user namespace: add the framework

[net-next-2.6.git] / include / linux / sched.h

#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H

#include <linux/auxvec.h>       /* For AT_VECTOR_SIZE */

/*
 * 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 */
#define CLONE_STOPPED           0x02000000      /* Start in stopped state */
#define CLONE_NEWUTS            0x04000000      /* New utsname group? */
#define CLONE_NEWIPC            0x08000000      /* New ipcs */

/*
 * 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

#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 <asm/system.h>
#include <asm/semaphore.h>
#include <asm/page.h>
#include <asm/ptrace.h>
#include <asm/mmu.h>
#include <asm/cputime.h>

#include <linux/smp.h>
#include <linux/sem.h>
#include <linux/signal.h>
#include <linux/securebits.h>
#include <linux/fs_struct.h>
#include <linux/compiler.h>
#include <linux/completion.h>
#include <linux/pid.h>
#include <linux/percpu.h>
#include <linux/topology.h>
#include <linux/seccomp.h>
#include <linux/rcupdate.h>
#include <linux/futex.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 <asm/processor.h>

struct exec_domain;
struct futex_pi_state;
struct bio;

/*
 * 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 */

#define FSHIFT          11              /* nr of bits of precision */
#define FIXED_1         (1<<FSHIFT)     /* 1.0 as fixed-point */
#define LOAD_FREQ       (5*HZ)          /* 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_active(void);
extern unsigned long nr_iowait(void);
extern unsigned long weighted_cpuload(const int cpu);

struct seq_file;
struct cfs_rq;
#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, u64 now);
#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, u64 now)
{
}
#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_NONINTERACTIVE     64
#define TASK_DEAD               128

#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;

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

extern cpumask_t nohz_cpu_mask;
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
extern int select_nohz_load_balancer(int cpu);
#else
static inline int select_nohz_load_balancer(int cpu)
{
        return 0;
}
#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);

#ifdef CONFIG_DETECT_SOFTLOCKUP
extern void softlockup_tick(void);
extern void spawn_softlockup_task(void);
extern void touch_softlockup_watchdog(void);
extern void touch_all_softlockup_watchdogs(void);
#else
static inline void softlockup_tick(void)
{
}
static inline void spawn_softlockup_task(void)
{
}
static inline void touch_softlockup_watchdog(void)
{
}
static inline void touch_all_softlockup_watchdogs(void)
{
}
#endif


/* Attach to any functions which should be ignored in wchan output. */
#define __sched         __attribute__((__section__(".sched.text")))
/* Is this address in the __sched functions? */
extern int in_sched_functions(unsigned long addr);

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

struct nsproxy;
struct user_namespace;

/* Maximum number of active map areas.. This is a random (large) number */
#define DEFAULT_MAX_MAP_COUNT   65536

extern int sysctl_max_map_count;

#include <linux/aio.h>

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);

#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
/*
 * The mm counters are not protected by its page_table_lock,
 * so must be incremented atomically.
 */
#define set_mm_counter(mm, member, value) atomic_long_set(&(mm)->_##member, value)
#define get_mm_counter(mm, member) ((unsigned long)atomic_long_read(&(mm)->_##member))
#define add_mm_counter(mm, member, value) atomic_long_add(value, &(mm)->_##member)
#define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member)
#define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member)
typedef atomic_long_t mm_counter_t;

#else  /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
/*
 * The mm counters are protected by its page_table_lock,
 * so can be incremented directly.
 */
#define set_mm_counter(mm, member, value) (mm)->_##member = (value)
#define get_mm_counter(mm, member) ((mm)->_##member)
#define add_mm_counter(mm, member, value) (mm)->_##member += (value)
#define inc_mm_counter(mm, member) (mm)->_##member++
#define dec_mm_counter(mm, member) (mm)->_##member--
typedef unsigned long mm_counter_t;

#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */

#define get_mm_rss(mm)                                  \
        (get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
#define update_hiwater_rss(mm)  do {                    \
        unsigned long _rss = get_mm_rss(mm);            \
        if ((mm)->hiwater_rss < _rss)                   \
                (mm)->hiwater_rss = _rss;               \
} while (0)
#define update_hiwater_vm(mm)   do {                    \
        if ((mm)->hiwater_vm < (mm)->total_vm)          \
                (mm)->hiwater_vm = (mm)->total_vm;      \
} while (0)

struct mm_struct {
        struct vm_area_struct * mmap;           /* list of VMAs */
        struct rb_root mm_rb;
        struct vm_area_struct * mmap_cache;     /* last find_vma result */
        unsigned long (*get_unmapped_area) (struct file *filp,
                                unsigned long addr, unsigned long len,
                                unsigned long pgoff, unsigned long flags);
        void (*unmap_area) (struct mm_struct *mm, unsigned long addr);
        unsigned long mmap_base;                /* base of mmap area */
        unsigned long task_size;                /* size of task vm space */
        unsigned long cached_hole_size;         /* if non-zero, the largest hole below free_area_cache */
        unsigned long free_area_cache;          /* first hole of size cached_hole_size or larger */
        pgd_t * pgd;
        atomic_t mm_users;                      /* How many users with user space? */
        atomic_t mm_count;                      /* How many references to "struct mm_struct" (users count as 1) */
        int map_count;                          /* number of VMAs */
        struct rw_semaphore mmap_sem;
        spinlock_t page_table_lock;             /* Protects page tables and some counters */

        struct list_head mmlist;                /* List of maybe swapped mm's.  These are globally strung
                                                 * together off init_mm.mmlist, and are protected
                                                 * by mmlist_lock
                                                 */

        /* Special counters, in some configurations protected by the
         * page_table_lock, in other configurations by being atomic.
         */
        mm_counter_t _file_rss;
        mm_counter_t _anon_rss;

        unsigned long hiwater_rss;      /* High-watermark of RSS usage */
        unsigned long hiwater_vm;       /* High-water virtual memory usage */

        unsigned long total_vm, locked_vm, shared_vm, exec_vm;
        unsigned long stack_vm, reserved_vm, def_flags, nr_ptes;
        unsigned long start_code, end_code, start_data, end_data;
        unsigned long start_brk, brk, start_stack;
        unsigned long arg_start, arg_end, env_start, env_end;

        unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */

        cpumask_t cpu_vm_mask;

        /* Architecture-specific MM context */
        mm_context_t context;

        /* Swap token stuff */
        /*
         * Last value of global fault stamp as seen by this process.
         * In other words, this value gives an indication of how long
         * it has been since this task got the token.
         * Look at mm/thrash.c
         */
        unsigned int faultstamp;
        unsigned int token_priority;
        unsigned int last_interval;

        unsigned char dumpable:2;

        /* coredumping support */
        int core_waiters;
        struct completion *core_startup_done, core_done;

        /* aio bits */
        rwlock_t                ioctx_list_lock;
        struct kioctx           *ioctx_list;
};

struct sighand_struct {
        atomic_t                count;
        struct k_sigaction      action[_NSIG];
        spinlock_t              siglock;
        struct list_head        signalfd_list;
};

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;
};

/*
 * NOTE! "signal_struct" does not have it's 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                count;
        atomic_t                live;

        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.
         */
        struct task_struct      *group_exit_task;
        int                     notify_count;

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

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

        /* ITIMER_REAL timer for the process */
        struct hrtimer real_timer;
        struct task_struct *tsk;
        ktime_t it_real_incr;

        /* ITIMER_PROF and ITIMER_VIRTUAL timers for the process */
        cputime_t it_prof_expires, it_virt_expires;
        cputime_t it_prof_incr, it_virt_incr;

        /* job control IDs */
        pid_t pgrp;
        struct pid *tty_old_pgrp;

        union {
                pid_t session __deprecated;
                pid_t __session;
        };

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

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

        /*
         * 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;
        unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
        unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
        unsigned long inblock, oublock, cinblock, coublock;

        /*
         * Cumulative ns of scheduled CPU time for 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];

        struct list_head cpu_timers[3];

        /* keep the process-shared keyrings here so that they do the right
         * thing in threads created with CLONE_THREAD */
#ifdef CONFIG_KEYS
        struct key *session_keyring;    /* keyring inherited over fork */
        struct key *process_keyring;    /* keyring private to this process */
#endif
#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
};

/* 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_DEQUEUED    0x00000002 /* stop signal dequeued */
#define SIGNAL_STOP_CONTINUED   0x00000004 /* SIGCONT since WCONTINUED reap */
#define SIGNAL_GROUP_EXIT       0x00000008 /* group exit in progress */

/*
 * 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
        /* protected by mq_lock */
        unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */
        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 list_head uidhash_list;
        uid_t uid;
};

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 pcnt;           /* # of times run on this cpu */
        unsigned long long cpu_time,  /* time spent on the cpu */
                           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_SCHEDSTATS
extern const struct file_operations proc_schedstat_operations;
#endif /* CONFIG_SCHEDSTATS */

#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 */
};
#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
};

/*
 * sched-domains (multiprocessor balancing) declarations:
 */

/*
 * Increase resolution of nice-level calculations:
 */
#define SCHED_LOAD_SHIFT        10
#define SCHED_LOAD_SCALE        (1L << SCHED_LOAD_SHIFT)

#define SCHED_LOAD_SCALE_FUZZ   (SCHED_LOAD_SCALE >> 5)

#ifdef CONFIG_SMP
#define SD_LOAD_BALANCE         1       /* Do load balancing on this domain. */
#define SD_BALANCE_NEWIDLE      2       /* Balance when about to become idle */
#define SD_BALANCE_EXEC         4       /* Balance on exec */
#define SD_BALANCE_FORK         8       /* Balance on fork, clone */
#define SD_WAKE_IDLE            16      /* Wake to idle CPU on task wakeup */
#define SD_WAKE_AFFINE          32      /* Wake task to waking CPU */
#define SD_WAKE_BALANCE         64      /* Perform balancing at task wakeup */
#define SD_SHARE_CPUPOWER       128     /* Domain members share cpu power */
#define SD_POWERSAVINGS_BALANCE 256     /* Balance for power savings */
#define SD_SHARE_PKG_RESOURCES  512     /* Domain members share cpu pkg resources */
#define SD_SERIALIZE            1024    /* Only a single load balancing instance */

#define BALANCE_FOR_MC_POWER    \
        (sched_smt_power_savings ? SD_POWERSAVINGS_BALANCE : 0)

#define BALANCE_FOR_PKG_POWER   \
        ((sched_mc_power_savings || sched_smt_power_savings) ?  \
         SD_POWERSAVINGS_BALANCE : 0)

#define test_sd_parent(sd, flag)        ((sd->parent &&         \
                                         (sd->parent->flags & flag)) ? 1 : 0)


struct sched_group {
        struct sched_group *next;       /* Must be a circular list */
        cpumask_t cpumask;

        /*
         * CPU power of this group, SCHED_LOAD_SCALE being max power for a
         * single CPU. This is read only (except for setup, hotplug CPU).
         * Note : Never change cpu_power without recompute its reciprocal
         */
        unsigned int __cpu_power;
        /*
         * reciprocal value of cpu_power to avoid expensive divides
         * (see include/linux/reciprocal_div.h)
         */
        u32 reciprocal_cpu_power;
};

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 */
        cpumask_t span;                 /* span of all CPUs in this 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 long long cache_hot_time; /* Task considered cache hot (ns) */
        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;
        int flags;                      /* See SD_* */

        /* 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 */

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

        /* Active load balancing */
        unsigned long alb_cnt;
        unsigned long alb_failed;
        unsigned long alb_pushed;

        /* SD_BALANCE_EXEC stats */
        unsigned long sbe_cnt;
        unsigned long sbe_balanced;
        unsigned long sbe_pushed;

        /* SD_BALANCE_FORK stats */
        unsigned long sbf_cnt;
        unsigned long sbf_balanced;
        unsigned long sbf_pushed;

        /* try_to_wake_up() stats */
        unsigned long ttwu_wake_remote;
        unsigned long ttwu_move_affine;
        unsigned long ttwu_move_balance;
#endif
};

extern int partition_sched_domains(cpumask_t *partition1,
                                    cpumask_t *partition2);

#endif  /* CONFIG_SMP */


struct io_context;                      /* See blkdev.h */
struct cpuset;

#define NGROUPS_SMALL           32
#define NGROUPS_PER_BLOCK       ((int)(PAGE_SIZE / sizeof(gid_t)))
struct group_info {
        int ngroups;
        atomic_t usage;
        gid_t small_block[NGROUPS_SMALL];
        int nblocks;
        gid_t *blocks[0];
};

/*
 * get_group_info() must be called with the owning task locked (via task_lock())
 * when task != current.  The reason being that the vast majority of callers are
 * looking at current->group_info, which can not be changed except by the
 * current task.  Changing current->group_info requires the task lock, too.
 */
#define get_group_info(group_info) do { \
        atomic_inc(&(group_info)->usage); \
} while (0)

#define put_group_info(group_info) do { \
        if (atomic_dec_and_test(&(group_info)->usage)) \
                groups_free(group_info); \
} while (0)

extern struct group_info *groups_alloc(int gidsetsize);
extern void groups_free(struct group_info *group_info);
extern int set_current_groups(struct group_info *group_info);
extern int groups_search(struct group_info *group_info, gid_t grp);
/* access the groups "array" with this macro */
#define GROUP_AT(gi, i) \
    ((gi)->blocks[(i)/NGROUPS_PER_BLOCK][(i)%NGROUPS_PER_BLOCK])

#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;

struct sched_class {
        struct sched_class *next;

        void (*enqueue_task) (struct rq *rq, struct task_struct *p,
                              int wakeup, u64 now);
        void (*dequeue_task) (struct rq *rq, struct task_struct *p,
                              int sleep, u64 now);
        void (*yield_task) (struct rq *rq, struct task_struct *p);

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

        struct task_struct * (*pick_next_task) (struct rq *rq, u64 now);
        void (*put_prev_task) (struct rq *rq, struct task_struct *p, u64 now);

        int (*load_balance) (struct rq *this_rq, int this_cpu,
                        struct rq *busiest,
                        unsigned long max_nr_move, unsigned long max_load_move,
                        struct sched_domain *sd, enum cpu_idle_type idle,
                        int *all_pinned, unsigned long *total_load_moved);

        void (*set_curr_task) (struct rq *rq);
        void (*task_tick) (struct rq *rq, struct task_struct *p);
        void (*task_new) (struct rq *rq, struct task_struct *p);
};

struct load_weight {
        unsigned long weight, inv_weight;
};

/*
 * CFS stats for a schedulable entity (task, task-group etc)
 *
 * Current field usage histogram:
 *
 *     4 se->block_start
 *     4 se->run_node
 *     4 se->sleep_start
 *     4 se->sleep_start_fair
 *     6 se->load.weight
 *     7 se->delta_fair
 *    15 se->wait_runtime
 */
struct sched_entity {
        long                    wait_runtime;
        unsigned long           delta_fair_run;
        unsigned long           delta_fair_sleep;
        unsigned long           delta_exec;
        s64                     fair_key;
        struct load_weight      load;           /* for load-balancing */
        struct rb_node          run_node;
        unsigned int            on_rq;

        u64                     wait_start_fair;
        u64                     wait_start;
        u64                     exec_start;
        u64                     sleep_start;
        u64                     sleep_start_fair;
        u64                     block_start;
        u64                     sleep_max;
        u64                     block_max;
        u64                     exec_max;
        u64                     wait_max;
        u64                     last_ran;

        u64                     sum_exec_runtime;
        s64                     sum_wait_runtime;
        s64                     sum_sleep_runtime;
        unsigned long           wait_runtime_overruns;
        unsigned long           wait_runtime_underruns;
#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 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;

        int lock_depth;         /* BKL lock depth */

#ifdef CONFIG_SMP
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
        int oncpu;
#endif
#endif

        int prio, static_prio, normal_prio;
        struct list_head run_list;
        struct sched_class *sched_class;
        struct sched_entity se;

        unsigned short ioprio;
#ifdef CONFIG_BLK_DEV_IO_TRACE
        unsigned int btrace_seq;
#endif

        unsigned int policy;
        cpumask_t cpus_allowed;
        unsigned int time_slice;

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

        struct list_head tasks;
        /*
         * ptrace_list/ptrace_children forms the list of my children
         * that were stolen by a ptracer.
         */
        struct list_head ptrace_children;
        struct list_head ptrace_list;

        struct mm_struct *mm, *active_mm;

/* task state */
        struct linux_binfmt *binfmt;
        int exit_state;
        int exit_code, exit_signal;
        int pdeath_signal;  /*  The signal sent when the parent dies  */
        /* ??? */
        unsigned int personality;
        unsigned did_exec: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->parent->pid)
         */
        struct task_struct *real_parent; /* real parent process (when being debugged) */
        struct task_struct *parent;     /* parent process */
        /*
         * children/sibling forms the list of my children plus the
         * tasks I'm ptracing.
         */
        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 */

        /* 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 */

        unsigned int rt_priority;
        cputime_t utime, stime;
        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;

        cputime_t it_prof_expires, it_virt_expires;
        unsigned long long it_sched_expires;
        struct list_head cpu_timers[3];

/* process credentials */
        uid_t uid,euid,suid,fsuid;
        gid_t gid,egid,sgid,fsgid;
        struct group_info *group_info;
        kernel_cap_t   cap_effective, cap_inheritable, cap_permitted;
        unsigned keep_capabilities:1;
        struct user_struct *user;
#ifdef CONFIG_KEYS
        struct key *request_key_auth;   /* assumed request_key authority */
        struct key *thread_keyring;     /* keyring private to this thread */
        unsigned char jit_keyring;      /* default keyring to attach requested keys to */
#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;
        int oomkilladj; /* OOM kill score adjustment (bit shift). */
        char comm[TASK_COMM_LEN]; /* executable name excluding path
                                     - access with [gs]et_task_comm (which lock
                                       it with task_lock())
                                     - initialized normally by flush_old_exec */
/* file system info */
        int link_count, total_link_count;
#ifdef CONFIG_SYSVIPC
/* ipc stuff */
        struct sysv_sem sysvsem;
#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;         /* To be restored with TIF_RESTORE_SIGMASK */
        struct sigpending pending;

        unsigned long sas_ss_sp;
        size_t sas_ss_size;
        int (*notifier)(void *priv);
        void *notifier_data;
        sigset_t *notifier_mask;
        
        void *security;
        struct audit_context *audit_context;
        seccomp_t seccomp;

/* Thread group tracking */
        u32 parent_exec_id;
        u32 self_exec_id;
/* Protection of (de-)allocation: mm, files, fs, tty, keyrings */
        spinlock_t alloc_lock;

        /* Protection of the PI data structures: */
        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;
        int hardirqs_enabled;
        unsigned long hardirq_enable_ip;
        unsigned int hardirq_enable_event;
        unsigned long hardirq_disable_ip;
        unsigned int hardirq_disable_event;
        int softirqs_enabled;
        unsigned long softirq_disable_ip;
        unsigned int softirq_disable_event;
        unsigned long softirq_enable_ip;
        unsigned int softirq_enable_event;
        int hardirq_context;
        int softirq_context;
#endif
#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH 30UL
        u64 curr_chain_key;
        int lockdep_depth;
        struct held_lock held_locks[MAX_LOCK_DEPTH];
        unsigned int lockdep_recursion;
#endif

/* journalling filesystem info */
        void *journal_info;

/* stacked block device info */
        struct bio *bio_list, **bio_tail;

/* 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.  */
/*
 * current io wait handle: wait queue entry to use for io waits
 * If this thread is processing aio, this points at the waitqueue
 * inside the currently handled kiocb. It may be NULL (i.e. default
 * to a stack based synchronous wait) if its doing sync IO.
 */
        wait_queue_t *io_wait;
#ifdef CONFIG_TASK_XACCT
/* i/o counters(bytes read/written, #syscalls */
        u64 rchar, wchar, syscr, syscw;
#endif
        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_stimexpd;/* stime since last update */
#endif
#ifdef CONFIG_NUMA
        struct mempolicy *mempolicy;
        short il_next;
#endif
#ifdef CONFIG_CPUSETS
        struct cpuset *cpuset;
        nodemask_t mems_allowed;
        int cpuset_mems_generation;
        int cpuset_mem_spread_rotor;
#endif
        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;

        atomic_t fs_excl;       /* holding fs exclusive resources */
        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
};

/*
 * 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 pid_t process_group(struct task_struct *tsk)
{
        return tsk->signal->pgrp;
}

static inline pid_t signal_session(struct signal_struct *sig)
{
        return sig->__session;
}

static inline pid_t process_session(struct task_struct *tsk)
{
        return signal_session(tsk->signal);
}

static inline void set_signal_session(struct signal_struct *sig, pid_t session)
{
        sig->__session = session;
}

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;
}

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;
}

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

/**
 * is_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.
 */
static inline int is_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);
}

/*
 * Per process flags
 */
#define PF_ALIGNWARN    0x00000001      /* Print alignment warning msgs */
                                        /* Not implemented yet, only for 486*/
#define PF_STARTING     0x00000002      /* being created */
#define PF_EXITING      0x00000004      /* getting shut down */
#define PF_EXITPIDONE   0x00000008      /* pi exit done on shut down */
#define PF_FORKNOEXEC   0x00000040      /* forked but didn't exec */
#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_FLUSHER      0x00001000      /* responsible for disk writeback */
#define PF_USED_MATH    0x00002000      /* if unset the fpu must be initialized before use */
#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_SWAPOFF      0x00080000      /* I am in swapoff */
#define PF_LESS_THROTTLE 0x00100000     /* Throttle me less: I clean memory */
#define PF_BORROWED_MM  0x00200000      /* I am a kthread doing use_mm */
#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_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 freezeable */

/*
 * 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)

#ifdef CONFIG_SMP
extern int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask);
#else
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
{
        if (!cpu_isset(0, new_mask))
                return -EINVAL;
        return 0;
}
#endif

extern unsigned long long sched_clock(void);
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_unstable_event(void);

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

extern void sched_idle_next(void);

extern unsigned int sysctl_sched_granularity;
extern unsigned int sysctl_sched_wakeup_granularity;
extern unsigned int sysctl_sched_batch_wakeup_granularity;
extern unsigned int sysctl_sched_stat_granularity;
extern unsigned int sysctl_sched_runtime_limit;
extern unsigned int sysctl_sched_child_runs_first;
extern unsigned int sysctl_sched_features;

#ifdef CONFIG_RT_MUTEXES
extern int rt_mutex_getprio(struct task_struct *p);
extern void rt_mutex_setprio(struct task_struct *p, int prio);
extern void rt_mutex_adjust_pi(struct task_struct *p);
#else
static inline int rt_mutex_getprio(struct task_struct *p)
{
        return p->normal_prio;
}
# define rt_mutex_adjust_pi(p)          do { } while (0)
#endif

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, struct sched_param *);
extern struct task_struct *idle_task(int cpu);
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;

extern struct   mm_struct init_mm;

#define find_task_by_pid(nr)    find_task_by_pid_type(PIDTYPE_PID, nr)
extern struct task_struct *find_task_by_pid_type(int type, int pid);
extern void __set_special_pids(pid_t session, pid_t pgrp);

/* per-UID process charging. */
extern struct user_struct * alloc_uid(struct user_namespace *, uid_t);
static inline struct user_struct *get_uid(struct user_struct *u)
{
        atomic_inc(&u->__count);
        return u;
}
extern void free_uid(struct user_struct *);
extern void switch_uid(struct user_struct *);

#include <asm/current.h>

extern void do_timer(unsigned long ticks);

extern int FASTCALL(wake_up_state(struct task_struct * tsk, unsigned int state));
extern int FASTCALL(wake_up_process(struct task_struct * tsk));
extern void FASTCALL(wake_up_new_task(struct task_struct * tsk,
                                                unsigned long clone_flags));
#ifdef CONFIG_SMP
 extern void kick_process(struct task_struct *tsk);
#else
 static inline void kick_process(struct task_struct *tsk) { }
#endif
extern void sched_fork(struct task_struct *p, int clone_flags);
extern void sched_dead(struct task_struct *p);

extern int in_group_p(gid_t);
extern int in_egroup_p(gid_t);

extern void proc_caches_init(void);
extern void flush_signals(struct task_struct *);
extern void ignore_signals(struct task_struct *);
extern void flush_signal_handlers(struct task_struct *, int force_default);
extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);

static inline int dequeue_signal_lock(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
{
        unsigned long flags;
        int ret;

        spin_lock_irqsave(&tsk->sighand->siglock, flags);
        ret = dequeue_signal(tsk, mask, info);
        spin_unlock_irqrestore(&tsk->sighand->siglock, flags);

        return ret;
}       

extern void block_all_signals(int (*notifier)(void *priv), void *priv,
                              sigset_t *mask);
extern void unblock_all_signals(void);
extern void release_task(struct task_struct * p);
extern int send_sig_info(int, struct siginfo *, struct task_struct *);
extern int send_group_sig_info(int, struct siginfo *, struct task_struct *);
extern int force_sigsegv(int, struct task_struct *);
extern int force_sig_info(int, struct siginfo *, struct task_struct *);
extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp);
extern int kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp);
extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid);
extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_t, u32);
extern int kill_pgrp(struct pid *pid, int sig, int priv);
extern int kill_pid(struct pid *pid, int sig, int priv);
extern int kill_proc_info(int, struct siginfo *, pid_t);
extern void do_notify_parent(struct task_struct *, int);
extern void force_sig(int, struct task_struct *);
extern void force_sig_specific(int, struct task_struct *);
extern int send_sig(int, struct task_struct *, int);
extern void zap_other_threads(struct task_struct *p);
extern int kill_proc(pid_t, int, int);
extern struct sigqueue *sigqueue_alloc(void);
extern void sigqueue_free(struct sigqueue *);
extern int send_sigqueue(int, struct sigqueue *,  struct task_struct *);
extern int send_group_sigqueue(int, struct sigqueue *,  struct task_struct *);
extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);

static inline int kill_cad_pid(int sig, int priv)
{
        return kill_pid(cad_pid, sig, priv);
}

/* These can be the second arg to send_sig_info/send_group_sig_info.  */
#define SEND_SIG_NOINFO ((struct siginfo *) 0)
#define SEND_SIG_PRIV   ((struct siginfo *) 1)
#define SEND_SIG_FORCED ((struct siginfo *) 2)

static inline int is_si_special(const struct siginfo *info)
{
        return info <= SEND_SIG_FORCED;
}

/* True if we are on the alternate signal stack.  */

static inline int on_sig_stack(unsigned long sp)
{
        return (sp - current->sas_ss_sp < current->sas_ss_size);
}

static inline int sas_ss_flags(unsigned long sp)
{
        return (current->sas_ss_size == 0 ? SS_DISABLE
                : on_sig_stack(sp) ? SS_ONSTACK : 0);
}

/*
 * Routines for handling mm_structs
 */
extern struct mm_struct * mm_alloc(void);

/* mmdrop drops the mm and the page tables */
extern void FASTCALL(__mmdrop(struct mm_struct *));
static inline void mmdrop(struct mm_struct * mm)
{
        if (unlikely(atomic_dec_and_test(&mm->mm_count)))
                __mmdrop(mm);
}

/* mmput gets rid of the mappings and all user-space */
extern void mmput(struct mm_struct *);
/* Grab a reference to a task's mm, if it is not already going away */
extern struct mm_struct *get_task_mm(struct task_struct *task);
/* Remove the current tasks stale references to the old mm_struct */
extern void mm_release(struct task_struct *, struct mm_struct *);

extern int  copy_thread(int, unsigned long, unsigned long, unsigned long, struct task_struct *, struct pt_regs *);
extern void flush_thread(void);
extern void exit_thread(void);

extern void exit_files(struct task_struct *);
extern void __cleanup_signal(struct signal_struct *);
extern void __cleanup_sighand(struct sighand_struct *);
extern void exit_itimers(struct signal_struct *);

extern NORET_TYPE void do_group_exit(int);

extern void daemonize(const char *, ...);
extern int allow_signal(int);
extern int disallow_signal(int);

extern int do_execve(char *, char __user * __user *, char __user * __user *, struct pt_regs *);
extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *);
struct task_struct *fork_idle(int);

extern void set_task_comm(struct task_struct *tsk, char *from);
extern void get_task_comm(char *to, struct task_struct *tsk);

#ifdef CONFIG_SMP
extern void wait_task_inactive(struct task_struct * p);
#else
#define wait_task_inactive(p)   do { } while (0)
#endif

#define remove_parent(p)        list_del_init(&(p)->sibling)
#define add_parent(p)           list_add_tail(&(p)->sibling,&(p)->parent->children)

#define next_task(p)    list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks)

#define for_each_process(p) \
        for (p = &init_task ; (p = next_task(p)) != &init_task ; )

/*
 * Careful: do_each_thread/while_each_thread is a double loop so
 *          'break' will not work as expected - use goto instead.
 */
#define do_each_thread(g, t) \
        for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do

#define while_each_thread(g, t) \
        while ((t = next_thread(t)) != g)

/* de_thread depends on thread_group_leader not being a pid based check */
#define thread_group_leader(p)  (p == p->group_leader)

/* Do to the insanities of de_thread it is possible for a process
 * to have the pid of the thread group leader without actually being
 * the thread group leader.  For iteration through the pids in proc
 * all we care about is that we have a task with the appropriate
 * pid, we don't actually care if we have the right task.
 */
static inline int has_group_leader_pid(struct task_struct *p)
{
        return p->pid == p->tgid;
}

static inline struct task_struct *next_thread(const struct task_struct *p)
{
        return list_entry(rcu_dereference(p->thread_group.next),
                          struct task_struct, thread_group);
}

static inline int thread_group_empty(struct task_struct *p)
{
        return list_empty(&p->thread_group);
}

#define delay_group_leader(p) \
                (thread_group_leader(p) && !thread_group_empty(p))

/*
 * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
 * subscriptions and synchronises with wait4().  Also used in procfs.  Also
 * pins the final release of task.io_context.  Also protects ->cpuset.
 *
 * Nests both inside and outside of read_lock(&tasklist_lock).
 * It must not be nested with write_lock_irq(&tasklist_lock),
 * neither inside nor outside.
 */
static inline void task_lock(struct task_struct *p)
{
        spin_lock(&p->alloc_lock);
}

static inline void task_unlock(struct task_struct *p)
{
        spin_unlock(&p->alloc_lock);
}

extern struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
                                                        unsigned long *flags);

static inline void unlock_task_sighand(struct task_struct *tsk,
                                                unsigned long *flags)
{
        spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
}

#ifndef __HAVE_THREAD_FUNCTIONS

#define task_thread_info(task)  ((struct thread_info *)(task)->stack)
#define task_stack_page(task)   ((task)->stack)

static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org)
{
        *task_thread_info(p) = *task_thread_info(org);
        task_thread_info(p)->task = p;
}

static inline unsigned long *end_of_stack(struct task_struct *p)
{
        return (unsigned long *)(task_thread_info(p) + 1);
}

#endif

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

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

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

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

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

static inline void set_tsk_need_resched(struct task_struct *tsk)
{
        set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
}

static inline void clear_tsk_need_resched(struct task_struct *tsk)
{
        clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
}

static inline int signal_pending(struct task_struct *p)
{
        return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
}
  
static inline int need_resched(void)
{
        return unlikely(test_thread_flag(TIF_NEED_RESCHED));
}

/*
 * cond_resched() and cond_resched_lock(): latency reduction via
 * explicit rescheduling in places that are safe. The return
 * value indicates whether a reschedule was done in fact.
 * cond_resched_lock() will drop the spinlock before scheduling,
 * cond_resched_softirq() will enable bhs before scheduling.
 */
extern int cond_resched(void);
extern int cond_resched_lock(spinlock_t * lock);
extern int cond_resched_softirq(void);

/*
 * Does a critical section need to be broken due to another
 * task waiting?:
 */
#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP)
# define need_lockbreak(lock) ((lock)->break_lock)
#else
# define need_lockbreak(lock) 0
#endif

/*
 * Does a critical section need to be broken due to another
 * task waiting or preemption being signalled:
 */
static inline int lock_need_resched(spinlock_t *lock)
{
        if (need_lockbreak(lock) || need_resched())
                return 1;
        return 0;
}

/*
 * Reevaluate whether the task has signals pending delivery.
 * Wake the task if so.
 * This is required every time the blocked sigset_t changes.
 * callers must hold sighand->siglock.
 */
extern void recalc_sigpending_and_wake(struct task_struct *t);
extern void recalc_sigpending(void);

extern void signal_wake_up(struct task_struct *t, int resume_stopped);

/*
 * Wrappers for p->thread_info->cpu access. No-op on UP.
 */
#ifdef CONFIG_SMP

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

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

#else

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

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

#endif /* CONFIG_SMP */

#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
extern void arch_pick_mmap_layout(struct mm_struct *mm);
#else
static inline void arch_pick_mmap_layout(struct mm_struct *mm)
{
        mm->mmap_base = TASK_UNMAPPED_BASE;
        mm->get_unmapped_area = arch_get_unmapped_area;
        mm->unmap_area = arch_unmap_area;
}
#endif

extern long sched_setaffinity(pid_t pid, cpumask_t new_mask);
extern long sched_getaffinity(pid_t pid, cpumask_t *mask);

extern int sched_mc_power_savings, sched_smt_power_savings;

extern void normalize_rt_tasks(void);

#ifdef CONFIG_TASK_XACCT
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
{
        tsk->rchar += amt;
}

static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
{
        tsk->wchar += amt;
}

static inline void inc_syscr(struct task_struct *tsk)
{
        tsk->syscr++;
}

static inline void inc_syscw(struct task_struct *tsk)
{
        tsk->syscw++;
}
#else
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
{
}

static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
{
}

static inline void inc_syscr(struct task_struct *tsk)
{
}

static inline void inc_syscw(struct task_struct *tsk)
{
}
#endif

#endif /* __KERNEL__ */

#endif