12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H

 * Define 'struct task_struct' and provide the main scheduler
 * APIs (schedule(), wakeup variants, etc.)

#include <uapi/linux/sched.h>

#include <asm/current.h>

#include <linux/pid.h>
#include <linux/sem.h>
#include <linux/shm.h>
#include <linux/kcov.h>
#include <linux/mutex.h>
#include <linux/plist.h>
#include <linux/hrtimer.h>
#include <linux/seccomp.h>
#include <linux/nodemask.h>
#include <linux/rcupdate.h>
#include <linux/resource.h>
#include <linux/latencytop.h>
#include <linux/sched/prio.h>
#include <linux/signal_types.h>
#include <linux/psi_types.h>
#include <linux/mm_types_task.h>
#include <linux/task_io_accounting.h>
#include <linux/rseq.h>

/* task_struct member predeclarations (sorted alphabetically): */
struct audit_context;
struct backing_dev_info;
struct bio_list;
struct blk_plug;
struct cfs_rq;
struct fs_struct;
struct futex_pi_state;
struct io_context;
struct mempolicy;
struct nameidata;
struct nsproxy;
struct perf_event_context;
struct pid_namespace;
struct pipe_inode_info;
struct rcu_node;
struct reclaim_state;
struct robust_list_head;
struct sched_attr;
struct sched_param;
struct seq_file;
struct sighand_struct;
struct signal_struct;
struct task_delay_info;
struct task_group;

 * Task state bitmask. NOTE! These bits are also
 * encoded in fs/proc/array.c: get_task_state().
 * We have two separate sets of flags: task->state
 * is about runnability, while task->exit_state are
 * about the task exiting. Confusing, but this way
 * modifying one set can't modify the other one by
 * mistake.

/* Used in tsk->state: */
#define TASK_RUNNING			0x0000
#define TASK_INTERRUPTIBLE		0x0001
#define __TASK_STOPPED			0x0004
#define __TASK_TRACED			0x0008
/* Used in tsk->exit_state: */
#define EXIT_DEAD			0x0010
#define EXIT_ZOMBIE			0x0020
/* Used in tsk->state again: */
#define TASK_PARKED			0x0040
#define TASK_DEAD			0x0080
#define TASK_WAKEKILL			0x0100
#define TASK_WAKING			0x0200
#define TASK_NOLOAD			0x0400
#define TASK_NEW			0x0800
#define TASK_STATE_MAX			0x1000

/* Convenience macros for the sake of set_current_state: */


/* Convenience macros for the sake of wake_up(): */

/* get_task_state(): */

#define task_is_traced(task)		((task->state & __TASK_TRACED) != 0)

#define task_is_stopped(task)		((task->state & __TASK_STOPPED) != 0)

#define task_is_stopped_or_traced(task)	((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)

#define task_contributes_to_load(task)	((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
					 (task->flags & PF_FROZEN) == 0 && \
					 (task->state & TASK_NOLOAD) == 0)


 * Special states are those that do not use the normal wait-loop pattern. See
 * the comment with set_special_state().
#define is_special_task_state(state)				\

#define __set_current_state(state_value)			\
	do {							\
		current->task_state_change = _THIS_IP_;		\
		current->state = (state_value);			\
	} while (0)

#define set_current_state(state_value)				\
	do {							\
		current->task_state_change = _THIS_IP_;		\
		smp_store_mb(current->state, (state_value));	\
	} while (0)

#define set_special_state(state_value)					\
	do {								\
		unsigned long flags; /* may shadow */			\
		WARN_ON_ONCE(!is_special_task_state(state_value));	\
		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
		current->task_state_change = _THIS_IP_;			\
		current->state = (state_value);				\
		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
	} while (0)
 * set_current_state() includes a barrier so that the write of current->state
 * is correctly serialised wrt the caller's subsequent test of whether to
 * actually sleep:
 *   for (;;) {
 *	set_current_state(TASK_UNINTERRUPTIBLE);
 *	if (!need_sleep)
 *		break;
 *	schedule();
 *   }
 *   __set_current_state(TASK_RUNNING);
 * If the caller does not need such serialisation (because, for instance, the
 * condition test and condition change and wakeup are under the same lock) then
 * use __set_current_state().
 * The above is typically ordered against the wakeup, which does:
 *   need_sleep = false;
 *   wake_up_state(p, TASK_UNINTERRUPTIBLE);
 * where wake_up_state() executes a full memory barrier before accessing the
 * task state.
 * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is,
 * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
 * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING).
 * However, with slightly different timing the wakeup TASK_RUNNING store can
 * also collide with the TASK_UNINTERRUPTIBLE store. Loosing that store is not
 * a problem either because that will result in one extra go around the loop
 * and our @cond test will save the day.
 * Also see the comments of try_to_wake_up().
#define __set_current_state(state_value)				\
	current->state = (state_value)

#define set_current_state(state_value)					\
	smp_store_mb(current->state, (state_value))

 * set_special_state() should be used for those states when the blocking task
 * can not use the regular condition based wait-loop. In that case we must
 * serialize against wakeups such that any possible in-flight TASK_RUNNING stores
 * will not collide with our state change.
#define set_special_state(state_value)					\
	do {								\
		unsigned long flags; /* may shadow */			\
		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
		current->state = (state_value);				\
		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
	} while (0)


/* Task command name length: */
#define TASK_COMM_LEN			16

extern void scheduler_tick(void);


extern long schedule_timeout(long timeout);
extern long schedule_timeout_interruptible(long timeout);
extern long schedule_timeout_killable(long timeout);
extern long schedule_timeout_uninterruptible(long timeout);
extern long schedule_timeout_idle(long timeout);
asmlinkage void schedule(void);
extern void schedule_preempt_disabled(void);

extern int __must_check io_schedule_prepare(void);
extern void io_schedule_finish(int token);
extern long io_schedule_timeout(long timeout);
extern void io_schedule(void);

 * struct prev_cputime - snapshot of system and user cputime
 * @utime: time spent in user mode
 * @stime: time spent in system mode
 * @lock: protects the above two fields
 * Stores previous user/system time values such that we can guarantee
 * monotonicity.
struct prev_cputime {
	u64				utime;
	u64				stime;
	raw_spinlock_t			lock;

 * struct task_cputime - collected CPU time counts
 * @utime:		time spent in user mode, in nanoseconds
 * @stime:		time spent in kernel mode, in nanoseconds
 * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
 * This structure groups together three kinds of CPU time that are tracked for
 * threads and thread groups.  Most things considering CPU time want to group
 * these counts together and treat all three of them in parallel.
struct task_cputime {
	u64				utime;
	u64				stime;
	unsigned long long		sum_exec_runtime;

/* Alternate field names when used on cache expirations: */
#define virt_exp			utime
#define prof_exp			stime
#define sched_exp			sum_exec_runtime

enum vtime_state {
	/* Task is sleeping or running in a CPU with VTIME inactive: */
	/* Task runs in userspace in a CPU with VTIME active: */
	/* Task runs in kernelspace in a CPU with VTIME active: */

struct vtime {
	seqcount_t		seqcount;
	unsigned long long	starttime;
	enum vtime_state	state;
	u64			utime;
	u64			stime;
	u64			gtime;

struct sched_info {
	/* Cumulative counters: */

	/* # of times we have run on this CPU: */
	unsigned long			pcount;

	/* Time spent waiting on a runqueue: */
	unsigned long long		run_delay;

	/* Timestamps: */

	/* When did we last run on a CPU? */
	unsigned long long		last_arrival;

	/* When were we last queued to run? */
	unsigned long long		last_queued;

#endif /* CONFIG_SCHED_INFO */

 * Integer metrics need fixed point arithmetic, e.g., sched/fair
 * has a few: load, load_avg, util_avg, freq, and capacity.
 * We define a basic fixed point arithmetic range, and then formalize
 * all these metrics based on that basic range.

struct load_weight {
	unsigned long			weight;
	u32				inv_weight;

 * struct util_est - Estimation utilization of FAIR tasks
 * @enqueued: instantaneous estimated utilization of a task/cpu
 * @ewma:     the Exponential Weighted Moving Average (EWMA)
 *            utilization of a task
 * Support data structure to track an Exponential Weighted Moving Average
 * (EWMA) of a FAIR task's utilization. New samples are added to the moving
 * average each time a task completes an activation. Sample's weight is chosen
 * so that the EWMA will be relatively insensitive to transient changes to the
 * task's workload.
 * The enqueued attribute has a slightly different meaning for tasks and cpus:
 * - task:   the task's util_avg at last task dequeue time
 * - cfs_rq: the sum of util_est.enqueued for each RUNNABLE task on that CPU
 * Thus, the util_est.enqueued of a task represents the contribution on the
 * estimated utilization of the CPU where that task is currently enqueued.
 * Only for tasks we track a moving average of the past instantaneous
 * estimated utilization. This allows to absorb sporadic drops in utilization
 * of an otherwise almost periodic task.
struct util_est {
	unsigned int			enqueued;
	unsigned int			ewma;
} __attribute__((__aligned__(sizeof(u64))));

 * The load_avg/util_avg accumulates an infinite geometric series
 * (see __update_load_avg() in kernel/sched/fair.c).
 * [load_avg definition]
 *   load_avg = runnable% * scale_load_down(load)
 * where runnable% is the time ratio that a sched_entity is runnable.
 * For cfs_rq, it is the aggregated load_avg of all runnable and
 * blocked sched_entities.
 * load_avg may also take frequency scaling into account:
 *   load_avg = runnable% * scale_load_down(load) * freq%
 * where freq% is the CPU frequency normalized to the highest frequency.
 * [util_avg definition]
 *   util_avg = running% * SCHED_CAPACITY_SCALE
 * where running% is the time ratio that a sched_entity is running on
 * a CPU. For cfs_rq, it is the aggregated util_avg of all runnable
 * and blocked sched_entities.
 * util_avg may also factor frequency scaling and CPU capacity scaling:
 *   util_avg = running% * SCHED_CAPACITY_SCALE * freq% * capacity%
 * where freq% is the same as above, and capacity% is the CPU capacity
 * normalized to the greatest capacity (due to uarch differences, etc).
 * N.B., the above ratios (runnable%, running%, freq%, and capacity%)
 * themselves are in the range of [0, 1]. To do fixed point arithmetics,
 * we therefore scale them to as large a range as necessary. This is for
 * example reflected by util_avg's SCHED_CAPACITY_SCALE.
 * [Overflow issue]
 * The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities
 * with the highest load (=88761), always runnable on a single cfs_rq,
 * and should not overflow as the number already hits PID_MAX_LIMIT.
 * For all other cases (including 32-bit kernels), struct load_weight's
 * weight will overflow first before we do, because:
 *    Max(load_avg) <= Max(load.weight)
 * Then it is the load_weight's responsibility to consider overflow
 * issues.
struct sched_avg {
	u64				last_update_time;
	u64				load_sum;
	u64				runnable_load_sum;
	u32				util_sum;
	u32				period_contrib;
	unsigned long			load_avg;
	unsigned long			runnable_load_avg;
	unsigned long			util_avg;
	struct util_est			util_est;
} ____cacheline_aligned;

struct sched_statistics {
	u64				wait_start;
	u64				wait_max;
	u64				wait_count;
	u64				wait_sum;
	u64				iowait_count;
	u64				iowait_sum;

	u64				sleep_start;
	u64				sleep_max;
	s64				sum_sleep_runtime;

	u64				block_start;
	u64				block_max;
	u64				exec_max;
	u64				slice_max;

	u64				nr_migrations_cold;
	u64				nr_failed_migrations_affine;
	u64				nr_failed_migrations_running;
	u64				nr_failed_migrations_hot;
	u64				nr_forced_migrations;

	u64				nr_wakeups;
	u64				nr_wakeups_sync;
	u64				nr_wakeups_migrate;
	u64				nr_wakeups_local;
	u64				nr_wakeups_remote;
	u64				nr_wakeups_affine;
	u64				nr_wakeups_affine_attempts;
	u64				nr_wakeups_passive;
	u64				nr_wakeups_idle;

struct sched_entity {
	/* For load-balancing: */
	struct load_weight		load;
	unsigned long			runnable_weight;
	struct rb_node			run_node;
	struct list_head		group_node;
	unsigned int			on_rq;

	u64				exec_start;
	u64				sum_exec_runtime;
	u64				vruntime;
	u64				prev_sum_exec_runtime;

	u64				nr_migrations;

	struct sched_statistics		statistics;

	int				depth;
	struct sched_entity		*parent;
	/* rq on which this entity is (to be) queued: */
	struct cfs_rq			*cfs_rq;
	/* rq "owned" by this entity/group: */
	struct cfs_rq			*my_q;

	 * Per entity load average tracking.
	 * Put into separate cache line so it does not
	 * collide with read-mostly values above.
	struct sched_avg		avg;

struct sched_rt_entity {
	struct list_head		run_list;
	unsigned long			timeout;
	unsigned long			watchdog_stamp;
	unsigned int			time_slice;
	unsigned short			on_rq;
	unsigned short			on_list;

	struct sched_rt_entity		*back;
	struct sched_rt_entity		*parent;
	/* rq on which this entity is (to be) queued: */
	struct rt_rq			*rt_rq;
	/* rq "owned" by this entity/group: */
	struct rt_rq			*my_q;
} __randomize_layout;

struct sched_dl_entity {
	struct rb_node			rb_node;

	 * Original scheduling parameters. Copied here from sched_attr
	 * during sched_setattr(), they will remain the same until
	 * the next sched_setattr().
	u64				dl_runtime;	/* Maximum runtime for each instance	*/
	u64				dl_deadline;	/* Relative deadline of each instance	*/
	u64				dl_period;	/* Separation of two instances (period) */
	u64				dl_bw;		/* dl_runtime / dl_period		*/
	u64				dl_density;	/* dl_runtime / dl_deadline		*/

	 * Actual scheduling parameters. Initialized with the values above,
	 * they are continously updated during task execution. Note that
	 * the remaining runtime could be < 0 in case we are in overrun.
	s64				runtime;	/* Remaining runtime for this instance	*/
	u64				deadline;	/* Absolute deadline for this instance	*/
	unsigned int			flags;		/* Specifying the scheduler behaviour	*/

	 * Some bool flags:
	 * @dl_throttled tells if we exhausted the runtime. If so, the
	 * task has to wait for a replenishment to be performed at the
	 * next firing of dl_timer.
	 * @dl_boosted tells if we are boosted due to DI. If so we are
	 * outside bandwidth enforcement mechanism (but only until we
	 * exit the critical section);
	 * @dl_yielded tells if task gave up the CPU before consuming
	 * all its available runtime during the last job.
	 * @dl_non_contending tells if the task is inactive while still
	 * contributing to the active utilization. In other words, it
	 * indicates if the inactive timer has been armed and its handler
	 * has not been executed yet. This flag is useful to avoid race
	 * conditions between the inactive timer handler and the wakeup
	 * code.
	 * @dl_overrun tells if the task asked to be informed about runtime
	 * overruns.
	unsigned int			dl_throttled      : 1;
	unsigned int			dl_boosted        : 1;
	unsigned int			dl_yielded        : 1;
	unsigned int			dl_non_contending : 1;
	unsigned int			dl_overrun	  : 1;

	 * Bandwidth enforcement timer. Each -deadline task has its
	 * own bandwidth to be enforced, thus we need one timer per task.
	struct hrtimer			dl_timer;

	 * Inactive timer, responsible for decreasing the active utilization
	 * at the "0-lag time". When a -deadline task blocks, it contributes
	 * to GRUB's active utilization until the "0-lag time", hence a
	 * timer is needed to decrease the active utilization at the correct
	 * time.
	struct hrtimer inactive_timer;

union rcu_special {
	struct {
		u8			blocked;
		u8			need_qs;
	} b; /* Bits. */
	u16 s; /* Set of bits. */

enum perf_event_task_context {
	perf_invalid_context = -1,
	perf_hw_context = 0,

struct wake_q_node {
	struct wake_q_node *next;

struct task_struct {
	 * For reasons of header soup (see current_thread_info()), this
	 * must be the first element of task_struct.
	struct thread_info		thread_info;
	/* -1 unrunnable, 0 runnable, >0 stopped: */
	volatile long			state;

	 * This begins the randomizable portion of task_struct. Only
	 * scheduling-critical items should be added above here.

	void				*stack;
	atomic_t			usage;
	/* Per task flags (PF_*), defined further below: */
	unsigned int			flags;
	unsigned int			ptrace;

	struct llist_node		wake_entry;
	int				on_cpu;
	/* Current CPU: */
	unsigned int			cpu;
	unsigned int			wakee_flips;
	unsigned long			wakee_flip_decay_ts;
	struct task_struct		*last_wakee;

	 * recent_used_cpu is initially set as the last CPU used by a task
	 * that wakes affine another task. Waker/wakee relationships can
	 * push tasks around a CPU where each wakeup moves to the next one.
	 * Tracking a recently used CPU allows a quick search for a recently
	 * used CPU that may be idle.
	int				recent_used_cpu;
	int				wake_cpu;
	int				on_rq;

	int				prio;
	int				static_prio;
	int				normal_prio;
	unsigned int			rt_priority;

	const struct sched_class	*sched_class;
	struct sched_entity		se;
	struct sched_rt_entity		rt;
	struct task_group		*sched_task_group;
	struct sched_dl_entity		dl;

	/* List of struct preempt_notifier: */
	struct hlist_head		preempt_notifiers;

	unsigned int			btrace_seq;

	unsigned int			policy;
	int				nr_cpus_allowed;
	cpumask_t			cpus_allowed;

	int				rcu_read_lock_nesting;
	union rcu_special		rcu_read_unlock_special;
	struct list_head		rcu_node_entry;
	struct rcu_node			*rcu_blocked_node;
#endif /* #ifdef CONFIG_PREEMPT_RCU */

	unsigned long			rcu_tasks_nvcsw;
	u8				rcu_tasks_holdout;
	u8				rcu_tasks_idx;
	int				rcu_tasks_idle_cpu;
	struct list_head		rcu_tasks_holdout_list;
#endif /* #ifdef CONFIG_TASKS_RCU */

	struct sched_info		sched_info;

	struct list_head		tasks;
	struct plist_node		pushable_tasks;
	struct rb_node			pushable_dl_tasks;

	struct mm_struct		*mm;
	struct mm_struct		*active_mm;

	/* Per-thread vma caching: */
	struct vmacache			vmacache;

	struct task_rss_stat		rss_stat;
	int				exit_state;
	int				exit_code;
	int				exit_signal;
	/* The signal sent when the parent dies: */
	int				pdeath_signal;
	/* JOBCTL_*, siglock protected: */
	unsigned long			jobctl;

	/* Used for emulating ABI behavior of previous Linux versions: */
	unsigned int			personality;

	/* Scheduler bits, serialized by scheduler locks: */
	unsigned			sched_reset_on_fork:1;
	unsigned			sched_contributes_to_load:1;
	unsigned			sched_migrated:1;
	unsigned			sched_remote_wakeup:1;
	unsigned			sched_psi_wake_requeue:1;

	/* Force alignment to the next boundary: */
	unsigned			:0;

	/* Unserialized, strictly 'current' */

	/* Bit to tell LSMs we're in execve(): */
	unsigned			in_execve:1;
	unsigned			in_iowait:1;
	unsigned			restore_sigmask:1;
	unsigned			in_user_fault:1;
	unsigned			brk_randomized:1;
	/* disallow userland-initiated cgroup migration */
	unsigned			no_cgroup_migration:1;
	/* to be used once the psi infrastructure lands upstream. */
	unsigned			use_memdelay:1;

	 * May usercopy functions fault on kernel addresses?
	 * This is not just a single bit because this can potentially nest.
	unsigned int			kernel_uaccess_faults_ok;

	unsigned long			atomic_flags; /* Flags requiring atomic access. */

	struct restart_block		restart_block;

	pid_t				pid;
	pid_t				tgid;

	/* Canary value for the -fstack-protector GCC feature: */
	unsigned long			stack_canary;
	 * Pointers to the (original) parent process, youngest child, younger sibling,
	 * older sibling, respectively.  (p->father can be replaced with
	 * p->real_parent->pid)

	/* Real parent process: */
	struct task_struct __rcu	*real_parent;

	/* Recipient of SIGCHLD, wait4() reports: */
	struct task_struct __rcu	*parent;

	 * Children/sibling form the list of natural children:
	struct list_head		children;
	struct list_head		sibling;
	struct task_struct		*group_leader;

	 * 'ptraced' is the list of tasks this task is using ptrace() on.
	 * This includes both natural children and PTRACE_ATTACH targets.
	 * 'ptrace_entry' is this task's link on the p->parent->ptraced list.
	struct list_head		ptraced;
	struct list_head		ptrace_entry;

	/* PID/PID hash table linkage. */
	struct pid			*thread_pid;
	struct hlist_node		pid_links[PIDTYPE_MAX];
	struct list_head		thread_group;
	struct list_head		thread_node;

	struct completion		*vfork_done;

	int __user			*set_child_tid;

	int __user			*clear_child_tid;

	u64				utime;
	u64				stime;
	u64				utimescaled;
	u64				stimescaled;
	u64				gtime;
	struct prev_cputime		prev_cputime;
	struct vtime			vtime;

	atomic_t			tick_dep_mask;
	/* Context switch counts: */
	unsigned long			nvcsw;
	unsigned long			nivcsw;

	/* Monotonic time in nsecs: */
	u64				start_time;

	/* Boot based time in nsecs: */
	u64				real_start_time;

	/* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */
	unsigned long			min_flt;
	unsigned long			maj_flt;

	struct task_cputime		cputime_expires;
	struct list_head		cpu_timers[3];

	/* Process credentials: */

	/* Tracer's credentials at attach: */
	const struct cred __rcu		*ptracer_cred;

	/* Objective and real subjective task credentials (COW): */
	const struct cred __rcu		*real_cred;

	/* Effective (overridable) subjective task credentials (COW): */
	const struct cred __rcu		*cred;

	 * executable name, excluding path.
	 * - normally initialized setup_new_exec()
	 * - access it with [gs]et_task_comm()
	 * - lock it with task_lock()
	char				comm[TASK_COMM_LEN];

	struct nameidata		*nameidata;

	struct sysv_sem			sysvsem;
	struct sysv_shm			sysvshm;
	unsigned long			last_switch_count;
	unsigned long			last_switch_time;
	/* Filesystem information: */
	struct fs_struct		*fs;

	/* Open file information: */
	struct files_struct		*files;

	/* Namespaces: */
	struct nsproxy			*nsproxy;

	/* Signal handlers: */
	struct signal_struct		*signal;
	struct sighand_struct		*sighand;
	sigset_t			blocked;
	sigset_t			real_blocked;
	/* Restored if set_restore_sigmask() was used: */
	sigset_t			saved_sigmask;
	struct sigpending		pending;
	unsigned long			sas_ss_sp;
	size_t				sas_ss_size;
	unsigned int			sas_ss_flags;

	struct callback_head		*task_works;

	struct audit_context		*audit_context;
	kuid_t				loginuid;
	unsigned int			sessionid;
	struct seccomp			seccomp;

	/* Thread group tracking: */
	u32				parent_exec_id;
	u32				self_exec_id;

	/* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */
	spinlock_t			alloc_lock;

	/* Protection of the PI data structures: */
	raw_spinlock_t			pi_lock;

	struct wake_q_node		wake_q;

	/* PI waiters blocked on a rt_mutex held by this task: */
	struct rb_root_cached		pi_waiters;
	/* Updated under owner's pi_lock and rq lock */
	struct task_struct		*pi_top_task;
	/* Deadlock detection and priority inheritance handling: */
	struct rt_mutex_waiter		*pi_blocked_on;

	/* Mutex deadlock detection: */
	struct mutex_waiter		*blocked_on;

	unsigned int			irq_events;
	unsigned long			hardirq_enable_ip;
	unsigned long			hardirq_disable_ip;
	unsigned int			hardirq_enable_event;
	unsigned int			hardirq_disable_event;
	int				hardirqs_enabled;
	int				hardirq_context;
	unsigned long			softirq_disable_ip;
	unsigned long			softirq_enable_ip;
	unsigned int			softirq_disable_event;
	unsigned int			softirq_enable_event;
	int				softirqs_enabled;
	int				softirq_context;

# define MAX_LOCK_DEPTH			48UL
	u64				curr_chain_key;
	int				lockdep_depth;
	unsigned int			lockdep_recursion;
	struct held_lock		held_locks[MAX_LOCK_DEPTH];

	unsigned int			in_ubsan;

	/* Journalling filesystem info: */
	void				*journal_info;

	/* Stacked block device info: */
	struct bio_list			*bio_list;

	/* Stack plugging: */
	struct blk_plug			*plug;

	/* VM state: */
	struct reclaim_state		*reclaim_state;

	struct backing_dev_info		*backing_dev_info;

	struct io_context		*io_context;

	/* Ptrace state: */
	unsigned long			ptrace_message;
	kernel_siginfo_t		*last_siginfo;

	struct task_io_accounting	ioac;
	/* Pressure stall state */
	unsigned int			psi_flags;
	/* Accumulated RSS usage: */
	u64				acct_rss_mem1;
	/* Accumulated virtual memory usage: */
	u64				acct_vm_mem1;
	/* stime + utime since last update: */
	u64				acct_timexpd;
	/* Protected by ->alloc_lock: */
	nodemask_t			mems_allowed;
	/* Seqence number to catch updates: */
	seqcount_t			mems_allowed_seq;
	int				cpuset_mem_spread_rotor;
	int				cpuset_slab_spread_rotor;
	/* Control Group info protected by css_set_lock: */
	struct css_set __rcu		*cgroups;
	/* cg_list protected by css_set_lock and tsk->alloc_lock: */
	struct list_head		cg_list;
	u32				closid;
	u32				rmid;
	struct robust_list_head __user	*robust_list;
	struct compat_robust_list_head __user *compat_robust_list;
	struct list_head		pi_state_list;
	struct futex_pi_state		*pi_state_cache;
	struct perf_event_context	*perf_event_ctxp[perf_nr_task_contexts];
	struct mutex			perf_event_mutex;
	struct list_head		perf_event_list;
	unsigned long			preempt_disable_ip;
	/* Protected by alloc_lock: */
	struct mempolicy		*mempolicy;
	short				il_prev;
	short				pref_node_fork;
	int				numa_scan_seq;
	unsigned int			numa_scan_period;
	unsigned int			numa_scan_period_max;
	int				numa_preferred_nid;
	unsigned long			numa_migrate_retry;
	/* Migration stamp: */
	u64				node_stamp;
	u64				last_task_numa_placement;
	u64				last_sum_exec_runtime;
	struct callback_head		numa_work;

	struct numa_group		*numa_group;

	 * numa_faults is an array split into four regions:
	 * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer
	 * in this precise order.
	 * faults_memory: Exponential decaying average of faults on a per-node
	 * basis. Scheduling placement decisions are made based on these
	 * counts. The values remain static for the duration of a PTE scan.
	 * faults_cpu: Track the nodes the process was running on when a NUMA
	 * hinting fault was incurred.
	 * faults_memory_buffer and faults_cpu_buffer: Record faults per node
	 * during the current scan window. When the scan completes, the counts
	 * in faults_memory and faults_cpu decay and these values are copied.
	unsigned long			*numa_faults;
	unsigned long			total_numa_faults;

	 * numa_faults_locality tracks if faults recorded during the last
	 * scan window were remote/local or failed to migrate. The task scan
	 * period is adapted based on the locality of the faults with different
	 * weights depending on whether they were shared or private faults
	unsigned long			numa_faults_locality[3];

	unsigned long			numa_pages_migrated;

	struct rseq __user *rseq;
	u32 rseq_len;
	u32 rseq_sig;
	 * RmW on rseq_event_mask must be performed atomically
	 * with respect to preemption.
	unsigned long rseq_event_mask;

	struct tlbflush_unmap_batch	tlb_ubc;

	struct rcu_head			rcu;

	/* Cache last used pipe for splice(): */
	struct pipe_inode_info		*splice_pipe;

	struct page_frag		task_frag;

	struct task_delay_info		*delays;

	int				make_it_fail;
	unsigned int			fail_nth;
	 * When (nr_dirtied >= nr_dirtied_pause), it's time to call
	 * balance_dirty_pages() for a dirty throttling pause:
	int				nr_dirtied;
	int				nr_dirtied_pause;
	/* Start of a write-and-pause period: */
	unsigned long			dirty_paused_when;

	int				latency_record_count;
	struct latency_record		latency_record[LT_SAVECOUNT];
	 * Time slack values; these are used to round up poll() and
	 * select() etc timeout values. These are in nanoseconds.
	u64				timer_slack_ns;
	u64				default_timer_slack_ns;

	unsigned int			kasan_depth;

	/* Index of current stored address in ret_stack: */
	int				curr_ret_stack;

	/* Stack of return addresses for return function tracing: */
	struct ftrace_ret_stack		*ret_stack;

	/* Timestamp for last schedule: */
	unsigned long long		ftrace_timestamp;

	 * Number of functions that haven't been traced
	 * because of depth overrun:
	atomic_t			trace_overrun;

	/* Pause tracing: */
	atomic_t			tracing_graph_pause;

	/* State flags for use by tracers: */
	unsigned long			trace;

	/* Bitmask and counter of trace recursion: */
	unsigned long			trace_recursion;
#endif /* CONFIG_TRACING */

	/* Coverage collection mode enabled for this task (0 if disabled): */
	unsigned int			kcov_mode;

	/* Size of the kcov_area: */
	unsigned int			kcov_size;

	/* Buffer for coverage collection: */
	void				*kcov_area;

	/* KCOV descriptor wired with this task or NULL: */
	struct kcov			*kcov;

	struct mem_cgroup		*memcg_in_oom;
	gfp_t				memcg_oom_gfp_mask;
	int				memcg_oom_order;

	/* Number of pages to reclaim on returning to userland: */
	unsigned int			memcg_nr_pages_over_high;

	/* Used by memcontrol for targeted memcg charge: */
	struct mem_cgroup		*active_memcg;

	struct request_queue		*throttle_queue;

	struct uprobe_task		*utask;
	unsigned int			sequential_io;
	unsigned int			sequential_io_avg;
	unsigned long			task_state_change;
	int				pagefault_disabled;
	struct task_struct		*oom_reaper_list;
	struct vm_struct		*stack_vm_area;
	/* A live task holds one reference: */
	atomic_t			stack_refcount;
	int patch_state;
	/* Used by LSM modules for access restriction: */
	void				*security;

	unsigned long			lowest_stack;
	unsigned long			prev_lowest_stack;

	 * New fields for task_struct should be added above here, so that
	 * they are included in the randomized portion of task_struct.

	/* CPU-specific state of this task: */
	struct thread_struct		thread;

	 * WARNING: on x86, 'thread_struct' contains a variable-sized
	 * structure.  It *MUST* be at the end of 'task_struct'.
	 * Do not put anything below here!

static inline struct pid *task_pid(struct task_struct *task)
	return task->thread_pid;

 * the helpers to get the task's different pids as they are seen
 * from various namespaces
 * task_xid_nr()     : global id, i.e. the id seen from the init namespace;
 * task_xid_vnr()    : virtual id, i.e. the id seen from the pid namespace of
 *                     current.
 * task_xid_nr_ns()  : id seen from the ns specified;
 * see also pid_nr() etc in include/linux/pid.h
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns);

static inline pid_t task_pid_nr(struct task_struct *tsk)
	return tsk->pid;

static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
	return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns);

static inline pid_t task_pid_vnr(struct task_struct *tsk)
	return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);

static inline pid_t task_tgid_nr(struct task_struct *tsk)
	return tsk->tgid;

 * pid_alive - check that a task structure is not stale
 * @p: Task structure to be checked.
 * Test if a process is not yet dead (at most zombie state)
 * If pid_alive fails, then pointers within the task structure
 * can be stale and must not be dereferenced.
 * Return: 1 if the process is alive. 0 otherwise.
static inline int pid_alive(const struct task_struct *p)
	return p->thread_pid != NULL;

static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);

static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);

static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
	return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);

static inline pid_t task_session_vnr(struct task_struct *tsk)
	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);

static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
	return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns);

static inline pid_t task_tgid_vnr(struct task_struct *tsk)
	return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL);

static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
	pid_t pid = 0;

	if (pid_alive(tsk))
		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);

	return pid;

static inline pid_t task_ppid_nr(const struct task_struct *tsk)
	return task_ppid_nr_ns(tsk, &init_pid_ns);

/* Obsolete, do not use: */
static inline pid_t task_pgrp_nr(struct task_struct *tsk)
	return task_pgrp_nr_ns(tsk, &init_pid_ns);


static inline unsigned int task_state_index(struct task_struct *tsk)
	unsigned int tsk_state = READ_ONCE(tsk->state);
	unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT;


	if (tsk_state == TASK_IDLE)

	return fls(state);

static inline char task_index_to_char(unsigned int state)
	static const char state_char[] = "RSDTtXZPI";

	BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1);

	return state_char[state];

static inline char task_state_to_char(struct task_struct *tsk)
	return task_index_to_char(task_state_index(tsk));

 * is_global_init - check if a task structure is init. Since init
 * is free to have sub-threads we need to check tgid.
 * @tsk: Task structure to be checked.
 * Check if a task structure is the first user space task the kernel created.
 * Return: 1 if the task structure is init. 0 otherwise.
static inline int is_global_init(struct task_struct *tsk)
	return task_tgid_nr(tsk) == 1;

extern struct pid *cad_pid;

 * Per process flags
#define PF_IDLE			0x00000002	/* I am an IDLE thread */
#define PF_EXITING		0x00000004	/* Getting shut down */
#define PF_EXITPIDONE		0x00000008	/* PI exit done on shut down */
#define PF_VCPU			0x00000010	/* I'm a virtual CPU */
#define PF_WQ_WORKER		0x00000020	/* I'm a workqueue worker */
#define PF_FORKNOEXEC		0x00000040	/* Forked but didn't exec */
#define PF_MCE_PROCESS		0x00000080      /* Process policy on mce errors */
#define PF_SUPERPRIV		0x00000100	/* Used super-user privileges */
#define PF_DUMPCORE		0x00000200	/* Dumped core */
#define PF_SIGNALED		0x00000400	/* Killed by a signal */
#define PF_MEMALLOC		0x00000800	/* Allocating memory */
#define PF_NPROC_EXCEEDED	0x00001000	/* set_user() noticed that RLIMIT_NPROC was exceeded */
#define PF_USED_MATH		0x00002000	/* If unset the fpu must be initialized before use */
#define PF_USED_ASYNC		0x00004000	/* Used async_schedule*(), used by module init */
#define PF_NOFREEZE		0x00008000	/* This thread should not be frozen */
#define PF_FROZEN		0x00010000	/* Frozen for system suspend */
#define PF_KSWAPD		0x00020000	/* I am kswapd */
#define PF_MEMALLOC_NOFS	0x00040000	/* All allocation requests will inherit GFP_NOFS */
#define PF_MEMALLOC_NOIO	0x00080000	/* All allocation requests will inherit GFP_NOIO */
#define PF_LESS_THROTTLE	0x00100000	/* Throttle me less: I clean memory */
#define PF_KTHREAD		0x00200000	/* I am a kernel thread */
#define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
#define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
#define PF_MEMSTALL		0x01000000	/* Stalled due to lack of memory */
#define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_allowed */
#define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
#define PF_MUTEX_TESTER		0x20000000	/* Thread belongs to the rt mutex tester */
#define PF_FREEZER_SKIP		0x40000000	/* Freezer should not count it as freezable */
#define PF_SUSPEND_TASK		0x80000000      /* This thread called freeze_processes() and should not be frozen */

 * Only the _current_ task can read/write to tsk->flags, but other
 * tasks can access tsk->flags in readonly mode for example
 * with tsk_used_math (like during threaded core dumping).
 * There is however an exception to this rule during ptrace
 * or during fork: the ptracer task is allowed to write to the
 * child->flags of its traced child (same goes for fork, the parent
 * can write to the child->flags), because we're guaranteed the
 * child is not running and in turn not changing child->flags
 * at the same time the parent does it.
#define clear_stopped_child_used_math(child)	do { (child)->flags &= ~PF_USED_MATH; } while (0)
#define set_stopped_child_used_math(child)	do { (child)->flags |= PF_USED_MATH; } while (0)
#define clear_used_math()			clear_stopped_child_used_math(current)
#define set_used_math()				set_stopped_child_used_math(current)

#define conditional_stopped_child_used_math(condition, child) \
	do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0)

#define conditional_used_math(condition)	conditional_stopped_child_used_math(condition, current)

#define copy_to_stopped_child_used_math(child) \
	do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0)

/* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */
#define tsk_used_math(p)			((p)->flags & PF_USED_MATH)
#define used_math()				tsk_used_math(current)

static inline bool is_percpu_thread(void)
	return (current->flags & PF_NO_SETAFFINITY) &&
		(current->nr_cpus_allowed  == 1);
	return true;

/* Per-process atomic flags. */
#define PFA_NO_NEW_PRIVS		0	/* May not gain new privileges. */
#define PFA_SPREAD_PAGE			1	/* Spread page cache over cpuset */
#define PFA_SPREAD_SLAB			2	/* Spread some slab caches over cpuset */
#define PFA_SPEC_SSB_DISABLE		3	/* Speculative Store Bypass disabled */
#define PFA_SPEC_SSB_FORCE_DISABLE	4	/* Speculative Store Bypass force disabled*/

#define TASK_PFA_TEST(name, func)					\
	static inline bool task_##func(struct task_struct *p)		\
	{ return test_bit(PFA_##name, &p->atomic_flags); }

#define TASK_PFA_SET(name, func)					\
	static inline void task_set_##func(struct task_struct *p)	\
	{ set_bit(PFA_##name, &p->atomic_flags); }

#define TASK_PFA_CLEAR(name, func)					\
	static inline void task_clear_##func(struct task_struct *p)	\
	{ clear_bit(PFA_##name, &p->atomic_flags); }

TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs)



TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable)

TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)

static inline void
current_restore_flags(unsigned long orig_flags, unsigned long flags)
	current->flags &= ~flags;
	current->flags |= orig_flags & flags;

extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed);
extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);
static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
	if (!cpumask_test_cpu(0, new_mask))
		return -EINVAL;
	return 0;

#ifndef cpu_relax_yield
#define cpu_relax_yield() cpu_relax()

extern int yield_to(struct task_struct *p, bool preempt);
extern void set_user_nice(struct task_struct *p, long nice);
extern int task_prio(const struct task_struct *p);

 * task_nice - return the nice value of a given task.
 * @p: the task in question.
 * Return: The nice value [ -20 ... 0 ... 19 ].
static inline int task_nice(const struct task_struct *p)
	return PRIO_TO_NICE((p)->static_prio);

extern int can_nice(const struct task_struct *p, const int nice);
extern int task_curr(const struct task_struct *p);
extern int idle_cpu(int cpu);
extern int available_idle_cpu(int cpu);
extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *);
extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *);
extern int sched_setattr(struct task_struct *, const struct sched_attr *);
extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *);
extern struct task_struct *idle_task(int cpu);

 * is_idle_task - is the specified task an idle task?
 * @p: the task in question.
 * Return: 1 if @p is an idle task. 0 otherwise.
static inline bool is_idle_task(const struct task_struct *p)
	return !!(p->flags & PF_IDLE);

extern struct task_struct *curr_task(int cpu);
extern void ia64_set_curr_task(int cpu, struct task_struct *p);

void yield(void);

union thread_union {
	struct task_struct task;
	struct thread_info thread_info;
	unsigned long stack[THREAD_SIZE/sizeof(long)];

extern struct thread_info init_thread_info;

extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)];

static inline struct thread_info *task_thread_info(struct task_struct *task)
	return &task->thread_info;
#elif !defined(__HAVE_THREAD_FUNCTIONS)
# define task_thread_info(task)	((struct thread_info *)(task)->stack)

 * find a task by one of its numerical ids
 * find_task_by_pid_ns():
 *      finds a task by its pid in the specified namespace
 * find_task_by_vpid():
 *      finds a task by its virtual pid
 * see also find_vpid() etc in include/linux/pid.h

extern struct task_struct *find_task_by_vpid(pid_t nr);
extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns);

 * find a task by its virtual pid and get the task struct
extern struct task_struct *find_get_task_by_vpid(pid_t nr);

extern int wake_up_state(struct task_struct *tsk, unsigned int state);
extern int wake_up_process(struct task_struct *tsk);
extern void wake_up_new_task(struct task_struct *tsk);

extern void kick_process(struct task_struct *tsk);
static inline void kick_process(struct task_struct *tsk) { }

extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec);

static inline void set_task_comm(struct task_struct *tsk, const char *from)
	__set_task_comm(tsk, from, false);

extern char *__get_task_comm(char *to, size_t len, struct task_struct *tsk);
#define get_task_comm(buf, tsk) ({			\
	BUILD_BUG_ON(sizeof(buf) != TASK_COMM_LEN);	\
	__get_task_comm(buf, sizeof(buf), tsk);		\

void scheduler_ipi(void);
extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
static inline void scheduler_ipi(void) { }
static inline unsigned long wait_task_inactive(struct task_struct *p, long match_state)
	return 1;

 * Set thread flags in other task's structures.
 * See asm/thread_info.h for TIF_xxxx flags available:
static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag)
	set_ti_thread_flag(task_thread_info(tsk), flag);

static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
	clear_ti_thread_flag(task_thread_info(tsk), flag);

static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag,
					  bool value)
	update_ti_thread_flag(task_thread_info(tsk), flag, value);

static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
	return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);

static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
	return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);

static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
	return test_ti_thread_flag(task_thread_info(tsk), flag);

static inline void set_tsk_need_resched(struct task_struct *tsk)

static inline void clear_tsk_need_resched(struct task_struct *tsk)

static inline int test_tsk_need_resched(struct task_struct *tsk)
	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));

 * cond_resched() and cond_resched_lock(): latency reduction via
 * explicit rescheduling in places that are safe. The return
 * value indicates whether a reschedule was done in fact.
 * cond_resched_lock() will drop the spinlock before scheduling,
extern int _cond_resched(void);
static inline int _cond_resched(void) { return 0; }

#define cond_resched() ({			\
	___might_sleep(__FILE__, __LINE__, 0);	\
	_cond_resched();			\

extern int __cond_resched_lock(spinlock_t *lock);

#define cond_resched_lock(lock) ({				\
	___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\
	__cond_resched_lock(lock);				\

static inline void cond_resched_rcu(void)

 * Does a critical section need to be broken due to another
 * task waiting?: (technically does not depend on CONFIG_PREEMPT,
 * but a general need for low latency)
static inline int spin_needbreak(spinlock_t *lock)
	return spin_is_contended(lock);
	return 0;

static __always_inline bool need_resched(void)
	return unlikely(tif_need_resched());

 * Wrappers for p->thread_info->cpu access. No-op on UP.

static inline unsigned int task_cpu(const struct task_struct *p)
	return p->cpu;
	return task_thread_info(p)->cpu;

extern void set_task_cpu(struct task_struct *p, unsigned int cpu);


static inline unsigned int task_cpu(const struct task_struct *p)
	return 0;

static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)

#endif /* CONFIG_SMP */

 * In order to reduce various lock holder preemption latencies provide an
 * interface to see if a vCPU is currently running or not.
 * This allows us to terminate optimistic spin loops and block, analogous to
 * the native optimistic spin heuristic of testing if the lock owner task is
 * running or not.
#ifndef vcpu_is_preempted
# define vcpu_is_preempted(cpu)	false

extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
extern long sched_getaffinity(pid_t pid, struct cpumask *mask);

#ifndef TASK_SIZE_OF


 * Map the event mask on the user-space ABI enum rseq_cs_flags
 * for direct mask checks.
enum rseq_event_mask_bits {

enum rseq_event_mask {

static inline void rseq_set_notify_resume(struct task_struct *t)
	if (t->rseq)
		set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);

void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs);

static inline void rseq_handle_notify_resume(struct ksignal *ksig,
					     struct pt_regs *regs)
	if (current->rseq)
		__rseq_handle_notify_resume(ksig, regs);

static inline void rseq_signal_deliver(struct ksignal *ksig,
				       struct pt_regs *regs)
	__set_bit(RSEQ_EVENT_SIGNAL_BIT, &current->rseq_event_mask);
	rseq_handle_notify_resume(ksig, regs);

/* rseq_preempt() requires preemption to be disabled. */
static inline void rseq_preempt(struct task_struct *t)
	__set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask);

/* rseq_migrate() requires preemption to be disabled. */
static inline void rseq_migrate(struct task_struct *t)
	__set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask);

 * If parent process has a registered restartable sequences area, the
 * child inherits. Only applies when forking a process, not a thread.
static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
	if (clone_flags & CLONE_THREAD) {
		t->rseq = NULL;
		t->rseq_len = 0;
		t->rseq_sig = 0;
		t->rseq_event_mask = 0;
	} else {
		t->rseq = current->rseq;
		t->rseq_len = current->rseq_len;
		t->rseq_sig = current->rseq_sig;
		t->rseq_event_mask = current->rseq_event_mask;

static inline void rseq_execve(struct task_struct *t)
	t->rseq = NULL;
	t->rseq_len = 0;
	t->rseq_sig = 0;
	t->rseq_event_mask = 0;


static inline void rseq_set_notify_resume(struct task_struct *t)
static inline void rseq_handle_notify_resume(struct ksignal *ksig,
					     struct pt_regs *regs)
static inline void rseq_signal_deliver(struct ksignal *ksig,
				       struct pt_regs *regs)
static inline void rseq_preempt(struct task_struct *t)
static inline void rseq_migrate(struct task_struct *t)
static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
static inline void rseq_execve(struct task_struct *t)



void rseq_syscall(struct pt_regs *regs);


static inline void rseq_syscall(struct pt_regs *regs)