linux/kernel/sched/core.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 *  kernel/sched/core.c
 *
 *  Core kernel CPU scheduler code
 *
 *  Copyright (C) 1991-2002  Linus Torvalds
 *  Copyright (C) 1998-2024  Ingo Molnar, Red Hat
 */
#include <linux/highmem.h>
#include <linux/hrtimer_api.h>
#include <linux/ktime_api.h>
#include <linux/sched/signal.h>
#include <linux/syscalls_api.h>
#include <linux/debug_locks.h>
#include <linux/prefetch.h>
#include <linux/capability.h>
#include <linux/pgtable_api.h>
#include <linux/wait_bit.h>
#include <linux/jiffies.h>
#include <linux/spinlock_api.h>
#include <linux/cpumask_api.h>
#include <linux/lockdep_api.h>
#include <linux/hardirq.h>
#include <linux/softirq.h>
#include <linux/refcount_api.h>
#include <linux/topology.h>
#include <linux/sched/clock.h>
#include <linux/sched/cond_resched.h>
#include <linux/sched/cputime.h>
#include <linux/sched/debug.h>
#include <linux/sched/hotplug.h>
#include <linux/sched/init.h>
#include <linux/sched/isolation.h>
#include <linux/sched/loadavg.h>
#include <linux/sched/mm.h>
#include <linux/sched/nohz.h>
#include <linux/sched/rseq_api.h>
#include <linux/sched/rt.h>

#include <linux/blkdev.h>
#include <linux/context_tracking.h>
#include <linux/cpuset.h>
#include <linux/delayacct.h>
#include <linux/init_task.h>
#include <linux/interrupt.h>
#include <linux/ioprio.h>
#include <linux/kallsyms.h>
#include <linux/kcov.h>
#include <linux/kprobes.h>
#include <linux/llist_api.h>
#include <linux/mmu_context.h>
#include <linux/mmzone.h>
#include <linux/mutex_api.h>
#include <linux/nmi.h>
#include <linux/nospec.h>
#include <linux/perf_event_api.h>
#include <linux/profile.h>
#include <linux/psi.h>
#include <linux/rcuwait_api.h>
#include <linux/rseq.h>
#include <linux/sched/wake_q.h>
#include <linux/scs.h>
#include <linux/slab.h>
#include <linux/syscalls.h>
#include <linux/vtime.h>
#include <linux/wait_api.h>
#include <linux/workqueue_api.h>

#ifdef CONFIG_PREEMPT_DYNAMIC
# ifdef CONFIG_GENERIC_ENTRY
#  include <linux/entry-common.h>
# endif
#endif

#include <uapi/linux/sched/types.h>

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

#define CREATE_TRACE_POINTS
#include <linux/sched/rseq_api.h>
#include <trace/events/sched.h>
#include <trace/events/ipi.h>
#undef CREATE_TRACE_POINTS

#include "sched.h"
#include "stats.h"

#include "autogroup.h"
#include "pelt.h"
#include "smp.h"
#include "stats.h"

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

EXPORT_TRACEPOINT_SYMBOL_GPL(…);
EXPORT_TRACEPOINT_SYMBOL_GPL(…);

/*
 * 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(…);
EXPORT_TRACEPOINT_SYMBOL_GPL(…);
EXPORT_TRACEPOINT_SYMBOL_GPL(…);
EXPORT_TRACEPOINT_SYMBOL_GPL(…);
EXPORT_TRACEPOINT_SYMBOL_GPL(…);
EXPORT_TRACEPOINT_SYMBOL_GPL(…);
EXPORT_TRACEPOINT_SYMBOL_GPL(…);
EXPORT_TRACEPOINT_SYMBOL_GPL(…);
EXPORT_TRACEPOINT_SYMBOL_GPL(…);
EXPORT_TRACEPOINT_SYMBOL_GPL(…);
EXPORT_TRACEPOINT_SYMBOL_GPL(…);
EXPORT_TRACEPOINT_SYMBOL_GPL(…);

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 …
const_debug unsigned int sysctl_sched_features = …;
#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 = …;
__read_mostly int sysctl_resched_latency_warn_once = …;
#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 = …;

__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(const struct task_struct *p)
{ … }

/*
 * 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(const struct task_struct *a,
			     const struct task_struct *b, bool in_fi)
{ … }

static inline bool __sched_core_less(const struct task_struct *a,
				     const struct task_struct *b)
{ … }

#define __node_2_sc(node) …

static inline bool rb_sched_core_less(struct rb_node *a, const struct rb_node *b)
{ … }

static inline int rb_sched_core_cmp(const void *key, const struct rb_node *node)
{ … }

void sched_core_enqueue(struct rq *rq, struct task_struct *p)
{ … }

void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags)
{ … }

static int sched_task_is_throttled(struct task_struct *p, int cpu)
{ … }

static struct task_struct *sched_core_next(struct task_struct *p, unsigned long cookie)
{ … }

/*
 * Find left-most (aka, highest priority) and unthrottled task matching @cookie.
 * If no suitable task is found, NULL will be returned.
 */
static struct task_struct *sched_core_find(struct rq *rq, unsigned long cookie)
{ … }

/*
 * 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)
{ … }

static void sched_core_unlock(int cpu, unsigned long *flags)
{ … }

static void __sched_core_flip(bool enabled)
{ … }

static void sched_core_assert_empty(void)
{ … }

static void __sched_core_enable(void)
{ … }

static void __sched_core_disable(void)
{ … }

void sched_core_get(void)
{ … }

static void __sched_core_put(struct work_struct *work)
{ … }

void sched_core_put(void)
{ … }

#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, int flags) { }

#endif /* CONFIG_SCHED_CORE */

/*
 * 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():	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)
{ … }

bool raw_spin_rq_trylock(struct rq *rq)
{ … }

void raw_spin_rq_unlock(struct rq *rq)
{ … }

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

/*
 * 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)
{ … }

/*
 * RQ-clock updating methods:
 */

static void update_rq_clock_task(struct rq *rq, s64 delta)
{ … }

void update_rq_clock(struct rq *rq)
{ … }

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

static void hrtick_clear(struct rq *rq)
{ … }

/*
 * High-resolution timer tick.
 * Runs from hardirq context with interrupts disabled.
 */
static enum hrtimer_restart hrtick(struct hrtimer *timer)
{ … }

#ifdef CONFIG_SMP

static void __hrtick_restart(struct rq *rq)
{ … }

/*
 * called from hardirq (IPI) context
 */
static void __hrtick_start(void *arg)
{ … }

/*
 * Called to set the hrtick timer state.
 *
 * called with rq->lock held and IRQs disabled
 */
void hrtick_start(struct rq *rq, u64 delay)
{ … }

#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)
{ … }
#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 */

/*
 * try_cmpxchg based fetch_or() macro so it works for different integer types:
 */
#define fetch_or(ptr, mask) …

#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 inline bool set_nr_and_not_polling(struct task_struct *p)
{ … }

/*
 * 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)
{ … }

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

#ifdef CONFIG_SMP
static inline 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

void wake_up_q(struct wake_q_head *head)
{ … }

/*
 * 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)
{ … }

void resched_cpu(int cpu)
{ … }

#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 up to date wrt jiffies etc).
 */
int get_nohz_timer_target(void)
{ … }

/*
 * 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)
{ … }

static bool wake_up_full_nohz_cpu(int cpu)
{ … }

/*
 * 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)
{ … }

static void nohz_csd_func(void *info)
{ … }

#endif /* CONFIG_NO_HZ_COMMON */

#ifdef CONFIG_NO_HZ_FULL
static inline bool __need_bw_check(struct rq *rq, struct task_struct *p)
{
	if (rq->nr_running != 1)
		return false;

	if (p->sched_class != &fair_sched_class)
		return false;

	if (!task_on_rq_queued(p))
		return false;

	return true;
}

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;

	/*
	 * If there is one task and it has CFS runtime bandwidth constraints
	 * and it's on the cpu now we don't want to stop the tick.
	 * This check prevents clearing the bit if a newly enqueued task here is
	 * dequeued by migrating while the constrained task continues to run.
	 * E.g. going from 2->1 without going through pick_next_task().
	 */
	if (sched_feat(HZ_BW) && __need_bw_check(rq, rq->curr)) {
		if (cfs_task_bw_constrained(rq->curr))
			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)
{ … }

int tg_nop(struct task_group *tg, void *data)
{ … }
#endif

void set_load_weight(struct task_struct *p, bool update_load)
{ … }

#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 */
static unsigned int __maybe_unused sysctl_sched_uclamp_util_min = …;

/* Max allowed maximum utilization */
static unsigned int __maybe_unused sysctl_sched_uclamp_util_max = …;

/*
 * 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 = …;

/* 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);

static inline unsigned int
uclamp_idle_value(struct rq *rq, enum uclamp_id clamp_id,
		  unsigned int clamp_value)
{ … }

static inline void uclamp_idle_reset(struct rq *rq, enum uclamp_id clamp_id,
				     unsigned int clamp_value)
{ … }

static inline
unsigned int uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id,
				   unsigned int clamp_value)
{ … }

static void __uclamp_update_util_min_rt_default(struct task_struct *p)
{ … }

static void uclamp_update_util_min_rt_default(struct task_struct *p)
{ … }

static inline struct uclamp_se
uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
{ … }

/*
 * 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)
{ … }

unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id)
{ … }

/*
 * 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)
{ … }

/*
 * 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)
{ … }

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 void uclamp_rq_reinc_id(struct rq *rq, struct task_struct *p,
				      enum uclamp_id clamp_id)
{ … }

static inline void
uclamp_update_active(struct task_struct *p)
{ … }

#ifdef CONFIG_UCLAMP_TASK_GROUP
static inline void
uclamp_update_active_tasks(struct cgroup_subsys_state *css)
{ … }

static void cpu_util_update_eff(struct cgroup_subsys_state *css);
#endif

#ifdef CONFIG_SYSCTL
#ifdef CONFIG_UCLAMP_TASK_GROUP
static void uclamp_update_root_tg(void)
{ … }
#else
static void uclamp_update_root_tg(void) { }
#endif

static void uclamp_sync_util_min_rt_default(void)
{ … }

static int sysctl_sched_uclamp_handler(const struct ctl_table *table, int write,
				void *buffer, size_t *lenp, loff_t *ppos)
{ … }
#endif

static void uclamp_fork(struct task_struct *p)
{ … }

static void uclamp_post_fork(struct task_struct *p)
{ … }

static void __init init_uclamp_rq(struct rq *rq)
{ … }

static void __init init_uclamp(void)
{ … }

#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 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)
{ … }

unsigned long get_wchan(struct task_struct *p)
{ … }

void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
{ … }

void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
{ … }

void activate_task(struct rq *rq, struct task_struct *p, int flags)
{ … }

void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
{ … }

/**
 * 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)
{ … }

/*
 * 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().
 */
void check_class_changed(struct rq *rq, struct task_struct *p,
			 const struct sched_class *prev_class,
			 int oldprio)
{ … }

void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags)
{ … }

static __always_inline
int __task_state_match(struct task_struct *p, unsigned int state)
{ … }

static __always_inline
int task_state_match(struct task_struct *p, unsigned int state)
{ … }

/*
 * wait_task_inactive - wait for a thread to unschedule.
 *
 * Wait for the thread to block in any of the states set in @match_state.
 * 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)
{ … }

#ifdef CONFIG_SMP

static void
__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx);

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

void migrate_disable(void)
{ … }
EXPORT_SYMBOL_GPL(…);

void migrate_enable(void)
{ … }
EXPORT_SYMBOL_GPL(…);

static inline bool rq_has_pinned_tasks(struct rq *rq)
{ … }

/*
 * 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)
{ … }

/*
 * 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)
{ … }

struct migration_arg { … };

/*
 * @refs: number of wait_for_completion()
 * @stop_pending: is @stop_work in use
 */
struct set_affinity_pending { … };

/*
 * 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)
{ … }

/*
 * migration_cpu_stop - this will be executed by a high-prio stopper thread
 * and performs thread migration by bumping thread off CPU then
 * 'pushing' onto another runqueue.
 */
static int migration_cpu_stop(void *data)
{ … }

int push_cpu_stop(void *arg)
{ … }

/*
 * 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, struct affinity_context *ctx)
{ … }

static void
__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
{ … }

/*
 * Used for kthread_bind() and select_fallback_rq(), in both cases the user
 * affinity (if any) should be destroyed too.
 */
void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
{ … }

int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
		      int node)
{ … }

static inline struct cpumask *clear_user_cpus_ptr(struct task_struct *p)
{ … }

void release_user_cpus_ptr(struct task_struct *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)
	__releases(rq->lock)
	__releases(p->pi_lock)
{ … }

/*
 * 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,
					 struct affinity_context *ctx,
					 struct rq *rq,
					 struct rq_flags *rf)
	__releases(rq->lock)
	__releases(p->pi_lock)
{ … }

/*
 * 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.
 */
int __set_cpus_allowed_ptr(struct task_struct *p, struct affinity_context *ctx)
{ … }

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

/*
 * 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.
 * If user_cpus_ptr is defined, use it as the basis for restricting CPU
 * affinity or use cpu_online_mask instead.
 *
 * 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)
{ … }

/*
 * Restrict the CPU affinity of task @p so that it is a subset of
 * task_cpu_possible_mask() and point @p->user_cpus_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)
{ … }

/*
 * Restore the affinity of a task @p which was previously restricted by a
 * call to force_compatible_cpus_allowed_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)
{ … }

void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
{ … }

#ifdef CONFIG_NUMA_BALANCING
static void __migrate_swap_task(struct task_struct *p, int cpu)
{ … }

struct migration_swap_arg { … };

static int migrate_swap_stop(void *data)
{ … }

/*
 * Cross migrate two tasks
 */
int migrate_swap(struct task_struct *cur, struct task_struct *p,
		int target_cpu, int curr_cpu)
{ … }
#endif /* CONFIG_NUMA_BALANCING */

/***
 * 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)
{ … }
EXPORT_SYMBOL_GPL(…);

/*
 * ->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)
{ … }

/*
 * 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)
{ … }

void sched_set_stop_task(int cpu, struct task_struct *stop)
{ … }

#else /* CONFIG_SMP */

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)
{ … }

/*
 * Mark the task runnable.
 */
static inline void ttwu_do_wakeup(struct task_struct *p)
{ … }

static void
ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
		 struct rq_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)
{ … }

#ifdef CONFIG_SMP
void sched_ttwu_pending(void *arg)
{ … }

/*
 * Prepare the scene for sending an IPI for a remote smp_call
 *
 * Returns true if the caller can proceed with sending the IPI.
 * Returns false otherwise.
 */
bool call_function_single_prep_ipi(int 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)
{ … }

void wake_up_if_idle(int cpu)
{ … }

bool cpus_equal_capacity(int this_cpu, int that_cpu)
{ … }

bool cpus_share_cache(int this_cpu, int that_cpu)
{ … }

/*
 * Whether CPUs are share cache resources, which means LLC on non-cluster
 * machines and LLC tag or L2 on machines with clusters.
 */
bool cpus_share_resources(int this_cpu, int that_cpu)
{ … }

static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
{ … }

static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
{ … }

#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)
{ … }

/*
 * 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 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.
 *
 *   For PREEMPT_RT, the lock wait and lock wakeups happen via TASK_RTLOCK_WAIT.
 *   No other bits set. This allows to distinguish all wakeup scenarios.
 *
 *   For FREEZER, the wakeup happens via TASK_FROZEN. No other bits set. This
 *   allows us to prevent early wakeup of tasks before they can be run on
 *   asymmetric ISA architectures (eg ARMv9).
 */
static __always_inline
bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
{ … }

/*
 * 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.
 */
int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
{ … }

static bool __task_needs_rq_lock(struct task_struct *p)
{ … }

/**
 * task_call_func - 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.
 *
 * Fix the task in it's current state by avoiding wakeups and or rq operations
 * and call @func(@arg) on it.  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:
 *   Whatever @func returns
 */
int task_call_func(struct task_struct *p, task_call_f func, void *arg)
{ … }

/**
 * cpu_curr_snapshot - Return a snapshot of the currently running task
 * @cpu: The CPU on which to snapshot the task.
 *
 * Returns the task_struct pointer of the task "currently" running on
 * the specified CPU.
 *
 * If the specified CPU was offline, the return value is whatever it
 * is, perhaps a pointer to the task_struct structure of that CPU's idle
 * task, but there is no guarantee.  Callers wishing a useful return
 * value must take some action to ensure that the specified CPU remains
 * online throughout.
 *
 * This function executes full memory barriers before and after fetching
 * the pointer, which permits the caller to confine this function's fetch
 * with respect to the caller's accesses to other shared variables.
 */
struct task_struct *cpu_curr_snapshot(int cpu)
{ … }

/**
 * 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)
{ … }
EXPORT_SYMBOL(…);

int wake_up_state(struct task_struct *p, unsigned int state)
{ … }

/*
 * 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)
{ … }

DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);

#ifdef CONFIG_NUMA_BALANCING

int sysctl_numa_balancing_mode;

static void __set_numabalancing_state(bool enabled)
{ … }

void set_numabalancing_state(bool enabled)
{ … }

#ifdef CONFIG_PROC_SYSCTL
static void reset_memory_tiering(void)
{ … }

static int sysctl_numa_balancing(const struct ctl_table *table, int write,
			  void *buffer, size_t *lenp, loff_t *ppos)
{ … }
#endif
#endif

#ifdef CONFIG_SCHEDSTATS

DEFINE_STATIC_KEY_FALSE(sched_schedstats);

static void set_schedstats(bool enabled)
{ … }

void force_schedstat_enabled(void)
{ … }

static int __init setup_schedstats(char *str)
{ … }
__setup(…);

#ifdef CONFIG_PROC_SYSCTL
static int sysctl_schedstats(const struct ctl_table *table, int write, void *buffer,
		size_t *lenp, loff_t *ppos)
{ … }
#endif /* CONFIG_PROC_SYSCTL */
#endif /* CONFIG_SCHEDSTATS */

#ifdef CONFIG_SYSCTL
static struct ctl_table sched_core_sysctls[] = …;
static int __init sched_core_sysctl_init(void)
{ … }
late_initcall(sched_core_sysctl_init);
#endif /* CONFIG_SYSCTL */

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

void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
{ … }

void sched_post_fork(struct task_struct *p)
{ … }

unsigned long to_ratio(u64 period, u64 runtime)
{ … }

/*
 * 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)
{ … }

#ifdef CONFIG_PREEMPT_NOTIFIERS

static DEFINE_STATIC_KEY_FALSE(preempt_notifier_key);

void preempt_notifier_inc(void)
{ … }
EXPORT_SYMBOL_GPL(…);

void preempt_notifier_dec(void)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * preempt_notifier_register - tell me when current is being preempted & rescheduled
 * @notifier: notifier struct to register
 */
void preempt_notifier_register(struct preempt_notifier *notifier)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * 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)
{ … }
EXPORT_SYMBOL_GPL(…);

static void __fire_sched_in_preempt_notifiers(struct task_struct *curr)
{ … }

static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{ … }

static void
__fire_sched_out_preempt_notifiers(struct task_struct *curr,
				   struct task_struct *next)
{ … }

static __always_inline void
fire_sched_out_preempt_notifiers(struct task_struct *curr,
				 struct task_struct *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)
{ … }

static inline void finish_task(struct task_struct *prev)
{ … }

#ifdef CONFIG_SMP

static void do_balance_callbacks(struct rq *rq, struct balance_callback *head)
{ … }

static void balance_push(struct rq *rq);

/*
 * balance_push_callback is a right abuse of the callback interface and plays
 * by significantly different rules.
 *
 * Where the normal balance_callback's purpose is to be ran in the same context
 * that queued it (only later, when it's safe to drop rq->lock again),
 * balance_push_callback is specifically targeted at __schedule().
 *
 * This abuse is tolerated because it places all the unlikely/odd cases behind
 * a single test, namely: rq->balance_callback == NULL.
 */
struct balance_callback balance_push_callback = …;

static inline struct balance_callback *
__splice_balance_callbacks(struct rq *rq, bool split)
{ … }

struct balance_callback *splice_balance_callbacks(struct rq *rq)
{ … }

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

void balance_callbacks(struct rq *rq, struct balance_callback *head)
{ … }

#else

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

#endif

static inline void
prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf)
{ … }

static inline void finish_lock_switch(struct rq *rq)
{ … }

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

#ifndef prepare_arch_switch
#define prepare_arch_switch(next) …
#endif

#ifndef finish_arch_post_lock_switch
#define finish_arch_post_lock_switch() …
#endif

static inline void kmap_local_sched_out(void)
{ … }

static inline void kmap_local_sched_in(void)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/*
 * 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)
{ … }

/*
 * 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)
{ … }

/*
 * 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)
{ … }
EXPORT_SYMBOL(…);

unsigned long long nr_context_switches_cpu(int cpu)
{ … }

unsigned long long nr_context_switches(void)
{ … }

/*
 * 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)
{ … }

/*
 * 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)
{ … }

#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)
{ … }

#endif

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

EXPORT_PER_CPU_SYMBOL(…);
EXPORT_PER_CPU_SYMBOL(…);

/*
 * 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)
{ … }

/*
 * 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)
{ … }

#ifdef CONFIG_SCHED_DEBUG
static u64 cpu_resched_latency(struct rq *rq)
{ … }

static int __init setup_resched_latency_warn_ms(char *str)
{ … }
__setup(…);
#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 sched_tick(void)
{ … }

#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 …
#define TICK_SCHED_REMOTE_OFFLINING …
#define TICK_SCHED_REMOTE_RUNNING …

/*
 * 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);
	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)) {
		guard(rq_lock_irq)(rq);
		struct task_struct *curr = rq->curr;

		if (cpu_online(cpu)) {
			update_rq_clock(rq);

			if (!is_idle_task(curr)) {
				/*
				 * Make sure the next tick runs within a
				 * reasonable amount of time.
				 */
				u64 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);
		}
	}

	/*
	 * 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_TYPE_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_TYPE_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)
{ … }

void preempt_count_add(int val)
{ … }
EXPORT_SYMBOL(…);
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)
{ … }

void preempt_count_sub(int val)
{ … }
EXPORT_SYMBOL(…);
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)
{ … }

/*
 * Print scheduling while atomic bug:
 */
static noinline void __schedule_bug(struct task_struct *prev)
{ … }

/*
 * Various schedule()-time debugging checks and statistics:
 */
static inline void schedule_debug(struct task_struct *prev, bool preempt)
{ … }

static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
				  struct rq_flags *rf)
{ … }

/*
 * 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)
{ … }

#ifdef CONFIG_SCHED_CORE
static inline bool is_task_rq_idle(struct task_struct *t)
{ … }

static inline bool cookie_equals(struct task_struct *a, unsigned long cookie)
{ … }

static inline bool cookie_match(struct task_struct *a, struct task_struct *b)
{ … }

static inline struct task_struct *pick_task(struct rq *rq)
{ … }

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

static void queue_core_balance(struct rq *rq);

static struct task_struct *
pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{ … }

static bool try_steal_cookie(int this, int that)
{ … }

static bool steal_cookie_task(int cpu, struct sched_domain *sd)
{ … }

static void sched_core_balance(struct rq *rq)
{ … }

static DEFINE_PER_CPU(struct balance_callback, core_balance_head);

static void queue_core_balance(struct rq *rq)
{ … }

DEFINE_LOCK_GUARD_1(core_lock, int,
		    sched_core_lock(*_T->lock, &_T->flags),
		    sched_core_unlock(*_T->lock, &_T->flags),
		     … } 

static void sched_core_cpu_starting(unsigned int cpu)
{ … }

static void sched_core_cpu_deactivate(unsigned int cpu)
{ … }

static inline void sched_core_cpu_dying(unsigned int cpu)
{ … }

#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 …
#define SM_PREEMPT …
#define SM_RTLOCK_WAIT …

#ifndef CONFIG_PREEMPT_RT
#define SM_MASK_PREEMPT …
#else
#define SM_MASK_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 sched_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)
{ … }

void __noreturn do_task_dead(void)
{ … }

static inline void sched_submit_work(struct task_struct *tsk)
{ … }

static void sched_update_worker(struct task_struct *tsk)
{ … }

static __always_inline void __schedule_loop(unsigned int sched_mode)
{ … }

asmlinkage __visible void __sched schedule(void)
{ … }
EXPORT_SYMBOL(…);

/*
 * 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)
{ … }

#if defined(CONFIG_CONTEXT_TRACKING_USER) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_USER_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)
{ … }

#ifdef CONFIG_PREEMPT_RT
void __sched notrace schedule_rtlock(void)
{
	__schedule_loop(SM_RTLOCK_WAIT);
}
NOKPROBE_SYMBOL(schedule_rtlock);
#endif

static void __sched notrace preempt_schedule_common(void)
{ … }

#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)
{ … }
NOKPROBE_SYMBOL(preempt_schedule);
EXPORT_SYMBOL(…);

#ifdef CONFIG_PREEMPT_DYNAMIC
#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
#ifndef preempt_schedule_dynamic_enabled
#define preempt_schedule_dynamic_enabled …
#define preempt_schedule_dynamic_disabled …
#endif
DEFINE_STATIC_CALL(…);
EXPORT_STATIC_CALL_TRAMP(…);
#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule);
void __sched notrace dynamic_preempt_schedule(void)
{
	if (!static_branch_unlikely(&sk_dynamic_preempt_schedule))
		return;
	preempt_schedule();
}
NOKPROBE_SYMBOL(dynamic_preempt_schedule);
EXPORT_SYMBOL(dynamic_preempt_schedule);
#endif
#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)
{ … }
EXPORT_SYMBOL_GPL(…);

#ifdef CONFIG_PREEMPT_DYNAMIC
#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
#ifndef preempt_schedule_notrace_dynamic_enabled
#define preempt_schedule_notrace_dynamic_enabled …
#define preempt_schedule_notrace_dynamic_disabled …
#endif
DEFINE_STATIC_CALL(…);
EXPORT_STATIC_CALL_TRAMP(…);
#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule_notrace);
void __sched notrace dynamic_preempt_schedule_notrace(void)
{
	if (!static_branch_unlikely(&sk_dynamic_preempt_schedule_notrace))
		return;
	preempt_schedule_notrace();
}
NOKPROBE_SYMBOL(dynamic_preempt_schedule_notrace);
EXPORT_SYMBOL(dynamic_preempt_schedule_notrace);
#endif
#endif

#endif /* CONFIG_PREEMPTION */

/*
 * This is the entry point to schedule() from kernel preemption
 * off of IRQ context.
 * Note, that this is called and return with IRQs disabled. This will
 * protect us against recursive calling from IRQ contexts.
 */
asmlinkage __visible void __sched preempt_schedule_irq(void)
{ … }

int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
			  void *key)
{ … }
EXPORT_SYMBOL(…);

void __setscheduler_prio(struct task_struct *p, int prio)
{ … }

#ifdef CONFIG_RT_MUTEXES

/*
 * Would be more useful with typeof()/auto_type but they don't mix with
 * bit-fields. Since it's a local thing, use int. Keep the generic sounding
 * name such that if someone were to implement this function we get to compare
 * notes.
 */
#define fetch_and_set(x, v) …

void rt_mutex_pre_schedule(void)
{ … }

void rt_mutex_schedule(void)
{ … }

void rt_mutex_post_schedule(void)
{ … }

/*
 * 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)
{ … }
#endif

#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
int __sched __cond_resched(void)
{ … }
EXPORT_SYMBOL(…);
#endif

#ifdef CONFIG_PREEMPT_DYNAMIC
#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
#define cond_resched_dynamic_enabled …
#define cond_resched_dynamic_disabled …
DEFINE_STATIC_CALL_RET0(…);
EXPORT_STATIC_CALL_TRAMP(…);

#define might_resched_dynamic_enabled …
#define might_resched_dynamic_disabled …
DEFINE_STATIC_CALL_RET0(…);
EXPORT_STATIC_CALL_TRAMP(…);
#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched);
int __sched dynamic_cond_resched(void)
{
	klp_sched_try_switch();
	if (!static_branch_unlikely(&sk_dynamic_cond_resched))
		return 0;
	return __cond_resched();
}
EXPORT_SYMBOL(dynamic_cond_resched);

static DEFINE_STATIC_KEY_FALSE(sk_dynamic_might_resched);
int __sched dynamic_might_resched(void)
{
	if (!static_branch_unlikely(&sk_dynamic_might_resched))
		return 0;
	return __cond_resched();
}
EXPORT_SYMBOL(dynamic_might_resched);
#endif
#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)
{ … }
EXPORT_SYMBOL(…);

int __cond_resched_rwlock_read(rwlock_t *lock)
{ … }
EXPORT_SYMBOL(…);

int __cond_resched_rwlock_write(rwlock_t *lock)
{ … }
EXPORT_SYMBOL(…);

#ifdef CONFIG_PREEMPT_DYNAMIC

#ifdef CONFIG_GENERIC_ENTRY
#include <linux/entry-common.h>
#endif

/*
 * 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 { … };

int preempt_dynamic_mode = …;

int sched_dynamic_mode(const char *str)
{ … }

#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
#define preempt_dynamic_enable(f) …
#define preempt_dynamic_disable(f) …
#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
#define preempt_dynamic_enable …
#define preempt_dynamic_disable …
#else
#error "Unsupported PREEMPT_DYNAMIC mechanism"
#endif

static DEFINE_MUTEX(sched_dynamic_mutex);
static bool klp_override;

static void __sched_dynamic_update(int mode)
{ … }

void sched_dynamic_update(int mode)
{ … }

#ifdef CONFIG_HAVE_PREEMPT_DYNAMIC_CALL

static int klp_cond_resched(void)
{ … }

void sched_dynamic_klp_enable(void)
{ … }

void sched_dynamic_klp_disable(void)
{ … }

#endif /* CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */

static int __init setup_preempt_mode(char *str)
{ … }
__setup(…);

static void __init preempt_dynamic_init(void)
{ … }

#define PREEMPT_MODEL_ACCESSOR(mode) …

PREEMPT_MODEL_ACCESSOR(…);
PREEMPT_MODEL_ACCESSOR(…);
PREEMPT_MODEL_ACCESSOR(…);

#else /* !CONFIG_PREEMPT_DYNAMIC: */

static inline void preempt_dynamic_init(void) { }

#endif /* CONFIG_PREEMPT_DYNAMIC */

int io_schedule_prepare(void)
{ … }

void io_schedule_finish(int 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)
{ … }
EXPORT_SYMBOL(…);

void __sched io_schedule(void)
{ … }
EXPORT_SYMBOL(…);

void sched_show_task(struct task_struct *p)
{ … }
EXPORT_SYMBOL_GPL(…);

static inline bool
state_filter_match(unsigned long state_filter, struct task_struct *p)
{ … }


void show_state_filter(unsigned int state_filter)
{ … }

/**
 * 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)
{ … }

#ifdef CONFIG_SMP

int cpuset_cpumask_can_shrink(const struct cpumask *cur,
			      const struct cpumask *trial)
{ … }

int task_can_attach(struct task_struct *p)
{ … }

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)
{ … }

/*
 * 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)
{ … }
#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)
{ … }

static int __balance_push_cpu_stop(void *arg)
{ … }

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)
{ … }

static void balance_push_set(int cpu, bool on)
{ … }

/*
 * Invoked from a CPUs hotplug control thread after the CPU has been marked
 * inactive. All tasks which are not per CPU kernel threads are either
 * pushed off this CPU now via balance_push() or placed on a different CPU
 * during wakeup. Wait until the CPU is quiescent.
 */
static void balance_hotplug_wait(void)
{ … }

#else

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

static inline void balance_push_set(int cpu, bool on)
{
}

static inline void balance_hotplug_wait(void)
{
}

#endif /* CONFIG_HOTPLUG_CPU */

void set_rq_online(struct rq *rq)
{ … }

void set_rq_offline(struct rq *rq)
{ … }

static inline void sched_set_rq_online(struct rq *rq, int cpu)
{ … }

static inline void sched_set_rq_offline(struct rq *rq, int cpu)
{ … }

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

/*
 * Update cpusets according to cpu_active mask.  If cpusets are
 * disabled, cpuset_update_active_cpus() becomes a simple wrapper
 * around partition_sched_domains().
 *
 * If we come here as part of a suspend/resume, don't touch cpusets because we
 * want to restore it back to its original state upon resume anyway.
 */
static void cpuset_cpu_active(void)
{ … }

static int cpuset_cpu_inactive(unsigned int cpu)
{ … }

static inline void sched_smt_present_inc(int cpu)
{ … }

static inline void sched_smt_present_dec(int cpu)
{ … }

int sched_cpu_activate(unsigned int cpu)
{ … }

int sched_cpu_deactivate(unsigned int cpu)
{ … }

static void sched_rq_cpu_starting(unsigned int cpu)
{ … }

int sched_cpu_starting(unsigned int cpu)
{ … }

#ifdef CONFIG_HOTPLUG_CPU

/*
 * Invoked immediately before the stopper thread is invoked to bring the
 * CPU down completely. At this point all per CPU kthreads except the
 * hotplug thread (current) and the stopper thread (inactive) have been
 * either parked or have been unbound from the outgoing CPU. Ensure that
 * any of those which might be on the way out are gone.
 *
 * If after this point a bound task is being woken on this CPU then the
 * responsible hotplug callback has failed to do it's job.
 * sched_cpu_dying() will catch it with the appropriate fireworks.
 */
int sched_cpu_wait_empty(unsigned int cpu)
{ … }

/*
 * Since this CPU is going 'away' for a while, fold any nr_active delta we
 * might have. Called from the CPU stopper task after ensuring that the
 * stopper is the last running task on the CPU, so nr_active count is
 * stable. We need to take the tear-down thread which is calling this into
 * account, so we hand in adjust = 1 to the load calculation.
 *
 * Also see the comment "Global load-average calculations".
 */
static void calc_load_migrate(struct rq *rq)
{ … }

static void dump_rq_tasks(struct rq *rq, const char *loglvl)
{ … }

int sched_cpu_dying(unsigned int cpu)
{ … }
#endif

void __init sched_init_smp(void)
{ … }

static int __init migration_init(void)
{ … }
early_initcall(migration_init);

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

int in_sched_functions(unsigned long addr)
{ … }

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

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

void __init sched_init(void)
{ … }

#ifdef CONFIG_DEBUG_ATOMIC_SLEEP

void __might_sleep(const char *file, int line)
{ … }
EXPORT_SYMBOL(…);

static void print_preempt_disable_ip(int preempt_offset, unsigned long ip)
{ … }

static inline bool resched_offsets_ok(unsigned int offsets)
{ … }

void __might_resched(const char *file, int line, unsigned int offsets)
{ … }
EXPORT_SYMBOL(…);

void __cant_sleep(const char *file, int line, int preempt_offset)
{ … }
EXPORT_SYMBOL_GPL(…);

#ifdef CONFIG_SMP
void __cant_migrate(const char *file, int line)
{ … }
EXPORT_SYMBOL_GPL(…);
#endif
#endif

#ifdef CONFIG_MAGIC_SYSRQ
void normalize_rt_tasks(void)
{ … }

#endif /* CONFIG_MAGIC_SYSRQ */

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

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

#endif /* defined(CONFIG_KGDB_KDB) */

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

static inline void alloc_uclamp_sched_group(struct task_group *tg,
					    struct task_group *parent)
{ … }

static void sched_free_group(struct task_group *tg)
{ … }

static void sched_free_group_rcu(struct rcu_head *rcu)
{ … }

static void sched_unregister_group(struct task_group *tg)
{ … }

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

void sched_online_group(struct task_group *tg, struct task_group *parent)
{ … }

/* RCU callback to free various structures associated with a task group */
static void sched_unregister_group_rcu(struct rcu_head *rhp)
{ … }

void sched_destroy_group(struct task_group *tg)
{ … }

void sched_release_group(struct task_group *tg)
{ … }

static struct task_group *sched_get_task_group(struct task_struct *tsk)
{ … }

static void sched_change_group(struct task_struct *tsk, struct task_group *group)
{ … }

/*
 * Change task's runqueue when it moves between groups.
 *
 * The caller of this function should have put the task in its new group by
 * now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect
 * its new group.
 */
void sched_move_task(struct task_struct *tsk)
{ … }

static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
{ … }

static struct cgroup_subsys_state *
cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{ … }

/* Expose task group only after completing cgroup initialization */
static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
{ … }

static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
{ … }

static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
{ … }

#ifdef CONFIG_RT_GROUP_SCHED
static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
{ … }
#endif

static void cpu_cgroup_attach(struct cgroup_taskset *tset)
{ … }

#ifdef CONFIG_UCLAMP_TASK_GROUP
static void cpu_util_update_eff(struct cgroup_subsys_state *css)
{ … }

/*
 * Integer 10^N with a given N exponent by casting to integer the literal "1eN"
 * C expression. Since there is no way to convert a macro argument (N) into a
 * character constant, use two levels of macros.
 */
#define _POW10(exp) …
#define POW10(exp) …

struct uclamp_request { … };

static inline struct uclamp_request
capacity_from_percent(char *buf)
{ … }

static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
				size_t nbytes, loff_t off,
				enum uclamp_id clamp_id)
{ … }

static ssize_t cpu_uclamp_min_write(struct kernfs_open_file *of,
				    char *buf, size_t nbytes,
				    loff_t off)
{ … }

static ssize_t cpu_uclamp_max_write(struct kernfs_open_file *of,
				    char *buf, size_t nbytes,
				    loff_t off)
{ … }

static inline void cpu_uclamp_print(struct seq_file *sf,
				    enum uclamp_id clamp_id)
{ … }

static int cpu_uclamp_min_show(struct seq_file *sf, void *v)
{ … }

static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
{ … }
#endif /* CONFIG_UCLAMP_TASK_GROUP */

#ifdef CONFIG_FAIR_GROUP_SCHED
static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
				struct cftype *cftype, u64 shareval)
{ … }

static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
			       struct cftype *cft)
{ … }

#ifdef CONFIG_CFS_BANDWIDTH
static DEFINE_MUTEX(cfs_constraints_mutex);

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

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

static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota,
				u64 burst)
{ … }

static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
{ … }

static long tg_get_cfs_quota(struct task_group *tg)
{ … }

static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
{ … }

static long tg_get_cfs_period(struct task_group *tg)
{ … }

static int tg_set_cfs_burst(struct task_group *tg, long cfs_burst_us)
{ … }

static long tg_get_cfs_burst(struct task_group *tg)
{ … }

static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css,
				  struct cftype *cft)
{ … }

static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css,
				   struct cftype *cftype, s64 cfs_quota_us)
{ … }

static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css,
				   struct cftype *cft)
{ … }

static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css,
				    struct cftype *cftype, u64 cfs_period_us)
{ … }

static u64 cpu_cfs_burst_read_u64(struct cgroup_subsys_state *css,
				  struct cftype *cft)
{ … }

static int cpu_cfs_burst_write_u64(struct cgroup_subsys_state *css,
				   struct cftype *cftype, u64 cfs_burst_us)
{ … }

struct cfs_schedulable_data { … };

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

static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
{ … }

static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
{ … }

static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
{ … }

static u64 throttled_time_self(struct task_group *tg)
{ … }

static int cpu_cfs_local_stat_show(struct seq_file *sf, void *v)
{ … }
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */

#ifdef CONFIG_RT_GROUP_SCHED
static int cpu_rt_runtime_write(struct cgroup_subsys_state *css,
				struct cftype *cft, s64 val)
{ … }

static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css,
			       struct cftype *cft)
{ … }

static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css,
				    struct cftype *cftype, u64 rt_period_us)
{ … }

static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
				   struct cftype *cft)
{ … }
#endif /* CONFIG_RT_GROUP_SCHED */

#ifdef CONFIG_FAIR_GROUP_SCHED
static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css,
			       struct cftype *cft)
{ … }

static int cpu_idle_write_s64(struct cgroup_subsys_state *css,
				struct cftype *cft, s64 idle)
{ … }
#endif

static struct cftype cpu_legacy_files[] = …;

static int cpu_extra_stat_show(struct seq_file *sf,
			       struct cgroup_subsys_state *css)
{ … }

static int cpu_local_stat_show(struct seq_file *sf,
			       struct cgroup_subsys_state *css)
{ … }

#ifdef CONFIG_FAIR_GROUP_SCHED
static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
			       struct cftype *cft)
{ … }

static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
				struct cftype *cft, u64 weight)
{ … }

static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
				    struct cftype *cft)
{ … }

static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
				     struct cftype *cft, s64 nice)
{ … }
#endif

static void __maybe_unused cpu_period_quota_print(struct seq_file *sf,
						  long period, long quota)
{ … }

/* caller should put the current value in *@periodp before calling */
static int __maybe_unused cpu_period_quota_parse(char *buf,
						 u64 *periodp, u64 *quotap)
{ … }

#ifdef CONFIG_CFS_BANDWIDTH
static int cpu_max_show(struct seq_file *sf, void *v)
{ … }

static ssize_t cpu_max_write(struct kernfs_open_file *of,
			     char *buf, size_t nbytes, loff_t off)
{ … }
#endif

static struct cftype cpu_files[] = …;

struct cgroup_subsys cpu_cgrp_subsys = …;

#endif	/* CONFIG_CGROUP_SCHED */

void dump_cpu_task(int cpu)
{ … }

/*
 * Nice levels are multiplicative, with a gentle 10% change for every
 * nice level changed. I.e. when a CPU-bound task goes from nice 0 to
 * nice 1, it will get ~10% less CPU time than another CPU-bound task
 * that remained on nice 0.
 *
 * The "10% effect" is relative and cumulative: from _any_ nice level,
 * if you go up 1 level, it's -10% CPU usage, if you go down 1 level
 * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
 * If a task goes up by ~10% and another task goes down by ~10% then
 * the relative distance between them is ~25%.)
 */
const int sched_prio_to_weight[40] = …;

/*
 * Inverse (2^32/x) values of the sched_prio_to_weight[] array, pre-calculated.
 *
 * In cases where the weight does not change often, we can use the
 * pre-calculated inverse to speed up arithmetics by turning divisions
 * into multiplications:
 */
const u32 sched_prio_to_wmult[40] = …;

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

#ifdef CONFIG_SCHED_MM_CID

/*
 * @cid_lock: Guarantee forward-progress of cid allocation.
 *
 * Concurrency ID allocation within a bitmap is mostly lock-free. The cid_lock
 * is only used when contention is detected by the lock-free allocation so
 * forward progress can be guaranteed.
 */
DEFINE_RAW_SPINLOCK(…);

/*
 * @use_cid_lock: Select cid allocation behavior: lock-free vs spinlock.
 *
 * When @use_cid_lock is 0, the cid allocation is lock-free. When contention is
 * detected, it is set to 1 to ensure that all newly coming allocations are
 * serialized by @cid_lock until the allocation which detected contention
 * completes and sets @use_cid_lock back to 0. This guarantees forward progress
 * of a cid allocation.
 */
int use_cid_lock;

/*
 * mm_cid remote-clear implements a lock-free algorithm to clear per-mm/cpu cid
 * concurrently with respect to the execution of the source runqueue context
 * switch.
 *
 * There is one basic properties we want to guarantee here:
 *
 * (1) Remote-clear should _never_ mark a per-cpu cid UNSET when it is actively
 * used by a task. That would lead to concurrent allocation of the cid and
 * userspace corruption.
 *
 * Provide this guarantee by introducing a Dekker memory ordering to guarantee
 * that a pair of loads observe at least one of a pair of stores, which can be
 * shown as:
 *
 *      X = Y = 0
 *
 *      w[X]=1          w[Y]=1
 *      MB              MB
 *      r[Y]=y          r[X]=x
 *
 * Which guarantees that x==0 && y==0 is impossible. But rather than using
 * values 0 and 1, this algorithm cares about specific state transitions of the
 * runqueue current task (as updated by the scheduler context switch), and the
 * per-mm/cpu cid value.
 *
 * Let's introduce task (Y) which has task->mm == mm and task (N) which has
 * task->mm != mm for the rest of the discussion. There are two scheduler state
 * transitions on context switch we care about:
 *
 * (TSA) Store to rq->curr with transition from (N) to (Y)
 *
 * (TSB) Store to rq->curr with transition from (Y) to (N)
 *
 * On the remote-clear side, there is one transition we care about:
 *
 * (TMA) cmpxchg to *pcpu_cid to set the LAZY flag
 *
 * There is also a transition to UNSET state which can be performed from all
 * sides (scheduler, remote-clear). It is always performed with a cmpxchg which
 * guarantees that only a single thread will succeed:
 *
 * (TMB) cmpxchg to *pcpu_cid to mark UNSET
 *
 * Just to be clear, what we do _not_ want to happen is a transition to UNSET
 * when a thread is actively using the cid (property (1)).
 *
 * Let's looks at the relevant combinations of TSA/TSB, and TMA transitions.
 *
 * Scenario A) (TSA)+(TMA) (from next task perspective)
 *
 * CPU0                                      CPU1
 *
 * Context switch CS-1                       Remote-clear
 *   - store to rq->curr: (N)->(Y) (TSA)     - cmpxchg to *pcpu_id to LAZY (TMA)
 *                                             (implied barrier after cmpxchg)
 *   - switch_mm_cid()
 *     - memory barrier (see switch_mm_cid()
 *       comment explaining how this barrier
 *       is combined with other scheduler
 *       barriers)
 *     - mm_cid_get (next)
 *       - READ_ONCE(*pcpu_cid)              - rcu_dereference(src_rq->curr)
 *
 * This Dekker ensures that either task (Y) is observed by the
 * rcu_dereference() or the LAZY flag is observed by READ_ONCE(), or both are
 * observed.
 *
 * If task (Y) store is observed by rcu_dereference(), it means that there is
 * still an active task on the cpu. Remote-clear will therefore not transition
 * to UNSET, which fulfills property (1).
 *
 * If task (Y) is not observed, but the lazy flag is observed by READ_ONCE(),
 * it will move its state to UNSET, which clears the percpu cid perhaps
 * uselessly (which is not an issue for correctness). Because task (Y) is not
 * observed, CPU1 can move ahead to set the state to UNSET. Because moving
 * state to UNSET is done with a cmpxchg expecting that the old state has the
 * LAZY flag set, only one thread will successfully UNSET.
 *
 * If both states (LAZY flag and task (Y)) are observed, the thread on CPU0
 * will observe the LAZY flag and transition to UNSET (perhaps uselessly), and
 * CPU1 will observe task (Y) and do nothing more, which is fine.
 *
 * What we are effectively preventing with this Dekker is a scenario where
 * neither LAZY flag nor store (Y) are observed, which would fail property (1)
 * because this would UNSET a cid which is actively used.
 */

void sched_mm_cid_migrate_from(struct task_struct *t)
{ … }

static
int __sched_mm_cid_migrate_from_fetch_cid(struct rq *src_rq,
					  struct task_struct *t,
					  struct mm_cid *src_pcpu_cid)
{ … }

static
int __sched_mm_cid_migrate_from_try_steal_cid(struct rq *src_rq,
					      struct task_struct *t,
					      struct mm_cid *src_pcpu_cid,
					      int src_cid)
{ … }

/*
 * Migration to dst cpu. Called with dst_rq lock held.
 * Interrupts are disabled, which keeps the window of cid ownership without the
 * source rq lock held small.
 */
void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t)
{ … }

static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_cid,
				      int cpu)
{ … }

static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu)
{ … }

static void sched_mm_cid_remote_clear_weight(struct mm_struct *mm, int cpu,
					     int weight)
{ … }

static void task_mm_cid_work(struct callback_head *work)
{ … }

void init_sched_mm_cid(struct task_struct *t)
{ … }

void task_tick_mm_cid(struct rq *rq, struct task_struct *curr)
{ … }

void sched_mm_cid_exit_signals(struct task_struct *t)
{ … }

void sched_mm_cid_before_execve(struct task_struct *t)
{ … }

void sched_mm_cid_after_execve(struct task_struct *t)
{ … }

void sched_mm_cid_fork(struct task_struct *t)
{ … }
#endif