/include/linux/sched.h

Large files files are truncated, but you can click here to view the full file

#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H

/*
 * cloning flags:
 */
#define CSIGNAL		0x000000ff	/* signal mask to be sent at exit */
#define CLONE_VM	0x00000100	/* set if VM shared between processes */
#define CLONE_FS	0x00000200	/* set if fs info shared between processes */
#define CLONE_FILES	0x00000400	/* set if open files shared between processes */
#define CLONE_SIGHAND	0x00000800	/* set if signal handlers and blocked signals shared */
#define CLONE_PTRACE	0x00002000	/* set if we want to let tracing continue on the child too */
#define CLONE_VFORK	0x00004000	/* set if the parent wants the child to wake it up on mm_release */
#define CLONE_PARENT	0x00008000	/* set if we want to have the same parent as the cloner */
#define CLONE_THREAD	0x00010000	/* Same thread group? */
#define CLONE_NEWNS	0x00020000	/* New namespace group? */
#define CLONE_SYSVSEM	0x00040000	/* share system V SEM_UNDO semantics */
#define CLONE_SETTLS	0x00080000	/* create a new TLS for the child */
#define CLONE_PARENT_SETTID	0x00100000	/* set the TID in the parent */
#define CLONE_CHILD_CLEARTID	0x00200000	/* clear the TID in the child */
#define CLONE_DETACHED		0x00400000	/* Unused, ignored */
#define CLONE_UNTRACED		0x00800000	/* set if the tracing process can't force CLONE_PTRACE on this clone */
#define CLONE_CHILD_SETTID	0x01000000	/* set the TID in the child */
/* 0x02000000 was previously the unused CLONE_STOPPED (Start in stopped state)
   and is now available for re-use. */
#define CLONE_NEWUTS		0x04000000	/* New utsname group? */
#define CLONE_NEWIPC		0x08000000	/* New ipcs */
#define CLONE_NEWUSER		0x10000000	/* New user namespace */
#define CLONE_NEWPID		0x20000000	/* New pid namespace */
#define CLONE_NEWNET		0x40000000	/* New network namespace */
#define CLONE_IO		0x80000000	/* Clone io context */

/*
 * Scheduling policies
 */
#define SCHED_NORMAL		0
#define SCHED_FIFO		1
#define SCHED_RR		2
#define SCHED_BATCH		3
/* SCHED_ISO: reserved but not implemented yet */
#define SCHED_IDLE		5
/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
#define SCHED_RESET_ON_FORK     0x40000000

#ifdef __KERNEL__

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

#include <linux/smp.h>
#include <linux/sem.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/proportions.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/task_io_accounting.h>
#include <linux/latencytop.h>
#include <linux/cred.h>
#include <linux/llist.h>

#include <asm/processor.h>

struct exec_domain;
struct futex_pi_state;
struct robust_list_head;
struct bio_list;
struct fs_struct;
struct perf_event_context;
struct blk_plug;

/*
 * List of flags we want to share for kernel threads,
 * if only because they are not used by them anyway.
 */
#define CLONE_KERNEL	(CLONE_FS | CLONE_FILES | CLONE_SIGHAND)

/*
 * 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 unsigned long nr_uninterruptible(void);
extern unsigned long nr_iowait(void);
extern unsigned long nr_iowait_cpu(int cpu);
extern unsigned long this_cpu_load(void);


extern void calc_global_load(unsigned long ticks);

extern unsigned long get_parent_ip(unsigned long addr);

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);
extern void
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
#else
static inline void
proc_sched_show_task(struct task_struct *p, struct seq_file *m)
{
}
static inline void proc_sched_set_task(struct task_struct *p)
{
}
static inline void
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
}
#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_ZOMBIE		16
#define EXIT_DEAD		32
/* in tsk->state again */
#define TASK_DEAD		64
#define TASK_WAKEKILL		128
#define TASK_WAKING		256
#define TASK_STATE_MAX		512

#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW"

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)

/* 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)

#define task_is_traced(task)	((task->state & __TASK_TRACED) != 0)
#define task_is_stopped(task)	((task->state & __TASK_STOPPED) != 0)
#define task_is_dead(task)	((task)->exit_state != 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)

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

/* 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 int runqueue_is_locked(int cpu);

#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
extern void select_nohz_load_balancer(int stop_tick);
extern void set_cpu_sd_state_idle(void);
extern int get_nohz_timer_target(void);
#else
static inline void select_nohz_load_balancer(int stop_tick) { }
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);

void io_schedule(void);
long io_schedule_timeout(long timeout);

extern void cpu_init (void);
extern void trap_init(void);
extern void update_process_times(int user);
extern void scheduler_tick(void);

extern void sched_show_task(struct task_struct *p);

#ifdef CONFIG_LOCKUP_DETECTOR
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;
void lockup_detector_init(void);
#else
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
extern unsigned int  sysctl_hung_task_panic;
extern unsigned long sysctl_hung_task_check_count;
extern unsigned long sysctl_hung_task_timeout_secs;
extern unsigned long sysctl_hung_task_warnings;
extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
					 void __user *buffer,
					 size_t *lenp, loff_t *ppos);
#else
/* Avoid need for ifdefs elsewhere in the code */
enum { sysctl_hung_task_timeout_secs = 0 };
#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);
asmlinkage void schedule(void);
extern void schedule_preempt_disabled(void);
extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);

struct nsproxy;
struct user_namespace;

/*
 * Default maximum number of active map areas, this limits the number of vmas
 * per mm struct. Users can overwrite this number by sysctl but there is a
 * problem.
 *
 * When a program's coredump is generated as ELF format, a section is created
 * per a vma. In ELF, the number of sections is represented in unsigned short.
 * This means the number of sections should be smaller than 65535 at coredump.
 * Because the kernel adds some informative sections to a image of program at
 * generating coredump, we need some margin. The number of extra sections is
 * 1-3 now and depends on arch. We use "5" as safe margin, here.
 */
#define MAPCOUNT_ELF_CORE_MARGIN	(5)
#define DEFAULT_MAX_MAP_COUNT	(USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)

extern int sysctl_max_map_count;

#include <linux/aio.h>

#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);
extern void arch_unmap_area(struct mm_struct *, unsigned long);
extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
#else
static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
#endif


extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);

/* mm flags */
/* dumpable bits */
#define MMF_DUMPABLE      0  /* core dump is permitted */
#define MMF_DUMP_SECURELY 1  /* core file is readable only by root */

#define MMF_DUMPABLE_BITS 2
#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1)

/* 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_FILTER_SHIFT	MMF_DUMPABLE_BITS
#define MMF_DUMP_FILTER_BITS	7
#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_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 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 prof_exp	stime
#define virt_exp	utime
#define sched_exp	sum_exec_runtime

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

/*
 * Disable preemption until the scheduler is running.
 * Reset by start_kernel()->sched_init()->init_idle().
 *
 * We include PREEMPT_ACTIVE to avoid cond_resched() from working
 * before the scheduler is active -- see should_resched().
 */
#define INIT_PREEMPT_COUNT	(1 + PREEMPT_ACTIVE)

/**
 * struct thread_group_cputimer - thread group interval timer counts
 * @cputime:		thread group interval timers.
 * @running:		non-zero when there are timers running and
 * 			@cputime receives updates.
 * @lock:		lock for fields in this struct.
 *
 * 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 cputime;
	int running;
	raw_spinlock_t lock;
};

#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;

	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 */
	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;

	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.
	 */
	cputime_t utime, stime, cutime, cstime;
	cputime_t gtime;
	cputime_t cgtime;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
	cputime_t prev_utime, prev_stime;
#endif
	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
#ifdef CONFIG_CGROUPS
	/*
	 * group_rwsem prevents new tasks from entering the threadgroup and
	 * member tasks from exiting,a more specifically, setting of
	 * PF_EXITING.  fork and exit paths are protected with this rwsem
	 * using threadgroup_change_begin/end().  Users which require
	 * threadgroup to remain stable should use threadgroup_[un]lock()
	 * which also takes care of exec path.  Currently, cgroup is the
	 * only user.
	 */
	struct rw_semaphore group_rwsem;
#endif

	int oom_adj;		/* OOM kill score adjustment (bit shift) */
	int oom_score_adj;	/* OOM kill score adjustment */
	int oom_score_adj_min;	/* OOM kill score adjustment minimum value.
				 * Only settable by CAP_SYS_RESOURCE. */

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

/* Context switch must be unlocked if interrupts are to be enabled */
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
# define __ARCH_WANT_UNLOCKED_CTXSW
#endif

/*
 * 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 */
/*
 * 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 files;		/* How many open files 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 ? */

#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;
	uid_t uid;
	struct user_namespace *user_ns;

#ifdef CONFIG_PERF_EVENTS
	atomic_long_t locked_vm;
#endif
};

extern int uids_sysfs_init(void);

extern struct user_struct *find_user(uid_t);

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


struct backing_dev_info;
struct reclaim_state;

#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
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 /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */

#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.
	 */
	struct timespec blkio_start, blkio_end;	/* 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 */

	struct timespec freepages_start, freepages_end;
	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
}

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

/*
 * Increase resolution of nice-level calculations for 64-bit architectures.
 * The extra resolution improves shares distribution and load balancing of
 * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
 * hierarchies, especially on larger systems. This is not a user-visible change
 * and does not change the user-interface for setting shares/weights.
 *
 * We increase resolution only if we have enough bits to allow this increased
 * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution
 * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the
 * increased costs.
 */
#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load  */
# define SCHED_LOAD_RESOLUTION	10
# define scale_load(w)		((w) << SCHED_LOAD_RESOLUTION)
# define scale_load_down(w)	((w) >> SCHED_LOAD_RESOLUTION)
#else
# define SCHED_LOAD_RESOLUTION	0
# define scale_load(w)		(w)
# define scale_load_down(w)	(w)
#endif

#define SCHED_LOAD_SHIFT	(10 + SCHED_LOAD_RESOLUTION)
#define SCHED_LOAD_SCALE	(1L << SCHED_LOAD_SHIFT)

/*
 * Increase resolution of cpu_power calculations
 */
#define SCHED_POWER_SHIFT	10
#define SCHED_POWER_SCALE	(1L << SCHED_POWER_SHIFT)

/*
 * 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_PREFER_LOCAL		0x0040  /* Prefer to keep tasks local to this domain */
#define SD_SHARE_CPUPOWER	0x0080	/* Domain members share cpu power */
#define SD_POWERSAVINGS_BALANCE	0x0100	/* Balance for power savings */
#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 */

enum powersavings_balance_level {
	POWERSAVINGS_BALANCE_NONE = 0,  /* No power saving load balance */
	POWERSAVINGS_BALANCE_BASIC,	/* Fill one thread/core/package
					 * first for long running threads
					 */
	POWERSAVINGS_BALANCE_WAKEUP,	/* Also bias task wakeups to semi-idle
					 * cpu package for power savings
					 */
	MAX_POWERSAVINGS_BALANCE_LEVELS
};

extern int sched_mc_power_savings, sched_smt_power_savings;

static inline int sd_balance_for_mc_power(void)
{
	if (sched_smt_power_savings)
		return SD_POWERSAVINGS_BALANCE;

	if (!sched_mc_power_savings)
		return SD_PREFER_SIBLING;

	return 0;
}

static inline int sd_balance_for_package_power(void)
{
	if (sched_mc_power_savings | sched_smt_power_savings)
		return SD_POWERSAVINGS_BALANCE;

	return SD_PREFER_SIBLING;
}

extern int __weak arch_sd_sibiling_asym_packing(void);

/*
 * Optimise SD flags for power savings:
 * SD_BALANCE_NEWIDLE helps aggressive task consolidation and power savings.
 * Keep default SD flags if sched_{smt,mc}_power_saving=0
 */

static inline int sd_power_saving_flags(void)
{
	if (sched_mc_power_savings | sched_smt_power_savings)
		return SD_BALANCE_NEWIDLE;

	return 0;
}

struct sched_group_power {
	atomic_t ref;
	/*
	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
	 * single CPU.
	 */
	unsigned int power, power_orig;
	unsigned long next_update;
	/*
	 * Number of busy cpus in this group.
	 */
	atomic_t nr_busy_cpus;
};

struct sched_group {
	struct sched_group *next;	/* Must be a circular list */
	atomic_t ref;

	unsigned int group_weight;
	struct sched_group_power *sgp;

	/*
	 * The CPUs this group covers.
	 *
	 * NOTE: this field is variable length. (Allocated dynamically
	 * by attaching extra space to the end of the structure,
	 * depending on how many CPUs the kernel has booted up with)
	 */
	unsigned long cpumask[0];
};

static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
{
	return to_cpumask(sg->cpumask);
}

/**
 * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
 * @group: The group whose first cpu is to be returned.
 */
static inline unsigned int group_first_cpu(struct sched_group *group)
{
	return cpumask_first(sched_group_cpus(group));
}

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_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 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 */

	u64 last_update;

#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 */
	unsigned int sbf_count;
	unsigned int sbf_balanced;
	unsigned int sbf_pushed;

	/* try_to_wake_up() stats */
	unsigned int ttwu_wake_remote;
	unsigned int ttwu_move_affine;
	unsigned int ttwu_move_balance;
#endif
#ifdef CONFIG_SCHED_DEBUG
	char *name;
#endif
	union {
		void *private;		/* used during construction */
		struct rcu_head rcu;	/* used during destruction */
	};

	unsigned int span_weight;
	/*
	 * Span of all CPUs in this domain.
	 *
	 * NOTE: this field is variable length. (Allocated dynamically
	 * by attaching extra space to the end of the structure,
	 * depending on how many CPUs the kernel has booted up with)
	 */
	unsigned long span[0];
};

static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
{
	return to_cpumask(sd->span);
}

extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
				    struct sched_domain_attr *dattr_new);

/* Allocate an array of sched domains, for partition_sched_domains(). */
cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);

/* Test a flag in parent sched domain */
static inline int test_sd_parent(struct sched_domain *sd, int flag)
{
	if (sd->parent && (sd->parent->flags & flag))
		return 1;

	return 0;
}

unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);

bool cpus_share_cache(int this_cpu, int that_cpu);

#else /* CONFIG_SMP */

struct sched_domain_attr;

static inline void
partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
			struct sched_domain_attr *dattr_new)
{
}

static inline bool cpus_share_cache(int this_cpu, int that_cpu)
{
	return true;
}

#endif	/* !CONFIG_SMP */


struct io_context;			/* See blkdev.h */


#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
extern void prefetch_stack(struct task_struct *t);
#else
static inline void prefetch_stack(struct task_struct *t) { }
#endif

struct audit_context;		/* See audit.c */
struct mempolicy;
struct pipe_inode_info;
struct uts_namespace;

struct rq;
struct sched_domain;

/*
 * wake flags
 */
#define WF_SYNC		0x01		/* waker goes to sleep after wakup */
#define WF_FORK		0x02		/* child wakeup after fork */
#define WF_MIGRATED	0x04		/* internal use, task got migrated */

#define ENQUEUE_WAKEUP		1
#define ENQUEUE_HEAD		2
#ifdef CONFIG_SMP
#define ENQUEUE_WAKING		4	/* sched_class::task_waking was called */
#else
#define ENQUEUE_WAKING		0
#endif

#define DEQUEUE_SLEEP		1

struct sched_class {
	const struct sched_class *next;

	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 (*yield_task) (struct rq *rq);
	bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);

	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);

	struct task_struct * (*pick_next_task) (struct rq *rq);
	void (*put_prev_task) (struct rq *rq, struct task_struct *p);

#ifdef CONFIG_SMP
	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);

	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
	void (*post_schedule) (struct rq *this_rq);
	void (*task_waking) (struct task_struct *task);
	void (*task_woken) (struct rq *this_rq, struct task_struct *task);

	void (*set_cpus_allowed)(struct task_struct *p,
				 const struct cpumask *newmask);

	void (*rq_online)(struct rq *rq);
	void (*rq_offline)(struct rq *rq);
#endif

	void (*set_curr_task) (struct rq *rq);
	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
	void (*task_fork) (struct task_struct *p);

	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
	void (*switched_to) (struct rq *this_rq, struct task_struct *task);
	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
			     int oldprio);

	unsigned int (*get_rr_interval) (struct rq *rq,
					 struct task_struct *task);

#ifdef CONFIG_FAIR_GROUP_SCHED
	void (*task_move_group) (struct task_struct *p, int on_rq);
#endif
};

struct load_weight {
	unsigned long weight, inv_weight;
};

#ifdef CONFIG_SCHEDSTATS
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;
};
#endif

struct sched_entity {
	struct load_weight	load;		/* for load-balancing */
	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;

#ifdef CONFIG_SCHEDSTATS
	struct sched_statistics statistics;
#endif

#ifdef CONFIG_FAIR_GROUP_SCHED
	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;
#endif
};

struct sched_rt_entity {
	struct list_head run_list;
	unsigned long timeout;
	unsigned int time_slice;
	int nr_cpus_allowed;

	struct sched_rt_entity *back;
#ifdef CONFIG_RT_GROUP_SCHED
	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;
#endif
};

/*
 * default timeslice is 100 msecs (used only for SCHED_RR tasks).
 * Timeslices get refilled after they expire.
 */
#define RR_TIMESLICE		(100 * HZ / 1000)

struct rcu_node;

enum perf_event_task_context {
	perf_invalid_context = -1,
	perf_hw_context = 0,
	perf_sw_context,
	perf_nr_task_contexts,
};

struct task_struct {
	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
	void *stack;
	atomic_t usage;
	unsigned int flags;	/* per process flags, defined below */
	unsigned int ptrace;

#ifdef CONFIG_SMP
	struct llist_node wake_entry;
	int on_cpu;
#endif
	int on_rq;

	int prio, static_prio, normal_prio;
	unsigned int rt_priority;
	const struct sched_class *sched_class;
	struct sched_entity se;
	struct sched_rt_entity rt;

#ifdef CONFIG_PREEMPT_NOTIFIERS
	/* list of struct preempt_notifier: */
	struct hlist_head preempt_notifiers;
#endif

	/*
	 * fpu_counter contains the number of consecutive context switches
	 * that the FPU is used. If this is over a threshold, the lazy fpu
	 * saving becomes unlazy to save the trap. This is an unsigned char
	 * so that after 256 times the counter wraps and the behavior turns
	 * lazy again; this to deal with bursty apps that only use FPU for
	 * a short time
	 */
	unsigned char fpu_counter;
#ifdef CONFIG_BLK_DEV_IO_TRACE
	unsigned int btrace_seq;
#endif

	unsigned int policy;
	cpumask_t cpus_allowed;

#ifdef CONFIG_PREEMPT_RCU
	int rcu_read_lock_nesting;
	char rcu_read_unlock_special;
	struct list_head rcu_node_entry;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TREE_PREEMPT_RCU
	struct rcu_node *rcu_blocked_node;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST
	struct rt_mutex *rcu_boost_mutex;
#endif /* #ifdef CONFIG_RCU_BOOST */

#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
	struct sched_info sched_info;
#endif

	struct list_head tasks;
#ifdef CONFIG_SMP
	struct plist_node pushable_tasks;
#endif

	struct mm_struct *mm, *active_mm;
#ifdef CONFIG_COMPAT_BRK
	unsigned brk_randomized:1;
#endif
#if defined(SPLIT_RSS_COUNTING)
	struct task_rss_stat	rss_stat;
#endif
/* task state */
	int exit_state;
	int exit_code, exit_signal;
	int pdeath_signal;  /*  The signal sent when the parent dies  */
	unsigned int jobctl;	/* JOBCTL_*, siglock protected */
	/* ??? */
	unsigned int personality;
	unsigned did_exec:1;
	unsigned in_execve:1;	/* Tell the LSMs that the process is doing an
				 * execve */
	unsigned in_iowait:1;


	/* Revert to default priority/policy when forking */
	unsigned sched_reset_on_fork:1;
	unsigned sched_contributes_to_load:1;

#ifdef CONFIG_GENERIC_HARDIRQS
	/* IRQ handler threads */
	unsigned irq_thread:1;
#endif

	pid_t pid;
	pid_t tgid;

#ifdef CONFIG_CC_STACKPROTECTOR
	/* Canary value for the -fstack-protector gcc feature */
	unsigned long stack_canary;
#endif

	/* 
	 * pointers to (original) parent process, youngest child, younger sibling,
	 * older sibling, respectively.  (p->father can be replaced with 
	 * p->real_parent->pid)
	 */
	struct task_struct __rcu *real_parent; /* real parent process */
	struct task_struct __rcu *parent; /* recipient of SIGCHLD, wait4() reports */
	/*
	 * children/sibling forms the list of my natural children
	 */
	struct list_head children;	/* list of my children */
	struct list_head sibling;	/* linkage in my parent's children list */
	struct task_struct *group_leader;	/* threadgroup leader */

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

	/* PID/PID hash table linkage. */
	struct pid_link pids[PIDTYPE_MAX];
	struct list_head thread_group;

	struct completion *vfork_done;		/* for vfork() */
	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */
	int __user *clear_child_tid;		/* CLONE_CHILD_CLEARTID */

	cputime_t utime, stime, utimescaled, stimescaled;
	cputime_t gtime;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
	cputime_t prev_utime, prev_stime;
#endif
	unsigned long nvcsw, nivcsw; /* context switch counts */
	struct timespec start_time; 		/* monotonic time */
	struct timespec real_start_time;	/* boot based time */
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
	unsigned long min_flt, maj_flt;

	struct task_cputime cputime_expires;
	struct list_head cpu_timers[3];

/* process credentials */
	const struct cred __rcu *real_cred; /* objective and real subjective task
					 * credentials (COW) */
	const struct cred __rcu *cred;	/* effective (overridable) subjective task
					 * credentials (COW) */
	struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */

	char comm[TASK_COMM_LEN]; /* executable name excluding path
				     - access with [gs]et_task_comm (which lock
				       it with task_lock())
				     - initialized normally by setup_new_exec */
/* file system info */
	int link_count, total_link_count;
#ifdef CONFIG_SYSVIPC
/* ipc stuff */
	struct sysv_sem sysvsem;
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
/* hung task detection */
	unsigned long last_switch_count;
#endif
/* CPU-specific state of this task */
	struct thread_struct thread;
/* 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, real_blocked;
	sigset_t saved_sigmask;	/* restored if set_restore_sigmask() was used */
	struct sigpending pending;

	unsigned long sas_ss_sp;
	size_t sas_ss_size;
	int (*notifier)(void *priv);
	void *notifier_data;
	sigset_t *notifier_mask;
	struct audit_context *audit_context;
#ifdef CONFIG_AUDITSYSCALL
	uid_t loginuid;
	unsigned int sessionid;
#endif
	seccomp_t seccomp;

/* Thread group tracking */
   	u32 parent_exec_id;
   	u32 self_exec_id;
/* Protection of (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;

#ifdef CONFIG_RT_MUTEXES
	/* PI waiters blocked on a rt_mutex held by this task */
	struct plist_head pi_waiters;
	/* Deadlock detection and priority inheritance handling */
	struct rt_mutex_waiter *pi_blocked_on;
#endif

#ifdef CONFIG_DEBUG_MUTEXES
	/* mutex deadlock detection */
	struct mutex_waiter *blocked_on;
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
	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;
#endif
#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH 48UL
	u64 curr_chain_key;
	int lockdep_depth;
	unsigned int lockdep_recursion;
	struct held_lock held_locks[MAX_LOCK_DEPTH];
	gfp_t lockdep_reclaim_gfp;
#endif

/* journalling filesystem info */
	void *journal_info;

/* stacked block device info */
	struct bio_list *bio_list;

#ifdef CONFIG_BLOCK
/* stack plugging */
	struct blk_plug *plug;
#endif

/* VM state */
	struct reclaim_state *reclaim_state;

	struct backing_dev_info *backing_dev_info;

	struct io_context *io_context;

	unsigned long ptrace_message;
	siginfo_t *last_siginfo; /* For ptrace use.  */
	struct task_io_accounting ioac;
#if defined(CONFIG_TASK_XACCT)
	u64 acct_rss_mem1;	/* accumulated rss usage */
	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
	cputime_t acct_timexpd;	/* stime + utime since last update */
#endif
#ifdef CONFIG_CPUSETS
	nodemask_t mems_allowed;	/* Protected by alloc_lock */
	seqcount_t mems_allowed_seq;	/* Seqence no to catch updates */
	int cpuset_mem_spread_rotor;
	int cpuset_slab_spread_rotor;
#endif
#ifdef CONFIG_CGROUPS
	/* 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;
#endif
#ifdef CONFIG_FUTEX
	struct robust_list_head __user *robust_list;
#ifdef CONFIG_COMPAT
	struct compat_robust_list_head __user *compat_robust_list;
#endif
	struct list_head pi_state_list;
	struct futex_pi_state *pi_state_cache;
#endif
#ifdef CONFIG_PERF_EVENTS
	struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
	struct mutex perf_event_mutex;
	struct list_head perf_event_list;
#endif
#ifdef CONFIG_NUMA
	struct mempolicy *mempolicy;	/* Protected by alloc_lock */
	short il_next;
	short pref_node_fork;
#endif
	struct rcu_head rcu;

	/*
	 * cache last used pipe for splice
	 */
	struct pipe_inode_info *splice_pipe;
#ifdef	CONFIG_TASK_DELAY_ACCT
	struct task_delay_info *delays;
#endif
#ifdef CONFIG_FAULT_INJECTION
	int make_it_fail;
#endif
	/*
	 * when (nr_dirtied >= nr_dirtied_pause), it's time to call
	 * balance_dirty_pages() for some dirty throttling pause
	 */
	int nr_dirtied;
	int nr_dirtied_pause;
	unsigned long dirty_paused_when; /* start of a write-and-pause period */

#ifdef CONFIG_LATENCYTOP
	int latency_record_count;
	struct latency_record latency_record[LT_SAVECOUNT];
#endif
	/*
	 * time slack values; these are used to round up poll() and
	 * select() etc timeout values. These are in nanoseconds.
	 */
	unsigned long timer_slack_ns;
	unsigned long default_timer_slack_ns;

	struct list_head	*scm_work_list;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
	/* 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;
	/* time stamp 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 for the tracing */
	atomic_t tracing_graph_pause;
#endif
#ifdef CONFIG_TRACING
	/* state flags for use by tracers */
	unsigned long trace;
	/* bitmask and counter of trace recursion */
	unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
#ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
	struct memcg_batch_info {
		int do_batch;	/* incremented when batch uncharge started */
		struct mem_cgroup *memcg; /* target memcg of uncharge */
		unsigned long nr_pages;	/* uncharged usage */
		unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
	} memcg_batch;
#endif
#ifdef CONFIG_HAVE_HW_BREAKPOINT
	atomic_t ptrace_bp_refcnt;
#endif
};

/* Future-safe accessor for struct task_struct's cpus_allowed. */
#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)

/*
 * Priority of a process goes from 0..MAX_PRIO-1, valid RT
 * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
 * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
 * values are inverted: lower p->prio value means higher priority.
 *
 * The MAX_USER_RT_PRIO value allows the actual maximum
 * RT priority to be separate from the value exported to
 * user-space.  This allows kernel threads to set their
 * priority to a value higher than any user task. Note:
 * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
 */

#define MAX_USER_RT_PRIO	100
#define MAX_RT_PRIO		MAX_USER_RT_PRIO

#define MAX_PRIO		(MAX_RT_PRIO + 40)
#define DEFAULT_PRIO		(MAX_RT_PRIO + 20)

static inline int rt_prio(int prio)
{
	if (unlikely(prio < MAX_RT_PRIO))
		return 1;
	return 0;
}

static inline int rt_task(struct task_struct *p)
{
	return rt_prio(p->prio);
}

static inline struct pid *task_pid(struct task_struct *task)
{
	return task->pids[PIDTYPE_PID].pid;
}

static inline struct pid *task_tgid(struct task_struct *task)
{
	return task->group_leader->pids[PIDTYPE_PID].pid;
}

/*
 * Without tasklist or rcu lock it is not safe to dereference
 * the result of task_pgrp/task_session even if task == current,
 * we can race with another thread doing sys_setsid/sys_setpgid.
 */
static inline struct pid *task_pgrp(struct task_struct *task)
{
	r…

Large files files are truncated, but you can click here to view the full file