sched/fair: Reorder cgroup creation code

[deliverable/linux.git] / kernel / sched / core.c

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

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

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

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

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

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

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

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

        lockdep_assert_held(&rq->lock);

        if (rq->clock_skip_update & RQCF_ACT_SKIP)
                return;

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

/*
 * Debugging: various feature bits
 */

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

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

#undef SCHED_FEAT

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

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

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

__read_mostly int scheduler_running;

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

/* cpus with isolated domains */
cpumask_var_t cpu_isolated_map;

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

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

        return rq;
}

/*
 * __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))) {
                        rf->cookie = lockdep_pin_lock(&rq->lock);
                        return rq;
                }
                raw_spin_unlock(&rq->lock);

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

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

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

#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);

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

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

        return HRTIMER_NORESTART;
}

#ifdef CONFIG_SMP

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

        hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
}

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

        raw_spin_lock(&rq->lock);
        __hrtick_restart(rq);
        rq->hrtick_csd_pending = 0;
        raw_spin_unlock(&rq->lock);
}

/*
 * Called to set the hrtick timer state.
 *
 * called with rq->lock held and irqs disabled
 */
void hrtick_start(struct rq *rq, u64 delay)
{
        struct hrtimer *timer = &rq->hrtick_timer;
        ktime_t time;
        s64 delta;

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

        hrtimer_set_expires(timer, time);

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

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

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

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

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

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

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

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

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

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

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

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

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

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

        get_task_struct(task);

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

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

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

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

                /*
                 * wake_up_process() implies a wmb() to pair 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;

        if (!raw_spin_trylock_irqsave(&rq->lock, flags))
                return;
        resched_curr(rq);
        raw_spin_unlock_irqrestore(&rq->lock, flags);
}

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

        if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu))
                return cpu;

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

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

        if (!is_housekeeping_cpu(cpu))
                cpu = housekeeping_any_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 (tick_nohz_full_cpu(cpu)) {
                if (cpu != smp_processor_id() ||
                    tick_nohz_tick_stopped())
                        tick_nohz_full_kick_cpu(cpu);
                return true;
        }

        return false;
}

void wake_up_nohz_cpu(int cpu)
{
        if (!wake_up_full_nohz_cpu(cpu))
                wake_up_idle_cpu(cpu);
}

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

        if (!test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)))
                return false;

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

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

#else /* CONFIG_NO_HZ_COMMON */

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

#endif /* CONFIG_NO_HZ_COMMON */

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

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

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

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

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

        return true;
}
#endif /* CONFIG_NO_HZ_FULL */

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

        while ((s64)(rq_clock(rq) - rq->age_stamp) > period) {
                /*
                 * Inline assembly required to prevent the compiler
                 * optimising this loop into a divmod call.
                 * See __iter_div_u64_rem() for another example of this.
                 */
                asm("" : "+rm" (rq->age_stamp));
                rq->age_stamp += period;
                rq->rt_avg /= 2;
        }
}

#endif /* CONFIG_SMP */

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

        parent = from;

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

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

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

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

static void set_load_weight(struct task_struct *p)
{
        int prio = p->static_prio - MAX_RT_PRIO;
        struct load_weight *load = &p->se.load;

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

        load->weight = scale_load(sched_prio_to_weight[prio]);
        load->inv_weight = sched_prio_to_wmult[prio];
}

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

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

void activate_task(struct rq *rq, struct task_struct *p, int flags)
{
        if (task_contributes_to_load(p))
                rq->nr_uninterruptible--;

        enqueue_task(rq, p, flags);
}

void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
{
        if (task_contributes_to_load(p))
                rq->nr_uninterruptible++;

        dequeue_task(rq, p, flags);
}

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

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

        rq->prev_irq_time += irq_delta;
        delta -= irq_delta;
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
        if (static_key_false((&paravirt_steal_rq_enabled))) {
                steal = paravirt_steal_clock(cpu_of(rq));
                steal -= rq->prev_steal_time_rq;

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

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

        rq->clock_task += delta;

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

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

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

                stop->sched_class = &stop_sched_class;
        }

        cpu_rq(cpu)->stop = stop;

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

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

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

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

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

/**
 * task_curr - is this task currently executing on a CPU?
 * @p: the task in question.
 *
 * Return: 1 if the task is currently executing. 0 otherwise.
 */
inline int task_curr(const struct task_struct *p)
{
        return cpu_curr(task_cpu(p)) == p;
}

/*
 * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock,
 * use the balance_callback list if you want balancing.
 *
 * this means any call to check_class_changed() must be followed by a call to
 * balance_callback().
 */
static inline void check_class_changed(struct rq *rq, struct task_struct *p,
                                       const struct sched_class *prev_class,
                                       int oldprio)
{
        if (prev_class != p->sched_class) {
                if (prev_class->switched_from)
                        prev_class->switched_from(rq, p);

                p->sched_class->switched_to(rq, p);
        } else if (oldprio != p->prio || dl_task(p))
                p->sched_class->prio_changed(rq, p, oldprio);
}

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

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

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

#ifdef CONFIG_SMP
/*
 * 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 task_struct *p, int new_cpu)
{
        lockdep_assert_held(&rq->lock);

        p->on_rq = TASK_ON_RQ_MIGRATING;
        dequeue_task(rq, p, 0);
        set_task_cpu(p, new_cpu);
        raw_spin_unlock(&rq->lock);

        rq = cpu_rq(new_cpu);

        raw_spin_lock(&rq->lock);
        BUG_ON(task_cpu(p) != new_cpu);
        enqueue_task(rq, p, 0);
        p->on_rq = TASK_ON_RQ_QUEUED;
        check_preempt_curr(rq, p, 0);

        return rq;
}

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

/*
 * Move (not current) task off this cpu, onto dest 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 task_struct *p, int dest_cpu)
{
        if (unlikely(!cpu_active(dest_cpu)))
                return rq;

        /* Affinity changed (again). */
        if (!cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
                return rq;

        rq = move_queued_task(rq, 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();

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

        raw_spin_lock(&p->pi_lock);
        raw_spin_lock(&rq->lock);
        /*
         * 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 && task_on_rq_queued(p))
                rq = __migrate_task(rq, p, arg->dest_cpu);
        raw_spin_unlock(&rq->lock);
        raw_spin_unlock(&p->pi_lock);

        local_irq_enable();
        return 0;
}

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

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

        lockdep_assert_held(&p->pi_lock);

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

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

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

        if (running)
                p->sched_class->set_curr_task(rq);
        if (queued)
                enqueue_task(rq, p, ENQUEUE_RESTORE);
}

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

        rq = task_rq_lock(p, &rf);

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

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

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

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

        do_set_cpus_allowed(p, new_mask);

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

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

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

        __set_task_cpu(p, new_cpu);
}

static void __migrate_swap_task(struct task_struct *p, int cpu)
{
        if (task_on_rq_queued(p)) {
                struct rq *src_rq, *dst_rq;

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

                p->on_rq = TASK_ON_RQ_MIGRATING;
                deactivate_task(src_rq, p, 0);
                set_task_cpu(p, cpu);
                activate_task(dst_rq, p, 0);
                p->on_rq = TASK_ON_RQ_QUEUED;
                check_preempt_curr(dst_rq, p, 0);
        } 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 targer 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, tsk_cpus_allowed(arg->src_task)))
                goto unlock;

        if (!cpumask_test_cpu(arg->src_cpu, tsk_cpus_allowed(arg->dst_task)))
                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)
{
        struct migration_swap_arg arg;
        int ret = -EINVAL;

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

        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, tsk_cpus_allowed(arg.src_task)))
                goto out;

        if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task)))
                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;
}

/*
 * 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 = ktime_set(0, NSEC_PER_SEC/HZ);

                        set_current_state(TASK_UNINTERRUPTIBLE);
                        schedule_hrtimeout(&to, HRTIMER_MODE_REL);
                        continue;
                }

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

        return ncsw;
}

/***
 * kick_process - kick a running thread to enter/exit the kernel
 * @p: the to-be-kicked thread
 *
 * Cause a process which is running on another CPU to enter
 * kernel-mode, without any delay. (to get signals handled.)
 *
 * NOTE: this function doesn't have to take the runqueue lock,
 * because all it wants to ensure is that the remote task enters
 * the kernel. If the IPI races and the task has been migrated
 * to another CPU then no harm is done and the purpose has been
 * achieved as well.
 */
void kick_process(struct task_struct *p)
{
        int cpu;

        preempt_disable();
        cpu = task_cpu(p);
        if ((cpu != smp_processor_id()) && task_curr(p))
                smp_send_reschedule(cpu);
        preempt_enable();
}
EXPORT_SYMBOL_GPL(kick_process);

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

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

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

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

                /* No more Mr. Nice Guy. */
                switch (state) {
                case cpuset:
                        if (IS_ENABLED(CONFIG_CPUSETS)) {
                                cpuset_cpus_allowed_fallback(p);
                                state = possible;
                                break;
                        }
                        /* fall-through */
                case possible:
                        do_set_cpus_allowed(p, cpu_possible_mask);
                        state = fail;
                        break;

                case fail:
                        BUG();
                        break;
                }
        }

out:
        if (state != cpuset) {
                /*
                 * Don't tell them about moving exiting tasks or
                 * kernel threads (both mm NULL), since they never
                 * leave kernel.
                 */
                if (p->mm && printk_ratelimit()) {
                        printk_deferred("process %d (%s) no longer affine to cpu%d\n",
                                        task_pid_nr(p), p->comm, cpu);
                }
        }

        return dest_cpu;
}

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

        if (tsk_nr_cpus_allowed(p) > 1)
                cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
        else
                cpu = cpumask_any(tsk_cpus_allowed(p));

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

        return cpu;
}

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

#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)
{
#ifdef CONFIG_SCHEDSTATS
        struct rq *rq = this_rq();

#ifdef CONFIG_SMP
        int this_cpu = smp_processor_id();

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

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

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

#endif /* CONFIG_SMP */

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

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

#endif /* CONFIG_SCHEDSTATS */
}

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

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

/*
 * Mark the task runnable and perform wakeup-preemption.
 */
static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
                           struct pin_cookie cookie)
{
        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.
                 */
                lockdep_unpin_lock(&rq->lock, cookie);
                p->sched_class->task_woken(rq, p);
                lockdep_repin_lock(&rq->lock, cookie);
        }

        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 pin_cookie cookie)
{
        int en_flags = ENQUEUE_WAKEUP;

        lockdep_assert_held(&rq->lock);

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

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

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

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

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

        return ret;
}

#ifdef CONFIG_SMP
void sched_ttwu_pending(void)
{
        struct rq *rq = this_rq();
        struct llist_node *llist = llist_del_all(&rq->wake_list);
        struct pin_cookie cookie;
        struct task_struct *p;
        unsigned long flags;

        if (!llist)
                return;

        raw_spin_lock_irqsave(&rq->lock, flags);
        cookie = lockdep_pin_lock(&rq->lock);

        while (llist) {
                int wake_flags = 0;

                p = llist_entry(llist, struct task_struct, wake_entry);
                llist = llist_next(llist);

                if (p->sched_remote_wakeup)
                        wake_flags = WF_MIGRATED;

                ttwu_do_activate(rq, p, wake_flags, cookie);
        }

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

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

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

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

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

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

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

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

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

        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 {
                raw_spin_lock_irqsave(&rq->lock, flags);
                if (is_idle_task(rq->curr))
                        smp_send_reschedule(cpu);
                /* Else cpu is not in idle, do nothing here */
                raw_spin_unlock_irqrestore(&rq->lock, flags);
        }

out:
        rcu_read_unlock();
}

bool cpus_share_cache(int this_cpu, int that_cpu)
{
        return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
}
#endif /* CONFIG_SMP */

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

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

        raw_spin_lock(&rq->lock);
        cookie = lockdep_pin_lock(&rq->lock);
        ttwu_do_activate(rq, p, wake_flags, cookie);
        lockdep_unpin_lock(&rq->lock, cookie);
        raw_spin_unlock(&rq->lock);
}

/*
 * 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
 *
 * Transitivity guarantees that B happens after A and C after B.
 * Note: we only require RCpc transitivity.
 * Note: the cpu doing B need not be c0 or c1
 *
 * Example:
 *
 *   CPU0            CPU1            CPU2
 *
 *   LOCK rq(0)->lock
 *   sched-out X
 *   sched-in Y
 *   UNLOCK rq(0)->lock
 *
 *                                   LOCK rq(0)->lock // orders against CPU0
 *                                   dequeue X
 *                                   UNLOCK rq(0)->lock
 *
 *                                   LOCK rq(1)->lock
 *                                   enqueue X
 *                                   UNLOCK rq(1)->lock
 *
 *                   LOCK rq(1)->lock // orders against CPU2
 *                   sched-out Z
 *                   sched-in X
 *                   UNLOCK rq(1)->lock
 *
 *
 *  BLOCKING -- aka. SLEEP + WAKEUP
 *
 * For blocking we (obviously) need to provide the same guarantee as for
 * migration. However the means are completely different as there is no lock
 * chain to provide order. Instead we do:
 *
 *   1) smp_store_release(X->on_cpu, 0)
 *   2) smp_cond_acquire(!X->on_cpu)
 *
 * Example:
 *
 *   CPU0 (schedule)  CPU1 (try_to_wake_up) CPU2 (schedule)
 *
 *   LOCK rq(0)->lock LOCK X->pi_lock
 *   dequeue X
 *   sched-out X
 *   smp_store_release(X->on_cpu, 0);
 *
 *                    smp_cond_acquire(!X->on_cpu);
 *                    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 observe the state that lead to our wakeup. That is, not only must our
 * task observe its own prior state, it must also observe the stores prior to
 * its wakeup.
 *
 * This means that any means of doing remote wakeups must order the CPU doing
 * the wakeup against the CPU the task is going to end up running on. This,
 * however, is already required for the regular Program-Order guarantee above,
 * since the waking CPU is the one issueing the ACQUIRE (smp_cond_acquire).
 *
 */

/**
 * try_to_wake_up - wake up a thread
 * @p: the thread to be awakened
 * @state: the mask of task states that can be woken
 * @wake_flags: wake modifier flags (WF_*)
 *
 * Put it on the run-queue if it's not already there. The "current"
 * thread is always on the run-queue (except when the actual
 * re-schedule is in progress), and as such you're allowed to do
 * the simpler "current->state = TASK_RUNNING" to mark yourself
 * runnable without the overhead of this.
 *
 * Return: %true if @p was woken up, %false if it was already running.
 * or @state didn't match @p's state.
 */
static int
try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
{
        unsigned long flags;
        int cpu, success = 0;

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

        trace_sched_waking(p);

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

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

#ifdef CONFIG_SMP
        /*
         * 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.
         *
         *  [S] ->on_cpu = 1;   [L] ->on_rq
         *      UNLOCK rq->lock
         *                      RMB
         *      LOCK   rq->lock
         *  [S] ->on_rq = 0;    [L] ->on_cpu
         *
         * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
         * from the consecutive calls to schedule(); the first switching to our
         * task, the second putting it to sleep.
         */
        smp_rmb();

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

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

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

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

        return success;
}

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

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

        lockdep_assert_held(&rq->lock);

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

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

        trace_sched_waking(p);

        if (!task_on_rq_queued(p))
                ttwu_activate(rq, p, ENQUEUE_WAKEUP);

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

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

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

/*
 * This function clears the sched_dl_entity static params.
 */
void __dl_clear_params(struct task_struct *p)
{
        struct sched_dl_entity *dl_se = &p->dl;

        dl_se->dl_runtime = 0;
        dl_se->dl_deadline = 0;
        dl_se->dl_period = 0;
        dl_se->flags = 0;
        dl_se->dl_bw = 0;

        dl_se->dl_throttled = 0;
        dl_se->dl_yielded = 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);
        __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_NUMA_BALANCING
        if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
                p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
                p->mm->numa_scan_seq = 0;
        }

        if (clone_flags & CLONE_VM)
                p->numa_preferred_nid = current->numa_preferred_nid;
        else
                p->numa_preferred_nid = -1;

        p->node_stamp = 0ULL;
        p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
        p->numa_scan_period = sysctl_numa_balancing_scan_delay;
        p->numa_work.next = &p->numa_work;
        p->numa_faults = NULL;
        p->last_task_numa_placement = 0;
        p->last_sum_exec_runtime = 0;

        p->numa_group = NULL;
#endif /* CONFIG_NUMA_BALANCING */
}

DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);

#ifdef CONFIG_NUMA_BALANCING

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

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

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

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

#ifdef CONFIG_SCHEDSTATS

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

                /*
                 * 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)) {
                put_cpu();
                return -EAGAIN;
        } else if (rt_prio(p->prio)) {
                p->sched_class = &rt_sched_class;
        } else {
                p->sched_class = &fair_sched_class;
        }

        init_entity_runnable_average(&p->se);

        /*
         * The child is not yet in the pid-hash so no cgroup attach races,
         * and the cgroup is pinned to this child due to cgroup_fork()
         * is ran before sched_fork().
         *
         * Silence PROVE_RCU.
         */
        raw_spin_lock_irqsave(&p->pi_lock, flags);
        /*
         * We're setting the cpu for the first time, we don't migrate,
         * so use __set_task_cpu().
         */
        __set_task_cpu(p, cpu);
        if (p->sched_class->task_fork)
                p->sched_class->task_fork(p);
        raw_spin_unlock_irqrestore(&p->pi_lock, flags);

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

        put_cpu();
        return 0;
}

unsigned long to_ratio(u64 period, u64 runtime)
{
        if (runtime == RUNTIME_INF)
                return 1ULL << 20;

        /*
         * 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 << 20, period);
}

#ifdef CONFIG_SMP
inline struct dl_bw *dl_bw_of(int i)
{
        RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
                         "sched RCU must be held");
        return &cpu_rq(i)->rd->dl_bw;
}

static inline int dl_bw_cpus(int i)
{
        struct root_domain *rd = cpu_rq(i)->rd;
        int cpus = 0;

        RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
                         "sched RCU must be held");
        for_each_cpu_and(i, rd->span, cpu_active_mask)
                cpus++;

        return cpus;
}
#else
inline struct dl_bw *dl_bw_of(int i)
{
        return &cpu_rq(i)->dl.dl_bw;
}

static inline int dl_bw_cpus(int i)
{
        return 1;
}
#endif

/*
 * We must be sure that accepting a new task (or allowing changing the
 * parameters of an existing one) is consistent with the bandwidth
 * constraints. If yes, this function also accordingly updates the currently
 * allocated bandwidth to reflect the new situation.
 *
 * This function is called while holding p's rq->lock.
 *
 * XXX we should delay bw change until the task's 0-lag point, see
 * __setparam_dl().
 */
static int dl_overflow(struct task_struct *p, int policy,
                       const struct sched_attr *attr)
{

        struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
        u64 period = attr->sched_period ?: attr->sched_deadline;
        u64 runtime = attr->sched_runtime;
        u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
        int cpus, err = -1;

        /* !deadline task may carry old deadline bandwidth */
        if (new_bw == p->dl.dl_bw && task_has_dl_policy(p))
                return 0;

        /*
         * Either if a task, enters, leave, or stays -deadline but changes
         * its parameters, we may need to update accordingly the total
         * allocated bandwidth of the container.
         */
        raw_spin_lock(&dl_b->lock);
        cpus = dl_bw_cpus(task_cpu(p));
        if (dl_policy(policy) && !task_has_dl_policy(p) &&
            !__dl_overflow(dl_b, cpus, 0, new_bw)) {
                __dl_add(dl_b, new_bw);
                err = 0;
        } else if (dl_policy(policy) && task_has_dl_policy(p) &&
                   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
                __dl_clear(dl_b, p->dl.dl_bw);
                __dl_add(dl_b, new_bw);
                err = 0;
        } else if (!dl_policy(policy) && task_has_dl_policy(p)) {
                __dl_clear(dl_b, p->dl.dl_bw);
                err = 0;
        }
        raw_spin_unlock(&dl_b->lock);

        return err;
}

extern void init_dl_bw(struct dl_bw *dl_b);

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

        raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
        p->state = TASK_RUNNING;
#ifdef CONFIG_SMP
        /*
         * Fork balancing, do it here and not earlier because:
         *  - cpus_allowed can change in the fork path
         *  - any previously selected cpu might disappear through hotplug
         *
         * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
         * as we're not fully set-up yet.
         */
        __set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif
        rq = __task_rq_lock(p, &rf);
        post_init_entity_util_avg(&p->se);

        activate_task(rq, p, 0);
        p->on_rq = TASK_ON_RQ_QUEUED;
        trace_sched_wakeup_new(p);
        check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
        if (p->sched_class->task_woken) {
                /*
                 * Nothing relies on rq->lock after this, so its fine to
                 * drop it.
                 */
                lockdep_unpin_lock(&rq->lock, rf.cookie);
                p->sched_class->task_woken(rq, p);
                lockdep_repin_lock(&rq->lock, rf.cookie);
        }
#endif
        task_rq_unlock(rq, p, &rf);
}

#ifdef CONFIG_PREEMPT_NOTIFIERS

static struct static_key preempt_notifier_key = STATIC_KEY_INIT_FALSE;

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

void preempt_notifier_dec(void)
{
        static_key_slow_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_key_false(&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_key_false(&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_key_false(&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 */

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

/**
 * finish_task_switch - clean up after a task-switch
 * @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_lock_switch), otherwise a concurrent wakeup can get prev
         * running on another CPU and we could rave with its RUNNING -> DEAD
         * transition, resulting in a double drop.
         */
        prev_state = prev->state;
        vtime_task_switch(prev);
        perf_event_task_sched_in(prev, current);
        finish_lock_switch(rq, prev);
        finish_arch_post_lock_switch();

        fire_sched_in_preempt_notifiers(current);
        if (mm)
                mmdrop(mm);
        if (unlikely(prev_state == TASK_DEAD)) {
                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);
                put_task_struct(prev);
        }

        tick_nohz_task_switch();
        return rq;
}

#ifdef CONFIG_SMP

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

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

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

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

#else

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

#endif

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

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

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

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

/*
 * 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 pin_cookie cookie)
{
        struct mm_struct *mm, *oldmm;

        prepare_task_switch(rq, prev, next);

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

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

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

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

        return finish_task_switch(prev);
}

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

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

        return sum;
}

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

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

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

        return sum;
}

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

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

        return sum;
}

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

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

#ifdef CONFIG_SMP

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

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

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

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

#endif

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

EXPORT_PER_CPU_SYMBOL(kstat);
EXPORT_PER_CPU_SYMBOL(kernel_cpustat);

/*
 * 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 64bit 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)) {
                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;

        sched_clock_tick();

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

        perf_event_task_tick();

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

#ifdef CONFIG_NO_HZ_FULL
/**
 * scheduler_tick_max_deferment
 *
 * Keep at least one tick per second when a single
 * active task is running because the scheduler doesn't
 * yet completely support full dynticks environment.
 *
 * This makes sure that uptime, CFS vruntime, load
 * balancing, etc... continue to move forward, even
 * with a very low granularity.
 *
 * Return: Maximum deferment in nanoseconds.
 */
u64 scheduler_tick_max_deferment(void)
{
        struct rq *rq = this_rq();
        unsigned long next, now = READ_ONCE(jiffies);

        next = rq->last_sched_tick + HZ;

        if (time_before_eq(next, now))
                return 0;

        return jiffies_to_nsecs(next - now);
}
#endif

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

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

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

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

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

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

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

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

        debug_show_held_locks(prev);
        print_modules();
        if (irqs_disabled())
                print_irqtrace_events(prev);
#ifdef CONFIG_DEBUG_PREEMPT
        if (in_atomic_preempt_off()) {
                pr_err("Preemption disabled at:");
                print_ip_sym(current->preempt_disable_ip);
                pr_cont("\n");
        }
#endif
        dump_stack();
        add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
}

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

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

        profile_hit(SCHED_PROFILING, __builtin_return_address(0));

        schedstat_inc(this_rq(), sched_count);
}

/*
 * Pick up the highest-prio task:
 */
static inline struct task_struct *
pick_next_task(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
{
        const struct sched_class *class = &fair_sched_class;
        struct task_struct *p;

        /*
         * Optimization: we know that if all tasks are in
         * the fair class we can call that function directly:
         */
        if (likely(prev->sched_class == class &&
                   rq->nr_running == rq->cfs.h_nr_running)) {
                p = fair_sched_class.pick_next_task(rq, prev, cookie);
                if (unlikely(p == RETRY_TASK))
                        goto again;

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

                return p;
        }

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

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

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

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

        /*
         * do_exit() calls schedule() with preemption disabled as an exception;
         * however we must fix that up, otherwise the next task will see an
         * inconsistent (higher) preempt count.
         *
         * It also avoids the below schedule_debug() test from complaining
         * about this.
         */
        if (unlikely(prev->state == TASK_DEAD))
                preempt_enable_no_resched_notrace();

        schedule_debug(prev);

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

        local_irq_disable();
        rcu_note_context_switch();

        /*
         * 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().
         */
        smp_mb__before_spinlock();
        raw_spin_lock(&rq->lock);
        cookie = lockdep_pin_lock(&rq->lock);

        rq->clock_skip_update <<= 1; /* promote REQ to ACT */

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

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

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

        if (task_on_rq_queued(prev))
                update_rq_clock(rq);

        next = pick_next_task(rq, prev, cookie);
        clear_tsk_need_resched(prev);
        clear_preempt_need_resched();
        rq->clock_skip_update = 0;

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

                trace_sched_switch(preempt, prev, next);
                rq = context_switch(rq, prev, next, cookie); /* unlocks the rq */
        } else {
                lockdep_unpin_lock(&rq->lock, cookie);
                raw_spin_unlock_irq(&rq->lock);
        }

        balance_callback(rq);
}
STACK_FRAME_NON_STANDARD(__schedule); /* switch_to() */

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

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

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

#ifdef CONFIG_CONTEXT_TRACKING
asmlinkage __visible void __sched schedule_user(void)
{
        /*
         * If we come here after a random call to set_need_resched(),
         * or we have been woken up remotely but the IPI has not yet arrived,
         * we haven't yet exited the RCU idle mode. Do it here manually until
         * we find a better solution.
         *
         * NB: There are buggy callers of this function.  Ideally we
         * should warn if prev_state != CONTEXT_USER, but that will trigger
         * too frequently to make sense yet.
         */
        enum ctx_state prev_state = exception_enter();
        schedule();
        exception_exit(prev_state);
}
#endif

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

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

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

#ifdef CONFIG_PREEMPT
/*
 * this is the entry point to schedule() from in-kernel preemption
 * off of preempt_enable. Kernel preemptions off return from interrupt
 * occur there and call schedule directly.
 */
asmlinkage __visible void __sched notrace preempt_schedule(void)
{
        /*
         * If there is a non-zero preempt_count or interrupts are disabled,
         * we do not want to preempt the current task. Just return..
         */
        if (likely(!preemptible()))
                return;

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

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

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

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

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

#endif /* CONFIG_PREEMPT */

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

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

        prev_state = exception_enter();

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

        exception_exit(prev_state);
}

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

#ifdef CONFIG_RT_MUTEXES

/*
 * rt_mutex_setprio - set the current priority of a task
 * @p: task
 * @prio: prio value (kernel-internal form)
 *
 * This function changes the 'effective' priority of a task. It does
 * not touch ->normal_prio like __setscheduler().
 *
 * Used by the rt_mutex code to implement priority inheritance
 * logic. Call site only calls if the priority of the task changed.
 */
void rt_mutex_setprio(struct task_struct *p, int prio)
{
        int oldprio, queued, running, queue_flag = DEQUEUE_SAVE | DEQUEUE_MOVE;
        const struct sched_class *prev_class;
        struct rq_flags rf;
        struct rq *rq;

        BUG_ON(prio > MAX_PRIO);

        rq = __task_rq_lock(p, &rf);

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

        trace_sched_pi_setprio(p, prio);
        oldprio = p->prio;

        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)) {
                struct task_struct *pi_task = rt_mutex_get_top_task(p);
                if (!dl_prio(p->normal_prio) ||
                    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
                        p->dl.dl_boosted = 1;
                        queue_flag |= ENQUEUE_REPLENISH;
                } else
                        p->dl.dl_boosted = 0;
                p->sched_class = &dl_sched_class;
        } else if (rt_prio(prio)) {
                if (dl_prio(oldprio))
                        p->dl.dl_boosted = 0;
                if (oldprio < prio)
                        queue_flag |= ENQUEUE_HEAD;
                p->sched_class = &rt_sched_class;
        } else {
                if (dl_prio(oldprio))
                        p->dl.dl_boosted = 0;
                if (rt_prio(oldprio))
                        p->rt.timeout = 0;
                p->sched_class = &fair_sched_class;
        }

        p->prio = prio;

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

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

        balance_callback(rq);
        preempt_enable();
}
#endif

void set_user_nice(struct task_struct *p, long nice)
{
        int old_prio, delta, queued;
        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);
        /*
         * 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);
        if (queued)
                dequeue_task(rq, p, DEQUEUE_SAVE);

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

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

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

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

#ifdef __ARCH_WANT_SYS_NICE

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

        /*
         * Setpriority might change our priority at the same moment.
         * We don't have to worry. Conceptually one call occurs first
         * and we have a single winner.
         */
        increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH);
        nice = task_nice(current) + increment;

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

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

        set_user_nice(current, nice);
        return 0;
}

#endif

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

/**
 * idle_cpu - is a given cpu idle currently?
 * @cpu: the processor in question.
 *
 * Return: 1 if the CPU is currently idle. 0 otherwise.
 */
int idle_cpu(int cpu)
{
        struct rq *rq = cpu_rq(cpu);

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

        if (rq->nr_running)
                return 0;

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

        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;
}

/*
 * This function initializes the sched_dl_entity of a newly becoming
 * SCHED_DEADLINE task.
 *
 * Only the static values are considered here, the actual runtime and the
 * absolute deadline will be properly calculated when the task is enqueued
 * for the first time with its new policy.
 */
static void
__setparam_dl(struct task_struct *p, const struct sched_attr *attr)
{
        struct sched_dl_entity *dl_se = &p->dl;

        dl_se->dl_runtime = attr->sched_runtime;
        dl_se->dl_deadline = attr->sched_deadline;
        dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
        dl_se->flags = attr->sched_flags;
        dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);

        /*
         * Changing the parameters of a task is 'tricky' and we're not doing
         * the correct thing -- also see task_dead_dl() and switched_from_dl().
         *
         * What we SHOULD do is delay the bandwidth release until the 0-lag
         * point. This would include retaining the task_struct until that time
         * and change dl_overflow() to not immediately decrement the current
         * amount.
         *
         * Instead we retain the current runtime/deadline and let the new
         * parameters take effect after the current reservation period lapses.
         * This is safe (albeit pessimistic) because the 0-lag point is always
         * before the current scheduling deadline.
         *
         * We can still have temporary overloads because we do not delay the
         * change in bandwidth until that time; so admission control is
         * not on the safe side. It does however guarantee tasks will never
         * consume more than promised.
         */
}

/*
 * 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);
}

/* Actually do priority change: must hold pi & rq lock. */
static void __setscheduler(struct rq *rq, struct task_struct *p,
                           const struct sched_attr *attr, bool keep_boost)
{
        __setscheduler_params(p, attr);

        /*
         * Keep a potential priority boosting if called from
         * sched_setscheduler().
         */
        if (keep_boost)
                p->prio = rt_mutex_get_effective_prio(p, normal_prio(p));
        else
                p->prio = normal_prio(p);

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

static void
__getparam_dl(struct task_struct *p, struct sched_attr *attr)
{
        struct sched_dl_entity *dl_se = &p->dl;

        attr->sched_priority = p->rt_priority;
        attr->sched_runtime = dl_se->dl_runtime;
        attr->sched_deadline = dl_se->dl_deadline;
        attr->sched_period = dl_se->dl_period;
        attr->sched_flags = dl_se->flags;
}

/*
 * This function validates the new parameters of a -deadline task.
 * We ask for the deadline not being zero, and greater or equal
 * than the runtime, as well as the period of being zero or
 * greater than deadline. Furthermore, we have to be sure that
 * user parameters are above the internal resolution of 1us (we
 * check sched_runtime only since it is always the smaller one) and
 * below 2^63 ns (we have to check both sched_deadline and
 * sched_period, as the latter can be zero).
 */
static bool
__checkparam_dl(const struct sched_attr *attr)
{
        /* deadline != 0 */
        if (attr->sched_deadline == 0)
                return false;

        /*
         * Since we truncate DL_SCALE bits, make sure we're at least
         * that big.
         */
        if (attr->sched_runtime < (1ULL << DL_SCALE))
                return false;

        /*
         * Since we use the MSB for wrap-around and sign issues, make
         * sure it's not set (mind that period can be equal to zero).
         */
        if (attr->sched_deadline & (1ULL << 63) ||
            attr->sched_period & (1ULL << 63))
                return false;

        /* runtime <= deadline <= period (if period != 0) */
        if ((attr->sched_period != 0 &&
             attr->sched_period < attr->sched_deadline) ||
            attr->sched_deadline < attr->sched_runtime)
                return false;

        return true;
}

/*
 * 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 bool dl_param_changed(struct task_struct *p,
                const struct sched_attr *attr)
{
        struct sched_dl_entity *dl_se = &p->dl;

        if (dl_se->dl_runtime != attr->sched_runtime ||
                dl_se->dl_deadline != attr->sched_deadline ||
                dl_se->dl_period != attr->sched_period ||
                dl_se->flags != attr->sched_flags)
                return true;

        return false;
}

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

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

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

        if (attr->sched_flags & ~(SCHED_FLAG_RESET_ON_FORK))
                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 (idle_policy(p->policy) && !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) {
                retval = security_task_setscheduler(p);
                if (retval)
                        return retval;
        }

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

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

        /*
         * 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;

                p->sched_reset_on_fork = reset_on_fork;
                task_rq_unlock(rq, p, &rf);
                return 0;
        }
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))) {
                        task_rq_unlock(rq, p, &rf);
                        return -EPERM;
                }
#endif
#ifdef CONFIG_SMP
                if (dl_bandwidth_enabled() && dl_policy(policy)) {
                        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_allowed) ||
                            rq->rd->dl_bw.bw == 0) {
                                task_rq_unlock(rq, p, &rf);
                                return -EPERM;
                        }
                }
#endif
        }

        /* recheck policy now with rq lock held */
        if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
                policy = oldpolicy = -1;
                task_rq_unlock(rq, p, &rf);
                goto recheck;
        }

        /*
         * 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)) && dl_overflow(p, policy, attr)) {
                task_rq_unlock(rq, p, &rf);
                return -EBUSY;
        }

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

        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.
                 */
                new_effective_prio = rt_mutex_get_effective_prio(p, newprio);
                if (new_effective_prio == 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;
        __setscheduler(rq, p, attr, pi);

        if (running)
                p->sched_class->set_curr_task(rq);
        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);
        }

        check_class_changed(rq, p, prev_class, oldprio);
        preempt_disable(); /* avoid rq from going away on us */
        task_rq_unlock(rq, p, &rf);

        if (pi)
                rt_mutex_adjust_pi(p);

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

        return 0;
}

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.
 *
 * 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);

/**
 * 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);

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

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

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

        return retval;
}

/*
 * 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;

        if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0))
                return -EFAULT;

        /*
         * 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;

        if (size > PAGE_SIZE)   /* silly large */
                goto err_size;

        if (!size)              /* abi compat */
                size = SCHED_ATTR_SIZE_VER0;

        if (size < SCHED_ATTR_SIZE_VER0)
                goto err_size;

        /*
         * If we're handed a bigger struct than we know of,
         * ensure all the unknown bits are 0 - i.e. new
         * user-space does not rely on any kernel feature
         * extensions we dont know about yet.
         */
        if (size > sizeof(*attr)) {
                unsigned char __user *addr;
                unsigned char __user *end;
                unsigned char val;

                addr = (void __user *)uattr + sizeof(*attr);
                end  = (void __user *)uattr + size;

                for (; addr < end; addr++) {
                        ret = get_user(val, addr);
                        if (ret)
                                return ret;
                        if (val)
                                goto err_size;
                }
                size = sizeof(*attr);
        }

        ret = copy_from_user(attr, uattr, size);
        if (ret)
                return -EFAULT;

        /*
         * 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)
{
        /* negative values for policy are not valid */
        if (policy < 0)
                return -EINVAL;

        return do_sched_setscheduler(pid, policy, param);
}

/**
 * sys_sched_setparam - set/change the RT priority of a thread
 * @pid: the pid in question.
 * @param: structure containing the new RT priority.
 *
 * 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;

        rcu_read_lock();
        retval = -ESRCH;
        p = find_process_by_pid(pid);
        if (p != NULL)
                retval = sched_setattr(p, &attr);
        rcu_read_unlock();

        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;
}

static int sched_read_attr(struct sched_attr __user *uattr,
                           struct sched_attr *attr,
                           unsigned int usize)
{
        int ret;

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

        /*
         * If we're handed a smaller struct than we know of,
         * ensure all the unknown bits are 0 - i.e. old
         * user-space does not get uncomplete information.
         */
        if (usize < sizeof(*attr)) {
                unsigned char *addr;
                unsigned char *end;

                addr = (void *)attr + usize;
                end  = (void *)attr + sizeof(*attr);

                for (; addr < end; addr++) {
                        if (*addr)
                                return -EFBIG;
                }

                attr->size = usize;
        }

        ret = copy_to_user(uattr, attr, attr->size);
        if (ret)
                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.
 * @size: sizeof(attr) for fwd/bwd comp.
 * @flags: for future extension.
 */
SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
                unsigned int, size, unsigned int, flags)
{
        struct sched_attr attr = {
                .size = sizeof(struct sched_attr),
        };
        struct task_struct *p;
        int retval;

        if (!uattr || pid < 0 || size > PAGE_SIZE ||
            size < 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;

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

        rcu_read_unlock();

        retval = sched_read_attr(uattr, &attr, size);
        return retval;

out_unlock:
        rcu_read_unlock();
        return retval;
}

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

        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
again:
        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);
                        goto again;
                }
        }
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_allowed, cpu_active_mask);
        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: 0 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) {
                size_t retlen = min_t(size_t, len, cpumask_size());

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

        return ret;
}

/**
 * sys_sched_yield - yield the current processor to other threads.
 *
 * This function yields the current CPU to other tasks. If there are no
 * other threads running on this CPU then this function will return.
 *
 * Return: 0.
 */
SYSCALL_DEFINE0(sched_yield)
{
        struct rq *rq = this_rq_lock();

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

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

        schedule();

        return 0;
}

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

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

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

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

/**
 * 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);
        sys_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, preempt);
        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);

/*
 * 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 old_iowait = current->in_iowait;
        struct rq *rq;
        long ret;

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

        delayacct_blkio_start();
        rq = raw_rq();
        atomic_inc(&rq->nr_iowait);
        ret = schedule_timeout(timeout);
        current->in_iowait = old_iowait;
        atomic_dec(&rq->nr_iowait);
        delayacct_blkio_end();

        return ret;
}
EXPORT_SYMBOL(io_schedule_timeout);

/**
 * 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;
}

/**
 * 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 timespec __user *, interval)
{
        struct task_struct *p;
        unsigned int time_slice;
        struct rq_flags rf;
        struct timespec t;
        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_timespec(time_slice, &t);
        retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
        return retval;

out_unlock:
        rcu_read_unlock();
        return retval;
}

static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;

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

        if (state)
                state = __ffs(state) + 1;
        printk(KERN_INFO "%-15.15s %c", p->comm,
                state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
#if BITS_PER_LONG == 32
        if (state == TASK_RUNNING)
                printk(KERN_CONT " running  ");
        else
                printk(KERN_CONT " %08lx ", thread_saved_pc(p));
#else
        if (state == TASK_RUNNING)
                printk(KERN_CONT "  running task    ");
        else
                printk(KERN_CONT " %016lx ", thread_saved_pc(p));
#endif
#ifdef CONFIG_DEBUG_STACK_USAGE
        free = stack_not_used(p);
#endif
        ppid = 0;
        rcu_read_lock();
        if (pid_alive(p))
                ppid = task_pid_nr(rcu_dereference(p->real_parent));
        rcu_read_unlock();
        printk(KERN_CONT "%5lu %5d %6d 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);
}

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

#if BITS_PER_LONG == 32
        printk(KERN_INFO
                "  task                PC stack   pid father\n");
#else
        printk(KERN_INFO
                "  task                        PC stack   pid father\n");
#endif
        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 || (p->state & state_filter))
                        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();
}

void init_idle_bootup_task(struct task_struct *idle)
{
        idle->sched_class = &idle_sched_class;
}

/**
 * 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_idle(struct task_struct *idle, int cpu)
{
        struct rq *rq = cpu_rq(cpu);
        unsigned long flags;

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

        __sched_fork(0, idle);
        idle->state = TASK_RUNNING;
        idle->se.exec_start = sched_clock();

        kasan_unpoison_task_stack(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->curr = rq->idle = 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
}

int cpuset_cpumask_can_shrink(const struct cpumask *cur,
                              const struct cpumask *trial)
{
        int ret = 1, trial_cpus;
        struct dl_bw *cur_dl_b;
        unsigned long flags;

        if (!cpumask_weight(cur))
                return ret;

        rcu_read_lock_sched();
        cur_dl_b = dl_bw_of(cpumask_any(cur));
        trial_cpus = cpumask_weight(trial);

        raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
        if (cur_dl_b->bw != -1 &&
            cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw)
                ret = 0;
        raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
        rcu_read_unlock_sched();

        return ret;
}

int task_can_attach(struct task_struct *p,
                    const struct cpumask *cs_cpus_allowed)
{
        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_allowed may be changed.
         */
        if (p->flags & PF_NO_SETAFFINITY) {
                ret = -EINVAL;
                goto out;
        }

#ifdef CONFIG_SMP
        if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
                                              cs_cpus_allowed)) {
                unsigned int dest_cpu = cpumask_any_and(cpu_active_mask,
                                                        cs_cpus_allowed);
                struct dl_bw *dl_b;
                bool overflow;
                int cpus;
                unsigned long flags;

                rcu_read_lock_sched();
                dl_b = dl_bw_of(dest_cpu);
                raw_spin_lock_irqsave(&dl_b->lock, flags);
                cpus = dl_bw_cpus(dest_cpu);
                overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw);
                if (overflow)
                        ret = -EBUSY;
                else {
                        /*
                         * We reserve space for this task in the destination
                         * root_domain, as we can't fail after this point.
                         * We will free resources in the source root_domain
                         * later on (see set_cpus_allowed_dl()).
                         */
                        __dl_add(dl_b, p->dl.dl_bw);
                }
                raw_spin_unlock_irqrestore(&dl_b->lock, flags);
                rcu_read_unlock_sched();

        }
#endif
out:
        return ret;
}

#ifdef CONFIG_SMP

static 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, tsk_cpus_allowed(p)))
                return -EINVAL;

        /* TODO: 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 (running)
                p->sched_class->set_curr_task(rq);
        if (queued)
                enqueue_task(rq, p, ENQUEUE_RESTORE);
        task_rq_unlock(rq, p, &rf);
}
#endif /* CONFIG_NUMA_BALANCING */

#ifdef CONFIG_HOTPLUG_CPU
/*
 * Ensures 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()));

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

/*
 * 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.
 *
 * Also see the comment "Global load-average calculations".
 */
static void calc_load_migrate(struct rq *rq)
{
        long delta = calc_load_fold_active(rq);
        if (delta)
                atomic_long_add(delta, &calc_load_tasks);
}

static void put_prev_task_fake(struct rq *rq, struct task_struct *prev)
{
}

static const struct sched_class fake_sched_class = {
        .put_prev_task = put_prev_task_fake,
};

static struct task_struct fake_task = {
        /*
         * Avoid pull_{rt,dl}_task()
         */
        .prio = MAX_PRIO + 1,
        .sched_class = &fake_sched_class,
};

/*
 * Migrate all tasks 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.
 */
static void migrate_tasks(struct rq *dead_rq)
{
        struct rq *rq = dead_rq;
        struct task_struct *next, *stop = rq->stop;
        struct pin_cookie cookie;
        int dest_cpu;

        /*
         * 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);

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

                /*
                 * pick_next_task assumes pinned rq->lock.
                 */
                cookie = lockdep_pin_lock(&rq->lock);
                next = pick_next_task(rq, &fake_task, cookie);
                BUG_ON(!next);
                next->sched_class->put_prev_task(rq, next);

                /*
                 * Rules for changing task_struct::cpus_allowed 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.
                 */
                lockdep_unpin_lock(&rq->lock, cookie);
                raw_spin_unlock(&rq->lock);
                raw_spin_lock(&next->pi_lock);
                raw_spin_lock(&rq->lock);

                /*
                 * 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.
                 */
                if (WARN_ON(task_rq(next) != rq || !task_on_rq_queued(next))) {
                        raw_spin_unlock(&next->pi_lock);
                        continue;
                }

                /* Find suitable destination for @next, with force if needed. */
                dest_cpu = select_fallback_rq(dead_rq->cpu, next);

                rq = __migrate_task(rq, next, dest_cpu);
                if (rq != dead_rq) {
                        raw_spin_unlock(&rq->lock);
                        rq = dead_rq;
                        raw_spin_lock(&rq->lock);
                }
                raw_spin_unlock(&next->pi_lock);
        }

        rq->stop = stop;
}
#endif /* CONFIG_HOTPLUG_CPU */

static 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);
                }
        }
}

static 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;
        }
}

static void set_cpu_rq_start_time(unsigned int cpu)
{
        struct rq *rq = cpu_rq(cpu);

        rq->age_stamp = sched_clock_cpu(cpu);
}

static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */

#ifdef CONFIG_SCHED_DEBUG

static __read_mostly int sched_debug_enabled;

static int __init sched_debug_setup(char *str)
{
        sched_debug_enabled = 1;

        return 0;
}
early_param("sched_debug", sched_debug_setup);

static inline bool sched_debug(void)
{
        return sched_debug_enabled;
}

static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
                                  struct cpumask *groupmask)
{
        struct sched_group *group = sd->groups;

        cpumask_clear(groupmask);

        printk(KERN_DEBUG "%*s domain %d: ", level, "", level);

        if (!(sd->flags & SD_LOAD_BALANCE)) {
                printk("does not load-balance\n");
                if (sd->parent)
                        printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
                                        " has parent");
                return -1;
        }

        printk(KERN_CONT "span %*pbl level %s\n",
               cpumask_pr_args(sched_domain_span(sd)), sd->name);

        if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
                printk(KERN_ERR "ERROR: domain->span does not contain "
                                "CPU%d\n", cpu);
        }
        if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
                printk(KERN_ERR "ERROR: domain->groups does not contain"
                                " CPU%d\n", cpu);
        }

        printk(KERN_DEBUG "%*s groups:", level + 1, "");
        do {
                if (!group) {
                        printk("\n");
                        printk(KERN_ERR "ERROR: group is NULL\n");
                        break;
                }

                if (!cpumask_weight(sched_group_cpus(group))) {
                        printk(KERN_CONT "\n");
                        printk(KERN_ERR "ERROR: empty group\n");
                        break;
                }

                if (!(sd->flags & SD_OVERLAP) &&
                    cpumask_intersects(groupmask, sched_group_cpus(group))) {
                        printk(KERN_CONT "\n");
                        printk(KERN_ERR "ERROR: repeated CPUs\n");
                        break;
                }

                cpumask_or(groupmask, groupmask, sched_group_cpus(group));

                printk(KERN_CONT " %*pbl",
                       cpumask_pr_args(sched_group_cpus(group)));
                if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
                        printk(KERN_CONT " (cpu_capacity = %d)",
                                group->sgc->capacity);
                }

                group = group->next;
        } while (group != sd->groups);
        printk(KERN_CONT "\n");

        if (!cpumask_equal(sched_domain_span(sd), groupmask))
                printk(KERN_ERR "ERROR: groups don't span domain->span\n");

        if (sd->parent &&
            !cpumask_subset(groupmask, sched_domain_span(sd->parent)))
                printk(KERN_ERR "ERROR: parent span is not a superset "
                        "of domain->span\n");
        return 0;
}

static void sched_domain_debug(struct sched_domain *sd, int cpu)
{
        int level = 0;

        if (!sched_debug_enabled)
                return;

        if (!sd) {
                printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
                return;
        }

        printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);

        for (;;) {
                if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
                        break;
                level++;
                sd = sd->parent;
                if (!sd)
                        break;
        }
}
#else /* !CONFIG_SCHED_DEBUG */
# define sched_domain_debug(sd, cpu) do { } while (0)
static inline bool sched_debug(void)
{
        return false;
}
#endif /* CONFIG_SCHED_DEBUG */

static int sd_degenerate(struct sched_domain *sd)
{
        if (cpumask_weight(sched_domain_span(sd)) == 1)
                return 1;

        /* Following flags need at least 2 groups */
        if (sd->flags & (SD_LOAD_BALANCE |
                         SD_BALANCE_NEWIDLE |
                         SD_BALANCE_FORK |
                         SD_BALANCE_EXEC |
                         SD_SHARE_CPUCAPACITY |
                         SD_SHARE_PKG_RESOURCES |
                         SD_SHARE_POWERDOMAIN)) {
                if (sd->groups != sd->groups->next)
                        return 0;
        }

        /* Following flags don't use groups */
        if (sd->flags & (SD_WAKE_AFFINE))
                return 0;

        return 1;
}

static int
sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
{
        unsigned long cflags = sd->flags, pflags = parent->flags;

        if (sd_degenerate(parent))
                return 1;

        if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
                return 0;

        /* Flags needing groups don't count if only 1 group in parent */
        if (parent->groups == parent->groups->next) {
                pflags &= ~(SD_LOAD_BALANCE |
                                SD_BALANCE_NEWIDLE |
                                SD_BALANCE_FORK |
                                SD_BALANCE_EXEC |
                                SD_SHARE_CPUCAPACITY |
                                SD_SHARE_PKG_RESOURCES |
                                SD_PREFER_SIBLING |
                                SD_SHARE_POWERDOMAIN);
                if (nr_node_ids == 1)
                        pflags &= ~SD_SERIALIZE;
        }
        if (~cflags & pflags)
                return 0;

        return 1;
}

static void free_rootdomain(struct rcu_head *rcu)
{
        struct root_domain *rd = container_of(rcu, struct root_domain, rcu);

        cpupri_cleanup(&rd->cpupri);
        cpudl_cleanup(&rd->cpudl);
        free_cpumask_var(rd->dlo_mask);
        free_cpumask_var(rd->rto_mask);
        free_cpumask_var(rd->online);
        free_cpumask_var(rd->span);
        kfree(rd);
}

static void rq_attach_root(struct rq *rq, struct root_domain *rd)
{
        struct root_domain *old_rd = NULL;
        unsigned long flags;

        raw_spin_lock_irqsave(&rq->lock, flags);

        if (rq->rd) {
                old_rd = rq->rd;

                if (cpumask_test_cpu(rq->cpu, old_rd->online))
                        set_rq_offline(rq);

                cpumask_clear_cpu(rq->cpu, old_rd->span);

                /*
                 * If we dont want to free the old_rd yet then
                 * set old_rd to NULL to skip the freeing later
                 * in this function:
                 */
                if (!atomic_dec_and_test(&old_rd->refcount))
                        old_rd = NULL;
        }

        atomic_inc(&rd->refcount);
        rq->rd = rd;

        cpumask_set_cpu(rq->cpu, rd->span);
        if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
                set_rq_online(rq);

        raw_spin_unlock_irqrestore(&rq->lock, flags);

        if (old_rd)
                call_rcu_sched(&old_rd->rcu, free_rootdomain);
}

static int init_rootdomain(struct root_domain *rd)
{
        memset(rd, 0, sizeof(*rd));

        if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
                goto out;
        if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
                goto free_span;
        if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
                goto free_online;
        if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
                goto free_dlo_mask;

        init_dl_bw(&rd->dl_bw);
        if (cpudl_init(&rd->cpudl) != 0)
                goto free_dlo_mask;

        if (cpupri_init(&rd->cpupri) != 0)
                goto free_rto_mask;
        return 0;

free_rto_mask:
        free_cpumask_var(rd->rto_mask);
free_dlo_mask:
        free_cpumask_var(rd->dlo_mask);
free_online:
        free_cpumask_var(rd->online);
free_span:
        free_cpumask_var(rd->span);
out:
        return -ENOMEM;
}

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

static void init_defrootdomain(void)
{
        init_rootdomain(&def_root_domain);

        atomic_set(&def_root_domain.refcount, 1);
}

static struct root_domain *alloc_rootdomain(void)
{
        struct root_domain *rd;

        rd = kmalloc(sizeof(*rd), GFP_KERNEL);
        if (!rd)
                return NULL;

        if (init_rootdomain(rd) != 0) {
                kfree(rd);
                return NULL;
        }

        return rd;
}

static void free_sched_groups(struct sched_group *sg, int free_sgc)
{
        struct sched_group *tmp, *first;

        if (!sg)
                return;

        first = sg;
        do {
                tmp = sg->next;

                if (free_sgc && atomic_dec_and_test(&sg->sgc->ref))
                        kfree(sg->sgc);

                kfree(sg);
                sg = tmp;
        } while (sg != first);
}

static void free_sched_domain(struct rcu_head *rcu)
{
        struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);

        /*
         * If its an overlapping domain it has private groups, iterate and
         * nuke them all.
         */
        if (sd->flags & SD_OVERLAP) {
                free_sched_groups(sd->groups, 1);
        } else if (atomic_dec_and_test(&sd->groups->ref)) {
                kfree(sd->groups->sgc);
                kfree(sd->groups);
        }
        kfree(sd);
}

static void destroy_sched_domain(struct sched_domain *sd, int cpu)
{
        call_rcu(&sd->rcu, free_sched_domain);
}

static void destroy_sched_domains(struct sched_domain *sd, int cpu)
{
        for (; sd; sd = sd->parent)
                destroy_sched_domain(sd, cpu);
}

/*
 * Keep a special pointer to the highest sched_domain that has
 * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
 * allows us to avoid some pointer chasing select_idle_sibling().
 *
 * Also keep a unique ID per domain (we use the first cpu number in
 * the cpumask of the domain), this allows us to quickly tell if
 * two cpus are in the same cache domain, see cpus_share_cache().
 */
DEFINE_PER_CPU(struct sched_domain *, sd_llc);
DEFINE_PER_CPU(int, sd_llc_size);
DEFINE_PER_CPU(int, sd_llc_id);
DEFINE_PER_CPU(struct sched_domain *, sd_numa);
DEFINE_PER_CPU(struct sched_domain *, sd_busy);
DEFINE_PER_CPU(struct sched_domain *, sd_asym);

static void update_top_cache_domain(int cpu)
{
        struct sched_domain *sd;
        struct sched_domain *busy_sd = NULL;
        int id = cpu;
        int size = 1;

        sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
        if (sd) {
                id = cpumask_first(sched_domain_span(sd));
                size = cpumask_weight(sched_domain_span(sd));
                busy_sd = sd->parent; /* sd_busy */
        }
        rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd);

        rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
        per_cpu(sd_llc_size, cpu) = size;
        per_cpu(sd_llc_id, cpu) = id;

        sd = lowest_flag_domain(cpu, SD_NUMA);
        rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);

        sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
        rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
}

/*
 * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
 * hold the hotplug lock.
 */
static void
cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
{
        struct rq *rq = cpu_rq(cpu);
        struct sched_domain *tmp;

        /* Remove the sched domains which do not contribute to scheduling. */
        for (tmp = sd; tmp; ) {
                struct sched_domain *parent = tmp->parent;
                if (!parent)
                        break;

                if (sd_parent_degenerate(tmp, parent)) {
                        tmp->parent = parent->parent;
                        if (parent->parent)
                                parent->parent->child = tmp;
                        /*
                         * Transfer SD_PREFER_SIBLING down in case of a
                         * degenerate parent; the spans match for this
                         * so the property transfers.
                         */
                        if (parent->flags & SD_PREFER_SIBLING)
                                tmp->flags |= SD_PREFER_SIBLING;
                        destroy_sched_domain(parent, cpu);
                } else
                        tmp = tmp->parent;
        }

        if (sd && sd_degenerate(sd)) {
                tmp = sd;
                sd = sd->parent;
                destroy_sched_domain(tmp, cpu);
                if (sd)
                        sd->child = NULL;
        }

        sched_domain_debug(sd, cpu);

        rq_attach_root(rq, rd);
        tmp = rq->sd;
        rcu_assign_pointer(rq->sd, sd);
        destroy_sched_domains(tmp, cpu);

        update_top_cache_domain(cpu);
}

/* Setup the mask of cpus configured for isolated domains */
static int __init isolated_cpu_setup(char *str)
{
        int ret;

        alloc_bootmem_cpumask_var(&cpu_isolated_map);
        ret = cpulist_parse(str, cpu_isolated_map);
        if (ret) {
                pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids);
                return 0;
        }
        return 1;
}
__setup("isolcpus=", isolated_cpu_setup);

struct s_data {
        struct sched_domain ** __percpu sd;
        struct root_domain      *rd;
};

enum s_alloc {
        sa_rootdomain,
        sa_sd,
        sa_sd_storage,
        sa_none,
};

/*
 * Build an iteration mask that can exclude certain CPUs from the upwards
 * domain traversal.
 *
 * Asymmetric node setups can result in situations where the domain tree is of
 * unequal depth, make sure to skip domains that already cover the entire
 * range.
 *
 * In that case build_sched_domains() will have terminated the iteration early
 * and our sibling sd spans will be empty. Domains should always include the
 * cpu they're built on, so check that.
 *
 */
static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
{
        const struct cpumask *span = sched_domain_span(sd);
        struct sd_data *sdd = sd->private;
        struct sched_domain *sibling;
        int i;

        for_each_cpu(i, span) {
                sibling = *per_cpu_ptr(sdd->sd, i);
                if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
                        continue;

                cpumask_set_cpu(i, sched_group_mask(sg));
        }
}

/*
 * Return the canonical balance cpu for this group, this is the first cpu
 * of this group that's also in the iteration mask.
 */
int group_balance_cpu(struct sched_group *sg)
{
        return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
}

static int
build_overlap_sched_groups(struct sched_domain *sd, int cpu)
{
        struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg;
        const struct cpumask *span = sched_domain_span(sd);
        struct cpumask *covered = sched_domains_tmpmask;
        struct sd_data *sdd = sd->private;
        struct sched_domain *sibling;
        int i;

        cpumask_clear(covered);

        for_each_cpu(i, span) {
                struct cpumask *sg_span;

                if (cpumask_test_cpu(i, covered))
                        continue;

                sibling = *per_cpu_ptr(sdd->sd, i);

                /* See the comment near build_group_mask(). */
                if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
                        continue;

                sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
                                GFP_KERNEL, cpu_to_node(cpu));

                if (!sg)
                        goto fail;

                sg_span = sched_group_cpus(sg);
                if (sibling->child)
                        cpumask_copy(sg_span, sched_domain_span(sibling->child));
                else
                        cpumask_set_cpu(i, sg_span);

                cpumask_or(covered, covered, sg_span);

                sg->sgc = *per_cpu_ptr(sdd->sgc, i);
                if (atomic_inc_return(&sg->sgc->ref) == 1)
                        build_group_mask(sd, sg);

                /*
                 * Initialize sgc->capacity such that even if we mess up the
                 * domains and no possible iteration will get us here, we won't
                 * die on a /0 trap.
                 */
                sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);

                /*
                 * Make sure the first group of this domain contains the
                 * canonical balance cpu. Otherwise the sched_domain iteration
                 * breaks. See update_sg_lb_stats().
                 */
                if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
                    group_balance_cpu(sg) == cpu)
                        groups = sg;

                if (!first)
                        first = sg;
                if (last)
                        last->next = sg;
                last = sg;
                last->next = first;
        }
        sd->groups = groups;

        return 0;

fail:
        free_sched_groups(first, 0);

        return -ENOMEM;
}

static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
{
        struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
        struct sched_domain *child = sd->child;

        if (child)
                cpu = cpumask_first(sched_domain_span(child));

        if (sg) {
                *sg = *per_cpu_ptr(sdd->sg, cpu);
                (*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu);
                atomic_set(&(*sg)->sgc->ref, 1); /* for claim_allocations */
        }

        return cpu;
}

/*
 * build_sched_groups will build a circular linked list of the groups
 * covered by the given span, and will set each group's ->cpumask correctly,
 * and ->cpu_capacity to 0.
 *
 * Assumes the sched_domain tree is fully constructed
 */
static int
build_sched_groups(struct sched_domain *sd, int cpu)
{
        struct sched_group *first = NULL, *last = NULL;
        struct sd_data *sdd = sd->private;
        const struct cpumask *span = sched_domain_span(sd);
        struct cpumask *covered;
        int i;

        get_group(cpu, sdd, &sd->groups);
        atomic_inc(&sd->groups->ref);

        if (cpu != cpumask_first(span))
                return 0;

        lockdep_assert_held(&sched_domains_mutex);
        covered = sched_domains_tmpmask;

        cpumask_clear(covered);

        for_each_cpu(i, span) {
                struct sched_group *sg;
                int group, j;

                if (cpumask_test_cpu(i, covered))
                        continue;

                group = get_group(i, sdd, &sg);
                cpumask_setall(sched_group_mask(sg));

                for_each_cpu(j, span) {
                        if (get_group(j, sdd, NULL) != group)
                                continue;

                        cpumask_set_cpu(j, covered);
                        cpumask_set_cpu(j, sched_group_cpus(sg));
                }

                if (!first)
                        first = sg;
                if (last)
                        last->next = sg;
                last = sg;
        }
        last->next = first;

        return 0;
}

/*
 * Initialize sched groups cpu_capacity.
 *
 * cpu_capacity indicates the capacity of sched group, which is used while
 * distributing the load between different sched groups in a sched domain.
 * Typically cpu_capacity for all the groups in a sched domain will be same
 * unless there are asymmetries in the topology. If there are asymmetries,
 * group having more cpu_capacity will pickup more load compared to the
 * group having less cpu_capacity.
 */
static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
{
        struct sched_group *sg = sd->groups;

        WARN_ON(!sg);

        do {
                sg->group_weight = cpumask_weight(sched_group_cpus(sg));
                sg = sg->next;
        } while (sg != sd->groups);

        if (cpu != group_balance_cpu(sg))
                return;

        update_group_capacity(sd, cpu);
        atomic_set(&sg->sgc->nr_busy_cpus, sg->group_weight);
}

/*
 * Initializers for schedule domains
 * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
 */

static int default_relax_domain_level = -1;
int sched_domain_level_max;

static int __init setup_relax_domain_level(char *str)
{
        if (kstrtoint(str, 0, &default_relax_domain_level))
                pr_warn("Unable to set relax_domain_level\n");

        return 1;
}
__setup("relax_domain_level=", setup_relax_domain_level);

static void set_domain_attribute(struct sched_domain *sd,
                                 struct sched_domain_attr *attr)
{
        int request;

        if (!attr || attr->relax_domain_level < 0) {
                if (default_relax_domain_level < 0)
                        return;
                else
                        request = default_relax_domain_level;
        } else
                request = attr->relax_domain_level;
        if (request < sd->level) {
                /* turn off idle balance on this domain */
                sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
        } else {
                /* turn on idle balance on this domain */
                sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
        }
}

static void __sdt_free(const struct cpumask *cpu_map);
static int __sdt_alloc(const struct cpumask *cpu_map);

static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
                                 const struct cpumask *cpu_map)
{
        switch (what) {
        case sa_rootdomain:
                if (!atomic_read(&d->rd->refcount))
                        free_rootdomain(&d->rd->rcu); /* fall through */
        case sa_sd:
                free_percpu(d->sd); /* fall through */
        case sa_sd_storage:
                __sdt_free(cpu_map); /* fall through */
        case sa_none:
                break;
        }
}

static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
                                                   const struct cpumask *cpu_map)
{
        memset(d, 0, sizeof(*d));

        if (__sdt_alloc(cpu_map))
                return sa_sd_storage;
        d->sd = alloc_percpu(struct sched_domain *);
        if (!d->sd)
                return sa_sd_storage;
        d->rd = alloc_rootdomain();
        if (!d->rd)
                return sa_sd;
        return sa_rootdomain;
}

/*
 * NULL the sd_data elements we've used to build the sched_domain and
 * sched_group structure so that the subsequent __free_domain_allocs()
 * will not free the data we're using.
 */
static void claim_allocations(int cpu, struct sched_domain *sd)
{
        struct sd_data *sdd = sd->private;

        WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
        *per_cpu_ptr(sdd->sd, cpu) = NULL;

        if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref))
                *per_cpu_ptr(sdd->sg, cpu) = NULL;

        if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref))
                *per_cpu_ptr(sdd->sgc, cpu) = NULL;
}

#ifdef CONFIG_NUMA
static int sched_domains_numa_levels;
enum numa_topology_type sched_numa_topology_type;
static int *sched_domains_numa_distance;
int sched_max_numa_distance;
static struct cpumask ***sched_domains_numa_masks;
static int sched_domains_curr_level;
#endif

/*
 * SD_flags allowed in topology descriptions.
 *
 * SD_SHARE_CPUCAPACITY      - describes SMT topologies
 * SD_SHARE_PKG_RESOURCES - describes shared caches
 * SD_NUMA                - describes NUMA topologies
 * SD_SHARE_POWERDOMAIN   - describes shared power domain
 *
 * Odd one out:
 * SD_ASYM_PACKING        - describes SMT quirks
 */
#define TOPOLOGY_SD_FLAGS               \
        (SD_SHARE_CPUCAPACITY |         \
         SD_SHARE_PKG_RESOURCES |       \
         SD_NUMA |                      \
         SD_ASYM_PACKING |              \
         SD_SHARE_POWERDOMAIN)

static struct sched_domain *
sd_init(struct sched_domain_topology_level *tl, int cpu)
{
        struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
        int sd_weight, sd_flags = 0;

#ifdef CONFIG_NUMA
        /*
         * Ugly hack to pass state to sd_numa_mask()...
         */
        sched_domains_curr_level = tl->numa_level;
#endif

        sd_weight = cpumask_weight(tl->mask(cpu));

        if (tl->sd_flags)
                sd_flags = (*tl->sd_flags)();
        if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
                        "wrong sd_flags in topology description\n"))
                sd_flags &= ~TOPOLOGY_SD_FLAGS;

        *sd = (struct sched_domain){
                .min_interval           = sd_weight,
                .max_interval           = 2*sd_weight,
                .busy_factor            = 32,
                .imbalance_pct          = 125,

                .cache_nice_tries       = 0,
                .busy_idx               = 0,
                .idle_idx               = 0,
                .newidle_idx            = 0,
                .wake_idx               = 0,
                .forkexec_idx           = 0,

                .flags                  = 1*SD_LOAD_BALANCE
                                        | 1*SD_BALANCE_NEWIDLE
                                        | 1*SD_BALANCE_EXEC
                                        | 1*SD_BALANCE_FORK
                                        | 0*SD_BALANCE_WAKE
                                        | 1*SD_WAKE_AFFINE
                                        | 0*SD_SHARE_CPUCAPACITY
                                        | 0*SD_SHARE_PKG_RESOURCES
                                        | 0*SD_SERIALIZE
                                        | 0*SD_PREFER_SIBLING
                                        | 0*SD_NUMA
                                        | sd_flags
                                        ,

                .last_balance           = jiffies,
                .balance_interval       = sd_weight,
                .smt_gain               = 0,
                .max_newidle_lb_cost    = 0,
                .next_decay_max_lb_cost = jiffies,
#ifdef CONFIG_SCHED_DEBUG
                .name                   = tl->name,
#endif
        };

        /*
         * Convert topological properties into behaviour.
         */

        if (sd->flags & SD_SHARE_CPUCAPACITY) {
                sd->flags |= SD_PREFER_SIBLING;
                sd->imbalance_pct = 110;
                sd->smt_gain = 1178; /* ~15% */

        } else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
                sd->imbalance_pct = 117;
                sd->cache_nice_tries = 1;
                sd->busy_idx = 2;

#ifdef CONFIG_NUMA
        } else if (sd->flags & SD_NUMA) {
                sd->cache_nice_tries = 2;
                sd->busy_idx = 3;
                sd->idle_idx = 2;

                sd->flags |= SD_SERIALIZE;
                if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
                        sd->flags &= ~(SD_BALANCE_EXEC |
                                       SD_BALANCE_FORK |
                                       SD_WAKE_AFFINE);
                }

#endif
        } else {
                sd->flags |= SD_PREFER_SIBLING;
                sd->cache_nice_tries = 1;
                sd->busy_idx = 2;
                sd->idle_idx = 1;
        }

        sd->private = &tl->data;

        return sd;
}

/*
 * Topology list, bottom-up.
 */
static struct sched_domain_topology_level default_topology[] = {
#ifdef CONFIG_SCHED_SMT
        { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
#endif
#ifdef CONFIG_SCHED_MC
        { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
#endif
        { cpu_cpu_mask, SD_INIT_NAME(DIE) },
        { NULL, },
};

static struct sched_domain_topology_level *sched_domain_topology =
        default_topology;

#define for_each_sd_topology(tl)                        \
        for (tl = sched_domain_topology; tl->mask; tl++)

void set_sched_topology(struct sched_domain_topology_level *tl)
{
        sched_domain_topology = tl;
}

#ifdef CONFIG_NUMA

static const struct cpumask *sd_numa_mask(int cpu)
{
        return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
}

static void sched_numa_warn(const char *str)
{
        static int done = false;
        int i,j;

        if (done)
                return;

        done = true;

        printk(KERN_WARNING "ERROR: %s\n\n", str);

        for (i = 0; i < nr_node_ids; i++) {
                printk(KERN_WARNING "  ");
                for (j = 0; j < nr_node_ids; j++)
                        printk(KERN_CONT "%02d ", node_distance(i,j));
                printk(KERN_CONT "\n");
        }
        printk(KERN_WARNING "\n");
}

bool find_numa_distance(int distance)
{
        int i;

        if (distance == node_distance(0, 0))
                return true;

        for (i = 0; i < sched_domains_numa_levels; i++) {
                if (sched_domains_numa_distance[i] == distance)
                        return true;
        }

        return false;
}

/*
 * A system can have three types of NUMA topology:
 * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system
 * NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes
 * NUMA_BACKPLANE: nodes can reach other nodes through a backplane
 *
 * The difference between a glueless mesh topology and a backplane
 * topology lies in whether communication between not directly
 * connected nodes goes through intermediary nodes (where programs
 * could run), or through backplane controllers. This affects
 * placement of programs.
 *
 * The type of topology can be discerned with the following tests:
 * - If the maximum distance between any nodes is 1 hop, the system
 *   is directly connected.
 * - If for two nodes A and B, located N > 1 hops away from each other,
 *   there is an intermediary node C, which is < N hops away from both
 *   nodes A and B, the system is a glueless mesh.
 */
static void init_numa_topology_type(void)
{
        int a, b, c, n;

        n = sched_max_numa_distance;

        if (sched_domains_numa_levels <= 1) {
                sched_numa_topology_type = NUMA_DIRECT;
                return;
        }

        for_each_online_node(a) {
                for_each_online_node(b) {
                        /* Find two nodes furthest removed from each other. */
                        if (node_distance(a, b) < n)
                                continue;

                        /* Is there an intermediary node between a and b? */
                        for_each_online_node(c) {
                                if (node_distance(a, c) < n &&
                                    node_distance(b, c) < n) {
                                        sched_numa_topology_type =
                                                        NUMA_GLUELESS_MESH;
                                        return;
                                }
                        }

                        sched_numa_topology_type = NUMA_BACKPLANE;
                        return;
                }
        }
}

static void sched_init_numa(void)
{
        int next_distance, curr_distance = node_distance(0, 0);
        struct sched_domain_topology_level *tl;
        int level = 0;
        int i, j, k;

        sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
        if (!sched_domains_numa_distance)
                return;

        /*
         * O(nr_nodes^2) deduplicating selection sort -- in order to find the
         * unique distances in the node_distance() table.
         *
         * Assumes node_distance(0,j) includes all distances in
         * node_distance(i,j) in order to avoid cubic time.
         */
        next_distance = curr_distance;
        for (i = 0; i < nr_node_ids; i++) {
                for (j = 0; j < nr_node_ids; j++) {
                        for (k = 0; k < nr_node_ids; k++) {
                                int distance = node_distance(i, k);

                                if (distance > curr_distance &&
                                    (distance < next_distance ||
                                     next_distance == curr_distance))
                                        next_distance = distance;

                                /*
                                 * While not a strong assumption it would be nice to know
                                 * about cases where if node A is connected to B, B is not
                                 * equally connected to A.
                                 */
                                if (sched_debug() && node_distance(k, i) != distance)
                                        sched_numa_warn("Node-distance not symmetric");

                                if (sched_debug() && i && !find_numa_distance(distance))
                                        sched_numa_warn("Node-0 not representative");
                        }
                        if (next_distance != curr_distance) {
                                sched_domains_numa_distance[level++] = next_distance;
                                sched_domains_numa_levels = level;
                                curr_distance = next_distance;
                        } else break;
                }

                /*
                 * In case of sched_debug() we verify the above assumption.
                 */
                if (!sched_debug())
                        break;
        }

        if (!level)
                return;

        /*
         * 'level' contains the number of unique distances, excluding the
         * identity distance node_distance(i,i).
         *
         * The sched_domains_numa_distance[] array includes the actual distance
         * numbers.
         */

        /*
         * Here, we should temporarily reset sched_domains_numa_levels to 0.
         * If it fails to allocate memory for array sched_domains_numa_masks[][],
         * the array will contain less then 'level' members. This could be
         * dangerous when we use it to iterate array sched_domains_numa_masks[][]
         * in other functions.
         *
         * We reset it to 'level' at the end of this function.
         */
        sched_domains_numa_levels = 0;

        sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
        if (!sched_domains_numa_masks)
                return;

        /*
         * Now for each level, construct a mask per node which contains all
         * cpus of nodes that are that many hops away from us.
         */
        for (i = 0; i < level; i++) {
                sched_domains_numa_masks[i] =
                        kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
                if (!sched_domains_numa_masks[i])
                        return;

                for (j = 0; j < nr_node_ids; j++) {
                        struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
                        if (!mask)
                                return;

                        sched_domains_numa_masks[i][j] = mask;

                        for_each_node(k) {
                                if (node_distance(j, k) > sched_domains_numa_distance[i])
                                        continue;

                                cpumask_or(mask, mask, cpumask_of_node(k));
                        }
                }
        }

        /* Compute default topology size */
        for (i = 0; sched_domain_topology[i].mask; i++);

        tl = kzalloc((i + level + 1) *
                        sizeof(struct sched_domain_topology_level), GFP_KERNEL);
        if (!tl)
                return;

        /*
         * Copy the default topology bits..
         */
        for (i = 0; sched_domain_topology[i].mask; i++)
                tl[i] = sched_domain_topology[i];

        /*
         * .. and append 'j' levels of NUMA goodness.
         */
        for (j = 0; j < level; i++, j++) {
                tl[i] = (struct sched_domain_topology_level){
                        .mask = sd_numa_mask,
                        .sd_flags = cpu_numa_flags,
                        .flags = SDTL_OVERLAP,
                        .numa_level = j,
                        SD_INIT_NAME(NUMA)
                };
        }

        sched_domain_topology = tl;

        sched_domains_numa_levels = level;
        sched_max_numa_distance = sched_domains_numa_distance[level - 1];

        init_numa_topology_type();
}

static void sched_domains_numa_masks_set(unsigned int cpu)
{
        int node = cpu_to_node(cpu);
        int i, j;

        for (i = 0; i < sched_domains_numa_levels; i++) {
                for (j = 0; j < nr_node_ids; j++) {
                        if (node_distance(j, node) <= sched_domains_numa_distance[i])
                                cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
                }
        }
}

static void sched_domains_numa_masks_clear(unsigned int cpu)
{
        int i, j;

        for (i = 0; i < sched_domains_numa_levels; i++) {
                for (j = 0; j < nr_node_ids; j++)
                        cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]);
        }
}

#else
static inline void sched_init_numa(void) { }
static void sched_domains_numa_masks_set(unsigned int cpu) { }
static void sched_domains_numa_masks_clear(unsigned int cpu) { }
#endif /* CONFIG_NUMA */

static int __sdt_alloc(const struct cpumask *cpu_map)
{
        struct sched_domain_topology_level *tl;
        int j;

        for_each_sd_topology(tl) {
                struct sd_data *sdd = &tl->data;

                sdd->sd = alloc_percpu(struct sched_domain *);
                if (!sdd->sd)
                        return -ENOMEM;

                sdd->sg = alloc_percpu(struct sched_group *);
                if (!sdd->sg)
                        return -ENOMEM;

                sdd->sgc = alloc_percpu(struct sched_group_capacity *);
                if (!sdd->sgc)
                        return -ENOMEM;

                for_each_cpu(j, cpu_map) {
                        struct sched_domain *sd;
                        struct sched_group *sg;
                        struct sched_group_capacity *sgc;

                        sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
                                        GFP_KERNEL, cpu_to_node(j));
                        if (!sd)
                                return -ENOMEM;

                        *per_cpu_ptr(sdd->sd, j) = sd;

                        sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
                                        GFP_KERNEL, cpu_to_node(j));
                        if (!sg)
                                return -ENOMEM;

                        sg->next = sg;

                        *per_cpu_ptr(sdd->sg, j) = sg;

                        sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(),
                                        GFP_KERNEL, cpu_to_node(j));
                        if (!sgc)
                                return -ENOMEM;

                        *per_cpu_ptr(sdd->sgc, j) = sgc;
                }
        }

        return 0;
}

static void __sdt_free(const struct cpumask *cpu_map)
{
        struct sched_domain_topology_level *tl;
        int j;

        for_each_sd_topology(tl) {
                struct sd_data *sdd = &tl->data;

                for_each_cpu(j, cpu_map) {
                        struct sched_domain *sd;

                        if (sdd->sd) {
                                sd = *per_cpu_ptr(sdd->sd, j);
                                if (sd && (sd->flags & SD_OVERLAP))
                                        free_sched_groups(sd->groups, 0);
                                kfree(*per_cpu_ptr(sdd->sd, j));
                        }

                        if (sdd->sg)
                                kfree(*per_cpu_ptr(sdd->sg, j));
                        if (sdd->sgc)
                                kfree(*per_cpu_ptr(sdd->sgc, j));
                }
                free_percpu(sdd->sd);
                sdd->sd = NULL;
                free_percpu(sdd->sg);
                sdd->sg = NULL;
                free_percpu(sdd->sgc);
                sdd->sgc = NULL;
        }
}

struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
                const struct cpumask *cpu_map, struct sched_domain_attr *attr,
                struct sched_domain *child, int cpu)
{
        struct sched_domain *sd = sd_init(tl, cpu);
        if (!sd)
                return child;

        cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
        if (child) {
                sd->level = child->level + 1;
                sched_domain_level_max = max(sched_domain_level_max, sd->level);
                child->parent = sd;
                sd->child = child;

                if (!cpumask_subset(sched_domain_span(child),
                                    sched_domain_span(sd))) {
                        pr_err("BUG: arch topology borken\n");
#ifdef CONFIG_SCHED_DEBUG
                        pr_err("     the %s domain not a subset of the %s domain\n",
                                        child->name, sd->name);
#endif
                        /* Fixup, ensure @sd has at least @child cpus. */
                        cpumask_or(sched_domain_span(sd),
                                   sched_domain_span(sd),
                                   sched_domain_span(child));
                }

        }
        set_domain_attribute(sd, attr);

        return sd;
}

/*
 * Build sched domains for a given set of cpus and attach the sched domains
 * to the individual cpus
 */
static int build_sched_domains(const struct cpumask *cpu_map,
                               struct sched_domain_attr *attr)
{
        enum s_alloc alloc_state;
        struct sched_domain *sd;
        struct s_data d;
        int i, ret = -ENOMEM;

        alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
        if (alloc_state != sa_rootdomain)
                goto error;

        /* Set up domains for cpus specified by the cpu_map. */
        for_each_cpu(i, cpu_map) {
                struct sched_domain_topology_level *tl;

                sd = NULL;
                for_each_sd_topology(tl) {
                        sd = build_sched_domain(tl, cpu_map, attr, sd, i);
                        if (tl == sched_domain_topology)
                                *per_cpu_ptr(d.sd, i) = sd;
                        if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
                                sd->flags |= SD_OVERLAP;
                        if (cpumask_equal(cpu_map, sched_domain_span(sd)))
                                break;
                }
        }

        /* Build the groups for the domains */
        for_each_cpu(i, cpu_map) {
                for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
                        sd->span_weight = cpumask_weight(sched_domain_span(sd));
                        if (sd->flags & SD_OVERLAP) {
                                if (build_overlap_sched_groups(sd, i))
                                        goto error;
                        } else {
                                if (build_sched_groups(sd, i))
                                        goto error;
                        }
                }
        }

        /* Calculate CPU capacity for physical packages and nodes */
        for (i = nr_cpumask_bits-1; i >= 0; i--) {
                if (!cpumask_test_cpu(i, cpu_map))
                        continue;

                for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
                        claim_allocations(i, sd);
                        init_sched_groups_capacity(i, sd);
                }
        }

        /* Attach the domains */
        rcu_read_lock();
        for_each_cpu(i, cpu_map) {
                sd = *per_cpu_ptr(d.sd, i);
                cpu_attach_domain(sd, d.rd, i);
        }
        rcu_read_unlock();

        ret = 0;
error:
        __free_domain_allocs(&d, alloc_state, cpu_map);
        return ret;
}

static cpumask_var_t *doms_cur; /* current sched domains */
static int ndoms_cur;           /* number of sched domains in 'doms_cur' */
static struct sched_domain_attr *dattr_cur;
                                /* attribues of custom domains in 'doms_cur' */

/*
 * Special case: If a kmalloc of a doms_cur partition (array of
 * cpumask) fails, then fallback to a single sched domain,
 * as determined by the single cpumask fallback_doms.
 */
static cpumask_var_t fallback_doms;

/*
 * arch_update_cpu_topology lets virtualized architectures update the
 * cpu core maps. It is supposed to return 1 if the topology changed
 * or 0 if it stayed the same.
 */
int __weak arch_update_cpu_topology(void)
{
        return 0;
}

cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
{
        int i;
        cpumask_var_t *doms;

        doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
        if (!doms)
                return NULL;
        for (i = 0; i < ndoms; i++) {
                if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
                        free_sched_domains(doms, i);
                        return NULL;
                }
        }
        return doms;
}

void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
{
        unsigned int i;
        for (i = 0; i < ndoms; i++)
                free_cpumask_var(doms[i]);
        kfree(doms);
}

/*
 * Set up scheduler domains and groups. Callers must hold the hotplug lock.
 * For now this just excludes isolated cpus, but could be used to
 * exclude other special cases in the future.
 */
static int init_sched_domains(const struct cpumask *cpu_map)
{
        int err;

        arch_update_cpu_topology();
        ndoms_cur = 1;
        doms_cur = alloc_sched_domains(ndoms_cur);
        if (!doms_cur)
                doms_cur = &fallback_doms;
        cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
        err = build_sched_domains(doms_cur[0], NULL);
        register_sched_domain_sysctl();

        return err;
}

/*
 * Detach sched domains from a group of cpus specified in cpu_map
 * These cpus will now be attached to the NULL domain
 */
static void detach_destroy_domains(const struct cpumask *cpu_map)
{
        int i;

        rcu_read_lock();
        for_each_cpu(i, cpu_map)
                cpu_attach_domain(NULL, &def_root_domain, i);
        rcu_read_unlock();
}

/* handle null as "default" */
static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
                        struct sched_domain_attr *new, int idx_new)
{
        struct sched_domain_attr tmp;

        /* fast path */
        if (!new && !cur)
                return 1;

        tmp = SD_ATTR_INIT;
        return !memcmp(cur ? (cur + idx_cur) : &tmp,
                        new ? (new + idx_new) : &tmp,
                        sizeof(struct sched_domain_attr));
}

/*
 * Partition sched domains as specified by the 'ndoms_new'
 * cpumasks in the array doms_new[] of cpumasks. This compares
 * doms_new[] to the current sched domain partitioning, doms_cur[].
 * It destroys each deleted domain and builds each new domain.
 *
 * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
 * The masks don't intersect (don't overlap.) We should setup one
 * sched domain for each mask. CPUs not in any of the cpumasks will
 * not be load balanced. If the same cpumask appears both in the
 * current 'doms_cur' domains and in the new 'doms_new', we can leave
 * it as it is.
 *
 * The passed in 'doms_new' should be allocated using
 * alloc_sched_domains.  This routine takes ownership of it and will
 * free_sched_domains it when done with it. If the caller failed the
 * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
 * and partition_sched_domains() will fallback to the single partition
 * 'fallback_doms', it also forces the domains to be rebuilt.
 *
 * If doms_new == NULL it will be replaced with cpu_online_mask.
 * ndoms_new == 0 is a special case for destroying existing domains,
 * and it will not create the default domain.
 *
 * Call with hotplug lock held
 */
void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
                             struct sched_domain_attr *dattr_new)
{
        int i, j, n;
        int new_topology;

        mutex_lock(&sched_domains_mutex);

        /* always unregister in case we don't destroy any domains */
        unregister_sched_domain_sysctl();

        /* Let architecture update cpu core mappings. */
        new_topology = arch_update_cpu_topology();

        n = doms_new ? ndoms_new : 0;

        /* Destroy deleted domains */
        for (i = 0; i < ndoms_cur; i++) {
                for (j = 0; j < n && !new_topology; j++) {
                        if (cpumask_equal(doms_cur[i], doms_new[j])
                            && dattrs_equal(dattr_cur, i, dattr_new, j))
                                goto match1;
                }
                /* no match - a current sched domain not in new doms_new[] */
                detach_destroy_domains(doms_cur[i]);
match1:
                ;
        }

        n = ndoms_cur;
        if (doms_new == NULL) {
                n = 0;
                doms_new = &fallback_doms;
                cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
                WARN_ON_ONCE(dattr_new);
        }

        /* Build new domains */
        for (i = 0; i < ndoms_new; i++) {
                for (j = 0; j < n && !new_topology; j++) {
                        if (cpumask_equal(doms_new[i], doms_cur[j])
                            && dattrs_equal(dattr_new, i, dattr_cur, j))
                                goto match2;
                }
                /* no match - add a new doms_new */
                build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL);
match2:
                ;
        }

        /* Remember the new sched domains */
        if (doms_cur != &fallback_doms)
                free_sched_domains(doms_cur, ndoms_cur);
        kfree(dattr_cur);       /* kfree(NULL) is safe */
        doms_cur = doms_new;
        dattr_cur = dattr_new;
        ndoms_cur = ndoms_new;

        register_sched_domain_sysctl();

        mutex_unlock(&sched_domains_mutex);
}

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

/*
 * 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.
                 */
                num_cpus_frozen--;
                if (likely(num_cpus_frozen)) {
                        partition_sched_domains(1, NULL, NULL);
                        return;
                }
                /*
                 * This is the last CPU online operation. So fall through and
                 * restore the original sched domains by considering the
                 * cpuset configurations.
                 */
        }
        cpuset_update_active_cpus(true);
}

static int cpuset_cpu_inactive(unsigned int cpu)
{
        unsigned long flags;
        struct dl_bw *dl_b;
        bool overflow;
        int cpus;

        if (!cpuhp_tasks_frozen) {
                rcu_read_lock_sched();
                dl_b = dl_bw_of(cpu);

                raw_spin_lock_irqsave(&dl_b->lock, flags);
                cpus = dl_bw_cpus(cpu);
                overflow = __dl_overflow(dl_b, cpus, 0, 0);
                raw_spin_unlock_irqrestore(&dl_b->lock, flags);

                rcu_read_unlock_sched();

                if (overflow)
                        return -EBUSY;
                cpuset_update_active_cpus(false);
        } 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);
        unsigned long flags;

        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.
         */
        raw_spin_lock_irqsave(&rq->lock, flags);
        if (rq->rd) {
                BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
                set_rq_online(rq);
        }
        raw_spin_unlock_irqrestore(&rq->lock, flags);

        update_max_interval();

        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.
         *
         * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might
         * not imply sync_sched(), so wait for both.
         *
         * Do sync before park smpboot threads to take care the rcu boost case.
         */
        if (IS_ENABLED(CONFIG_PREEMPT))
                synchronize_rcu_mult(call_rcu, call_rcu_sched);
        else
                synchronize_rcu();

        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);

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

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

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

        /* Handle pending wakeups and then migrate everything off */
        sched_ttwu_pending();
        raw_spin_lock_irqsave(&rq->lock, flags);
        if (rq->rd) {
                BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
                set_rq_offline(rq);
        }
        migrate_tasks(rq);
        BUG_ON(rq->nr_running != 1);
        raw_spin_unlock_irqrestore(&rq->lock, flags);
        calc_load_migrate(rq);
        update_max_interval();
        nohz_balance_exit_idle(cpu);
        hrtick_clear(rq);
        return 0;
}
#endif

void __init sched_init_smp(void)
{
        cpumask_var_t non_isolated_cpus;

        alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
        alloc_cpumask_var(&fallback_doms, GFP_KERNEL);

        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);
        init_sched_domains(cpu_active_mask);
        cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
        if (cpumask_empty(non_isolated_cpus))
                cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
        mutex_unlock(&sched_domains_mutex);

        /* Move init over to a non-isolated CPU */
        if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0)
                BUG();
        sched_init_granularity();
        free_cpumask_var(non_isolated_cpus);

        init_sched_rt_class();
        init_sched_dl_class();
        sched_smp_initialized = true;
}

static int __init migration_init(void)
{
        sched_rq_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);

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

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

#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));
        }
#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
                root_task_group.shares = ROOT_TASK_GROUP_LOAD;
                INIT_LIST_HEAD(&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_cfs_bandwidth(&root_task_group.cfs_bandwidth);
                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

                for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
                        rq->cpu_load[j] = 0;

#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;

                INIT_LIST_HEAD(&rq->cfs_tasks);

                rq_attach_root(rq, &def_root_domain);
#ifdef CONFIG_NO_HZ_COMMON
                rq->last_load_update_tick = jiffies;
                rq->nohz_flags = 0;
#endif
#ifdef CONFIG_NO_HZ_FULL
                rq->last_sched_tick = 0;
#endif
#endif /* CONFIG_SMP */
                init_rq_hrtick(rq);
                atomic_set(&rq->nr_iowait, 0);
        }

        set_load_weight(&init_task);

#ifdef CONFIG_PREEMPT_NOTIFIERS
        INIT_HLIST_HEAD(&init_task.preempt_notifiers);
#endif

        /*
         * The boot idle thread does lazy MMU switching as well:
         */
        atomic_inc(&init_mm.mm_count);
        enter_lazy_tlb(&init_mm, current);

        /*
         * During early bootup we pretend to be a normal task:
         */
        current->sched_class = &fair_sched_class;

        /*
         * 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());

        calc_load_update = jiffies + LOAD_FREQ;

#ifdef CONFIG_SMP
        zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT);
        /* May be allocated at isolcpus cmdline parse time */
        if (cpu_isolated_map == NULL)
                zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
        idle_thread_set_boot_cpu();
        set_cpu_rq_start_time(smp_processor_id());
#endif
        init_sched_fair_class();

        init_schedstats();

        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)
{
        static unsigned long prev_jiffy;        /* ratelimiting */

        rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
        if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
             !is_idle_task(current)) ||
            system_state != SYSTEM_RUNNING || oops_in_progress)
                return;
        if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
                return;
        prev_jiffy = jiffies;

        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, pid: %d, name: %s\n",
                        in_atomic(), irqs_disabled(),
                        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);
#ifdef CONFIG_DEBUG_PREEMPT
        if (!preempt_count_equals(preempt_offset)) {
                pr_err("Preemption disabled at:");
                print_ip_sym(current->preempt_disable_ip);
                pr_cont("\n");
        }
#endif
        dump_stack();
}
EXPORT_SYMBOL(___might_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;
#ifdef CONFIG_SCHEDSTATS
                p->se.statistics.wait_start     = 0;
                p->se.statistics.sleep_start    = 0;
                p->se.statistics.block_start    = 0;
#endif

                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
/**
 * 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 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 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;

        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);

        WARN_ON(!parent); /* root should already exist */

        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;
        struct rq_flags rf;
        struct rq *rq;

        rq = task_rq_lock(tsk, &rf);

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

        if (queued)
                dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE);
        if (unlikely(running))
                put_prev_task(rq, tsk);

        sched_change_group(tsk, TASK_MOVE_GROUP);

        if (unlikely(running))
                tsk->sched_class->set_curr_task(rq);
        if (queued)
                enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE);

        task_rq_unlock(rq, tsk, &rf);
}
#endif /* CONFIG_CGROUP_SCHED */

#ifdef CONFIG_RT_GROUP_SCHED
/*
 * Ensure that the real time constraints are schedulable.
 */
static DEFINE_MUTEX(rt_constraints_mutex);

/* Must be called with tasklist_lock held */
static inline int tg_has_rt_tasks(struct task_group *tg)
{
        struct task_struct *g, *p;

        /*
         * Autogroups do not have RT tasks; see autogroup_create().
         */
        if (task_group_is_autogroup(tg))
                return 0;

        for_each_process_thread(g, p) {
                if (rt_task(p) && task_group(p) == tg)
                        return 1;
        }

        return 0;
}

struct rt_schedulable_data {
        struct task_group *tg;
        u64 rt_period;
        u64 rt_runtime;
};

static int tg_rt_schedulable(struct task_group *tg, void *data)
{
        struct rt_schedulable_data *d = data;
        struct task_group *child;
        unsigned long total, sum = 0;
        u64 period, runtime;

        period = ktime_to_ns(tg->rt_bandwidth.rt_period);
        runtime = tg->rt_bandwidth.rt_runtime;

        if (tg == d->tg) {
                period = d->rt_period;
                runtime = d->rt_runtime;
        }

        /*
         * Cannot have more runtime than the period.
         */
        if (runtime > period && runtime != RUNTIME_INF)
                return -EINVAL;

        /*
         * Ensure we don't starve existing RT tasks.
         */
        if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
                return -EBUSY;

        total = to_ratio(period, runtime);

        /*
         * Nobody can have more than the global setting allows.
         */
        if (total > to_ratio(global_rt_period(), global_rt_runtime()))
                return -EINVAL;

        /*
         * The sum of our children's runtime should not exceed our own.
         */
        list_for_each_entry_rcu(child, &tg->children, siblings) {
                period = ktime_to_ns(child->rt_bandwidth.rt_period);
                runtime = child->rt_bandwidth.rt_runtime;

                if (child == d->tg) {
                        period = d->rt_period;
                        runtime = d->rt_runtime;
                }

                sum += to_ratio(period, runtime);
        }

        if (sum > total)
                return -EINVAL;

        return 0;
}

static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
{
        int ret;

        struct rt_schedulable_data data = {
                .tg = tg,
                .rt_period = period,
                .rt_runtime = runtime,
        };

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

        return ret;
}

static int tg_set_rt_bandwidth(struct task_group *tg,
                u64 rt_period, u64 rt_runtime)
{
        int i, err = 0;

        /*
         * Disallowing the root group RT runtime is BAD, it would disallow the
         * kernel creating (and or operating) RT threads.
         */
        if (tg == &root_task_group && rt_runtime == 0)
                return -EINVAL;

        /* No period doesn't make any sense. */
        if (rt_period == 0)
                return -EINVAL;

        mutex_lock(&rt_constraints_mutex);
        read_lock(&tasklist_lock);
        err = __rt_schedulable(tg, rt_period, rt_runtime);
        if (err)
                goto unlock;

        raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
        tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
        tg->rt_bandwidth.rt_runtime = rt_runtime;

        for_each_possible_cpu(i) {
                struct rt_rq *rt_rq = tg->rt_rq[i];

                raw_spin_lock(&rt_rq->rt_runtime_lock);
                rt_rq->rt_runtime = rt_runtime;
                raw_spin_unlock(&rt_rq->rt_runtime_lock);
        }
        raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
unlock:
        read_unlock(&tasklist_lock);
        mutex_unlock(&rt_constraints_mutex);

        return err;
}

static int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
{
        u64 rt_runtime, rt_period;

        rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
        rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
        if (rt_runtime_us < 0)
                rt_runtime = RUNTIME_INF;

        return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
}

static long sched_group_rt_runtime(struct task_group *tg)
{
        u64 rt_runtime_us;

        if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF)
                return -1;

        rt_runtime_us = tg->rt_bandwidth.rt_runtime;
        do_div(rt_runtime_us, NSEC_PER_USEC);
        return rt_runtime_us;
}

static int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
{
        u64 rt_runtime, rt_period;

        rt_period = rt_period_us * NSEC_PER_USEC;
        rt_runtime = tg->rt_bandwidth.rt_runtime;

        return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
}

static long sched_group_rt_period(struct task_group *tg)
{
        u64 rt_period_us;

        rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period);
        do_div(rt_period_us, NSEC_PER_USEC);
        return rt_period_us;
}
#endif /* CONFIG_RT_GROUP_SCHED */

#ifdef CONFIG_RT_GROUP_SCHED
static int sched_rt_global_constraints(void)
{
        int ret = 0;

        mutex_lock(&rt_constraints_mutex);
        read_lock(&tasklist_lock);
        ret = __rt_schedulable(NULL, 0, 0);
        read_unlock(&tasklist_lock);
        mutex_unlock(&rt_constraints_mutex);

        return ret;
}

static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
{
        /* Don't accept realtime tasks when there is no way for them to run */
        if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
                return 0;

        return 1;
}

#else /* !CONFIG_RT_GROUP_SCHED */
static int sched_rt_global_constraints(void)
{
        unsigned long flags;
        int i;

        raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
        for_each_possible_cpu(i) {
                struct rt_rq *rt_rq = &cpu_rq(i)->rt;

                raw_spin_lock(&rt_rq->rt_runtime_lock);
                rt_rq->rt_runtime = global_rt_runtime();
                raw_spin_unlock(&rt_rq->rt_runtime_lock);
        }
        raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);

        return 0;
}
#endif /* CONFIG_RT_GROUP_SCHED */

static int sched_dl_global_validate(void)
{
        u64 runtime = global_rt_runtime();
        u64 period = global_rt_period();
        u64 new_bw = to_ratio(period, runtime);
        struct dl_bw *dl_b;
        int cpu, ret = 0;
        unsigned long flags;

        /*
         * Here we want to check the bandwidth not being set to some
         * value smaller than the currently allocated bandwidth in
         * any of the root_domains.
         *
         * FIXME: Cycling on all the CPUs is overdoing, but simpler than
         * cycling on root_domains... Discussion on different/better
         * solutions is welcome!
         */
        for_each_possible_cpu(cpu) {
                rcu_read_lock_sched();
                dl_b = dl_bw_of(cpu);

                raw_spin_lock_irqsave(&dl_b->lock, flags);
                if (new_bw < dl_b->total_bw)
                        ret = -EBUSY;
                raw_spin_unlock_irqrestore(&dl_b->lock, flags);

                rcu_read_unlock_sched();

                if (ret)
                        break;
        }

        return ret;
}

static void sched_dl_do_global(void)
{
        u64 new_bw = -1;
        struct dl_bw *dl_b;
        int cpu;
        unsigned long flags;

        def_dl_bandwidth.dl_period = global_rt_period();
        def_dl_bandwidth.dl_runtime = global_rt_runtime();

        if (global_rt_runtime() != RUNTIME_INF)
                new_bw = to_ratio(global_rt_period(), global_rt_runtime());

        /*
         * FIXME: As above...
         */
        for_each_possible_cpu(cpu) {
                rcu_read_lock_sched();
                dl_b = dl_bw_of(cpu);

                raw_spin_lock_irqsave(&dl_b->lock, flags);
                dl_b->bw = new_bw;
                raw_spin_unlock_irqrestore(&dl_b->lock, flags);

                rcu_read_unlock_sched();
        }
}

static int sched_rt_global_validate(void)
{
        if (sysctl_sched_rt_period <= 0)
                return -EINVAL;

        if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
                (sysctl_sched_rt_runtime > sysctl_sched_rt_period))
                return -EINVAL;

        return 0;
}

static void sched_rt_do_global(void)
{
        def_rt_bandwidth.rt_runtime = global_rt_runtime();
        def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
}

int sched_rt_handler(struct ctl_table *table, int write,
                void __user *buffer, size_t *lenp,
                loff_t *ppos)
{
        int old_period, old_runtime;
        static DEFINE_MUTEX(mutex);
        int ret;

        mutex_lock(&mutex);
        old_period = sysctl_sched_rt_period;
        old_runtime = sysctl_sched_rt_runtime;

        ret = proc_dointvec(table, write, buffer, lenp, ppos);

        if (!ret && write) {
                ret = sched_rt_global_validate();
                if (ret)
                        goto undo;

                ret = sched_dl_global_validate();
                if (ret)
                        goto undo;

                ret = sched_rt_global_constraints();
                if (ret)
                        goto undo;

                sched_rt_do_global();
                sched_dl_do_global();
        }
        if (0) {
undo:
                sysctl_sched_rt_period = old_period;
                sysctl_sched_rt_runtime = old_runtime;
        }
        mutex_unlock(&mutex);

        return ret;
}

int sched_rr_handler(struct ctl_table *table, int write,
                void __user *buffer, size_t *lenp,
                loff_t *ppos)
{
        int ret;
        static DEFINE_MUTEX(mutex);

        mutex_lock(&mutex);
        ret = proc_dointvec(table, write, buffer, lenp, ppos);
        /* make sure that internally we keep jiffies */
        /* also, writing zero resets timeslice to default */
        if (!ret && write) {
                sched_rr_timeslice = sched_rr_timeslice <= 0 ?
                        RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
        }
        mutex_unlock(&mutex);
        return ret;
}

#ifdef CONFIG_CGROUP_SCHED

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);

        sched_online_group(tg, parent);

        return &tg->css;
}

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);

        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;
#else
                /* We don't support RT-tasks being in separate groups */
                if (task->sched_class != &fair_sched_class)
                        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;
}

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);
}

#ifdef CONFIG_FAIR_GROUP_SCHED
static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
                                struct cftype *cftype, u64 shareval)
{
        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 */
const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */

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;

        /*
         * 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;

                raw_spin_lock_irq(&rq->lock);
                cfs_rq->runtime_enabled = runtime_enabled;
                cfs_rq->runtime_remaining = 0;

                if (cfs_rq->throttled)
                        unthrottle_cfs_rq(cfs_rq);
                raw_spin_unlock_irq(&rq->lock);
        }
        if (runtime_was_enabled && !runtime_enabled)
                cfs_bandwidth_usage_dec();
out_unlock:
        mutex_unlock(&cfs_constraints_mutex);
        put_online_cpus();

        return ret;
}

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
                quota = (u64)cfs_quota_us * NSEC_PER_USEC;

        return tg_set_cfs_bandwidth(tg, period, quota);
}

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;
}

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

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

        return tg_set_cfs_bandwidth(tg, period, quota);
}

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, inherit when no
                 * limit is set
                 */
                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_stats_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);

        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_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_stats_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
        { }     /* terminate */
};

struct cgroup_subsys cpu_cgrp_subsys = {
        .css_alloc      = cpu_cgroup_css_alloc,
        .css_released   = cpu_cgroup_css_released,
        .css_free       = cpu_cgroup_css_free,
        .fork           = cpu_cgroup_fork,
        .can_attach     = cpu_cgroup_can_attach,
        .attach         = cpu_cgroup_attach,
        .legacy_cftypes = cpu_files,
        .early_init     = 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] = {
 /* -20 */     88761,     71755,     56483,     46273,     36291,
 /* -15 */     29154,     23254,     18705,     14949,     11916,
 /* -10 */      9548,      7620,      6100,      4904,      3906,
 /*  -5 */      3121,      2501,      1991,      1586,      1277,
 /*   0 */      1024,       820,       655,       526,       423,
 /*   5 */       335,       272,       215,       172,       137,
 /*  10 */       110,        87,        70,        56,        45,
 /*  15 */        36,        29,        23,        18,        15,
};

/*
 * Inverse (2^32/x) values of the 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] = {
 /* -20 */     48388,     59856,     76040,     92818,    118348,
 /* -15 */    147320,    184698,    229616,    287308,    360437,
 /* -10 */    449829,    563644,    704093,    875809,   1099582,
 /*  -5 */   1376151,   1717300,   2157191,   2708050,   3363326,
 /*   0 */   4194304,   5237765,   6557202,   8165337,  10153587,
 /*   5 */  12820798,  15790321,  19976592,  24970740,  31350126,
 /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
 /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
};