CKRM e16 memory controller.

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

#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H

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

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

struct exec_domain;
extern int exec_shield;
extern int exec_shield_randomize;
extern int print_fatal_signals;

/*
 * 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_IDLETASK  0x00001000      /* set if new pid should be 0 (kernel only)*/
#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 */

/*
 * 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;

#define CT_TO_SECS(x)   ((x) / HZ)
#define CT_TO_USECS(x)  (((x) % HZ) * 1000000/HZ)

extern int nr_threads;
extern int last_pid;
DECLARE_PER_CPU(unsigned long, process_counts);
DECLARE_PER_CPU(struct runqueue, runqueues);
extern int nr_processes(void);
extern unsigned long nr_running(void);
extern unsigned long nr_uninterruptible(void);
extern unsigned long nr_iowait(void);

#include <linux/time.h>
#include <linux/param.h>
#include <linux/resource.h>
#include <linux/timer.h>

#include <asm/processor.h>
#include <linux/vserver/context.h>

#define TASK_RUNNING            0
#define TASK_INTERRUPTIBLE      1
#define TASK_UNINTERRUPTIBLE    2
#define TASK_STOPPED            4
#define TASK_ZOMBIE             8
#define TASK_DEAD               16
#define TASK_ONHOLD             32

#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))

#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))

/*
 * Scheduling policies
 */
#define SCHED_NORMAL            0
#define SCHED_FIFO              1
#define SCHED_RR                2

struct sched_param {
        int sched_priority;
};

#ifdef __KERNEL__

#include <linux/taskdelays.h>
#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;

typedef struct task_struct task_t;

extern void sched_init(void);
extern void sched_init_smp(void);
extern void init_idle(task_t *idle, int cpu);

extern cpumask_t nohz_cpu_mask;

extern void show_state(void);
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(int user_tick, int system);
extern unsigned long cache_decay_ticks;

/* 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));
asmlinkage void schedule(void);

struct 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_exec_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 vm_area_struct *area);
extern void arch_unmap_area_topdown(struct vm_area_struct *area);


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);
        unsigned long (*get_unmapped_exec_area) (struct file *filp,
                                unsigned long addr, unsigned long len,
                                unsigned long pgoff, unsigned long flags);
        void (*unmap_area) (struct vm_area_struct *area);
        unsigned long mmap_base;                /* base of mmap area */
        unsigned long free_area_cache;          /* first hole */
        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 task page tables and mm->rss */

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

        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 rss, total_vm, locked_vm;
        unsigned long def_flags;

        unsigned long saved_auxv[40]; /* for /proc/PID/auxv */

        unsigned dumpable:1;
        cpumask_t cpu_vm_mask;

        /* Architecture-specific MM context */
        mm_context_t context;
        struct vx_info *mm_vx_info;

        /* Token based thrashing protection. */
        unsigned long swap_token_time;
        char recent_pagein;

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

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

        struct kioctx           default_kioctx;
#ifdef CONFIG_CKRM_RES_MEM
        struct ckrm_mem_res *memclass;
        struct list_head        tasklist; /* list of all tasks sharing this address space */
        spinlock_t              peertask_lock; /* protect above tasklist */
#endif
};

extern int mmlist_nr;

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

/*
 * 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;

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

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

        /* thread group exit support */
        int                     group_exit;
        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;

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

        /* job control IDs */
        pid_t pgrp;
        pid_t tty_old_pgrp;
        pid_t session;
        /* boolean value for session group leader */
        int leader;

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

/*
 * Priority of a process goes from 0..MAX_PRIO-1, valid RT
 * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL 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 rt_task(p)              ((p)->prio < MAX_RT_PRIO)

/*
 * 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? */
        /* 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 ? */

        /* Hash table maintenance information */
        struct list_head uidhash_list;
        uid_t uid;
        xid_t xid;
};

extern struct user_struct *find_user(xid_t, uid_t);

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

typedef struct prio_array prio_array_t;
struct backing_dev_info;
struct reclaim_state;

/* POSIX.1b interval timer structure. */
struct k_itimer {
        struct list_head list;           /* free/ allocate list */
        spinlock_t it_lock;
        clockid_t it_clock;             /* which timer type */
        timer_t it_id;                  /* timer id */
        int it_overrun;                 /* overrun on pending signal  */
        int it_overrun_last;             /* overrun on last delivered signal */
        int it_requeue_pending;          /* waiting to requeue this timer */
        int it_sigev_notify;             /* notify word of sigevent struct */
        int it_sigev_signo;              /* signo word of sigevent struct */
        sigval_t it_sigev_value;         /* value word of sigevent struct */
        unsigned long it_incr;          /* interval specified in jiffies */
        struct task_struct *it_process; /* process to send signal to */
        struct timer_list it_timer;
        struct sigqueue *sigq;          /* signal queue entry. */
        struct list_head abs_timer_entry; /* clock abs_timer_list */
        struct timespec wall_to_prev;   /* wall_to_monotonic used when set */
};


struct io_context;                      /* See blkdev.h */
void exit_io_context(void);

#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)

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


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

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

        int lock_depth;         /* Lock depth */

        int prio, static_prio;
        struct list_head run_list;
        prio_array_t *array;

        unsigned long sleep_avg;
        long interactive_credit;
        unsigned long long timestamp;
        int activated;

        unsigned long policy;
        cpumask_t cpus_allowed;
        unsigned int time_slice, first_time_slice;

        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_code, exit_signal;
        int pdeath_signal;  /*  The signal sent when the parent dies  */
        /* ??? */
        unsigned long personality;
        int did_exec:1;
        pid_t pid;
        pid_t tgid;
        /* 
         * 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];

        wait_queue_head_t wait_chldexit;        /* for wait4() */
        struct completion *vfork_done;          /* for vfork() */
        int __user *set_child_tid;              /* CLONE_CHILD_SETTID */
        int __user *clear_child_tid;            /* CLONE_CHILD_CLEARTID */

        unsigned long rt_priority;
        unsigned long it_real_value, it_prof_value, it_virt_value;
        unsigned long it_real_incr, it_prof_incr, it_virt_incr;
        struct timer_list real_timer;
        unsigned long utime, stime, cutime, cstime;
        unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; /* context switch counts */
        u64 start_time;
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
        unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
/* 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;
        int keep_capabilities:1;
        struct user_struct *user;
/* limits */
        struct rlimit rlim[RLIM_NLIMITS];
        unsigned short used_math;
        char comm[16];
/* file system info */
        int link_count, total_link_count;
/* ipc stuff */
        struct sysv_sem sysvsem;
/* CPU-specific state of this task */
        struct thread_struct thread;
/* filesystem information */
        struct fs_struct *fs;
/* open file information */
        struct files_struct *files;
/* namespace */
        struct namespace *namespace;
/* signal handlers */
        struct signal_struct *signal;
        struct sighand_struct *sighand;

        sigset_t blocked, real_blocked;
        struct sigpending pending;

        unsigned long sas_ss_sp;
        size_t sas_ss_size;
        int (*notifier)(void *priv);
        void *notifier_data;
        sigset_t *notifier_mask;

        /* TUX state */
        void *tux_info;
        void (*tux_exit)(void);

        
        void *security;
        struct audit_context *audit_context;

/* vserver context data */
        xid_t xid;
        struct vx_info *vx_info;

/* vserver network data */
        nid_t nid;
        struct nx_info *nx_info;

/* Thread group tracking */
        u32 parent_exec_id;
        u32 self_exec_id;
/* Protection of (de-)allocation: mm, files, fs, tty */
        spinlock_t alloc_lock;
/* Protection of proc_dentry: nesting proc_lock, dcache_lock, write_lock_irq(&tasklist_lock); */
        spinlock_t proc_lock;
/* context-switch lock */
        spinlock_t switch_lock;

/* journalling filesystem info */
        void *journal_info;

/* VM state */
        struct reclaim_state *reclaim_state;

        struct dentry *proc_dentry;
        struct backing_dev_info *backing_dev_info;

        struct io_context *io_context;

        int ioprio;

        unsigned long ptrace_message;
        siginfo_t *last_siginfo; /* For ptrace use.  */

#ifdef CONFIG_NUMA
        struct mempolicy *mempolicy;
        short il_next;          /* could be shared with used_math */
#endif

#ifdef CONFIG_CKRM
        spinlock_t  ckrm_tsklock; 
        void       *ce_data;
#ifdef CONFIG_CKRM_TYPE_TASKCLASS
        // .. Hubertus should change to CONFIG_CKRM_TYPE_TASKCLASS 
        struct ckrm_task_class *taskclass;
        struct list_head        taskclass_link;
#ifdef CONFIG_CKRM_CPU_SCHEDULE
        struct ckrm_cpu_class *cpu_class;
#endif
#endif // CONFIG_CKRM_TYPE_TASKCLASS
#ifdef CONFIG_CKRM_RES_MEM
        struct list_head        mm_peers; // list of tasks using same mm_struct
#endif // CONFIG_CKRM_RES_MEM
#endif // CONFIG_CKRM
        struct task_delay_info  delays;
};

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

extern void __put_task_struct(struct task_struct *tsk);
#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
#define put_task_struct(tsk) \
do { if (atomic_dec_and_test(&(tsk)->usage)) __put_task_struct(tsk); } while(0)

/*
 * 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_DEAD         0x00000008      /* Dead */
#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_MEMDIE       0x00001000      /* Killed for out-of-memory */
#define PF_FLUSHER      0x00002000      /* responsible for disk writeback */

#define PF_FREEZE       0x00004000      /* this task should be frozen for suspend */
#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_SYNCWRITE    0x00200000      /* I am doing a sync write */
#define PF_RELOCEXEC    0x00400000      /* relocate shared libraries */


#define PF_MEMIO        0x00400000      /* I am  potentially doing I/O for mem */
#define PF_IOWAIT       0x00800000      /* I am waiting on disk I/O */

#ifdef CONFIG_SMP
#define SCHED_LOAD_SCALE        128UL   /* increase resolution of load */

#define SD_BALANCE_NEWIDLE      1       /* Balance when about to become idle */
#define SD_BALANCE_EXEC         2       /* Balance on exec */
#define SD_BALANCE_CLONE        4       /* Balance on clone */
#define SD_WAKE_IDLE            8       /* Wake to idle CPU on task wakeup */
#define SD_WAKE_AFFINE          16      /* Wake task to waking CPU */
#define SD_WAKE_BALANCE         32      /* Perform balancing at task wakeup */
#define SD_SHARE_CPUPOWER       64      /* Domain members share cpu power */

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 should be read only (except for setup). Although
         * it will need to be written to at cpu hot(un)plug time, perhaps the
         * cpucontrol semaphore will provide enough exclusion?
         */
        unsigned long cpu_power;
};

struct sched_domain {
        /* These fields must be setup */
        struct sched_domain *parent;    /* top 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 per_cpu_gain;      /* CPU % gained by adding domain cpus */
        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 */
};

/* Common values for SMT siblings */
#define SD_SIBLING_INIT (struct sched_domain) {         \
        .span                   = CPU_MASK_NONE,        \
        .parent                 = NULL,                 \
        .groups                 = NULL,                 \
        .min_interval           = 1,                    \
        .max_interval           = 2,                    \
        .busy_factor            = 8,                    \
        .imbalance_pct          = 110,                  \
        .cache_hot_time         = 0,                    \
        .cache_nice_tries       = 0,                    \
        .per_cpu_gain           = 15,                   \
        .flags                  = SD_BALANCE_NEWIDLE    \
                                | SD_BALANCE_EXEC       \
                                | SD_BALANCE_CLONE      \
                                | SD_WAKE_AFFINE        \
                                | SD_WAKE_IDLE          \
                                | SD_SHARE_CPUPOWER,    \
        .last_balance           = jiffies,              \
        .balance_interval       = 1,                    \
        .nr_balance_failed      = 0,                    \
}

/* Common values for CPUs */
#define SD_CPU_INIT (struct sched_domain) {             \
        .span                   = CPU_MASK_NONE,        \
        .parent                 = NULL,                 \
        .groups                 = NULL,                 \
        .min_interval           = 1,                    \
        .max_interval           = 4,                    \
        .busy_factor            = 64,                   \
        .imbalance_pct          = 125,                  \
        .cache_hot_time         = (5*1000000/2),        \
        .cache_nice_tries       = 1,                    \
        .per_cpu_gain           = 100,                  \
        .flags                  = SD_BALANCE_NEWIDLE    \
                                | SD_BALANCE_EXEC       \
                                | SD_BALANCE_CLONE      \
                                | SD_WAKE_AFFINE        \
                                | SD_WAKE_BALANCE,      \
        .last_balance           = jiffies,              \
        .balance_interval       = 1,                    \
        .nr_balance_failed      = 0,                    \
}

#ifdef CONFIG_NUMA
/* Common values for NUMA nodes */
#define SD_NODE_INIT (struct sched_domain) {            \
        .span                   = CPU_MASK_NONE,        \
        .parent                 = NULL,                 \
        .groups                 = NULL,                 \
        .min_interval           = 8,                    \
        .max_interval           = 32,                   \
        .busy_factor            = 32,                   \
        .imbalance_pct          = 125,                  \
        .cache_hot_time         = (10*1000000),         \
        .cache_nice_tries       = 1,                    \
        .per_cpu_gain           = 100,                  \
        .flags                  = SD_BALANCE_EXEC       \
                                | SD_BALANCE_CLONE      \
                                | SD_WAKE_BALANCE,      \
        .last_balance           = jiffies,              \
        .balance_interval       = 1,                    \
        .nr_balance_failed      = 0,                    \
}
#endif

extern void cpu_attach_domain(struct sched_domain *sd, int cpu);

extern int set_cpus_allowed(task_t *p, cpumask_t new_mask);
#else
static inline int set_cpus_allowed(task_t *p, cpumask_t new_mask)
{
        return 0;
}
#endif

extern unsigned long long sched_clock(void);

#ifdef CONFIG_SMP
extern void sched_balance_exec(void);
#else
#define sched_balance_exec()   {}
#endif

extern void sched_idle_next(void);
extern void set_user_nice(task_t *p, long nice);
extern int task_prio(const task_t *p);
extern int task_nice(const task_t *p);
extern int task_curr(const task_t *p);
extern int idle_cpu(int cpu);

void yield(void);

/*
 * These are the runqueue data structures:
 */
typedef struct runqueue runqueue_t;

#ifdef CONFIG_CKRM_CPU_SCHEDULE
#include <linux/ckrm_classqueue.h>
#endif

#ifdef CONFIG_CKRM_CPU_SCHEDULE

/**
 *  if belong to different class, compare class priority
 *  otherwise compare task priority 
 */
#define TASK_PREEMPTS_CURR(p, rq) \
        (((p)->cpu_class != (rq)->curr->cpu_class) && ((rq)->curr != (rq)->idle))? class_preempts_curr((p),(rq)->curr) : ((p)->prio < (rq)->curr->prio)
#else
#define BITMAP_SIZE ((((MAX_PRIO+1+7)/8)+sizeof(long)-1)/sizeof(long))
struct prio_array {
        unsigned int nr_active;
        unsigned long bitmap[BITMAP_SIZE];
        struct list_head queue[MAX_PRIO];
};
#define rq_active(p,rq)   (rq->active)
#define rq_expired(p,rq)  (rq->expired)
#define ckrm_rebalance_tick(j,this_cpu) do {} while (0)
#define TASK_PREEMPTS_CURR(p, rq) \
        ((p)->prio < (rq)->curr->prio)
#endif

/*
 * This is the main, per-CPU runqueue data structure.
 *
 * Locking rule: those places that want to lock multiple runqueues
 * (such as the load balancing or the thread migration code), lock
 * acquire operations must be ordered by ascending &runqueue.
 */
struct runqueue {
        spinlock_t lock;

        /*
         * nr_running and cpu_load should be in the same cacheline because
         * remote CPUs use both these fields when doing load calculation.
         */
        unsigned long nr_running;
#if defined(CONFIG_SMP)
        unsigned long cpu_load;
#endif
        unsigned long long nr_switches, nr_preempt;
        unsigned long expired_timestamp, nr_uninterruptible;
        unsigned long long timestamp_last_tick;
        task_t *curr, *idle;
        struct mm_struct *prev_mm;
#ifdef CONFIG_CKRM_CPU_SCHEDULE
        unsigned long ckrm_cpu_load;
        struct classqueue_struct classqueue;   
#else
        prio_array_t *active, *expired, arrays[2];
#endif
        int best_expired_prio;
        atomic_t nr_iowait;

#ifdef CONFIG_SMP
        struct sched_domain *sd;

        /* For active balancing */
        int active_balance;
        int push_cpu;

        task_t *migration_thread;
        struct list_head migration_queue;
#endif
        struct list_head hold_queue;
        int idle_tokens;
};

/*
 * 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;

extern struct task_struct *find_task_by_pid(int pid);
extern void set_special_pids(pid_t session, pid_t pgrp);
extern void __set_special_pids(pid_t session, pid_t pgrp);

/* per-UID process charging. */
extern struct user_struct * alloc_uid(xid_t, 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 unsigned long itimer_ticks;
extern unsigned long itimer_next;
extern void do_timer(struct pt_regs *);

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_forked_process(struct task_struct * tsk));
#ifdef CONFIG_SMP
 extern void kick_process(struct task_struct *tsk);
 extern void FASTCALL(wake_up_forked_thread(struct task_struct * tsk));
#else
 static inline void kick_process(struct task_struct *tsk) { }
 static inline void wake_up_forked_thread(struct task_struct * tsk)
 {
        wake_up_forked_process(tsk);
 }
#endif
extern void FASTCALL(sched_fork(task_t * p));
extern void FASTCALL(sched_exit(task_t * 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 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_sig_info(int, struct siginfo *, struct task_struct *);
extern int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp);
extern int kill_pg_info(int, struct siginfo *, pid_t);
extern int kill_sl_info(int, struct siginfo *, pid_t);
extern int kill_proc_info(int, struct siginfo *, pid_t);
extern void notify_parent(struct task_struct *, int);
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_pg(pid_t, int, int);
extern int kill_sl(pid_t, int, int);
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, const struct k_sigaction *, struct k_sigaction *);
extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);

/* 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)

/* 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);
}


#ifdef CONFIG_SECURITY
/* code is in security.c */
extern int capable(int cap);
#else
static inline int capable(int cap)
{
        if (cap_raised(current->cap_effective, cap)) {
                current->flags |= PF_SUPERPRIV;
                return 1;
        }
        return 0;
}
#endif

/*
 * 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 (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 the mm if its not already going away */
extern struct mm_struct *mmgrab(struct mm_struct *);
/* 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_mm(struct task_struct *);
extern void exit_files(struct task_struct *);
extern void exit_signal(struct task_struct *);
extern void __exit_signal(struct task_struct *);
extern void exit_sighand(struct task_struct *);
extern void __exit_sighand(struct task_struct *);
extern void exit_itimers(struct signal_struct *);

extern NORET_TYPE void do_group_exit(int);

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

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 *);
extern struct task_struct * copy_process(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *);

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

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

#define REMOVE_LINKS(p) do {                                    \
        if (thread_group_leader(p))                             \
                list_del_init(&(p)->tasks);                     \
        remove_parent(p);                                       \
        } while (0)

#define SET_LINKS(p) do {                                       \
        if (thread_group_leader(p))                             \
                list_add_tail(&(p)->tasks,&init_task.tasks);    \
        add_parent(p, (p)->parent);                             \
        } while (0)

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

extern task_t * FASTCALL(next_thread(const task_t *p));

#define thread_group_leader(p)  (p->pid == p->tgid)

static inline int thread_group_empty(task_t *p)
{
        struct pid *pid = p->pids[PIDTYPE_TGID].pidptr;

        return pid->task_list.next->next == &pid->task_list;
}

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

extern void unhash_process(struct task_struct *p);

/*
 * Protects ->fs, ->files, ->mm, ->ptrace, ->group_info and synchronises with
 * wait4().
 *
 * 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);
}
 
/**
 * get_task_mm - acquire a reference to the task's mm
 *
 * Returns %NULL if the task has no mm. User must release
 * the mm via mmput() after use.
 */
static inline struct mm_struct * get_task_mm(struct task_struct * task)
{
        struct mm_struct * mm;
 
        task_lock(task);
        mm = task->mm;
        if (mm)
                mm = mmgrab(mm);
        task_unlock(task);

        return mm;
}

/* 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(tsk->thread_info,flag);
}

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

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

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

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

extern void __cond_resched(void);

static inline void cond_resched(void)
{
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
        __might_sleep(__FILE__, __LINE__, 0);
#endif
        __cond_resched();
}

/*
 * cond_resched_lock() - if a reschedule is pending, drop the given lock,
 * call schedule, and on return reacquire the lock.
 *
 * This works OK both with and without CONFIG_PREEMPT.  We do strange low-level
 * operations here to prevent schedule() from being called twice (once via
 * spin_unlock(), once by hand).
 */
extern void __cond_resched_lock(spinlock_t * lock);

static inline void cond_resched_lock(spinlock_t * lock)
{
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
        __might_sleep(__FILE__, __LINE__, 1);
#endif
        __cond_resched_lock(lock);
}

/* Reevaluate whether the task has signals pending delivery.
   This is required every time the blocked sigset_t changes.
   callers must hold sighand->siglock.  */

extern FASTCALL(void recalc_sigpending_tsk(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 p->thread_info->cpu;
}

static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
{
        p->thread_info->cpu = 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 */


/* API for registering delay info */
#ifdef CONFIG_DELAY_ACCT

#define test_delay_flag(tsk,flg)                ((tsk)->flags & (flg))
#define set_delay_flag(tsk,flg)                 ((tsk)->flags |= (flg))
#define clear_delay_flag(tsk,flg)               ((tsk)->flags &= ~(flg))

#define def_delay_var(var)                      unsigned long long var
#define get_delay(tsk,field)                    ((tsk)->delays.field)

#define start_delay(var)                        ((var) = sched_clock())
#define start_delay_set(var,flg)                (set_delay_flag(current,flg),(var) = sched_clock())

#define inc_delay(tsk,field) (((tsk)->delays.field)++)

/* because of hardware timer drifts in SMPs and task continue on different cpu
 * then where the start_ts was taken there is a possibility that
 * end_ts < start_ts by some usecs. In this case we ignore the diff
 * and add nothing to the total.
 */
#ifdef CONFIG_SMP
#define test_ts_integrity(start_ts,end_ts)  (likely((end_ts) > (start_ts)))
#else
#define test_ts_integrity(start_ts,end_ts)  (1)
#endif

#define add_delay_ts(tsk,field,start_ts,end_ts) \
        do { if (test_ts_integrity(start_ts,end_ts)) (tsk)->delays.field += ((end_ts)-(start_ts)); } while (0)

#define add_delay_clear(tsk,field,start_ts,flg)        \
        do {                                           \
                unsigned long long now = sched_clock();\
                add_delay_ts(tsk,field,start_ts,now);  \
                clear_delay_flag(tsk,flg);             \
        } while (0)

static inline void add_io_delay(unsigned long long dstart) 
{
        struct task_struct * tsk = current;
        unsigned long long now = sched_clock();
        unsigned long long val;

        if (test_ts_integrity(dstart,now))
                val = now - dstart;
        else
                val = 0;
        if (test_delay_flag(tsk,PF_MEMIO)) {
                tsk->delays.mem_iowait_total += val;
                tsk->delays.num_memwaits++;
        } else {
                tsk->delays.iowait_total += val;
                tsk->delays.num_iowaits++;
        }
        clear_delay_flag(tsk,PF_IOWAIT);
}

inline static void init_delays(struct task_struct *tsk)
{
        memset((void*)&tsk->delays,0,sizeof(tsk->delays));
}

#else

#define test_delay_flag(tsk,flg)                (0)
#define set_delay_flag(tsk,flg)                 do { } while (0)
#define clear_delay_flag(tsk,flg)               do { } while (0)

#define def_delay_var(var)                            
#define get_delay(tsk,field)                    (0)

#define start_delay(var)                        do { } while (0)
#define start_delay_set(var,flg)                do { } while (0)

#define inc_delay(tsk,field)                    do { } while (0)
#define add_delay_ts(tsk,field,start_ts,now)    do { } while (0)
#define add_delay_clear(tsk,field,start_ts,flg) do { } while (0)
#define add_io_delay(dstart)                    do { } while (0) 
#define init_delays(tsk)                        do { } while (0)
#endif



#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

#endif /* __KERNEL__ */

#endif