cached clamp values are expected to be
 * always valid. If it's detected they are not, as defensive programming,
 * enforce the expected state and warn.
 */
static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
                                    enum uclamp_id clamp_id)
{
    struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id];
    struct uclamp_se *uc_se = &p->uclamp[clamp_id];
    struct uclamp_bucket *bucket;
    unsigned int bkt_clamp;
    unsigned int rq_clamp;

    lockdep_assert_held(&rq->lock);

    /*
     * If sched_uclamp_used was enabled after task @p was enqueued,
     * we could end up with unbalanced call to uclamp_rq_dec_id().
     *
     * In this case the uc_se->active flag should be false since no uclamp
     * accounting was performed at enqueue time and we can just return
     * here.
     *
     * Need to be careful of the following enqeueue/dequeue ordering
     * problem too
     *
     *    enqueue(taskA)
     *    // sched_uclamp_used gets enabled
     *    enqueue(taskB)
     *    dequeue(taskA)
     *    // Must not decrement bukcet->tasks here
     *    dequeue(taskB)
     *
     * where we could end up with stale data in uc_se and
     * bucket[uc_se->bucket_id].
     *
     * The following check here eliminates the possibility of such race.
     */
    if (unlikely(!uc_se->active)) {
        return;
    }

    bucket = &uc_rq->bucket[uc_se->bucket_id];

    SCHED_WARN_ON(!bucket->tasks);
    if (likely(bucket->tasks)) {
        bucket->tasks--;
    }

    uc_se->active = false;

    /*
     * Keep "local max aggregation" simple and accept to (possibly)
     * overboost some RUNNABLE tasks in the same bucket.
     * The rq clamp bucket value is reset to its base value whenever
     * there are no more RUNNABLE tasks refcounting it.
     */
    if (likely(bucket->tasks)) {
        return;
    }

    rq_clamp = READ_ONCE(uc_rq->value);
    /*
     * Defensive programming: this should never happen. If it happens,
     * e.g. due to future modification, warn and fixup the expected value.
     */
    SCHED_WARN_ON(bucket->value > rq_clamp);
    if (bucket->value >= rq_clamp) {
        bkt_clamp = uclamp_rq_max_value(rq, clamp_id, uc_se->value);
        WRITE_ONCE(uc_rq->value, bkt_clamp);
    }
}

static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
{
    enum uclamp_id clamp_id;

    /*
     * Avoid any overhead until uclamp is actually used by the userspace.
     *
     * The condition is constructed such that a NOP is generated when
     * sched_uclamp_used is disabled.
     */
    if (!static_branch_unlikely(&sched_uclamp_used)) {
        return;
    }

    if (unlikely(!p->sched_class->uclamp_enabled)) {
        return;
    }

    cycle_each_clamp_id(clamp_id) uclamp_rq_inc_id(rq, p, clamp_id);

    /* Reset clamp idle holding when there is one RUNNABLE task */
    if (rq->uclamp_flags & UCLAMP_FLAG_IDLE) {
        rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE;
    }
}

static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
{
    enum uclamp_id clamp_id;

    /*
     * Avoid any overhead until uclamp is actually used by the userspace.
     *
     * The condition is constructed such that a NOP is generated when
     * sched_uclamp_used is disabled.
     */
    if (!static_branch_unlikely(&sched_uclamp_used)) {
        return;
    }

    if (unlikely(!p->sched_class->uclamp_enabled)) {
        return;
    }

    cycle_each_clamp_id(clamp_id) uclamp_rq_dec_id(rq, p, clamp_id);
}

static inline void uclamp_rq_reinc_id(struct rq *rq, struct task_struct *p,
                                      enum uclamp_id clamp_id)
{
    if (!p->uclamp[clamp_id].active) {
        return;
    }

    uclamp_rq_dec_id(rq, p, clamp_id);
    uclamp_rq_inc_id(rq, p, clamp_id);

    /*
     * Make sure to clear the idle flag if we've transiently reached 0
     * active tasks on rq.
     */
    if (clamp_id == UCLAMP_MAX && (rq->uclamp_flags & UCLAMP_FLAG_IDLE)) {
        rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE;
    }
}

static inline void uclamp_update_active(struct task_struct *p)
{
    enum uclamp_id clamp_id;
    struct rq_flags rf;
    struct rq *rq;

    /*
     * Lock the task and the rq where the task is (or was) queued.
     *
     * We might lock the (previous) rq of a !RUNNABLE task, but that's the
     * price to pay to safely serialize util_{min,max} updates with
     * enqueues, dequeues and migration operations.
     * This is the same locking schema used by __set_cpus_allowed_ptr().
     */
    rq = task_rq_lock(p, &rf);

    /*
     * Setting the clamp bucket is serialized by task_rq_lock().
     * If the task is not yet RUNNABLE and its task_struct is not
     * affecting a valid clamp bucket, the next time it's enqueued,
     * it will already see the updated clamp bucket value.
     */
    cycle_each_clamp_id(clamp_id) uclamp_rq_reinc_id(rq, p, clamp_id);

    task_rq_unlock(rq, p, &rf);
}

#ifdef CONFIG_UCLAMP_TASK_GROUP
static inline void uclamp_update_active_tasks(struct cgroup_subsys_state *css)
{
    struct css_task_iter it;
    struct task_struct *p;

    css_task_iter_start(css, 0, &it);
    while ((p = css_task_iter_next(&it))) {
        uclamp_update_active(p);
    }
    css_task_iter_end(&it);
}

static void cpu_util_update_eff(struct cgroup_subsys_state *css);
static void uclamp_update_root_tg(void)
{
    struct task_group *tg = &root_task_group;

    uclamp_se_set(&tg->uclamp_req[UCLAMP_MIN], sysctl_sched_uclamp_util_min,
                  false);
    uclamp_se_set(&tg->uclamp_req[UCLAMP_MAX], sysctl_sched_uclamp_util_max,
                  false);

    rcu_read_lock();
    cpu_util_update_eff(&root_task_group.css);
    rcu_read_unlock();
}
#else
static void uclamp_update_root_tg(void)
{
}
#endif

int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
                                void *buffer, size_t *lenp, loff_t *ppos)
{
    bool update_root_tg = false;
    int old_min, old_max, old_min_rt;
    int result;

    mutex_lock(&uclamp_mutex);
    old_min = sysctl_sched_uclamp_util_min;
    old_max = sysctl_sched_uclamp_util_max;
    old_min_rt = sysctl_sched_uclamp_util_min_rt_default;

    result = proc_dointvec(table, write, buffer, lenp, ppos);
    if (result) {
        goto undo;
    }
    if (!write) {
        goto done;
    }

    if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max ||
        sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE ||
        sysctl_sched_uclamp_util_min_rt_default > SCHED_CAPACITY_SCALE) {
        result = -EINVAL;
        goto undo;
    }

    if (old_min != sysctl_sched_uclamp_util_min) {
        uclamp_se_set(&uclamp_default[UCLAMP_MIN], sysctl_sched_uclamp_util_min,
                      false);
        update_root_tg = true;
    }
    if (old_max != sysctl_sched_uclamp_util_max) {
        uclamp_se_set(&uclamp_default[UCLAMP_MAX], sysctl_sched_uclamp_util_max,
                      false);
        update_root_tg = true;
    }

    if (update_root_tg) {
        static_branch_enable(&sched_uclamp_used);
        uclamp_update_root_tg();
    }

    if (old_min_rt != sysctl_sched_uclamp_util_min_rt_default) {
        static_branch_enable(&sched_uclamp_used);
        uclamp_sync_util_min_rt_default();
    }

    /*
     * We update all RUNNABLE tasks only when task groups are in use.
     * Otherwise, keep it simple and do just a lazy update at each next
     * task enqueue time.
     */

    goto done;

undo:
    sysctl_sched_uclamp_util_min = old_min;
    sysctl_sched_uclamp_util_max = old_max;
    sysctl_sched_uclamp_util_min_rt_default = old_min_rt;
done:
    mutex_unlock(&uclamp_mutex);

    return result;
}

static int uclamp_validate(struct task_struct *p, const struct sched_attr *attr)
{
    unsigned int lower_bound = p->uclamp_req[UCLAMP_MIN].value;
    unsigned int upper_bound = p->uclamp_req[UCLAMP_MAX].value;

    if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
        lower_bound = attr->sched_util_min;
    }
    if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
        upper_bound = attr->sched_util_max;
    }

    if (lower_bound > upper_bound) {
        return -EINVAL;
    }
    if (upper_bound > SCHED_CAPACITY_SCALE) {
        return -EINVAL;
    }

    /*
     * We have valid uclamp attributes; make sure uclamp is enabled.
     *
     * We need to do that here, because enabling static branches is a
     * blocking operation which obviously cannot be done while holding
     * scheduler locks.
     */
    static_branch_enable(&sched_uclamp_used);

    return 0;
}

static void __setscheduler_uclamp(struct task_struct *p,
                                  const struct sched_attr *attr)
{
    enum uclamp_id clamp_id;

    /*
     * On scheduling class change, reset to default clamps for tasks
     * without a task-specific value.
     */
    cycle_each_clamp_id(clamp_id) {
        struct uclamp_se *uc_se = &p->uclamp_req[clamp_id];

        /* Keep using defined clamps across class changes */
        if (uc_se->user_defined) {
            continue;
        }

        /*
         * RT by default have a 100% boost value that could be modified
         * at runtime.
         */
        if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN)) {
            __uclamp_update_util_min_rt_default(p);
        } else {
            uclamp_se_set(uc_se, uclamp_none(clamp_id), false);
        }
    }

    if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP))) {
        return;
    }

    if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
        uclamp_se_set(&p->uclamp_req[UCLAMP_MIN], attr->sched_util_min, true);
    }

    if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
        uclamp_se_set(&p->uclamp_req[UCLAMP_MAX], attr->sched_util_max, true);
    }
}

static void uclamp_fork(struct task_struct *p)
{
    enum uclamp_id clamp_id;

    /*
     * We don't need to hold task_rq_lock() when updating p->uclamp_* here
     * as the task is still at its early fork stages.
     */
    cycle_each_clamp_id(clamp_id) p->uclamp[clamp_id].active = false;

    if (likely(!p->sched_reset_on_fork)) {
        return;
    }

    cycle_each_clamp_id(clamp_id) {
        uclamp_se_set(&p->uclamp_req[clamp_id], uclamp_none(clamp_id), false);
    }
}

static void uclamp_post_fork(struct task_struct *p)
{
    uclamp_update_util_min_rt_default(p);
}

static void __init init_uclamp_rq(struct rq *rq)
{
    enum uclamp_id clamp_id;
    struct uclamp_rq *uc_rq = rq->uclamp;

    cycle_each_clamp_id(clamp_id) {
        uc_rq[clamp_id] = (struct uclamp_rq) {.value = uclamp_none(clamp_id)};
    }

    rq->uclamp_flags = UCLAMP_FLAG_IDLE;
}

static void __init init_uclamp(void)
{
    struct uclamp_se uc_max = {};
    enum uclamp_id clamp_id;
    int cpu;

    for_each_possible_cpu(cpu) init_uclamp_rq(cpu_rq(cpu));

    cycle_each_clamp_id(clamp_id)
    {
        uclamp_se_set(&init_task.uclamp_req[clamp_id], uclamp_none(clamp_id),
                      false);
    }

    /* System defaults allow max clamp values for both indexes */
    uclamp_se_set(&uc_max, uclamp_none(UCLAMP_MAX), false);
    cycle_each_clamp_id(clamp_id)
    {
        uclamp_default[clamp_id] = uc_max;
#ifdef CONFIG_UCLAMP_TASK_GROUP
        root_task_group.uclamp_req[clamp_id] = uc_max;
        root_task_group.uclamp[clamp_id] = uc_max;
#endif
    }
}

#else  /* CONFIG_UCLAMP_TASK */
static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
{
}
static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
{
}
static inline int uclamp_validate(struct task_struct *p,
                                  const struct sched_attr *attr)
{
    return -EOPNOTSUPP;
}
static void __setscheduler_uclamp(struct task_struct *p,
                                  const struct sched_attr *attr)
{
}
static inline void uclamp_fork(struct task_struct *p)
{
}
static inline void uclamp_post_fork(struct task_struct *p)
{
}
static inline void init_uclamp(void)
{
}
#endif /* CONFIG_UCLAMP_TASK */

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);
        psi_enqueue(p, flags & ENQUEUE_WAKEUP);
    }

    uclamp_rq_inc(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);
        psi_dequeue(p, flags & DEQUEUE_SLEEP);
    }

    uclamp_rq_dec(rq, p);
    p->sched_class->dequeue_task(rq, p, flags);
}

void activate_task(struct rq *rq, struct task_struct *p, int flags)
{
    enqueue_task(rq, p, flags);

    p->on_rq = TASK_ON_RQ_QUEUED;
}

void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
{
    p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;

    dequeue_task(rq, p, flags);
}

static inline int __normal_prio(int policy, int rt_prio, int nice)
{
    int prio;

    if (dl_policy(policy)) {
        prio = MAX_DL_PRIO - 1;
    } else if (rt_policy(policy)) {
        prio = MAX_RT_PRIO - 1 - rt_prio;
    } else {
        prio = NICE_TO_PRIO(nice);
    }

    return 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)
{
    return __normal_prio(p->policy, p->rt_priority,
                         PRIO_TO_NICE(p->static_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)
{
    if (p->sched_class == rq->curr->sched_class) {
        rq->curr->sched_class->check_preempt_curr(rq, p, flags);
    } else if (p->sched_class > rq->curr->sched_class) {
        resched_curr(rq);
    }

    /*
     * 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

/*
 * Per-CPU kthreads are allowed to run on !active && 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_ptr)) {
        return false;
    }

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

    if (!cpu_active(cpu)) {
        return false;
    }

    return cpumask_test_cpu(cpu, task_cpu_possible_mask(p));
}

/*
 * 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);

    deactivate_task(rq, p, DEQUEUE_NOCLOCK);
#ifdef CONFIG_SCHED_WALT
    double_lock_balance(rq, cpu_rq(new_cpu));
    if (!(rq->clock_update_flags & RQCF_UPDATED)) {
        update_rq_clock(rq);
    }
#endif
    set_task_cpu(p, new_cpu);
#ifdef CONFIG_SCHED_WALT
    double_rq_unlock(cpu_rq(new_cpu), rq);
#else
    rq_unlock(rq, rf);
#endif

    rq = cpu_rq(new_cpu);

    rq_lock(rq, rf);
    BUG_ON(task_cpu(p) != new_cpu);
    activate_task(rq, p, 0);
    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_ptr
     * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
     */
    flush_smp_call_function_from_idle();

    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_mask, 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_next_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;
#ifdef CONFIG_CPU_ISOLATION_OPT
    cpumask_t allowed_mask;
#endif

    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_mask, new_mask)) {
        goto out;
    }

#ifdef CONFIG_CPU_ISOLATION_OPT
    cpumask_andnot(&allowed_mask, new_mask, cpu_isolated_mask);
    cpumask_and(&allowed_mask, &allowed_mask, cpu_valid_mask);

    dest_cpu = cpumask_any(&allowed_mask);
    if (dest_cpu >= nr_cpu_ids) {
        cpumask_and(&allowed_mask, cpu_valid_mask, new_mask);
        dest_cpu = cpumask_any(&allowed_mask);
        if (!cpumask_intersects(new_mask, cpu_valid_mask)) {
            ret = -EINVAL;
            goto out;
        }
    }
#else
    /*
     * Picking a ~random cpu helps in cases where we are changing affinity
     * for groups of tasks (ie. cpuset), so that load balancing is not
     * immediately required to distribute the tasks within their new mask.
     */
    dest_cpu = cpumask_any_and_distribute(cpu_valid_mask, new_mask);
    if (dest_cpu >= nr_cpu_ids) {
        ret = -EINVAL;
        goto out;
    }
#endif

    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 */
#ifdef CONFIG_CPU_ISOLATION_OPT
    if (cpumask_test_cpu(task_cpu(p), &allowed_mask)) {
        goto out;
    }
#else
    if (cpumask_test_cpu(task_cpu(p), new_mask)) {
        goto out;
    }
#endif

    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);
        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);
        fixup_busy_time(p, new_cpu);
    }

    __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);

        deactivate_task(src_rq, p, 0);
        set_task_cpu(p, cpu);
        activate_task(dst_rq, p, 0);
        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_ptr)) {
        goto unlock;
    }

    if (!cpumask_test_cpu(arg->src_cpu, arg->dst_task->cpus_ptr)) {
        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_ptr)) {
        goto out;
    }

    if (!cpumask_test_cpu(arg.src_cpu, arg.dst_task->cpus_ptr)) {
        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_ptr 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.
 */
#ifdef CONFIG_CPU_ISOLATION_OPT
static int select_fallback_rq(int cpu, struct task_struct *p, bool allow_iso)
#else
static int select_fallback_rq(int cpu, struct task_struct *p)
#endif
{
    int nid = cpu_to_node(cpu);
    const struct cpumask *nodemask = NULL;
    enum { cpuset, possible, fail, bug } state = cpuset;
    int dest_cpu;
#ifdef CONFIG_CPU_ISOLATION_OPT
    int isolated_candidate = -1;
#endif

    /*
     * 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 (cpu_isolated(dest_cpu)) {
                continue;
            }
            if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) {
                return dest_cpu;
            }
        }
    }

    for (;;) {
        /* Any allowed, online CPU? */
        for_each_cpu(dest_cpu, p->cpus_ptr)
        {
            if (!is_cpu_allowed(p, dest_cpu)) {
                continue;
            }
#ifdef CONFIG_CPU_ISOLATION_OPT
            if (cpu_isolated(dest_cpu)) {
                if (allow_iso) {
                    isolated_candidate = dest_cpu;
                }
                continue;
            }
            goto out;
        }

        if (isolated_candidate != -1) {
            dest_cpu = isolated_candidate;
#endif
            goto out;
        }

        /* No more Mr. Nice Guy. */
        switch (state) {
            case cpuset:
                if (IS_ENABLED(CONFIG_CPUSETS)) {
                    cpuset_cpus_allowed_fallback(p);
                    state = possible;
                    break;
                }
                fallthrough;
            case possible:
                do_set_cpus_allowed(p, task_cpu_possible_mask(p));
                state = fail;
                break;
            case fail:
#ifdef CONFIG_CPU_ISOLATION_OPT
                allow_iso = true;
                state = bug;
                break;
#else
#endif

            case bug:
                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_ptr is stable.
 */
static inline int select_task_rq(struct task_struct *p, int cpu, int sd_flags,
                                 int wake_flags)
{
#ifdef CONFIG_CPU_ISOLATION_OPT
    bool allow_isolated = (p->flags & PF_KTHREAD);
#endif

    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_ptr);
    }

    /*
     * 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_ptr
     * 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 ]
     */
#ifdef CONFIG_CPU_ISOLATION_OPT
    if (unlikely(!is_cpu_allowed(p, cpu)) ||
        (cpu_isolated(cpu) && !allow_isolated)) {
        cpu = select_fallback_rq(task_cpu(p), p, allow_isolated);
    }
#else
    if (unlikely(!is_cpu_allowed(p, cpu))) {
        cpu = select_fallback_rq(task_cpu(p), p);
    }
#endif

    return cpu;
}

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);
    }
}

/*
 * 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;

    if (wake_flags & WF_SYNC) {
        en_flags |= ENQUEUE_WAKEUP_SYNC;
    }

    lockdep_assert_held(&rq->lock);

    if (p->sched_contributes_to_load) {
        rq->nr_uninterruptible--;
    }

#ifdef CONFIG_SMP
    if (wake_flags & WF_MIGRATED) {
        en_flags |= ENQUEUE_MIGRATED;
    } else
#endif
        if (p->in_iowait) {
        delayacct_blkio_end(p);
        atomic_dec(&task_rq(p)->nr_iowait);
    }

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

/*
 * Consider @p being inside a wait loop:
 *
 *   for (;;) {
 *      set_current_state(TASK_UNINTERRUPTIBLE);
 *
 *      if (CONDITION)
 *         break;
 *
 *      schedule();
 *   }
 *   __set_current_state(TASK_RUNNING);
 *
 * between set_current_state() and schedule(). In this case @p is still
 * runnable, so all that needs doing is change p->state back to TASK_RUNNING in
 * an atomic manner.
 *
 * By taking task_rq(p)->lock we serialize against schedule(), if @p->on_rq
 * then schedule() must still happen and p->state can be changed to
 * TASK_RUNNING. Otherwise we lost the race, schedule() has happened, and we
 * need to do a full wakeup with enqueue.
 *
 * Returns: %true when the wakeup is done,
 *          %false otherwise.
 */
static int ttwu_runnable(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 *arg)
{
    struct llist_node *llist = arg;
    struct rq *rq = this_rq();
    struct task_struct *p, *t;
    struct rq_flags rf;

    if (!llist) {
        return;
    }

    /*
     * rq::ttwu_pending racy indication of out-standing wakeups.
     * Races such that false-negatives are possible, since they
     * are shorter lived that false-positives would be.
     */
    WRITE_ONCE(rq->ttwu_pending, 0);

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

    llist_for_each_entry_safe(p, t, llist, wake_entry.llist)
    {
        if (WARN_ON_ONCE(p->on_cpu)) {
            smp_cond_load_acquire(&p->on_cpu, !VAL);
        }

        if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq))) {
            set_task_cpu(p, cpu_of(rq));
        }

        ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);
    }

    rq_unlock_irqrestore(rq, &rf);
}

void send_call_function_single_ipi(int cpu)
{
    struct rq *rq = cpu_rq(cpu);

    if (!set_nr_if_polling(rq->idle)) {
        arch_send_call_function_single_ipi(cpu);
    } else {
        trace_sched_wake_idle_without_ipi(cpu);
    }
}

/*
 * Queue a task on the target CPUs wake_list and wake the CPU via IPI if
 * necessary. The wakee CPU on receipt of the IPI will queue the task
 * via sched_ttwu_wakeup() for activation so the wakee incurs the cost
 * of the wakeup instead of the waker.
 */
static void __ttwu_queue_wakelist(struct task_struct *p, int cpu,
                                  int wake_flags)
{
    struct rq *rq = cpu_rq(cpu);

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

    WRITE_ONCE(rq->ttwu_pending, 1);
    __smp_call_single_queue(cpu, &p->wake_entry.llist);
}

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)
{
    if (this_cpu == that_cpu) {
        return true;
    }

    return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
}

static inline bool ttwu_queue_cond(int cpu, int wake_flags)
{
    /*
     * If the CPU does not share cache, then queue the task on the
     * remote rqs wakelist to avoid accessing remote data.
     */
    if (!cpus_share_cache(smp_processor_id(), cpu)) {
        return true;
    }

    /*
     * If the task is descheduling and the only running task on the
     * CPU then use the wakelist to offload the task activation to
     * the soon-to-be-idle CPU as the current CPU is likely busy.
     * nr_running is checked to avoid unnecessary task stacking.
     */
    if ((wake_flags & WF_ON_CPU) && cpu_rq(cpu)->nr_running <= 1) {
        return true;
    }

    return false;
}

static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
{
    if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu, wake_flags)) {
        if (WARN_ON_ONCE(cpu == smp_processor_id())) {
            return false;
        }

        sched_clock_cpu(cpu); /* Sync clocks across CPUs */
        __ttwu_queue_wakelist(p, cpu, wake_flags);
        return true;
    }

    return false;
}

#else /* !CONFIG_SMP */

static inline bool ttwu_queue_wakelist(struct task_struct *p, int cpu,
                                       int wake_flags)
{
    return false;
}

#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 (ttwu_queue_wakelist(p, cpu, wake_flags)) {
        return;
    }

    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)   -- finish_task()
 *   2) smp_cond_load_acquire(!X->on_cpu) -- try_to_wake_up()
 *
 * 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().
 */

#ifdef CONFIG_SMP
#ifdef CONFIG_SCHED_WALT
/* utility function to update walt signals at wakeup */
static inline void walt_try_to_wake_up(struct task_struct *p)
{
    struct rq *rq = cpu_rq(task_cpu(p));
    struct rq_flags rf;
    u64 wallclock;

    rq_lock_irqsave(rq, &rf);
    wallclock = sched_ktime_clock();
    update_task_ravg(rq->curr, rq, TASK_UPDATE, wallclock, 0);
    update_task_ravg(p, rq, TASK_WAKE, wallclock, 0);
    rq_unlock_irqrestore(rq, &rf);
}
#else
#define walt_try_to_wake_up(a)                                                 \
    {                                                                          \
    }
#endif
#endif

/**
 * 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_*)
 *
 * Conceptually does
 *
 *   If (@state & @p->state) @p->state = TASK_RUNNING.
 *
 * If the task was not queued/runnable, also place it back on a runqueue.
 *
 * This function is atomic against schedule() which would dequeue the task.
 *
 * It issues a full memory barrier before accessing @p->state, see the comment
 * with set_current_state().
 *
 * Uses p->pi_lock to serialize against concurrent wake-ups.
 *
 * Relies on p->pi_lock stabilizing:
 *  - p->sched_class
 *  - p->cpus_ptr
 *  - p->sched_task_group
 * in order to do migration, see its use of select_task_rq()/set_task_cpu().
 *
 * Tries really hard to only take one task_rq(p)->lock for performance.
 * Takes rq->lock in:
 *  - ttwu_runnable()    -- old rq, unavoidable, see comment there;
 *  - ttwu_queue()       -- new rq, for enqueue of the task;
 *  - psi_ttwu_dequeue() -- much sadness :-( accounting will kill us.
 *
 * As a consequence we race really badly with just about everything. See the
 * many memory barriers and their comments for details.
 *
 * 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;

    preempt_disable();
    if (p == current) {
        /*
         * We're waking current, this means 'p->on_rq' and 'task_cpu(p)
         * == smp_processor_id()'. Together this means we can special
         * case the whole 'p->on_rq && ttwu_runnable()' case below
         * without taking any locks.
         *
         * In particular:
         *  - we rely on Program-Order guarantees for all the ordering,
         *  - we're serialized against set_special_state() by virtue of
         *    it disabling IRQs (this allows not taking ->pi_lock).
         */
        if (!(p->state & state)) {
            goto out;
        }

        success = 1;
        trace_sched_waking(p);
        p->state = TASK_RUNNING;
        trace_sched_wakeup(p);
        goto out;
    }

    /*
     * 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 smp_store_mb()
     * in set_current_state() that the waiting thread does.
     */
    raw_spin_lock_irqsave(&p->pi_lock, flags);
    smp_mb__after_spinlock();
    if (!(p->state & state)) {
        goto unlock;
    }

#ifdef CONFIG_FREEZER
    /*
     * If we're going to wake up a thread which may be frozen, then
     * we can only do so if we have an active CPU which is capable of
     * running it. This may not be the case when resuming from suspend,
     * as the secondary CPUs may not yet be back online. See __thaw_task()
     * for the actual wakeup.
     */
    if (unlikely(frozen_or_skipped(p)) &&
        !cpumask_intersects(cpu_active_mask, task_cpu_possible_mask(p))) {
        goto unlock;
    }
#endif

    trace_sched_waking(p);

    /* We're going to change ->state: */
    success = 1;

    /*
     * 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().
     *
     * A similar smb_rmb() lives in try_invoke_on_locked_down_task().
     */
    smp_rmb();
    if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags)) {
        goto unlock;
    }

#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().
     *
     * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
     * schedule()'s deactivate_task() has 'happened' and p will no longer
     * care about it's own p->state. See the comment in __schedule().
     */
    smp_acquire__after_ctrl_dep();

    walt_try_to_wake_up(p);

    /*
     * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
     * == 0), which means we need to do an enqueue, change p->state to
     * TASK_WAKING such that we can unlock p->pi_lock before doing the
     * enqueue, such as ttwu_queue_wakelist().
     */
    p->state = TASK_WAKING;

    /*
     * If the owning (remote) CPU is still in the middle of schedule() with
     * this task as prev, considering queueing p on the remote CPUs wake_list
     * which potentially sends an IPI instead of spinning on p->on_cpu to
     * let the waker make forward progress. This is safe because IRQs are
     * disabled and the IPI will deliver after on_cpu is cleared.
     *
     * Ensure we load task_cpu(p) after p->on_cpu:
     *
     * set_task_cpu(p, cpu);
     *   STORE p->cpu = @cpu
     * __schedule() (switch to task 'p')
     *   LOCK rq->lock
     *   smp_mb__after_spin_lock()        smp_cond_load_acquire(&p->on_cpu)
     *   STORE p->on_cpu = 1        LOAD p->cpu
     *
     * to ensure we observe the correct CPU on which the task is currently
     * scheduling.
     */
    if (smp_load_acquire(&p->on_cpu) &&
        ttwu_queue_wakelist(p, task_cpu(p), wake_flags | WF_ON_CPU)) {
        goto unlock;
    }

    /*
     * 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);

    cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
    if (task_cpu(p) != cpu) {
        if (p->in_iowait) {
            delayacct_blkio_end(p);
            atomic_dec(&task_rq(p)->nr_iowait);
        }

        wake_flags |= WF_MIGRATED;
        psi_ttwu_dequeue(p);
        set_task_cpu(p, cpu);
    }
#else
    cpu = task_cpu(p);
#endif /* CONFIG_SMP */

    ttwu_queue(p, cpu, wake_flags);
unlock:
    raw_spin_unlock_irqrestore(&p->pi_lock, flags);
out:
    if (success) {
        ttwu_stat(p, task_cpu(p), wake_flags);
    }
    preempt_enable();

    return success;
}

/**
 * try_invoke_on_locked_down_task - Invoke a function on task in fixed state
 * @p: Process for which the function is to be invoked, can be @current.
 * @func: Function to invoke.
 * @arg: Argument to function.
 *
 * If the specified task can be quickly locked into a definite state
 * (either sleeping or on a given runqueue), arrange to keep it in that
 * state while invoking @func(@arg).  This function can use ->on_rq and
 * task_curr() to work out what the state is, if required.  Given that
 * @func can be invoked with a runqueue lock held, it had better be quite
 * lightweight.
 *
 * Returns:
 *    @false if the task slipped out from under the locks.
 *    @true if the task was locked onto a runqueue or is sleeping.
 *        However, @func can override this by returning @false.
 */
bool try_invoke_on_locked_down_task(struct task_struct *p,
                                    bool (*func)(struct task_struct *t,
                                                 void *arg),
                                    void *arg)
{
    struct rq_flags rf;
    bool ret = false;
    struct rq *rq;

    raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
    if (p->on_rq) {
        rq = __task_rq_lock(p, &rf);
        if (task_rq(p) == rq) {
            ret = func(p, arg);
        }
        rq_unlock(rq, &rf);
    } else {
        switch (p->state) {
            case TASK_RUNNING:
            case TASK_WAKING:
                break;
            default:
                smp_rmb(); // See smp_rmb() comment in try_to_wake_up().
                if (!p->on_rq) {
                    ret = func(p, arg);
                }
        }
    }
    raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
    return ret;
}

/**
 * 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

#ifdef CONFIG_COMPACTION
    p->capture_control = NULL;
#endif
    init_numa_balancing(clone_flags, p);
#ifdef CONFIG_SMP
    p->wake_entry.u_flags = CSD_TYPE_TTWU;
#endif
#ifdef CONFIG_SCHED_RTG
    p->rtg_depth = 0;
#endif
}

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 *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 *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)
{
    init_new_task_load(p);
    __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;

#ifdef CONFIG_SCHED_LATENCY_NICE
    /* Propagate the parent's latency requirements to the child as well */
    p->latency_prio = current->latency_prio;
#endif

    uclamp_fork(p);

    /*
     * 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;
#ifdef CONFIG_SCHED_RTG
            if (current->rtg_depth != 0) {
                p->static_prio = current->static_prio;
            } else {
                p->static_prio = NICE_TO_PRIO(0);
            }
#else
            p->static_prio = NICE_TO_PRIO(0);
#endif
            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 = p->static_prio;
        set_load_weight(p);

#ifdef CONFIG_SCHED_LATENCY_NICE
        p->latency_prio = NICE_TO_LATENCY(0);
        set_latency_weight(p);
#endif

        /*
         * 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);

#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;
}

void sched_post_fork(struct task_struct *p, struct kernel_clone_args *kargs)
{
    unsigned long flags;
#ifdef CONFIG_CGROUP_SCHED
    struct task_group *tg;
#endif

    raw_spin_lock_irqsave(&p->pi_lock, flags);
#ifdef CONFIG_CGROUP_SCHED
    tg = container_of(kargs->cset->subsys[cpu_cgrp_id], struct task_group, css);
    p->sched_task_group = autogroup_task_group(p, tg);
#endif
    rseq_migrate(p);
    /*
     * 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);

    uclamp_post_fork(p);
}

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);
    add_new_task_to_grp(p);

    p->state = TASK_RUNNING;
#ifdef CONFIG_SMP
    /*
     * Fork balancing, do it here and not earlier because:
     *  - cpus_ptr 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);
    rseq_migrate(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);

    mark_task_starting(p);

    activate_task(rq, p, ENQUEUE_NOCLOCK);
    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.
     *
     * See the ttwu() WF_ON_CPU case and its ordering comment.
     */
    WRITE_ONCE(next->on_cpu, 1);
#endif
}

static inline void finish_task(struct task_struct *prev)
{
#ifdef CONFIG_SMP
    /*
     * This must be the very last reference to @prev from this CPU. After
     * p->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, _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_rcu_user(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)
{
    prepare_task_switch(rq, prev, next);

    /*
     * 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);

    /*
     * kernel -> kernel   lazy + transfer active
     *   user -> kernel   lazy + mmgrab() active
     *
     * kernel ->   user   switch + mmdrop() active
     *   user ->   user   switch
     */
    if (!next->mm) { // to kernel
        enter_lazy_tlb(prev->active_mm, next);

        next->active_mm = prev->active_mm;
        if (prev->mm) { // from user
            mmgrab(prev->active_mm);
        } else {
            prev->active_mm = NULL;
        }
    } else { // to user
        membarrier_switch_mm(rq, prev->active_mm, next->mm);
        /*
         * sys_membarrier() requires an smp_mb() between setting
         * rq->curr / membarrier_switch_mm() and returning to userspace.
         *
         * The below provides this either through switch_mm(), or in
         * case 'prev->active_mm == next->mm' through
         * finish_task_switch()'s mmdrop().
         */
        switch_mm_irqs_off(prev->active_mm, next->mm, next);

        if (!prev->mm) { // from kernel
            /* will mmdrop() in finish_task_switch(). */
            rq->prev_mm = prev->active_mm;
            prev->active_mm = NULL;
        }
    }

    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-preemptible 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;
}

/*
 * Consumers of these two interfaces, like for example the cpuidle menu
 * governor, are using nonsensical data. Preferring shallow idle state selection
 * 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)
{
    return atomic_read(&cpu_rq(cpu)->nr_iowait);
}

/*
 * 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 += nr_iowait_cpu(i);

    return sum;
}

#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) && likely(!cpu_isolated(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;
    u64 wallclock;
    unsigned long thermal_pressure;

    arch_scale_freq_tick();
    sched_clock_tick();

    rq_lock(rq, &rf);

    set_window_start(rq);
    wallclock = sched_ktime_clock();
    update_task_ravg(rq->curr, rq, TASK_UPDATE, wallclock, 0);
    update_rq_clock(rq);
    thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
    update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure);
    curr->sched_class->task_tick(rq, curr, 0);
    calc_global_load_tick(rq);
    psi_task_tick(rq);

    rq_unlock(rq, &rf);

#ifdef CONFIG_SCHED_RTG
    sched_update_rtg_tick(curr);
#endif
    perf_event_task_tick();

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

#ifdef CONFIG_SCHED_EAS
    if (curr->sched_class->check_for_migration) {
        curr->sched_class->check_for_migration(rq, curr);
    }
#endif
#endif
}

#ifdef CONFIG_NO_HZ_FULL

struct tick_work {
    int cpu;
    atomic_t state;
    struct delayed_work work;
};
/* Values for ->state, see diagram below. */
#define TICK_SCHED_REMOTE_OFFLINE 0
#define TICK_SCHED_REMOTE_OFFLINING 1
#define TICK_SCHED_REMOTE_RUNNING 2

/*
 * State diagram for ->state:
 *
 *
 *          TICK_SCHED_REMOTE_OFFLINE
 *                    |   ^
 *                    |   |
 *                    |   | sched_tick_remote()
 *                    |   |
 *                    |   |
 *                    +--TICK_SCHED_REMOTE_OFFLINING
 *                    |   ^
 *                    |   |
 * sched_tick_start() |   | sched_tick_stop()
 *                    |   |
 *                    V   |
 *          TICK_SCHED_REMOTE_RUNNING
 *
 *
 * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote()
 * and sched_tick_start() are happy to leave the state in RUNNING.
 */

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;
    int os;

    /*
     * 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 (!tick_nohz_tick_stopped_cpu(cpu)) {
        goto out_requeue;
    }

    rq_lock_irq(rq, &rf);
    curr = rq->curr;
    if (cpu_is_offline(cpu)) {
        goto out_unlock;
    }

    update_rq_clock(rq);

    if (!is_idle_task(curr)) {
        /*
         * Make sure the next tick runs within a reasonable
         * amount of time.
         */
        delta = rq_clock_task(rq) - curr->se.exec_start;
        WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 0x3);
    }
    curr->sched_class->task_tick(rq, curr, 0);

    calc_load_nohz_remote(rq);
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.  But
     * first update state to reflect hotplug activity if required.
     */
    os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING);
    WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE);
    if (os == TICK_SCHED_REMOTE_RUNNING) {
        queue_delayed_work(system_unbound_wq, dwork, HZ);
    }
}

static void sched_tick_start(int cpu)
{
    int os;
    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);
    os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING);
    WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING);
    if (os == TICK_SCHED_REMOTE_OFFLINE) {
        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;
    int os;

    if (housekeeping_cpu(cpu, HK_FLAG_TICK)) {
        return;
    }

    WARN_ON_ONCE(!tick_work_cpu);

    twork = per_cpu_ptr(tick_work_cpu, cpu);
    /* There cannot be competing actions, but don't rely on stop-machine. */
    os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING);
    WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING);
    /* Don't cancel, as this would mess up the state machine. */
}
#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_PREEMPTION) &&                                              \
    (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 - 0xa);
#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(KERN_ERR, preempt_disable_ip);
    }
    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, bool preempt)
{
#ifdef CONFIG_SCHED_STACK_END_CHECK
    if (task_stack_end_corrupted(prev)) {
        panic("corrupted stack end detected inside scheduler\n");
    }

    if (task_scs_end_corrupted(prev)) {
        panic("corrupted shadow stack detected inside scheduler\n");
    }
#endif

#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
    if (!preempt && prev->state && prev->non_block_count) {
        printk(KERN_ERR "BUG: scheduling in a non-blocking section: %s/%d/%i\n",
               prev->comm, prev->pid, prev->non_block_count);
        dump_stack();
        add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
    }
#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);
}

static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
                                  struct rq_flags *rf)
{
#ifdef CONFIG_SMP
    const struct sched_class *class;
    /*
     * We must do the balancing pass before put_prev_task(), such
     * that when we release the rq->lock the task is in the same
     * state as before we took rq->lock.
     *
     * We can terminate the balance pass as soon as we know there is
     * a runnable task of @class priority or higher.
     */
    for_class_range(class, prev->sched_class, &idle_sched_class)
    {
        if (class->balance(rq, prev, rf)) {
            break;
        }
    }
#endif

    put_prev_task(rq, prev);
}

/*
 * 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 <= &fair_sched_class &&
               rq->nr_running == rq->cfs.h_nr_running)) {
        p = pick_next_task_fair(rq, prev, rf);
        if (unlikely(p == RETRY_TASK)) {
            goto restart;
        }

        /* Assumes fair_sched_class->next == idle_sched_class */
        if (!p) {
            put_prev_task(rq, prev);
            p = pick_next_task_idle(rq);
        }

        return p;
    }

restart:
    put_prev_task_balance(rq, prev, rf);

    for_each_class(class)
    {
        p = class->pick_next_task(rq);
        if (p) {
            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_PREEMPTION=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_PREEMPTION 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;
    unsigned long prev_state;
    struct rq_flags rf;
    struct rq *rq;
    int cpu;
    u64 wallclock;

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

    schedule_debug(prev, preempt);

    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():
     *
     * __set_current_state(@state)        signal_wake_up()
     * schedule()                  set_tsk_thread_flag(p, TIF_SIGPENDING)
     *                      wake_up_state(p, state)
     *   LOCK rq->lock                LOCK p->pi_state
     *   smp_mb__after_spinlock()            smp_mb__after_spinlock()
     *     if (signal_pending_state())        if (p->state & @state)
     *
     * Also, 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;

    /*
     * We must load prev->state once (task_struct::state is volatile), such
     * that:
     *
     *  - we form a control dependency vs deactivate_task() below.
     *  - ptrace_{,un}freeze_traced() can change ->state underneath us.
     */
    prev_state = prev->state;
    if (!preempt && prev_state) {
        if (signal_pending_state(prev_state, prev)) {
            prev->state = TASK_RUNNING;
        } else {
            prev->sched_contributes_to_load =
                (prev_state & TASK_UNINTERRUPTIBLE) &&
                !(prev_state & TASK_NOLOAD) && !(prev->flags & PF_FROZEN);

            if (prev->sched_contributes_to_load) {
                rq->nr_uninterruptible++;
            }

            /*
             * __schedule()            ttwu()
             *   prev_state = prev->state;    if (p->on_rq && ...)
             *   if (prev_state)            goto out;
             *     p->on_rq = 0;          smp_acquire__after_ctrl_dep();
             *                  p->state = TASK_WAKING
             *
             * Where __schedule() and ttwu() have matching control dependencies.
             *
             * After this, schedule() must not care about p->state any more.
             */
            deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);

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

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

    wallclock = sched_ktime_clock();
    if (likely(prev != next)) {
#ifdef CONFIG_SCHED_WALT
        if (!prev->on_rq) {
            prev->last_sleep_ts = wallclock;
        }
#endif
        update_task_ravg(prev, rq, PUT_PREV_TASK, wallclock, 0);
        update_task_ravg(next, rq, PICK_NEXT_TASK, wallclock, 0);
        rq->nr_switches++;
        /*
         * RCU users of rcu_dereference(rq->curr) may not see
         * changes to task_struct made by pick_next_task().
         */
        RCU_INIT_POINTER(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;

        psi_sched_switch(prev, next, !task_on_rq_queued(prev));

        trace_sched_switch(preempt, prev, next);

        /* Also unlocks the rq: */
        rq = context_switch(rq, prev, next, &rf);
    } else {
        update_task_ravg(prev, rq, TASK_UPDATE, wallclock, 0);
        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)
{
    unsigned int task_flags;

    if (!tsk->state) {
        return;
    }

    task_flags = tsk->flags;
    /*
     * If a worker went to sleep, notify and ask workqueue whether
     * it wants to wake up a task to maintain concurrency.
     * As this function is called inside the schedule() context,
     * we disable preemption to avoid it calling schedule() again
     * in the possible wakeup of a kworker and because wq_worker_sleeping()
     * requires it.
     */
    if (task_flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
        preempt_disable();
        if (task_flags & PF_WQ_WORKER) {
            wq_worker_sleeping(tsk);
        } else {
            io_wq_worker_sleeping(tsk);
        }
        preempt_enable_no_resched();
    }

    if (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);
    }
}

static void sched_update_worker(struct task_struct *tsk)
{
    if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
        if (tsk->flags & PF_WQ_WORKER) {
            wq_worker_running(tsk);
        } else {
            io_wq_worker_running(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());
    sched_update_worker(tsk);
}
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_PREEMPTION
/*
 * This is the entry point to schedule() from in-kernel preemption
 * off of preempt_enable.
 */
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_PREEMPTION */

/*
 * 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)
{
    WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && (wake_flags & ~(WF_SYNC)));
    return try_to_wake_up(curr->private, mode, wake_flags);
}
EXPORT_SYMBOL(default_wake_function);

static void __setscheduler_prio(struct task_struct *p, int prio)
{
    if (dl_prio(prio)) {
        p->sched_class = &dl_sched_class;
    } else if (rt_prio(prio)) {
        p->sched_class = &rt_sched_class;
    } else {
        p->sched_class = &fair_sched_class;
    }

    p->prio = prio;
}

#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_prio(pi_task->prio) &&
             dl_entity_preempt(&pi_task->dl, &p->dl))) {
            p->dl.pi_se = pi_task->dl.pi_se;
            queue_flag |= ENQUEUE_REPLENISH;
        } else {
            p->dl.pi_se = &p->dl;
        }
    } else if (rt_prio(prio)) {
        if (dl_prio(oldprio)) {
            p->dl.pi_se = &p->dl;
        }
        if (oldprio < prio) {
            queue_flag |= ENQUEUE_HEAD;
        }
    } else {
        if (dl_prio(oldprio)) {
            p->dl.pi_se = &p->dl;
        }
        if (rt_prio(oldprio)) {
            p->rt.timeout = 0;
        }
    }

    __setscheduler_prio(p, prio);

    if (queued) {
        enqueue_task(rq, p, queue_flag);
    }
    if (running) {
        set_next_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;
    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);
    old_prio = p->prio;
    p->prio = effective_prio(p);

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

    /*
     * If the task increased its priority or is running and
     * lowered its priority, then reschedule its CPU:
     */
    p->sched_class->prio_changed(rq, p, old_prio);

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 (rq->ttwu_pending) {
        return 0;
    }
#endif

    return 1;
}

/**
 * available_idle_cpu - is a given CPU idle for enqueuing work.
 * @cpu: the CPU in question.
 *
 * Return: 1 if the CPU is currently idle. 0 otherwise.
 */
int available_idle_cpu(int cpu)
{
    if (!idle_cpu(cpu)) {
        return 0;
    }

    if (vcpu_is_preempted(cpu)) {
        return 0;
    }

    return 1;
}

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

/**
 * find_process_by_pid - find a process with a matching PID value.
 * @pid: the pid in question.
 *
 * The task of @pid, if found. %NULL otherwise.
 */
static struct task_struct *find_process_by_pid(pid_t pid)
{
    return pid ? find_task_by_vpid(pid) : current;
}

/*
 * sched_setparam() passes in -1 for its policy, to let the functions
 * it calls know not to change it.
 */
#define SETPARAM_POLICY (-1)

static void __setscheduler_params(struct task_struct *p,
                                  const struct sched_attr *attr)
{
    int policy = attr->sched_policy;

    if (policy == SETPARAM_POLICY) {
        policy = p->policy;
    }

    p->policy = policy;

    if (dl_policy(policy)) {
        __setparam_dl(p, attr);
    } else if (fair_policy(policy)) {
        p->static_prio = NICE_TO_PRIO(attr->sched_nice);
    }

    /*
     * __sched_setscheduler() ensures attr->sched_priority == 0 when
     * !rt_policy. Always setting this ensures that things like
     * getparam()/getattr() don't report silly values for !rt tasks.
     */
    p->rt_priority = attr->sched_priority;
    p->normal_prio = normal_prio(p);
    set_load_weight(p);
}

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

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

static int __sched_setscheduler(struct task_struct *p,
                                const struct sched_attr *attr, bool user,
                                bool pi)
{
    int oldpolicy = -1, policy = attr->sched_policy;
    int retval, oldprio, newprio, queued, running;
    const struct sched_class *prev_class;
    struct rq_flags rf;
    int reset_on_fork;
    int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
    struct rq *rq;

    /* The pi code expects interrupts enabled */
    BUG_ON(pi && in_interrupt());
    while (1) {
        /* Double check policy once rq lock held: */
        if (policy < 0) {
            reset_on_fork = p->sched_reset_on_fork;
            policy = oldpolicy = p->policy;
        } else {
            reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK);

            if (!valid_policy(policy)) {
                return -EINVAL;
            }
        }

        if (attr->sched_flags & ~(SCHED_FLAG_ALL | SCHED_FLAG_SUGOV)) {
            return -EINVAL;
        }

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

        /*
         * Allow unprivileged RT tasks to decrease priority:
         */
        if (user && !capable(CAP_SYS_NICE)) {
            if (fair_policy(policy)) {
                if (attr->sched_nice < task_nice(p) &&
                    !can_nice(p, attr->sched_nice)) {
                    return -EPERM;
                }
            }

            if (rt_policy(policy)) {
                unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO);
                /* Can't set/change the rt policy: */
                if (policy != p->policy && !rlim_rtprio) {
                    return -EPERM;
                }

                /* Can't increase priority: */
                if (attr->sched_priority > p->rt_priority &&
                    attr->sched_priority > rlim_rtprio) {
                    return -EPERM;
                }
            }

            /*
             * Can't set/change SCHED_DEADLINE policy at all for now
             * (safest behavior); in the future we would like to allow
             * unprivileged DL tasks to increase their relative deadline
             * or reduce their runtime (both ways reducing utilization)
             */
            if (dl_policy(policy)) {
                return -EPERM;
            }

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

            /* Can't change other user's priorities: */
            if (!check_same_owner(p)) {
                return -EPERM;
            }

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

        if (user) {
            if (attr->sched_flags & SCHED_FLAG_SUGOV) {
                return -EINVAL;
            }

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

        /* Update task specific "requested" clamps */
        if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) {
            retval = uclamp_validate(p, attr);
            if (retval) {
                return retval;
            }
        }

        if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE) {
            retval = latency_nice_validate(p, user, attr);
            if (retval) {
                return retval;
            }
        }

        if (pi) {
            cpuset_read_lock();
        }

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

        /*
         * Changing the policy of the stop threads its a very bad idea:
         */
        if (p == rq->stop) {
            retval = -EINVAL;
            goto unlock;
        }

        /*
         * If not changing anything there's no need to proceed further,
         * but store a possible modification of reset_on_fork.
         */
        if (unlikely(policy == p->policy)) {
            if (fair_policy(policy) && attr->sched_nice != task_nice(p)) {
                goto change;
            }
            if (rt_policy(policy) && attr->sched_priority != p->rt_priority) {
                goto change;
            }
            if (dl_policy(policy) && dl_param_changed(p, attr)) {
                goto change;
            }
            if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) {
                goto change;
            }
#ifdef CONFIG_SCHED_LATENCY_NICE
            if ((attr->sched_flags & SCHED_FLAG_LATENCY_NICE) &&
                (attr->sched_latency_nice != LATENCY_TO_NICE(p->latency_prio))) {
                goto change;
            }
#endif

            p->sched_reset_on_fork = reset_on_fork;
            retval = 0;
            goto unlock;
        }
    change:

        if (user) {
#ifdef CONFIG_RT_GROUP_SCHED
            /*
             * Do not allow realtime tasks into groups that have no runtime
             * assigned.
             */
            if (rt_bandwidth_enabled() && rt_policy(policy) &&
                task_group(p)->rt_bandwidth.rt_runtime == 0 &&
                !task_group_is_autogroup(task_group(p))) {
                retval = -EPERM;
                goto unlock;
            }
#endif
#ifdef CONFIG_SMP
            if (dl_bandwidth_enabled() && dl_policy(policy) &&
                !(attr->sched_flags & SCHED_FLAG_SUGOV)) {
                cpumask_t *span = rq->rd->span;

                /*
                 * Don't allow tasks with an affinity mask smaller than
                 * the entire root_domain to become SCHED_DEADLINE. We
                 * will also fail if there's no bandwidth available.
                 */
                if (!cpumask_subset(span, p->cpus_ptr) ||
                    rq->rd->dl_bw.bw == 0) {
                    retval = -EPERM;
                    goto unlock;
                }
            }
#endif
        }

        /* Re-check policy now with rq lock held: */
        if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
            policy = oldpolicy = -1;
            task_rq_unlock(rq, p, &rf);
            if (pi) {
                cpuset_read_unlock();
            }
            continue;
        }
        break;
    }

    /*
     * If setscheduling to SCHED_DEADLINE (or changing the parameters
     * of a SCHED_DEADLINE task) we need to check if enough bandwidth
     * is available.
     */
    if ((dl_policy(policy) || dl_task(p)) &&
        sched_dl_overflow(p, policy, attr)) {
        retval = -EBUSY;
        goto unlock;
    }

    p->sched_reset_on_fork = reset_on_fork;
    oldprio = p->prio;

    newprio = __normal_prio(policy, attr->sched_priority, attr->sched_nice);
    if (pi) {
        /*
         * Take priority boosted tasks into account. If the new
         * effective priority is unchanged, we just store the new
         * normal parameters and do not touch the scheduler class and
         * the runqueue. This will be done when the task deboost
         * itself.
         */
        newprio = rt_effective_prio(p, newprio);
        if (newprio == oldprio) {
            queue_flags &= ~DEQUEUE_MOVE;
        }
    }

    queued = task_on_rq_queued(p);
    running = task_current(rq, p);
    if (queued) {
        dequeue_task(rq, p, queue_flags);
    }
    if (running) {
        put_prev_task(rq, p);
    }

    prev_class = p->sched_class;

    if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
        __setscheduler_params(p, attr);
        __setscheduler_prio(p, newprio);
    }
    __setscheduler_latency(p, attr);
    __setscheduler_uclamp(p, attr);

    if (queued) {
        /*
         * We enqueue to tail when the priority of a task is
         * increased (user space view).
         */
        if (oldprio < p->prio) {
            queue_flags |= ENQUEUE_HEAD;
        }

        enqueue_task(rq, p, queue_flags);
    }
    if (running) {
        set_next_task(rq, p);
    }

    check_class_changed(rq, p, prev_class, oldprio);

    /* Avoid rq from going away on us: */
    preempt_disable();
    task_rq_unlock(rq, p, &rf);

    if (pi) {
        cpuset_read_unlock();
        rt_mutex_adjust_pi(p);
    }

    /* Run balance callbacks after we've adjusted the PI chain: */
    balance_callback(rq);
    preempt_enable();

    return 0;

unlock:
    task_rq_unlock(rq, p, &rf);
    if (pi) {
        cpuset_read_unlock();
    }
    return retval;
}

static int _sched_setscheduler(struct task_struct *p, int policy,
                               const struct sched_param *param, bool check)
{
    struct sched_attr attr = {
        .sched_policy = policy,
        .sched_priority = param->sched_priority,
        .sched_nice = PRIO_TO_NICE(p->static_prio),
    };

    /* Fixup the legacy SCHED_RESET_ON_FORK hack. */
    if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
        attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
        policy &= ~SCHED_RESET_ON_FORK;
        attr.sched_policy = policy;
    }

    return __sched_setscheduler(p, &attr, check, true);
}
/**
 * sched_setscheduler - change the scheduling policy and/or RT priority of a
 * thread.
 * @p: the task in question.
 * @policy: new policy.
 * @param: structure containing the new RT priority.
 *
 * Use sched_set_fifo(), read its comment.
 *
 * Return: 0 on success. An error code otherwise.
 *
 * NOTE that the task may be already dead.
 */
int sched_setscheduler(struct task_struct *p, int policy,
                       const struct sched_param *param)
{
    return _sched_setscheduler(p, policy, param, true);
}
EXPORT_SYMBOL_GPL(sched_setscheduler);

int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
{
    return __sched_setscheduler(p, attr, true, true);
}
EXPORT_SYMBOL_GPL(sched_setattr);

int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
{
    return __sched_setscheduler(p, attr, false, true);
}
EXPORT_SYMBOL_GPL(sched_setattr_nocheck);

/**
 * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority
 * of a thread from kernelspace.
 * @p: the task in question.
 * @policy: new policy.
 * @param: structure containing the new RT priority.
 *
 * Just like sched_setscheduler, only don't bother checking if the
 * current context has permission.  For example, this is needed in
 * stop_machine(): we create temporary high priority worker threads,
 * but our caller might not have that capability.
 *
 * Return: 0 on success. An error code otherwise.
 */
int sched_setscheduler_nocheck(struct task_struct *p, int policy,
                               const struct sched_param *param)
{
    return _sched_setscheduler(p, policy, param, false);
}
EXPORT_SYMBOL_GPL(sched_setscheduler_nocheck);

/*
 * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally
 * incapable of resource management, which is the one thing an OS really should
 * be doing.
 *
 * This is of course the reason it is limited to privileged users only.
 *
 * Worse still; it is fundamentally impossible to compose static priority
 * workloads. You cannot take two correctly working static prio workloads
 * and smash them together and still expect them to work.
 *
 * For this reason 'all' FIFO tasks the kernel creates are basically at:
 *
 *   MAX_RT_PRIO / 2
 *
 * The administrator _MUST_ configure the system, the kernel simply doesn't
 * know enough information to make a sensible choice.
 */
void sched_set_fifo(struct task_struct *p)
{
    struct sched_param sp = {.sched_priority = MAX_RT_PRIO / 2};
    WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
}
EXPORT_SYMBOL_GPL(sched_set_fifo);

/*
 * For when you don't much care about FIFO, but want to be above SCHED_NORMAL.
 */
void sched_set_fifo_low(struct task_struct *p)
{
    struct sched_param sp = {.sched_priority = 1};
    WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
}
EXPORT_SYMBOL_GPL(sched_set_fifo_low);

void sched_set_normal(struct task_struct *p, int nice)
{
    struct sched_attr attr = {
        .sched_policy = SCHED_NORMAL,
        .sched_nice = nice,
    };
    WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0);
}
EXPORT_SYMBOL_GPL(sched_set_normal);

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

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

    rcu_read_lock();
    retval = -ESRCH;
    p = find_process_by_pid(pid);
    if (likely(p)) {
        get_task_struct(p);
    }
    rcu_read_unlock();

    if (likely(p)) {
        retval = sched_setscheduler(p, policy, &lparam);
        put_task_struct(p);
    }

    return retval;
}

/*
 * Mimics kernel/events/core.c perf_copy_attr().
 */
static int sched_copy_attr(struct sched_attr __user *uattr,
                           struct sched_attr *attr)
{
    u32 size;
    int ret;

    /* Zero the full structure, so that a short copy will be nice: */
    memset(attr, 0, sizeof(*attr));

    ret = get_user(size, &uattr->size);
    if (ret) {
        return ret;
    }

    /* ABI compatibility quirk: */
    if (!size) {
        size = SCHED_ATTR_SIZE_VER0;
    }
    if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE) {
        goto err_size;
    }

    ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size);
    if (ret) {
        if (ret == -E2BIG) {
            goto err_size;
        }
        return ret;
    }

    if ((attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) &&
        size < SCHED_ATTR_SIZE_VER1) {
        return -EINVAL;
    }

#ifdef CONFIG_SCHED_LATENCY_NICE
    if ((attr->sched_flags & SCHED_FLAG_LATENCY_NICE) &&
        size < SCHED_ATTR_SIZE_VER2) {
        return -EINVAL;
    }
#endif
    /*
     * XXX: Do we want to be lenient like existing syscalls; or do we want
     * to be strict and return an error on out-of-bounds values?
     */
    attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE);

    return 0;

err_size:
    put_user(sizeof(*attr), &uattr->size);
    return -E2BIG;
}

/**
 * sys_sched_setscheduler - set/change the scheduler policy and RT priority
 * @pid: the pid in question.
 * @policy: new policy.
 * @param: structure containing the new RT priority.
 *
 * Return: 0 on success. An error code otherwise.
 */
SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
                struct sched_param __user *, param)
{
    if (policy < 0) {
        return -EINVAL;
    }

    return do_sched_setscheduler(pid, policy, param);
}

/**
 * sys_sched_setparam - set/change the RT priority of a thread
 * @pid: the pid in question.
 * @param: structure containing the new RT priority.
 *
 * Return: 0 on success. An error code otherwise.
 */
SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
{
    return do_sched_setscheduler(pid, SETPARAM_POLICY, param);
}

/**
 * sys_sched_setattr - same as above, but with extended sched_attr
 * @pid: the pid in question.
 * @uattr: structure containing the extended parameters.
 * @flags: for future extension.
 */
SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
                unsigned int, flags)
{
    struct sched_attr attr;
    struct task_struct *p;
    int retval;

    if (!uattr || pid < 0 || flags) {
        return -EINVAL;
    }

    retval = sched_copy_attr(uattr, &attr);
    if (retval) {
        return retval;
    }

    if ((int)attr.sched_policy < 0) {
        return -EINVAL;
    }
    if (attr.sched_flags & SCHED_FLAG_KEEP_POLICY) {
        attr.sched_policy = SETPARAM_POLICY;
    }

    rcu_read_lock();
    retval = -ESRCH;
    p = find_process_by_pid(pid);
    if (likely(p)) {
        get_task_struct(p);
    }
    rcu_read_unlock();

    if (likely(p)) {
        retval = sched_setattr(p, &attr);
        put_task_struct(p);
    }

    return retval;
}

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

    if (pid < 0) {
        return -EINVAL;
    }

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

/**
 * sys_sched_getparam - get the RT priority of a thread
 * @pid: the pid in question.
 * @param: structure containing the RT priority.
 *
 * Return: On success, 0 and the RT priority is in @param. Otherwise, an error
 * code.
 */
SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
{
    struct sched_param lp = {.sched_priority = 0};
    struct task_struct *p;
    int retval;

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

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

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

    if (task_has_rt_policy(p)) {
        lp.sched_priority = p->rt_priority;
    }
    rcu_read_unlock();

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

    return retval;

out_unlock:
    rcu_read_unlock();
    return retval;
}

/*
 * Copy the kernel size attribute structure (which might be larger
 * than what user-space knows about) to user-space.
 *
 * Note that all cases are valid: user-space buffer can be larger or
 * smaller than the kernel-space buffer. The usual case is that both
 * have the same size.
 */
static int sched_attr_copy_to_user(struct sched_attr __user *uattr,
                                   struct sched_attr *kattr, unsigned int usize)
{
    unsigned int ksize = sizeof(*kattr);

    if (!access_ok(uattr, usize)) {
        return -EFAULT;
    }

    /*
     * sched_getattr() ABI forwards and backwards compatibility:
     *
     * If usize == ksize then we just copy everything to user-space and all is
     * good.
     *
     * If usize < ksize then we only copy as much as user-space has space for,
     * this keeps ABI compatibility as well. We skip the rest.
     *
     * If usize > ksize then user-space is using a newer version of the ABI,
     * which part the kernel doesn't know about. Just ignore it - tooling can
     * detect the kernel's knowledge of attributes from the attr->size value
     * which is set to ksize in this case.
     */
    kattr->size = min(usize, ksize);

    if (copy_to_user(uattr, kattr, kattr->size)) {
        return -EFAULT;
    }

    return 0;
}

/**
 * sys_sched_getattr - similar to sched_getparam, but with sched_attr
 * @pid: the pid in question.
 * @uattr: structure containing the extended parameters.
 * @usize: sizeof(attr) for fwd/bwd comp.
 * @flags: for future extension.
 */
SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
                unsigned int, usize, unsigned int, flags)
{
    struct sched_attr kattr = {};
    struct task_struct *p;
    int retval;

    if (!uattr || pid < 0 || usize > PAGE_SIZE ||
        usize < SCHED_ATTR_SIZE_VER0 || flags) {
        return -EINVAL;
    }

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

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

    kattr.sched_policy = p->policy;
    if (p->sched_reset_on_fork) {
        kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
    }
    if (task_has_dl_policy(p)) {
        __getparam_dl(p, &kattr);
    } else if (task_has_rt_policy(p)) {
        kattr.sched_priority = p->rt_priority;
    } else {
        kattr.sched_nice = task_nice(p);
    }

#ifdef CONFIG_SCHED_LATENCY_NICE
    kattr.sched_latency_nice = LATENCY_TO_NICE(p->latency_prio);
#endif

#ifdef CONFIG_UCLAMP_TASK
    /*
     * This could race with another potential updater, but this is fine
     * because it'll correctly read the old or the new value. We don't need
     * to guarantee who wins the race as long as it doesn't return garbage.
     */
    kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
    kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
#endif

    rcu_read_unlock();

    return sched_attr_copy_to_user(uattr, &kattr, usize);

out_unlock:
    rcu_read_unlock();
    return retval;
}

long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
{
    cpumask_var_t cpus_allowed, new_mask;
    struct task_struct *p;
    int retval;
#ifdef CONFIG_CPU_ISOLATION_OPT
    int dest_cpu;
    cpumask_t allowed_mask;
#endif

    rcu_read_lock();

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

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

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

    retval = security_task_setscheduler(p);
    if (retval) {
        goto out_free_new_mask;
    }

    cpuset_cpus_allowed(p, cpus_allowed);
    cpumask_and(new_mask, in_mask, cpus_allowed);

    /*
     * Since bandwidth control happens on root_domain basis,
     * if admission test is enabled, we only admit -deadline
     * tasks allowed to run on all the CPUs in the task's
     * root_domain.
     */
#ifdef CONFIG_SMP
    if (task_has_dl_policy(p) && dl_bandwidth_enabled()) {
        rcu_read_lock();
        if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) {
            retval = -EBUSY;
            rcu_read_unlock();
            goto out_free_new_mask;
        }
        rcu_read_unlock();
    }
#endif
    while (1) {
#ifdef CONFIG_CPU_ISOLATION_OPT
        cpumask_andnot(&allowed_mask, new_mask, cpu_isolated_mask);
        dest_cpu = cpumask_any_and(cpu_active_mask, &allowed_mask);
        if (dest_cpu < nr_cpu_ids) {
#endif
            retval = __set_cpus_allowed_ptr(p, new_mask, true);
            if (!retval) {
                cpuset_cpus_allowed(p, cpus_allowed);
                if (!cpumask_subset(new_mask, cpus_allowed)) {
                    /*
                     * We must have raced with a concurrent cpuset
                     * update. Just reset the cpus_allowed to the
                     * cpuset's cpus_allowed
                     */
                    cpumask_copy(new_mask, cpus_allowed);
                    continue;
                }
            }
#ifdef CONFIG_CPU_ISOLATION_OPT
        } else {
            retval = -EINVAL;
        }
#endif
        break;
    }

out_free_new_mask:
    free_cpumask_var(new_mask);
out_free_cpus_allowed:
    free_cpumask_var(cpus_allowed);
out_put_task:
    put_task_struct(p);
    return retval;
}

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

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

/**
 * sys_sched_setaffinity - set the CPU affinity of a process
 * @pid: pid of the process
 * @len: length in bytes of the bitmask pointed to by user_mask_ptr
 * @user_mask_ptr: user-space pointer to the new CPU mask
 *
 * Return: 0 on success. An error code otherwise.
 */
SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
                unsigned long __user *, user_mask_ptr)
{
    cpumask_var_t new_mask;
    int retval;

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

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

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

    rcu_read_lock();

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

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

    raw_spin_lock_irqsave(&p->pi_lock, flags);
    cpumask_and(mask, &p->cpus_mask, cpu_active_mask);

#ifdef CONFIG_CPU_ISOLATION_OPT
    /* The userspace tasks are forbidden to run on
     * isolated CPUs. So exclude isolated CPUs from
     * the getaffinity.
     */
    if (!(p->flags & PF_KTHREAD)) {
        cpumask_andnot(mask, mask, cpu_isolated_mask);
    }
#endif

    raw_spin_unlock_irqrestore(&p->pi_lock, flags);

out_unlock:
    rcu_read_unlock();

    return retval;
}

/**
 * sys_sched_getaffinity - get the CPU affinity of a process
 * @pid: pid of the process
 * @len: length in bytes of the bitmask pointed to by user_mask_ptr
 * @user_mask_ptr: user-space pointer to hold the current CPU mask
 *
 * Return: size of CPU mask copied to user_mask_ptr on success. An
 * error code otherwise.
 */
SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
                unsigned long __user *, user_mask_ptr)
{
    int ret;
    cpumask_var_t mask;

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

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

    ret = sched_getaffinity(pid, mask);
    if (ret == 0) {
        unsigned int retlen = min(len, cpumask_size());

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

    return ret;
}

/**
 * sys_sched_yield - yield the current processor to other threads.
 *
 * This function yields the current CPU to other tasks. If there are no
 * other threads running on this CPU then this function will return.
 *
 * Return: 0.
 */
static void do_sched_yield(void)
{
    struct rq_flags rf;
    struct rq *rq;

    rq = this_rq_lock_irq(&rf);

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

    preempt_disable();
    rq_unlock_irq(rq, &rf);
    sched_preempt_enable_no_resched();

    schedule();
}

SYSCALL_DEFINE0(sched_yield)
{
    do_sched_yield();
    return 0;
}

#ifndef CONFIG_PREEMPTION
int __sched _cond_resched(void)
{
    if (should_resched(0)) {
        preempt_schedule_common();
        return 1;
    }
    rcu_all_qs();
    return 0;
}
EXPORT_SYMBOL(_cond_resched);
#endif

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

    lockdep_assert_held(lock);

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

/**
 * yield - yield the current processor to other threads.
 *
 * Do not ever use this function, there's a 99% chance you're doing it wrong.
 *
 * The scheduler is at all times free to pick the calling task as the most
 * eligible task to run, if removing the yield() call from your code breaks
 * it, its already broken.
 *
 * Typical broken usage is:
 *
 * while (!event)
 *    yield();
 *
 * where one assumes that yield() will let 'the other' process run that will
 * make event true. If the current task is a SCHED_FIFO task that will never
 * happen. Never use yield() as a progress guarantee!!
 *
 * If you want to use yield() to wait for something, use wait_event().
 * If you want to use yield() to be 'nice' for others, use cond_resched().
 * If you still want to use yield(), do not!
 */
void __sched yield(void)
{
    set_current_state(TASK_RUNNING);
    do_sched_yield();
}
EXPORT_SYMBOL(yield);

/**
 * yield_to - yield the current processor to another thread in
 * your thread group, or accelerate that thread toward the
 * processor it's on.
 * @p: target task
 * @preempt: whether task preemption is allowed or not
 *
 * It's the caller's job to ensure that the target task struct
 * can't go away on us before we can do any checks.
 *
 * Return:
 *    true (>0) if we indeed boosted the target task.
 *    false (0) if we failed to boost the target.
 *    -ESRCH if there's no task to yield to.
 */
int __sched yield_to(struct task_struct *p, bool preempt)
{
    struct task_struct *curr = current;
    struct rq *rq, *p_rq;
    unsigned long flags;
    int yielded = 0;

    local_irq_save(flags);
    rq = this_rq();

again:
    p_rq = task_rq(p);
    /*
     * If we're the only runnable task on the rq and target rq also
     * has only one task, there's absolutely no point in yielding.
     */
    if (rq->nr_running == 1 && p_rq->nr_running == 1) {
        yielded = -ESRCH;
        goto out_irq;
    }

    double_rq_lock(rq, p_rq);
    if (task_rq(p) != p_rq) {
        double_rq_unlock(rq, p_rq);
        goto again;
    }

    if (!curr->sched_class->yield_to_task) {
        goto out_unlock;
    }

    if (curr->sched_class != p->sched_class) {
        goto out_unlock;
    }

    if (task_running(p_rq, p) || p->state) {
        goto out_unlock;
    }

    yielded = curr->sched_class->yield_to_task(rq, p);
    if (yielded) {
        schedstat_inc(rq->yld_count);
        /*
         * Make p's CPU reschedule; pick_next_entity takes care of
         * fairness.
         */
        if (preempt && rq != p_rq) {
            resched_curr(p_rq);
        }
    }

out_unlock:
    double_rq_unlock(rq, p_rq);
out_irq:
    local_irq_restore(flags);

    if (yielded > 0) {
        schedule();
    }

    return yielded;
}
EXPORT_SYMBOL_GPL(yield_to);

int io_schedule_prepare(void)
{
    int old_iowait = current->in_iowait;

    current->in_iowait = 1;
    blk_schedule_flush_plug(current);

    return old_iowait;
}

void io_schedule_finish(int token)
{
    current->in_iowait = token;
}

/*
 * This task is about to go to sleep on IO. Increment rq->nr_iowait so
 * that process accounting knows that this is a task in IO wait state.
 */
long __sched io_schedule_timeout(long timeout)
{
    int token;
    long ret;

    token = io_schedule_prepare();
    ret = schedule_timeout(timeout);
    io_schedule_finish(token);

    return ret;
}
EXPORT_SYMBOL(io_schedule_timeout);

void __sched io_schedule(void)
{
    int token;

    token = io_schedule_prepare();
    schedule();
    io_schedule_finish(token);
}
EXPORT_SYMBOL(io_schedule);

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

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

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

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

static int sched_rr_get_interval(pid_t pid, struct timespec64 *t)
{
    struct task_struct *p;
    unsigned int time_slice;
    struct rq_flags rf;
    struct rq *rq;
    int retval;

    if (pid < 0) {
        return -EINVAL;
    }

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

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

    rq = task_rq_lock(p, &rf);
    time_slice = 0;
    if (p->sched_class->get_rr_interval) {
        time_slice = p->sched_class->get_rr_interval(rq, p);
    }
    task_rq_unlock(rq, p, &rf);

    rcu_read_unlock();
    jiffies_to_timespec64(time_slice, t);
    return 0;

out_unlock:
    rcu_read_unlock();
    return retval;
}

/**
 * sys_sched_rr_get_interval - return the default timeslice of a process.
 * @pid: pid of the process.
 * @interval: userspace pointer to the timeslice value.
 *
 * this syscall writes the default timeslice value of a given process
 * into the user-space timespec buffer. A value of '0' means infinity.
 *
 * Return: On success, 0 and the timeslice is in @interval. Otherwise,
 * an error code.
 */
SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
                struct __kernel_timespec __user *, interval)
{
    struct timespec64 t;
    int retval = sched_rr_get_interval(pid, &t);

    if (retval == 0) {
        retval = put_timespec64(&t, interval);
    }

    return retval;
}

#ifdef CONFIG_COMPAT_32BIT_TIME
SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid,
                struct old_timespec32 __user *, interval)
{
    struct timespec64 t;
    int retval = sched_rr_get_interval(pid, &t);

    if (retval == 0) {
        retval = put_old_timespec32(&t, interval);
    }
    return retval;
}
#endif

void sched_show_task(struct task_struct *p)
{
    unsigned long free = 0;
    int ppid;

    if (!try_get_task_stack(p)) {
        return;
    }

    pr_info("task:%-15.15s state:%c", p->comm, task_state_to_char(p));

    if (p->state == TASK_RUNNING) {
        pr_cont("  running task    ");
    }
#ifdef CONFIG_DEBUG_STACK_USAGE
    free = stack_not_used(p);
#endif
    ppid = 0;
    rcu_read_lock();
    if (pid_alive(p)) {
        ppid = task_pid_nr(rcu_dereference(p->real_parent));
    }
    rcu_read_unlock();
    pr_cont(" stack:%5lu pid:%5d ppid:%6d flags:0x%08lx\n", free,
            task_pid_nr(p), ppid, (unsigned long)task_thread_info(p)->flags);

    print_worker_info(KERN_INFO, p);
    show_stack(p, NULL, KERN_INFO);
    put_task_stack(p);
}
EXPORT_SYMBOL_GPL(sched_show_task);

static inline bool state_filter_match(unsigned long state_filter,
                                      struct task_struct *p)
{
    /* no filter, everything matches */
    if (!state_filter) {
        return true;
    }

    /* filter, but doesn't match */
    if (!(p->state & state_filter)) {
        return false;
    }

    /*
     * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows
     * TASK_KILLABLE).
     */
    if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE) {
        return false;
    }

    return true;
}

void show_state_filter(unsigned long state_filter)
{
    struct task_struct *g, *p;

    rcu_read_lock();
    for_each_process_thread(g, p)
    {
        /*
         * reset the NMI-timeout, listing all files on a slow
         * console might take a lot of time:
         * Also, reset softlockup watchdogs on all CPUs, because
         * another CPU might be blocked waiting for us to process
         * an IPI.
         */
        touch_nmi_watchdog();
        touch_all_softlockup_watchdogs();
        if (state_filter_match(state_filter, p)) {
            sched_show_task(p);
        }
    }

#ifdef CONFIG_SCHED_DEBUG
    if (!state_filter) {
        sysrq_sched_debug_show();
    }
#endif
    rcu_read_unlock();
    /*
     * Only show locks if all tasks are dumped:
     */
    if (!state_filter) {
        debug_show_all_locks();
    }
}

/**
 * init_idle - set up an idle thread for a given CPU
 * @idle: task in question
 * @cpu: CPU the idle task belongs to
 *
 * NOTE: this function does not set the idle thread's NEED_RESCHED
 * flag, to make booting more robust.
 */
void __init init_idle(struct task_struct *idle, int cpu)
{
    struct rq *rq = cpu_rq(cpu);
    unsigned long flags;

    __sched_fork(0, idle);

    raw_spin_lock_irqsave(&idle->pi_lock, flags);
    raw_spin_lock(&rq->lock);

    idle->state = TASK_RUNNING;
    idle->se.exec_start = sched_clock();
    idle->flags |= PF_IDLE;


#ifdef CONFIG_SMP
    /*
     * Its possible that init_idle() gets called multiple times on a task,
     * in that case do_set_cpus_allowed() will not do the right thing.
     *
     * And since this is boot we can forgo the serialization.
     */
    set_cpus_allowed_common(idle, cpumask_of(cpu));
#endif
    /*
     * We're having a chicken and egg problem, even though we are
     * holding rq->lock, the CPU isn't yet set to this CPU so the
     * lockdep check in task_group() will fail.
     *
     * Similar case to sched_fork(). / Alternatively we could
     * use task_rq_lock() here and obtain the other rq->lock.
     *
     * Silence PROVE_RCU
     */
    rcu_read_lock();
    __set_task_cpu(idle, cpu);
    rcu_read_unlock();

    rq->idle = idle;
    rcu_assign_pointer(rq->curr, idle);
    idle->on_rq = TASK_ON_RQ_QUEUED;
#ifdef CONFIG_SMP
    idle->on_cpu = 1;
#endif
    raw_spin_unlock(&rq->lock);
    raw_spin_unlock_irqrestore(&idle->pi_lock, flags);

    /* Set the preempt count _outside_ the spinlocks! */
    init_idle_preempt_count(idle, cpu);

    /*
     * The idle tasks have their own, simple scheduling class:
     */
    idle->sched_class = &idle_sched_class;
    ftrace_graph_init_idle_task(idle, cpu);
    vtime_init_idle(idle, cpu);
#ifdef CONFIG_SMP
    sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
#endif
}

#ifdef CONFIG_SMP

int cpuset_cpumask_can_shrink(const struct cpumask *cur,
                              const struct cpumask *trial)
{
    int ret = 1;

    if (!cpumask_weight(cur)) {
        return ret;
    }

    ret = dl_cpuset_cpumask_can_shrink(cur, trial);

    return ret;
}

int task_can_attach(struct task_struct *p,
                    const struct cpumask *cs_effective_cpus)
{
    int ret = 0;

    /*
     * Kthreads which disallow setaffinity shouldn't be moved
     * to a new cpuset; we don't want to change their CPU
     * affinity and isolating such threads by their set of
     * allowed nodes is unnecessary.  Thus, cpusets are not
     * applicable for such threads.  This prevents checking for
     * success of set_cpus_allowed_ptr() on all attached tasks
     * before cpus_mask may be changed.
     */
    if (p->flags & PF_NO_SETAFFINITY) {
        ret = -EINVAL;
        goto out;
    }

    if (dl_task(p) &&
        !cpumask_intersects(task_rq(p)->rd->span, cs_effective_cpus)) {
        int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus);
        if (unlikely(cpu >= nr_cpu_ids))
            return -EINVAL;
        ret = dl_cpu_busy(cpu, p);
    }

out:
    return ret;
}

bool sched_smp_initialized __read_mostly;

#ifdef CONFIG_NUMA_BALANCING
/* Migrate current task p to target_cpu */
int migrate_task_to(struct task_struct *p, int target_cpu)
{
    struct migration_arg arg = {p, target_cpu};
    int curr_cpu = task_cpu(p);
    if (curr_cpu == target_cpu) {
        return 0;
    }

    if (!cpumask_test_cpu(target_cpu, p->cpus_ptr)) {
        return -EINVAL;
    }

    /* This is not properly updating schedstats */

    trace_sched_move_numa(p, curr_cpu, target_cpu);
    return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
}

/*
 * Requeue a task on a given node and accurately track the number of NUMA
 * tasks on the runqueues
 */
void sched_setnuma(struct task_struct *p, int nid)
{
    bool queued, running;
    struct rq_flags rf;
    struct rq *rq;

    rq = task_rq_lock(p, &rf);
    queued = task_on_rq_queued(p);
    running = task_current(rq, p);

    if (queued) {
        dequeue_task(rq, p, DEQUEUE_SAVE);
    }
    if (running) {
        put_prev_task(rq, p);
    }

    p->numa_preferred_nid = nid;

    if (queued) {
        enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
    }
    if (running) {
        set_next_task(rq, p);
    }
    task_rq_unlock(rq, p, &rf);
}
#endif /* CONFIG_NUMA_BALANCING */

#ifdef CONFIG_HOTPLUG_CPU
/*
 * Ensure that the idle task is using init_mm right before its CPU goes
 * offline.
 */
void idle_task_exit(void)
{
    struct mm_struct *mm = current->active_mm;

    BUG_ON(cpu_online(smp_processor_id()));
    BUG_ON(current != this_rq()->idle);

    if (mm != &init_mm) {
        switch_mm(mm, &init_mm, current);
        finish_arch_post_lock_switch();
    }

    /* finish_cpu(), as ran on the BP, will clean up the active_mm state */
}

/*
 * Since this CPU is going 'away' for a while, fold any nr_active delta
 * we might have. Assumes we're called after migrate_tasks() so that the
 * nr_active count is stable. We need to take the teardown thread which
 * is calling this into account, so we hand in adjust = 1 to the load
 * calculation.
 *
 * Also see the comment "Global load-average calculations".
 */
static void calc_load_migrate(struct rq *rq)
{
    long delta = calc_load_fold_active(rq, 1);
    if (delta) {
        atomic_long_add(delta, &calc_load_tasks);
    }
}

static struct task_struct *__pick_migrate_task(struct rq *rq)
{
    const struct sched_class *class;
    struct task_struct *next;

    for_each_class(class)
    {
        next = class->pick_next_task(rq);
        if (next) {
            next->sched_class->put_prev_task(rq, next);
            return next;
        }
    }

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

#ifdef CONFIG_CPU_ISOLATION_OPT
/*
 * Remove a task from the runqueue and pretend that it's migrating. This
 * should prevent migrations for the detached task and disallow further
 * changes to tsk_cpus_allowed.
 */
static void detach_one_task_core(struct task_struct *p, struct rq *rq,
                                 struct list_head *tasks)
{
    lockdep_assert_held(&rq->lock);

    p->on_rq = TASK_ON_RQ_MIGRATING;
    deactivate_task(rq, p, 0);
    list_add(&p->se.group_node, tasks);
}

static void attach_tasks_core(struct list_head *tasks, struct rq *rq)
{
    struct task_struct *p;

    lockdep_assert_held(&rq->lock);

    while (!list_empty(tasks)) {
        p = list_first_entry(tasks, struct task_struct, se.group_node);
        list_del_init(&p->se.group_node);

        BUG_ON(task_rq(p) != rq);
        activate_task(rq, p, 0);
        p->on_rq = TASK_ON_RQ_QUEUED;
    }
}

#else

static void detach_one_task_core(struct task_struct *p, struct rq *rq,
                                 struct list_head *tasks)
{
}

static void attach_tasks_core(struct list_head *tasks, struct rq *rq)
{
}

#endif /* CONFIG_CPU_ISOLATION_OPT */

/*
 * Migrate all tasks (not pinned if pinned argument say so) from the rq,
 * sleeping tasks will be migrated by try_to_wake_up()->select_task_rq().
 *
 * Called with rq->lock held even though we'er in stop_machine() and
 * there's no concurrency possible, we hold the required locks anyway
 * because of lock validation efforts.
 */
void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf,
                   bool migrate_pinned_tasks)
{
    struct rq *rq = dead_rq;
    struct task_struct *next, *stop = rq->stop;
    struct rq_flags orf = *rf;
    int dest_cpu;
    unsigned int num_pinned_kthreads = 1; /* this thread */
    LIST_HEAD(tasks);
    cpumask_t avail_cpus;

#ifdef CONFIG_CPU_ISOLATION_OPT
    cpumask_andnot(&avail_cpus, cpu_online_mask, cpu_isolated_mask);
#else
    cpumask_copy(&avail_cpus, cpu_online_mask);
#endif

    /*
     * Fudge the rq selection such that the below task selection loop
     * doesn't get stuck on the currently eligible stop task.
     *
     * We're currently inside stop_machine() and the rq is either stuck
     * in the stop_machine_cpu_stop() loop, or we're executing this code,
     * either way we should never end up calling schedule() until we're
     * done here.
     */
    rq->stop = NULL;

    /*
     * put_prev_task() and pick_next_task() sched
     * class method both need to have an up-to-date
     * value of rq->clock[_task]
     */
    update_rq_clock(rq);

#ifdef CONFIG_SCHED_DEBUG
    /* note the clock update in orf */
    orf.clock_update_flags |= RQCF_UPDATED;
#endif

    for (;;) {
        /*
         * There's this thread running, bail when that's the only
         * remaining thread.
         */
        if (rq->nr_running == 1) {
            break;
        }

        next = __pick_migrate_task(rq);
        if (!migrate_pinned_tasks && (next->flags & PF_KTHREAD) &&
            !cpumask_intersects(&avail_cpus, &next->cpus_mask)) {
            detach_one_task_core(next, rq, &tasks);
            num_pinned_kthreads += 1;
            continue;
        }

        /*
         * Rules for changing task_struct::cpus_mask are holding
         * both pi_lock and rq->lock, such that holding either
         * stabilizes the mask.
         *
         * Drop rq->lock is not quite as disastrous as it usually is
         * because !cpu_active at this point, which means load-balance
         * will not interfere. Also, stop-machine.
         */
        rq_unlock(rq, rf);
        raw_spin_lock(&next->pi_lock);
        rq_relock(rq, rf);
        if (!(rq->clock_update_flags & RQCF_UPDATED)) {
            update_rq_clock(rq);
        }

        /*
         * Since we're inside stop-machine, _nothing_ should have
         * changed the task, WARN if weird stuff happened, because in
         * that case the above rq->lock drop is a fail too.
         * However, during cpu isolation the load balancer might have
         * interferred since we don't stop all CPUs. Ignore warning for
         * this case.
         */
        if (task_rq(next) != rq || !task_on_rq_queued(next)) {
            WARN_ON(migrate_pinned_tasks);
            raw_spin_unlock(&next->pi_lock);
            continue;
        }

        /* Find suitable destination for @next, with force if needed. */
#ifdef CONFIG_CPU_ISOLATION_OPT
        dest_cpu = select_fallback_rq(dead_rq->cpu, next, false);
#else
        dest_cpu = select_fallback_rq(dead_rq->cpu, next);
#endif
        rq = __migrate_task(rq, rf, next, dest_cpu);
        if (rq != dead_rq) {
            rq_unlock(rq, rf);
            rq = dead_rq;
            *rf = orf;
            rq_relock(rq, rf);
            if (!(rq->clock_update_flags & RQCF_UPDATED)) {
                update_rq_clock(rq);
            }
        }
        raw_spin_unlock(&next->pi_lock);
    }

    rq->stop = stop;

    if (num_pinned_kthreads > 1) {
        attach_tasks_core(&tasks, rq);
    }
}

#ifdef CONFIG_SCHED_EAS
static void clear_eas_migration_request(int cpu)
{
    struct rq *rq = cpu_rq(cpu);
    unsigned long flags;

    clear_reserved(cpu);
    if (rq->push_task) {
        struct task_struct *push_task = NULL;

        raw_spin_lock_irqsave(&rq->lock, flags);
        if (rq->push_task) {
            clear_reserved(rq->push_cpu);
            push_task = rq->push_task;
            rq->push_task = NULL;
        }
        rq->active_balance = 0;
        raw_spin_unlock_irqrestore(&rq->lock, flags);
        if (push_task) {
            put_task_struct(push_task);
        }
    }
}
#else
static inline void clear_eas_migration_request(int cpu)
{
}
#endif

#ifdef CONFIG_CPU_ISOLATION_OPT
int do_isolation_work_cpu_stop(void *data)
{
    unsigned int cpu = smp_processor_id();
    struct rq *rq = cpu_rq(cpu);
    struct rq_flags rf;

    watchdog_disable(cpu);

    local_irq_disable();

    irq_migrate_all_off_this_cpu();

    flush_smp_call_function_from_idle();

    /* Update our root-domain */
    rq_lock(rq, &rf);

    /*
     * Temporarily mark the rq as offline. This will allow us to
     * move tasks off the CPU.
     */
    if (rq->rd) {
        BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
        set_rq_offline(rq);
    }

    migrate_tasks(rq, &rf, false);

    if (rq->rd) {
        set_rq_online(rq);
    }
    rq_unlock(rq, &rf);

    clear_eas_migration_request(cpu);
    local_irq_enable();
    return 0;
}

int do_unisolation_work_cpu_stop(void *data)
{
    watchdog_enable(smp_processor_id());
    return 0;
}

static void sched_update_group_capacities(int cpu)
{
    struct sched_domain *sd;

    mutex_lock(&sched_domains_mutex);
    rcu_read_lock();

    for_each_domain(cpu, sd)
    {
        int balance_cpu = group_balance_cpu(sd->groups);

        init_sched_groups_capacity(cpu, sd);
        /*
         * Need to ensure this is also called with balancing
         * cpu.
         */
        if (cpu != balance_cpu) {
            init_sched_groups_capacity(balance_cpu, sd);
        }
    }

    rcu_read_unlock();
    mutex_unlock(&sched_domains_mutex);
}

static unsigned int cpu_isolation_vote[NR_CPUS];

int sched_isolate_count(const cpumask_t *mask, bool include_offline)
{
    cpumask_t count_mask = CPU_MASK_NONE;

    if (include_offline) {
        cpumask_complement(&count_mask, cpu_online_mask);
        cpumask_or(&count_mask, &count_mask, cpu_isolated_mask);
        cpumask_and(&count_mask, &count_mask, mask);
    } else {
        cpumask_and(&count_mask, mask, cpu_isolated_mask);
    }

    return cpumask_weight(&count_mask);
}

/*
 * 1) CPU is isolated and cpu is offlined:
 *    Unisolate the core.
 * 2) CPU is not isolated and CPU is offlined:
 *    No action taken.
 * 3) CPU is offline and request to isolate
 *    Request ignored.
 * 4) CPU is offline and isolated:
 *    Not a possible state.
 * 5) CPU is online and request to isolate
 *    Normal case: Isolate the CPU
 * 6) CPU is not isolated and comes back online
 *    Nothing to do
 *
 * Note: The client calling sched_isolate_cpu() is repsonsible for ONLY
 * calling sched_unisolate_cpu() on a CPU that the client previously isolated.
 * Client is also responsible for unisolating when a core goes offline
 * (after CPU is marked offline).
 */
int sched_isolate_cpu(int cpu)
{
    struct rq *rq;
    cpumask_t avail_cpus;
    int ret_code = 0;
    u64 start_time = 0;

    if (trace_sched_isolate_enabled()) {
        start_time = sched_clock();
    }

    cpu_maps_update_begin();

    cpumask_andnot(&avail_cpus, cpu_online_mask, cpu_isolated_mask);

    if (cpu < 0 || cpu >= nr_cpu_ids || !cpu_possible(cpu) ||
        !cpu_online(cpu) || cpu >= NR_CPUS) {
        ret_code = -EINVAL;
        goto out;
    }

    rq = cpu_rq(cpu);

    if (++cpu_isolation_vote[cpu] > 1) {
        goto out;
    }

    /* We cannot isolate ALL cpus in the system */
    if (cpumask_weight(&avail_cpus) == 1) {
        --cpu_isolation_vote[cpu];
        ret_code = -EINVAL;
        goto out;
    }

    /*
     * There is a race between watchdog being enabled by hotplug and
     * core isolation disabling the watchdog. When a CPU is hotplugged in
     * and the hotplug lock has been released the watchdog thread might
     * not have run yet to enable the watchdog.
     * We have to wait for the watchdog to be enabled before proceeding.
     */
    if (!watchdog_configured(cpu)) {
        msleep(0x14);
        if (!watchdog_configured(cpu)) {
            --cpu_isolation_vote[cpu];
            ret_code = -EBUSY;
            goto out;
        }
    }

    set_cpu_isolated(cpu, true);
    cpumask_clear_cpu(cpu, &avail_cpus);

    /* Migrate timers */
    smp_call_function_any(&avail_cpus, hrtimer_quiesce_cpu, &cpu, 1);
    smp_call_function_any(&avail_cpus, timer_quiesce_cpu, &cpu, 1);

    watchdog_disable(cpu);
    irq_lock_sparse();
    stop_cpus(cpumask_of(cpu), do_isolation_work_cpu_stop, 0);
    irq_unlock_sparse();

    calc_load_migrate(rq);
    update_max_interval();
    sched_update_group_capacities(cpu);

out:
    cpu_maps_update_done();
    trace_sched_isolate(cpu, cpumask_bits(cpu_isolated_mask)[0], start_time, 1);
    return ret_code;
}

/*
 * Note: The client calling sched_isolate_cpu() is repsonsible for ONLY
 * calling sched_unisolate_cpu() on a CPU that the client previously isolated.
 * Client is also responsible for unisolating when a core goes offline
 * (after CPU is marked offline).
 */
int sched_unisolate_cpu_unlocked(int cpu)
{
    int ret_code = 0;
    u64 start_time = 0;

    if (cpu < 0 || cpu >= nr_cpu_ids || !cpu_possible(cpu) || cpu >= NR_CPUS) {
        ret_code = -EINVAL;
        goto out;
    }

    if (trace_sched_isolate_enabled()) {
        start_time = sched_clock();
    }

    if (!cpu_isolation_vote[cpu]) {
        ret_code = -EINVAL;
        goto out;
    }

    if (--cpu_isolation_vote[cpu]) {
        goto out;
    }

    set_cpu_isolated(cpu, false);
    update_max_interval();
    sched_update_group_capacities(cpu);

    if (cpu_online(cpu)) {
        stop_cpus(cpumask_of(cpu), do_unisolation_work_cpu_stop, 0);

        /* Kick CPU to immediately do load balancing */
        if (!atomic_fetch_or(NOHZ_KICK_MASK, nohz_flags(cpu))) {
            smp_send_reschedule(cpu);
        }
    }

out:
    trace_sched_isolate(cpu, cpumask_bits(cpu_isolated_mask)[0], start_time, 0);
    return ret_code;
}

int sched_unisolate_cpu(int cpu)
{
    int ret_code;

    cpu_maps_update_begin();
    ret_code = sched_unisolate_cpu_unlocked(cpu);
    cpu_maps_update_done();
    return ret_code;
}

#endif /* CONFIG_CPU_ISOLATION_OPT */

#endif /* CONFIG_HOTPLUG_CPU */

void set_rq_online(struct rq *rq)
{
    if (!rq->online) {
        const struct sched_class *class;

        cpumask_set_cpu(rq->cpu, rq->rd->online);
        rq->online = 1;

        for_each_class(class)
        {
            if (class->rq_online) {
                class->rq_online(rq);
            }
        }
    }
}

void set_rq_offline(struct rq *rq)
{
    if (rq->online) {
        const struct sched_class *class;

        for_each_class(class)
        {
            if (class->rq_offline) {
                class->rq_offline(rq);
            }
        }

        cpumask_clear_cpu(rq->cpu, rq->rd->online);
        rq->online = 0;
    }
}

/*
 * used to mark begin/end of suspend/resume:
 */
static int num_cpus_frozen;

/*
 * Update cpusets according to cpu_active mask.  If cpusets are
 * disabled, cpuset_update_active_cpus() becomes a simple wrapper
 * around partition_sched_domains().
 *
 * If we come here as part of a suspend/resume, don't touch cpusets because we
 * want to restore it back to its original state upon resume anyway.
 */
static void cpuset_cpu_active(void)
{
    if (cpuhp_tasks_frozen) {
        /*
         * num_cpus_frozen tracks how many CPUs are involved in suspend
         * resume sequence. As long as this is not the last online
         * operation in the resume sequence, just build a single sched
         * domain, ignoring cpusets.
         */
        partition_sched_domains(1, NULL, NULL);
        if (--num_cpus_frozen) {
            return;
        }
        /*
         * This is the last CPU online operation. So fall through and
         * restore the original sched domains by considering the
         * cpuset configurations.
         */
        cpuset_force_rebuild();
    }
    cpuset_update_active_cpus();
}

static int cpuset_cpu_inactive(unsigned int cpu)
{
    if (!cpuhp_tasks_frozen) {
        int ret = dl_cpu_busy(cpu, NULL);
        if (ret) {
            return ret;
        }
        cpuset_update_active_cpus();
    } else {
        num_cpus_frozen++;
        partition_sched_domains(1, NULL, NULL);
    }
    return 0;
}

int sched_cpu_activate(unsigned int cpu)
{
    struct rq *rq = cpu_rq(cpu);
    struct rq_flags rf;

#ifdef CONFIG_SCHED_SMT
    /*
     * When going up, increment the number of cores with SMT present.
     */
    if (cpumask_weight(cpu_smt_mask(cpu)) == 0x2) {
        static_branch_inc_cpuslocked(&sched_smt_present);
    }
#endif
    set_cpu_active(cpu, true);

    if (sched_smp_initialized) {
        sched_domains_numa_masks_set(cpu);
        cpuset_cpu_active();
    }

    /*
     * Put the rq online, if not already. This happens:
     *
     * 1) In the early boot process, because we build the real domains
     *    after all CPUs have been brought up.
     *
     * 2) At runtime, if cpuset_cpu_active() fails to rebuild the
     *    domains.
     */
    rq_lock_irqsave(rq, &rf);
    if (rq->rd) {
        BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
        set_rq_online(rq);
    }
    rq_unlock_irqrestore(rq, &rf);

    return 0;
}

int sched_cpu_deactivate(unsigned int cpu)
{
    int ret;

    set_cpu_active(cpu, false);
    /*
     * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU
     * users of this state to go away such that all new such users will
     * observe it.
     *
     * Do sync before park smpboot threads to take care the rcu boost case.
     */
    synchronize_rcu();

#ifdef CONFIG_SCHED_SMT
    /*
     * When going down, decrement the number of cores with SMT present.
     */
    if (cpumask_weight(cpu_smt_mask(cpu)) == 0x2) {
        static_branch_dec_cpuslocked(&sched_smt_present);
    }
#endif

    if (!sched_smp_initialized) {
        return 0;
    }

    ret = cpuset_cpu_inactive(cpu);
    if (ret) {
        set_cpu_active(cpu, true);
        return ret;
    }
    sched_domains_numa_masks_clear(cpu);
    return 0;
}

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

    raw_spin_lock_irqsave(&rq->lock, flags);
    set_window_start(rq);
    raw_spin_unlock_irqrestore(&rq->lock, flags);

    rq->calc_load_update = calc_load_update;
    update_max_interval();
}

int sched_cpu_starting(unsigned int cpu)
{
    sched_rq_cpu_starting(cpu);
    sched_tick_start(cpu);
    clear_eas_migration_request(cpu);
    return 0;
}

#ifdef CONFIG_HOTPLUG_CPU
int sched_cpu_dying(unsigned int cpu)
{
    struct rq *rq = cpu_rq(cpu);
    struct rq_flags rf;

    /* Handle pending wakeups and then migrate everything off */
    sched_tick_stop(cpu);

    rq_lock_irqsave(rq, &rf);

    if (rq->rd) {
        BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
        set_rq_offline(rq);
    }
    migrate_tasks(rq, &rf, true);
    BUG_ON(rq->nr_running != 1);
    rq_unlock_irqrestore(rq, &rf);

    clear_eas_migration_request(cpu);

    calc_load_migrate(rq);
    update_max_interval();
    nohz_balance_exit_idle(rq);
    hrtick_clear(rq);
    return 0;
}
#endif

void __init sched_init_smp(void)
{
    sched_init_numa();

    /*
     * There's no userspace yet to cause hotplug operations; hence all the
     * CPU masks are stable and all blatant races in the below code cannot
     * happen.
     */
    mutex_lock(&sched_domains_mutex);
    sched_init_domains(cpu_active_mask);
    mutex_unlock(&sched_domains_mutex);

    update_cluster_topology();

    /* Move init over to a non-isolated CPU */
    if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) <
        0) {
        BUG();
    }
    sched_init_granularity();

    init_sched_rt_class();
    init_sched_dl_class();

    sched_smp_initialized = true;
}

static int __init migration_init(void)
{
    sched_cpu_starting(smp_processor_id());
    return 0;
}
early_initcall(migration_init);

#else
void __init sched_init_smp(void)
{
    sched_init_granularity();
}
#endif /* CONFIG_SMP */

int in_sched_functions(unsigned long addr)
{
    return in_lock_functions(addr) ||
           (addr >= (unsigned long)__sched_text_start &&
            addr < (unsigned long)__sched_text_end);
}

#ifdef CONFIG_CGROUP_SCHED
/*
 * Default task group.
 * Every task in system belongs to this group at bootup.
 */
struct task_group root_task_group;
LIST_HEAD(task_groups);

/* Cacheline aligned slab cache for task_group */
static struct kmem_cache *task_group_cache __read_mostly;
#endif

DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
DECLARE_PER_CPU(cpumask_var_t, select_idle_mask);

void __init sched_init(void)
{
    unsigned long ptr = 0;
    int i;

    /* Make sure the linker didn't screw up */
    BUG_ON(&idle_sched_class + 1 != &fair_sched_class ||
           &fair_sched_class + 1 != &rt_sched_class ||
           &rt_sched_class + 1 != &dl_sched_class);
#ifdef CONFIG_SMP
    BUG_ON(&dl_sched_class + 1 != &stop_sched_class);
#endif

    wait_bit_init();

    init_clusters();

#ifdef CONFIG_FAIR_GROUP_SCHED
    ptr += 2 * nr_cpu_ids * sizeof(void **);
#endif
#ifdef CONFIG_RT_GROUP_SCHED
    ptr += 2 * nr_cpu_ids * sizeof(void **);
#endif
    if (ptr) {
        ptr = (unsigned long)kzalloc(ptr, GFP_NOWAIT);

#ifdef CONFIG_FAIR_GROUP_SCHED
        root_task_group.se = (struct sched_entity **)ptr;
        ptr += nr_cpu_ids * sizeof(void **);

        root_task_group.cfs_rq = (struct cfs_rq **)ptr;
        ptr += nr_cpu_ids * sizeof(void **);

        root_task_group.shares = ROOT_TASK_GROUP_LOAD;
        init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
        root_task_group.rt_se = (struct sched_rt_entity **)ptr;
        ptr += nr_cpu_ids * sizeof(void **);

        root_task_group.rt_rq = (struct rt_rq **)ptr;
        ptr += nr_cpu_ids * sizeof(void **);

#endif /* CONFIG_RT_GROUP_SCHED */
    }
#ifdef CONFIG_CPUMASK_OFFSTACK
    for_each_possible_cpu(i)
    {
        per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
            cpumask_size(), GFP_KERNEL, cpu_to_node(i));
        per_cpu(select_idle_mask, i) = (cpumask_var_t)kzalloc_node(
            cpumask_size(), GFP_KERNEL, cpu_to_node(i));
    }
#endif /* CONFIG_CPUMASK_OFFSTACK */

    init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(),
                      global_rt_runtime());
    init_dl_bandwidth(&def_dl_bandwidth, global_rt_period(),
                      global_rt_runtime());

#ifdef CONFIG_SMP
    init_defrootdomain();
#endif

#ifdef CONFIG_RT_GROUP_SCHED
    init_rt_bandwidth(&root_task_group.rt_bandwidth, global_rt_period(),
                      global_rt_runtime());
#endif /* CONFIG_RT_GROUP_SCHED */

#ifdef CONFIG_CGROUP_SCHED
    task_group_cache = KMEM_CACHE(task_group, 0);

    list_add(&root_task_group.list, &task_groups);
    INIT_LIST_HEAD(&root_task_group.children);
    INIT_LIST_HEAD(&root_task_group.siblings);
    autogroup_init(&init_task);
#endif /* CONFIG_CGROUP_SCHED */

    for_each_possible_cpu(i)
    {
        struct rq *rq;

        rq = cpu_rq(i);
        raw_spin_lock_init(&rq->lock);
        rq->nr_running = 0;
        rq->calc_load_active = 0;
        rq->calc_load_update = jiffies + LOAD_FREQ;
        init_cfs_rq(&rq->cfs);
        init_rt_rq(&rq->rt);
        init_dl_rq(&rq->dl);
#ifdef CONFIG_FAIR_GROUP_SCHED
        INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
        rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
        /*
         * How much CPU bandwidth does root_task_group get?
         *
         * In case of task-groups formed thr' the cgroup filesystem, it
         * gets 100% of the CPU resources in the system. This overall
         * system CPU resource is divided among the tasks of
         * root_task_group and its child task-groups in a fair manner,
         * based on each entity's (task or task-group's) weight
         * (se->load.weight).
         *
         * In other words, if root_task_group has 10 tasks of weight
         * 1024) and two child groups A0 and A1 (of weight 1024 each),
         * then A0's share of the CPU resource is:
         *
         *    A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
         *
         * We achieve this by letting root_task_group's tasks sit
         * directly in rq->cfs (i.e root_task_group->se[] = NULL).
         */
        init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL);
#endif /* CONFIG_FAIR_GROUP_SCHED */

        rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
#ifdef CONFIG_RT_GROUP_SCHED
        init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
#endif
#ifdef CONFIG_SMP
        rq->sd = NULL;
        rq->rd = NULL;
        rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
        rq->balance_callback = NULL;
        rq->active_balance = 0;
        rq->next_balance = jiffies;
        rq->push_cpu = 0;
        rq->cpu = i;
        rq->online = 0;
        rq->idle_stamp = 0;
        rq->avg_idle = 2 * sysctl_sched_migration_cost;
        rq->max_idle_balance_cost = sysctl_sched_migration_cost;
        walt_sched_init_rq(rq);

        INIT_LIST_HEAD(&rq->cfs_tasks);

        rq_attach_root(rq, &def_root_domain);
#ifdef CONFIG_NO_HZ_COMMON
        rq->last_blocked_load_update_tick = jiffies;
        atomic_set(&rq->nohz_flags, 0);

        rq_csd_init(rq, &rq->nohz_csd, nohz_csd_func);
#endif
#endif /* CONFIG_SMP */
        hrtick_rq_init(rq);
        atomic_set(&rq->nr_iowait, 0);
    }

    BUG_ON(alloc_related_thread_groups());
    set_load_weight(&init_task);
    /*
     * The boot idle thread does lazy MMU switching as well:
     */
    mmgrab(&init_mm);
    enter_lazy_tlb(&init_mm, current);

    /*
     * Make us the idle thread. Technically, schedule() should not be
     * called from this thread, however somewhere below it might be,
     * but because we are the idle thread, we just pick up running again
     * when this runqueue becomes "idle".
     */
    init_idle(current, smp_processor_id());
    init_new_task_load(current);

    calc_load_update = jiffies + LOAD_FREQ;

#ifdef CONFIG_SMP
    idle_thread_set_boot_cpu();
#endif
    init_sched_fair_class();

    init_schedstats();

    psi_init();

    init_uclamp();

    scheduler_running = 1;
}

#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
static inline int preempt_count_equals(int preempt_offset)
{
    int nested = preempt_count() + rcu_preempt_depth();

    return (nested == preempt_offset);
}

void __might_sleep(const char *file, int line, int preempt_offset)
{
    /*
     * Blocking primitives will set (and therefore destroy) current->state,
     * since we will exit with TASK_RUNNING make sure we enter with it,
     * otherwise we will destroy state.
     */
    WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change,
              "do not call blocking ops when !TASK_RUNNING; "
              "state=%lx set at [<%p>] %pS\n",
              current->state, (void *)current->task_state_change,
              (void *)current->task_state_change);

    ___might_sleep(file, line, preempt_offset);
}
EXPORT_SYMBOL(__might_sleep);

void ___might_sleep(const char *file, int line, int preempt_offset)
{
    /* Ratelimiting timestamp: */
    static unsigned long prev_jiffy;

    unsigned long preempt_disable_ip;

    /* WARN_ON_ONCE() by default, no rate limit required: */
    rcu_sleep_check();

    if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
         !is_idle_task(current) && !current->non_block_count) ||
        system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
        oops_in_progress) {
        return;
    }

    if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) {
        return;
    }
    prev_jiffy = jiffies;

    /* Save this before calling printk(), since that will clobber it: */
    preempt_disable_ip = get_preempt_disable_ip(current);

    printk(KERN_ERR
           "BUG: sleeping function called from invalid context at %s:%d\n",
           file, line);
    printk(KERN_ERR "in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: "
                    "%d, name: %s\n",
           in_atomic(), irqs_disabled(), current->non_block_count, current->pid,
           current->comm);

    if (task_stack_end_corrupted(current)) {
        printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
    }

    debug_show_held_locks(current);
    if (irqs_disabled()) {
        print_irqtrace_events(current);
    }
    if (IS_ENABLED(CONFIG_DEBUG_PREEMPT) &&
        !preempt_count_equals(preempt_offset)) {
        pr_err("Preemption disabled at:");
        print_ip_sym(KERN_ERR, preempt_disable_ip);
    }
    dump_stack();
    add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
}
EXPORT_SYMBOL(___might_sleep);

void __cant_sleep(const char *file, int line, int preempt_offset)
{
    static unsigned long prev_jiffy;

    if (irqs_disabled()) {
        return;
    }

    if (!IS_ENABLED(CONFIG_PREEMPT_COUNT)) {
        return;
    }

    if (preempt_count() > preempt_offset) {
        return;
    }

    if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) {
        return;
    }
    prev_jiffy = jiffies;

    printk(KERN_ERR "BUG: assuming atomic context at %s:%d\n", file, line);
    printk(KERN_ERR "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
           in_atomic(), irqs_disabled(), current->pid, current->comm);

    debug_show_held_locks(current);
    dump_stack();
    add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
}
EXPORT_SYMBOL_GPL(__cant_sleep);
#endif

#ifdef CONFIG_MAGIC_SYSRQ
void normalize_rt_tasks(void)
{
    struct task_struct *g, *p;
    struct sched_attr attr = {
        .sched_policy = SCHED_NORMAL,
    };

    read_lock(&tasklist_lock);
    for_each_process_thread(g, p)
    {
        /*
         * Only normalize user tasks:
         */
        if (p->flags & PF_KTHREAD) {
            continue;
        }

        p->se.exec_start = 0;
        schedstat_set(p->se.statistics.wait_start, 0);
        schedstat_set(p->se.statistics.sleep_start, 0);
        schedstat_set(p->se.statistics.block_start, 0);

        if (!dl_task(p) && !rt_task(p)) {
            /*
             * Renice negative nice level userspace
             * tasks back to 0:
             */
            if (task_nice(p) < 0) {
                set_user_nice(p, 0);
            }
            continue;
        }

        __sched_setscheduler(p, &attr, false, false);
    }
    read_unlock(&tasklist_lock);
}

#endif /* CONFIG_MAGIC_SYSRQ */

#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB)
/*
 * These functions are only useful for the IA64 MCA handling, or kdb.
 *
 * They can only be called when the whole system has been
 * stopped - every CPU needs to be quiescent, and no scheduling
 * activity can take place. Using them for anything else would
 * be a serious bug, and as a result, they aren't even visible
 * under any other configuration.
 */

/**
 * curr_task - return the current task for a given CPU.
 * @cpu: the processor in question.
 *
 * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
 *
 * Return: The current task for @cpu.
 */
struct task_struct *curr_task(int cpu)
{
    return cpu_curr(cpu);
}

#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */

#ifdef CONFIG_IA64
/**
 * ia64_set_curr_task - set the current task for a given CPU.
 * @cpu: the processor in question.
 * @p: the task pointer to set.
 *
 * Description: This function must only be used when non-maskable interrupts
 * are serviced on a separate stack. It allows the architecture to switch the
 * notion of the current task on a CPU in a non-blocking manner. This function
 * must be called with all CPU's synchronized, and interrupts disabled, the
 * and caller must save the original value of the current task (see
 * curr_task() above) and restore that value before reenabling interrupts and
 * re-starting the system.
 *
 * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
 */
void ia64_set_curr_task(int cpu, struct task_struct *p)
{
    cpu_curr(cpu) = p;
}

#endif

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

static inline void alloc_uclamp_sched_group(struct task_group *tg,
                                            struct task_group *parent)
{
#ifdef CONFIG_UCLAMP_TASK_GROUP
    enum uclamp_id clamp_id;

    cycle_each_clamp_id(clamp_id) {
        uclamp_se_set(&tg->uclamp_req[clamp_id], uclamp_none(clamp_id), false);
        tg->uclamp[clamp_id] = parent->uclamp[clamp_id];
    }
#endif
}

static void sched_free_group(struct task_group *tg)
{
    free_fair_sched_group(tg);
    free_rt_sched_group(tg);
    autogroup_free(tg);
    kmem_cache_free(task_group_cache, tg);
}

/* allocate runqueue etc for a new task group */
struct task_group *sched_create_group(struct task_group *parent)
{
    struct task_group *tg;

    tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
    if (!tg) {
        return ERR_PTR(-ENOMEM);
    }

    if (!alloc_fair_sched_group(tg, parent)) {
        goto err;
    }

    if (!alloc_rt_sched_group(tg, parent)) {
        goto err;
    }

    alloc_uclamp_sched_group(tg, parent);

    return tg;

err:
    sched_free_group(tg);
    return ERR_PTR(-ENOMEM);
}

void sched_online_group(struct task_group *tg, struct task_group *parent)
{
    unsigned long flags;

    spin_lock_irqsave(&task_group_lock, flags);
    list_add_rcu(&tg->list, &task_groups);

    /* Root should already exist: */
    WARN_ON(!parent);

    tg->parent = parent;
    INIT_LIST_HEAD(&tg->children);
    list_add_rcu(&tg->siblings, &parent->children);
    spin_unlock_irqrestore(&task_group_lock, flags);

    online_fair_sched_group(tg);
}

/* rcu callback to free various structures associated with a task group */
static void sched_free_group_rcu(struct rcu_head *rhp)
{
    /* Now it should be safe to free those cfs_rqs: */
    sched_free_group(container_of(rhp, struct task_group, rcu));
}

void sched_destroy_group(struct task_group *tg)
{
    /* Wait for possible concurrent references to cfs_rqs complete: */
    call_rcu(&tg->rcu, sched_free_group_rcu);
}

void sched_offline_group(struct task_group *tg)
{
    unsigned long flags;

    /* End participation in shares distribution: */
    unregister_fair_sched_group(tg);

    spin_lock_irqsave(&task_group_lock, flags);
    list_del_rcu(&tg->list);
    list_del_rcu(&tg->siblings);
    spin_unlock_irqrestore(&task_group_lock, flags);
}

static void sched_change_group(struct task_struct *tsk, int type)
{
    struct task_group *tg;

    /*
     * All callers are synchronized by task_rq_lock(); we do not use RCU
     * which is pointless here. Thus, we pass "true" to task_css_check()
     * to prevent lockdep warnings.
     */
    tg = container_of(task_css_check(tsk, cpu_cgrp_id, true), struct task_group,
                      css);
    tg = autogroup_task_group(tsk, tg);
    tsk->sched_task_group = tg;

#ifdef CONFIG_FAIR_GROUP_SCHED
    if (tsk->sched_class->task_change_group) {
        tsk->sched_class->task_change_group(tsk, type);
    } else
#endif
        set_task_rq(tsk, task_cpu(tsk));
}

/*
 * Change task's runqueue when it moves between groups.
 *
 * The caller of this function should have put the task in its new group by
 * now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect
 * its new group.
 */
void sched_move_task(struct task_struct *tsk)
{
    int queued, running,
        queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
    struct rq_flags rf;
    struct rq *rq;

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

    running = task_current(rq, tsk);
    queued = task_on_rq_queued(tsk);
    if (queued) {
        dequeue_task(rq, tsk, queue_flags);
    }
    if (running) {
        put_prev_task(rq, tsk);
    }

    sched_change_group(tsk, TASK_MOVE_GROUP);

    if (queued) {
        enqueue_task(rq, tsk, queue_flags);
    }
    if (running) {
        set_next_task(rq, tsk);
        /*
         * After changing group, the running task may have joined a
         * throttled one but it's still the running task. Trigger a
         * resched to make sure that task can still run.
         */
        resched_curr(rq);
    }

    task_rq_unlock(rq, tsk, &rf);
}

static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
{
    return css ? container_of(css, struct task_group, css) : NULL;
}

static struct cgroup_subsys_state *
cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
    struct task_group *parent = css_tg(parent_css);
    struct task_group *tg;

    if (!parent) {
        /* This is early initialization for the top cgroup */
        return &root_task_group.css;
    }

    tg = sched_create_group(parent);
    if (IS_ERR(tg)) {
        return ERR_PTR(-ENOMEM);
    }

#ifdef CONFIG_SCHED_RTG_CGROUP
    tg->colocate = false;
    tg->colocate_update_disabled = false;
#endif

    return &tg->css;
}

/* Expose task group only after completing cgroup initialization */
static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
{
    struct task_group *tg = css_tg(css);
    struct task_group *parent = css_tg(css->parent);

    if (parent) {
        sched_online_group(tg, parent);
    }

#ifdef CONFIG_UCLAMP_TASK_GROUP
    /* Propagate the effective uclamp value for the new group */
    mutex_lock(&uclamp_mutex);
    rcu_read_lock();
    cpu_util_update_eff(css);
    rcu_read_unlock();
    mutex_unlock(&uclamp_mutex);
#endif

    return 0;
}

static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
{
    struct task_group *tg = css_tg(css);

    sched_offline_group(tg);
}

static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
{
    struct task_group *tg = css_tg(css);

    /*
     * Relies on the RCU grace period between css_released() and this.
     */
    sched_free_group(tg);
}

/*
 * This is called before wake_up_new_task(), therefore we really only
 * have to set its group bits, all the other stuff does not apply.
 */
static void cpu_cgroup_fork(struct task_struct *task)
{
    struct rq_flags rf;
    struct rq *rq;

    rq = task_rq_lock(task, &rf);

    update_rq_clock(rq);
    sched_change_group(task, TASK_SET_GROUP);

    task_rq_unlock(rq, task, &rf);
}

static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
{
    struct task_struct *task;
    struct cgroup_subsys_state *css;
    int ret = 0;

    cgroup_taskset_for_each(task, css, tset)
    {
#ifdef CONFIG_RT_GROUP_SCHED
        if (!sched_rt_can_attach(css_tg(css), task)) {
            return -EINVAL;
        }
#endif
        /*
         * Serialize against wake_up_new_task() such that if its
         * running, we're sure to observe its full state.
         */
        raw_spin_lock_irq(&task->pi_lock);
        /*
         * Avoid calling sched_move_task() before wake_up_new_task()
         * has happened. This would lead to problems with PELT, due to
         * move wanting to detach+attach while we're not attached yet.
         */
        if (task->state == TASK_NEW) {
            ret = -EINVAL;
        }
        raw_spin_unlock_irq(&task->pi_lock);

        if (ret) {
            break;
        }
    }
    return ret;
}

#if defined(CONFIG_UCLAMP_TASK_GROUP) && defined(CONFIG_SCHED_RTG_CGROUP)
static void schedgp_attach(struct cgroup_taskset *tset)
{
    struct task_struct *task;
    struct cgroup_subsys_state *css;
    bool colocate;
    struct task_group *tg;

    cgroup_taskset_first(tset, &css);
    tg = css_tg(css);

    colocate = tg->colocate;

    cgroup_taskset_for_each(task, css, tset)
        sync_cgroup_colocation(task, colocate);
}
#else
static void schedgp_attach(struct cgroup_taskset *tset)
{
}
#endif
static void cpu_cgroup_attach(struct cgroup_taskset *tset)
{
    struct task_struct *task;
    struct cgroup_subsys_state *css;

    cgroup_taskset_for_each(task, css, tset) sched_move_task(task);

    schedgp_attach(tset);
}

#ifdef CONFIG_UCLAMP_TASK_GROUP
static void cpu_util_update_eff(struct cgroup_subsys_state *css)
{
    struct cgroup_subsys_state *top_css = css;
    struct uclamp_se *uc_parent = NULL;
    struct uclamp_se *uc_se = NULL;
    unsigned int eff[UCLAMP_CNT];
    enum uclamp_id clamp_id;
    unsigned int clamps;

    lockdep_assert_held(&uclamp_mutex);
    SCHED_WARN_ON(!rcu_read_lock_held());

    css_for_each_descendant_pre(css, top_css)
    {
        uc_parent = css_tg(css)->parent ? css_tg(css)->parent->uclamp : NULL;

        cycle_each_clamp_id(clamp_id) {
            /* Assume effective clamps matches requested clamps */
            eff[clamp_id] = css_tg(css)->uclamp_req[clamp_id].value;
            /* Cap effective clamps with parent's effective clamps */
            if (uc_parent && eff[clamp_id] > uc_parent[clamp_id].value) {
                eff[clamp_id] = uc_parent[clamp_id].value;
            }
        }
        /* Ensure protection is always capped by limit */
        eff[UCLAMP_MIN] = min(eff[UCLAMP_MIN], eff[UCLAMP_MAX]);

        /* Propagate most restrictive effective clamps */
        clamps = 0x0;
        uc_se = css_tg(css)->uclamp;
        cycle_each_clamp_id(clamp_id) {
            if (eff[clamp_id] == uc_se[clamp_id].value) {
                continue;
            }
            uc_se[clamp_id].value = eff[clamp_id];
            uc_se[clamp_id].bucket_id = uclamp_bucket_id(eff[clamp_id]);
            clamps |= (0x1 << clamp_id);
        }
        if (!clamps) {
            css = css_rightmost_descendant(css);
            continue;
        }

        /* Immediately update descendants RUNNABLE tasks */
        uclamp_update_active_tasks(css);
    }
}

/*
 * Integer 10^N with a given N exponent by casting to integer the literal "1eN"
 * C expression. Since there is no way to convert a macro argument (N) into a
 * character constant, use two levels of macros.
 */
#define EXP_POW10(exp) ((unsigned int)1e##exp)
#define POW10(exp) EXP_POW10(exp)

struct uclamp_request {
#define UCLAMP_PERCENT_SHIFT 2
#define UCLAMP_PERCENT_SCALE (100 * POW10(UCLAMP_PERCENT_SHIFT))
    s64 percent;
    u64 util;
    int ret;
};

static inline struct uclamp_request capacity_from_percent(char *buf)
{
    struct uclamp_request req = {
        .percent = UCLAMP_PERCENT_SCALE,
        .util = SCHED_CAPACITY_SCALE,
        .ret = 0,
    };

    buf = strim(buf);
    if (strcmp(buf, "max")) {
        req.ret = cgroup_parse_float(buf, UCLAMP_PERCENT_SHIFT, &req.percent);
        if (req.ret) {
            return req;
        }
        if ((u64)req.percent > UCLAMP_PERCENT_SCALE) {
            req.ret = -ERANGE;
            return req;
        }

        req.util = req.percent << SCHED_CAPACITY_SHIFT;
        req.util = DIV_ROUND_CLOSEST_ULL(req.util, UCLAMP_PERCENT_SCALE);
    }

    return req;
}

static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
                                size_t nbytes, loff_t off,
                                enum uclamp_id clamp_id)
{
    struct uclamp_request req;
    struct task_group *tg;

    req = capacity_from_percent(buf);
    if (req.ret) {
        return req.ret;
    }

    static_branch_enable(&sched_uclamp_used);

    mutex_lock(&uclamp_mutex);
    rcu_read_lock();

    tg = css_tg(of_css(of));
    if (tg->uclamp_req[clamp_id].value != req.util) {
        uclamp_se_set(&tg->uclamp_req[clamp_id], req.util, false);
    }

    /*
     * Because of not recoverable conversion rounding we keep track of the
     * exact requested value
     */
    tg->uclamp_pct[clamp_id] = req.percent;

    /* Update effective clamps to track the most restrictive value */
    cpu_util_update_eff(of_css(of));

    rcu_read_unlock();
    mutex_unlock(&uclamp_mutex);

    return nbytes;
}

static ssize_t cpu_uclamp_min_write(struct kernfs_open_file *of, char *buf,
                                    size_t nbytes, loff_t off)
{
    return cpu_uclamp_write(of, buf, nbytes, off, UCLAMP_MIN);
}

static ssize_t cpu_uclamp_max_write(struct kernfs_open_file *of, char *buf,
                                    size_t nbytes, loff_t off)
{
    return cpu_uclamp_write(of, buf, nbytes, off, UCLAMP_MAX);
}

static inline void cpu_uclamp_print(struct seq_file *sf,
                                    enum uclamp_id clamp_id)
{
    struct task_group *tg;
    u64 util_clamp;
    u64 percent;
    u32 rem;

    rcu_read_lock();
    tg = css_tg(seq_css(sf));
    util_clamp = tg->uclamp_req[clamp_id].value;
    rcu_read_unlock();

    if (util_clamp == SCHED_CAPACITY_SCALE) {
        seq_puts(sf, "max\n");
        return;
    }

    percent = tg->uclamp_pct[clamp_id];
    percent = div_u64_rem(percent, POW10(UCLAMP_PERCENT_SHIFT), &rem);
    seq_printf(sf, "%llu.%0*u\n", percent, UCLAMP_PERCENT_SHIFT, rem);
}

static int cpu_uclamp_min_show(struct seq_file *sf, void *v)
{
    cpu_uclamp_print(sf, UCLAMP_MIN);
    return 0;
}

static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
{
    cpu_uclamp_print(sf, UCLAMP_MAX);
    return 0;
}

#ifdef CONFIG_SCHED_RTG_CGROUP
static u64 sched_colocate_read(struct cgroup_subsys_state *css,
                               struct cftype *cft)
{
    struct task_group *tg = css_tg(css);

    return (u64)tg->colocate;
}

static int sched_colocate_write(struct cgroup_subsys_state *css,
                                struct cftype *cft, u64 colocate)
{
    struct task_group *tg = css_tg(css);

    if (tg->colocate_update_disabled) {
        return -EPERM;
    }

    tg->colocate = !!colocate;
    tg->colocate_update_disabled = true;

    return 0;
}
#endif /* CONFIG_SCHED_RTG_CGROUP */
#endif /* CONFIG_UCLAMP_TASK_GROUP */

#ifdef CONFIG_FAIR_GROUP_SCHED
static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
                                struct cftype *cftype, u64 shareval)
{
    if (shareval > scale_load_down(ULONG_MAX)) {
        shareval = MAX_SHARES;
    }
    return sched_group_set_shares(css_tg(css), scale_load(shareval));
}

static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
                               struct cftype *cft)
{
    struct task_group *tg = css_tg(css);

    return (u64)scale_load_down(tg->shares);
}

#ifdef CONFIG_CFS_BANDWIDTH
static DEFINE_MUTEX(cfs_constraints_mutex);

const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC;         /* 1s */
static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
/* More than 203 days if BW_SHIFT equals 20. */
static const u64 max_cfs_runtime = MAX_BW * NSEC_PER_USEC;

static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);

static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
{
    int i, ret = 0, runtime_enabled, runtime_was_enabled;
    struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;

    if (tg == &root_task_group) {
        return -EINVAL;
    }

    /*
     * Ensure we have at some amount of bandwidth every period.  This is
     * to prevent reaching a state of large arrears when throttled via
     * entity_tick() resulting in prolonged exit starvation.
     */
    if (quota < min_cfs_quota_period || period < min_cfs_quota_period) {
        return -EINVAL;
    }

    /*
     * Likewise, bound things on the otherside by preventing insane quota
     * periods.  This also allows us to normalize in computing quota
     * feasibility.
     */
    if (period > max_cfs_quota_period) {
        return -EINVAL;
    }

    /*
     * Bound quota to defend quota against overflow during bandwidth shift.
     */
    if (quota != RUNTIME_INF && quota > max_cfs_runtime) {
        return -EINVAL;
    }

    /*
     * Prevent race between setting of cfs_rq->runtime_enabled and
     * unthrottle_offline_cfs_rqs().
     */
    get_online_cpus();
    mutex_lock(&cfs_constraints_mutex);
    ret = __cfs_schedulable(tg, period, quota);
    if (ret) {
        goto out_unlock;
    }

    runtime_enabled = quota != RUNTIME_INF;
    runtime_was_enabled = cfs_b->quota != RUNTIME_INF;
    /*
     * If we need to toggle cfs_bandwidth_used, off->on must occur
     * before making related changes, and on->off must occur afterwards
     */
    if (runtime_enabled && !runtime_was_enabled) {
        cfs_bandwidth_usage_inc();
    }
    raw_spin_lock_irq(&cfs_b->lock);
    cfs_b->period = ns_to_ktime(period);
    cfs_b->quota = quota;

    __refill_cfs_bandwidth_runtime(cfs_b);

    /* Restart the period timer (if active) to handle new period expiry: */
    if (runtime_enabled) {
        start_cfs_bandwidth(cfs_b);
    }

    raw_spin_unlock_irq(&cfs_b->lock);

    for_each_online_cpu(i)
    {
        struct cfs_rq *cfs_rq = tg->cfs_rq[i];
        struct rq *rq = cfs_rq->rq;
        struct rq_flags rf;

        rq_lock_irq(rq, &rf);
        cfs_rq->runtime_enabled = runtime_enabled;
        cfs_rq->runtime_remaining = 0;

        if (cfs_rq->throttled) {
            unthrottle_cfs_rq(cfs_rq);
        }
        rq_unlock_irq(rq, &rf);
    }
    if (runtime_was_enabled && !runtime_enabled) {
        cfs_bandwidth_usage_dec();
    }
out_unlock:
    mutex_unlock(&cfs_constraints_mutex);
    put_online_cpus();

    return ret;
}

static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
{
    u64 quota, period;

    period = ktime_to_ns(tg->cfs_bandwidth.period);
    if (cfs_quota_us < 0) {
        quota = RUNTIME_INF;
    } else if ((u64)cfs_quota_us <= U64_MAX / NSEC_PER_USEC) {
        quota = (u64)cfs_quota_us * NSEC_PER_USEC;
    } else {
        return -EINVAL;
    }

    return tg_set_cfs_bandwidth(tg, period, quota);
}

static long tg_get_cfs_quota(struct task_group *tg)
{
    u64 quota_us;

    if (tg->cfs_bandwidth.quota == RUNTIME_INF) {
        return -1;
    }

    quota_us = tg->cfs_bandwidth.quota;
    do_div(quota_us, NSEC_PER_USEC);

    return quota_us;
}

static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
{
    u64 quota, period;

    if ((u64)cfs_period_us > U64_MAX / NSEC_PER_USEC) {
        return -EINVAL;
    }

    period = (u64)cfs_period_us * NSEC_PER_USEC;
    quota = tg->cfs_bandwidth.quota;

    return tg_set_cfs_bandwidth(tg, period, quota);
}

static long tg_get_cfs_period(struct task_group *tg)
{
    u64 cfs_period_us;

    cfs_period_us = ktime_to_ns(tg->cfs_bandwidth.period);
    do_div(cfs_period_us, NSEC_PER_USEC);

    return cfs_period_us;
}

static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css,
                                  struct cftype *cft)
{
    return tg_get_cfs_quota(css_tg(css));
}

static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css,
                                   struct cftype *cftype, s64 cfs_quota_us)
{
    return tg_set_cfs_quota(css_tg(css), cfs_quota_us);
}

static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css,
                                   struct cftype *cft)
{
    return tg_get_cfs_period(css_tg(css));
}

static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css,
                                    struct cftype *cftype, u64 cfs_period_us)
{
    return tg_set_cfs_period(css_tg(css), cfs_period_us);
}

struct cfs_schedulable_data {
    struct task_group *tg;
    u64 period, quota;
};

/*
 * normalize group quota/period to be quota/max_period
 * note: units are usecs
 */
static u64 normalize_cfs_quota(struct task_group *tg,
                               struct cfs_schedulable_data *d)
{
    u64 quota, period;

    if (tg == d->tg) {
        period = d->period;
        quota = d->quota;
    } else {
        period = tg_get_cfs_period(tg);
        quota = tg_get_cfs_quota(tg);
    }

    /* note: these should typically be equivalent */
    if (quota == RUNTIME_INF || quota == -1) {
        return RUNTIME_INF;
    }

    return to_ratio(period, quota);
}

static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
{
    struct cfs_schedulable_data *d = data;
    struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
    s64 quota = 0, parent_quota = -1;

    if (!tg->parent) {
        quota = RUNTIME_INF;
    } else {
        struct cfs_bandwidth *parent_b = &tg->parent->cfs_bandwidth;

        quota = normalize_cfs_quota(tg, d);
        parent_quota = parent_b->hierarchical_quota;

        /*
         * Ensure max(child_quota) <= parent_quota.  On cgroup2,
         * always take the min.  On cgroup1, only inherit when no
         * limit is set:
         */
        if (cgroup_subsys_on_dfl(cpu_cgrp_subsys)) {
            quota = min(quota, parent_quota);
        } else {
            if (quota == RUNTIME_INF) {
                quota = parent_quota;
            } else if (parent_quota != RUNTIME_INF && quota > parent_quota) {
                return -EINVAL;
            }
        }
    }
    cfs_b->hierarchical_quota = quota;

    return 0;
}

static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
{
    int ret;
    struct cfs_schedulable_data data = {
        .tg = tg,
        .period = period,
        .quota = quota,
    };

    if (quota != RUNTIME_INF) {
        do_div(data.period, NSEC_PER_USEC);
        do_div(data.quota, NSEC_PER_USEC);
    }

    rcu_read_lock();
    ret = walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data);
    rcu_read_unlock();

    return ret;
}

static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
{
    struct task_group *tg = css_tg(seq_css(sf));
    struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;

    seq_printf(sf, "nr_periods %d\n", cfs_b->nr_periods);
    seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled);
    seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);

    if (schedstat_enabled() && tg != &root_task_group) {
        u64 ws = 0;
        int i;

        for_each_possible_cpu(i) ws +=
            schedstat_val(tg->se[i]->statistics.wait_sum);

        seq_printf(sf, "wait_sum %llu\n", ws);
    }

    return 0;
}
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */

#ifdef CONFIG_RT_GROUP_SCHED
static int cpu_rt_runtime_write(struct cgroup_subsys_state *css,
                                struct cftype *cft, s64 val)
{
    return sched_group_set_rt_runtime(css_tg(css), val);
}

static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css,
                               struct cftype *cft)
{
    return sched_group_rt_runtime(css_tg(css));
}

static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css,
                                    struct cftype *cftype, u64 rt_period_us)
{
    return sched_group_set_rt_period(css_tg(css), rt_period_us);
}

static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
                                   struct cftype *cft)
{
    return sched_group_rt_period(css_tg(css));
}
#endif /* CONFIG_RT_GROUP_SCHED */

static struct cftype cpu_legacy_files[] = {
#ifdef CONFIG_FAIR_GROUP_SCHED
    {
        .name = "shares",
        .read_u64 = cpu_shares_read_u64,
        .write_u64 = cpu_shares_write_u64,
    },
#endif
#ifdef CONFIG_CFS_BANDWIDTH
    {
        .name = "cfs_quota_us",
        .read_s64 = cpu_cfs_quota_read_s64,
        .write_s64 = cpu_cfs_quota_write_s64,
    },
    {
        .name = "cfs_period_us",
        .read_u64 = cpu_cfs_period_read_u64,
        .write_u64 = cpu_cfs_period_write_u64,
    },
    {
        .name = "stat",
        .seq_show = cpu_cfs_stat_show,
    },
#endif
#ifdef CONFIG_RT_GROUP_SCHED
    {
        .name = "rt_runtime_us",
        .read_s64 = cpu_rt_runtime_read,
        .write_s64 = cpu_rt_runtime_write,
    },
    {
        .name = "rt_period_us",
        .read_u64 = cpu_rt_period_read_uint,
        .write_u64 = cpu_rt_period_write_uint,
    },
#endif
#ifdef CONFIG_UCLAMP_TASK_GROUP
    {
        .name = "uclamp.min",
        .flags = CFTYPE_NOT_ON_ROOT,
        .seq_show = cpu_uclamp_min_show,
        .write = cpu_uclamp_min_write,
    },
    {
        .name = "uclamp.max",
        .flags = CFTYPE_NOT_ON_ROOT,
        .seq_show = cpu_uclamp_max_show,
        .write = cpu_uclamp_max_write,
    },
#ifdef CONFIG_SCHED_RTG_CGROUP
    {
        .name = "uclamp.colocate",
        .flags = CFTYPE_NOT_ON_ROOT,
        .read_u64 = sched_colocate_read,
        .write_u64 = sched_colocate_write,
    },
#endif
#endif
    {} /* Terminate */
};

static int cpu_extra_stat_show(struct seq_file *sf,
                               struct cgroup_subsys_state *css)
{
#ifdef CONFIG_CFS_BANDWIDTH
    {
        struct task_group *tg = css_tg(css);
        struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
        u64 throttled_usec;

        throttled_usec = cfs_b->throttled_time;
        do_div(throttled_usec, NSEC_PER_USEC);

        seq_printf(sf,
                   "nr_periods %d\n"
                   "nr_throttled %d\n"
                   "throttled_usec %llu\n",
                   cfs_b->nr_periods, cfs_b->nr_throttled, throttled_usec);
    }
#endif
    return 0;
}

#ifdef CONFIG_FAIR_GROUP_SCHED
static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
                               struct cftype *cft)
{
    struct task_group *tg = css_tg(css);
    u64 weight = scale_load_down(tg->shares);

    return DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 0x400);
}

static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
                                struct cftype *cft, u64 weight)
{
    /*
     * cgroup weight knobs should use the common MIN, DFL and MAX
     * values which are 1, 100 and 10000 respectively.  While it loses
     * a bit of range on both ends, it maps pretty well onto the shares
     * value used by scheduler and the round-trip conversions preserve
     * the original value over the entire range.
     */
    if (weight < CGROUP_WEIGHT_MIN || weight > CGROUP_WEIGHT_MAX) {
        return -ERANGE;
    }

    weight = DIV_ROUND_CLOSEST_ULL(weight * 0x400, CGROUP_WEIGHT_DFL);

    return sched_group_set_shares(css_tg(css), scale_load(weight));
}

static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
                                    struct cftype *cft)
{
    unsigned long weight = scale_load_down(css_tg(css)->shares);
    int last_delta = INT_MAX;
    int prio, delta;

    /* find the closest nice value to the current weight */
    for (prio = 0; prio < ARRAY_SIZE(sched_prio_to_weight); prio++) {
        delta = abs(sched_prio_to_weight[prio] - weight);
        if (delta >= last_delta) {
            break;
        }
        last_delta = delta;
    }

    return PRIO_TO_NICE(prio - 1 + MAX_RT_PRIO);
}

static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
                                     struct cftype *cft, s64 nice)
{
    unsigned long weight;
    int idx;

    if (nice < MIN_NICE || nice > MAX_NICE) {
        return -ERANGE;
    }

    idx = NICE_TO_PRIO(nice) - MAX_RT_PRIO;
    idx = array_index_nospec(idx, 0x28);
    weight = sched_prio_to_weight[idx];

    return sched_group_set_shares(css_tg(css), scale_load(weight));
}
#endif

static void __maybe_unused cpu_period_quota_print(struct seq_file *sf,
                                                  long period, long quota)
{
    if (quota < 0) {
        seq_puts(sf, "max");
    } else {
        seq_printf(sf, "%ld", quota);
    }

    seq_printf(sf, " %ld\n", period);
}

/* caller should put the current value in *@periodp before calling */
static int __maybe_unused cpu_period_quota_parse(char *buf, u64 *periodp,
                                                 u64 *quotap)
{
    char tok[21]; /* U64_MAX */

    if (sscanf(buf, "%20s %llu", tok, periodp) < 1) {
        return -EINVAL;
    }

    *periodp *= NSEC_PER_USEC;

    if (sscanf(tok, "%llu", quotap)) {
        *quotap *= NSEC_PER_USEC;
    } else if (!strcmp(tok, "max")) {
        *quotap = RUNTIME_INF;
    } else {
        return -EINVAL;
    }

    return 0;
}

#ifdef CONFIG_CFS_BANDWIDTH
static int cpu_max_show(struct seq_file *sf, void *v)
{
    struct task_group *tg = css_tg(seq_css(sf));

    cpu_period_quota_print(sf, tg_get_cfs_period(tg), tg_get_cfs_quota(tg));
    return 0;
}

static ssize_t cpu_max_write(struct kernfs_open_file *of, char *buf,
                             size_t nbytes, loff_t off)
{
    struct task_group *tg = css_tg(of_css(of));
    u64 period = tg_get_cfs_period(tg);
    u64 quota;
    int ret;

    ret = cpu_period_quota_parse(buf, &period, &quota);
    if (!ret) {
        ret = tg_set_cfs_bandwidth(tg, period, quota);
    }
    return ret ?: nbytes;
}
#endif

static struct cftype cpu_files[] = {
#ifdef CONFIG_FAIR_GROUP_SCHED
    {
        .name = "weight",
        .flags = CFTYPE_NOT_ON_ROOT,
        .read_u64 = cpu_weight_read_u64,
        .write_u64 = cpu_weight_write_u64,
    },
    {
        .name = "weight.nice",
        .flags = CFTYPE_NOT_ON_ROOT,
        .read_s64 = cpu_weight_nice_read_s64,
        .write_s64 = cpu_weight_nice_write_s64,
    },
#endif
#ifdef CONFIG_CFS_BANDWIDTH
    {
        .name = "max",
        .flags = CFTYPE_NOT_ON_ROOT,
        .seq_show = cpu_max_show,
        .write = cpu_max_write,
    },
#endif
#ifdef CONFIG_UCLAMP_TASK_GROUP
    {
        .name = "uclamp.min",
        .flags = CFTYPE_NOT_ON_ROOT,
        .seq_show = cpu_uclamp_min_show,
        .write = cpu_uclamp_min_write,
    },
    {
        .name = "uclamp.max",
        .flags = CFTYPE_NOT_ON_ROOT,
        .seq_show = cpu_uclamp_max_show,
        .write = cpu_uclamp_max_write,
    },
#endif
    {} /* terminate */
};

struct cgroup_subsys cpu_cgrp_subsys = {
    .css_alloc = cpu_cgroup_css_alloc,
    .css_online = cpu_cgroup_css_online,
    .css_released = cpu_cgroup_css_released,
    .css_free = cpu_cgroup_css_free,
    .css_extra_stat_show = cpu_extra_stat_show,
    .fork = cpu_cgroup_fork,
    .can_attach = cpu_cgroup_can_attach,
    .attach = cpu_cgroup_attach,
    .legacy_cftypes = cpu_legacy_files,
    .dfl_cftypes = cpu_files,
    .early_init = true,
    .threaded = true,
};

#endif /* CONFIG_CGROUP_SCHED */

void dump_cpu_task(int cpu)
{
    pr_info("Task dump for CPU %d:\n", cpu);
    sched_show_task(cpu_curr(cpu));
}

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

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

#ifdef CONFIG_SCHED_LATENCY_NICE
/*
 * latency weight for wakeup preemption
 */
const int sched_latency_to_weight[40] = {
    1024, 973,  922,  870,  819,  /* -20 */
    768,  717,  666,  614,  563,  /* -15 */
    512,  461,  410,  358,  307,  /* -10 */
    256,  205,  154,  102,  51,   /*  -5 */
    0,    -51,  -102, -154, -205, /*   0 */
    -256, -307, -358, -410, -461, /*   5 */
    -512, -563, -614, -666, -717, /*  10 */
    -768, -819, -870, -922, -973, /*  15 */
};
#endif

void call_trace_sched_update_nr_running(struct rq *rq, int count)
{
    trace_sched_update_nr_running_tp(rq, count);
}

#ifdef CONFIG_SCHED_WALT
/*
 * sched_exit() - Set EXITING_TASK_MARKER in task's ravg.demand field
 *
 * Stop accounting (exiting) task's future cpu usage
 *
 * We need this so that reset_all_windows_stats() can function correctly.
 * reset_all_window_stats() depends on do_each_thread/for_each_thread task
 * iterators to reset *all* task's statistics. Exiting tasks however become
 * invisible to those iterators. sched_exit() is called on a exiting task prior
 * to being removed from task_list, which will let reset_all_window_stats()
 * function correctly.
 */
void sched_exit(struct task_struct *p)
{
    struct rq_flags rf;
    struct rq *rq;
    u64 wallclock;

#ifdef CONFIG_SCHED_RTG
    sched_set_group_id(p, 0);
#endif

    rq = task_rq_lock(p, &rf);

    /* rq->curr == p */
    wallclock = sched_ktime_clock();
    update_task_ravg(rq->curr, rq, TASK_UPDATE, wallclock, 0);
    dequeue_task(rq, p, 0);
    /*
     * task's contribution is already removed from the
     * cumulative window demand in dequeue. As the
     * task's stats are reset, the next enqueue does
     * not change the cumulative window demand.
     */
    reset_task_stats(p);
    p->ravg.mark_start = wallclock;
    p->ravg.sum_history[0] = EXITING_TASK_MARKER;

    enqueue_task(rq, p, 0);
    task_rq_unlock(rq, p, &rf);
    free_task_load_ptrs(p);
}
#endif /* CONFIG_SCHED_WALT */