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/interrupt.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/notifier.h>
#include <linux/thread_info.h>
#include <linux/time.h>
#include <linux/jiffies.h>

#include <asm/uaccess.h>
#include <asm/div64.h>

/*
 * per-CPU timer vector definitions:
 */
#define TVN_BITS 6
#define TVR_BITS 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 {
	int index;
	struct list_head vec[TVN_SIZE];
} tvec_t;

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

typedef struct timer_list timer_t;

struct tvec_t_base_s {
	spinlock_t lock;
	unsigned long timer_jiffies;
	timer_t *running_timer;
	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;

/* Fake initialization */
static DEFINE_PER_CPU(tvec_base_t, tvec_bases) = { SPIN_LOCK_UNLOCKED };

static void check_timer_failed(timer_t *timer)
{
	static int whine_count;
	if (whine_count < 16) {
		whine_count++;
		printk("Uninitialised timer!\n");
		printk("This is just a warning.  Your computer is OK\n");
		printk("function=0x%p, data=0x%lx\n",
			timer->function, timer->data);
		dump_stack();
	}
	/*
	 * Now fix it up
	 */
	spin_lock_init(&timer->lock);
	timer->magic = TIMER_MAGIC;
}

static inline void check_timer(timer_t *timer)
{
	if (timer->magic != TIMER_MAGIC)
		check_timer_failed(timer);
}

static inline void internal_add_timer(tvec_base_t *base, timer_t *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->tv1.index;
	} else if (idx <= 0xffffffffUL) {
		int i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK;
		vec = base->tv5.vec + i;
	} else {
		/* Can only get here on architectures with 64-bit jiffies */
		INIT_LIST_HEAD(&timer->entry);
		return;
	}
	/*
	 * Timers are FIFO:
	 */
	list_add_tail(&timer->entry, vec);
}

/***
 * add_timer - start a timer
 * @timer: the timer to be added
 *
 * The kernel will do a ->function(->data) callback from the
 * timer interrupt at the ->expired point in the future. The
 * current time is 'jiffies'.
 *
 * The timer's ->expired, ->function (and if the handler uses it, ->data)
 * fields must be set prior calling this function.
 *
 * Timers with an ->expired field in the past will be executed in the next
 * timer tick. It's illegal to add an already pending timer.
 */
void add_timer(timer_t *timer)
{
	int cpu = get_cpu();
	tvec_base_t *base = &per_cpu(tvec_bases, cpu);
  	unsigned long flags;
  
  	BUG_ON(timer_pending(timer) || !timer->function);

	check_timer(timer);

	spin_lock_irqsave(&base->lock, flags);
	internal_add_timer(base, timer);
	timer->base = base;
	spin_unlock_irqrestore(&base->lock, flags);
	put_cpu();
}

/***
 * 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.
 */
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);

	check_timer(timer);

	spin_lock_irqsave(&base->lock, flags);
	internal_add_timer(base, timer);
	timer->base = base;
	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(timer_t *timer, unsigned long expires)
{
	tvec_base_t *old_base, *new_base;
	unsigned long flags;
	int ret = 0;

	BUG_ON(!timer->function);

	check_timer(timer);

	/*
	 * 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;

	spin_lock_irqsave(&timer->lock, flags);
	new_base = &per_cpu(tvec_bases, smp_processor_id());
repeat:
	old_base = timer->base;

	/*
	 * Prevent deadlocks via ordering by old_base < new_base.
	 */
	if (old_base && (new_base != old_base)) {
		if (old_base < new_base) {
			spin_lock(&new_base->lock);
			spin_lock(&old_base->lock);
		} else {
			spin_lock(&old_base->lock);
			spin_lock(&new_base->lock);
		}
		/*
		 * The timer base might have been cancelled while we were
		 * trying to take the lock(s):
		 */
		if (timer->base != old_base) {
			spin_unlock(&new_base->lock);
			spin_unlock(&old_base->lock);
			goto repeat;
		}
	} else
		spin_lock(&new_base->lock);

	/*
	 * Delete the previous timeout (if there was any), and install
	 * the new one:
	 */
	if (old_base) {
		list_del(&timer->entry);
		ret = 1;
	}
	timer->expires = expires;
	internal_add_timer(new_base, timer);
	timer->base = new_base;

	if (old_base && (new_base != old_base))
		spin_unlock(&old_base->lock);
	spin_unlock(&new_base->lock);
	spin_unlock_irqrestore(&timer->lock, flags);

	return ret;
}

/***
 * 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(timer_t *timer)
{
	unsigned long flags;
	tvec_base_t *base;

	check_timer(timer);

repeat:
 	base = timer->base;
	if (!base)
		return 0;
	spin_lock_irqsave(&base->lock, flags);
	if (base != timer->base) {
		spin_unlock_irqrestore(&base->lock, flags);
		goto repeat;
	}
	list_del(&timer->entry);
	timer->base = NULL;
	spin_unlock_irqrestore(&base->lock, flags);

	return 1;
}

#ifdef CONFIG_SMP
/***
 * 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. 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(timer_t *timer)
{
	tvec_base_t *base;
	int i, ret = 0;

	check_timer(timer);

del_again:
	ret += del_timer(timer);

	for (i = 0; i < NR_CPUS; i++) {
		if (!cpu_online(i))
			continue;

		base = &per_cpu(tvec_bases, i);
		if (base->running_timer == timer) {
			while (base->running_timer == timer) {
				cpu_relax();
				preempt_check_resched();
			}
			break;
		}
	}
	if (timer_pending(timer))
		goto del_again;

	return ret;
}
#endif


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

	head = tv->vec + tv->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) {
		timer_t *tmp;

		tmp = list_entry(curr, timer_t, entry);
		if (tmp->base != base)
			BUG();
		next = curr->next;
		internal_add_timer(base, tmp);
		curr = next;
	}
	INIT_LIST_HEAD(head);

	return tv->index = (tv->index + 1) & TVN_MASK;
}

/***
 * __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.
 */
static inline void __run_timers(tvec_base_t *base)
{
	spin_lock_irq(&base->lock);
	while ((long)(jiffies - base->timer_jiffies) >= 0) {
		struct list_head *head, *curr;

		/*
		 * Cascade timers:
		 */
		if (!base->tv1.index &&
			(cascade(base, &base->tv2) == 1) &&
				(cascade(base, &base->tv3) == 1) &&
					cascade(base, &base->tv4) == 1)
			cascade(base, &base->tv5);
repeat:
		head = base->tv1.vec + base->tv1.index;
		curr = head->next;
		if (curr != head) {
			void (*fn)(unsigned long);
			unsigned long data;
			timer_t *timer;

			timer = list_entry(curr, timer_t, entry);
 			fn = timer->function;
 			data = timer->data;

			list_del(&timer->entry);
			timer->base = NULL;
#if CONFIG_SMP
			base->running_timer = timer;
#endif
			spin_unlock_irq(&base->lock);
			if (!fn)
				printk("Bad: timer %p has NULL fn. (data: %08lx)\n", timer, data);
			else
				fn(data);
			spin_lock_irq(&base->lock);
			goto repeat;
		}
		++base->timer_jiffies; 
		base->tv1.index = (base->tv1.index + 1) & TVR_MASK;
	}
#if CONFIG_SMP
	base->running_timer = NULL;
#endif
	spin_unlock_irq(&base->lock);
}

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

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

/* The current time */
struct timespec xtime __attribute__ ((aligned (16)));

/* 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)		*/
long time_phase;			/* phase offset (scaled us)	*/
long time_freq = ((1000000 + HZ/2) % HZ - HZ/2) << SHIFT_USEC;
					/* frequency offset (scaled ppm)*/
long time_adj;				/* tick adjust (scaled 1 / HZ)	*/
long time_reftime;			/* time at last adjustment (s)	*/
long time_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--;
	    time_state = TIME_OOP;
	    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++;
	    time_state = TIME_WAIT;
	    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.
     */
    if (time_offset < 0) {
	ltemp = -time_offset;
	if (!(time_status & STA_FLL))
	    ltemp >>= SHIFT_KG + time_constant;
	if (ltemp > (MAXPHASE / MINSEC) << SHIFT_UPDATE)
	    ltemp = (MAXPHASE / MINSEC) << SHIFT_UPDATE;
	time_offset += ltemp;
	time_adj = -ltemp << (SHIFT_SCALE - SHIFT_HZ - SHIFT_UPDATE);
    } else {
	ltemp = time_offset;
	if (!(time_status & STA_FLL))
	    ltemp >>= SHIFT_KG + time_constant;
	if (ltemp > (MAXPHASE / MINSEC) << SHIFT_UPDATE)
	    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. When the PPS signal is engaged, gnaw on the
     * watchdog counter and update the frequency computed by
     * the pll and the PPS signal.
     */
    pps_valid++;
    if (pps_valid == PPS_VALID) {	/* PPS signal lost */
	pps_jitter = MAXTIME;
	pps_stabil = MAXFREQ;
	time_status &= ~(STA_PPSSIGNAL | STA_PPSJITTER |
			 STA_PPSWANDER | STA_PPSERROR);
    }
    ltemp = time_freq + pps_freq;
    if (ltemp < 0)
	time_adj -= -ltemp >>
	    (SHIFT_USEC + SHIFT_HZ - SHIFT_SCALE);
    else
	time_adj += 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)
     */
    if (time_adj < 0)
	time_adj -= (-time_adj >> 2) + (-time_adj >> 5);
    else
	time_adj += (time_adj >> 2) + (time_adj >> 5);
#endif
}

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

	if ( (time_adjust_step = time_adjust) != 0 ) {
	    /* 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
	     */
	     if (time_adjust > tickadj)
		time_adjust_step = tickadj;
	     else if (time_adjust < -tickadj)
		time_adjust_step = -tickadj;
	     
	    /* Reduce by this step the amount of time left  */
	    time_adjust -= time_adjust_step;
	}
	xtime.tv_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 <= -FINEUSEC) {
		long ltemp = -time_phase >> (SHIFT_SCALE - 10);
		time_phase += ltemp << (SHIFT_SCALE - 10);
		xtime.tv_nsec -= ltemp;
	}
	else if (time_phase >= FINEUSEC) {
		long ltemp = time_phase >> (SHIFT_SCALE - 10);
		time_phase -= ltemp << (SHIFT_SCALE - 10);
		xtime.tv_nsec += ltemp;
	}
}

/*
 * 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();
	} while (ticks);

	if (xtime.tv_nsec >= 1000000000) {
	    xtime.tv_nsec -= 1000000000;
	    xtime.tv_sec++;
	    second_overflow();
	}
}

static inline void do_process_times(struct task_struct *p,
	unsigned long user, unsigned long system)
{
	unsigned long psecs;

	psecs = (p->utime += user);
	psecs += (p->stime += system);
	if (psecs / HZ > p->rlim[RLIMIT_CPU].rlim_cur) {
		/* Send SIGXCPU every second.. */
		if (!(psecs % HZ))
			send_sig(SIGXCPU, p, 1);
		/* and SIGKILL when we go over max.. */
		if (psecs / HZ > p->rlim[RLIMIT_CPU].rlim_max)
			send_sig(SIGKILL, p, 1);
	}
}

static inline void do_it_virt(struct task_struct * p, unsigned long ticks)
{
	unsigned long it_virt = p->it_virt_value;

	if (it_virt) {
		it_virt -= ticks;
		if (!it_virt) {
			it_virt = p->it_virt_incr;
			send_sig(SIGVTALRM, p, 1);
		}
		p->it_virt_value = it_virt;
	}
}

static inline void do_it_prof(struct task_struct *p)
{
	unsigned long it_prof = p->it_prof_value;

	if (it_prof) {
		if (--it_prof == 0) {
			it_prof = p->it_prof_incr;
			send_sig(SIGPROF, p, 1);
		}
		p->it_prof_value = it_prof;
	}
}

void update_one_process(struct task_struct *p, unsigned long user,
			unsigned long system, int cpu)
{
	do_process_times(p, user, system);
	do_it_virt(p, user);
	do_it_prof(p);
}	

/*
 * 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(), system = user_tick ^ 1;

	update_one_process(p, user_tick, system, cpu);
	run_local_timers();
	scheduler_tick(user_tick, system);
}

/*
 * Nr of active tasks - counted in fixed-point numbers
 */
static unsigned long count_active_tasks(void)
{
	return (nr_running() + nr_uninterruptible()) * 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];

/*
 * 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;

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

/*
 * 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 = &per_cpu(tvec_bases, smp_processor_id());

	if ((long)(jiffies - base->timer_jiffies) >= 0)
		__run_timers(base);
}

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

/*
 * 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);
	}
	last_time_offset = 0;
	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++;
#ifndef CONFIG_SMP
	/* SMP process accounting uses the local APIC timer */

	update_process_times(user_mode(regs));
#endif
	update_times();
}

#if !defined(__alpha__) && !defined(__ia64__)

extern int do_setitimer(int, struct itimerval *, struct itimerval *);

/*
 * 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)
{
	struct itimerval it_new, it_old;
	unsigned int oldalarm;

	it_new.it_interval.tv_sec = it_new.it_interval.tv_usec = 0;
	it_new.it_value.tv_sec = seconds;
	it_new.it_value.tv_usec = 0;
	do_setitimer(ITIMER_REAL, &it_new, &it_old);
	oldalarm = it_old.it_value.tv_sec;
	/* ehhh.. We can't return 0 if we have an alarm pending.. */
	/* And we'd better return too much than too little anyway */
	if (it_old.it_value.tv_usec)
		oldalarm++;
	return oldalarm;
}

#endif

#ifndef __alpha__

/*
 * The Alpha uses getxpid, getxuid, and getxgid instead.  Maybe this
 * should be moved into arch/i386 instead?
 */

/**
 * 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 current->tgid;
}

/*
 * Accessing ->group_leader->real_parent is not SMP-safe, it could
 * change from under us. However, rather than getting any lock
 * we can use an optimistic algorithm: get the parent
 * pid, and go back and check that the parent is still
 * the same. If it has changed (which is extremely unlikely
 * indeed), we just try again..
 *
 * NOTE! This depends on the fact that even if we _do_
 * get an old value of "parent", we can happily dereference
 * the pointer (it was and remains a dereferencable kernel pointer
 * no matter what): we just can't necessarily trust the result
 * until we know that the parent pointer is valid.
 *
 * NOTE2: ->group_leader never changes from under us.
 */
asmlinkage long sys_getppid(void)
{
	int pid;
	struct task_struct *me = current;
	struct task_struct *parent;

	parent = me->group_leader->real_parent;
	for (;;) {
		pid = parent->tgid;
#if CONFIG_SMP
{
		struct task_struct *old = parent;

		/*
		 * Make sure we read the pid before re-reading the
		 * parent pointer:
		 */
		rmb();
		parent = me->group_leader->real_parent;
		if (old != parent)
			continue;
}
#endif
		break;
	}
	return pid;
}

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.
 */
signed long schedule_timeout(signed long timeout)
{
	timer_t 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;

	init_timer(&timer);
	timer.expires = expire;
	timer.data = (unsigned long) current;
	timer.function = process_timeout;

	add_timer(&timer);
	schedule();
	del_timer_sync(&timer);

	timeout = expire - jiffies;

 out:
	return timeout < 0 ? 0 : timeout;
}

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

static long nanosleep_restart(struct restart_block *restart)
{
	unsigned long expire = restart->arg0, now = jiffies;
	struct timespec *rmtp = (struct timespec *) restart->arg1;
	long ret;

	/* Did it expire while we handled signals? */
	if (!time_after(expire, now))
		return 0;

	current->state = TASK_INTERRUPTIBLE;
	expire = schedule_timeout(expire - now);

	ret = 0;
	if (expire) {
		struct timespec t;
		jiffies_to_timespec(expire, &t);

		ret = -ERESTART_RESTARTBLOCK;
		if (rmtp && copy_to_user(rmtp, &t, sizeof(t)))
			ret = -EFAULT;
		/* The 'restart' block is already filled in */
	}
	return ret;
}

asmlinkage long sys_nanosleep(struct timespec *rqtp, struct timespec *rmtp)
{
	struct timespec t;
	unsigned long expire;
	long ret;

	if (copy_from_user(&t, rqtp, sizeof(t)))
		return -EFAULT;

	if ((t.tv_nsec >= 1000000000L) || (t.tv_nsec < 0) || (t.tv_sec < 0))
		return -EINVAL;

	expire = timespec_to_jiffies(&t) + (t.tv_sec || t.tv_nsec);
	current->state = TASK_INTERRUPTIBLE;
	expire = schedule_timeout(expire);

	ret = 0;
	if (expire) {
		struct restart_block *restart;
		jiffies_to_timespec(expire, &t);
		if (rmtp && copy_to_user(rmtp, &t, sizeof(t)))
			return -EFAULT;

		restart = &current_thread_info()->restart_block;
		restart->fn = nanosleep_restart;
		restart->arg0 = jiffies + expire;
		restart->arg1 = (unsigned long) rmtp;
		ret = -ERESTART_RESTARTBLOCK;
	}
	return ret;
}

/*
 * sys_sysinfo - fill in sysinfo struct
 */ 
asmlinkage long sys_sysinfo(struct sysinfo *info)
{
	struct sysinfo val;
	u64 uptime;
	unsigned long mem_total, sav_total;
	unsigned int mem_unit, bitcount;
	unsigned long seq;

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

	do {
		seq = read_seqbegin(&xtime_lock);

		uptime = jiffies_64;
		do_div(uptime, HZ);
		val.uptime = (unsigned long) uptime;

		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 void __devinit init_timers_cpu(int cpu)
{
	int j;
	tvec_base_t *base;
       
	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);
}
	
static int __devinit timer_cpu_notify(struct notifier_block *self, 
				unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;
	switch(action) {
	case CPU_UP_PREPARE:
		init_timers_cpu(cpu);
		break;
	default:
		break;
	}
	return NOTIFY_OK;
}

static struct notifier_block __devinitdata 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);
}