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

#include "sched.h"

#include <linux/nospec.h>

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

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

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

#include "pelt.h"
#include "smp.h"

/*
 * Export tracepoints that act as a bare tracehook (ie: have no trace event
 * associated with them) to allow external modules to probe them.
 */
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_cfs_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);

DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);

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

/*
 * Print a warning if need_resched is set for the given duration (if
 * LATENCY_WARN is enabled).
 *
 * If sysctl_resched_latency_warn_once is set, only one warning will be shown
 * per boot.
 */
__read_mostly int sysctl_resched_latency_warn_ms = 100;
__read_mostly int sysctl_resched_latency_warn_once = 1;
#endif /* CONFIG_SCHED_DEBUG */

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

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

__read_mostly int scheduler_running;

#ifdef CONFIG_SCHED_CORE

DEFINE_STATIC_KEY_FALSE(__sched_core_enabled);

/* kernel prio, less is more */
static inline int __task_prio(struct task_struct *p)
{
	if (p->sched_class == &stop_sched_class) /* trumps deadline */
		return -2;

	if (rt_prio(p->prio)) /* includes deadline */
		return p->prio; /* [-1, 99] */

	if (p->sched_class == &idle_sched_class)
		return MAX_RT_PRIO + NICE_WIDTH; /* 140 */

	return MAX_RT_PRIO + MAX_NICE; /* 120, squash fair */
}

/*
 * l(a,b)
 * le(a,b) := !l(b,a)
 * g(a,b)  := l(b,a)
 * ge(a,b) := !l(a,b)
 */

/* real prio, less is less */
static inline bool prio_less(struct task_struct *a, struct task_struct *b, bool in_fi)
{

	int pa = __task_prio(a), pb = __task_prio(b);

	if (-pa < -pb)
		return true;

	if (-pb < -pa)
		return false;

	if (pa == -1) /* dl_prio() doesn't work because of stop_class above */
		return !dl_time_before(a->dl.deadline, b->dl.deadline);

	if (pa == MAX_RT_PRIO + MAX_NICE)	/* fair */
		return cfs_prio_less(a, b, in_fi);

	return false;
}

static inline bool __sched_core_less(struct task_struct *a, struct task_struct *b)
{
	if (a->core_cookie < b->core_cookie)
		return true;

	if (a->core_cookie > b->core_cookie)
		return false;

	/* flip prio, so high prio is leftmost */
	if (prio_less(b, a, task_rq(a)->core->core_forceidle))
		return true;

	return false;
}

#define __node_2_sc(node) rb_entry((node), struct task_struct, core_node)

static inline bool rb_sched_core_less(struct rb_node *a, const struct rb_node *b)
{
	return __sched_core_less(__node_2_sc(a), __node_2_sc(b));
}

static inline int rb_sched_core_cmp(const void *key, const struct rb_node *node)
{
	const struct task_struct *p = __node_2_sc(node);
	unsigned long cookie = (unsigned long)key;

	if (cookie < p->core_cookie)
		return -1;

	if (cookie > p->core_cookie)
		return 1;

	return 0;
}

void sched_core_enqueue(struct rq *rq, struct task_struct *p)
{
	rq->core->core_task_seq++;

	if (!p->core_cookie)
		return;

	rb_add(&p->core_node, &rq->core_tree, rb_sched_core_less);
}

void sched_core_dequeue(struct rq *rq, struct task_struct *p)
{
	rq->core->core_task_seq++;

	if (!sched_core_enqueued(p))
		return;

	rb_erase(&p->core_node, &rq->core_tree);
	RB_CLEAR_NODE(&p->core_node);
}

/*
 * Find left-most (aka, highest priority) task matching @cookie.
 */
static struct task_struct *sched_core_find(struct rq *rq, unsigned long cookie)
{
	struct rb_node *node;

	node = rb_find_first((void *)cookie, &rq->core_tree, rb_sched_core_cmp);
	/*
	 * The idle task always matches any cookie!
	 */
	if (!node)
		return idle_sched_class.pick_task(rq);

	return __node_2_sc(node);
}

static struct task_struct *sched_core_next(struct task_struct *p, unsigned long cookie)
{
	struct rb_node *node = &p->core_node;

	node = rb_next(node);
	if (!node)
		return NULL;

	p = container_of(node, struct task_struct, core_node);
	if (p->core_cookie != cookie)
		return NULL;

	return p;
}

/*
 * Magic required such that:
 *
 *	raw_spin_rq_lock(rq);
 *	...
 *	raw_spin_rq_unlock(rq);
 *
 * ends up locking and unlocking the _same_ lock, and all CPUs
 * always agree on what rq has what lock.
 *
 * XXX entirely possible to selectively enable cores, don't bother for now.
 */

static DEFINE_MUTEX(sched_core_mutex);
static atomic_t sched_core_count;
static struct cpumask sched_core_mask;

static void sched_core_lock(int cpu, unsigned long *flags)
{
	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
	int t, i = 0;

	local_irq_save(*flags);
	for_each_cpu(t, smt_mask)
		raw_spin_lock_nested(&cpu_rq(t)->__lock, i++);
}

static void sched_core_unlock(int cpu, unsigned long *flags)
{
	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
	int t;

	for_each_cpu(t, smt_mask)
		raw_spin_unlock(&cpu_rq(t)->__lock);
	local_irq_restore(*flags);
}

static void __sched_core_flip(bool enabled)
{
	unsigned long flags;
	int cpu, t;

	cpus_read_lock();

	/*
	 * Toggle the online cores, one by one.
	 */
	cpumask_copy(&sched_core_mask, cpu_online_mask);
	for_each_cpu(cpu, &sched_core_mask) {
		const struct cpumask *smt_mask = cpu_smt_mask(cpu);

		sched_core_lock(cpu, &flags);

		for_each_cpu(t, smt_mask)
			cpu_rq(t)->core_enabled = enabled;

		sched_core_unlock(cpu, &flags);

		cpumask_andnot(&sched_core_mask, &sched_core_mask, smt_mask);
	}

	/*
	 * Toggle the offline CPUs.
	 */
	cpumask_copy(&sched_core_mask, cpu_possible_mask);
	cpumask_andnot(&sched_core_mask, &sched_core_mask, cpu_online_mask);

	for_each_cpu(cpu, &sched_core_mask)
		cpu_rq(cpu)->core_enabled = enabled;

	cpus_read_unlock();
}

static void sched_core_assert_empty(void)
{
	int cpu;

	for_each_possible_cpu(cpu)
		WARN_ON_ONCE(!RB_EMPTY_ROOT(&cpu_rq(cpu)->core_tree));
}

static void __sched_core_enable(void)
{
	static_branch_enable(&__sched_core_enabled);
	/*
	 * Ensure all previous instances of raw_spin_rq_*lock() have finished
	 * and future ones will observe !sched_core_disabled().
	 */
	synchronize_rcu();
	__sched_core_flip(true);
	sched_core_assert_empty();
}

static void __sched_core_disable(void)
{
	sched_core_assert_empty();
	__sched_core_flip(false);
	static_branch_disable(&__sched_core_enabled);
}

void sched_core_get(void)
{
	if (atomic_inc_not_zero(&sched_core_count))
		return;

	mutex_lock(&sched_core_mutex);
	if (!atomic_read(&sched_core_count))
		__sched_core_enable();

	smp_mb__before_atomic();
	atomic_inc(&sched_core_count);
	mutex_unlock(&sched_core_mutex);
}

static void __sched_core_put(struct work_struct *work)
{
	if (atomic_dec_and_mutex_lock(&sched_core_count, &sched_core_mutex)) {
		__sched_core_disable();
		mutex_unlock(&sched_core_mutex);
	}
}

void sched_core_put(void)
{
	static DECLARE_WORK(_work, __sched_core_put);

	/*
	 * "There can be only one"
	 *
	 * Either this is the last one, or we don't actually need to do any
	 * 'work'. If it is the last *again*, we rely on
	 * WORK_STRUCT_PENDING_BIT.
	 */
	if (!atomic_add_unless(&sched_core_count, -1, 1))
		schedule_work(&_work);
}

#else /* !CONFIG_SCHED_CORE */

static inline void sched_core_enqueue(struct rq *rq, struct task_struct *p) { }
static inline void sched_core_dequeue(struct rq *rq, struct task_struct *p) { }

#endif /* CONFIG_SCHED_CORE */

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


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

void raw_spin_rq_lock_nested(struct rq *rq, int subclass)
{
	raw_spinlock_t *lock;

	/* Matches synchronize_rcu() in __sched_core_enable() */
	preempt_disable();
	if (sched_core_disabled()) {
		raw_spin_lock_nested(&rq->__lock, subclass);
		/* preempt_count *MUST* be > 1 */
		preempt_enable_no_resched();
		return;
	}

	for (;;) {
		lock = __rq_lockp(rq);
		raw_spin_lock_nested(lock, subclass);
		if (likely(lock == __rq_lockp(rq))) {
			/* preempt_count *MUST* be > 1 */
			preempt_enable_no_resched();
			return;
		}
		raw_spin_unlock(lock);
	}
}

bool raw_spin_rq_trylock(struct rq *rq)
{
	raw_spinlock_t *lock;
	bool ret;

	/* Matches synchronize_rcu() in __sched_core_enable() */
	preempt_disable();
	if (sched_core_disabled()) {
		ret = raw_spin_trylock(&rq->__lock);
		preempt_enable();
		return ret;
	}

	for (;;) {
		lock = __rq_lockp(rq);
		ret = raw_spin_trylock(lock);
		if (!ret || (likely(lock == __rq_lockp(rq)))) {
			preempt_enable();
			return ret;
		}
		raw_spin_unlock(lock);
	}
}

void raw_spin_rq_unlock(struct rq *rq)
{
	raw_spin_unlock(rq_lockp(rq));
}

#ifdef CONFIG_SMP
/*
 * double_rq_lock - safely lock two runqueues
 */
void double_rq_lock(struct rq *rq1, struct rq *rq2)
{
	lockdep_assert_irqs_disabled();

	if (rq_order_less(rq2, rq1))
		swap(rq1, rq2);

	raw_spin_rq_lock(rq1);
	if (__rq_lockp(rq1) == __rq_lockp(rq2))
		return;

	raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING);
}
#endif

/*
 * __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_rq_lock(rq);
		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
			rq_pin_lock(rq, rf);
			return rq;
		}
		raw_spin_rq_unlock(rq);

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

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

/*
 * RQ-clock updating methods:
 */

static void update_rq_clock_task(struct rq *rq, s64 delta)
{
/*
 * In theory, the compile should just see 0 here, and optimize out the call
 * to sched_rt_avg_update. But I don't trust it...
 */
	s64 __maybe_unused steal = 0, irq_delta = 0;

#ifdef CONFIG_IRQ_TIME_ACCOUNTING
	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;

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

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

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

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

	rq->clock_task += delta;

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

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

	lockdep_assert_rq_held(rq);

	if (rq->clock_update_flags & RQCF_ACT_SKIP)
		return;

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

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

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

static void hrtick_clear(struct rq *rq)
{
	if (hrtimer_active(&rq->hrtick_timer))
		hrtimer_cancel(&rq->hrtick_timer);
}

/*
 * High-resolution timer tick.
 * Runs from hardirq context with interrupts disabled.
 */
static enum hrtimer_restart hrtick(struct hrtimer *timer)
{
	struct rq *rq = container_of(timer, struct rq, hrtick_timer);
	struct rq_flags rf;

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

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

	return HRTIMER_NORESTART;
}

#ifdef CONFIG_SMP

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

	hrtimer_start(timer, time, HRTIMER_MODE_ABS_PINNED_HARD);
}

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

	rq_lock(rq, &rf);
	__hrtick_restart(rq);
	rq_unlock(rq, &rf);
}

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

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

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

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

#endif /* CONFIG_SMP */

static void hrtick_rq_init(struct rq *rq)
{
#ifdef CONFIG_SMP
	INIT_CSD(&rq->hrtick_csd, __hrtick_start, rq);
#endif
	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
	rq->hrtick_timer.function = hrtick;
}
#else	/* CONFIG_SCHED_HRTICK */
static inline void hrtick_clear(struct rq *rq)
{
}

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

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

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

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

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

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

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

static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
{
	struct wake_q_node *node = &task->wake_q;

	/*
	 * Atomically grab the task, if ->wake_q is !nil already it means
	 * it's already queued (either by us or someone else) and will get the
	 * wakeup due to that.
	 *
	 * In order to ensure that a pending wakeup will observe our pending
	 * state, even in the failed case, an explicit smp_mb() must be used.
	 */
	smp_mb__before_atomic();
	if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)))
		return false;

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

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

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

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

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

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

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

/*
 * resched_curr - mark rq's current task 'to be rescheduled now'.
 *
 * On UP this means the setting of the need_resched flag, on SMP it
 * might also involve a cross-CPU call to trigger the scheduler on
 * the target CPU.
 */
void resched_curr(struct rq *rq)
{
	struct task_struct *curr = rq->curr;
	int cpu;

	lockdep_assert_rq_held(rq);

	if (test_tsk_need_resched(curr))
		return;

	cpu = cpu_of(rq);

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

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

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

	raw_spin_rq_lock_irqsave(rq, flags);
	if (cpu_online(cpu) || cpu == smp_processor_id())
		resched_curr(rq);
	raw_spin_rq_unlock_irqrestore(rq, flags);
}

#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ_COMMON
/*
 * In the semi idle case, use the nearest busy CPU for migrating timers
 * from an idle CPU.  This is good for power-savings.
 *
 * We don't do similar optimization for completely idle system, as
 * selecting an idle CPU will add more delays to the timers than intended
 * (as that CPU's timer base may not be uptodate wrt jiffies etc).
 */
int get_nohz_timer_target(void)
{
	int i, cpu = smp_processor_id(), default_cpu = -1;
	struct sched_domain *sd;
	const struct cpumask *hk_mask;

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

	hk_mask = housekeeping_cpumask(HK_FLAG_TIMER);

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

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

	if (default_cpu == -1)
		default_cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
	cpu = default_cpu;
unlock:
	rcu_read_unlock();
	return cpu;
}

/*
 * When add_timer_on() enqueues a timer into the timer wheel of an
 * idle CPU then this timer might expire before the next timer event
 * which is scheduled to wake up that CPU. In case of a completely
 * idle system the next event might even be infinite time into the
 * future. wake_up_idle_cpu() ensures that the CPU is woken up and
 * leaves the inner idle loop so the newly added timer is taken into
 * account when the CPU goes back to idle and evaluates the timer
 * wheel for the next timer event.
 */
static void wake_up_idle_cpu(int cpu)
{
	struct rq *rq = cpu_rq(cpu);

	if (cpu == smp_processor_id())
		return;

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

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

	return false;
}

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

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

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

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

#endif /* CONFIG_NO_HZ_COMMON */

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

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

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

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

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

	return true;
}
#endif /* CONFIG_NO_HZ_FULL */
#endif /* CONFIG_SMP */

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

	parent = from;

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

	return uclamp_none(UCLAMP_MIN);
}

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

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

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

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

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

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

	lockdep_assert_held(&p->pi_lock);

	uc_se = &p->uclamp_req[UCLAMP_MIN];

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

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

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

	if (!rt_task(p))
		return;

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

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

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

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

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

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

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

	return uc_req;
}

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

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

	return uc_req;
}

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

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

	uc_eff = uclamp_eff_get(p, clamp_id);

	return (unsigned long)uc_eff.value;
}

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

	lockdep_assert_rq_held(rq);

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

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

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

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

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

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

	lockdep_assert_rq_held(rq);

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

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

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

	uc_se->active = false;

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

	task_rq_unlock(rq, p, &rf);
}

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

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

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

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

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

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

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

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

	if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max ||
	    sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE	||
	    sysctl_sched_uclamp_util_min_rt_default > SCHED_CAPACITY_SCALE) {

		result = -EINVAL;
		goto undo;
	}

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

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

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

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

	goto done;

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

	return result;
}

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

	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
		util_min = attr->sched_util_min;

		if (util_min + 1 > SCHED_CAPACITY_SCALE + 1)
			return -EINVAL;
	}

	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
		util_max = attr->sched_util_max;

		if (util_max + 1 > SCHED_CAPACITY_SCALE + 1)
			return -EINVAL;
	}

	if (util_min != -1 && util_max != -1 && util_min > util_max)
		return -EINVAL;

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

	return 0;
}

static bool uclamp_reset(const struct sched_attr *attr,
			 enum uclamp_id clamp_id,
			 struct uclamp_se *uc_se)
{
	/* Reset on sched class change for a non user-defined clamp value. */
	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)) &&
	    !uc_se->user_defined)
		return true;

	/* Reset on sched_util_{min,max} == -1. */
	if (clamp_id == UCLAMP_MIN &&
	    attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN &&
	    attr->sched_util_min == -1) {
		return true;
	}

	if (clamp_id == UCLAMP_MAX &&
	    attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX &&
	    attr->sched_util_max == -1) {
		return true;
	}

	return false;
}

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

	for_each_clamp_id(clamp_id) {
		struct uclamp_se *uc_se = &p->uclamp_req[clamp_id];
		unsigned int value;

		if (!uclamp_reset(attr, clamp_id, uc_se))
			continue;

		/*
		 * RT by default have a 100% boost value that could be modified
		 * at runtime.
		 */
		if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
			value = sysctl_sched_uclamp_util_min_rt_default;
		else
			value = uclamp_none(clamp_id);

		uclamp_se_set(uc_se, value, false);

	}

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

	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN &&
	    attr->sched_util_min != -1) {
		uclamp_se_set(&p->uclamp_req[UCLAMP_MIN],
			      attr->sched_util_min, true);
	}

	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX &&
	    attr->sched_util_max != -1) {
		uclamp_se_set(&p->uclamp_req[UCLAMP_MAX],
			      attr->sched_util_max, true);
	}
}

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

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

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

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

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

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

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

	rq->uclamp_flags = 0;
}

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

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

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

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

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

bool sched_task_on_rq(struct task_struct *p)
{
	return task_on_rq_queued(p);
}

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

	if (!(flags & ENQUEUE_RESTORE)) {
		sched_info_enqueue(rq, p);
		psi_enqueue(p, flags & ENQUEUE_WAKEUP);
	}

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

	if (sched_core_enabled(rq))
		sched_core_enqueue(rq, p);
}

static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
{
	if (sched_core_enabled(rq))
		sched_core_dequeue(rq, p);

	if (!(flags & DEQUEUE_NOCLOCK))
		update_rq_clock(rq);

	if (!(flags & DEQUEUE_SAVE)) {
		sched_info_dequeue(rq, p);
		psi_dequeue(p, flags & DEQUEUE_SLEEP);
	}

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

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

	p->on_rq = TASK_ON_RQ_QUEUED;
}

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

	dequeue_task(rq, p, flags);
}

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

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

	return prio;
}

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

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

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

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

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

void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
{
	if (p->sched_class == rq->curr->sched_class)
		rq->curr->sched_class->check_preempt_curr(rq, p, flags);
	else if (p->sched_class > rq->curr->sched_class)
		resched_curr(rq);

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

#ifdef CONFIG_SMP

static void
__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags);

static int __set_cpus_allowed_ptr(struct task_struct *p,
				  const struct cpumask *new_mask,
				  u32 flags);

static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
{
	if (likely(!p->migration_disabled))
		return;

	if (p->cpus_ptr != &p->cpus_mask)
		return;

	/*
	 * Violates locking rules! see comment in __do_set_cpus_allowed().
	 */
	__do_set_cpus_allowed(p, cpumask_of(rq->cpu), SCA_MIGRATE_DISABLE);
}

void migrate_disable(void)
{
	struct task_struct *p = current;

	if (p->migration_disabled) {
		p->migration_disabled++;
		return;
	}

	preempt_disable();
	this_rq()->nr_pinned++;
	p->migration_disabled = 1;
	preempt_enable();
}
EXPORT_SYMBOL_GPL(migrate_disable);

void migrate_enable(void)
{
	struct task_struct *p = current;

	if (p->migration_disabled > 1) {
		p->migration_disabled--;
		return;
	}

	/*
	 * Ensure stop_task runs either before or after this, and that
	 * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
	 */
	preempt_disable();
	if (p->cpus_ptr != &p->cpus_mask)
		__set_cpus_allowed_ptr(p, &p->cpus_mask, SCA_MIGRATE_ENABLE);
	/*
	 * Mustn't clear migration_disabled() until cpus_ptr points back at the
	 * regular cpus_mask, otherwise things that race (eg.
	 * select_fallback_rq) get confused.
	 */
	barrier();
	p->migration_disabled = 0;
	this_rq()->nr_pinned--;
	preempt_enable();
}
EXPORT_SYMBOL_GPL(migrate_enable);

static inline bool rq_has_pinned_tasks(struct rq *rq)
{
	return rq->nr_pinned;
}

/*
 * Per-CPU kthreads are allowed to run on !active && online CPUs, see
 * __set_cpus_allowed_ptr() and select_fallback_rq().
 */
static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
{
	/* When not in the task's cpumask, no point in looking further. */
	if (!cpumask_test_cpu(cpu, p->cpus_ptr))
		return false;

	/* migrate_disabled() must be allowed to finish. */
	if (is_migration_disabled(p))
		return cpu_online(cpu);

	/* Non kernel threads are not allowed during either online or offline. */
	if (!(p->flags & PF_KTHREAD))
		return cpu_active(cpu) && task_cpu_possible(cpu, p);

	/* KTHREAD_IS_PER_CPU is always allowed. */
	if (kthread_is_per_cpu(p))
		return cpu_online(cpu);

	/* Regular kernel threads don't get to stay during offline. */
	if (cpu_dying(cpu))
		return false;

	/* But are allowed during online. */
	return cpu_online(cpu);
}

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

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

	deactivate_task(rq, p, DEQUEUE_NOCLOCK);
	set_task_cpu(p, new_cpu);
	rq_unlock(rq, rf);

	rq = cpu_rq(new_cpu);

	rq_lock(rq, rf);
	BUG_ON(task_cpu(p) != new_cpu);
	activate_task(rq, p, 0);
	check_preempt_curr(rq, p, 0);

	return rq;
}

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

/*
 * @refs: number of wait_for_completion()
 * @stop_pending: is @stop_work in use
 */
struct set_affinity_pending {
	refcount_t		refs;
	unsigned int		stop_pending;
	struct completion	done;
	struct cpu_stop_work	stop_work;
	struct migration_arg	arg;
};

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

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

	return rq;
}

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

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

	raw_spin_lock(&p->pi_lock);
	rq_lock(rq, &rf);

	/*
	 * If we were passed a pending, then ->stop_pending was set, thus
	 * p->migration_pending must have remained stable.
	 */
	WARN_ON_ONCE(pending && pending != p->migration_pending);

	/*
	 * If task_rq(p) != rq, it cannot be migrated here, because we're
	 * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
	 * we're holding p->pi_lock.
	 */
	if (task_rq(p) == rq) {
		if (is_migration_disabled(p))
			goto out;

		if (pending) {
			p->migration_pending = NULL;
			complete = true;

			if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask))
				goto out;
		}

		if (task_on_rq_queued(p))
			rq = __migrate_task(rq, &rf, p, arg->dest_cpu);
		else
			p->wake_cpu = arg->dest_cpu;

		/*
		 * XXX __migrate_task() can fail, at which point we might end
		 * up running on a dodgy CPU, AFAICT this can only happen
		 * during CPU hotplug, at which point we'll get pushed out
		 * anyway, so it's probably not a big deal.
		 */

	} else if (pending) {
		/*
		 * This happens when we get migrated between migrate_enable()'s
		 * preempt_enable() and scheduling the stopper task. At that
		 * point we're a regular task again and not current anymore.
		 *
		 * A !PREEMPT kernel has a giant hole here, which makes it far
		 * more likely.
		 */

		/*
		 * The task moved before the stopper got to run. We're holding
		 * ->pi_lock, so the allowed mask is stable - if it got
		 * somewhere allowed, we're done.
		 */
		if (cpumask_test_cpu(task_cpu(p), p->cpus_ptr)) {
			p->migration_pending = NULL;
			complete = true;
			goto out;
		}

		/*
		 * When migrate_enable() hits a rq mis-match we can't reliably
		 * determine is_migration_disabled() and so have to chase after
		 * it.
		 */
		WARN_ON_ONCE(!pending->stop_pending);
		task_rq_unlock(rq, p, &rf);
		stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop,
				    &pending->arg, &pending->stop_work);
		return 0;
	}
out:
	if (pending)
		pending->stop_pending = false;
	task_rq_unlock(rq, p, &rf);

	if (complete)
		complete_all(&pending->done);

	return 0;
}

int push_cpu_stop(void *arg)
{
	struct rq *lowest_rq = NULL, *rq = this_rq();
	struct task_struct *p = arg;

	raw_spin_lock_irq(&p->pi_lock);
	raw_spin_rq_lock(rq);

	if (task_rq(p) != rq)
		goto out_unlock;

	if (is_migration_disabled(p)) {
		p->migration_flags |= MDF_PUSH;
		goto out_unlock;
	}

	p->migration_flags &= ~MDF_PUSH;

	if (p->sched_class->find_lock_rq)
		lowest_rq = p->sched_class->find_lock_rq(p, rq);

	if (!lowest_rq)
		goto out_unlock;

	// XXX validate p is still the highest prio task
	if (task_rq(p) == rq) {
		deactivate_task(rq, p, 0);
		set_task_cpu(p, lowest_rq->cpu);
		activate_task(lowest_rq, p, 0);
		resched_curr(lowest_rq);
	}

	double_unlock_balance(rq, lowest_rq);

out_unlock:
	rq->push_busy = false;
	raw_spin_rq_unlock(rq);
	raw_spin_unlock_irq(&p->pi_lock);

	put_task_struct(p);
	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, u32 flags)
{
	if (flags & (SCA_MIGRATE_ENABLE | SCA_MIGRATE_DISABLE)) {
		p->cpus_ptr = new_mask;
		return;
	}

	cpumask_copy(&p->cpus_mask, new_mask);
	p->nr_cpus_allowed = cpumask_weight(new_mask);
}

static void
__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags)
{
	struct rq *rq = task_rq(p);
	bool queued, running;

	/*
	 * This here violates the locking rules for affinity, since we're only
	 * supposed to change these variables while holding both rq->lock and
	 * p->pi_lock.
	 *
	 * HOWEVER, it magically works, because ttwu() is the only code that
	 * accesses these variables under p->pi_lock and only does so after
	 * smp_cond_load_acquire(&p->on_cpu, !VAL), and we're in __schedule()
	 * before finish_task().
	 *
	 * XXX do further audits, this smells like something putrid.
	 */
	if (flags & SCA_MIGRATE_DISABLE)
		SCHED_WARN_ON(!p->on_cpu);
	else
		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_rq_held(rq);
		dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
	}
	if (running)
		put_prev_task(rq, p);

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

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

void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
{
	__do_set_cpus_allowed(p, new_mask, 0);
}

int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
		      int node)
{
	if (!src->user_cpus_ptr)
		return 0;

	dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
	if (!dst->user_cpus_ptr)
		return -ENOMEM;

	cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
	return 0;
}

static inline struct cpumask *clear_user_cpus_ptr(struct task_struct *p)
{
	struct cpumask *user_mask = NULL;

	swap(p->user_cpus_ptr, user_mask);

	return user_mask;
}

void release_user_cpus_ptr(struct task_struct *p)
{
	kfree(clear_user_cpus_ptr(p));
}

/*
 * This function is wildly self concurrent; here be dragons.
 *
 *
 * When given a valid mask, __set_cpus_allowed_ptr() must block until the
 * designated task is enqueued on an allowed CPU. If that task is currently
 * running, we have to kick it out using the CPU stopper.
 *
 * Migrate-Disable comes along and tramples all over our nice sandcastle.
 * Consider:
 *
 *     Initial conditions: P0->cpus_mask = [0, 1]
 *
 *     P0@CPU0                  P1
 *
 *     migrate_disable();
 *     <preempted>
 *                              set_cpus_allowed_ptr(P0, [1]);
 *
 * P1 *cannot* return from this set_cpus_allowed_ptr() call until P0 executes
 * its outermost migrate_enable() (i.e. it exits its Migrate-Disable region).
 * This means we need the following scheme:
 *
 *     P0@CPU0                  P1
 *
 *     migrate_disable();
 *     <preempted>
 *                              set_cpus_allowed_ptr(P0, [1]);
 *                                <blocks>
 *     <resumes>
 *     migrate_enable();
 *       __set_cpus_allowed_ptr();
 *       <wakes local stopper>
 *                         `--> <woken on migration completion>
 *
 * Now the fun stuff: there may be several P1-like tasks, i.e. multiple
 * concurrent set_cpus_allowed_ptr(P0, [*]) calls. CPU affinity changes of any
 * task p are serialized by p->pi_lock, which we can leverage: the one that
 * should come into effect at the end of the Migrate-Disable region is the last
 * one. This means we only need to track a single cpumask (i.e. p->cpus_mask),
 * but we still need to properly signal those waiting tasks at the appropriate
 * moment.
 *
 * This is implemented using struct set_affinity_pending. The first
 * __set_cpus_allowed_ptr() caller within a given Migrate-Disable region will
 * setup an instance of that struct and install it on the targeted task_struct.
 * Any and all further callers will reuse that instance. Those then wait for
 * a completion signaled at the tail of the CPU stopper callback (1), triggered
 * on the end of the Migrate-Disable region (i.e. outermost migrate_enable()).
 *
 *
 * (1) In the cases covered above. There is one more where the completion is
 * signaled within affine_move_task() itself: when a subsequent affinity request
 * occurs after the stopper bailed out due to the targeted task still being
 * Migrate-Disable. Consider:
 *
 *     Initial conditions: P0->cpus_mask = [0, 1]
 *
 *     CPU0		  P1				P2
 *     <P0>
 *       migrate_disable();
 *       <preempted>
 *                        set_cpus_allowed_ptr(P0, [1]);
 *                          <blocks>
 *     <migration/0>
 *       migration_cpu_stop()
 *         is_migration_disabled()
 *           <bails>
 *                                                       set_cpus_allowed_ptr(P0, [0, 1]);
 *                                                         <signal completion>
 *                          <awakes>
 *
 * Note that the above is safe vs a concurrent migrate_enable(), as any
 * pending affinity completion is preceded by an uninstallation of
 * p->migration_pending done with p->pi_lock held.
 */
static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flags *rf,
			    int dest_cpu, unsigned int flags)
{
	struct set_affinity_pending my_pending = { }, *pending = NULL;
	bool stop_pending, complete = false;

	/* Can the task run on the task's current CPU? If so, we're done */
	if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) {
		struct task_struct *push_task = NULL;

		if ((flags & SCA_MIGRATE_ENABLE) &&
		    (p->migration_flags & MDF_PUSH) && !rq->push_busy) {
			rq->push_busy = true;
			push_task = get_task_struct(p);
		}

		/*
		 * If there are pending waiters, but no pending stop_work,
		 * then complete now.
		 */
		pending = p->migration_pending;
		if (pending && !pending->stop_pending) {
			p->migration_pending = NULL;
			complete = true;
		}

		task_rq_unlock(rq, p, rf);

		if (push_task) {
			stop_one_cpu_nowait(rq->cpu, push_cpu_stop,
					    p, &rq->push_work);
		}

		if (complete)
			complete_all(&pending->done);

		return 0;
	}

	if (!(flags & SCA_MIGRATE_ENABLE)) {
		/* serialized by p->pi_lock */
		if (!p->migration_pending) {
			/* Install the request */
			refcount_set(&my_pending.refs, 1);
			init_completion(&my_pending.done);
			my_pending.arg = (struct migration_arg) {
				.task = p,
				.dest_cpu = dest_cpu,
				.pending = &my_pending,
			};

			p->migration_pending = &my_pending;
		} else {
			pending = p->migration_pending;
			refcount_inc(&pending->refs);
			/*
			 * Affinity has changed, but we've already installed a
			 * pending. migration_cpu_stop() *must* see this, else
			 * we risk a completion of the pending despite having a
			 * task on a disallowed CPU.
			 *
			 * Serialized by p->pi_lock, so this is safe.
			 */
			pending->arg.dest_cpu = dest_cpu;
		}
	}
	pending = p->migration_pending;
	/*
	 * - !MIGRATE_ENABLE:
	 *   we'll have installed a pending if there wasn't one already.
	 *
	 * - MIGRATE_ENABLE:
	 *   we're here because the current CPU isn't matching anymore,
	 *   the only way that can happen is because of a concurrent
	 *   set_cpus_allowed_ptr() call, which should then still be
	 *   pending completion.
	 *
	 * Either way, we really should have a @pending here.
	 */
	if (WARN_ON_ONCE(!pending)) {
		task_rq_unlock(rq, p, rf);
		return -EINVAL;
	}

	if (task_running(rq, p) || READ_ONCE(p->__state) == TASK_WAKING) {
		/*
		 * MIGRATE_ENABLE gets here because 'p == current', but for
		 * anything else we cannot do is_migration_disabled(), punt
		 * and have the stopper function handle it all race-free.
		 */
		stop_pending = pending->stop_pending;
		if (!stop_pending)
			pending->stop_pending = true;

		if (flags & SCA_MIGRATE_ENABLE)
			p->migration_flags &= ~MDF_PUSH;

		task_rq_unlock(rq, p, rf);

		if (!stop_pending) {
			stop_one_cpu_nowait(cpu_of(rq), migration_cpu_stop,
					    &pending->arg, &pending->stop_work);
		}

		if (flags & SCA_MIGRATE_ENABLE)
			return 0;
	} else {

		if (!is_migration_disabled(p)) {
			if (task_on_rq_queued(p))
				rq = move_queued_task(rq, rf, p, dest_cpu);

			if (!pending->stop_pending) {
				p->migration_pending = NULL;
				complete = true;
			}
		}
		task_rq_unlock(rq, p, rf);

		if (complete)
			complete_all(&pending->done);
	}

	wait_for_completion(&pending->done);

	if (refcount_dec_and_test(&pending->refs))
		wake_up_var(&pending->refs); /* No UaF, just an address */

	/*
	 * Block the original owner of &pending until all subsequent callers
	 * have seen the completion and decremented the refcount
	 */
	wait_var_event(&my_pending.refs, !refcount_read(&my_pending.refs));

	/* ARGH */
	WARN_ON_ONCE(my_pending.stop_pending);

	return 0;
}

/*
 * Called with both p->pi_lock and rq->lock held; drops both before returning.
 */
static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
					 const struct cpumask *new_mask,
					 u32 flags,
					 struct rq *rq,
					 struct rq_flags *rf)
	__releases(rq->lock)
	__releases(p->pi_lock)
{
	const struct cpumask *cpu_allowed_mask = task_cpu_possible_mask(p);
	const struct cpumask *cpu_valid_mask = cpu_active_mask;
	bool kthread = p->flags & PF_KTHREAD;
	struct cpumask *user_mask = NULL;
	unsigned int dest_cpu;
	int ret = 0;

	update_rq_clock(rq);

	if (kthread || is_migration_disabled(p)) {
		/*
		 * Kernel threads are allowed on online && !active CPUs,
		 * however, during cpu-hot-unplug, even these might get pushed
		 * away if not KTHREAD_IS_PER_CPU.
		 *
		 * Specifically, migration_disabled() tasks must not fail the
		 * cpumask_any_and_distribute() pick below, esp. so on
		 * SCA_MIGRATE_ENABLE, otherwise we'll not call
		 * set_cpus_allowed_common() and actually reset p->cpus_ptr.
		 */
		cpu_valid_mask = cpu_online_mask;
	}

	if (!kthread && !cpumask_subset(new_mask, cpu_allowed_mask)) {
		ret = -EINVAL;
		goto out;
	}

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

	if (!(flags & SCA_MIGRATE_ENABLE)) {
		if (cpumask_equal(&p->cpus_mask, new_mask))
			goto out;

		if (WARN_ON_ONCE(p == current &&
				 is_migration_disabled(p) &&
				 !cpumask_test_cpu(task_cpu(p), new_mask))) {
			ret = -EBUSY;
			goto out;
		}
	}

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

	__do_set_cpus_allowed(p, new_mask, flags);

	if (flags & SCA_USER)
		user_mask = clear_user_cpus_ptr(p);

	ret = affine_move_task(rq, p, rf, dest_cpu, flags);

	kfree(user_mask);

	return ret;

out:
	task_rq_unlock(rq, p, rf);

	return ret;
}

/*
 * 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, u32 flags)
{
	struct rq_flags rf;
	struct rq *rq;

	rq = task_rq_lock(p, &rf);
	return __set_cpus_allowed_ptr_locked(p, new_mask, flags, rq, &rf);
}

int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
{
	return __set_cpus_allowed_ptr(p, new_mask, 0);
}
EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);

/*
 * Change a given task's CPU affinity to the intersection of its current
 * affinity mask and @subset_mask, writing the resulting mask to @new_mask
 * and pointing @p->user_cpus_ptr to a copy of the old mask.
 * If the resulting mask is empty, leave the affinity unchanged and return
 * -EINVAL.
 */
static int restrict_cpus_allowed_ptr(struct task_struct *p,
				     struct cpumask *new_mask,
				     const struct cpumask *subset_mask)
{
	struct cpumask *user_mask = NULL;
	struct rq_flags rf;
	struct rq *rq;
	int err;

	if (!p->user_cpus_ptr) {
		user_mask = kmalloc(cpumask_size(), GFP_KERNEL);
		if (!user_mask)
			return -ENOMEM;
	}

	rq = task_rq_lock(p, &rf);

	/*
	 * Forcefully restricting the affinity of a deadline task is
	 * likely to cause problems, so fail and noisily override the
	 * mask entirely.
	 */
	if (task_has_dl_policy(p) && dl_bandwidth_enabled()) {
		err = -EPERM;
		goto err_unlock;
	}

	if (!cpumask_and(new_mask, &p->cpus_mask, subset_mask)) {
		err = -EINVAL;
		goto err_unlock;
	}

	/*
	 * We're about to butcher the task affinity, so keep track of what
	 * the user asked for in case we're able to restore it later on.
	 */
	if (user_mask) {
		cpumask_copy(user_mask, p->cpus_ptr);
		p->user_cpus_ptr = user_mask;
	}

	return __set_cpus_allowed_ptr_locked(p, new_mask, 0, rq, &rf);

err_unlock:
	task_rq_unlock(rq, p, &rf);
	kfree(user_mask);
	return err;
}

/*
 * Restrict the CPU affinity of task @p so that it is a subset of
 * task_cpu_possible_mask() and point @p->user_cpu_ptr to a copy of the
 * old affinity mask. If the resulting mask is empty, we warn and walk
 * up the cpuset hierarchy until we find a suitable mask.
 */
void force_compatible_cpus_allowed_ptr(struct task_struct *p)
{
	cpumask_var_t new_mask;
	const struct cpumask *override_mask = task_cpu_possible_mask(p);

	alloc_cpumask_var(&new_mask, GFP_KERNEL);

	/*
	 * __migrate_task() can fail silently in the face of concurrent
	 * offlining of the chosen destination CPU, so take the hotplug
	 * lock to ensure that the migration succeeds.
	 */
	cpus_read_lock();
	if (!cpumask_available(new_mask))
		goto out_set_mask;

	if (!restrict_cpus_allowed_ptr(p, new_mask, override_mask))
		goto out_free_mask;

	/*
	 * We failed to find a valid subset of the affinity mask for the
	 * task, so override it based on its cpuset hierarchy.
	 */
	cpuset_cpus_allowed(p, new_mask);
	override_mask = new_mask;

out_set_mask:
	if (printk_ratelimit()) {
		printk_deferred("Overriding affinity for process %d (%s) to CPUs %*pbl\n",
				task_pid_nr(p), p->comm,
				cpumask_pr_args(override_mask));
	}

	WARN_ON(set_cpus_allowed_ptr(p, override_mask));
out_free_mask:
	cpus_read_unlock();
	free_cpumask_var(new_mask);
}

static int
__sched_setaffinity(struct task_struct *p, const struct cpumask *mask);

/*
 * Restore the affinity of a task @p which was previously restricted by a
 * call to force_compatible_cpus_allowed_ptr(). This will clear (and free)
 * @p->user_cpus_ptr.
 *
 * It is the caller's responsibility to serialise this with any calls to
 * force_compatible_cpus_allowed_ptr(@p).
 */
void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
{
	struct cpumask *user_mask = p->user_cpus_ptr;
	unsigned long flags;

	/*
	 * Try to restore the old affinity mask. If this fails, then
	 * we free the mask explicitly to avoid it being inherited across
	 * a subsequent fork().
	 */
	if (!user_mask || !__sched_setaffinity(p, user_mask))
		return;

	raw_spin_lock_irqsave(&p->pi_lock, flags);
	user_mask = clear_user_cpus_ptr(p);
	raw_spin_unlock_irqrestore(&p->pi_lock, flags);

	kfree(user_mask);
}

void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
{
#ifdef CONFIG_SCHED_DEBUG
	unsigned int state = READ_ONCE(p->__state);

	/*
	 * We should never call set_task_cpu() on a blocked task,
	 * ttwu() will sort out the placement.
	 */
	WARN_ON_ONCE(state != TASK_RUNNING && 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(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(__rq_lockp(task_rq(p)))));
#endif
	/*
	 * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
	 */
	WARN_ON_ONCE(!cpu_online(new_cpu));

	WARN_ON_ONCE(is_migration_disabled(p));
#endif

	trace_sched_migrate_task(p, new_cpu);

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

	__set_task_cpu(p, new_cpu);
}

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

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

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

		deactivate_task(src_rq, p, 0);
		set_task_cpu(p, cpu);
		activate_task(dst_rq, p, 0);
		check_preempt_curr(dst_rq, p, 0);

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

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

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

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

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

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

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

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

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

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

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

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

	ret = 0;

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

	return ret;
}

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

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

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

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

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

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

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

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

/*
 * wait_task_inactive - wait for a thread to unschedule.
 *
 * If @match_state is nonzero, it's the @p->state value just checked and
 * not expected to change.  If it changes, i.e. @p might have woken up,
 * then return zero.  When we succeed in waiting for @p to be off its CPU,
 * we return a positive number (its total switch count).  If a second call
 * a short while later returns the same number, the caller can be sure that
 * @p has remained unscheduled the whole time.
 *
 * The caller must ensure that the task *will* unschedule sometime soon,
 * else this function might spin for a *long* time. This function can't
 * be called with interrupts off, or it may introduce deadlock with
 * smp_call_function() if an IPI is sent by the same process we are
 * waiting to become inactive.
 */
unsigned long wait_task_inactive(struct task_struct *p, unsigned int 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(READ_ONCE(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 || READ_ONCE(p->__state) == match_state)
			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
		task_rq_unlock(rq, p, &rf);

		/*
		 * If it changed from the expected state, bail out now.
		 */
		if (unlikely(!ncsw))
			break;

		/*
		 * Was it really running after all now that we
		 * checked with the proper locks actually held?
		 *
		 * Oops. Go back and try again..
		 */
		if (unlikely(running)) {
			cpu_relax();
			continue;
		}

		/*
		 * It's not enough that it's not actively running,
		 * it must be off the runqueue _entirely_, and not
		 * preempted!
		 *
		 * So if it was still runnable (but just not actively
		 * running right now), it's preempted, and we should
		 * yield - it could be a while.
		 */
		if (unlikely(queued)) {
			ktime_t to = NSEC_PER_SEC / HZ;

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

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

	return ncsw;
}

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

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

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

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

			goto out;
		}

		/* No more Mr. Nice Guy. */
		switch (state) {
		case cpuset:
			if (cpuset_cpus_allowed_fallback(p)) {
				state = possible;
				break;
			}
			fallthrough;
		case possible:
			/*
			 * XXX When called from select_task_rq() we only
			 * hold p->pi_lock and again violate locking order.
			 *
			 * More yuck to audit.
			 */
			do_set_cpus_allowed(p, task_cpu_possible_mask(p));
			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_ptr is stable.
 */
static inline
int select_task_rq(struct task_struct *p, int cpu, int wake_flags)
{
	lockdep_assert_held(&p->pi_lock);

	if (p->nr_cpus_allowed > 1 && !is_migration_disabled(p))
		cpu = p->sched_class->select_task_rq(p, cpu, wake_flags);
	else
		cpu = cpumask_any(p->cpus_ptr);

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

	return cpu;
}

void sched_set_stop_task(int cpu, struct task_struct *stop)
{
	static struct lock_class_key stop_pi_lock;
	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;

		/*
		 * The PI code calls rt_mutex_setprio() with ->pi_lock held to
		 * adjust the effective priority of a task. As a result,
		 * rt_mutex_setprio() can trigger (RT) balancing operations,
		 * which can then trigger wakeups of the stop thread to push
		 * around the current task.
		 *
		 * The stop task itself will never be part of the PI-chain, it
		 * never blocks, therefore that ->pi_lock recursion is safe.
		 * Tell lockdep about this by placing the stop->pi_lock in its
		 * own class.
		 */
		lockdep_set_class(&stop->pi_lock, &stop_pi_lock);
	}

	cpu_rq(cpu)->stop = stop;

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

#else /* CONFIG_SMP */

static inline int __set_cpus_allowed_ptr(struct task_struct *p,
					 const struct cpumask *new_mask,
					 u32 flags)
{
	return set_cpus_allowed_ptr(p, new_mask);
}

static inline void migrate_disable_switch(struct rq *rq, struct task_struct *p) { }

static inline bool rq_has_pinned_tasks(struct rq *rq)
{
	return false;
}

#endif /* !CONFIG_SMP */

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

	if (!schedstat_enabled())
		return;

	rq = this_rq();

#ifdef CONFIG_SMP
	if (cpu == rq->cpu) {
		__schedstat_inc(rq->ttwu_local);
		__schedstat_inc(p->se.statistics.nr_wakeups_local);
	} else {
		struct sched_domain *sd;

		__schedstat_inc(p->se.statistics.nr_wakeups_remote);
		rcu_read_lock();
		for_each_domain(rq->cpu, sd) {
			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
				__schedstat_inc(sd->ttwu_wake_remote);
				break;
			}
		}
		rcu_read_unlock();
	}

	if (wake_flags & WF_MIGRATED)
		__schedstat_inc(p->se.statistics.nr_wakeups_migrate);
#endif /* CONFIG_SMP */

	__schedstat_inc(rq->ttwu_count);
	__schedstat_inc(p->se.statistics.nr_wakeups);

	if (wake_flags & WF_SYNC)
		__schedstat_inc(p->se.statistics.nr_wakeups_sync);
}

/*
 * Mark the task runnable and perform wakeup-preemption.
 */
static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
			   struct rq_flags *rf)
{
	check_preempt_curr(rq, p, wake_flags);
	WRITE_ONCE(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 it's safe to
		 * drop the rq->lock, hereafter rq is only used for statistics.
		 */
		rq_unpin_lock(rq, rf);
		p->sched_class->task_woken(rq, p);
		rq_repin_lock(rq, rf);
	}

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

		update_avg(&rq->avg_idle, delta);

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

		rq->wake_stamp = jiffies;
		rq->wake_avg_idle = rq->avg_idle / 2;

		rq->idle_stamp = 0;
	}
#endif
}

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

	lockdep_assert_rq_held(rq);

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

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

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

/*
 * Consider @p being inside a wait loop:
 *
 *   for (;;) {
 *      set_current_state(TASK_UNINTERRUPTIBLE);
 *
 *      if (CONDITION)
 *         break;
 *
 *      schedule();
 *   }
 *   __set_current_state(TASK_RUNNING);
 *
 * between set_current_state() and schedule(). In this case @p is still
 * runnable, so all that needs doing is change p->state back to TASK_RUNNING in
 * an atomic manner.
 *
 * By taking task_rq(p)->lock we serialize against schedule(), if @p->on_rq
 * then schedule() must still happen and p->state can be changed to
 * TASK_RUNNING. Otherwise we lost the race, schedule() has happened, and we
 * need to do a full wakeup with enqueue.
 *
 * Returns: %true when the wakeup is done,
 *          %false otherwise.
 */
static int ttwu_runnable(struct task_struct *p, int wake_flags)
{
	struct rq_flags rf;
	struct rq *rq;
	int ret = 0;

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

	return ret;
}

#ifdef CONFIG_SMP
void sched_ttwu_pending(void *arg)
{
	struct llist_node *llist = arg;
	struct rq *rq = this_rq();
	struct task_struct *p, *t;
	struct rq_flags rf;

	if (!llist)
		return;

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

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

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

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

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

	rq_unlock_irqrestore(rq, &rf);
}

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

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

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

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

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

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

	rcu_read_lock();

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

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

out:
	rcu_read_unlock();
}

bool cpus_share_cache(int this_cpu, int that_cpu)
{
	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
}

static inline bool ttwu_queue_cond(int cpu, int wake_flags)
{
	/*
	 * Do not complicate things with the async wake_list while the CPU is
	 * in hotplug state.
	 */
	if (!cpu_active(cpu))
		return false;

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

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

	return false;
}

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

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

	return false;
}

#else /* !CONFIG_SMP */

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

#endif /* CONFIG_SMP */

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

	if (ttwu_queue_wakelist(p, cpu, wake_flags))
		return;

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

/*
 * Invoked from try_to_wake_up() to check whether the task can be woken up.
 *
 * The caller holds p::pi_lock if p != current or has preemption
 * disabled when p == current.
 *
 * The rules of PREEMPT_RT saved_state:
 *
 *   The related locking code always holds p::pi_lock when updating
 *   p::saved_state, which means the code is fully serialized in both cases.
 *
 *   The lock wait and lock wakeups happen via TASK_RTLOCK_WAIT. No other
 *   bits set. This allows to distinguish all wakeup scenarios.
 */
static __always_inline
bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
{
	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
		WARN_ON_ONCE((state & TASK_RTLOCK_WAIT) &&
			     state != TASK_RTLOCK_WAIT);
	}

	if (READ_ONCE(p->__state) & state) {
		*success = 1;
		return true;
	}

#ifdef CONFIG_PREEMPT_RT
	/*
	 * Saved state preserves the task state across blocking on
	 * an RT lock.  If the state matches, set p::saved_state to
	 * TASK_RUNNING, but do not wake the task because it waits
	 * for a lock wakeup. Also indicate success because from
	 * the regular waker's point of view this has succeeded.
	 *
	 * After acquiring the lock the task will restore p::__state
	 * from p::saved_state which ensures that the regular
	 * wakeup is not lost. The restore will also set
	 * p::saved_state to TASK_RUNNING so any further tests will
	 * not result in false positives vs. @success
	 */
	if (p->saved_state & state) {
		p->saved_state = TASK_RUNNING;
		*success = 1;
	}
#endif
	return false;
}

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

/**
 * try_to_wake_up - wake up a thread
 * @p: the thread to be awakened
 * @state: the mask of task states that can be woken
 * @wake_flags: wake modifier flags (WF_*)
 *
 * Conceptually does:
 *
 *   If (@state & @p->state) @p->state = TASK_RUNNING.
 *
 * If the task was not queued/runnable, also place it back on a runqueue.
 *
 * This function is atomic against schedule() which would dequeue the task.
 *
 * It issues a full memory barrier before accessing @p->state, see the comment
 * with set_current_state().
 *
 * Uses p->pi_lock to serialize against concurrent wake-ups.
 *
 * Relies on p->pi_lock stabilizing:
 *  - p->sched_class
 *  - p->cpus_ptr
 *  - p->sched_task_group
 * in order to do migration, see its use of select_task_rq()/set_task_cpu().
 *
 * Tries really hard to only take one task_rq(p)->lock for performance.
 * Takes rq->lock in:
 *  - ttwu_runnable()    -- old rq, unavoidable, see comment there;
 *  - ttwu_queue()       -- new rq, for enqueue of the task;
 *  - psi_ttwu_dequeue() -- much sadness :-( accounting will kill us.
 *
 * As a consequence we race really badly with just about everything. See the
 * many memory barriers and their comments for details.
 *
 * Return: %true if @p->state changes (an actual wakeup was done),
 *	   %false otherwise.
 */
static int
try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
{
	unsigned long flags;
	int cpu, success = 0;

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

		trace_sched_waking(p);
		WRITE_ONCE(p->__state, TASK_RUNNING);
		trace_sched_wakeup(p);
		goto out;
	}

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

	trace_sched_waking(p);

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

#ifdef CONFIG_SMP
	/*
	 * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
	 * possible to, falsely, observe p->on_cpu == 0.
	 *
	 * One must be running (->on_cpu == 1) in order to remove oneself
	 * from the runqueue.
	 *
	 * __schedule() (switch to task 'p')	try_to_wake_up()
	 *   STORE p->on_cpu = 1		  LOAD p->on_rq
	 *   UNLOCK rq->lock
	 *
	 * __schedule() (put 'p' to sleep)
	 *   LOCK rq->lock			  smp_rmb();
	 *   smp_mb__after_spinlock();
	 *   STORE p->on_rq = 0			  LOAD p->on_cpu
	 *
	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
	 * __schedule().  See the comment for smp_mb__after_spinlock().
	 *
	 * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
	 * schedule()'s deactivate_task() has 'happened' and p will no longer
	 * care about it's own p->state. See the comment in __schedule().
	 */
	smp_acquire__after_ctrl_dep();

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

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

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

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

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

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

	return success;
}

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

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

/**
 * wake_up_process - Wake up a specific process
 * @p: The process to be woken up.
 *
 * Attempt to wake up the nominated process and move it to the set of runnable
 * processes.
 *
 * Return: 1 if the process was woken up, 0 if it was already running.
 *
 * This function executes a full memory barrier before accessing the task state.
 */
int wake_up_process(struct task_struct *p)
{
	return try_to_wake_up(p, TASK_NORMAL, 0);
}
EXPORT_SYMBOL(wake_up_process);

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

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

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

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

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

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

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

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

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

DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);

#ifdef CONFIG_NUMA_BALANCING

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

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

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

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

#ifdef CONFIG_SCHEDSTATS

DEFINE_STATIC_KEY_FALSE(sched_schedstats);

static 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;

	if (!strcmp(str, "enable")) {
		set_schedstats(true);
		ret = 1;
	} else if (!strcmp(str, "disable")) {
		set_schedstats(false);
		ret = 1;
	}
out:
	if (!ret)
		pr_warn("Unable to parse schedstats=\n");

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

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

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

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

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

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

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

	uclamp_fork(p);

	/*
	 * Revert to default priority/policy on fork if requested.
	 */
	if (unlikely(p->sched_reset_on_fork)) {
		if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
			p->policy = SCHED_NORMAL;
			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 = p->static_prio;
		set_load_weight(p, false);

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

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

	init_entity_runnable_average(&p->se);

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

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

void sched_post_fork(struct task_struct *p)
{
	uclamp_post_fork(p);
}

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

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

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

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

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

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

#ifdef CONFIG_PREEMPT_NOTIFIERS

static DEFINE_STATIC_KEY_FALSE(preempt_notifier_key);

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

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

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

	hlist_add_head(&notifier->link, &current->preempt_notifiers);
}
EXPORT_SYMBOL_GPL(preempt_notifier_register);

/**
 * preempt_notifier_unregister - no longer interested in preemption notifications
 * @notifier: notifier struct to unregister
 *
 * This is *not* safe to call from within a preemption notifier.
 */
void preempt_notifier_unregister(struct preempt_notifier *notifier)
{
	hlist_del(&notifier->link);
}
EXPORT_SYMBOL_GPL(preempt_notifier_unregister);

static void __fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
	struct preempt_notifier *notifier;

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

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

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

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

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

#else /* !CONFIG_PREEMPT_NOTIFIERS */

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

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

#endif /* CONFIG_PREEMPT_NOTIFIERS */

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

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

#ifdef CONFIG_SMP

static void do_balance_callbacks(struct rq *rq, struct callback_head *head)
{
	void (*func)(struct rq *rq);
	struct callback_head *next;

	lockdep_assert_rq_held(rq);

	while (head) {
		func = (void (*)(struct rq *))head->func;
		next = head->next;
		head->next = NULL;
		head = next;

		func(rq);
	}
}

static void balance_push(struct rq *rq);

struct callback_head balance_push_callback = {
	.next = NULL,
	.func = (void (*)(struct callback_head *))balance_push,
};

static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
{
	struct callback_head *head = rq->balance_callback;

	lockdep_assert_rq_held(rq);
	if (head)
		rq->balance_callback = NULL;

	return head;
}

static void __balance_callbacks(struct rq *rq)
{
	do_balance_callbacks(rq, splice_balance_callbacks(rq));
}

static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
{
	unsigned long flags;

	if (unlikely(head)) {
		raw_spin_rq_lock_irqsave(rq, flags);
		do_balance_callbacks(rq, head);
		raw_spin_rq_unlock_irqrestore(rq, flags);
	}
}

#else

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

static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
{
	return NULL;
}

static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
{
}

#endif

static inline void
prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf)
{
	/*
	 * Since the runqueue lock will be released by the next
	 * task (which is an invalid locking op but in the case
	 * of the scheduler it's an obvious special-case), so we
	 * do an early lockdep release here:
	 */
	rq_unpin_lock(rq, rf);
	spin_release(&__rq_lockp(rq)->dep_map, _THIS_IP_);
#ifdef CONFIG_DEBUG_SPINLOCK
	/* this is a valid case when another task releases the spinlock */
	rq_lockp(rq)->owner = next;
#endif
}

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

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

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

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

static inline void kmap_local_sched_out(void)
{
#ifdef CONFIG_KMAP_LOCAL
	if (unlikely(current->kmap_ctrl.idx))
		__kmap_local_sched_out();
#endif
}

static inline void kmap_local_sched_in(void)
{
#ifdef CONFIG_KMAP_LOCAL
	if (unlikely(current->kmap_ctrl.idx))
		__kmap_local_sched_in();
#endif
}

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

/**
 * finish_task_switch - clean up after a task-switch
 * @prev: the thread we just switched away from.
 *
 * finish_task_switch must be called after the context switch, paired
 * with a prepare_task_switch call before the context switch.
 * finish_task_switch will reconcile locking set up by prepare_task_switch,
 * and do any other architecture-specific cleanup actions.
 *
 * Note that we may have delayed dropping an mm in context_switch(). If
 * so, we finish that here outside of the runqueue lock. (Doing it
 * with the lock held can cause deadlocks; see schedule() for
 * details.)
 *
 * The context switch have flipped the stack from under us and restored the
 * local variables which were saved when this task called schedule() in the
 * past. prev == current is still correct but we need to recalculate this_rq
 * because prev may have moved to another CPU.
 */
static struct rq *finish_task_switch(struct task_struct *prev)
	__releases(rq->lock)
{
	struct rq *rq = this_rq();
	struct mm_struct *mm = rq->prev_mm;
	long prev_state;

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

	rq->prev_mm = NULL;

	/*
	 * A task struct has one reference for the use as "current".
	 * If a task dies, then it sets TASK_DEAD in tsk->state and calls
	 * schedule one last time. The schedule call will never return, and
	 * the scheduled task must drop that reference.
	 *
	 * We must observe prev->state before clearing prev->on_cpu (in
	 * finish_task), otherwise a concurrent wakeup can get prev
	 * running on another CPU and we could rave with its RUNNING -> DEAD
	 * transition, resulting in a double drop.
	 */
	prev_state = READ_ONCE(prev->__state);
	vtime_task_switch(prev);
	perf_event_task_sched_in(prev, current);
	finish_task(prev);
	tick_nohz_task_switch();
	finish_lock_switch(rq);
	finish_arch_post_lock_switch();
	kcov_finish_switch(current);
	/*
	 * kmap_local_sched_out() is invoked with rq::lock held and
	 * interrupts disabled. There is no requirement for that, but the
	 * sched out code does not have an interrupt enabled section.
	 * Restoring the maps on sched in does not require interrupts being
	 * disabled either.
	 */
	kmap_local_sched_in();

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

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

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

		put_task_struct_rcu_user(prev);
	}

	return rq;
}

/**
 * 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)
{
	/*
	 * 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).
	 */

	finish_task_switch(prev);
	preempt_enable();

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

	calculate_sigpending();
}

/*
 * context_switch - switch to the new MM and the new thread's register state.
 */
static __always_inline struct rq *
context_switch(struct rq *rq, struct task_struct *prev,
	       struct task_struct *next, struct rq_flags *rf)
{
	prepare_task_switch(rq, prev, next);

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

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

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

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

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

	prepare_lock_switch(rq, next, rf);

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

	return finish_task_switch(prev);
}

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

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

	return sum;
}

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

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

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

	return sum;
}

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

unsigned int nr_iowait_cpu(int cpu)
{
	return atomic_read(&cpu_rq(cpu)->nr_iowait);
}

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

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

	for_each_possible_cpu(i)
		sum += nr_iowait_cpu(i);

	return sum;
}

#ifdef CONFIG_SMP

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

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

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

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

#endif

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

EXPORT_PER_CPU_SYMBOL(kstat);
EXPORT_PER_CPU_SYMBOL(kernel_cpustat);

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

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

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

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

	return ns;
}

#ifdef CONFIG_SCHED_DEBUG
static u64 cpu_resched_latency(struct rq *rq)
{
	int latency_warn_ms = READ_ONCE(sysctl_resched_latency_warn_ms);
	u64 resched_latency, now = rq_clock(rq);
	static bool warned_once;

	if (sysctl_resched_latency_warn_once && warned_once)
		return 0;

	if (!need_resched() || !latency_warn_ms)
		return 0;

	if (system_state == SYSTEM_BOOTING)
		return 0;

	if (!rq->last_seen_need_resched_ns) {
		rq->last_seen_need_resched_ns = now;
		rq->ticks_without_resched = 0;
		return 0;
	}

	rq->ticks_without_resched++;
	resched_latency = now - rq->last_seen_need_resched_ns;
	if (resched_latency <= latency_warn_ms * NSEC_PER_MSEC)
		return 0;

	warned_once = true;

	return resched_latency;
}

static int __init setup_resched_latency_warn_ms(char *str)
{
	long val;

	if ((kstrtol(str, 0, &val))) {
		pr_warn("Unable to set resched_latency_warn_ms\n");
		return 1;
	}

	sysctl_resched_latency_warn_ms = val;
	return 1;
}
__setup("resched_latency_warn_ms=", setup_resched_latency_warn_ms);
#else
static inline u64 cpu_resched_latency(struct rq *rq) { return 0; }
#endif /* CONFIG_SCHED_DEBUG */

/*
 * This function gets called by the timer code, with HZ frequency.
 * We call it with interrupts disabled.
 */
void scheduler_tick(void)
{
	int cpu = smp_processor_id();
	struct rq *rq = cpu_rq(cpu);
	struct task_struct *curr = rq->curr;
	struct rq_flags rf;
	unsigned long thermal_pressure;
	u64 resched_latency;

	arch_scale_freq_tick();
	sched_clock_tick();

	rq_lock(rq, &rf);

	update_rq_clock(rq);
	thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
	update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure);
	curr->sched_class->task_tick(rq, curr, 0);
	if (sched_feat(LATENCY_WARN))
		resched_latency = cpu_resched_latency(rq);
	calc_global_load_tick(rq);

	rq_unlock(rq, &rf);

	if (sched_feat(LATENCY_WARN) && resched_latency)
		resched_latency_warn(cpu, resched_latency);

	perf_event_task_tick();

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

#ifdef CONFIG_NO_HZ_FULL

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

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

static struct tick_work __percpu *tick_work_cpu;

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

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

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

	update_rq_clock(rq);

	if (!is_idle_task(curr)) {
		/*
		 * Make sure the next tick runs within a reasonable
		 * amount of time.
		 */
		delta = rq_clock_task(rq) - curr->se.exec_start;
		WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
	}
	curr->sched_class->task_tick(rq, curr, 0);

	calc_load_nohz_remote(rq);
out_unlock:
	rq_unlock_irq(rq, &rf);
out_requeue:

	/*
	 * Run the remote tick once per second (1Hz). This arbitrary
	 * frequency is large enough to avoid overload but short enough
	 * to keep scheduler internal stats reasonably up to date.  But
	 * first update state to reflect hotplug activity if required.
	 */
	os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING);
	WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE);
	if (os == TICK_SCHED_REMOTE_RUNNING)
		queue_delayed_work(system_unbound_wq, dwork, HZ);
}

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

	if (housekeeping_cpu(cpu, HK_FLAG_TICK))
		return;

	WARN_ON_ONCE(!tick_work_cpu);

	twork = per_cpu_ptr(tick_work_cpu, cpu);
	os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING);
	WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING);
	if (os == TICK_SCHED_REMOTE_OFFLINE) {
		twork->cpu = cpu;
		INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
		queue_delayed_work(system_unbound_wq, &twork->work, HZ);
	}
}

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

	if (housekeeping_cpu(cpu, HK_FLAG_TICK))
		return;

	WARN_ON_ONCE(!tick_work_cpu);

	twork = per_cpu_ptr(tick_work_cpu, cpu);
	/* There cannot be competing actions, but don't rely on stop-machine. */
	os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING);
	WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING);
	/* Don't cancel, as this would mess up the state machine. */
}
#endif /* CONFIG_HOTPLUG_CPU */

int __init sched_tick_offload_init(void)
{
	tick_work_cpu = alloc_percpu(struct tick_work);
	BUG_ON(!tick_work_cpu);
	return 0;
}

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

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

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

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

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

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

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

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

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

	if (oops_in_progress)
		return;

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

	debug_show_held_locks(prev);
	print_modules();
	if (irqs_disabled())
		print_irqtrace_events(prev);
	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
	    && in_atomic_preempt_off()) {
		pr_err("Preemption disabled at:");
		print_ip_sym(KERN_ERR, preempt_disable_ip);
	}
	if (panic_on_warn)
		panic("scheduling while atomic\n");

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

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

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

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

	if (unlikely(in_atomic_preempt_off())) {
		__schedule_bug(prev);
		preempt_count_set(PREEMPT_DISABLED);
	}
	rcu_sleep_check();
	SCHED_WARN_ON(ct_state() == CONTEXT_USER);

	profile_hit(SCHED_PROFILING, __builtin_return_address(0));

	schedstat_inc(this_rq()->sched_count);
}

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

	put_prev_task(rq, prev);
}

/*
 * Pick up the highest-prio task:
 */
static inline struct task_struct *
__pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
	const struct sched_class *class;
	struct task_struct *p;

	/*
	 * Optimization: we know that if all tasks are in the fair class we can
	 * call that function directly, but only if the @prev task wasn't of a
	 * higher scheduling class, because otherwise those lose the
	 * opportunity to pull in more work from other CPUs.
	 */
	if (likely(prev->sched_class <= &fair_sched_class &&
		   rq->nr_running == rq->cfs.h_nr_running)) {

		p = pick_next_task_fair(rq, prev, rf);
		if (unlikely(p == RETRY_TASK))
			goto restart;

		/* Assume the next prioritized class is idle_sched_class */
		if (!p) {
			put_prev_task(rq, prev);
			p = pick_next_task_idle(rq);
		}

		return p;
	}

restart:
	put_prev_task_balance(rq, prev, rf);

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

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

#ifdef CONFIG_SCHED_CORE
static inline bool is_task_rq_idle(struct task_struct *t)
{
	return (task_rq(t)->idle == t);
}

static inline bool cookie_equals(struct task_struct *a, unsigned long cookie)
{
	return is_task_rq_idle(a) || (a->core_cookie == cookie);
}

static inline bool cookie_match(struct task_struct *a, struct task_struct *b)
{
	if (is_task_rq_idle(a) || is_task_rq_idle(b))
		return true;

	return a->core_cookie == b->core_cookie;
}

// XXX fairness/fwd progress conditions
/*
 * Returns
 * - NULL if there is no runnable task for this class.
 * - the highest priority task for this runqueue if it matches
 *   rq->core->core_cookie or its priority is greater than max.
 * - Else returns idle_task.
 */
static struct task_struct *
pick_task(struct rq *rq, const struct sched_class *class, struct task_struct *max, bool in_fi)
{
	struct task_struct *class_pick, *cookie_pick;
	unsigned long cookie = rq->core->core_cookie;

	class_pick = class->pick_task(rq);
	if (!class_pick)
		return NULL;

	if (!cookie) {
		/*
		 * If class_pick is tagged, return it only if it has
		 * higher priority than max.
		 */
		if (max && class_pick->core_cookie &&
		    prio_less(class_pick, max, in_fi))
			return idle_sched_class.pick_task(rq);

		return class_pick;
	}

	/*
	 * If class_pick is idle or matches cookie, return early.
	 */
	if (cookie_equals(class_pick, cookie))
		return class_pick;

	cookie_pick = sched_core_find(rq, cookie);

	/*
	 * If class > max && class > cookie, it is the highest priority task on
	 * the core (so far) and it must be selected, otherwise we must go with
	 * the cookie pick in order to satisfy the constraint.
	 */
	if (prio_less(cookie_pick, class_pick, in_fi) &&
	    (!max || prio_less(max, class_pick, in_fi)))
		return class_pick;

	return cookie_pick;
}

extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi);

static struct task_struct *
pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
	struct task_struct *next, *max = NULL;
	const struct sched_class *class;
	const struct cpumask *smt_mask;
	bool fi_before = false;
	int i, j, cpu, occ = 0;
	bool need_sync;

	if (!sched_core_enabled(rq))
		return __pick_next_task(rq, prev, rf);

	cpu = cpu_of(rq);

	/* Stopper task is switching into idle, no need core-wide selection. */
	if (cpu_is_offline(cpu)) {
		/*
		 * Reset core_pick so that we don't enter the fastpath when
		 * coming online. core_pick would already be migrated to
		 * another cpu during offline.
		 */
		rq->core_pick = NULL;
		return __pick_next_task(rq, prev, rf);
	}

	/*
	 * If there were no {en,de}queues since we picked (IOW, the task
	 * pointers are all still valid), and we haven't scheduled the last
	 * pick yet, do so now.
	 *
	 * rq->core_pick can be NULL if no selection was made for a CPU because
	 * it was either offline or went offline during a sibling's core-wide
	 * selection. In this case, do a core-wide selection.
	 */
	if (rq->core->core_pick_seq == rq->core->core_task_seq &&
	    rq->core->core_pick_seq != rq->core_sched_seq &&
	    rq->core_pick) {
		WRITE_ONCE(rq->core_sched_seq, rq->core->core_pick_seq);

		next = rq->core_pick;
		if (next != prev) {
			put_prev_task(rq, prev);
			set_next_task(rq, next);
		}

		rq->core_pick = NULL;
		return next;
	}

	put_prev_task_balance(rq, prev, rf);

	smt_mask = cpu_smt_mask(cpu);
	need_sync = !!rq->core->core_cookie;

	/* reset state */
	rq->core->core_cookie = 0UL;
	if (rq->core->core_forceidle) {
		need_sync = true;
		fi_before = true;
		rq->core->core_forceidle = false;
	}

	/*
	 * core->core_task_seq, core->core_pick_seq, rq->core_sched_seq
	 *
	 * @task_seq guards the task state ({en,de}queues)
	 * @pick_seq is the @task_seq we did a selection on
	 * @sched_seq is the @pick_seq we scheduled
	 *
	 * However, preemptions can cause multiple picks on the same task set.
	 * 'Fix' this by also increasing @task_seq for every pick.
	 */
	rq->core->core_task_seq++;

	/*
	 * Optimize for common case where this CPU has no cookies
	 * and there are no cookied tasks running on siblings.
	 */
	if (!need_sync) {
		for_each_class(class) {
			next = class->pick_task(rq);
			if (next)
				break;
		}

		if (!next->core_cookie) {
			rq->core_pick = NULL;
			/*
			 * For robustness, update the min_vruntime_fi for
			 * unconstrained picks as well.
			 */
			WARN_ON_ONCE(fi_before);
			task_vruntime_update(rq, next, false);
			goto done;
		}
	}

	for_each_cpu(i, smt_mask) {
		struct rq *rq_i = cpu_rq(i);

		rq_i->core_pick = NULL;

		if (i != cpu)
			update_rq_clock(rq_i);
	}

	/*
	 * Try and select tasks for each sibling in descending sched_class
	 * order.
	 */
	for_each_class(class) {
again:
		for_each_cpu_wrap(i, smt_mask, cpu) {
			struct rq *rq_i = cpu_rq(i);
			struct task_struct *p;

			if (rq_i->core_pick)
				continue;

			/*
			 * If this sibling doesn't yet have a suitable task to
			 * run; ask for the most eligible task, given the
			 * highest priority task already selected for this
			 * core.
			 */
			p = pick_task(rq_i, class, max, fi_before);
			if (!p)
				continue;

			if (!is_task_rq_idle(p))
				occ++;

			rq_i->core_pick = p;
			if (rq_i->idle == p && rq_i->nr_running) {
				rq->core->core_forceidle = true;
				if (!fi_before)
					rq->core->core_forceidle_seq++;
			}

			/*
			 * If this new candidate is of higher priority than the
			 * previous; and they're incompatible; we need to wipe
			 * the slate and start over. pick_task makes sure that
			 * p's priority is more than max if it doesn't match
			 * max's cookie.
			 *
			 * NOTE: this is a linear max-filter and is thus bounded
			 * in execution time.
			 */
			if (!max || !cookie_match(max, p)) {
				struct task_struct *old_max = max;

				rq->core->core_cookie = p->core_cookie;
				max = p;

				if (old_max) {
					rq->core->core_forceidle = false;
					for_each_cpu(j, smt_mask) {
						if (j == i)
							continue;

						cpu_rq(j)->core_pick = NULL;
					}
					occ = 1;
					goto again;
				}
			}
		}
	}

	rq->core->core_pick_seq = rq->core->core_task_seq;
	next = rq->core_pick;
	rq->core_sched_seq = rq->core->core_pick_seq;

	/* Something should have been selected for current CPU */
	WARN_ON_ONCE(!next);

	/*
	 * Reschedule siblings
	 *
	 * NOTE: L1TF -- at this point we're no longer running the old task and
	 * sending an IPI (below) ensures the sibling will no longer be running
	 * their task. This ensures there is no inter-sibling overlap between
	 * non-matching user state.
	 */
	for_each_cpu(i, smt_mask) {
		struct rq *rq_i = cpu_rq(i);

		/*
		 * An online sibling might have gone offline before a task
		 * could be picked for it, or it might be offline but later
		 * happen to come online, but its too late and nothing was
		 * picked for it.  That's Ok - it will pick tasks for itself,
		 * so ignore it.
		 */
		if (!rq_i->core_pick)
			continue;

		/*
		 * Update for new !FI->FI transitions, or if continuing to be in !FI:
		 * fi_before     fi      update?
		 *  0            0       1
		 *  0            1       1
		 *  1            0       1
		 *  1            1       0
		 */
		if (!(fi_before && rq->core->core_forceidle))
			task_vruntime_update(rq_i, rq_i->core_pick, rq->core->core_forceidle);

		rq_i->core_pick->core_occupation = occ;

		if (i == cpu) {
			rq_i->core_pick = NULL;
			continue;
		}

		/* Did we break L1TF mitigation requirements? */
		WARN_ON_ONCE(!cookie_match(next, rq_i->core_pick));

		if (rq_i->curr == rq_i->core_pick) {
			rq_i->core_pick = NULL;
			continue;
		}

		resched_curr(rq_i);
	}

done:
	set_next_task(rq, next);
	return next;
}

static bool try_steal_cookie(int this, int that)
{
	struct rq *dst = cpu_rq(this), *src = cpu_rq(that);
	struct task_struct *p;
	unsigned long cookie;
	bool success = false;

	local_irq_disable();
	double_rq_lock(dst, src);

	cookie = dst->core->core_cookie;
	if (!cookie)
		goto unlock;

	if (dst->curr != dst->idle)
		goto unlock;

	p = sched_core_find(src, cookie);
	if (p == src->idle)
		goto unlock;

	do {
		if (p == src->core_pick || p == src->curr)
			goto next;

		if (!cpumask_test_cpu(this, &p->cpus_mask))
			goto next;

		if (p->core_occupation > dst->idle->core_occupation)
			goto next;

		deactivate_task(src, p, 0);
		set_task_cpu(p, this);
		activate_task(dst, p, 0);

		resched_curr(dst);

		success = true;
		break;

next:
		p = sched_core_next(p, cookie);
	} while (p);

unlock:
	double_rq_unlock(dst, src);
	local_irq_enable();

	return success;
}

static bool steal_cookie_task(int cpu, struct sched_domain *sd)
{
	int i;

	for_each_cpu_wrap(i, sched_domain_span(sd), cpu) {
		if (i == cpu)
			continue;

		if (need_resched())
			break;

		if (try_steal_cookie(cpu, i))
			return true;
	}

	return false;
}

static void sched_core_balance(struct rq *rq)
{
	struct sched_domain *sd;
	int cpu = cpu_of(rq);

	preempt_disable();
	rcu_read_lock();
	raw_spin_rq_unlock_irq(rq);
	for_each_domain(cpu, sd) {
		if (need_resched())
			break;

		if (steal_cookie_task(cpu, sd))
			break;
	}
	raw_spin_rq_lock_irq(rq);
	rcu_read_unlock();
	preempt_enable();
}

static DEFINE_PER_CPU(struct callback_head, core_balance_head);

void queue_core_balance(struct rq *rq)
{
	if (!sched_core_enabled(rq))
		return;

	if (!rq->core->core_cookie)
		return;

	if (!rq->nr_running) /* not forced idle */
		return;

	queue_balance_callback(rq, &per_cpu(core_balance_head, rq->cpu), sched_core_balance);
}

static void sched_core_cpu_starting(unsigned int cpu)
{
	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
	struct rq *rq = cpu_rq(cpu), *core_rq = NULL;
	unsigned long flags;
	int t;

	sched_core_lock(cpu, &flags);

	WARN_ON_ONCE(rq->core != rq);

	/* if we're the first, we'll be our own leader */
	if (cpumask_weight(smt_mask) == 1)
		goto unlock;

	/* find the leader */
	for_each_cpu(t, smt_mask) {
		if (t == cpu)
			continue;
		rq = cpu_rq(t);
		if (rq->core == rq) {
			core_rq = rq;
			break;
		}
	}

	if (WARN_ON_ONCE(!core_rq)) /* whoopsie */
		goto unlock;

	/* install and validate core_rq */
	for_each_cpu(t, smt_mask) {
		rq = cpu_rq(t);

		if (t == cpu)
			rq->core = core_rq;

		WARN_ON_ONCE(rq->core != core_rq);
	}

unlock:
	sched_core_unlock(cpu, &flags);
}

static void sched_core_cpu_deactivate(unsigned int cpu)
{
	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
	struct rq *rq = cpu_rq(cpu), *core_rq = NULL;
	unsigned long flags;
	int t;

	sched_core_lock(cpu, &flags);

	/* if we're the last man standing, nothing to do */
	if (cpumask_weight(smt_mask) == 1) {
		WARN_ON_ONCE(rq->core != rq);
		goto unlock;
	}

	/* if we're not the leader, nothing to do */
	if (rq->core != rq)
		goto unlock;

	/* find a new leader */
	for_each_cpu(t, smt_mask) {
		if (t == cpu)
			continue;
		core_rq = cpu_rq(t);
		break;
	}

	if (WARN_ON_ONCE(!core_rq)) /* impossible */
		goto unlock;

	/* copy the shared state to the new leader */
	core_rq->core_task_seq      = rq->core_task_seq;
	core_rq->core_pick_seq      = rq->core_pick_seq;
	core_rq->core_cookie        = rq->core_cookie;
	core_rq->core_forceidle     = rq->core_forceidle;
	core_rq->core_forceidle_seq = rq->core_forceidle_seq;

	/* install new leader */
	for_each_cpu(t, smt_mask) {
		rq = cpu_rq(t);
		rq->core = core_rq;
	}

unlock:
	sched_core_unlock(cpu, &flags);
}

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

	if (rq->core != rq)
		rq->core = rq;
}

#else /* !CONFIG_SCHED_CORE */

static inline void sched_core_cpu_starting(unsigned int cpu) {}
static inline void sched_core_cpu_deactivate(unsigned int cpu) {}
static inline void sched_core_cpu_dying(unsigned int cpu) {}

static struct task_struct *
pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
	return __pick_next_task(rq, prev, rf);
}

#endif /* CONFIG_SCHED_CORE */

/*
 * Constants for the sched_mode argument of __schedule().
 *
 * The mode argument allows RT enabled kernels to differentiate a
 * preemption from blocking on an 'sleeping' spin/rwlock. Note that
 * SM_MASK_PREEMPT for !RT has all bits set, which allows the compiler to
 * optimize the AND operation out and just check for zero.
 */
#define SM_NONE			0x0
#define SM_PREEMPT		0x1
#define SM_RTLOCK_WAIT		0x2

#ifndef CONFIG_PREEMPT_RT
# define SM_MASK_PREEMPT	(~0U)
#else
# define SM_MASK_PREEMPT	SM_PREEMPT
#endif

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

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

	schedule_debug(prev, !!sched_mode);

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

	local_irq_disable();
	rcu_note_context_switch(!!sched_mode);

	/*
	 * Make sure that signal_pending_state()->signal_pending() below
	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
	 * done by the caller to avoid the race with signal_wake_up():
	 *
	 * __set_current_state(@state)		signal_wake_up()
	 * schedule()				  set_tsk_thread_flag(p, TIF_SIGPENDING)
	 *					  wake_up_state(p, state)
	 *   LOCK rq->lock			    LOCK p->pi_state
	 *   smp_mb__after_spinlock()		    smp_mb__after_spinlock()
	 *     if (signal_pending_state())	    if (p->state & @state)
	 *
	 * Also, the membarrier system call requires a full memory barrier
	 * after coming from user-space, before storing to rq->curr.
	 */
	rq_lock(rq, &rf);
	smp_mb__after_spinlock();

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

	switch_count = &prev->nivcsw;

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

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

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

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

	next = pick_next_task(rq, prev, &rf);
	clear_tsk_need_resched(prev);
	clear_preempt_need_resched();
#ifdef CONFIG_SCHED_DEBUG
	rq->last_seen_need_resched_ns = 0;
#endif

	if (likely(prev != next)) {
		rq->nr_switches++;
		/*
		 * RCU users of rcu_dereference(rq->curr) may not see
		 * changes to task_struct made by pick_next_task().
		 */
		RCU_INIT_POINTER(rq->curr, next);
		/*
		 * The membarrier system call requires each architecture
		 * to have a full memory barrier after updating
		 * rq->curr, before returning to user-space.
		 *
		 * Here are the schemes providing that barrier on the
		 * various architectures:
		 * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC.
		 *   switch_mm() rely on membarrier_arch_switch_mm() on PowerPC.
		 * - finish_lock_switch() for weakly-ordered
		 *   architectures where spin_unlock is a full barrier,
		 * - switch_to() for arm64 (weakly-ordered, spin_unlock
		 *   is a RELEASE barrier),
		 */
		++*switch_count;

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

		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next);

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

		rq_unpin_lock(rq, &rf);
		__balance_callbacks(rq);
		raw_spin_rq_unlock_irq(rq);
	}
}

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

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

	__schedule(SM_NONE);
	BUG();

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

static inline void sched_submit_work(struct task_struct *tsk)
{
	unsigned int task_flags;

	if (task_is_running(tsk))
		return;

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

	if (tsk_is_pi_blocked(tsk))
		return;

	/*
	 * If we are going to sleep and we have plugged IO queued,
	 * make sure to submit it to avoid deadlocks.
	 */
	if (blk_needs_flush_plug(tsk))
		blk_schedule_flush_plug(tsk);
}

static void sched_update_worker(struct task_struct *tsk)
{
	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
		if (tsk->flags & PF_WQ_WORKER)
			wq_worker_running(tsk);
		else
			io_wq_worker_running(tsk);
	}
}

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

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

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

#if defined(CONFIG_CONTEXT_TRACKING) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK)
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();
}

#ifdef CONFIG_PREEMPT_RT
void __sched notrace schedule_rtlock(void)
{
	do {
		preempt_disable();
		__schedule(SM_RTLOCK_WAIT);
		sched_preempt_enable_no_resched();
	} while (need_resched());
}
NOKPROBE_SYMBOL(schedule_rtlock);
#endif

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(SM_PREEMPT);
		preempt_latency_stop(1);
		preempt_enable_no_resched_notrace();

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

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

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

#ifdef CONFIG_PREEMPT_DYNAMIC
DEFINE_STATIC_CALL(preempt_schedule, __preempt_schedule_func);
EXPORT_STATIC_CALL_TRAMP(preempt_schedule);
#endif


/**
 * 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(SM_PREEMPT);
		exception_exit(prev_ctx);

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

#ifdef CONFIG_PREEMPT_DYNAMIC
DEFINE_STATIC_CALL(preempt_schedule_notrace, __preempt_schedule_notrace_func);
EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
#endif

#endif /* CONFIG_PREEMPTION */

#ifdef CONFIG_PREEMPT_DYNAMIC

#include <linux/entry-common.h>

/*
 * SC:cond_resched
 * SC:might_resched
 * SC:preempt_schedule
 * SC:preempt_schedule_notrace
 * SC:irqentry_exit_cond_resched
 *
 *
 * NONE:
 *   cond_resched               <- __cond_resched
 *   might_resched              <- RET0
 *   preempt_schedule           <- NOP
 *   preempt_schedule_notrace   <- NOP
 *   irqentry_exit_cond_resched <- NOP
 *
 * VOLUNTARY:
 *   cond_resched               <- __cond_resched
 *   might_resched              <- __cond_resched
 *   preempt_schedule           <- NOP
 *   preempt_schedule_notrace   <- NOP
 *   irqentry_exit_cond_resched <- NOP
 *
 * FULL:
 *   cond_resched               <- RET0
 *   might_resched              <- RET0
 *   preempt_schedule           <- preempt_schedule
 *   preempt_schedule_notrace   <- preempt_schedule_notrace
 *   irqentry_exit_cond_resched <- irqentry_exit_cond_resched
 */

enum {
	preempt_dynamic_none = 0,
	preempt_dynamic_voluntary,
	preempt_dynamic_full,
};

int preempt_dynamic_mode = preempt_dynamic_full;

int sched_dynamic_mode(const char *str)
{
	if (!strcmp(str, "none"))
		return preempt_dynamic_none;

	if (!strcmp(str, "voluntary"))
		return preempt_dynamic_voluntary;

	if (!strcmp(str, "full"))
		return preempt_dynamic_full;

	return -EINVAL;
}

void sched_dynamic_update(int mode)
{
	/*
	 * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
	 * the ZERO state, which is invalid.
	 */
	static_call_update(cond_resched, __cond_resched);
	static_call_update(might_resched, __cond_resched);
	static_call_update(preempt_schedule, __preempt_schedule_func);
	static_call_update(preempt_schedule_notrace, __preempt_schedule_notrace_func);
	static_call_update(irqentry_exit_cond_resched, irqentry_exit_cond_resched);

	switch (mode) {
	case preempt_dynamic_none:
		static_call_update(cond_resched, __cond_resched);
		static_call_update(might_resched, (void *)&__static_call_return0);
		static_call_update(preempt_schedule, NULL);
		static_call_update(preempt_schedule_notrace, NULL);
		static_call_update(irqentry_exit_cond_resched, NULL);
		pr_info("Dynamic Preempt: none\n");
		break;

	case preempt_dynamic_voluntary:
		static_call_update(cond_resched, __cond_resched);
		static_call_update(might_resched, __cond_resched);
		static_call_update(preempt_schedule, NULL);
		static_call_update(preempt_schedule_notrace, NULL);
		static_call_update(irqentry_exit_cond_resched, NULL);
		pr_info("Dynamic Preempt: voluntary\n");
		break;

	case preempt_dynamic_full:
		static_call_update(cond_resched, (void *)&__static_call_return0);
		static_call_update(might_resched, (void *)&__static_call_return0);
		static_call_update(preempt_schedule, __preempt_schedule_func);
		static_call_update(preempt_schedule_notrace, __preempt_schedule_notrace_func);
		static_call_update(irqentry_exit_cond_resched, irqentry_exit_cond_resched);
		pr_info("Dynamic Preempt: full\n");
		break;
	}

	preempt_dynamic_mode = mode;
}

static int __init setup_preempt_mode(char *str)
{
	int mode = sched_dynamic_mode(str);
	if (mode < 0) {
		pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
		return 1;
	}

	sched_dynamic_update(mode);
	return 0;
}
__setup("preempt=", setup_preempt_mode);

#endif /* CONFIG_PREEMPT_DYNAMIC */

/*
 * 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(SM_PREEMPT);
		local_irq_disable();
		sched_preempt_enable_no_resched();
	} while (need_resched());

	exception_exit(prev_state);
}

int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
			  void *key)
{
	WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~WF_SYNC);
	return try_to_wake_up(curr->private, mode, wake_flags);
}
EXPORT_SYMBOL(default_wake_function);

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

	p->prio = prio;
}

#ifdef CONFIG_RT_MUTEXES

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

	return prio;
}

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

	return __rt_effective_prio(pi_task, prio);
}

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

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

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

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

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

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

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

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

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

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

	__setscheduler_prio(p, prio);

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

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

	rq_unpin_lock(rq, &rf);
	__balance_callbacks(rq);
	raw_spin_rq_unlock(rq);

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

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

	if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
		return;
	/*
	 * We have to be careful, if called from sys_setpriority(),
	 * the task might be in the middle of scheduling on another CPU.
	 */
	rq = task_rq_lock(p, &rf);
	update_rq_clock(rq);

	/*
	 * The RT priorities are set via sched_setscheduler(), but we still
	 * allow the 'normal' nice value to be set - but as expected
	 * it won't have any effect on scheduling until the task is
	 * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR:
	 */
	if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
		p->static_prio = NICE_TO_PRIO(nice);
		goto out_unlock;
	}
	queued = task_on_rq_queued(p);
	running = task_current(rq, p);
	if (queued)
		dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
	if (running)
		put_prev_task(rq, p);

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

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

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

out_unlock:
	task_rq_unlock(rq, p, &rf);
}
EXPORT_SYMBOL(set_user_nice);

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

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

#ifdef __ARCH_WANT_SYS_NICE

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

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

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

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

	set_user_nice(current, nice);
	return 0;
}

#endif

/**
 * task_prio - return the priority value of a given task.
 * @p: the task in question.
 *
 * Return: The priority value as seen by users in /proc.
 *
 * sched policy         return value   kernel prio    user prio/nice
 *
 * normal, batch, idle     [0 ... 39]  [100 ... 139]          0/[-20 ... 19]
 * fifo, rr             [-2 ... -100]     [98 ... 0]  [1 ... 99]
 * deadline                     -101             -1           0
 */
int task_prio(const struct task_struct *p)
{
	return p->prio - MAX_RT_PRIO;
}

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

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

	if (rq->nr_running)
		return 0;

#ifdef CONFIG_SMP
	if (rq->ttwu_pending)
		return 0;
#endif

	return 1;
}

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

	if (vcpu_is_preempted(cpu))
		return 0;

	return 1;
}

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

#ifdef CONFIG_SMP
/*
 * This function computes an effective utilization for the given CPU, to be
 * used for frequency selection given the linear relation: f = u * f_max.
 *
 * The scheduler tracks the following metrics:
 *
 *   cpu_util_{cfs,rt,dl,irq}()
 *   cpu_bw_dl()
 *
 * Where the cfs,rt and dl util numbers are tracked with the same metric and
 * synchronized windows and are thus directly comparable.
 *
 * The cfs,rt,dl utilization are the running times measured with rq->clock_task
 * which excludes things like IRQ and steal-time. These latter are then accrued
 * in the irq utilization.
 *
 * The DL bandwidth number otoh is not a measured metric but a value computed
 * based on the task model parameters and gives the minimal utilization
 * required to meet deadlines.
 */
unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
				 unsigned long max, enum cpu_util_type type,
				 struct task_struct *p)
{
	unsigned long dl_util, util, irq;
	struct rq *rq = cpu_rq(cpu);

	if (!uclamp_is_used() &&
	    type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
		return max;
	}

	/*
	 * Early check to see if IRQ/steal time saturates the CPU, can be
	 * because of inaccuracies in how we track these -- see
	 * update_irq_load_avg().
	 */
	irq = cpu_util_irq(rq);
	if (unlikely(irq >= max))
		return max;

	/*
	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
	 * CFS tasks and we use the same metric to track the effective
	 * utilization (PELT windows are synchronized) we can directly add them
	 * to obtain the CPU's actual utilization.
	 *
	 * CFS and RT utilization can be boosted or capped, depending on
	 * utilization clamp constraints requested by currently RUNNABLE
	 * tasks.
	 * When there are no CFS RUNNABLE tasks, clamps are released and
	 * frequency will be gracefully reduced with the utilization decay.
	 */
	util = util_cfs + cpu_util_rt(rq);
	if (type == FREQUENCY_UTIL)
		util = uclamp_rq_util_with(rq, util, p);

	dl_util = cpu_util_dl(rq);

	/*
	 * For frequency selection we do not make cpu_util_dl() a permanent part
	 * of this sum because we want to use cpu_bw_dl() later on, but we need
	 * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such
	 * that we select f_max when there is no idle time.
	 *
	 * NOTE: numerical errors or stop class might cause us to not quite hit
	 * saturation when we should -- something for later.
	 */
	if (util + dl_util >= max)
		return max;

	/*
	 * OTOH, for energy computation we need the estimated running time, so
	 * include util_dl and ignore dl_bw.
	 */
	if (type == ENERGY_UTIL)
		util += dl_util;

	/*
	 * There is still idle time; further improve the number by using the
	 * irq metric. Because IRQ/steal time is hidden from the task clock we
	 * need to scale the task numbers:
	 *
	 *              max - irq
	 *   U' = irq + --------- * U
	 *                 max
	 */
	util = scale_irq_capacity(util, irq, max);
	util += irq;

	/*
	 * Bandwidth required by DEADLINE must always be granted while, for
	 * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
	 * to gracefully reduce the frequency when no tasks show up for longer
	 * periods of time.
	 *
	 * Ideally we would like to set bw_dl as min/guaranteed freq and util +
	 * bw_dl as requested freq. However, cpufreq is not yet ready for such
	 * an interface. So, we only do the latter for now.
	 */
	if (type == FREQUENCY_UTIL)
		util += cpu_bw_dl(rq);

	return min(max, util);
}

unsigned long sched_cpu_util(int cpu, unsigned long max)
{
	return effective_cpu_util(cpu, cpu_util_cfs(cpu_rq(cpu)), max,
				  ENERGY_UTIL, NULL);
}
#endif /* CONFIG_SMP */

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

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

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

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

	p->policy = policy;

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

	/*
	 * __sched_setscheduler() ensures attr->sched_priority == 0 when
	 * !rt_policy. Always setting this ensures that things like
	 * getparam()/getattr() don't report silly values for !rt tasks.
	 */
	p->rt_priority = attr->sched_priority;
	p->normal_prio = normal_prio(p);
	set_load_weight(p, 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 int __sched_setscheduler(struct task_struct *p,
				const struct sched_attr *attr,
				bool user, bool pi)
{
	int oldpolicy = -1, policy = attr->sched_policy;
	int retval, oldprio, newprio, queued, running;
	const struct sched_class *prev_class;
	struct callback_head *head;
	struct rq_flags rf;
	int reset_on_fork;
	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
	struct rq *rq;

	/* The pi code expects interrupts enabled */
	BUG_ON(pi && in_interrupt());
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_ALL | SCHED_FLAG_SUGOV))
		return -EINVAL;

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

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

		if (rt_policy(policy)) {
			unsigned long rlim_rtprio =
					task_rlimit(p, RLIMIT_RTPRIO);

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

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

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

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

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

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

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

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

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

	if (pi)
		cpuset_read_lock();

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

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

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

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

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

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

	/* Re-check policy now with rq lock held: */
	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
		policy = oldpolicy = -1;
		task_rq_unlock(rq, p, &rf);
		if (pi)
			cpuset_read_unlock();
		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)) && sched_dl_overflow(p, policy, attr)) {
		retval = -EBUSY;
		goto unlock;
	}

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

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

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

	prev_class = p->sched_class;

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

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

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

	check_class_changed(rq, p, prev_class, oldprio);

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

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

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

	return 0;

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

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

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

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

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

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

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

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

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

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

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

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

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

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

	return retval;
}

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

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

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

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

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

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

	/*
	 * 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;
}

static void get_params(struct task_struct *p, struct sched_attr *attr)
{
	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);
}

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

	return do_sched_setscheduler(pid, policy, param);
}

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

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

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

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

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

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

	if (likely(p)) {
		if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
			get_params(p, &attr);
		retval = sched_setattr(p, &attr);
		put_task_struct(p);
	}

	return retval;
}

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

	if (pid < 0)
		return -EINVAL;

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

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

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

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

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

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

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

	return retval;

out_unlock:
	rcu_read_unlock();
	return retval;
}

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

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

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

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

	return 0;
}

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

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

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

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

	kattr.sched_policy = p->policy;
	if (p->sched_reset_on_fork)
		kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
	get_params(p, &kattr);
	kattr.sched_flags &= SCHED_FLAG_ALL;

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

	rcu_read_unlock();

	return sched_attr_copy_to_user(uattr, &kattr, usize);

out_unlock:
	rcu_read_unlock();
	return retval;
}

#ifdef CONFIG_SMP
int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
{
	int ret = 0;

	/*
	 * If the task isn't a deadline task or admission control is
	 * disabled then we don't care about affinity changes.
	 */
	if (!task_has_dl_policy(p) || !dl_bandwidth_enabled())
		return 0;

	/*
	 * 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.
	 */
	rcu_read_lock();
	if (!cpumask_subset(task_rq(p)->rd->span, mask))
		ret = -EBUSY;
	rcu_read_unlock();
	return ret;
}
#endif

static int
__sched_setaffinity(struct task_struct *p, const struct cpumask *mask)
{
	int retval;
	cpumask_var_t cpus_allowed, new_mask;

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

	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
		retval = -ENOMEM;
		goto out_free_cpus_allowed;
	}

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

	retval = dl_task_check_affinity(p, new_mask);
	if (retval)
		goto out_free_new_mask;
again:
	retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK | SCA_USER);
	if (retval)
		goto out_free_new_mask;

	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 cpumask 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);
	return retval;
}

long sched_setaffinity(pid_t pid, const struct cpumask *in_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 (!check_same_owner(p)) {
		rcu_read_lock();
		if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
			rcu_read_unlock();
			retval = -EPERM;
			goto out_put_task;
		}
		rcu_read_unlock();
	}

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

	retval = __sched_setaffinity(p, in_mask);
out_put_task:
	put_task_struct(p);
	return retval;
}

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

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

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

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

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

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

	rcu_read_lock();

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

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

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

out_unlock:
	rcu_read_unlock();

	return retval;
}

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

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

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

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

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

	return ret;
}

static void do_sched_yield(void)
{
	struct rq_flags rf;
	struct rq *rq;

	rq = this_rq_lock_irq(&rf);

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

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

	schedule();
}

/**
 * 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)
{
	do_sched_yield();
	return 0;
}

#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
int __sched __cond_resched(void)
{
	if (should_resched(0)) {
		preempt_schedule_common();
		return 1;
	}
	/*
	 * In preemptible kernels, ->rcu_read_lock_nesting tells the tick
	 * whether the current CPU is in an RCU read-side critical section,
	 * so the tick can report quiescent states even for CPUs looping
	 * in kernel context.  In contrast, in non-preemptible kernels,
	 * RCU readers leave no in-memory hints, which means that CPU-bound
	 * processes executing in kernel context might never report an
	 * RCU quiescent state.  Therefore, the following code causes
	 * cond_resched() to report a quiescent state, but only when RCU
	 * is in urgent need of one.
	 */
#ifndef CONFIG_PREEMPT_RCU
	rcu_all_qs();
#endif
	return 0;
}
EXPORT_SYMBOL(__cond_resched);
#endif

#ifdef CONFIG_PREEMPT_DYNAMIC
DEFINE_STATIC_CALL_RET0(cond_resched, __cond_resched);
EXPORT_STATIC_CALL_TRAMP(cond_resched);

DEFINE_STATIC_CALL_RET0(might_resched, __cond_resched);
EXPORT_STATIC_CALL_TRAMP(might_resched);
#endif

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

	lockdep_assert_held(lock);

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

int __cond_resched_rwlock_read(rwlock_t *lock)
{
	int resched = should_resched(PREEMPT_LOCK_OFFSET);
	int ret = 0;

	lockdep_assert_held_read(lock);

	if (rwlock_needbreak(lock) || resched) {
		read_unlock(lock);
		if (resched)
			preempt_schedule_common();
		else
			cpu_relax();
		ret = 1;
		read_lock(lock);
	}
	return ret;
}
EXPORT_SYMBOL(__cond_resched_rwlock_read);

int __cond_resched_rwlock_write(rwlock_t *lock)
{
	int resched = should_resched(PREEMPT_LOCK_OFFSET);
	int ret = 0;

	lockdep_assert_held_write(lock);

	if (rwlock_needbreak(lock) || resched) {
		write_unlock(lock);
		if (resched)
			preempt_schedule_common();
		else
			cpu_relax();
		ret = 1;
		write_lock(lock);
	}
	return ret;
}
EXPORT_SYMBOL(__cond_resched_rwlock_write);

/**
 * 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, it's already broken.
 *
 * Typical broken usage is:
 *
 * while (!event)
 *	yield();
 *
 * where one assumes that yield() will let 'the other' process run that will
 * make event true. If the current task is a SCHED_FIFO task that will never
 * happen. Never use yield() as a progress guarantee!!
 *
 * If you want to use yield() to wait for something, use wait_event().
 * If you want to use yield() to be 'nice' for others, use cond_resched().
 * If you still want to use yield(), do not!
 */
void __sched yield(void)
{
	set_current_state(TASK_RUNNING);
	do_sched_yield();
}
EXPORT_SYMBOL(yield);

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

	local_irq_save(flags);
	rq = this_rq();

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

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

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

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

	if (task_running(p_rq, p) || !task_is_running(p))
		goto out_unlock;

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

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

	if (yielded > 0)
		schedule();

	return yielded;
}
EXPORT_SYMBOL_GPL(yield_to);

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

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

	return old_iowait;
}

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

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

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

	return ret;
}
EXPORT_SYMBOL(io_schedule_timeout);

void __sched io_schedule(void)
{
	int token;

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

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

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

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

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

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

	if (pid < 0)
		return -EINVAL;

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

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

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

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

out_unlock:
	rcu_read_unlock();
	return retval;
}

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

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

	return retval;
}

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

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

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

	if (!try_get_task_stack(p))
		return;

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

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

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

static inline bool
state_filter_match(unsigned long state_filter, struct task_struct *p)
{
	unsigned int state = READ_ONCE(p->__state);

	/* no filter, everything matches */
	if (!state_filter)
		return true;

	/* filter, but doesn't match */
	if (!(state & state_filter))
		return false;

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

	return true;
}


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

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

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

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

	__sched_fork(0, idle);

	/*
	 * The idle task doesn't need the kthread struct to function, but it
	 * is dressed up as a per-CPU kthread and thus needs to play the part
	 * if we want to avoid special-casing it in code that deals with per-CPU
	 * kthreads.
	 */
	set_kthread_struct(idle);

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

	idle->__state = TASK_RUNNING;
	idle->se.exec_start = sched_clock();
	/*
	 * PF_KTHREAD should already be set at this point; regardless, make it
	 * look like a proper per-CPU kthread.
	 */
	idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY;
	kthread_set_per_cpu(idle, cpu);

	scs_task_reset(idle);
	kasan_unpoison_task_stack(idle);

#ifdef CONFIG_SMP
	/*
	 * It's 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), 0);
#endif
	/*
	 * We're having a chicken and egg problem, even though we are
	 * holding rq->lock, the CPU isn't yet set to this CPU so the
	 * lockdep check in task_group() will fail.
	 *
	 * Similar case to sched_fork(). / Alternatively we could
	 * use task_rq_lock() here and obtain the other rq->lock.
	 *
	 * Silence PROVE_RCU
	 */
	rcu_read_lock();
	__set_task_cpu(idle, cpu);
	rcu_read_unlock();

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

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

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

#ifdef CONFIG_SMP

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

	if (!cpumask_weight(cur))
		return ret;

	ret = dl_cpuset_cpumask_can_shrink(cur, trial);

	return ret;
}

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

	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
					      cs_cpus_allowed))
		ret = dl_task_can_attach(p, cs_cpus_allowed);

out:
	return ret;
}

bool sched_smp_initialized __read_mostly;

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

	if (curr_cpu == target_cpu)
		return 0;

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

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

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

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

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

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

static int __balance_push_cpu_stop(void *arg)
{
	struct task_struct *p = arg;
	struct rq *rq = this_rq();
	struct rq_flags rf;
	int cpu;

	raw_spin_lock_irq(&p->pi_lock);
	rq_lock(rq, &rf);

	update_rq_clock(rq);

	if (task_rq(p) == rq && task_on_rq_queued(p)) {
		cpu = select_fallback_rq(rq->cpu, p);
		rq = __migrate_task(rq, &rf, p, cpu);
	}

	rq_unlock(rq, &rf);
	raw_spin_unlock_irq(&p->pi_lock);

	put_task_struct(p);

	return 0;
}

static DEFINE_PER_CPU(struct cpu_stop_work, push_work);

/*
 * Ensure we only run per-cpu kthreads once the CPU goes !active.
 *
 * This is enabled below SCHED_AP_ACTIVE; when !cpu_active(), but only
 * effective when the hotplug motion is down.
 */
static void balance_push(struct rq *rq)
{
	struct task_struct *push_task = rq->curr;

	lockdep_assert_rq_held(rq);

	/*
	 * Ensure the thing is persistent until balance_push_set(.on = false);
	 */
	rq->balance_callback = &balance_push_callback;

	/*
	 * Only active while going offline and when invoked on the outgoing
	 * CPU.
	 */
	if (!cpu_dying(rq->cpu) || rq != this_rq())
		return;

	/*
	 * Both the cpu-hotplug and stop task are in this case and are
	 * required to complete the hotplug process.
	 */
	if (kthread_is_per_cpu(push_task) ||
	    is_migration_disabled(push_task)) {

		/*
		 * If this is the idle task on the outgoing CPU try to wake
		 * up the hotplug control thread which might wait for the
		 * last task to vanish. The rcuwait_active() check is
		 * accurate here because the waiter is pinned on this CPU
		 * and can't obviously be running in parallel.
		 *
		 * On RT kernels this also has to check whether there are
		 * pinned and scheduled out tasks on the runqueue. They
		 * need to leave the migrate disabled section first.
		 */
		if (!rq->nr_running && !rq_has_pinned_tasks(rq) &&
		    rcuwait_active(&rq->hotplug_wait)) {
			raw_spin_rq_unlock(rq);
			rcuwait_wake_up(&rq->hotplug_wait);
			raw_spin_rq_lock(rq);
		}
		return;
	}

	get_task_struct(push_task);
	/*
	 * Temporarily drop rq->lock such that we can wake-up the stop task.
	 * Both preemption and IRQs are still disabled.
	 */
	raw_spin_rq_unlock(rq);
	stop_one_cpu_nowait(rq->cpu, __balance_push_cpu_stop, push_task,
			    this_cpu_ptr(&push_work));
	/*
	 * At this point need_resched() is true and we'll take the loop in
	 * schedule(). The next pick is obviously going to be the stop task
	 * which kthread_is_per_cpu() and will push this task away.
	 */
	raw_spin_rq_lock(rq);
}

static void balance_push_set(int cpu, bool on)
{
	struct rq *rq = cpu_rq(cpu);
	struct rq_flags rf;

	rq_lock_irqsave(rq, &rf);
	if (on) {
		WARN_ON_ONCE(rq->balance_callback);
		rq->balance_callback = &balance_push_callback;
	} else if (