sched.h

#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H

#include <uapi/linux/sched.h>

#include <linux/sched/prio.h>


struct sched_param {
	int sched_priority;
};

#include <asm/param.h>	/* for HZ */

#include <linux/capability.h>
#include <linux/threads.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
#include <linux/plist.h>
#include <linux/rbtree.h>
#include <linux/thread_info.h>
#include <linux/cpumask.h>
#include <linux/errno.h>
#include <linux/nodemask.h>
#include <linux/mm_types.h>
#include <linux/preempt.h>

#include <asm/page.h>
#include <asm/ptrace.h>
#include <linux/cputime.h>

#include <linux/smp.h>
#include <linux/sem.h>
#include <linux/shm.h>
#include <linux/signal.h>
#include <linux/compiler.h>
#include <linux/completion.h>
#include <linux/pid.h>
#include <linux/percpu.h>
#include <linux/topology.h>
#include <linux/seccomp.h>
#include <linux/rcupdate.h>
#include <linux/rculist.h>
#include <linux/rtmutex.h>

#include <linux/time.h>
#include <linux/param.h>
#include <linux/resource.h>
#include <linux/timer.h>
#include <linux/hrtimer.h>
#include <linux/kcov.h>
#include <linux/task_io_accounting.h>
#include <linux/latencytop.h>
#include <linux/cred.h>
#include <linux/llist.h>
#include <linux/uidgid.h>
#include <linux/gfp.h>
#include <linux/magic.h>
#include <linux/cgroup-defs.h>

#include <asm/processor.h>

#define SCHED_ATTR_SIZE_VER0	48	/* sizeof first published struct */

/*
 * Extended scheduling parameters data structure.
 *
 * This is needed because the original struct sched_param can not be
 * altered without introducing ABI issues with legacy applications
 * (e.g., in sched_getparam()).
 *
 * However, the possibility of specifying more than just a priority for
 * the tasks may be useful for a wide variety of application fields, e.g.,
 * multimedia, streaming, automation and control, and many others.
 *
 * This variant (sched_attr) is meant at describing a so-called
 * sporadic time-constrained task. In such model a task is specified by:
 *  - the activation period or minimum instance inter-arrival time;
 *  - the maximum (or average, depending on the actual scheduling
 *    discipline) computation time of all instances, a.k.a. runtime;
 *  - the deadline (relative to the actual activation time) of each
 *    instance.
 * Very briefly, a periodic (sporadic) task asks for the execution of
 * some specific computation --which is typically called an instance--
 * (at most) every period. Moreover, each instance typically lasts no more
 * than the runtime and must be completed by time instant t equal to
 * the instance activation time + the deadline.
 *
 * This is reflected by the actual fields of the sched_attr structure:
 *
 *  @size		size of the structure, for fwd/bwd compat.
 *
 *  @sched_policy	task's scheduling policy
 *  @sched_flags	for customizing the scheduler behaviour
 *  @sched_nice		task's nice value      (SCHED_NORMAL/BATCH)
 *  @sched_priority	task's static priority (SCHED_FIFO/RR)
 *  @sched_deadline	representative of the task's deadline
 *  @sched_runtime	representative of the task's runtime
 *  @sched_period	representative of the task's period
 *
 * Given this task model, there are a multiplicity of scheduling algorithms
 * and policies, that can be used to ensure all the tasks will make their
 * timing constraints.
 *
 * As of now, the SCHED_DEADLINE policy (sched_dl scheduling class) is the
 * only user of this new interface. More information about the algorithm
 * available in the scheduling class file or in Documentation/.
 */
struct sched_attr {
	u32 size;

	u32 sched_policy;
	u64 sched_flags;

	/* SCHED_NORMAL, SCHED_BATCH */
	s32 sched_nice;

	/* SCHED_FIFO, SCHED_RR */
	u32 sched_priority;

	/* SCHED_DEADLINE */
	u64 sched_runtime;
	u64 sched_deadline;
	u64 sched_period;
};

struct futex_pi_state;
struct robust_list_head;
struct bio_list;
struct fs_struct;
struct perf_event_context;
struct blk_plug;
struct filename;
struct nameidata;

#define VMACACHE_BITS 2
#define VMACACHE_SIZE (1U << VMACACHE_BITS)
#define VMACACHE_MASK (VMACACHE_SIZE - 1)

/*
 * These are the constant used to fake the fixed-point load-average
 * counting. Some notes:
 *  - 11 bit fractions expand to 22 bits by the multiplies: this gives
 *    a load-average precision of 10 bits integer + 11 bits fractional
 *  - if you want to count load-averages more often, you need more
 *    precision, or rounding will get you. With 2-second counting freq,
 *    the EXP_n values would be 1981, 2034 and 2043 if still using only
 *    11 bit fractions.
 */
extern unsigned long avenrun[];		/* Load averages */
extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);

#define FSHIFT		11		/* nr of bits of precision */
#define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
#define LOAD_FREQ	(5*HZ+1)	/* 5 sec intervals */
#define EXP_1		1884		/* 1/exp(5sec/1min) as fixed-point */
#define EXP_5		2014		/* 1/exp(5sec/5min) */
#define EXP_15		2037		/* 1/exp(5sec/15min) */

#define CALC_LOAD(load,exp,n) \
	load *= exp; \
	load += n*(FIXED_1-exp); \
	load >>= FSHIFT;

extern unsigned long total_forks;
extern int nr_threads;
DECLARE_PER_CPU(unsigned long, process_counts);
extern int nr_processes(void);
extern unsigned long nr_running(void);
extern bool single_task_running(void);
extern unsigned long nr_iowait(void);
extern unsigned long nr_iowait_cpu(int cpu);
extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);

extern void calc_global_load(unsigned long ticks);

#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
extern void cpu_load_update_nohz_start(void);
extern void cpu_load_update_nohz_stop(void);
#else
static inline void cpu_load_update_nohz_start(void) { }
static inline void cpu_load_update_nohz_stop(void) { }
#endif

extern void dump_cpu_task(int cpu);

struct seq_file;
struct cfs_rq;
struct task_group;
#ifdef CONFIG_SCHED_DEBUG
extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
extern void proc_sched_set_task(struct task_struct *p);
#endif

/*
 * 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.
 */
#define TASK_RUNNING		0
#define TASK_INTERRUPTIBLE	1
#define TASK_UNINTERRUPTIBLE	2
#define __TASK_STOPPED		4
#define __TASK_TRACED		8
/* in tsk->exit_state */
#define EXIT_DEAD		16
#define EXIT_ZOMBIE		32
#define EXIT_TRACE		(EXIT_ZOMBIE | EXIT_DEAD)
/* in tsk->state again */
#define TASK_DEAD		64
#define TASK_WAKEKILL		128
#define TASK_WAKING		256
#define TASK_PARKED		512
#define TASK_NOLOAD		1024
#define TASK_NEW		2048
#define TASK_STATE_MAX		4096

#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn"

extern char ___assert_task_state[1 - 2*!!(
		sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];

/* Convenience macros for the sake of set_task_state */
#define TASK_KILLABLE		(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
#define TASK_STOPPED		(TASK_WAKEKILL | __TASK_STOPPED)
#define TASK_TRACED		(TASK_WAKEKILL | __TASK_TRACED)

#define TASK_IDLE		(TASK_UNINTERRUPTIBLE | TASK_NOLOAD)

/* Convenience macros for the sake of wake_up */
#define TASK_NORMAL		(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
#define TASK_ALL		(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)

/* get_task_state() */
#define TASK_REPORT		(TASK_RUNNING | TASK_INTERRUPTIBLE | \
				 TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
				 __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD)

#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)

#ifdef CONFIG_DEBUG_ATOMIC_SLEEP

#define __set_task_state(tsk, state_value)			\
	do {							\
		(tsk)->task_state_change = _THIS_IP_;		\
		(tsk)->state = (state_value);			\
	} while (0)
#define set_task_state(tsk, state_value)			\
	do {							\
		(tsk)->task_state_change = _THIS_IP_;		\
		smp_store_mb((tsk)->state, (state_value));		\
	} 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:
 *
 *	set_current_state(TASK_UNINTERRUPTIBLE);
 *	if (do_i_need_to_sleep())
 *		schedule();
 *
 * If the caller does not need such serialisation then use __set_current_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)

#else

#define __set_task_state(tsk, state_value)		\
	do { (tsk)->state = (state_value); } while (0)
#define set_task_state(tsk, state_value)		\
	smp_store_mb((tsk)->state, (state_value))

/*
 * 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:
 *
 *	set_current_state(TASK_UNINTERRUPTIBLE);
 *	if (do_i_need_to_sleep())
 *		schedule();
 *
 * If the caller does not need such serialisation then use __set_current_state()
 */
#define __set_current_state(state_value)		\
	do { current->state = (state_value); } while (0)
#define set_current_state(state_value)			\
	smp_store_mb(current->state, (state_value))

#endif

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

#include <linux/spinlock.h>

/*
 * This serializes "schedule()" and also protects
 * the run-queue from deletions/modifications (but
 * _adding_ to the beginning of the run-queue has
 * a separate lock).
 */
extern rwlock_t tasklist_lock;
extern spinlock_t mmlist_lock;

struct task_struct;

#ifdef CONFIG_PROVE_RCU
extern int lockdep_tasklist_lock_is_held(void);
#endif /* #ifdef CONFIG_PROVE_RCU */

extern void sched_init(void);
extern void sched_init_smp(void);
extern asmlinkage void schedule_tail(struct task_struct *prev);
extern void init_idle(struct task_struct *idle, int cpu);
extern void init_idle_bootup_task(struct task_struct *idle);

extern cpumask_var_t cpu_isolated_map;

extern int runqueue_is_locked(int cpu);

#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
extern void nohz_balance_enter_idle(int cpu);
extern void set_cpu_sd_state_idle(void);
extern int get_nohz_timer_target(void);
#else
static inline void nohz_balance_enter_idle(int cpu) { }
static inline void set_cpu_sd_state_idle(void) { }
#endif

/*
 * Only dump TASK_* tasks. (0 for all tasks)
 */
extern void show_state_filter(unsigned long state_filter);

static inline void show_state(void)
{
	show_state_filter(0);
}

extern void show_regs(struct pt_regs *);

/*
 * TASK is a pointer to the task whose backtrace we want to see (or NULL for current
 * task), SP is the stack pointer of the first frame that should be shown in the back
 * trace (or NULL if the entire call-chain of the task should be shown).
 */
extern void show_stack(struct task_struct *task, unsigned long *sp);

extern void cpu_init (void);
extern void trap_init(void);
extern void update_process_times(int user);
extern void scheduler_tick(void);
extern int sched_cpu_starting(unsigned int cpu);
extern int sched_cpu_activate(unsigned int cpu);
extern int sched_cpu_deactivate(unsigned int cpu);

#ifdef CONFIG_HOTPLUG_CPU
extern int sched_cpu_dying(unsigned int cpu);
#else
# define sched_cpu_dying	NULL
#endif

extern void sched_show_task(struct task_struct *p);

#ifdef CONFIG_LOCKUP_DETECTOR
extern void touch_softlockup_watchdog_sched(void);
extern void touch_softlockup_watchdog(void);
extern void touch_softlockup_watchdog_sync(void);
extern void touch_all_softlockup_watchdogs(void);
extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
				  void __user *buffer,
				  size_t *lenp, loff_t *ppos);
extern unsigned int  softlockup_panic;
extern unsigned int  hardlockup_panic;
void lockup_detector_init(void);
#else
static inline void touch_softlockup_watchdog_sched(void)
{
}
static inline void touch_softlockup_watchdog(void)
{
}
static inline void touch_softlockup_watchdog_sync(void)
{
}
static inline void touch_all_softlockup_watchdogs(void)
{
}
static inline void lockup_detector_init(void)
{
}
#endif

#ifdef CONFIG_DETECT_HUNG_TASK
void reset_hung_task_detector(void);
#else
static inline void reset_hung_task_detector(void)
{
}
#endif

/* Attach to any functions which should be ignored in wchan output. */
#define __sched		__attribute__((__section__(".sched.text")))

/* Linker adds these: start and end of __sched functions */
extern char __sched_text_start[], __sched_text_end[];

/* Is this address in the __sched functions? */
extern int in_sched_functions(unsigned long addr);

#define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
extern signed long schedule_timeout(signed long timeout);
extern signed long schedule_timeout_interruptible(signed long timeout);
extern signed long schedule_timeout_killable(signed long timeout);
extern signed long schedule_timeout_uninterruptible(signed long timeout);
extern signed long schedule_timeout_idle(signed long timeout);
asmlinkage void schedule(void);
extern void schedule_preempt_disabled(void);

extern long io_schedule_timeout(long timeout);

static inline void io_schedule(void)
{
	io_schedule_timeout(MAX_SCHEDULE_TIMEOUT);
}

void __noreturn do_task_dead(void);

struct nsproxy;
struct user_namespace;

#ifdef CONFIG_MMU
extern void arch_pick_mmap_layout(struct mm_struct *mm);
extern unsigned long
arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
		       unsigned long, unsigned long);
extern unsigned long
arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
			  unsigned long len, unsigned long pgoff,
			  unsigned long flags);
#else
static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
#endif

#define SUID_DUMP_DISABLE	0	/* No setuid dumping */
#define SUID_DUMP_USER		1	/* Dump as user of process */
#define SUID_DUMP_ROOT		2	/* Dump as root */

/* mm flags */

/* for SUID_DUMP_* above */
#define MMF_DUMPABLE_BITS 2
#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1)

extern void set_dumpable(struct mm_struct *mm, int value);
/*
 * This returns the actual value of the suid_dumpable flag. For things
 * that are using this for checking for privilege transitions, it must
 * test against SUID_DUMP_USER rather than treating it as a boolean
 * value.
 */
static inline int __get_dumpable(unsigned long mm_flags)
{
	return mm_flags & MMF_DUMPABLE_MASK;
}

static inline int get_dumpable(struct mm_struct *mm)
{
	return __get_dumpable(mm->flags);
}

/* coredump filter bits */
#define MMF_DUMP_ANON_PRIVATE	2
#define MMF_DUMP_ANON_SHARED	3
#define MMF_DUMP_MAPPED_PRIVATE	4
#define MMF_DUMP_MAPPED_SHARED	5
#define MMF_DUMP_ELF_HEADERS	6
#define MMF_DUMP_HUGETLB_PRIVATE 7
#define MMF_DUMP_HUGETLB_SHARED  8
#define MMF_DUMP_DAX_PRIVATE	9
#define MMF_DUMP_DAX_SHARED	10

#define MMF_DUMP_FILTER_SHIFT	MMF_DUMPABLE_BITS
#define MMF_DUMP_FILTER_BITS	9
#define MMF_DUMP_FILTER_MASK \
	(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
#define MMF_DUMP_FILTER_DEFAULT \
	((1 << MMF_DUMP_ANON_PRIVATE) |	(1 << MMF_DUMP_ANON_SHARED) |\
	 (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF)

#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS
# define MMF_DUMP_MASK_DEFAULT_ELF	(1 << MMF_DUMP_ELF_HEADERS)
#else
# define MMF_DUMP_MASK_DEFAULT_ELF	0
#endif
					/* leave room for more dump flags */
#define MMF_VM_MERGEABLE	16	/* KSM may merge identical pages */
#define MMF_VM_HUGEPAGE		17	/* set when VM_HUGEPAGE is set on vma */
#define MMF_EXE_FILE_CHANGED	18	/* see prctl_set_mm_exe_file() */

#define MMF_HAS_UPROBES		19	/* has uprobes */
#define MMF_RECALC_UPROBES	20	/* MMF_HAS_UPROBES can be wrong */
#define MMF_OOM_SKIP		21	/* mm is of no interest for the OOM killer */
#define MMF_UNSTABLE		22	/* mm is unstable for copy_from_user */
#define MMF_HUGE_ZERO_PAGE	23      /* mm has ever used the global huge zero page */

#define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)

struct sighand_struct {
	atomic_t		count;
	struct k_sigaction	action[_NSIG];
	spinlock_t		siglock;
	wait_queue_head_t	signalfd_wqh;
};

struct pacct_struct {
	int			ac_flag;
	long			ac_exitcode;
	unsigned long		ac_mem;
	cputime_t		ac_utime, ac_stime;
	unsigned long		ac_minflt, ac_majflt;
};

struct cpu_itimer {
	cputime_t expires;
	cputime_t incr;
	u32 error;
	u32 incr_error;
};

/**
 * struct prev_cputime - snaphsot 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 {
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
	cputime_t utime;
	cputime_t stime;
	raw_spinlock_t lock;
#endif
};

static inline void prev_cputime_init(struct prev_cputime *prev)
{
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
	prev->utime = prev->stime = 0;
	raw_spin_lock_init(&prev->lock);
#endif
}

/**
 * struct task_cputime - collected CPU time counts
 * @utime:		time spent in user mode, in &cputime_t units
 * @stime:		time spent in kernel mode, in &cputime_t units
 * @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 {
	cputime_t utime;
	cputime_t stime;
	unsigned long long sum_exec_runtime;
};

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

#define INIT_CPUTIME	\
	(struct task_cputime) {					\
		.utime = 0,					\
		.stime = 0,					\
		.sum_exec_runtime = 0,				\
	}

/*
 * This is the atomic variant of task_cputime, which can be used for
 * storing and updating task_cputime statistics without locking.
 */
struct task_cputime_atomic {
	atomic64_t utime;
	atomic64_t stime;
	atomic64_t sum_exec_runtime;
};

#define INIT_CPUTIME_ATOMIC \
	(struct task_cputime_atomic) {				\
		.utime = ATOMIC64_INIT(0),			\
		.stime = ATOMIC64_INIT(0),			\
		.sum_exec_runtime = ATOMIC64_INIT(0),		\
	}

#define PREEMPT_DISABLED	(PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)

/*
 * Disable preemption until the scheduler is running -- use an unconditional
 * value so that it also works on !PREEMPT_COUNT kernels.
 *
 * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count().
 */
#define INIT_PREEMPT_COUNT	PREEMPT_OFFSET

/*
 * Initial preempt_count value; reflects the preempt_count schedule invariant
 * which states that during context switches:
 *
 *    preempt_count() == 2*PREEMPT_DISABLE_OFFSET
 *
 * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels.
 * Note: See finish_task_switch().
 */
#define FORK_PREEMPT_COUNT	(2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)

/**
 * struct thread_group_cputimer - thread group interval timer counts
 * @cputime_atomic:	atomic thread group interval timers.
 * @running:		true when there are timers running and
 *			@cputime_atomic receives updates.
 * @checking_timer:	true when a thread in the group is in the
 *			process of checking for thread group timers.
 *
 * This structure contains the version of task_cputime, above, that is
 * used for thread group CPU timer calculations.
 */
struct thread_group_cputimer {
	struct task_cputime_atomic cputime_atomic;
	bool running;
	bool checking_timer;
};

#include <linux/rwsem.h>
struct autogroup;

/*
 * NOTE! "signal_struct" does not have its own
 * locking, because a shared signal_struct always
 * implies a shared sighand_struct, so locking
 * sighand_struct is always a proper superset of
 * the locking of signal_struct.
 */
struct signal_struct {
	atomic_t		sigcnt;
	atomic_t		live;
	int			nr_threads;
	struct list_head	thread_head;

	wait_queue_head_t	wait_chldexit;	/* for wait4() */

	/* current thread group signal load-balancing target: */
	struct task_struct	*curr_target;

	/* shared signal handling: */
	struct sigpending	shared_pending;

	/* thread group exit support */
	int			group_exit_code;
	/* overloaded:
	 * - notify group_exit_task when ->count is equal to notify_count
	 * - everyone except group_exit_task is stopped during signal delivery
	 *   of fatal signals, group_exit_task processes the signal.
	 */
	int			notify_count;
	struct task_struct	*group_exit_task;

	/* thread group stop support, overloads group_exit_code too */
	int			group_stop_count;
	unsigned int		flags; /* see SIGNAL_* flags below */

	/*
	 * PR_SET_CHILD_SUBREAPER marks a process, like a service
	 * manager, to re-parent orphan (double-forking) child processes
	 * to this process instead of 'init'. The service manager is
	 * able to receive SIGCHLD signals and is able to investigate
	 * the process until it calls wait(). All children of this
	 * process will inherit a flag if they should look for a
	 * child_subreaper process at exit.
	 */
	unsigned int		is_child_subreaper:1;
	unsigned int		has_child_subreaper:1;

	/* POSIX.1b Interval Timers */
	int			posix_timer_id;
	struct list_head	posix_timers;

	/* ITIMER_REAL timer for the process */
	struct hrtimer real_timer;
	struct pid *leader_pid;
	ktime_t it_real_incr;

	/*
	 * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use
	 * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these
	 * values are defined to 0 and 1 respectively
	 */
	struct cpu_itimer it[2];

	/*
	 * Thread group totals for process CPU timers.
	 * See thread_group_cputimer(), et al, for details.
	 */
	struct thread_group_cputimer cputimer;

	/* Earliest-expiration cache. */
	struct task_cputime cputime_expires;

#ifdef CONFIG_NO_HZ_FULL
	atomic_t tick_dep_mask;
#endif

	struct list_head cpu_timers[3];

	struct pid *tty_old_pgrp;

	/* boolean value for session group leader */
	int leader;

	struct tty_struct *tty; /* NULL if no tty */

#ifdef CONFIG_SCHED_AUTOGROUP
	struct autogroup *autogroup;
#endif
	/*
	 * Cumulative resource counters for dead threads in the group,
	 * and for reaped dead child processes forked by this group.
	 * Live threads maintain their own counters and add to these
	 * in __exit_signal, except for the group leader.
	 */
	seqlock_t stats_lock;
	cputime_t utime, stime, cutime, cstime;
	cputime_t gtime;
	cputime_t cgtime;
	struct prev_cputime prev_cputime;
	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
	unsigned long inblock, oublock, cinblock, coublock;
	unsigned long maxrss, cmaxrss;
	struct task_io_accounting ioac;

	/*
	 * Cumulative ns of schedule CPU time fo dead threads in the
	 * group, not including a zombie group leader, (This only differs
	 * from jiffies_to_ns(utime + stime) if sched_clock uses something
	 * other than jiffies.)
	 */
	unsigned long long sum_sched_runtime;

	/*
	 * We don't bother to synchronize most readers of this at all,
	 * because there is no reader checking a limit that actually needs
	 * to get both rlim_cur and rlim_max atomically, and either one
	 * alone is a single word that can safely be read normally.
	 * getrlimit/setrlimit use task_lock(current->group_leader) to
	 * protect this instead of the siglock, because they really
	 * have no need to disable irqs.
	 */
	struct rlimit rlim[RLIM_NLIMITS];

#ifdef CONFIG_BSD_PROCESS_ACCT
	struct pacct_struct pacct;	/* per-process accounting information */
#endif
#ifdef CONFIG_TASKSTATS
	struct taskstats *stats;
#endif
#ifdef CONFIG_AUDIT
	unsigned audit_tty;
	struct tty_audit_buf *tty_audit_buf;
#endif

	/*
	 * Thread is the potential origin of an oom condition; kill first on
	 * oom
	 */
	bool oom_flag_origin;
	short oom_score_adj;		/* OOM kill score adjustment */
	short oom_score_adj_min;	/* OOM kill score adjustment min value.
					 * Only settable by CAP_SYS_RESOURCE. */
	struct mm_struct *oom_mm;	/* recorded mm when the thread group got
					 * killed by the oom killer */

	struct mutex cred_guard_mutex;	/* guard against foreign influences on
					 * credential calculations
					 * (notably. ptrace) */
};

/*
 * Bits in flags field of signal_struct.
 */
#define SIGNAL_STOP_STOPPED	0x00000001 /* job control stop in effect */
#define SIGNAL_STOP_CONTINUED	0x00000002 /* SIGCONT since WCONTINUED reap */
#define SIGNAL_GROUP_EXIT	0x00000004 /* group exit in progress */
#define SIGNAL_GROUP_COREDUMP	0x00000008 /* coredump in progress */
/*
 * Pending notifications to parent.
 */
#define SIGNAL_CLD_STOPPED	0x00000010
#define SIGNAL_CLD_CONTINUED	0x00000020
#define SIGNAL_CLD_MASK		(SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED)

#define SIGNAL_UNKILLABLE	0x00000040 /* for init: ignore fatal signals */

/* If true, all threads except ->group_exit_task have pending SIGKILL */
static inline int signal_group_exit(const struct signal_struct *sig)
{
	return	(sig->flags & SIGNAL_GROUP_EXIT) ||
		(sig->group_exit_task != NULL);
}

/*
 * Some day this will be a full-fledged user tracking system..
 */
struct user_struct {
	atomic_t __count;	/* reference count */
	atomic_t processes;	/* How many processes does this user have? */
	atomic_t sigpending;	/* How many pending signals does this user have? */
#ifdef CONFIG_INOTIFY_USER
	atomic_t inotify_watches; /* How many inotify watches does this user have? */
	atomic_t inotify_devs;	/* How many inotify devs does this user have opened? */
#endif
#ifdef CONFIG_FANOTIFY
	atomic_t fanotify_listeners;
#endif
#ifdef CONFIG_EPOLL
	atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
#endif
#ifdef CONFIG_POSIX_MQUEUE
	/* protected by mq_lock	*/
	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
#endif
	unsigned long locked_shm; /* How many pages of mlocked shm ? */
	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
	atomic_long_t pipe_bufs;  /* how many pages are allocated in pipe buffers */

#ifdef CONFIG_KEYS
	struct key *uid_keyring;	/* UID specific keyring */
	struct key *session_keyring;	/* UID's default session keyring */
#endif

	/* Hash table maintenance information */
	struct hlist_node uidhash_node;
	kuid_t uid;

#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL)
	atomic_long_t locked_vm;
#endif
};

extern int uids_sysfs_init(void);

extern struct user_struct *find_user(kuid_t);

extern struct user_struct root_user;
#define INIT_USER (&root_user)


struct backing_dev_info;
struct reclaim_state;

#ifdef CONFIG_SCHED_INFO
struct sched_info {
	/* cumulative counters */
	unsigned long pcount;	      /* # of times run on this cpu */
	unsigned long long run_delay; /* time spent waiting on a runqueue */

	/* timestamps */
	unsigned long long last_arrival,/* when we last ran on a cpu */
			   last_queued;	/* when we were last queued to run */
};
#endif /* CONFIG_SCHED_INFO */

#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info {
	spinlock_t	lock;
	unsigned int	flags;	/* Private per-task flags */

	/* For each stat XXX, add following, aligned appropriately
	 *
	 * struct timespec XXX_start, XXX_end;
	 * u64 XXX_delay;
	 * u32 XXX_count;
	 *
	 * Atomicity of updates to XXX_delay, XXX_count protected by
	 * single lock above (split into XXX_lock if contention is an issue).
	 */

	/*
	 * XXX_count is incremented on every XXX operation, the delay
	 * associated with the operation is added to XXX_delay.
	 * XXX_delay contains the accumulated delay time in nanoseconds.
	 */
	u64 blkio_start;	/* Shared by blkio, swapin */
	u64 blkio_delay;	/* wait for sync block io completion */
	u64 swapin_delay;	/* wait for swapin block io completion */
	u32 blkio_count;	/* total count of the number of sync block */
				/* io operations performed */
	u32 swapin_count;	/* total count of the number of swapin block */
				/* io operations performed */

	u64 freepages_start;
	u64 freepages_delay;	/* wait for memory reclaim */
	u32 freepages_count;	/* total count of memory reclaim */
};
#endif	/* CONFIG_TASK_DELAY_ACCT */

static inline int sched_info_on(void)
{
#ifdef CONFIG_SCHEDSTATS
	return 1;
#elif defined(CONFIG_TASK_DELAY_ACCT)
	extern int delayacct_on;
	return delayacct_on;
#else
	return 0;
#endif
}

#ifdef CONFIG_SCHEDSTATS
void force_schedstat_enabled(void);
#endif

enum cpu_idle_type {
	CPU_IDLE,
	CPU_NOT_IDLE,
	CPU_NEWLY_IDLE,
	CPU_MAX_IDLE_TYPES
};

/*
 * 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.
 */
# define SCHED_FIXEDPOINT_SHIFT	10
# define SCHED_FIXEDPOINT_SCALE	(1L << SCHED_FIXEDPOINT_SHIFT)

/*
 * Increase resolution of cpu_capacity calculations
 */
#define SCHED_CAPACITY_SHIFT	SCHED_FIXEDPOINT_SHIFT
#define SCHED_CAPACITY_SCALE	(1L << SCHED_CAPACITY_SHIFT)

/*
 * Wake-queues are lists of tasks with a pending wakeup, whose
 * callers have already marked the task as woken internally,
 * and can thus carry on. A common use case is being able to
 * do the wakeups once the corresponding user lock as been
 * released.
 *
 * We hold reference to each task in the list across the wakeup,
 * thus guaranteeing that the memory is still valid by the time
 * the actual wakeups are performed in wake_up_q().
 *
 * One per task suffices, because there's never a need for a task to be
 * in two wake queues simultaneously; it is forbidden to abandon a task
 * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is
 * already in a wake queue, the wakeup will happen soon and the second
 * waker can just skip it.
 *
 * The WAKE_Q macro declares and initializes the list head.
 * wake_up_q() does NOT reinitialize the list; it's expected to be
 * called near the end of a function, where the fact that the queue is
 * not used again will be easy to see by inspection.
 *
 * Note that this can cause spurious wakeups. schedule() callers
 * must ensure the call is done inside a loop, confirming that the
 * wakeup condition has in fact occurred.
 */
struct wake_q_node {
	struct wake_q_node *next;
};

struct wake_q_head {
	struct wake_q_node *first;
	struct wake_q_node **lastp;
};

#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)

#define WAKE_Q(name)					\
	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }

extern void wake_q_add(struct wake_q_head *head,
		       struct task_struct *task);
extern void wake_up_q(struct wake_q_head *head);

/*
 * sched-domains (multiprocessor balancing) declarations:
 */
#ifdef CONFIG_SMP
#define SD_LOAD_BALANCE		0x0001	/* Do load balancing on this domain. */
#define SD_BALANCE_NEWIDLE	0x0002	/* Balance when about to become idle */
#define SD_BALANCE_EXEC		0x0004	/* Balance on exec */
#define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
#define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
#define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
#define SD_ASYM_CPUCAPACITY	0x0040  /* Groups have different max cpu capacities */
#define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share cpu capacity */
#define SD_SHARE_POWERDOMAIN	0x0100	/* Domain members share power domain */
#define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
#define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
#define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
#define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
#define SD_OVERLAP		0x2000	/* sched_domains of this level overlap */
#define SD_NUMA			0x4000	/* cross-node balancing */

#ifdef CONFIG_SCHED_SMT
static inline int cpu_smt_flags(void)
{
	return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
}
#endif

#ifdef CONFIG_SCHED_MC
static inline int cpu_core_flags(void)
{
	return SD_SHARE_PKG_RESOURCES;
}
#endif

#ifdef CONFIG_NUMA
static inline int cpu_numa_flags(void)
{
	return SD_NUMA;
}
#endif

struct sched_domain_attr {
	int relax_domain_level;
};

#define SD_ATTR_INIT	(struct sched_domain_attr) {	\
	.relax_domain_level = -1,			\
}

extern int sched_domain_level_max;

struct sched_group;

struct sched_domain_shared {
	atomic_t	ref;
	atomic_t	nr_busy_cpus;
	int		has_idle_cores;
};

struct sched_domain {
	/* These fields must be setup */
	struct sched_domain *parent;	/* top domain must be null terminated */
	struct sched_domain *child;	/* bottom domain must be null terminated */
	struct sched_group *groups;	/* the balancing groups of the domain */
	unsigned long min_interval;	/* Minimum balance interval ms */
	unsigned long max_interval;	/* Maximum balance interval ms */
	unsigned int busy_factor;	/* less balancing by factor if busy */
	unsigned int imbalance_pct;	/* No balance until over watermark */
	unsigned int cache_nice_tries;	/* Leave cache hot tasks for # tries */
	unsigned int busy_idx;
	unsigned int idle_idx;
	unsigned int newidle_idx;
	unsigned int wake_idx;
	unsigned int forkexec_idx;
	unsigned int smt_gain;

	int nohz_idle;			/* NOHZ IDLE status */
	int flags;			/* See SD_* */
	int level;

	/* Runtime fields. */
	unsigned long last_balance;	/* init to jiffies. units in jiffies */
	unsigned int balance_interval;	/* initialise to 1. units in ms. */
	unsigned int nr_balance_failed; /* initialise to 0 */

	/* idle_balance() stats */
	u64 max_newidle_lb_cost;
	unsigned long next_decay_max_lb_cost;

	u64 avg_scan_cost;		/* select_idle_sibling */

#ifdef CONFIG_SCHEDSTATS
	/* load_balance() stats */
	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
	unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
	unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
	unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
	unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
	unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
	unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
	unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES];

	/* Active load balancing */
	unsigned int alb_count;
	unsigned int alb_failed;
	unsigned int alb_pushed;

	/* SD_BALANCE_EXEC stats */
	unsigned int sbe_count;
	unsigned int sbe_balanced;
	unsigned int sbe_pushed;

	/* SD_BALANCE_FORK stats */