hrtimer.c

linux 2.6.19 kernel source code before patching

/*
 *  linux/kernel/hrtimer.c
 *
 *  Copyright(C) 2005-2006, Thomas Gleixner <[e-mail]>
 *  Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
 *  Copyright(C) 2006-2007  Timesys Corp., Thomas Gleixner
 *
 *  High-resolution kernel timers
 *
 *  In contrast to the low-resolution timeout API implemented in
 *  kernel/timer.c, hrtimers provide finer resolution and accuracy
 *  depending on system configuration and capabilities.
 *
 *  These timers are currently used for:
 *   - itimers
 *   - POSIX timers
 *   - nanosleep
 *   - precise in-kernel timing
 *
 *  Started by: Thomas Gleixner and Ingo Molnar
 *
 *  Credits:
 *	based on kernel/timer.c
 *
 *	Help, testing, suggestions, bugfixes, improvements were
 *	provided by:
 *
 *	George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel
 *	et. al.
 *
 *  For licencing details see kernel-base/COPYING
 */

#include <linux/cpu.h>
#include <linux/irq.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/hrtimer.h>
#include <linux/notifier.h>
#include <linux/syscalls.h>
#include <linux/kallsyms.h>
#include <linux/interrupt.h>
#include <linux/tick.h>
#include <linux/seq_file.h>
#include <linux/err.h>

#include <asm/uaccess.h>

/**
 * ktime_get - get the monotonic time in ktime_t format
 *
 * returns the time in ktime_t format
 */
ktime_t ktime_get(void)
{
	struct timespec now;

	ktime_get_ts(&now);

	return timespec_to_ktime(now);
}
EXPORT_SYMBOL_GPL(ktime_get);

/**
 * ktime_get_real - get the real (wall-) time in ktime_t format
 *
 * returns the time in ktime_t format
 */
ktime_t ktime_get_real(void)
{
	struct timespec now;

	getnstimeofday(&now);

	return timespec_to_ktime(now);
}

EXPORT_SYMBOL_GPL(ktime_get_real);

/*
 * The timer bases:
 *
 * Note: If we want to add new timer bases, we have to skip the two
 * clock ids captured by the cpu-timers. We do this by holding empty
 * entries rather than doing math adjustment of the clock ids.
 * This ensures that we capture erroneous accesses to these clock ids
 * rather than moving them into the range of valid clock id's.
 */
DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
{

	.clock_base =
	{
		{
			.index = CLOCK_REALTIME,
			.get_time = &ktime_get_real,
			.resolution = KTIME_LOW_RES,
		},
		{
			.index = CLOCK_MONOTONIC,
			.get_time = &ktime_get,
			.resolution = KTIME_LOW_RES,
		},
	}
};

/**
 * ktime_get_ts - get the monotonic clock in timespec format
 * @ts:		pointer to timespec variable
 *
 * The function calculates the monotonic clock from the realtime
 * clock and the wall_to_monotonic offset and stores the result
 * in normalized timespec format in the variable pointed to by @ts.
 */
void ktime_get_ts(struct timespec *ts)
{
	struct timespec tomono;
	unsigned long seq;

	do {
		seq = read_seqbegin(&xtime_lock);
		getnstimeofday(ts);
		tomono = wall_to_monotonic;

	} while (read_seqretry(&xtime_lock, seq));

	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec,
				ts->tv_nsec + tomono.tv_nsec);
}
EXPORT_SYMBOL_GPL(ktime_get_ts);

/*
 * Get the coarse grained time at the softirq based on xtime and
 * wall_to_monotonic.
 */
static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
{
	ktime_t xtim, tomono;
	struct timespec xts, tom;
	unsigned long seq;

	do {
		seq = read_seqbegin(&xtime_lock);
#ifdef CONFIG_NO_HZ
		getnstimeofday(&xts);
#else
		xts = xtime;
#endif
		tom = wall_to_monotonic;
	} while (read_seqretry(&xtime_lock, seq));

	xtim = timespec_to_ktime(xts);
	tomono = timespec_to_ktime(tom);
	base->clock_base[CLOCK_REALTIME].softirq_time = xtim;
	base->clock_base[CLOCK_MONOTONIC].softirq_time =
		ktime_add(xtim, tomono);
}

/*
 * Helper function to check, whether the timer is running the callback
 * function
 */
static inline int hrtimer_callback_running(struct hrtimer *timer)
{
	return timer->state & HRTIMER_STATE_CALLBACK;
}

/*
 * Functions and macros which are different for UP/SMP systems are kept in a
 * single place
 */
#ifdef CONFIG_SMP

/*
 * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].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 the lists/queues.
 *
 * 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
struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
					     unsigned long *flags)
{
	struct hrtimer_clock_base *base;

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

/*
 * Switch the timer base to the current CPU when possible.
 */
static inline struct hrtimer_clock_base *
switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base)
{
	struct hrtimer_clock_base *new_base;
	struct hrtimer_cpu_base *new_cpu_base;

	new_cpu_base = &__get_cpu_var(hrtimer_bases);
	new_base = &new_cpu_base->clock_base[base->index];

	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,
		 * so we keep it on the same CPU. No hassle vs. reprogramming
		 * the event source in the high resolution case. The softirq
		 * code will take care of this when the timer function has
		 * completed. There is no conflict as we hold the lock until
		 * the timer is enqueued.
		 */
		if (unlikely(hrtimer_callback_running(timer)))
			return base;

		/* See the comment in lock_timer_base() */
		timer->base = NULL;
		spin_unlock(&base->cpu_base->lock);
		spin_lock(&new_base->cpu_base->lock);
		timer->base = new_base;
	}
	return new_base;
}

#else /* CONFIG_SMP */

static inline struct hrtimer_clock_base *
lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
{
	struct hrtimer_clock_base *base = timer->base;

	spin_lock_irqsave(&base->cpu_base->lock, *flags);

	return base;
}

# define switch_hrtimer_base(t, b)	(b)

#endif	/* !CONFIG_SMP */

/*
 * Functions for the union type storage format of ktime_t which are
 * too large for inlining:
 */
#if BITS_PER_LONG < 64
# ifndef CONFIG_KTIME_SCALAR
/**
 * ktime_add_ns - Add a scalar nanoseconds value to a ktime_t variable
 * @kt:		addend
 * @nsec:	the scalar nsec value to add
 *
 * Returns the sum of kt and nsec in ktime_t format
 */
ktime_t ktime_add_ns(const ktime_t kt, u64 nsec)
{
	ktime_t tmp;

	if (likely(nsec < NSEC_PER_SEC)) {
		tmp.tv64 = nsec;
	} else {
		unsigned long rem = do_div(nsec, NSEC_PER_SEC);

		tmp = ktime_set((long)nsec, rem);
	}

	return ktime_add(kt, tmp);
}

EXPORT_SYMBOL_GPL(ktime_add_ns);
# endif /* !CONFIG_KTIME_SCALAR */

/*
 * Divide a ktime value by a nanosecond value
 */
unsigned long ktime_divns(const ktime_t kt, s64 div)
{
	u64 dclc, inc, dns;
	int sft = 0;

	dclc = dns = ktime_to_ns(kt);
	inc = div;
	/* Make sure the divisor is less than 2^32: */
	while (div >> 32) {
		sft++;
		div >>= 1;
	}
	dclc >>= sft;
	do_div(dclc, (unsigned long) div);

	return (unsigned long) dclc;
}
#endif /* BITS_PER_LONG >= 64 */

/* High resolution timer related functions */
#ifdef CONFIG_HIGH_RES_TIMERS

/*
 * High resolution timer enabled ?
 */
static int hrtimer_hres_enabled __read_mostly  = 1;

/*
 * Enable / Disable high resolution mode
 */
static int __init setup_hrtimer_hres(char *str)
{
	if (!strcmp(str, "off"))
		hrtimer_hres_enabled = 0;
	else if (!strcmp(str, "on"))
		hrtimer_hres_enabled = 1;
	else
		return 0;
	return 1;
}

__setup("highres=", setup_hrtimer_hres);

/*
 * hrtimer_high_res_enabled - query, if the highres mode is enabled
 */
static inline int hrtimer_is_hres_enabled(void)
{
	return hrtimer_hres_enabled;
}

/*
 * Is the high resolution mode active ?
 */
static inline int hrtimer_hres_active(void)
{
	return __get_cpu_var(hrtimer_bases).hres_active;
}

/*
 * Reprogram the event source with checking both queues for the
 * next event
 * Called with interrupts disabled and base->lock held
 */
static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
{
	int i;
	struct hrtimer_clock_base *base = cpu_base->clock_base;
	ktime_t expires;

	cpu_base->expires_next.tv64 = KTIME_MAX;

	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
		struct hrtimer *timer;

		if (!base->first)
			continue;
		timer = rb_entry(base->first, struct hrtimer, node);
		expires = ktime_sub(timer->expires, base->offset);
		if (expires.tv64 < cpu_base->expires_next.tv64)
			cpu_base->expires_next = expires;
	}

	if (cpu_base->expires_next.tv64 != KTIME_MAX)
		tick_program_event(cpu_base->expires_next, 1);
}

/*
 * Shared reprogramming for clock_realtime and clock_monotonic
 *
 * When a timer is enqueued and expires earlier than the already enqueued
 * timers, we have to check, whether it expires earlier than the timer for
 * which the clock event device was armed.
 *
 * Called with interrupts disabled and base->cpu_base.lock held
 */
static int hrtimer_reprogram(struct hrtimer *timer,
			     struct hrtimer_clock_base *base)
{
	ktime_t *expires_next = &__get_cpu_var(hrtimer_bases).expires_next;
	ktime_t expires = ktime_sub(timer->expires, base->offset);
	int res;

	/*
	 * When the callback is running, we do not reprogram the clock event
	 * device. The timer callback is either running on a different CPU or
	 * the callback is executed in the hrtimer_interupt context. The
	 * reprogramming is handled either by the softirq, which called the
	 * callback or at the end of the hrtimer_interrupt.
	 */
	if (hrtimer_callback_running(timer))
		return 0;

	if (expires.tv64 >= expires_next->tv64)
		return 0;

	/*
	 * Clockevents returns -ETIME, when the event was in the past.
	 */
	res = tick_program_event(expires, 0);
	if (!IS_ERR_VALUE(res))
		*expires_next = expires;
	return res;
}


/*
 * Retrigger next event is called after clock was set
 *
 * Called with interrupts disabled via on_each_cpu()
 */
static void retrigger_next_event(void *arg)
{
	struct hrtimer_cpu_base *base;
	struct timespec realtime_offset;
	unsigned long seq;

	if (!hrtimer_hres_active())
		return;

	do {
		seq = read_seqbegin(&xtime_lock);
		set_normalized_timespec(&realtime_offset,
					-wall_to_monotonic.tv_sec,
					-wall_to_monotonic.tv_nsec);
	} while (read_seqretry(&xtime_lock, seq));

	base = &__get_cpu_var(hrtimer_bases);

	/* Adjust CLOCK_REALTIME offset */
	spin_lock(&base->lock);
	base->clock_base[CLOCK_REALTIME].offset =
		timespec_to_ktime(realtime_offset);

	hrtimer_force_reprogram(base);
	spin_unlock(&base->lock);
}

/*
 * Clock realtime was set
 *
 * Change the offset of the realtime clock vs. the monotonic
 * clock.
 *
 * We might have to reprogram the high resolution timer interrupt. On
 * SMP we call the architecture specific code to retrigger _all_ high
 * resolution timer interrupts. On UP we just disable interrupts and
 * call the high resolution interrupt code.
 */
void clock_was_set(void)
{
	/* Retrigger the CPU local events everywhere */
	on_each_cpu(retrigger_next_event, NULL, 0, 1);
}

/*
 * During resume we might have to reprogram the high resolution timer
 * interrupt (on the local CPU):
 */
void hres_timers_resume(void)
{
	WARN_ON_ONCE(num_online_cpus() > 1);

	/* Retrigger the CPU local events: */
	retrigger_next_event(NULL);
}

/*
 * Check, whether the timer is on the callback pending list
 */
static inline int hrtimer_cb_pending(const struct hrtimer *timer)
{
	return timer->state & HRTIMER_STATE_PENDING;
}