Revert "futex_requeue_pi optimization"

[linux-2.6] / kernel / time.c

/*
 *  linux/kernel/time.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  This file contains the interface functions for the various
 *  time related system calls: time, stime, gettimeofday, settimeofday,
 *                             adjtime
 */
/*
 * Modification history kernel/time.c
 * 
 * 1993-09-02    Philip Gladstone
 *      Created file with time related functions from sched.c and adjtimex() 
 * 1993-10-08    Torsten Duwe
 *      adjtime interface update and CMOS clock write code
 * 1995-08-13    Torsten Duwe
 *      kernel PLL updated to 1994-12-13 specs (rfc-1589)
 * 1999-01-16    Ulrich Windl
 *      Introduced error checking for many cases in adjtimex().
 *      Updated NTP code according to technical memorandum Jan '96
 *      "A Kernel Model for Precision Timekeeping" by Dave Mills
 *      Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10)
 *      (Even though the technical memorandum forbids it)
 * 2004-07-14    Christoph Lameter
 *      Added getnstimeofday to allow the posix timer functions to return
 *      with nanosecond accuracy
 */

#include <linux/module.h>
#include <linux/timex.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/syscalls.h>
#include <linux/security.h>
#include <linux/fs.h>
#include <linux/module.h>

#include <asm/uaccess.h>
#include <asm/unistd.h>

/* 
 * The timezone where the local system is located.  Used as a default by some
 * programs who obtain this value by using gettimeofday.
 */
struct timezone sys_tz;

EXPORT_SYMBOL(sys_tz);

#ifdef __ARCH_WANT_SYS_TIME

/*
 * sys_time() can be implemented in user-level using
 * sys_gettimeofday().  Is this for backwards compatibility?  If so,
 * why not move it into the appropriate arch directory (for those
 * architectures that need it).
 */
asmlinkage long sys_time(time_t __user * tloc)
{
        time_t i;
        struct timeval tv;

        do_gettimeofday(&tv);
        i = tv.tv_sec;

        if (tloc) {
                if (put_user(i,tloc))
                        i = -EFAULT;
        }
        return i;
}

/*
 * sys_stime() can be implemented in user-level using
 * sys_settimeofday().  Is this for backwards compatibility?  If so,
 * why not move it into the appropriate arch directory (for those
 * architectures that need it).
 */
 
asmlinkage long sys_stime(time_t __user *tptr)
{
        struct timespec tv;
        int err;

        if (get_user(tv.tv_sec, tptr))
                return -EFAULT;

        tv.tv_nsec = 0;

        err = security_settime(&tv, NULL);
        if (err)
                return err;

        do_settimeofday(&tv);
        return 0;
}

#endif /* __ARCH_WANT_SYS_TIME */

asmlinkage long sys_gettimeofday(struct timeval __user *tv, struct timezone __user *tz)
{
        if (likely(tv != NULL)) {
                struct timeval ktv;
                do_gettimeofday(&ktv);
                if (copy_to_user(tv, &ktv, sizeof(ktv)))
                        return -EFAULT;
        }
        if (unlikely(tz != NULL)) {
                if (copy_to_user(tz, &sys_tz, sizeof(sys_tz)))
                        return -EFAULT;
        }
        return 0;
}

/*
 * Adjust the time obtained from the CMOS to be UTC time instead of
 * local time.
 * 
 * This is ugly, but preferable to the alternatives.  Otherwise we
 * would either need to write a program to do it in /etc/rc (and risk
 * confusion if the program gets run more than once; it would also be 
 * hard to make the program warp the clock precisely n hours)  or
 * compile in the timezone information into the kernel.  Bad, bad....
 *
 *                                              - TYT, 1992-01-01
 *
 * The best thing to do is to keep the CMOS clock in universal time (UTC)
 * as real UNIX machines always do it. This avoids all headaches about
 * daylight saving times and warping kernel clocks.
 */
static inline void warp_clock(void)
{
        write_seqlock_irq(&xtime_lock);
        wall_to_monotonic.tv_sec -= sys_tz.tz_minuteswest * 60;
        xtime.tv_sec += sys_tz.tz_minuteswest * 60;
        time_interpolator_reset();
        write_sequnlock_irq(&xtime_lock);
        clock_was_set();
}

/*
 * In case for some reason the CMOS clock has not already been running
 * in UTC, but in some local time: The first time we set the timezone,
 * we will warp the clock so that it is ticking UTC time instead of
 * local time. Presumably, if someone is setting the timezone then we
 * are running in an environment where the programs understand about
 * timezones. This should be done at boot time in the /etc/rc script,
 * as soon as possible, so that the clock can be set right. Otherwise,
 * various programs will get confused when the clock gets warped.
 */

int do_sys_settimeofday(struct timespec *tv, struct timezone *tz)
{
        static int firsttime = 1;
        int error = 0;

        if (tv && !timespec_valid(tv))
                return -EINVAL;

        error = security_settime(tv, tz);
        if (error)
                return error;

        if (tz) {
                /* SMP safe, global irq locking makes it work. */
                sys_tz = *tz;
                if (firsttime) {
                        firsttime = 0;
                        if (!tv)
                                warp_clock();
                }
        }
        if (tv)
        {
                /* SMP safe, again the code in arch/foo/time.c should
                 * globally block out interrupts when it runs.
                 */
                return do_settimeofday(tv);
        }
        return 0;
}

asmlinkage long sys_settimeofday(struct timeval __user *tv,
                                struct timezone __user *tz)
{
        struct timeval user_tv;
        struct timespec new_ts;
        struct timezone new_tz;

        if (tv) {
                if (copy_from_user(&user_tv, tv, sizeof(*tv)))
                        return -EFAULT;
                new_ts.tv_sec = user_tv.tv_sec;
                new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC;
        }
        if (tz) {
                if (copy_from_user(&new_tz, tz, sizeof(*tz)))
                        return -EFAULT;
        }

        return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
}

asmlinkage long sys_adjtimex(struct timex __user *txc_p)
{
        struct timex txc;               /* Local copy of parameter */
        int ret;

        /* Copy the user data space into the kernel copy
         * structure. But bear in mind that the structures
         * may change
         */
        if(copy_from_user(&txc, txc_p, sizeof(struct timex)))
                return -EFAULT;
        ret = do_adjtimex(&txc);
        return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret;
}

inline struct timespec current_kernel_time(void)
{
        struct timespec now;
        unsigned long seq;

        do {
                seq = read_seqbegin(&xtime_lock);
                
                now = xtime;
        } while (read_seqretry(&xtime_lock, seq));

        return now; 
}

EXPORT_SYMBOL(current_kernel_time);

/**
 * current_fs_time - Return FS time
 * @sb: Superblock.
 *
 * Return the current time truncated to the time granularity supported by
 * the fs.
 */
struct timespec current_fs_time(struct super_block *sb)
{
        struct timespec now = current_kernel_time();
        return timespec_trunc(now, sb->s_time_gran);
}
EXPORT_SYMBOL(current_fs_time);

/*
 * Convert jiffies to milliseconds and back.
 *
 * Avoid unnecessary multiplications/divisions in the
 * two most common HZ cases:
 */
unsigned int inline jiffies_to_msecs(const unsigned long j)
{
#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
        return (MSEC_PER_SEC / HZ) * j;
#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
        return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
#else
        return (j * MSEC_PER_SEC) / HZ;
#endif
}
EXPORT_SYMBOL(jiffies_to_msecs);

unsigned int inline jiffies_to_usecs(const unsigned long j)
{
#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
        return (USEC_PER_SEC / HZ) * j;
#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
        return (j + (HZ / USEC_PER_SEC) - 1)/(HZ / USEC_PER_SEC);
#else
        return (j * USEC_PER_SEC) / HZ;
#endif
}
EXPORT_SYMBOL(jiffies_to_usecs);

/**
 * timespec_trunc - Truncate timespec to a granularity
 * @t: Timespec
 * @gran: Granularity in ns.
 *
 * Truncate a timespec to a granularity. gran must be smaller than a second.
 * Always rounds down.
 *
 * This function should be only used for timestamps returned by
 * current_kernel_time() or CURRENT_TIME, not with do_gettimeofday() because
 * it doesn't handle the better resolution of the later.
 */
struct timespec timespec_trunc(struct timespec t, unsigned gran)
{
        /*
         * Division is pretty slow so avoid it for common cases.
         * Currently current_kernel_time() never returns better than
         * jiffies resolution. Exploit that.
         */
        if (gran <= jiffies_to_usecs(1) * 1000) {
                /* nothing */
        } else if (gran == 1000000000) {
                t.tv_nsec = 0;
        } else {
                t.tv_nsec -= t.tv_nsec % gran;
        }
        return t;
}
EXPORT_SYMBOL(timespec_trunc);

#ifdef CONFIG_TIME_INTERPOLATION
void getnstimeofday (struct timespec *tv)
{
        unsigned long seq,sec,nsec;

        do {
                seq = read_seqbegin(&xtime_lock);
                sec = xtime.tv_sec;
                nsec = xtime.tv_nsec+time_interpolator_get_offset();
        } while (unlikely(read_seqretry(&xtime_lock, seq)));

        while (unlikely(nsec >= NSEC_PER_SEC)) {
                nsec -= NSEC_PER_SEC;
                ++sec;
        }
        tv->tv_sec = sec;
        tv->tv_nsec = nsec;
}
EXPORT_SYMBOL_GPL(getnstimeofday);

int do_settimeofday (struct timespec *tv)
{
        time_t wtm_sec, sec = tv->tv_sec;
        long wtm_nsec, nsec = tv->tv_nsec;

        if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
                return -EINVAL;

        write_seqlock_irq(&xtime_lock);
        {
                wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
                wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);

                set_normalized_timespec(&xtime, sec, nsec);
                set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);

                time_adjust = 0;                /* stop active adjtime() */
                time_status |= STA_UNSYNC;
                time_maxerror = NTP_PHASE_LIMIT;
                time_esterror = NTP_PHASE_LIMIT;
                time_interpolator_reset();
        }
        write_sequnlock_irq(&xtime_lock);
        clock_was_set();
        return 0;
}
EXPORT_SYMBOL(do_settimeofday);

void do_gettimeofday (struct timeval *tv)
{
        unsigned long seq, nsec, usec, sec, offset;
        do {
                seq = read_seqbegin(&xtime_lock);
                offset = time_interpolator_get_offset();
                sec = xtime.tv_sec;
                nsec = xtime.tv_nsec;
        } while (unlikely(read_seqretry(&xtime_lock, seq)));

        usec = (nsec + offset) / 1000;

        while (unlikely(usec >= USEC_PER_SEC)) {
                usec -= USEC_PER_SEC;
                ++sec;
        }

        tv->tv_sec = sec;
        tv->tv_usec = usec;
}

EXPORT_SYMBOL(do_gettimeofday);


#else
#ifndef CONFIG_GENERIC_TIME
/*
 * Simulate gettimeofday using do_gettimeofday which only allows a timeval
 * and therefore only yields usec accuracy
 */
void getnstimeofday(struct timespec *tv)
{
        struct timeval x;

        do_gettimeofday(&x);
        tv->tv_sec = x.tv_sec;
        tv->tv_nsec = x.tv_usec * NSEC_PER_USEC;
}
EXPORT_SYMBOL_GPL(getnstimeofday);
#endif
#endif

/* Converts Gregorian date to seconds since 1970-01-01 00:00:00.
 * Assumes input in normal date format, i.e. 1980-12-31 23:59:59
 * => year=1980, mon=12, day=31, hour=23, min=59, sec=59.
 *
 * [For the Julian calendar (which was used in Russia before 1917,
 * Britain & colonies before 1752, anywhere else before 1582,
 * and is still in use by some communities) leave out the
 * -year/100+year/400 terms, and add 10.]
 *
 * This algorithm was first published by Gauss (I think).
 *
 * WARNING: this function will overflow on 2106-02-07 06:28:16 on
 * machines were long is 32-bit! (However, as time_t is signed, we
 * will already get problems at other places on 2038-01-19 03:14:08)
 */
unsigned long
mktime(const unsigned int year0, const unsigned int mon0,
       const unsigned int day, const unsigned int hour,
       const unsigned int min, const unsigned int sec)
{
        unsigned int mon = mon0, year = year0;

        /* 1..12 -> 11,12,1..10 */
        if (0 >= (int) (mon -= 2)) {
                mon += 12;      /* Puts Feb last since it has leap day */
                year -= 1;
        }

        return ((((unsigned long)
                  (year/4 - year/100 + year/400 + 367*mon/12 + day) +
                  year*365 - 719499
            )*24 + hour /* now have hours */
          )*60 + min /* now have minutes */
        )*60 + sec; /* finally seconds */
}

EXPORT_SYMBOL(mktime);

/**
 * set_normalized_timespec - set timespec sec and nsec parts and normalize
 *
 * @ts:         pointer to timespec variable to be set
 * @sec:        seconds to set
 * @nsec:       nanoseconds to set
 *
 * Set seconds and nanoseconds field of a timespec variable and
 * normalize to the timespec storage format
 *
 * Note: The tv_nsec part is always in the range of
 *      0 <= tv_nsec < NSEC_PER_SEC
 * For negative values only the tv_sec field is negative !
 */
void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec)
{
        while (nsec >= NSEC_PER_SEC) {
                nsec -= NSEC_PER_SEC;
                ++sec;
        }
        while (nsec < 0) {
                nsec += NSEC_PER_SEC;
                --sec;
        }
        ts->tv_sec = sec;
        ts->tv_nsec = nsec;
}

/**
 * ns_to_timespec - Convert nanoseconds to timespec
 * @nsec:       the nanoseconds value to be converted
 *
 * Returns the timespec representation of the nsec parameter.
 */
struct timespec ns_to_timespec(const s64 nsec)
{
        struct timespec ts;

        if (!nsec)
                return (struct timespec) {0, 0};

        ts.tv_sec = div_long_long_rem_signed(nsec, NSEC_PER_SEC, &ts.tv_nsec);
        if (unlikely(nsec < 0))
                set_normalized_timespec(&ts, ts.tv_sec, ts.tv_nsec);

        return ts;
}
EXPORT_SYMBOL(ns_to_timespec);

/**
 * ns_to_timeval - Convert nanoseconds to timeval
 * @nsec:       the nanoseconds value to be converted
 *
 * Returns the timeval representation of the nsec parameter.
 */
struct timeval ns_to_timeval(const s64 nsec)
{
        struct timespec ts = ns_to_timespec(nsec);
        struct timeval tv;

        tv.tv_sec = ts.tv_sec;
        tv.tv_usec = (suseconds_t) ts.tv_nsec / 1000;

        return tv;
}
EXPORT_SYMBOL(ns_to_timeval);

/*
 * When we convert to jiffies then we interpret incoming values
 * the following way:
 *
 * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET)
 *
 * - 'too large' values [that would result in larger than
 *   MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
 *
 * - all other values are converted to jiffies by either multiplying
 *   the input value by a factor or dividing it with a factor
 *
 * We must also be careful about 32-bit overflows.
 */
unsigned long msecs_to_jiffies(const unsigned int m)
{
        /*
         * Negative value, means infinite timeout:
         */
        if ((int)m < 0)
                return MAX_JIFFY_OFFSET;

#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
        /*
         * HZ is equal to or smaller than 1000, and 1000 is a nice
         * round multiple of HZ, divide with the factor between them,
         * but round upwards:
         */
        return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ);
#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
        /*
         * HZ is larger than 1000, and HZ is a nice round multiple of
         * 1000 - simply multiply with the factor between them.
         *
         * But first make sure the multiplication result cannot
         * overflow:
         */
        if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
                return MAX_JIFFY_OFFSET;

        return m * (HZ / MSEC_PER_SEC);
#else
        /*
         * Generic case - multiply, round and divide. But first
         * check that if we are doing a net multiplication, that
         * we wouldnt overflow:
         */
        if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
                return MAX_JIFFY_OFFSET;

        return (m * HZ + MSEC_PER_SEC - 1) / MSEC_PER_SEC;
#endif
}
EXPORT_SYMBOL(msecs_to_jiffies);

unsigned long usecs_to_jiffies(const unsigned int u)
{
        if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET))
                return MAX_JIFFY_OFFSET;
#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
        return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ);
#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
        return u * (HZ / USEC_PER_SEC);
#else
        return (u * HZ + USEC_PER_SEC - 1) / USEC_PER_SEC;
#endif
}
EXPORT_SYMBOL(usecs_to_jiffies);

/*
 * The TICK_NSEC - 1 rounds up the value to the next resolution.  Note
 * that a remainder subtract here would not do the right thing as the
 * resolution values don't fall on second boundries.  I.e. the line:
 * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
 *
 * Rather, we just shift the bits off the right.
 *
 * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
 * value to a scaled second value.
 */
unsigned long
timespec_to_jiffies(const struct timespec *value)
{
        unsigned long sec = value->tv_sec;
        long nsec = value->tv_nsec + TICK_NSEC - 1;

        if (sec >= MAX_SEC_IN_JIFFIES){
                sec = MAX_SEC_IN_JIFFIES;
                nsec = 0;
        }
        return (((u64)sec * SEC_CONVERSION) +
                (((u64)nsec * NSEC_CONVERSION) >>
                 (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;

}
EXPORT_SYMBOL(timespec_to_jiffies);

void
jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
{
        /*
         * Convert jiffies to nanoseconds and separate with
         * one divide.
         */
        u64 nsec = (u64)jiffies * TICK_NSEC;
        value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &value->tv_nsec);
}
EXPORT_SYMBOL(jiffies_to_timespec);

/* Same for "timeval"
 *
 * Well, almost.  The problem here is that the real system resolution is
 * in nanoseconds and the value being converted is in micro seconds.
 * Also for some machines (those that use HZ = 1024, in-particular),
 * there is a LARGE error in the tick size in microseconds.

 * The solution we use is to do the rounding AFTER we convert the
 * microsecond part.  Thus the USEC_ROUND, the bits to be shifted off.
 * Instruction wise, this should cost only an additional add with carry
 * instruction above the way it was done above.
 */
unsigned long
timeval_to_jiffies(const struct timeval *value)
{
        unsigned long sec = value->tv_sec;
        long usec = value->tv_usec;

        if (sec >= MAX_SEC_IN_JIFFIES){
                sec = MAX_SEC_IN_JIFFIES;
                usec = 0;
        }
        return (((u64)sec * SEC_CONVERSION) +
                (((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
                 (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
}
EXPORT_SYMBOL(timeval_to_jiffies);

void jiffies_to_timeval(const unsigned long jiffies, struct timeval *value)
{
        /*
         * Convert jiffies to nanoseconds and separate with
         * one divide.
         */
        u64 nsec = (u64)jiffies * TICK_NSEC;
        long tv_usec;

        value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &tv_usec);
        tv_usec /= NSEC_PER_USEC;
        value->tv_usec = tv_usec;
}
EXPORT_SYMBOL(jiffies_to_timeval);

/*
 * Convert jiffies/jiffies_64 to clock_t and back.
 */
clock_t jiffies_to_clock_t(long x)
{
#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
        return x / (HZ / USER_HZ);
#else
        u64 tmp = (u64)x * TICK_NSEC;
        do_div(tmp, (NSEC_PER_SEC / USER_HZ));
        return (long)tmp;
#endif
}
EXPORT_SYMBOL(jiffies_to_clock_t);

unsigned long clock_t_to_jiffies(unsigned long x)
{
#if (HZ % USER_HZ)==0
        if (x >= ~0UL / (HZ / USER_HZ))
                return ~0UL;
        return x * (HZ / USER_HZ);
#else
        u64 jif;

        /* Don't worry about loss of precision here .. */
        if (x >= ~0UL / HZ * USER_HZ)
                return ~0UL;

        /* .. but do try to contain it here */
        jif = x * (u64) HZ;
        do_div(jif, USER_HZ);
        return jif;
#endif
}
EXPORT_SYMBOL(clock_t_to_jiffies);

u64 jiffies_64_to_clock_t(u64 x)
{
#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
        do_div(x, HZ / USER_HZ);
#else
        /*
         * There are better ways that don't overflow early,
         * but even this doesn't overflow in hundreds of years
         * in 64 bits, so..
         */
        x *= TICK_NSEC;
        do_div(x, (NSEC_PER_SEC / USER_HZ));
#endif
        return x;
}

EXPORT_SYMBOL(jiffies_64_to_clock_t);

u64 nsec_to_clock_t(u64 x)
{
#if (NSEC_PER_SEC % USER_HZ) == 0
        do_div(x, (NSEC_PER_SEC / USER_HZ));
#elif (USER_HZ % 512) == 0
        x *= USER_HZ/512;
        do_div(x, (NSEC_PER_SEC / 512));
#else
        /*
         * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024,
         * overflow after 64.99 years.
         * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ...
         */
        x *= 9;
        do_div(x, (unsigned long)((9ull * NSEC_PER_SEC + (USER_HZ/2)) /
                                  USER_HZ));
#endif
        return x;
}

#if (BITS_PER_LONG < 64)
u64 get_jiffies_64(void)
{
        unsigned long seq;
        u64 ret;

        do {
                seq = read_seqbegin(&xtime_lock);
                ret = jiffies_64;
        } while (read_seqretry(&xtime_lock, seq));
        return ret;
}

EXPORT_SYMBOL(get_jiffies_64);
#endif

EXPORT_SYMBOL(jiffies);