Revert to Fedora kernel-2.6.17-1.2187_FC5 patched with vs2.0.2.1; there are too many...

[linux-2.6.git] / kernel / timer.c

/*
 *  linux/kernel/timer.c
 *
 *  Kernel internal timers, kernel timekeeping, basic process system calls
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  1997-01-28  Modified by Finn Arne Gangstad to make timers scale better.
 *
 *  1997-09-10  Updated NTP code according to technical memorandum Jan '96
 *              "A Kernel Model for Precision Timekeeping" by Dave Mills
 *  1998-12-24  Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
 *              serialize accesses to xtime/lost_ticks).
 *                              Copyright (C) 1998  Andrea Arcangeli
 *  1999-03-10  Improved NTP compatibility by Ulrich Windl
 *  2002-05-31  Move sys_sysinfo here and make its locking sane, Robert Love
 *  2000-10-05  Implemented scalable SMP per-CPU timer handling.
 *                              Copyright (C) 2000, 2001, 2002  Ingo Molnar
 *              Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar
 */

#include <linux/kernel_stat.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/notifier.h>
#include <linux/thread_info.h>
#include <linux/time.h>
#include <linux/jiffies.h>
#include <linux/posix-timers.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
#include <linux/delay.h>
#include <linux/vs_base.h>
#include <linux/vs_cvirt.h>
#include <linux/vserver/sched.h>

#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/div64.h>
#include <asm/timex.h>
#include <asm/io.h>

#ifdef CONFIG_TIME_INTERPOLATION
static void time_interpolator_update(long delta_nsec);
#else
#define time_interpolator_update(x)
#endif

u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;

EXPORT_SYMBOL(jiffies_64);

/*
 * per-CPU timer vector definitions:
 */
#define TVN_BITS (CONFIG_BASE_SMALL ? 4 : 6)
#define TVR_BITS (CONFIG_BASE_SMALL ? 6 : 8)
#define TVN_SIZE (1 << TVN_BITS)
#define TVR_SIZE (1 << TVR_BITS)
#define TVN_MASK (TVN_SIZE - 1)
#define TVR_MASK (TVR_SIZE - 1)

typedef struct tvec_s {
        struct list_head vec[TVN_SIZE];
} tvec_t;

typedef struct tvec_root_s {
        struct list_head vec[TVR_SIZE];
} tvec_root_t;

struct tvec_t_base_s {
        spinlock_t lock;
        struct timer_list *running_timer;
        unsigned long timer_jiffies;
        tvec_root_t tv1;
        tvec_t tv2;
        tvec_t tv3;
        tvec_t tv4;
        tvec_t tv5;
} ____cacheline_aligned_in_smp;

typedef struct tvec_t_base_s tvec_base_t;

tvec_base_t boot_tvec_bases;
EXPORT_SYMBOL(boot_tvec_bases);
static DEFINE_PER_CPU(tvec_base_t *, tvec_bases) = { &boot_tvec_bases };

static inline void set_running_timer(tvec_base_t *base,
                                        struct timer_list *timer)
{
#ifdef CONFIG_SMP
        base->running_timer = timer;
#endif
}

static void internal_add_timer(tvec_base_t *base, struct timer_list *timer)
{
        unsigned long expires = timer->expires;
        unsigned long idx = expires - base->timer_jiffies;
        struct list_head *vec;

        if (idx < TVR_SIZE) {
                int i = expires & TVR_MASK;
                vec = base->tv1.vec + i;
        } else if (idx < 1 << (TVR_BITS + TVN_BITS)) {
                int i = (expires >> TVR_BITS) & TVN_MASK;
                vec = base->tv2.vec + i;
        } else if (idx < 1 << (TVR_BITS + 2 * TVN_BITS)) {
                int i = (expires >> (TVR_BITS + TVN_BITS)) & TVN_MASK;
                vec = base->tv3.vec + i;
        } else if (idx < 1 << (TVR_BITS + 3 * TVN_BITS)) {
                int i = (expires >> (TVR_BITS + 2 * TVN_BITS)) & TVN_MASK;
                vec = base->tv4.vec + i;
        } else if ((signed long) idx < 0) {
                /*
                 * Can happen if you add a timer with expires == jiffies,
                 * or you set a timer to go off in the past
                 */
                vec = base->tv1.vec + (base->timer_jiffies & TVR_MASK);
        } else {
                int i;
                /* If the timeout is larger than 0xffffffff on 64-bit
                 * architectures then we use the maximum timeout:
                 */
                if (idx > 0xffffffffUL) {
                        idx = 0xffffffffUL;
                        expires = idx + base->timer_jiffies;
                }
                i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK;
                vec = base->tv5.vec + i;
        }
        /*
         * Timers are FIFO:
         */
        list_add_tail(&timer->entry, vec);
}

/***
 * init_timer - initialize a timer.
 * @timer: the timer to be initialized
 *
 * init_timer() must be done to a timer prior calling *any* of the
 * other timer functions.
 */
void fastcall init_timer(struct timer_list *timer)
{
        timer->entry.next = NULL;
        timer->base = per_cpu(tvec_bases, raw_smp_processor_id());
}
EXPORT_SYMBOL(init_timer);

static inline void detach_timer(struct timer_list *timer,
                                        int clear_pending)
{
        struct list_head *entry = &timer->entry;

        __list_del(entry->prev, entry->next);
        if (clear_pending)
                entry->next = NULL;
        entry->prev = LIST_POISON2;
}

/*
 * We are using hashed locking: holding per_cpu(tvec_bases).lock
 * means that all timers which are tied to this base via timer->base are
 * locked, and the base itself is locked too.
 *
 * So __run_timers/migrate_timers can safely modify all timers which could
 * be found on ->tvX lists.
 *
 * When the timer's base is locked, and the timer removed from list, it is
 * possible to set timer->base = NULL and drop the lock: the timer remains
 * locked.
 */
static tvec_base_t *lock_timer_base(struct timer_list *timer,
                                        unsigned long *flags)
{
        tvec_base_t *base;

        for (;;) {
                base = timer->base;
                if (likely(base != NULL)) {
                        spin_lock_irqsave(&base->lock, *flags);
                        if (likely(base == timer->base))
                                return base;
                        /* The timer has migrated to another CPU */
                        spin_unlock_irqrestore(&base->lock, *flags);
                }
                cpu_relax();
        }
}

int __mod_timer(struct timer_list *timer, unsigned long expires)
{
        tvec_base_t *base, *new_base;
        unsigned long flags;
        int ret = 0;

        BUG_ON(!timer->function);

        base = lock_timer_base(timer, &flags);

        if (timer_pending(timer)) {
                detach_timer(timer, 0);
                ret = 1;
        }

        new_base = __get_cpu_var(tvec_bases);

        if (base != new_base) {
                /*
                 * We are trying to schedule the timer on the local CPU.
                 * However we can't change timer's base while it is running,
                 * otherwise del_timer_sync() can't detect that the timer's
                 * handler yet has not finished. This also guarantees that
                 * the timer is serialized wrt itself.
                 */
                if (likely(base->running_timer != timer)) {
                        /* See the comment in lock_timer_base() */
                        timer->base = NULL;
                        spin_unlock(&base->lock);
                        base = new_base;
                        spin_lock(&base->lock);
                        timer->base = base;
                }
        }

        timer->expires = expires;
        internal_add_timer(base, timer);
        spin_unlock_irqrestore(&base->lock, flags);

        return ret;
}

EXPORT_SYMBOL(__mod_timer);

/***
 * add_timer_on - start a timer on a particular CPU
 * @timer: the timer to be added
 * @cpu: the CPU to start it on
 *
 * This is not very scalable on SMP. Double adds are not possible.
 */
void add_timer_on(struct timer_list *timer, int cpu)
{
        tvec_base_t *base = per_cpu(tvec_bases, cpu);
        unsigned long flags;

        BUG_ON(timer_pending(timer) || !timer->function);
        spin_lock_irqsave(&base->lock, flags);
        timer->base = base;
        internal_add_timer(base, timer);
        spin_unlock_irqrestore(&base->lock, flags);
}


/***
 * mod_timer - modify a timer's timeout
 * @timer: the timer to be modified
 *
 * mod_timer is a more efficient way to update the expire field of an
 * active timer (if the timer is inactive it will be activated)
 *
 * mod_timer(timer, expires) is equivalent to:
 *
 *     del_timer(timer); timer->expires = expires; add_timer(timer);
 *
 * Note that if there are multiple unserialized concurrent users of the
 * same timer, then mod_timer() is the only safe way to modify the timeout,
 * since add_timer() cannot modify an already running timer.
 *
 * The function returns whether it has modified a pending timer or not.
 * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an
 * active timer returns 1.)
 */
int mod_timer(struct timer_list *timer, unsigned long expires)
{
        BUG_ON(!timer->function);

        /*
         * This is a common optimization triggered by the
         * networking code - if the timer is re-modified
         * to be the same thing then just return:
         */
        if (timer->expires == expires && timer_pending(timer))
                return 1;

        return __mod_timer(timer, expires);
}

EXPORT_SYMBOL(mod_timer);

/***
 * del_timer - deactive a timer.
 * @timer: the timer to be deactivated
 *
 * del_timer() deactivates a timer - this works on both active and inactive
 * timers.
 *
 * The function returns whether it has deactivated a pending timer or not.
 * (ie. del_timer() of an inactive timer returns 0, del_timer() of an
 * active timer returns 1.)
 */
int del_timer(struct timer_list *timer)
{
        tvec_base_t *base;
        unsigned long flags;
        int ret = 0;

        if (timer_pending(timer)) {
                base = lock_timer_base(timer, &flags);
                if (timer_pending(timer)) {
                        detach_timer(timer, 1);
                        ret = 1;
                }
                spin_unlock_irqrestore(&base->lock, flags);
        }

        return ret;
}

EXPORT_SYMBOL(del_timer);

#ifdef CONFIG_SMP
/*
 * This function tries to deactivate a timer. Upon successful (ret >= 0)
 * exit the timer is not queued and the handler is not running on any CPU.
 *
 * It must not be called from interrupt contexts.
 */
int try_to_del_timer_sync(struct timer_list *timer)
{
        tvec_base_t *base;
        unsigned long flags;
        int ret = -1;

        base = lock_timer_base(timer, &flags);

        if (base->running_timer == timer)
                goto out;

        ret = 0;
        if (timer_pending(timer)) {
                detach_timer(timer, 1);
                ret = 1;
        }
out:
        spin_unlock_irqrestore(&base->lock, flags);

        return ret;
}

/***
 * del_timer_sync - deactivate a timer and wait for the handler to finish.
 * @timer: the timer to be deactivated
 *
 * This function only differs from del_timer() on SMP: besides deactivating
 * the timer it also makes sure the handler has finished executing on other
 * CPUs.
 *
 * Synchronization rules: callers must prevent restarting of the timer,
 * otherwise this function is meaningless. It must not be called from
 * interrupt contexts. The caller must not hold locks which would prevent
 * completion of the timer's handler. The timer's handler must not call
 * add_timer_on(). Upon exit the timer is not queued and the handler is
 * not running on any CPU.
 *
 * The function returns whether it has deactivated a pending timer or not.
 */
int del_timer_sync(struct timer_list *timer)
{
        for (;;) {
                int ret = try_to_del_timer_sync(timer);
                if (ret >= 0)
                        return ret;
        }
}

EXPORT_SYMBOL(del_timer_sync);
#endif

static int cascade(tvec_base_t *base, tvec_t *tv, int index)
{
        /* cascade all the timers from tv up one level */
        struct list_head *head, *curr;

        head = tv->vec + index;
        curr = head->next;
        /*
         * We are removing _all_ timers from the list, so we don't  have to
         * detach them individually, just clear the list afterwards.
         */
        while (curr != head) {
                struct timer_list *tmp;

                tmp = list_entry(curr, struct timer_list, entry);
                BUG_ON(tmp->base != base);
                curr = curr->next;
                internal_add_timer(base, tmp);
        }
        INIT_LIST_HEAD(head);

        return index;
}

/***
 * __run_timers - run all expired timers (if any) on this CPU.
 * @base: the timer vector to be processed.
 *
 * This function cascades all vectors and executes all expired timer
 * vectors.
 */
#define INDEX(N) (base->timer_jiffies >> (TVR_BITS + N * TVN_BITS)) & TVN_MASK

static inline void __run_timers(tvec_base_t *base)
{
        struct timer_list *timer;

        spin_lock_irq(&base->lock);
        while (time_after_eq(jiffies, base->timer_jiffies)) {
                struct list_head work_list = LIST_HEAD_INIT(work_list);
                struct list_head *head = &work_list;
                int index = base->timer_jiffies & TVR_MASK;
 
                /*
                 * Cascade timers:
                 */
                if (!index &&
                        (!cascade(base, &base->tv2, INDEX(0))) &&
                                (!cascade(base, &base->tv3, INDEX(1))) &&
                                        !cascade(base, &base->tv4, INDEX(2)))
                        cascade(base, &base->tv5, INDEX(3));
                ++base->timer_jiffies; 
                list_splice_init(base->tv1.vec + index, &work_list);
                while (!list_empty(head)) {
                        void (*fn)(unsigned long);
                        unsigned long data;

                        timer = list_entry(head->next,struct timer_list,entry);
                        fn = timer->function;
                        data = timer->data;

                        set_running_timer(base, timer);
                        detach_timer(timer, 1);
                        spin_unlock_irq(&base->lock);
                        {
                                int preempt_count = preempt_count();
                                fn(data);
                                if (preempt_count != preempt_count()) {
                                        printk(KERN_WARNING "huh, entered %p "
                                               "with preempt_count %08x, exited"
                                               " with %08x?\n",
                                               fn, preempt_count,
                                               preempt_count());
                                        BUG();
                                }
                        }
                        spin_lock_irq(&base->lock);
                }
        }
        set_running_timer(base, NULL);
        spin_unlock_irq(&base->lock);
}

#ifdef CONFIG_NO_IDLE_HZ
/*
 * Find out when the next timer event is due to happen. This
 * is used on S/390 to stop all activity when a cpus is idle.
 * This functions needs to be called disabled.
 */
unsigned long next_timer_interrupt(void)
{
        tvec_base_t *base;
        struct list_head *list;
        struct timer_list *nte;
        unsigned long expires;
        unsigned long hr_expires = MAX_JIFFY_OFFSET;
        ktime_t hr_delta;
        tvec_t *varray[4];
        int i, j;

        hr_delta = hrtimer_get_next_event();
        if (hr_delta.tv64 != KTIME_MAX) {
                struct timespec tsdelta;
                tsdelta = ktime_to_timespec(hr_delta);
                hr_expires = timespec_to_jiffies(&tsdelta);
                if (hr_expires < 3)
                        return hr_expires + jiffies;
        }
        hr_expires += jiffies;

        base = __get_cpu_var(tvec_bases);
        spin_lock(&base->lock);
        expires = base->timer_jiffies + (LONG_MAX >> 1);
        list = NULL;

        /* Look for timer events in tv1. */
        j = base->timer_jiffies & TVR_MASK;
        do {
                list_for_each_entry(nte, base->tv1.vec + j, entry) {
                        expires = nte->expires;
                        if (j < (base->timer_jiffies & TVR_MASK))
                                list = base->tv2.vec + (INDEX(0));
                        goto found;
                }
                j = (j + 1) & TVR_MASK;
        } while (j != (base->timer_jiffies & TVR_MASK));

        /* Check tv2-tv5. */
        varray[0] = &base->tv2;
        varray[1] = &base->tv3;
        varray[2] = &base->tv4;
        varray[3] = &base->tv5;
        for (i = 0; i < 4; i++) {
                j = INDEX(i);
                do {
                        if (list_empty(varray[i]->vec + j)) {
                                j = (j + 1) & TVN_MASK;
                                continue;
                        }
                        list_for_each_entry(nte, varray[i]->vec + j, entry)
                                if (time_before(nte->expires, expires))
                                        expires = nte->expires;
                        if (j < (INDEX(i)) && i < 3)
                                list = varray[i + 1]->vec + (INDEX(i + 1));
                        goto found;
                } while (j != (INDEX(i)));
        }
found:
        if (list) {
                /*
                 * The search wrapped. We need to look at the next list
                 * from next tv element that would cascade into tv element
                 * where we found the timer element.
                 */
                list_for_each_entry(nte, list, entry) {
                        if (time_before(nte->expires, expires))
                                expires = nte->expires;
                }
        }
        spin_unlock(&base->lock);

        /*
         * It can happen that other CPUs service timer IRQs and increment
         * jiffies, but we have not yet got a local timer tick to process
         * the timer wheels.  In that case, the expiry time can be before
         * jiffies, but since the high-resolution timer here is relative to
         * jiffies, the default expression when high-resolution timers are
         * not active,
         *
         *   time_before(MAX_JIFFY_OFFSET + jiffies, expires)
         *
         * would falsely evaluate to true.  If that is the case, just
         * return jiffies so that we can immediately fire the local timer
         */
        if (time_before(expires, jiffies))
                return jiffies;

        /*
         * It can happen that other CPUs service timer IRQs and increment
         * jiffies, but we have not yet got a local timer tick to process
         * the timer wheels.  In that case, the expiry time can be before
         * jiffies, but since the high-resolution timer here is relative to
         * jiffies, the default expression when high-resolution timers are
         * not active,
         *
         *   time_before(MAX_JIFFY_OFFSET + jiffies, expires)
         *
         * would falsely evaluate to true.  If that is the case, just
         * return jiffies so that we can immediately fire the local timer
         */
        if (time_before(expires, jiffies))
                return jiffies;

        if (time_before(hr_expires, expires))
                return hr_expires;

        return expires;
}
#endif

/******************************************************************/

/*
 * Timekeeping variables
 */
unsigned long tick_usec = TICK_USEC;            /* USER_HZ period (usec) */
unsigned long tick_nsec = TICK_NSEC;            /* ACTHZ period (nsec) */

/* 
 * The current time 
 * wall_to_monotonic is what we need to add to xtime (or xtime corrected 
 * for sub jiffie times) to get to monotonic time.  Monotonic is pegged
 * at zero at system boot time, so wall_to_monotonic will be negative,
 * however, we will ALWAYS keep the tv_nsec part positive so we can use
 * the usual normalization.
 */
struct timespec xtime __attribute__ ((aligned (16)));
struct timespec wall_to_monotonic __attribute__ ((aligned (16)));

EXPORT_SYMBOL(xtime);

/* Don't completely fail for HZ > 500.  */
int tickadj = 500/HZ ? : 1;             /* microsecs */


/*
 * phase-lock loop variables
 */
/* TIME_ERROR prevents overwriting the CMOS clock */
int time_state = TIME_OK;               /* clock synchronization status */
int time_status = STA_UNSYNC;           /* clock status bits            */
long time_offset;                       /* time adjustment (us)         */
long time_constant = 2;                 /* pll time constant            */
long time_tolerance = MAXFREQ;          /* frequency tolerance (ppm)    */
long time_precision = 1;                /* clock precision (us)         */
long time_maxerror = NTP_PHASE_LIMIT;   /* maximum error (us)           */
long time_esterror = NTP_PHASE_LIMIT;   /* estimated error (us)         */
static long time_phase;                 /* phase offset (scaled us)     */
long time_freq = (((NSEC_PER_SEC + HZ/2) % HZ - HZ/2) << SHIFT_USEC) / NSEC_PER_USEC;
                                        /* frequency offset (scaled ppm)*/
static long time_adj;                   /* tick adjust (scaled 1 / HZ)  */
long time_reftime;                      /* time at last adjustment (s)  */
long time_adjust;
long time_next_adjust;

/*
 * this routine handles the overflow of the microsecond field
 *
 * The tricky bits of code to handle the accurate clock support
 * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
 * They were originally developed for SUN and DEC kernels.
 * All the kudos should go to Dave for this stuff.
 *
 */
static void second_overflow(void)
{
        long ltemp;

        /* Bump the maxerror field */
        time_maxerror += time_tolerance >> SHIFT_USEC;
        if (time_maxerror > NTP_PHASE_LIMIT) {
                time_maxerror = NTP_PHASE_LIMIT;
                time_status |= STA_UNSYNC;
        }

        /*
         * Leap second processing. If in leap-insert state at the end of the
         * day, the system clock is set back one second; if in leap-delete
         * state, the system clock is set ahead one second. The microtime()
         * routine or external clock driver will insure that reported time is
         * always monotonic. The ugly divides should be replaced.
         */
        switch (time_state) {
        case TIME_OK:
                if (time_status & STA_INS)
                        time_state = TIME_INS;
                else if (time_status & STA_DEL)
                        time_state = TIME_DEL;
                break;
        case TIME_INS:
                if (xtime.tv_sec % 86400 == 0) {
                        xtime.tv_sec--;
                        wall_to_monotonic.tv_sec++;
                        /*
                         * The timer interpolator will make time change
                         * gradually instead of an immediate jump by one second
                         */
                        time_interpolator_update(-NSEC_PER_SEC);
                        time_state = TIME_OOP;
                        clock_was_set();
                        printk(KERN_NOTICE "Clock: inserting leap second "
                                        "23:59:60 UTC\n");
                }
                break;
        case TIME_DEL:
                if ((xtime.tv_sec + 1) % 86400 == 0) {
                        xtime.tv_sec++;
                        wall_to_monotonic.tv_sec--;
                        /*
                         * Use of time interpolator for a gradual change of
                         * time
                         */
                        time_interpolator_update(NSEC_PER_SEC);
                        time_state = TIME_WAIT;
                        clock_was_set();
                        printk(KERN_NOTICE "Clock: deleting leap second "
                                        "23:59:59 UTC\n");
                }
                break;
        case TIME_OOP:
                time_state = TIME_WAIT;
                break;
        case TIME_WAIT:
                if (!(time_status & (STA_INS | STA_DEL)))
                time_state = TIME_OK;
        }

        /*
         * Compute the phase adjustment for the next second. In PLL mode, the
         * offset is reduced by a fixed factor times the time constant. In FLL
         * mode the offset is used directly. In either mode, the maximum phase
         * adjustment for each second is clamped so as to spread the adjustment
         * over not more than the number of seconds between updates.
         */
        ltemp = time_offset;
        if (!(time_status & STA_FLL))
                ltemp = shift_right(ltemp, SHIFT_KG + time_constant);
        ltemp = min(ltemp, (MAXPHASE / MINSEC) << SHIFT_UPDATE);
        ltemp = max(ltemp, -(MAXPHASE / MINSEC) << SHIFT_UPDATE);
        time_offset -= ltemp;
        time_adj = ltemp << (SHIFT_SCALE - SHIFT_HZ - SHIFT_UPDATE);

        /*
         * Compute the frequency estimate and additional phase adjustment due
         * to frequency error for the next second.
         */
        ltemp = time_freq;
        time_adj += shift_right(ltemp,(SHIFT_USEC + SHIFT_HZ - SHIFT_SCALE));

#if HZ == 100
        /*
         * Compensate for (HZ==100) != (1 << SHIFT_HZ).  Add 25% and 3.125% to
         * get 128.125; => only 0.125% error (p. 14)
         */
        time_adj += shift_right(time_adj, 2) + shift_right(time_adj, 5);
#endif
#if HZ == 250
        /*
         * Compensate for (HZ==250) != (1 << SHIFT_HZ).  Add 1.5625% and
         * 0.78125% to get 255.85938; => only 0.05% error (p. 14)
         */
        time_adj += shift_right(time_adj, 6) + shift_right(time_adj, 7);
#endif
#if HZ == 1000
        /*
         * Compensate for (HZ==1000) != (1 << SHIFT_HZ).  Add 1.5625% and
         * 0.78125% to get 1023.4375; => only 0.05% error (p. 14)
         */
        time_adj += shift_right(time_adj, 6) + shift_right(time_adj, 7);
#endif
}

/*
 * Returns how many microseconds we need to add to xtime this tick
 * in doing an adjustment requested with adjtime.
 */
static long adjtime_adjustment(void)
{
        long time_adjust_step;

        time_adjust_step = time_adjust;
        if (time_adjust_step) {
                /*
                 * We are doing an adjtime thing.  Prepare time_adjust_step to
                 * be within bounds.  Note that a positive time_adjust means we
                 * want the clock to run faster.
                 *
                 * Limit the amount of the step to be in the range
                 * -tickadj .. +tickadj
                 */
                time_adjust_step = min(time_adjust_step, (long)tickadj);
                time_adjust_step = max(time_adjust_step, (long)-tickadj);
        }
        return time_adjust_step;
}

/* in the NTP reference this is called "hardclock()" */
static void update_wall_time_one_tick(void)
{
        long time_adjust_step, delta_nsec;

        time_adjust_step = adjtime_adjustment();
        if (time_adjust_step)
                /* Reduce by this step the amount of time left  */
                time_adjust -= time_adjust_step;
        delta_nsec = tick_nsec + time_adjust_step * 1000;
        /*
         * Advance the phase, once it gets to one microsecond, then
         * advance the tick more.
         */
        time_phase += time_adj;
        if ((time_phase >= FINENSEC) || (time_phase <= -FINENSEC)) {
                long ltemp = shift_right(time_phase, (SHIFT_SCALE - 10));
                time_phase -= ltemp << (SHIFT_SCALE - 10);
                delta_nsec += ltemp;
        }
        xtime.tv_nsec += delta_nsec;
        time_interpolator_update(delta_nsec);

        /* Changes by adjtime() do not take effect till next tick. */
        if (time_next_adjust != 0) {
                time_adjust = time_next_adjust;
                time_next_adjust = 0;
        }
}

/*
 * Return how long ticks are at the moment, that is, how much time
 * update_wall_time_one_tick will add to xtime next time we call it
 * (assuming no calls to do_adjtimex in the meantime).
 * The return value is in fixed-point nanoseconds with SHIFT_SCALE-10
 * bits to the right of the binary point.
 * This function has no side-effects.
 */
u64 current_tick_length(void)
{
        long delta_nsec;

        delta_nsec = tick_nsec + adjtime_adjustment() * 1000;
        return ((u64) delta_nsec << (SHIFT_SCALE - 10)) + time_adj;
}

/*
 * Using a loop looks inefficient, but "ticks" is
 * usually just one (we shouldn't be losing ticks,
 * we're doing this this way mainly for interrupt
 * latency reasons, not because we think we'll
 * have lots of lost timer ticks
 */
static void update_wall_time(unsigned long ticks)
{
        do {
                ticks--;
                update_wall_time_one_tick();
                if (xtime.tv_nsec >= 1000000000) {
                        xtime.tv_nsec -= 1000000000;
                        xtime.tv_sec++;
                        second_overflow();
                }
        } while (ticks);
}

/*
 * Called from the timer interrupt handler to charge one tick to the current 
 * process.  user_tick is 1 if the tick is user time, 0 for system.
 */
void update_process_times(int user_tick)
{
        struct task_struct *p = current;
        int cpu = smp_processor_id();

        /* Note: this timer irq context must be accounted for as well. */
        if (user_tick)
                account_user_time(p, jiffies_to_cputime(1));
        else
                account_system_time(p, HARDIRQ_OFFSET, jiffies_to_cputime(1));
        run_local_timers();
        if (rcu_pending(cpu))
                rcu_check_callbacks(cpu, user_tick);
        scheduler_tick();
        run_posix_cpu_timers(p);
}

/*
 * Nr of active tasks - counted in fixed-point numbers
 */
static unsigned long count_active_tasks(void)
{
        return nr_active() * FIXED_1;
}

/*
 * Hmm.. Changed this, as the GNU make sources (load.c) seems to
 * imply that avenrun[] is the standard name for this kind of thing.
 * Nothing else seems to be standardized: the fractional size etc
 * all seem to differ on different machines.
 *
 * Requires xtime_lock to access.
 */
unsigned long avenrun[3];

EXPORT_SYMBOL(avenrun);

/*
 * calc_load - given tick count, update the avenrun load estimates.
 * This is called while holding a write_lock on xtime_lock.
 */
static inline void calc_load(unsigned long ticks)
{
        unsigned long active_tasks; /* fixed-point */
        static int count = LOAD_FREQ;

        count -= ticks;
        if (count < 0) {
                count += LOAD_FREQ;
                active_tasks = count_active_tasks();
                CALC_LOAD(avenrun[0], EXP_1, active_tasks);
                CALC_LOAD(avenrun[1], EXP_5, active_tasks);
                CALC_LOAD(avenrun[2], EXP_15, active_tasks);
        }
}

/* jiffies at the most recent update of wall time */
unsigned long wall_jiffies = INITIAL_JIFFIES;

/*
 * This read-write spinlock protects us from races in SMP while
 * playing with xtime and avenrun.
 */
#ifndef ARCH_HAVE_XTIME_LOCK
seqlock_t xtime_lock __cacheline_aligned_in_smp = SEQLOCK_UNLOCKED;

EXPORT_SYMBOL(xtime_lock);
#endif

/*
 * This function runs timers and the timer-tq in bottom half context.
 */
static void run_timer_softirq(struct softirq_action *h)
{
        tvec_base_t *base = __get_cpu_var(tvec_bases);

        hrtimer_run_queues();
        if (time_after_eq(jiffies, base->timer_jiffies))
                __run_timers(base);
}

/*
 * Called by the local, per-CPU timer interrupt on SMP.
 */
void run_local_timers(void)
{
        raise_softirq(TIMER_SOFTIRQ);
        softlockup_tick();
}

/*
 * Called by the timer interrupt. xtime_lock must already be taken
 * by the timer IRQ!
 */
static inline void update_times(void)
{
        unsigned long ticks;

        ticks = jiffies - wall_jiffies;
        if (ticks) {
                wall_jiffies += ticks;
                update_wall_time(ticks);
        }
        calc_load(ticks);
}
  
/*
 * The 64-bit jiffies value is not atomic - you MUST NOT read it
 * without sampling the sequence number in xtime_lock.
 * jiffies is defined in the linker script...
 */

void do_timer(struct pt_regs *regs)
{
        jiffies_64++;
        /* prevent loading jiffies before storing new jiffies_64 value. */
        barrier();
        update_times();
}

#ifdef __ARCH_WANT_SYS_ALARM

/*
 * For backwards compatibility?  This can be done in libc so Alpha
 * and all newer ports shouldn't need it.
 */
asmlinkage unsigned long sys_alarm(unsigned int seconds)
{
        return alarm_setitimer(seconds);
}

#endif


/**
 * sys_getpid - return the thread group id of the current process
 *
 * Note, despite the name, this returns the tgid not the pid.  The tgid and
 * the pid are identical unless CLONE_THREAD was specified on clone() in
 * which case the tgid is the same in all threads of the same group.
 *
 * This is SMP safe as current->tgid does not change.
 */
asmlinkage long sys_getpid(void)
{
        return vx_map_tgid(current->tgid);
}

/*
 * Accessing ->real_parent is not SMP-safe, it could
 * change from under us. However, we can use a stale
 * value of ->real_parent under rcu_read_lock(), see
 * release_task()->call_rcu(delayed_put_task_struct).
 */
asmlinkage long sys_getppid(void)
{
        int pid;

        rcu_read_lock();
        pid = rcu_dereference(current->real_parent)->tgid;
        rcu_read_unlock();
        return vx_map_pid(pid);
}

#ifdef __alpha__

/*
 * The Alpha uses getxpid, getxuid, and getxgid instead.
 */

asmlinkage long do_getxpid(long *ppid)
{
        *ppid = sys_getppid();
        return sys_getpid();
}

#else /* _alpha_ */

asmlinkage long sys_getuid(void)
{
        /* Only we change this so SMP safe */
        return current->uid;
}

asmlinkage long sys_geteuid(void)
{
        /* Only we change this so SMP safe */
        return current->euid;
}

asmlinkage long sys_getgid(void)
{
        /* Only we change this so SMP safe */
        return current->gid;
}

asmlinkage long sys_getegid(void)
{
        /* Only we change this so SMP safe */
        return  current->egid;
}

#endif

static void process_timeout(unsigned long __data)
{
        wake_up_process((task_t *)__data);
}

/**
 * schedule_timeout - sleep until timeout
 * @timeout: timeout value in jiffies
 *
 * Make the current task sleep until @timeout jiffies have
 * elapsed. The routine will return immediately unless
 * the current task state has been set (see set_current_state()).
 *
 * You can set the task state as follows -
 *
 * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to
 * pass before the routine returns. The routine will return 0
 *
 * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
 * delivered to the current task. In this case the remaining time
 * in jiffies will be returned, or 0 if the timer expired in time
 *
 * The current task state is guaranteed to be TASK_RUNNING when this
 * routine returns.
 *
 * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule
 * the CPU away without a bound on the timeout. In this case the return
 * value will be %MAX_SCHEDULE_TIMEOUT.
 *
 * In all cases the return value is guaranteed to be non-negative.
 */
fastcall signed long __sched schedule_timeout(signed long timeout)
{
        struct timer_list timer;
        unsigned long expire;

        switch (timeout)
        {
        case MAX_SCHEDULE_TIMEOUT:
                /*
                 * These two special cases are useful to be comfortable
                 * in the caller. Nothing more. We could take
                 * MAX_SCHEDULE_TIMEOUT from one of the negative value
                 * but I' d like to return a valid offset (>=0) to allow
                 * the caller to do everything it want with the retval.
                 */
                schedule();
                goto out;
        default:
                /*
                 * Another bit of PARANOID. Note that the retval will be
                 * 0 since no piece of kernel is supposed to do a check
                 * for a negative retval of schedule_timeout() (since it
                 * should never happens anyway). You just have the printk()
                 * that will tell you if something is gone wrong and where.
                 */
                if (timeout < 0)
                {
                        printk(KERN_ERR "schedule_timeout: wrong timeout "
                                "value %lx from %p\n", timeout,
                                __builtin_return_address(0));
                        current->state = TASK_RUNNING;
                        goto out;
                }
        }

        expire = timeout + jiffies;

        setup_timer(&timer, process_timeout, (unsigned long)current);
        __mod_timer(&timer, expire);
        schedule();
        del_singleshot_timer_sync(&timer);

        timeout = expire - jiffies;

 out:
        return timeout < 0 ? 0 : timeout;
}
EXPORT_SYMBOL(schedule_timeout);

/*
 * We can use __set_current_state() here because schedule_timeout() calls
 * schedule() unconditionally.
 */
signed long __sched schedule_timeout_interruptible(signed long timeout)
{
        __set_current_state(TASK_INTERRUPTIBLE);
        return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_interruptible);

signed long __sched schedule_timeout_uninterruptible(signed long timeout)
{
        __set_current_state(TASK_UNINTERRUPTIBLE);
        return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_uninterruptible);

/* Thread ID - the internal kernel "pid" */
asmlinkage long sys_gettid(void)
{
        return current->pid;
}

/*
 * sys_sysinfo - fill in sysinfo struct
 */ 
asmlinkage long sys_sysinfo(struct sysinfo __user *info)
{
        struct sysinfo val;
        unsigned long mem_total, sav_total;
        unsigned int mem_unit, bitcount;
        unsigned long seq;

        memset((char *)&val, 0, sizeof(struct sysinfo));

        do {
                struct timespec tp;
                seq = read_seqbegin(&xtime_lock);

                /*
                 * This is annoying.  The below is the same thing
                 * posix_get_clock_monotonic() does, but it wants to
                 * take the lock which we want to cover the loads stuff
                 * too.
                 */

                getnstimeofday(&tp);
                tp.tv_sec += wall_to_monotonic.tv_sec;
                tp.tv_nsec += wall_to_monotonic.tv_nsec;
                if (tp.tv_nsec - NSEC_PER_SEC >= 0) {
                        tp.tv_nsec = tp.tv_nsec - NSEC_PER_SEC;
                        tp.tv_sec++;
                }
                if (vx_flags(VXF_VIRT_UPTIME, 0))
                        vx_vsi_uptime(&tp, NULL);
                val.uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);

                val.loads[0] = avenrun[0] << (SI_LOAD_SHIFT - FSHIFT);
                val.loads[1] = avenrun[1] << (SI_LOAD_SHIFT - FSHIFT);
                val.loads[2] = avenrun[2] << (SI_LOAD_SHIFT - FSHIFT);

                val.procs = nr_threads;
        } while (read_seqretry(&xtime_lock, seq));

        si_meminfo(&val);
        si_swapinfo(&val);

        /*
         * If the sum of all the available memory (i.e. ram + swap)
         * is less than can be stored in a 32 bit unsigned long then
         * we can be binary compatible with 2.2.x kernels.  If not,
         * well, in that case 2.2.x was broken anyways...
         *
         *  -Erik Andersen <andersee@debian.org>
         */

        mem_total = val.totalram + val.totalswap;
        if (mem_total < val.totalram || mem_total < val.totalswap)
                goto out;
        bitcount = 0;
        mem_unit = val.mem_unit;
        while (mem_unit > 1) {
                bitcount++;
                mem_unit >>= 1;
                sav_total = mem_total;
                mem_total <<= 1;
                if (mem_total < sav_total)
                        goto out;
        }

        /*
         * If mem_total did not overflow, multiply all memory values by
         * val.mem_unit and set it to 1.  This leaves things compatible
         * with 2.2.x, and also retains compatibility with earlier 2.4.x
         * kernels...
         */

        val.mem_unit = 1;
        val.totalram <<= bitcount;
        val.freeram <<= bitcount;
        val.sharedram <<= bitcount;
        val.bufferram <<= bitcount;
        val.totalswap <<= bitcount;
        val.freeswap <<= bitcount;
        val.totalhigh <<= bitcount;
        val.freehigh <<= bitcount;

 out:
        if (copy_to_user(info, &val, sizeof(struct sysinfo)))
                return -EFAULT;

        return 0;
}

static int __devinit init_timers_cpu(int cpu)
{
        int j;
        tvec_base_t *base;
        static char __devinitdata tvec_base_done[NR_CPUS];

        if (!tvec_base_done[cpu]) {
                static char boot_done;

                if (boot_done) {
                        /*
                         * The APs use this path later in boot
                         */
                        base = kmalloc_node(sizeof(*base), GFP_KERNEL,
                                                cpu_to_node(cpu));
                        if (!base)
                                return -ENOMEM;
                        memset(base, 0, sizeof(*base));
                        per_cpu(tvec_bases, cpu) = base;
                } else {
                        /*
                         * This is for the boot CPU - we use compile-time
                         * static initialisation because per-cpu memory isn't
                         * ready yet and because the memory allocators are not
                         * initialised either.
                         */
                        boot_done = 1;
                        base = &boot_tvec_bases;
                }
                tvec_base_done[cpu] = 1;
        } else {
                base = per_cpu(tvec_bases, cpu);
        }

        spin_lock_init(&base->lock);
        for (j = 0; j < TVN_SIZE; j++) {
                INIT_LIST_HEAD(base->tv5.vec + j);
                INIT_LIST_HEAD(base->tv4.vec + j);
                INIT_LIST_HEAD(base->tv3.vec + j);
                INIT_LIST_HEAD(base->tv2.vec + j);
        }
        for (j = 0; j < TVR_SIZE; j++)
                INIT_LIST_HEAD(base->tv1.vec + j);

        base->timer_jiffies = jiffies;
        return 0;
}

#ifdef CONFIG_HOTPLUG_CPU
static void migrate_timer_list(tvec_base_t *new_base, struct list_head *head)
{
        struct timer_list *timer;

        while (!list_empty(head)) {
                timer = list_entry(head->next, struct timer_list, entry);
                detach_timer(timer, 0);
                timer->base = new_base;
                internal_add_timer(new_base, timer);
        }
}

static void __devinit migrate_timers(int cpu)
{
        tvec_base_t *old_base;
        tvec_base_t *new_base;
        int i;

        BUG_ON(cpu_online(cpu));
        old_base = per_cpu(tvec_bases, cpu);
        new_base = get_cpu_var(tvec_bases);

        local_irq_disable();
        spin_lock(&new_base->lock);
        spin_lock(&old_base->lock);

        BUG_ON(old_base->running_timer);

        for (i = 0; i < TVR_SIZE; i++)
                migrate_timer_list(new_base, old_base->tv1.vec + i);
        for (i = 0; i < TVN_SIZE; i++) {
                migrate_timer_list(new_base, old_base->tv2.vec + i);
                migrate_timer_list(new_base, old_base->tv3.vec + i);
                migrate_timer_list(new_base, old_base->tv4.vec + i);
                migrate_timer_list(new_base, old_base->tv5.vec + i);
        }

        spin_unlock(&old_base->lock);
        spin_unlock(&new_base->lock);
        local_irq_enable();
        put_cpu_var(tvec_bases);
}
#endif /* CONFIG_HOTPLUG_CPU */

static int timer_cpu_notify(struct notifier_block *self,
                                unsigned long action, void *hcpu)
{
        long cpu = (long)hcpu;
        switch(action) {
        case CPU_UP_PREPARE:
                if (init_timers_cpu(cpu) < 0)
                        return NOTIFY_BAD;
                break;
#ifdef CONFIG_HOTPLUG_CPU
        case CPU_DEAD:
                migrate_timers(cpu);
                break;
#endif
        default:
                break;
        }
        return NOTIFY_OK;
}

static struct notifier_block timers_nb = {
        .notifier_call  = timer_cpu_notify,
};


void __init init_timers(void)
{
        timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
                                (void *)(long)smp_processor_id());
        register_cpu_notifier(&timers_nb);
        open_softirq(TIMER_SOFTIRQ, run_timer_softirq, NULL);
}

#ifdef CONFIG_TIME_INTERPOLATION

struct time_interpolator *time_interpolator __read_mostly;
static struct time_interpolator *time_interpolator_list __read_mostly;
static DEFINE_SPINLOCK(time_interpolator_lock);

static inline u64 time_interpolator_get_cycles(unsigned int src)
{
        unsigned long (*x)(void);

        switch (src)
        {
                case TIME_SOURCE_FUNCTION:
                        x = time_interpolator->addr;
                        return x();

                case TIME_SOURCE_MMIO64 :
                        return readq_relaxed((void __iomem *)time_interpolator->addr);

                case TIME_SOURCE_MMIO32 :
                        return readl_relaxed((void __iomem *)time_interpolator->addr);

                default: return get_cycles();
        }
}

static inline u64 time_interpolator_get_counter(int writelock)
{
        unsigned int src = time_interpolator->source;

        if (time_interpolator->jitter)
        {
                u64 lcycle;
                u64 now;

                do {
                        lcycle = time_interpolator->last_cycle;
                        now = time_interpolator_get_cycles(src);
                        if (lcycle && time_after(lcycle, now))
                                return lcycle;

                        /* When holding the xtime write lock, there's no need
                         * to add the overhead of the cmpxchg.  Readers are
                         * force to retry until the write lock is released.
                         */
                        if (writelock) {
                                time_interpolator->last_cycle = now;
                                return now;
                        }
                        /* Keep track of the last timer value returned. The use of cmpxchg here
                         * will cause contention in an SMP environment.
                         */
                } while (unlikely(cmpxchg(&time_interpolator->last_cycle, lcycle, now) != lcycle));
                return now;
        }
        else
                return time_interpolator_get_cycles(src);
}

void time_interpolator_reset(void)
{
        time_interpolator->offset = 0;
        time_interpolator->last_counter = time_interpolator_get_counter(1);
}

#define GET_TI_NSECS(count,i) (((((count) - i->last_counter) & (i)->mask) * (i)->nsec_per_cyc) >> (i)->shift)

unsigned long time_interpolator_get_offset(void)
{
        /* If we do not have a time interpolator set up then just return zero */
        if (!time_interpolator)
                return 0;

        return time_interpolator->offset +
                GET_TI_NSECS(time_interpolator_get_counter(0), time_interpolator);
}

#define INTERPOLATOR_ADJUST 65536
#define INTERPOLATOR_MAX_SKIP 10*INTERPOLATOR_ADJUST

static void time_interpolator_update(long delta_nsec)
{
        u64 counter;
        unsigned long offset;

        /* If there is no time interpolator set up then do nothing */
        if (!time_interpolator)
                return;

        /*
         * The interpolator compensates for late ticks by accumulating the late
         * time in time_interpolator->offset. A tick earlier than expected will
         * lead to a reset of the offset and a corresponding jump of the clock
         * forward. Again this only works if the interpolator clock is running
         * slightly slower than the regular clock and the tuning logic insures
         * that.
         */

        counter = time_interpolator_get_counter(1);
        offset = time_interpolator->offset +
                        GET_TI_NSECS(counter, time_interpolator);

        if (delta_nsec < 0 || (unsigned long) delta_nsec < offset)
                time_interpolator->offset = offset - delta_nsec;
        else {
                time_interpolator->skips++;
                time_interpolator->ns_skipped += delta_nsec - offset;
                time_interpolator->offset = 0;
        }
        time_interpolator->last_counter = counter;

        /* Tuning logic for time interpolator invoked every minute or so.
         * Decrease interpolator clock speed if no skips occurred and an offset is carried.
         * Increase interpolator clock speed if we skip too much time.
         */
        if (jiffies % INTERPOLATOR_ADJUST == 0)
        {
                if (time_interpolator->skips == 0 && time_interpolator->offset > tick_nsec)
                        time_interpolator->nsec_per_cyc--;
                if (time_interpolator->ns_skipped > INTERPOLATOR_MAX_SKIP && time_interpolator->offset == 0)
                        time_interpolator->nsec_per_cyc++;
                time_interpolator->skips = 0;
                time_interpolator->ns_skipped = 0;
        }
}

static inline int
is_better_time_interpolator(struct time_interpolator *new)
{
        if (!time_interpolator)
                return 1;
        return new->frequency > 2*time_interpolator->frequency ||
            (unsigned long)new->drift < (unsigned long)time_interpolator->drift;
}

void
register_time_interpolator(struct time_interpolator *ti)
{
        unsigned long flags;

        /* Sanity check */
        BUG_ON(ti->frequency == 0 || ti->mask == 0);

        ti->nsec_per_cyc = ((u64)NSEC_PER_SEC << ti->shift) / ti->frequency;
        spin_lock(&time_interpolator_lock);
        write_seqlock_irqsave(&xtime_lock, flags);
        if (is_better_time_interpolator(ti)) {
                time_interpolator = ti;
                time_interpolator_reset();
        }
        write_sequnlock_irqrestore(&xtime_lock, flags);

        ti->next = time_interpolator_list;
        time_interpolator_list = ti;
        spin_unlock(&time_interpolator_lock);
}

void
unregister_time_interpolator(struct time_interpolator *ti)
{
        struct time_interpolator *curr, **prev;
        unsigned long flags;

        spin_lock(&time_interpolator_lock);
        prev = &time_interpolator_list;
        for (curr = *prev; curr; curr = curr->next) {
                if (curr == ti) {
                        *prev = curr->next;
                        break;
                }
                prev = &curr->next;
        }

        write_seqlock_irqsave(&xtime_lock, flags);
        if (ti == time_interpolator) {
                /* we lost the best time-interpolator: */
                time_interpolator = NULL;
                /* find the next-best interpolator */
                for (curr = time_interpolator_list; curr; curr = curr->next)
                        if (is_better_time_interpolator(curr))
                                time_interpolator = curr;
                time_interpolator_reset();
        }
        write_sequnlock_irqrestore(&xtime_lock, flags);
        spin_unlock(&time_interpolator_lock);
}
#endif /* CONFIG_TIME_INTERPOLATION */

/**
 * msleep - sleep safely even with waitqueue interruptions
 * @msecs: Time in milliseconds to sleep for
 */
void msleep(unsigned int msecs)
{
        unsigned long timeout = msecs_to_jiffies(msecs) + 1;

        while (timeout)
                timeout = schedule_timeout_uninterruptible(timeout);
}

EXPORT_SYMBOL(msleep);

/**
 * msleep_interruptible - sleep waiting for signals
 * @msecs: Time in milliseconds to sleep for
 */
unsigned long msleep_interruptible(unsigned int msecs)
{
        unsigned long timeout = msecs_to_jiffies(msecs) + 1;

        while (timeout && !signal_pending(current))
                timeout = schedule_timeout_interruptible(timeout);
        return jiffies_to_msecs(timeout);
}

EXPORT_SYMBOL(msleep_interruptible);