#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H

#include <uapi/linux/sched.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/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_mask.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 <linux/uidgid.h>
#include <linux/gfp.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_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 void update_cpu_load_nohz(void);

extern unsigned long get_parent_ip(unsigned long addr);

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);
extern 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_PARKED             512
#define TASK_STATE_MAX          1024

#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"

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_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);

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
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);
asmlinkage void schedule(void);
extern void schedule_preempt_disabled(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


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

#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 */
/* 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_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_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 cputime - snaphsot of system and user cputime
 * @utime: time spent in user mode
 * @stime: time spent in system mode
 *
 * Gathers a generic snapshot of user and system time.
 */
struct cputime {
        cputime_t utime;
        cputime_t stime;
};

/**
 * 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 is an extension of struct cputime that includes the total runtime
 * spent by the task from the scheduler point of view.
 *
 * As a result, 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,                          \
        }

#ifdef CONFIG_PREEMPT_COUNT
#define PREEMPT_DISABLED        (1 + PREEMPT_ENABLED)
#else
#define PREEMPT_DISABLED        PREEMPT_ENABLED
#endif

/*
 * 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      (PREEMPT_DISABLED + 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 */
        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;

        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_NATIVE
        struct cputime prev_cputime;
#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;
        unsigned audit_tty_log_passwd;
        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

        oom_flags_t oom_flags;
        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 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 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;
        kuid_t uid;

#ifdef CONFIG_PERF_EVENTS
        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;

#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 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_SHARE_CPUPOWER       0x0080  /* Domain members share cpu power */
#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 */

extern int __weak arch_sd_sibiling_asym_packing(void);

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 {
        /* 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;

#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);

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 load_weight {
        unsigned long weight;
        u32 inv_weight;
};

struct sched_avg {
        /*
         * These sums represent an infinite geometric series and so are bound
         * above by 1024/(1-y).  Thus we only need a u32 to store them for all
         * choices of y < 1-2^(-32)*1024.
         */
        u32 runnable_avg_sum, runnable_avg_period;
        u64 last_runnable_update;
        s64 decay_count;
        unsigned long load_avg_contrib;
};

#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

#ifdef CONFIG_SMP
        /* Per-entity load-tracking */
        struct sched_avg        avg;
#endif
};

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

        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
};


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;
        struct task_struct *last_wakee;
        unsigned long wakee_flips;
        unsigned long wakee_flip_decay_ts;

        int wake_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_CGROUP_SCHED
        struct task_group *sched_task_group;
#endif

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

#ifdef CONFIG_BLK_DEV_IO_TRACE
        unsigned int btrace_seq;
#endif

        unsigned int policy;
        int nr_cpus_allowed;
        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 */

        /* Used for emulating ABI behavior of previous Linux versions */
        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;

        /* task may not gain privileges */
        unsigned no_new_privs:1;

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

        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_NATIVE
        struct cputime prev_cputime;
#endif
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
        seqlock_t vtime_seqlock;
        unsigned long long vtime_snap;
        enum {
                VTIME_SLEEPING = 0,
                VTIME_USER,
                VTIME_SYS,
        } vtime_snap_whence;
#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) */
        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 callback_head *task_works;

        struct audit_context *audit_context;
#ifdef CONFIG_AUDITSYSCALL
        kuid_t loginuid;
        unsigned int sessionid;
#endif
        struct seccomp 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
#ifdef CONFIG_NUMA_BALANCING
        int numa_scan_seq;
        unsigned int numa_scan_period;
        unsigned int numa_scan_period_max;
        int numa_preferred_nid;
        int numa_migrate_deferred;
        unsigned long numa_migrate_retry;
        u64 node_stamp;                 /* migration stamp  */
        struct callback_head numa_work;

        struct list_head numa_entry;
        struct numa_group *numa_group;

        /*
         * Exponential decaying average of faults on a per-node basis.
         * Scheduling placement decisions are made based on the these counts.
         * The values remain static for the duration of a PTE scan
         */
        unsigned long *numa_faults;
        unsigned long total_numa_faults;

        /*
         * numa_faults_buffer records faults per node during the current
         * scan window. When the scan completes, the counts in numa_faults
         * decay and these values are copied.
         */
        unsigned long *numa_faults_buffer;

        /*
         * numa_faults_locality tracks if faults recorded during the last
         * scan window were remote/local. 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[2];

        unsigned long numa_pages_migrated;
#endif /* CONFIG_NUMA_BALANCING */

        struct rcu_head rcu;

        /*
         * cache last used pipe for splice
         */
        struct pipe_inode_info *splice_pipe;

        struct page_frag task_frag;

#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;

#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_MEMCG /* 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;
        unsigned int memcg_kmem_skip_account;
        struct memcg_oom_info {
                struct mem_cgroup *memcg;
                gfp_t gfp_mask;
                int order;
                unsigned int may_oom:1;
        } memcg_oom;
#endif
#ifdef CONFIG_UPROBES
        struct uprobe_task *utask;
#endif
#if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE)
        unsigned int    sequential_io;
        unsigned int    sequential_io_avg;
#endif
};

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

#define TNF_MIGRATED    0x01
#define TNF_NO_GROUP    0x02
#define TNF_SHARED      0x04
#define TNF_FAULT_LOCAL 0x08

#ifdef CONFIG_NUMA_BALANCING
extern void task_numa_fault(int last_node, int node, int pages, int flags);
extern pid_t task_numa_group_id(struct task_struct *p);
extern void set_numabalancing_state(bool enabled);
extern void task_numa_free(struct task_struct *p);

extern unsigned int sysctl_numa_balancing_migrate_deferred;
#else
static inline void task_numa_fault(int last_node, int node, int pages,
                                   int flags)
{
}
static inline pid_t task_numa_group_id(struct task_struct *p)
{
        return 0;
}
static inline void set_numabalancing_state(bool enabled)
{
}
static inline void task_numa_free(struct task_struct *p)
{
}
#endif

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)
{
        return task->group_leader->pids[PIDTYPE_PGID].pid;
}

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

struct pid_namespace;

/*
 * 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;
 *
 * set_task_vxid()   : assigns a virtual id to a task;
 *
 * 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_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);

static inline pid_t task_tgid_vnr(struct task_struct *tsk)
{
        return pid_vnr(task_tgid(tsk));
}


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);
}

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

/**
 * 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(struct task_struct *p)
{
        return p->pids[PIDTYPE_PID].pid != NULL;
}

/**
 * is_global_init - check if a task structure is init
 * @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 tsk->pid == 1;
}

extern struct pid *cad_pid;

extern void free_task(struct task_struct *tsk);
#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)

extern void __put_task_struct(struct task_struct *t);

static inline void put_task_struct(struct task_struct *t)
{
        if (atomic_dec_and_test(&t->usage))
                __put_task_struct(t);
}

#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
extern void task_cputime(struct task_struct *t,
                         cputime_t *utime, cputime_t *stime);
extern void task_cputime_scaled(struct task_struct *t,
                                cputime_t *utimescaled, cputime_t *stimescaled);
extern cputime_t task_gtime(struct task_struct *t);
#else
static inline void task_cputime(struct task_struct *t,
                                cputime_t *utime, cputime_t *stime)
{
        if (utime)
                *utime = t->utime;
        if (stime)
                *stime = t->stime;
}

static inline void task_cputime_scaled(struct task_struct *t,
                                       cputime_t *utimescaled,
                                       cputime_t *stimescaled)
{
        if (utimescaled)
                *utimescaled = t->utimescaled;
        if (stimescaled)
                *stimescaled = t->stimescaled;
}

static inline cputime_t task_gtime(struct task_struct *t)
{
        return t->gtime;
}
#endif
extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);

/*
 * Per process flags
 */
#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_FSTRANS      0x00020000      /* inside a filesystem transaction */
#define PF_KSWAPD       0x00040000      /* I am kswapd */
#define PF_MEMALLOC_NOIO 0x00080000     /* Allocating memory without IO involved */
#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_SPREAD_PAGE  0x01000000      /* Spread page cache over cpuset */
#define PF_SPREAD_SLAB  0x02000000      /* Spread some slab caches over cpuset */
#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_MEMPOLICY    0x10000000      /* Non-default NUMA mempolicy */
#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)

/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */
static inline gfp_t memalloc_noio_flags(gfp_t flags)
{
        if (unlikely(current->flags & PF_MEMALLOC_NOIO))
                flags &= ~__GFP_IO;
        return flags;
}

static inline unsigned int memalloc_noio_save(void)
{
        unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
        current->flags |= PF_MEMALLOC_NOIO;
        return flags;
}

static inline void memalloc_noio_restore(unsigned int flags)
{
        current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
}

/*
 * task->jobctl flags
 */
#define JOBCTL_STOP_SIGMASK     0xffff  /* signr of the last group stop */

#define JOBCTL_STOP_DEQUEUED_BIT 16     /* stop signal dequeued */
#define JOBCTL_STOP_PENDING_BIT 17      /* task should stop for group stop */
#define JOBCTL_STOP_CONSUME_BIT 18      /* consume group stop count */
#define JOBCTL_TRAP_STOP_BIT    19      /* trap for STOP */
#define JOBCTL_TRAP_NOTIFY_BIT  20      /* trap for NOTIFY */
#define JOBCTL_TRAPPING_BIT     21      /* switching to TRACED */
#define JOBCTL_LISTENING_BIT    22      /* ptracer is listening for events */

#define JOBCTL_STOP_DEQUEUED    (1 << JOBCTL_STOP_DEQUEUED_BIT)
#define JOBCTL_STOP_PENDING     (1 << JOBCTL_STOP_PENDING_BIT)
#define JOBCTL_STOP_CONSUME     (1 << JOBCTL_STOP_CONSUME_BIT)
#define JOBCTL_TRAP_STOP        (1 << JOBCTL_TRAP_STOP_BIT)
#define JOBCTL_TRAP_NOTIFY      (1 << JOBCTL_TRAP_NOTIFY_BIT)
#define JOBCTL_TRAPPING         (1 << JOBCTL_TRAPPING_BIT)
#define JOBCTL_LISTENING        (1 << JOBCTL_LISTENING_BIT)

#define JOBCTL_TRAP_MASK        (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
#define JOBCTL_PENDING_MASK     (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)

extern bool task_set_jobctl_pending(struct task_struct *task,
                                    unsigned int mask);
extern void task_clear_jobctl_trapping(struct task_struct *task);
extern void task_clear_jobctl_pending(struct task_struct *task,
                                      unsigned int mask);

#ifdef CONFIG_PREEMPT_RCU

#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */

static inline void rcu_copy_process(struct task_struct *p)
{
        p->rcu_read_lock_nesting = 0;
        p->rcu_read_unlock_special = 0;
#ifdef CONFIG_TREE_PREEMPT_RCU
        p->rcu_blocked_node = NULL;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST
        p->rcu_boost_mutex = NULL;
#endif /* #ifdef CONFIG_RCU_BOOST */
        INIT_LIST_HEAD(&p->rcu_node_entry);
}

#else

static inline void rcu_copy_process(struct task_struct *p)
{
}

#endif

static inline void tsk_restore_flags(struct task_struct *task,
                                unsigned long orig_flags, unsigned long flags)
{
        task->flags &= ~flags;
        task->flags |= orig_flags & flags;
}

#ifdef CONFIG_SMP
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);
#else
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;
}
#endif

#ifdef CONFIG_NO_HZ_COMMON
void calc_load_enter_idle(void);
void calc_load_exit_idle(void);
#else
static inline void calc_load_enter_idle(void) { }
static inline void calc_load_exit_idle(void) { }
#endif /* CONFIG_NO_HZ_COMMON */

#ifndef CONFIG_CPUMASK_OFFSTACK
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
{
        return set_cpus_allowed_ptr(p, &new_mask);
}
#endif

/*
 * Do not use outside of architecture code which knows its limitations.
 *
 * sched_clock() has no promise of monotonicity or bounded drift between
 * CPUs, use (which you should not) requires disabling IRQs.
 *
 * Please use one of the three interfaces below.
 */
extern unsigned long long notrace sched_clock(void);
/*
 * See the comment in kernel/sched/clock.c
 */
extern u64 cpu_clock(int cpu);
extern u64 local_clock(void);
extern u64 sched_clock_cpu(int cpu);


extern void sched_clock_init(void);

#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
static inline void sched_clock_tick(void)
{
}

static inline void sched_clock_idle_sleep_event(void)
{
}

static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
{
}
#else
/*
 * Architectures can set this to 1 if they have specified
 * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
 * but then during bootup it turns out that sched_clock()
 * is reliable after all:
 */
extern int sched_clock_stable;

extern void sched_clock_tick(void);
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
#endif

#ifdef CONFIG_IRQ_TIME_ACCOUNTING
/*
 * An i/f to runtime opt-in for irq time accounting based off of sched_clock.
 * The reason for this explicit opt-in is not to have perf penalty with
 * slow sched_clocks.
 */
extern void enable_sched_clock_irqtime(void);
extern void disable_sched_clock_irqtime(void);
#else
static inline void enable_sched_clock_irqtime(void) {}
static inline void disable_sched_clock_irqtime(void) {}
#endif

extern unsigned long long
task_sched_runtime(struct task_struct *task);

/* sched_exec is called by processes performing an exec */
#ifdef CONFIG_SMP
extern void sched_exec(void);
#else
#define sched_exec()   {}
#endif

extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);

#ifdef CONFIG_HOTPLUG_CPU
extern void idle_task_exit(void);
#else
static inline void idle_task_exit(void) {}
#endif

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

#ifdef CONFIG_NO_HZ_FULL
extern bool sched_can_stop_tick(void);
extern u64 scheduler_tick_max_deferment(void);
#else
static inline bool sched_can_stop_tick(void) { return false; }
#endif

#ifdef CONFIG_SCHED_AUTOGROUP
extern void sched_autogroup_create_attach(struct task_struct *p);
extern void sched_autogroup_detach(struct task_struct *p);
extern void sched_autogroup_fork(struct signal_struct *sig);
extern void sched_autogroup_exit(struct signal_struct *sig);
#ifdef CONFIG_PROC_FS
extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m);
extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice);
#endif
#else
static inline void sched_autogroup_create_attach(struct task_struct *p) { }
static inline void sched_autogroup_detach(struct task_struct *p) { }
static inline void sched_autogroup_fork(struct signal_struct *sig) { }
static inline void sched_autogroup_exit(struct signal_struct *sig) { }
#endif

extern bool 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);
extern int task_nice(const struct task_struct *p);
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 sched_setscheduler(struct task_struct *, int,
                              const struct sched_param *);
extern int sched_setscheduler_nocheck(struct task_struct *, int,
                                      const struct sched_param *);
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->pid == 0;
}
extern struct task_struct *curr_task(int cpu);
extern void set_curr_task(int cpu, struct task_struct *p);

void yield(void);

/*
 * The default (Linux) execution domain.
 */
extern struct exec_domain       default_exec_domain;

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

#ifndef __HAVE_ARCH_KSTACK_END
static inline int kstack_end(void *addr)
{
        /* Reliable end of stack detection:
         * Some APM bios versions misalign the stack
         */
        return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*)));
}
#endif

extern union thread_union init_thread_union;
extern struct task_struct init_task;