Luca's patch ported

[cbs-scheduler.git] / kernel / hrtimer.c

/*
 *  linux/kernel/hrtimer.c
 *
 *  Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
 *  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/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 <linux/debugobjects.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);
                xts = current_kernel_time();
                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);
}

/*
 * 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);

/**
 * ktime_sub_ns - Subtract a scalar nanoseconds value from a ktime_t variable
 * @kt:         minuend
 * @nsec:       the scalar nsec value to subtract
 *
 * Returns the subtraction of @nsec from @kt in ktime_t format
 */
ktime_t ktime_sub_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_sub(kt, tmp);
}

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

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

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

        return dclc;
}
#endif /* BITS_PER_LONG >= 64 */

/*
 * Add two ktime values and do a safety check for overflow:
 */
ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs)
{
        ktime_t res = ktime_add(lhs, rhs);

        /*
         * We use KTIME_SEC_MAX here, the maximum timeout which we can
         * return to user space in a timespec:
         */
        if (res.tv64 < 0 || res.tv64 < lhs.tv64 || res.tv64 < rhs.tv64)
                res = ktime_set(KTIME_SEC_MAX, 0);

        return res;
}

#ifdef CONFIG_DEBUG_OBJECTS_TIMERS

static struct debug_obj_descr hrtimer_debug_descr;

/*
 * fixup_init is called when:
 * - an active object is initialized
 */
static int hrtimer_fixup_init(void *addr, enum debug_obj_state state)
{
        struct hrtimer *timer = addr;

        switch (state) {
        case ODEBUG_STATE_ACTIVE:
                hrtimer_cancel(timer);
                debug_object_init(timer, &hrtimer_debug_descr);
                return 1;
        default:
                return 0;
        }
}

/*
 * fixup_activate is called when:
 * - an active object is activated
 * - an unknown object is activated (might be a statically initialized object)
 */
static int hrtimer_fixup_activate(void *addr, enum debug_obj_state state)
{
        switch (state) {

        case ODEBUG_STATE_NOTAVAILABLE:
                WARN_ON_ONCE(1);
                return 0;

        case ODEBUG_STATE_ACTIVE:
                WARN_ON(1);

        default:
                return 0;
        }
}

/*
 * fixup_free is called when:
 * - an active object is freed
 */
static int hrtimer_fixup_free(void *addr, enum debug_obj_state state)
{
        struct hrtimer *timer = addr;

        switch (state) {
        case ODEBUG_STATE_ACTIVE:
                hrtimer_cancel(timer);
                debug_object_free(timer, &hrtimer_debug_descr);
                return 1;
        default:
                return 0;
        }
}

static struct debug_obj_descr hrtimer_debug_descr = {
        .name           = "hrtimer",
        .fixup_init     = hrtimer_fixup_init,
        .fixup_activate = hrtimer_fixup_activate,
        .fixup_free     = hrtimer_fixup_free,
};

static inline void debug_hrtimer_init(struct hrtimer *timer)
{
        debug_object_init(timer, &hrtimer_debug_descr);
}

static inline void debug_hrtimer_activate(struct hrtimer *timer)
{
        debug_object_activate(timer, &hrtimer_debug_descr);
}

static inline void debug_hrtimer_deactivate(struct hrtimer *timer)
{
        debug_object_deactivate(timer, &hrtimer_debug_descr);
}

static inline void debug_hrtimer_free(struct hrtimer *timer)
{
        debug_object_free(timer, &hrtimer_debug_descr);
}

static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
                           enum hrtimer_mode mode);

void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id,
                           enum hrtimer_mode mode)
{
        debug_object_init_on_stack(timer, &hrtimer_debug_descr);
        __hrtimer_init(timer, clock_id, mode);
}

void destroy_hrtimer_on_stack(struct hrtimer *timer)
{
        debug_object_free(timer, &hrtimer_debug_descr);
}

#else
static inline void debug_hrtimer_init(struct hrtimer *timer) { }
static inline void debug_hrtimer_activate(struct hrtimer *timer) { }
static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
#endif

/* 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(struct hrtimer_cpu_base *cpu_base)
{
        return cpu_base->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(hrtimer_get_expires(timer), base->offset);
                /*
                 * clock_was_set() has changed base->offset so the
                 * result might be negative. Fix it up to prevent a
                 * false positive in clockevents_program_event()
                 */
                if (expires.tv64 < 0)
                        expires.tv64 = 0;
                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(hrtimer_get_expires(timer), base->offset);
        int res;

        WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);

        /*
         * 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_interrupt context. The
         * reprogramming is handled at the end of the hrtimer_interrupt.
         */
        if (hrtimer_callback_running(timer))
                return 0;

        /*
         * CLOCK_REALTIME timer might be requested with an absolute
         * expiry time which is less than base->offset. Nothing wrong
         * about that, just avoid to call into the tick code, which
         * has now objections against negative expiry values.
         */
        if (expires.tv64 < 0)
                return -ETIME;

        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 = &__get_cpu_var(hrtimer_bases);

        struct timespec realtime_offset;
        unsigned long seq;

        if (!hrtimer_hres_active(base))
                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));

        /* 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, 1);
}

/*
 * During resume we might have to reprogram the high resolution timer
 * interrupt (on the local CPU):
 */
void hres_timers_resume(void)
{
        WARN_ONCE(!irqs_disabled(),
                  KERN_INFO "hres_timers_resume() called with IRQs enabled!");

        retrigger_next_event(NULL);
}

/*
 * Initialize the high resolution related parts of cpu_base
 */
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
{
        base->expires_next.tv64 = KTIME_MAX;
        base->hres_active = 0;
}

/*
 * Initialize the high resolution related parts of a hrtimer
 */
static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
{
}

static void __run_hrtimer(struct hrtimer *timer);
static int hrtimer_rt_defer(struct hrtimer *timer);

/*
 * When High resolution timers are active, try to reprogram. Note, that in case
 * the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry
 * check happens. The timer gets enqueued into the rbtree. The reprogramming
 * and expiry check is done in the hrtimer_interrupt or in the softirq.
 */
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
                                            struct hrtimer_clock_base *base,
                                            int wakeup)
{
#ifdef CONFIG_PREEMPT_RT
again:
#endif
        if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
#ifdef CONFIG_PREEMPT_RT
                /*
                 * Move softirq based timers away from the rbtree in
                 * case it expired already. Otherwise we would have a
                 * stale base->first entry until the softirq runs.
                 */
                if (!hrtimer_rt_defer(timer)) {
                        __run_hrtimer(timer);
                        /*
                         * __run_hrtimer might have requeued timer and
                         * it could be base->first again.
                         */
                        if (base->first == &timer->node)
                                goto again;
                        return 1;
                }
#endif
                if (wakeup) {
                        spin_unlock(&base->cpu_base->lock);
                        raise_softirq_irqoff(HRTIMER_SOFTIRQ);
                        spin_lock(&base->cpu_base->lock);
                } else
                        __raise_softirq_irqoff(HRTIMER_SOFTIRQ);

                return 1;
        }

        return 0;
}

/*
 * Switch to high resolution mode
 */
static int hrtimer_switch_to_hres(struct hrtimer_cpu_base *base)
{
        unsigned long flags;

        if (base->hres_active)
                return 1;

        local_irq_save(flags);

        if (tick_init_highres()) {
                local_irq_restore(flags);
                printk(KERN_WARNING "Could not switch to high resolution "
                       "mode on CPU %d\n", raw_smp_processor_id());
                return 0;
        }
        base->hres_active = 1;
        base->clock_base[CLOCK_REALTIME].resolution = KTIME_HIGH_RES;
        base->clock_base[CLOCK_MONOTONIC].resolution = KTIME_HIGH_RES;

        tick_setup_sched_timer();

        /* "Retrigger" the interrupt to get things going */
        retrigger_next_event(NULL);
        local_irq_restore(flags);
        return 1;
}

#else

static inline int hrtimer_hres_active(struct hrtimer_cpu_base *base)
{
        return 0;
}
static inline int hrtimer_is_hres_enabled(void) { return 0; }
static inline int hrtimer_switch_to_hres(struct hrtimer_cpu_base *base)
{
        return 0;
}
static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base) { }
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
                                            struct hrtimer_clock_base *base,
                                            int wakeup)
{
        return 0;
}

static inline int hrtimer_reprogram(struct hrtimer *timer,
                                    struct hrtimer_clock_base *base)
{
        return 0;
}

static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { }

#endif /* CONFIG_HIGH_RES_TIMERS */

#ifdef CONFIG_TIMER_STATS
void __timer_stats_hrtimer_set_start_info(struct hrtimer *timer, void *addr)
{
        if (timer->start_site)
                return;

        timer->start_site = addr;
        memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
        timer->start_pid = current->pid;
}
#endif

/*
 * Counterpart to lock_hrtimer_base above:
 */
static inline
void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
{
        spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags);
}

/**
 * hrtimer_forward - forward the timer expiry
 * @timer:      hrtimer to forward
 * @now:        forward past this time
 * @interval:   the interval to forward
 *
 * Forward the timer expiry so it will expire in the future.
 * Returns the number of overruns.
 */
u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
{
        u64 orun = 1;
        ktime_t delta;

        delta = ktime_sub(now, hrtimer_get_expires(timer));

        if (delta.tv64 < 0)
                return 0;

        if (interval.tv64 < timer->base->resolution.tv64)
                interval.tv64 = timer->base->resolution.tv64;

        if (unlikely(delta.tv64 >= interval.tv64)) {
                s64 incr = ktime_to_ns(interval);

                orun = ktime_divns(delta, incr);
                hrtimer_add_expires_ns(timer, incr * orun);
                if (hrtimer_get_expires_tv64(timer) > now.tv64)
                        return orun;
                /*
                 * This (and the ktime_add() below) is the
                 * correction for exact:
                 */
                orun++;
        }
        hrtimer_add_expires(timer, interval);

        return orun;
}
EXPORT_SYMBOL_GPL(hrtimer_forward);

/*
 * enqueue_hrtimer - internal function to (re)start a timer
 *
 * The timer is inserted in expiry order. Insertion into the
 * red black tree is O(log(n)). Must hold the base lock.
 *
 * Returns 1 when the new timer is the leftmost timer in the tree.
 */
static int enqueue_hrtimer(struct hrtimer *timer,
                           struct hrtimer_clock_base *base)
{
        struct rb_node **link = &base->active.rb_node;
        struct rb_node *parent = NULL;
        struct hrtimer *entry;
        int leftmost = 1;

        debug_hrtimer_activate(timer);

        /*
         * Find the right place in the rbtree:
         */
        while (*link) {
                parent = *link;
                entry = rb_entry(parent, struct hrtimer, node);
                /*
                 * We dont care about collisions. Nodes with
                 * the same expiry time stay together.
                 */
                if (hrtimer_get_expires_tv64(timer) <
                                hrtimer_get_expires_tv64(entry)) {
                        link = &(*link)->rb_left;
                } else {
                        link = &(*link)->rb_right;
                        leftmost = 0;
                }
        }

        /*
         * Insert the timer to the rbtree and check whether it
         * replaces the first pending timer
         */
        if (leftmost)
                base->first = &timer->node;

        rb_link_node(&timer->node, parent, link);
        rb_insert_color(&timer->node, &base->active);
        /*
         * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
         * state of a possibly running callback.
         */
        timer->state |= HRTIMER_STATE_ENQUEUED;

        return leftmost;
}

#ifdef CONFIG_PREEMPT_SOFTIRQS
# define wake_up_timer_waiters(b)       wake_up(&(b)->wait)

/**
 * hrtimer_wait_for_timer - Wait for a running timer
 *
 * @timer:      timer to wait for
 *
 * The function waits in case the timers callback function is
 * currently executed on the waitqueue of the timer base. The
 * waitqueue is woken up after the timer callback function has
 * finished execution.
 */
void hrtimer_wait_for_timer(const struct hrtimer *timer)
{
        struct hrtimer_clock_base *base = timer->base;

        if (base && base->cpu_base && !timer->irqsafe)
                wait_event(base->cpu_base->wait,
                           !(timer->state & HRTIMER_STATE_CALLBACK));
}

#else
# define wake_up_timer_waiters(b)       do { } while (0)
#endif

/*
 * __remove_hrtimer - internal function to remove a timer
 *
 * Caller must hold the base lock.
 *
 * High resolution timer mode reprograms the clock event device when the
 * timer is the one which expires next. The caller can disable this by setting
 * reprogram to zero. This is useful, when the context does a reprogramming
 * anyway (e.g. timer interrupt)
 */
static void __remove_hrtimer(struct hrtimer *timer,
                             struct hrtimer_clock_base *base,
                             unsigned long newstate, int reprogram)
{
        if (timer->state & HRTIMER_STATE_ENQUEUED) {

                if (unlikely(!list_empty(&timer->cb_entry))) {
                        list_del_init(&timer->cb_entry);
                        goto out;
                }
                /*
                 * Remove the timer from the rbtree and replace the
                 * first entry pointer if necessary.
                 */
                if (base->first == &timer->node) {
                        base->first = rb_next(&timer->node);
                        /* Reprogram the clock event device. if enabled */
                        if (reprogram && hrtimer_hres_active(base->cpu_base))
                                hrtimer_force_reprogram(base->cpu_base);
                }
                rb_erase(&timer->node, &base->active);
        }
out:
        timer->state = newstate;
}

/*
 * remove hrtimer, called with base lock held
 */
static inline int
remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
{
        if (hrtimer_is_queued(timer)) {
                int reprogram;

                /*
                 * Remove the timer and force reprogramming when high
                 * resolution mode is active and the timer is on the current
                 * CPU. If we remove a timer on another CPU, reprogramming is
                 * skipped. The interrupt event on this CPU is fired and
                 * reprogramming happens in the interrupt handler. This is a
                 * rare case and less expensive than a smp call.
                 */
                debug_hrtimer_deactivate(timer);
                timer_stats_hrtimer_clear_start_info(timer);
                reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
                __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE,
                                 reprogram);
                return 1;
        }
        return 0;
}

int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
                unsigned long delta_ns, const enum hrtimer_mode mode,
                int wakeup)
{
        struct hrtimer_clock_base *base, *new_base;
        unsigned long flags;
        int ret, leftmost;

        base = lock_hrtimer_base(timer, &flags);

        /* Remove an active timer from the queue: */
        ret = remove_hrtimer(timer, base);

        /* Switch the timer base, if necessary: */
        new_base = switch_hrtimer_base(timer, base);

        if (mode == HRTIMER_MODE_REL) {
                tim = ktime_add_safe(tim, new_base->get_time());
                /*
                 * CONFIG_TIME_LOW_RES is a temporary way for architectures
                 * to signal that they simply return xtime in
                 * do_gettimeoffset(). In this case we want to round up by
                 * resolution when starting a relative timer, to avoid short
                 * timeouts. This will go away with the GTOD framework.
                 */
#ifdef CONFIG_TIME_LOW_RES
                tim = ktime_add_safe(tim, base->resolution);
#endif
        }

        hrtimer_set_expires_range_ns(timer, tim, delta_ns);

        timer_stats_hrtimer_set_start_info(timer);

        leftmost = enqueue_hrtimer(timer, new_base);

        /*
         * Only allow reprogramming if the new base is on this CPU.
         * (it might still be on another CPU if the timer was pending)
         *
         * XXX send_remote_softirq() ?
         */
        if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases))
                hrtimer_enqueue_reprogram(timer, new_base, wakeup);

        unlock_hrtimer_base(timer, &flags);

        return ret;
}

/**
 * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
 * @timer:      the timer to be added
 * @tim:        expiry time
 * @delta_ns:   "slack" range for the timer
 * @mode:       expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
 *
 * Returns:
 *  0 on success
 *  1 when the timer was active
 */
int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
                unsigned long delta_ns, const enum hrtimer_mode mode)
{
        return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1);
}
EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);

/**
 * hrtimer_start - (re)start an hrtimer on the current CPU
 * @timer:      the timer to be added
 * @tim:        expiry time
 * @mode:       expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
 *
 * Returns:
 *  0 on success
 *  1 when the timer was active
 */
int
hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
{
        return __hrtimer_start_range_ns(timer, tim, 0, mode, 1);
}
EXPORT_SYMBOL_GPL(hrtimer_start);


/**
 * hrtimer_try_to_cancel - try to deactivate a timer
 * @timer:      hrtimer to stop
 *
 * Returns:
 *  0 when the timer was not active
 *  1 when the timer was active
 * -1 when the timer is currently excuting the callback function and
 *    cannot be stopped
 */
int hrtimer_try_to_cancel(struct hrtimer *timer)
{
        struct hrtimer_clock_base *base;
        unsigned long flags;
        int ret = -1;

        base = lock_hrtimer_base(timer, &flags);

        if (!hrtimer_callback_running(timer))
                ret = remove_hrtimer(timer, base);

        unlock_hrtimer_base(timer, &flags);

        return ret;

}
EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel);

/**
 * hrtimer_cancel - cancel a timer and wait for the handler to finish.
 * @timer:      the timer to be cancelled
 *
 * Returns:
 *  0 when the timer was not active
 *  1 when the timer was active
 */
int hrtimer_cancel(struct hrtimer *timer)
{
        for (;;) {
                int ret = hrtimer_try_to_cancel(timer);

                if (ret >= 0)
                        return ret;
                hrtimer_wait_for_timer(timer);
        }
}
EXPORT_SYMBOL_GPL(hrtimer_cancel);

/**
 * hrtimer_get_remaining - get remaining time for the timer
 * @timer:      the timer to read
 */
ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
{
        struct hrtimer_clock_base *base;
        unsigned long flags;
        ktime_t rem;

        base = lock_hrtimer_base(timer, &flags);
        rem = hrtimer_expires_remaining(timer);
        unlock_hrtimer_base(timer, &flags);

        return rem;
}
EXPORT_SYMBOL_GPL(hrtimer_get_remaining);

#ifdef CONFIG_NO_HZ
/**
 * hrtimer_get_next_event - get the time until next expiry event
 *
 * Returns the delta to the next expiry event or KTIME_MAX if no timer
 * is pending.
 */
ktime_t hrtimer_get_next_event(void)
{
        struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
        struct hrtimer_clock_base *base = cpu_base->clock_base;
        ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
        unsigned long flags;
        int i;

        spin_lock_irqsave(&cpu_base->lock, flags);

        if (!hrtimer_hres_active(cpu_base)) {
                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);
                        delta.tv64 = hrtimer_get_expires_tv64(timer);
                        delta = ktime_sub(delta, base->get_time());
                        if (delta.tv64 < mindelta.tv64)
                                mindelta.tv64 = delta.tv64;
                }
        }

        spin_unlock_irqrestore(&cpu_base->lock, flags);

        if (mindelta.tv64 < 0)
                mindelta.tv64 = 0;
        return mindelta;
}
#endif

static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
                           enum hrtimer_mode mode)
{
        struct hrtimer_cpu_base *cpu_base;

        memset(timer, 0, sizeof(struct hrtimer));

        cpu_base = &__raw_get_cpu_var(hrtimer_bases);

        if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
                clock_id = CLOCK_MONOTONIC;

        timer->base = &cpu_base->clock_base[clock_id];
        INIT_LIST_HEAD(&timer->cb_entry);
        hrtimer_init_timer_hres(timer);

#ifdef CONFIG_TIMER_STATS
        timer->start_site = NULL;
        timer->start_pid = -1;
        memset(timer->start_comm, 0, TASK_COMM_LEN);
#endif
}

/**
 * hrtimer_init - initialize a timer to the given clock
 * @timer:      the timer to be initialized
 * @clock_id:   the clock to be used
 * @mode:       timer mode abs/rel
 */
void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
                  enum hrtimer_mode mode)
{
        debug_hrtimer_init(timer);
        __hrtimer_init(timer, clock_id, mode);
}
EXPORT_SYMBOL_GPL(hrtimer_init);

/**
 * hrtimer_get_res - get the timer resolution for a clock
 * @which_clock: which clock to query
 * @tp:          pointer to timespec variable to store the resolution
 *
 * Store the resolution of the clock selected by @which_clock in the
 * variable pointed to by @tp.
 */
int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
{
        struct hrtimer_cpu_base *cpu_base;

        cpu_base = &__raw_get_cpu_var(hrtimer_bases);
        *tp = ktime_to_timespec(cpu_base->clock_base[which_clock].resolution);

        return 0;
}
EXPORT_SYMBOL_GPL(hrtimer_get_res);

static void __run_hrtimer(struct hrtimer *timer)
{
        struct hrtimer_clock_base *base = timer->base;
        struct hrtimer_cpu_base *cpu_base = base->cpu_base;
        enum hrtimer_restart (*fn)(struct hrtimer *);
        int restart;

        WARN_ON(!irqs_disabled());

        debug_hrtimer_deactivate(timer);
        __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
        timer_stats_account_hrtimer(timer);
        fn = timer->function;

        /*
         * Because we run timers from hardirq context, there is no chance
         * they get migrated to another cpu, therefore its safe to unlock
         * the timer base.
         */
        spin_unlock(&cpu_base->lock);
        restart = fn(timer);
        spin_lock(&cpu_base->lock);

        /*
         * Note: We clear the CALLBACK bit after enqueue_hrtimer and
         * we do not reprogramm the event hardware. Happens either in
         * hrtimer_start_range_ns() or in hrtimer_interrupt()
         */
        if (restart != HRTIMER_NORESTART) {
                BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
                enqueue_hrtimer(timer, base);
        }
        timer->state &= ~HRTIMER_STATE_CALLBACK;
}

#ifdef CONFIG_PREEMPT_RT

static void hrtimer_rt_reprogram(int restart, struct hrtimer *timer,
                                 struct hrtimer_clock_base *base)
{
        /*
         * Note, we clear the callback flag before we requeue the
         * timer otherwise we trigger the callback_running() check
         * in hrtimer_reprogram().
         */
        timer->state &= ~HRTIMER_STATE_CALLBACK;

        if (restart != HRTIMER_NORESTART) {
                BUG_ON(hrtimer_active(timer));
                /*
                 * Enqueue the timer, if it's the leftmost timer then
                 * we need to reprogram it.
                 */
                if (!enqueue_hrtimer(timer, base))
                        return;

                if (hrtimer_reprogram(timer, base))
                        goto requeue;

        } else if (hrtimer_active(timer)) {
                /*
                 * If the timer was rearmed on another CPU, reprogram
                 * the event device.
                 */
                if (base->first == &timer->node &&
                    hrtimer_reprogram(timer, base))
                        goto requeue;
        }
        return;

requeue:
        /*
         * Timer is expired. Thus move it from tree to pending list
         * again.
         */
        __remove_hrtimer(timer, base, timer->state, 0);
        list_add_tail(&timer->cb_entry, &base->expired);
}

/*
 * The changes in mainline which removed the callback modes from
 * hrtimer are not yet working with -rt. The non wakeup_process()
 * based callbacks which involve sleeping locks need to be treated
 * seperately.
 */
static void hrtimer_rt_run_pending(void)
{
        enum hrtimer_restart (*fn)(struct hrtimer *);
        struct hrtimer_cpu_base *cpu_base;
        struct hrtimer_clock_base *base;
        struct hrtimer *timer;
        int index, restart;

        local_irq_disable();
        cpu_base = &per_cpu(hrtimer_bases, smp_processor_id());

        spin_lock(&cpu_base->lock);

        for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
                base = &cpu_base->clock_base[index];

                while (!list_empty(&base->expired)) {
                        timer = list_first_entry(&base->expired,
                                                 struct hrtimer, cb_entry);

                        /*
                         * Same as the above __run_hrtimer function
                         * just we run with interrupts enabled.
                         */
                        debug_hrtimer_deactivate(timer);
                        __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
                        timer_stats_account_hrtimer(timer);
                        fn = timer->function;

                        spin_unlock_irq(&cpu_base->lock);
                        restart = fn(timer);
                        spin_lock_irq(&cpu_base->lock);

                        hrtimer_rt_reprogram(restart, timer, base);
                }
        }
        spin_unlock_irq(&cpu_base->lock);

        wake_up_timer_waiters(cpu_base);
}

static int hrtimer_rt_defer(struct hrtimer *timer)
{
        if (timer->irqsafe)
                return 0;

        __remove_hrtimer(timer, timer->base, timer->state, 0);
        list_add_tail(&timer->cb_entry, &timer->base->expired);
        return 1;
}

#else

static inline void hrtimer_rt_run_pending(void) { }
static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; }

#endif

#ifdef CONFIG_HIGH_RES_TIMERS

static int force_clock_reprogram;

/*
 * After 5 iteration's attempts, we consider that hrtimer_interrupt()
 * is hanging, which could happen with something that slows the interrupt
 * such as the tracing. Then we force the clock reprogramming for each future
 * hrtimer interrupts to avoid infinite loops and use the min_delta_ns
 * threshold that we will overwrite.
 * The next tick event will be scheduled to 3 times we currently spend on
 * hrtimer_interrupt(). This gives a good compromise, the cpus will spend
 * 1/4 of their time to process the hrtimer interrupts. This is enough to
 * let it running without serious starvation.
 */

static inline void
hrtimer_interrupt_hanging(struct clock_event_device *dev,
                        ktime_t try_time)
{
        force_clock_reprogram = 1;
        dev->min_delta_ns = (unsigned long)try_time.tv64 * 3;
        printk(KERN_WARNING "hrtimer: interrupt too slow, "
                "forcing clock min delta to %lu ns\n", dev->min_delta_ns);
}
/*
 * High resolution timer interrupt
 * Called with interrupts disabled
 */
void hrtimer_interrupt(struct clock_event_device *dev)
{
        struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
        struct hrtimer_clock_base *base;
        ktime_t expires_next, now;
        int nr_retries = 0;
        int i, raise = 0;

        BUG_ON(!cpu_base->hres_active);
        cpu_base->nr_events++;
        dev->next_event.tv64 = KTIME_MAX;

 retry:
        /* 5 retries is enough to notice a hang */
        if (!(++nr_retries % 5))
                hrtimer_interrupt_hanging(dev, ktime_sub(ktime_get(), now));

        now = ktime_get();

        expires_next.tv64 = KTIME_MAX;

        base = cpu_base->clock_base;

        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
                ktime_t basenow;
                struct rb_node *node;

                spin_lock(&cpu_base->lock);

                basenow = ktime_add(now, base->offset);

                while ((node = base->first)) {
                        struct hrtimer *timer;

                        timer = rb_entry(node, struct hrtimer, node);

                        /*
                         * The immediate goal for using the softexpires is
                         * minimizing wakeups, not running timers at the
                         * earliest interrupt after their soft expiration.
                         * This allows us to avoid using a Priority Search
                         * Tree, which can answer a stabbing querry for
                         * overlapping intervals and instead use the simple
                         * BST we already have.
                         * We don't add extra wakeups by delaying timers that
                         * are right-of a not yet expired timer, because that
                         * timer will have to trigger a wakeup anyway.
                         */

                        if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
                                ktime_t expires;

                                expires = ktime_sub(hrtimer_get_expires(timer),
                                                    base->offset);
                                if (expires.tv64 < expires_next.tv64)
                                        expires_next = expires;
                                break;
                        }

                        if (!hrtimer_rt_defer(timer))
                                __run_hrtimer(timer);
                        else
                                raise = 1;
                }
                spin_unlock(&cpu_base->lock);
                base++;
        }

        cpu_base->expires_next = expires_next;

        /* Reprogramming necessary ? */
        if (expires_next.tv64 != KTIME_MAX) {
                if (tick_program_event(expires_next, force_clock_reprogram))
                        goto retry;
        }

        if (raise)
                raise_softirq_irqoff(HRTIMER_SOFTIRQ);
}

/*
 * local version of hrtimer_peek_ahead_timers() called with interrupts
 * disabled.
 */
static void __hrtimer_peek_ahead_timers(void)
{
        struct hrtimer_cpu_base *cpu_base;
        struct tick_device *td;

        cpu_base = &__get_cpu_var(hrtimer_bases);
        if (!hrtimer_hres_active(cpu_base))
                return;

        td = &__get_cpu_var(tick_cpu_device);
        if (td && td->evtdev)
                hrtimer_interrupt(td->evtdev);
}

/**
 * hrtimer_peek_ahead_timers -- run soft-expired timers now
 *
 * hrtimer_peek_ahead_timers will peek at the timer queue of
 * the current cpu and check if there are any timers for which
 * the soft expires time has passed. If any such timers exist,
 * they are run immediately and then removed from the timer queue.
 *
 */
void hrtimer_peek_ahead_timers(void)
{
        unsigned long flags;

        local_irq_save(flags);
        __hrtimer_peek_ahead_timers();
        local_irq_restore(flags);
}

#else /* CONFIG_HIGH_RES_TIMERS */

static inline void __hrtimer_peek_ahead_timers(void) { }

#endif  /* !CONFIG_HIGH_RES_TIMERS */

static void run_hrtimer_softirq(struct softirq_action *h)
{
        hrtimer_rt_run_pending();
}

/*
 * Called from timer softirq every jiffy, expire hrtimers:
 *
 * For HRT its the fall back code to run the softirq in the timer
 * softirq context in case the hrtimer initialization failed or has
 * not been done yet.
 */
void hrtimer_run_pending(void)
{
        struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);

        if (hrtimer_hres_active(cpu_base))
                return;

        /*
         * This _is_ ugly: We have to check in the softirq context,
         * whether we can switch to highres and / or nohz mode. The
         * clocksource switch happens in the timer interrupt with
         * xtime_lock held. Notification from there only sets the
         * check bit in the tick_oneshot code, otherwise we might
         * deadlock vs. xtime_lock.
         */
        if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
                hrtimer_switch_to_hres(cpu_base);
}

/*
 * Called from hardirq context every jiffy
 */
void hrtimer_run_queues(void)
{
        struct rb_node *node;
        struct hrtimer_cpu_base *cpu_base;
        struct hrtimer_clock_base *base;
        int index, gettime = 1, raise = 0;

        cpu_base = &per_cpu(hrtimer_bases, raw_smp_processor_id());
        if (hrtimer_hres_active(cpu_base))
                return;

        for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
                base = &cpu_base->clock_base[index];

                if (!base->first)
                        continue;

                if (gettime) {
                        hrtimer_get_softirq_time(cpu_base);
                        gettime = 0;
                }

                spin_lock(&cpu_base->lock);

                while ((node = base->first)) {
                        struct hrtimer *timer;

                        timer = rb_entry(node, struct hrtimer, node);
                        if (base->softirq_time.tv64 <=
                                        hrtimer_get_expires_tv64(timer))
                                break;

                        if (!hrtimer_rt_defer(timer))
                                __run_hrtimer(timer);
                        else
                                raise = 1;
                }
                spin_unlock(&cpu_base->lock);
        }

        if (raise)
                raise_softirq_irqoff(HRTIMER_SOFTIRQ);
}

/*
 * Sleep related functions:
 */
static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer)
{
        struct hrtimer_sleeper *t =
                container_of(timer, struct hrtimer_sleeper, timer);
        struct task_struct *task = t->task;

        t->task = NULL;
        if (task)
                wake_up_process(task);

        return HRTIMER_NORESTART;
}

void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
{
        sl->timer.function = hrtimer_wakeup;
        sl->timer.irqsafe = 1;
        sl->task = task;
}

static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
{
        hrtimer_init_sleeper(t, current);

        do {
                set_current_state(TASK_INTERRUPTIBLE);
                hrtimer_start_expires(&t->timer, mode);
                if (!hrtimer_active(&t->timer))
                        t->task = NULL;

                if (likely(t->task))
                        schedule();

                hrtimer_cancel(&t->timer);
                mode = HRTIMER_MODE_ABS;

        } while (t->task && !signal_pending(current));

        __set_current_state(TASK_RUNNING);

        return t->task == NULL;
}

static int update_rmtp(struct hrtimer *timer, struct timespec __user *rmtp)
{
        struct timespec rmt;
        ktime_t rem;

        rem = hrtimer_expires_remaining(timer);
        if (rem.tv64 <= 0)
                return 0;
        rmt = ktime_to_timespec(rem);

        if (copy_to_user(rmtp, &rmt, sizeof(*rmtp)))
                return -EFAULT;

        return 1;
}

long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
{
        struct hrtimer_sleeper t;
        struct timespec __user  *rmtp;
        int ret = 0;

        hrtimer_init_on_stack(&t.timer, restart->nanosleep.index,
                                HRTIMER_MODE_ABS);
        hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);

        if (do_nanosleep(&t, HRTIMER_MODE_ABS))
                goto out;

        rmtp = restart->nanosleep.rmtp;
        if (rmtp) {
                ret = update_rmtp(&t.timer, rmtp);
                if (ret <= 0)
                        goto out;
        }

        /* The other values in restart are already filled in */
        ret = -ERESTART_RESTARTBLOCK;
out:
        destroy_hrtimer_on_stack(&t.timer);
        return ret;
}

long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
                       const enum hrtimer_mode mode, const clockid_t clockid)
{
        struct restart_block *restart;
        struct hrtimer_sleeper t;
        int ret = 0;
        unsigned long slack;

        slack = current->timer_slack_ns;
        if (rt_task(current))
                slack = 0;

        hrtimer_init_on_stack(&t.timer, clockid, mode);
        hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack);
        if (do_nanosleep(&t, mode))
                goto out;

        /* Absolute timers do not update the rmtp value and restart: */
        if (mode == HRTIMER_MODE_ABS) {
                ret = -ERESTARTNOHAND;
                goto out;
        }

        if (rmtp) {
                ret = update_rmtp(&t.timer, rmtp);
                if (ret <= 0)
                        goto out;
        }

        restart = &current_thread_info()->restart_block;
        restart->fn = hrtimer_nanosleep_restart;
        restart->nanosleep.index = t.timer.base->index;
        restart->nanosleep.rmtp = rmtp;
        restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer);

        ret = -ERESTART_RESTARTBLOCK;
out:
        destroy_hrtimer_on_stack(&t.timer);
        return ret;
}

SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
                struct timespec __user *, rmtp)
{
        struct timespec tu;

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

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

        return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}

/*
 * Functions related to boot-time initialization:
 */
static void __cpuinit init_hrtimers_cpu(int cpu)
{
        struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
        int i;

        spin_lock_init(&cpu_base->lock);

        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
                cpu_base->clock_base[i].cpu_base = cpu_base;
                INIT_LIST_HEAD(&cpu_base->clock_base[i].expired);
        }

        hrtimer_init_hres(cpu_base);
#ifdef CONFIG_PREEMPT_RT
        init_waitqueue_head(&cpu_base->wait);
#endif
}

#ifdef CONFIG_HOTPLUG_CPU

static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
                                struct hrtimer_clock_base *new_base)
{
        struct hrtimer *timer;
        struct rb_node *node;

        while ((node = rb_first(&old_base->active))) {
                timer = rb_entry(node, struct hrtimer, node);
                BUG_ON(hrtimer_callback_running(timer));
                debug_hrtimer_deactivate(timer);

                /*
                 * Mark it as STATE_MIGRATE not INACTIVE otherwise the
                 * timer could be seen as !active and just vanish away
                 * under us on another CPU
                 */
                __remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0);
                timer->base = new_base;
                /*
                 * Enqueue the timers on the new cpu. This does not
                 * reprogram the event device in case the timer
                 * expires before the earliest on this CPU, but we run
                 * hrtimer_interrupt after we migrated everything to
                 * sort out already expired timers and reprogram the
                 * event device.
                 */
                enqueue_hrtimer(timer, new_base);

                /* Clear the migration state bit */
                timer->state &= ~HRTIMER_STATE_MIGRATE;
        }
}

static void migrate_hrtimers(int scpu)
{
        struct hrtimer_cpu_base *old_base, *new_base;
        int i;

        BUG_ON(cpu_online(scpu));
        tick_cancel_sched_timer(scpu);

        local_irq_disable();
        old_base = &per_cpu(hrtimer_bases, scpu);
        new_base = &__get_cpu_var(hrtimer_bases);
        /*
         * The caller is globally serialized and nobody else
         * takes two locks at once, deadlock is not possible.
         */
        spin_lock(&new_base->lock);
        spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);

        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
                migrate_hrtimer_list(&old_base->clock_base[i],
                                     &new_base->clock_base[i]);
        }

        spin_unlock(&old_base->lock);
        spin_unlock(&new_base->lock);

        /* Check, if we got expired work to do */
        __hrtimer_peek_ahead_timers();
        local_irq_enable();
}

#endif /* CONFIG_HOTPLUG_CPU */

static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
                                        unsigned long action, void *hcpu)
{
        int scpu = (long)hcpu;

        switch (action) {

        case CPU_UP_PREPARE:
        case CPU_UP_PREPARE_FROZEN:
                init_hrtimers_cpu(scpu);
                break;

#ifdef CONFIG_HOTPLUG_CPU
        case CPU_DYING:
        case CPU_DYING_FROZEN:
                clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu);
                break;
        case CPU_DEAD:
        case CPU_DEAD_FROZEN:
        {
                clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu);
                migrate_hrtimers(scpu);
                break;
        }
#endif

        default:
                break;
        }

        return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata hrtimers_nb = {
        .notifier_call = hrtimer_cpu_notify,
};

void __init hrtimers_init(void)
{
        hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
                          (void *)(long)smp_processor_id());
        register_cpu_notifier(&hrtimers_nb);
        open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
}

/**
 * schedule_hrtimeout_range - sleep until timeout
 * @expires:    timeout value (ktime_t)
 * @delta:      slack in expires timeout (ktime_t)
 * @mode:       timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
 *
 * Make the current task sleep until the given expiry time has
 * elapsed. The routine will return immediately unless
 * the current task state has been set (see set_current_state()).
 *
 * The @delta argument gives the kernel the freedom to schedule the
 * actual wakeup to a time that is both power and performance friendly.
 * The kernel give the normal best effort behavior for "@expires+@delta",
 * but may decide to fire the timer earlier, but no earlier than @expires.
 *
 * You can set the task state as follows -
 *
 * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
 * pass before the routine returns.
 *
 * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
 * delivered to the current task.
 *
 * The current task state is guaranteed to be TASK_RUNNING when this
 * routine returns.
 *
 * Returns 0 when the timer has expired otherwise -EINTR
 */
int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
                               const enum hrtimer_mode mode)
{
        struct hrtimer_sleeper t;

        /*
         * Optimize when a zero timeout value is given. It does not
         * matter whether this is an absolute or a relative time.
         */
        if (expires && !expires->tv64) {
                __set_current_state(TASK_RUNNING);
                return 0;
        }

        /*
         * A NULL parameter means "inifinte"
         */
        if (!expires) {
                schedule();
                __set_current_state(TASK_RUNNING);
                return -EINTR;
        }

        hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode);
        hrtimer_set_expires_range_ns(&t.timer, *expires, delta);

        hrtimer_init_sleeper(&t, current);

        hrtimer_start_expires(&t.timer, mode);
        if (!hrtimer_active(&t.timer))
                t.task = NULL;

        if (likely(t.task))
                schedule();

        hrtimer_cancel(&t.timer);
        destroy_hrtimer_on_stack(&t.timer);

        __set_current_state(TASK_RUNNING);

        return !t.task ? 0 : -EINTR;
}
EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);

/**
 * schedule_hrtimeout - sleep until timeout
 * @expires:    timeout value (ktime_t)
 * @mode:       timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
 *
 * Make the current task sleep until the given expiry time has
 * 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 time is guaranteed to
 * pass before the routine returns.
 *
 * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
 * delivered to the current task.
 *
 * The current task state is guaranteed to be TASK_RUNNING when this
 * routine returns.
 *
 * Returns 0 when the timer has expired otherwise -EINTR
 */
int __sched schedule_hrtimeout(ktime_t *expires,
                               const enum hrtimer_mode mode)
{
        return schedule_hrtimeout_range(expires, 0, mode);
}
EXPORT_SYMBOL_GPL(schedule_hrtimeout);