These changes are the raw update to linux-4.4.6-rt14. Kernel sources

[kvmfornfv.git] / kernel / kernel / time / 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/export.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 <linux/sched.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
#include <linux/sched/deadline.h>
#include <linux/timer.h>
#include <linux/kthread.h>
#include <linux/freezer.h>

#include <asm/uaccess.h>

#include <trace/events/timer.h>
#include <trace/events/hist.h>

#include "tick-internal.h"

/*
 * The timer bases:
 *
 * There are more clockids than hrtimer bases. Thus, we index
 * into the timer bases by the hrtimer_base_type enum. When trying
 * to reach a base using a clockid, hrtimer_clockid_to_base()
 * is used to convert from clockid to the proper hrtimer_base_type.
 */
DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
{
        .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
        .seq = SEQCNT_ZERO(hrtimer_bases.seq),
        .clock_base =
        {
                {
                        .index = HRTIMER_BASE_MONOTONIC,
                        .clockid = CLOCK_MONOTONIC,
                        .get_time = &ktime_get,
                },
                {
                        .index = HRTIMER_BASE_REALTIME,
                        .clockid = CLOCK_REALTIME,
                        .get_time = &ktime_get_real,
                },
                {
                        .index = HRTIMER_BASE_BOOTTIME,
                        .clockid = CLOCK_BOOTTIME,
                        .get_time = &ktime_get_boottime,
                },
                {
                        .index = HRTIMER_BASE_TAI,
                        .clockid = CLOCK_TAI,
                        .get_time = &ktime_get_clocktai,
                },
        }
};

static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
        [CLOCK_REALTIME]        = HRTIMER_BASE_REALTIME,
        [CLOCK_MONOTONIC]       = HRTIMER_BASE_MONOTONIC,
        [CLOCK_BOOTTIME]        = HRTIMER_BASE_BOOTTIME,
        [CLOCK_TAI]             = HRTIMER_BASE_TAI,
};

static inline int hrtimer_clockid_to_base(clockid_t clock_id)
{
        return hrtimer_clock_to_base_table[clock_id];
}

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

/*
 * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base()
 * such that hrtimer_callback_running() can unconditionally dereference
 * timer->base->cpu_base
 */
static struct hrtimer_cpu_base migration_cpu_base = {
        .seq = SEQCNT_ZERO(migration_cpu_base),
        .clock_base = { { .cpu_base = &migration_cpu_base, }, },
};

#define migration_base  migration_cpu_base.clock_base[0]

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

/*
 * With HIGHRES=y we do not migrate the timer when it is expiring
 * before the next event on the target cpu because we cannot reprogram
 * the target cpu hardware and we would cause it to fire late.
 *
 * Called with cpu_base->lock of target cpu held.
 */
static int
hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
{
#ifdef CONFIG_HIGH_RES_TIMERS
        ktime_t expires;

        if (!new_base->cpu_base->hres_active)
                return 0;

        expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
        return expires.tv64 <= new_base->cpu_base->expires_next.tv64;
#else
        return 0;
#endif
}

#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
static inline
struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
                                         int pinned)
{
        if (pinned || !base->migration_enabled)
                return base;
        return &per_cpu(hrtimer_bases, get_nohz_timer_target());
}
#else
static inline
struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
                                         int pinned)
{
        return base;
}
#endif

/*
 * We switch the timer base to a power-optimized selected CPU target,
 * if:
 *      - NO_HZ_COMMON is enabled
 *      - timer migration is enabled
 *      - the timer callback is not running
 *      - the timer is not the first expiring timer on the new target
 *
 * If one of the above requirements is not fulfilled we move the timer
 * to the current CPU or leave it on the previously assigned CPU if
 * the timer callback is currently running.
 */
static inline struct hrtimer_clock_base *
switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
                    int pinned)
{
        struct hrtimer_cpu_base *new_cpu_base, *this_cpu_base;
        struct hrtimer_clock_base *new_base;
        int basenum = base->index;

        this_cpu_base = this_cpu_ptr(&hrtimer_bases);
        new_cpu_base = get_target_base(this_cpu_base, pinned);
again:
        new_base = &new_cpu_base->clock_base[basenum];

        if (base != new_base) {
                /*
                 * We are trying to move timer to new_base.
                 * 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_hrtimer_base() */
                timer->base = &migration_base;
                raw_spin_unlock(&base->cpu_base->lock);
                raw_spin_lock(&new_base->cpu_base->lock);

                if (new_cpu_base != this_cpu_base &&
                    hrtimer_check_target(timer, new_base)) {
                        raw_spin_unlock(&new_base->cpu_base->lock);
                        raw_spin_lock(&base->cpu_base->lock);
                        new_cpu_base = this_cpu_base;
                        timer->base = base;
                        goto again;
                }
                timer->base = new_base;
        } else {
                if (new_cpu_base != this_cpu_base &&
                    hrtimer_check_target(timer, new_base)) {
                        new_cpu_base = this_cpu_base;
                        goto again;
                }
        }
        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;

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

        return base;
}

# define switch_hrtimer_base(t, b, p)   (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
/*
 * Divide a ktime value by a nanosecond value
 */
s64 __ktime_divns(const ktime_t kt, s64 div)
{
        int sft = 0;
        s64 dclc;
        u64 tmp;

        dclc = ktime_to_ns(kt);
        tmp = dclc < 0 ? -dclc : dclc;

        /* Make sure the divisor is less than 2^32: */
        while (div >> 32) {
                sft++;
                div >>= 1;
        }
        tmp >>= sft;
        do_div(tmp, (unsigned long) div);
        return dclc < 0 ? -tmp : tmp;
}
EXPORT_SYMBOL_GPL(__ktime_divns);
#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;
}

EXPORT_SYMBOL_GPL(ktime_add_safe);

#ifdef CONFIG_DEBUG_OBJECTS_TIMERS

static struct debug_obj_descr hrtimer_debug_descr;

static void *hrtimer_debug_hint(void *addr)
{
        return ((struct hrtimer *) addr)->function;
}

/*
 * 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",
        .debug_hint     = hrtimer_debug_hint,
        .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);
}
EXPORT_SYMBOL_GPL(hrtimer_init_on_stack);

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

static inline void
debug_init(struct hrtimer *timer, clockid_t clockid,
           enum hrtimer_mode mode)
{
        debug_hrtimer_init(timer);
        trace_hrtimer_init(timer, clockid, mode);
}

static inline void debug_activate(struct hrtimer *timer)
{
        debug_hrtimer_activate(timer);
        trace_hrtimer_start(timer);
}

static inline void debug_deactivate(struct hrtimer *timer)
{
        debug_hrtimer_deactivate(timer);
        trace_hrtimer_cancel(timer);
}

#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
static inline void hrtimer_update_next_timer(struct hrtimer_cpu_base *cpu_base,
                                             struct hrtimer *timer)
{
#ifdef CONFIG_HIGH_RES_TIMERS
        cpu_base->next_timer = timer;
#endif
}

static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
{
        struct hrtimer_clock_base *base = cpu_base->clock_base;
        ktime_t expires, expires_next = { .tv64 = KTIME_MAX };
        unsigned int active = cpu_base->active_bases;

        hrtimer_update_next_timer(cpu_base, NULL);
        for (; active; base++, active >>= 1) {
                struct timerqueue_node *next;
                struct hrtimer *timer;

                if (!(active & 0x01))
                        continue;

                next = timerqueue_getnext(&base->active);
                timer = container_of(next, struct hrtimer, node);
                expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
                if (expires.tv64 < expires_next.tv64) {
                        expires_next = expires;
                        hrtimer_update_next_timer(cpu_base, timer);
                }
        }
        /*
         * clock_was_set() might have changed base->offset of any of
         * the clock bases so the result might be negative. Fix it up
         * to prevent a false positive in clockevents_program_event().
         */
        if (expires_next.tv64 < 0)
                expires_next.tv64 = 0;
        return expires_next;
}
#endif

static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
{
        ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
        ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
        ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;

        return ktime_get_update_offsets_now(&base->clock_was_set_seq,
                                            offs_real, offs_boot, offs_tai);
}

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

/*
 * High resolution timer enabled ?
 */
static int hrtimer_hres_enabled __read_mostly  = 1;
unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC;
EXPORT_SYMBOL_GPL(hrtimer_resolution);

/*
 * 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;
}

static inline int hrtimer_hres_active(void)
{
        return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases));
}

/*
 * 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 skip_equal)
{
        ktime_t expires_next;

        if (!cpu_base->hres_active)
                return;

        expires_next = __hrtimer_get_next_event(cpu_base);

        if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
                return;

        cpu_base->expires_next.tv64 = expires_next.tv64;

        /*
         * If a hang was detected in the last timer interrupt then we
         * leave the hang delay active in the hardware. We want the
         * system to make progress. That also prevents the following
         * scenario:
         * T1 expires 50ms from now
         * T2 expires 5s from now
         *
         * T1 is removed, so this code is called and would reprogram
         * the hardware to 5s from now. Any hrtimer_start after that
         * will not reprogram the hardware due to hang_detected being
         * set. So we'd effectivly block all timers until the T2 event
         * fires.
         */
        if (cpu_base->hang_detected)
                return;

        tick_program_event(cpu_base->expires_next, 1);
}

/*
 * 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 void hrtimer_reprogram(struct hrtimer *timer,
                              struct hrtimer_clock_base *base)
{
        struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
        ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);

        WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);

        /*
         * If the timer is not on the current cpu, we cannot reprogram
         * the other cpus clock event device.
         */
        if (base->cpu_base != cpu_base)
                return;

        /*
         * If the hrtimer interrupt is running, then it will
         * reevaluate the clock bases and reprogram the clock event
         * device. The callbacks are always executed in hard interrupt
         * context so we don't need an extra check for a running
         * callback.
         */
        if (cpu_base->in_hrtirq)
                return;

        if (base->cpu_base != cpu_base)
                return 0;

       if (cpu_base->in_hrtirq)
               return 0;

        /*
         * CLOCK_REALTIME timer might be requested with an absolute
         * expiry time which is less than base->offset. Set it to 0.
         */
        if (expires.tv64 < 0)
                expires.tv64 = 0;

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

        /* Update the pointer to the next expiring timer */
        cpu_base->next_timer = timer;

        /*
         * If a hang was detected in the last timer interrupt then we
         * do not schedule a timer which is earlier than the expiry
         * which we enforced in the hang detection. We want the system
         * to make progress.
         */
        if (cpu_base->hang_detected)
                return;

        cpu_base->expires_next = expires;
        /*
         * Program the timer hardware. We enforce the expiry for
         * events which are already in the past.
         */
        tick_program_event(expires, 1);
}

/*
 * 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;
}

/*
 * 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 = this_cpu_ptr(&hrtimer_bases);

        if (!base->hres_active)
                return;

        raw_spin_lock(&base->lock);
        hrtimer_update_base(base);
        hrtimer_force_reprogram(base, 0);
        raw_spin_unlock(&base->lock);
}

/*
 * Switch to high resolution mode
 */
static void hrtimer_switch_to_hres(void)
{
        struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);

        if (tick_init_highres()) {
                printk(KERN_WARNING "Could not switch to high resolution "
                                    "mode on CPU %d\n", base->cpu);
                return;
        }
        base->hres_active = 1;
        hrtimer_resolution = HIGH_RES_NSEC;

        tick_setup_sched_timer();
        /* "Retrigger" the interrupt to get things going */
        retrigger_next_event(NULL);
}

static void clock_was_set_work(struct work_struct *work)
{
        clock_was_set();
}

static DECLARE_WORK(hrtimer_work, clock_was_set_work);

#ifdef CONFIG_PREEMPT_RT_FULL
/*
 * RT can not call schedule_work from real interrupt context.
 * Need to make a thread to do the real work.
 */
static struct task_struct *clock_set_delay_thread;
static bool do_clock_set_delay;

static int run_clock_set_delay(void *ignore)
{
        while (!kthread_should_stop()) {
                set_current_state(TASK_INTERRUPTIBLE);
                if (do_clock_set_delay) {
                        do_clock_set_delay = false;
                        schedule_work(&hrtimer_work);
                }
                schedule();
        }
        __set_current_state(TASK_RUNNING);
        return 0;
}

void clock_was_set_delayed(void)
{
        do_clock_set_delay = true;
        /* Make visible before waking up process */
        smp_wmb();
        wake_up_process(clock_set_delay_thread);
}

static __init int create_clock_set_delay_thread(void)
{
        clock_set_delay_thread = kthread_run(run_clock_set_delay, NULL, "kclksetdelayd");
        BUG_ON(!clock_set_delay_thread);
        return 0;
}
early_initcall(create_clock_set_delay_thread);
#else /* PREEMPT_RT_FULL */
/*
 * Called from timekeeping and resume code to reprogramm the hrtimer
 * interrupt device on all cpus.
 */
void clock_was_set_delayed(void)
{
        schedule_work(&hrtimer_work);
}
#endif

#else

static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *b) { return 0; }
static inline int hrtimer_hres_active(void) { return 0; }
static inline int hrtimer_is_hres_enabled(void) { return 0; }
static inline void hrtimer_switch_to_hres(void) { }
static inline void
hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { }
static inline void hrtimer_reprogram(struct hrtimer *timer,
                                     struct hrtimer_clock_base *base) { }
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
static inline void retrigger_next_event(void *arg) { }

#endif /* CONFIG_HIGH_RES_TIMERS */

/*
 * 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)
{
#ifdef CONFIG_HIGH_RES_TIMERS
        /* Retrigger the CPU local events everywhere */
        on_each_cpu(retrigger_next_event, NULL, 1);
#endif
        timerfd_clock_was_set();
}

/*
 * During resume we might have to reprogram the high resolution timer
 * interrupt on all online CPUs.  However, all other CPUs will be
 * stopped with IRQs interrupts disabled so the clock_was_set() call
 * must be deferred.
 */
void hrtimers_resume(void)
{
        WARN_ONCE(!irqs_disabled(),
                  KERN_INFO "hrtimers_resume() called with IRQs enabled!");

        /* Retrigger on the local CPU */
        retrigger_next_event(NULL);
        /* And schedule a retrigger for all others */
        clock_was_set_delayed();
}

static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
{
#ifdef CONFIG_TIMER_STATS
        if (timer->start_site)
                return;
        timer->start_site = __builtin_return_address(0);
        memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
        timer->start_pid = current->pid;
#endif
}

static inline void timer_stats_hrtimer_clear_start_info(struct hrtimer *timer)
{
#ifdef CONFIG_TIMER_STATS
        timer->start_site = NULL;
#endif
}

static inline void timer_stats_account_hrtimer(struct hrtimer *timer)
{
#ifdef CONFIG_TIMER_STATS
        if (likely(!timer_stats_active))
                return;
        timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
                                 timer->function, timer->start_comm, 0);
#endif
}

/*
 * Counterpart to lock_hrtimer_base above:
 */
static inline
void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
{
        raw_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.
 *
 * Can be safely called from the callback function of @timer. If
 * called from other contexts @timer must neither be enqueued nor
 * running the callback and the caller needs to take care of
 * serialization.
 *
 * Note: This only updates the timer expiry value and does not requeue
 * the timer.
 */
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 (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED))
                return 0;

        if (interval.tv64 < hrtimer_resolution)
                interval.tv64 = hrtimer_resolution;

        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);

#ifdef CONFIG_PREEMPT_RT_BASE
# 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,
                                !(hrtimer_callback_running(timer)));
}

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

/*
 * 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)
{
        debug_activate(timer);

        base->cpu_base->active_bases |= 1 << base->index;

        timer->state = HRTIMER_STATE_ENQUEUED;

        return timerqueue_add(&base->active, &timer->node);
}

/*
 * __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,
                             u8 newstate, int reprogram)
{
        struct hrtimer_cpu_base *cpu_base = base->cpu_base;
        u8 state = timer->state;

        timer->state = newstate;
        if (!(state & HRTIMER_STATE_ENQUEUED))
                return;

        if (unlikely(!list_empty(&timer->cb_entry))) {
                list_del_init(&timer->cb_entry);
                return;
        }

        if (!timerqueue_del(&base->active, &timer->node))
                cpu_base->active_bases &= ~(1 << base->index);

#ifdef CONFIG_HIGH_RES_TIMERS
        /*
         * Note: If reprogram is false we do not update
         * cpu_base->next_timer. This happens when we remove the first
         * timer on a remote cpu. No harm as we never dereference
         * cpu_base->next_timer. So the worst thing what can happen is
         * an superflous call to hrtimer_force_reprogram() on the
         * remote cpu later on if the same timer gets enqueued again.
         */
        if (reprogram && timer == cpu_base->next_timer)
                hrtimer_force_reprogram(cpu_base, 1);
#endif
}

/*
 * remove hrtimer, called with base lock held
 */
static inline int
remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart)
{
        if (hrtimer_is_queued(timer)) {
                u8 state = timer->state;
                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_deactivate(timer);
                timer_stats_hrtimer_clear_start_info(timer);
                reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases);

                if (!restart)
                        state = HRTIMER_STATE_INACTIVE;

                __remove_hrtimer(timer, base, state, reprogram);
                return 1;
        }
        return 0;
}

static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim,
                                            const enum hrtimer_mode mode)
{
#ifdef CONFIG_TIME_LOW_RES
        /*
         * CONFIG_TIME_LOW_RES indicates that the system has no way to return
         * granular time values. For relative timers we add hrtimer_resolution
         * (i.e. one jiffie) to prevent short timeouts.
         */
        timer->is_rel = mode & HRTIMER_MODE_REL;
        if (timer->is_rel)
                tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution));
#endif
        return tim;
}

/**
 * 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_MODE_ABS) or
 *              relative (HRTIMER_MODE_REL)
 */
void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
                            unsigned long delta_ns, const enum hrtimer_mode mode)
{
        struct hrtimer_clock_base *base, *new_base;
        unsigned long flags;
        int leftmost;

        base = lock_hrtimer_base(timer, &flags);

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

        if (mode & HRTIMER_MODE_REL)
                tim = ktime_add_safe(tim, base->get_time());

        tim = hrtimer_update_lowres(timer, tim, mode);

        hrtimer_set_expires_range_ns(timer, tim, delta_ns);

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

        timer_stats_hrtimer_set_start_info(timer);
#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
        {
                ktime_t now = new_base->get_time();

                if (ktime_to_ns(tim) < ktime_to_ns(now))
                        timer->praecox = now;
                else
                        timer->praecox = ktime_set(0, 0);
        }
#endif
        leftmost = enqueue_hrtimer(timer, new_base);
        if (!leftmost)
                goto unlock;

        if (!hrtimer_is_hres_active(timer)) {
                /*
                 * Kick to reschedule the next tick to handle the new timer
                 * on dynticks target.
                 */
                if (new_base->cpu_base->nohz_active)
                        wake_up_nohz_cpu(new_base->cpu_base->cpu);
        } else {
                hrtimer_reprogram(timer, new_base);
        }
unlock:
        unlock_hrtimer_base(timer, &flags);
}
EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);

/**
 * 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;

        /*
         * Check lockless first. If the timer is not active (neither
         * enqueued nor running the callback, nothing to do here.  The
         * base lock does not serialize against a concurrent enqueue,
         * so we can avoid taking it.
         */
        if (!hrtimer_active(timer))
                return 0;

        base = lock_hrtimer_base(timer, &flags);

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

        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
 * @adjust:     adjust relative timers when CONFIG_TIME_LOW_RES=y
 */
ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust)
{
        unsigned long flags;
        ktime_t rem;

        lock_hrtimer_base(timer, &flags);
        if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust)
                rem = hrtimer_expires_remaining_adjusted(timer);
        else
                rem = hrtimer_expires_remaining(timer);
        unlock_hrtimer_base(timer, &flags);

        return rem;
}
EXPORT_SYMBOL_GPL(__hrtimer_get_remaining);

#ifdef CONFIG_NO_HZ_COMMON
/**
 * hrtimer_get_next_event - get the time until next expiry event
 *
 * Returns the next expiry time or KTIME_MAX if no timer is pending.
 */
u64 hrtimer_get_next_event(void)
{
        struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
        u64 expires = KTIME_MAX;
        unsigned long flags;

        raw_spin_lock_irqsave(&cpu_base->lock, flags);

        if (!__hrtimer_hres_active(cpu_base))
                expires = __hrtimer_get_next_event(cpu_base).tv64;

        raw_spin_unlock_irqrestore(&cpu_base->lock, flags);

        return expires;
}
#endif

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

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

        cpu_base = raw_cpu_ptr(&hrtimer_bases);

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

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

#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_init(timer, clock_id, mode);
        __hrtimer_init(timer, clock_id, mode);
}
EXPORT_SYMBOL_GPL(hrtimer_init);

/*
 * A timer is active, when it is enqueued into the rbtree or the
 * callback function is running or it's in the state of being migrated
 * to another cpu.
 *
 * It is important for this function to not return a false negative.
 */
bool hrtimer_active(const struct hrtimer *timer)
{
        struct hrtimer_cpu_base *cpu_base;
        unsigned int seq;

        do {
                cpu_base = READ_ONCE(timer->base->cpu_base);
                seq = raw_read_seqcount_begin(&cpu_base->seq);

                if (timer->state != HRTIMER_STATE_INACTIVE ||
                    cpu_base->running_soft == timer ||
                    cpu_base->running == timer)
                        return true;

        } while (read_seqcount_retry(&cpu_base->seq, seq) ||
                 cpu_base != READ_ONCE(timer->base->cpu_base));

        return false;
}
EXPORT_SYMBOL_GPL(hrtimer_active);

/*
 * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3
 * distinct sections:
 *
 *  - queued:   the timer is queued
 *  - callback: the timer is being ran
 *  - post:     the timer is inactive or (re)queued
 *
 * On the read side we ensure we observe timer->state and cpu_base->running
 * from the same section, if anything changed while we looked at it, we retry.
 * This includes timer->base changing because sequence numbers alone are
 * insufficient for that.
 *
 * The sequence numbers are required because otherwise we could still observe
 * a false negative if the read side got smeared over multiple consequtive
 * __run_hrtimer() invocations.
 */

static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
                          struct hrtimer_clock_base *base,
                          struct hrtimer *timer, ktime_t *now)
{
        enum hrtimer_restart (*fn)(struct hrtimer *);
        int restart;

        lockdep_assert_held(&cpu_base->lock);

        debug_deactivate(timer);
        cpu_base->running = timer;

        /*
         * Separate the ->running assignment from the ->state assignment.
         *
         * As with a regular write barrier, this ensures the read side in
         * hrtimer_active() cannot observe cpu_base->running == NULL &&
         * timer->state == INACTIVE.
         */
        raw_write_seqcount_barrier(&cpu_base->seq);

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

        /*
         * Clear the 'is relative' flag for the TIME_LOW_RES case. If the
         * timer is restarted with a period then it becomes an absolute
         * timer. If its not restarted it does not matter.
         */
        if (IS_ENABLED(CONFIG_TIME_LOW_RES))
                timer->is_rel = false;

        /*
         * 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.
         */
        raw_spin_unlock(&cpu_base->lock);
        trace_hrtimer_expire_entry(timer, now);
        restart = fn(timer);
        trace_hrtimer_expire_exit(timer);
        raw_spin_lock(&cpu_base->lock);

        /*
         * Note: We clear the running state after enqueue_hrtimer and
         * we do not reprogramm the event hardware. Happens either in
         * hrtimer_start_range_ns() or in hrtimer_interrupt()
         *
         * Note: Because we dropped the cpu_base->lock above,
         * hrtimer_start_range_ns() can have popped in and enqueued the timer
         * for us already.
         */
        if (restart != HRTIMER_NORESTART &&
            !(timer->state & HRTIMER_STATE_ENQUEUED))
                enqueue_hrtimer(timer, base);

        /*
         * Separate the ->running assignment from the ->state assignment.
         *
         * As with a regular write barrier, this ensures the read side in
         * hrtimer_active() cannot observe cpu_base->running == NULL &&
         * timer->state == INACTIVE.
         */
        raw_write_seqcount_barrier(&cpu_base->seq);

        WARN_ON_ONCE(cpu_base->running != timer);
        cpu_base->running = NULL;
}

#ifdef CONFIG_PREEMPT_RT_BASE
static void hrtimer_rt_reprogram(int restart, struct hrtimer *timer,
                                 struct hrtimer_clock_base *base)
{
        int leftmost;

        if (restart != HRTIMER_NORESTART &&
            !(timer->state & HRTIMER_STATE_ENQUEUED)) {

                leftmost = enqueue_hrtimer(timer, base);
                if (!leftmost)
                        return;
#ifdef CONFIG_HIGH_RES_TIMERS
                if (!hrtimer_is_hres_active(timer)) {
                        /*
                         * Kick to reschedule the next tick to handle the new timer
                         * on dynticks target.
                         */
                        if (base->cpu_base->nohz_active)
                                wake_up_nohz_cpu(base->cpu_base->cpu);
                } else {

                        hrtimer_reprogram(timer, base);
                }
#endif
        }
}

/*
 * 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());

        raw_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_deactivate(timer);
                        cpu_base->running_soft = timer;
                        raw_write_seqcount_barrier(&cpu_base->seq);

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

                        raw_spin_unlock_irq(&cpu_base->lock);
                        restart = fn(timer);
                        raw_spin_lock_irq(&cpu_base->lock);

                        hrtimer_rt_reprogram(restart, timer, base);
                        raw_write_seqcount_barrier(&cpu_base->seq);

                        WARN_ON_ONCE(cpu_base->running_soft != timer);
                        cpu_base->running_soft = NULL;
                }
        }

        raw_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 int hrtimer_rt_defer(struct hrtimer *timer) { return 0; }

#endif

static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer);

static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
{
        struct hrtimer_clock_base *base = cpu_base->clock_base;
        unsigned int active = cpu_base->active_bases;
        int raise = 0;

        for (; active; base++, active >>= 1) {
                struct timerqueue_node *node;
                ktime_t basenow;

                if (!(active & 0x01))
                        continue;

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

                while ((node = timerqueue_getnext(&base->active))) {
                        struct hrtimer *timer;

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

                        trace_hrtimer_interrupt(raw_smp_processor_id(),
                            ktime_to_ns(ktime_sub(ktime_to_ns(timer->praecox) ?
                                timer->praecox : hrtimer_get_expires(timer),
                                basenow)),
                            current,
                            timer->function == hrtimer_wakeup ?
                            container_of(timer, struct hrtimer_sleeper,
                                timer)->task : NULL);

                        /*
                         * 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))
                                break;

                        if (!hrtimer_rt_defer(timer))
                                __run_hrtimer(cpu_base, base, timer, &basenow);
                        else
                                raise = 1;
                }
        }
        if (raise)
                raise_softirq_irqoff(HRTIMER_SOFTIRQ);
}

#ifdef CONFIG_HIGH_RES_TIMERS

/*
 * High resolution timer interrupt
 * Called with interrupts disabled
 */
void hrtimer_interrupt(struct clock_event_device *dev)
{
        struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
        ktime_t expires_next, now, entry_time, delta;
        int retries = 0;

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

        raw_spin_lock(&cpu_base->lock);
        entry_time = now = hrtimer_update_base(cpu_base);
retry:
        cpu_base->in_hrtirq = 1;
        /*
         * We set expires_next to KTIME_MAX here with cpu_base->lock
         * held to prevent that a timer is enqueued in our queue via
         * the migration code. This does not affect enqueueing of
         * timers which run their callback and need to be requeued on
         * this CPU.
         */
        cpu_base->expires_next.tv64 = KTIME_MAX;

        __hrtimer_run_queues(cpu_base, now);

        /* Reevaluate the clock bases for the next expiry */
        expires_next = __hrtimer_get_next_event(cpu_base);
        /*
         * Store the new expiry value so the migration code can verify
         * against it.
         */
        cpu_base->expires_next = expires_next;
        cpu_base->in_hrtirq = 0;
        raw_spin_unlock(&cpu_base->lock);

        /* Reprogramming necessary ? */
        if (!tick_program_event(expires_next, 0)) {
                cpu_base->hang_detected = 0;
                return;
        }

        /*
         * The next timer was already expired due to:
         * - tracing
         * - long lasting callbacks
         * - being scheduled away when running in a VM
         *
         * We need to prevent that we loop forever in the hrtimer
         * interrupt routine. We give it 3 attempts to avoid
         * overreacting on some spurious event.
         *
         * Acquire base lock for updating the offsets and retrieving
         * the current time.
         */
        raw_spin_lock(&cpu_base->lock);
        now = hrtimer_update_base(cpu_base);
        cpu_base->nr_retries++;
        if (++retries < 3)
                goto retry;
        /*
         * Give the system a chance to do something else than looping
         * here. We stored the entry time, so we know exactly how long
         * we spent here. We schedule the next event this amount of
         * time away.
         */
        cpu_base->nr_hangs++;
        cpu_base->hang_detected = 1;
        raw_spin_unlock(&cpu_base->lock);
        delta = ktime_sub(now, entry_time);
        if ((unsigned int)delta.tv64 > cpu_base->max_hang_time)
                cpu_base->max_hang_time = (unsigned int) delta.tv64;
        /*
         * Limit it to a sensible value as we enforce a longer
         * delay. Give the CPU at least 100ms to catch up.
         */
        if (delta.tv64 > 100 * NSEC_PER_MSEC)
                expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
        else
                expires_next = ktime_add(now, delta);
        tick_program_event(expires_next, 1);
        printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
                    ktime_to_ns(delta));
}

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

        if (!hrtimer_hres_active())
                return;

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

#else /* CONFIG_HIGH_RES_TIMERS */

static inline void __hrtimer_peek_ahead_timers(void) { }

#endif  /* !CONFIG_HIGH_RES_TIMERS */

/*
 * Called from run_local_timers in hardirq context every jiffy
 */
void hrtimer_run_queues(void)
{
        struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
        ktime_t now;

        if (__hrtimer_hres_active(cpu_base))
                return;

        /*
         * This _is_ ugly: We have to check periodically, whether we
         * can switch to highres and / or nohz mode. The clocksource
         * switch happens 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();
                return;
        }

        raw_spin_lock(&cpu_base->lock);
        now = hrtimer_update_base(cpu_base);
        __hrtimer_run_queues(cpu_base, now);
        raw_spin_unlock(&cpu_base->lock);
}

/*
 * 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;
}
EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);

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

        do {
                set_current_state(state);
                hrtimer_start_expires(&t->timer, mode);

                if (likely(t->task))
                        freezable_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.clockid,
                                HRTIMER_MODE_ABS);
        hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);

        /* cpu_chill() does not care about restart state. */
        if (do_nanosleep(&t, HRTIMER_MODE_ABS, TASK_INTERRUPTIBLE))
                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;
}

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

        slack = current->timer_slack_ns;
        if (dl_task(current) || 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, state))
                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->restart_block;
        restart->fn = hrtimer_nanosleep_restart;
        restart->nanosleep.clockid = t.timer.base->clockid;
        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;
}

long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
                       const enum hrtimer_mode mode, const clockid_t clockid)
{
        return __hrtimer_nanosleep(rqtp, rmtp, mode, clockid, TASK_INTERRUPTIBLE);
}

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);
}

#ifdef CONFIG_PREEMPT_RT_FULL
/*
 * Sleep for 1 ms in hope whoever holds what we want will let it go.
 */
void cpu_chill(void)
{
        struct timespec tu = {
                .tv_nsec = NSEC_PER_MSEC,
        };
        unsigned int freeze_flag = current->flags & PF_NOFREEZE;

        current->flags |= PF_NOFREEZE;
        __hrtimer_nanosleep(&tu, NULL, HRTIMER_MODE_REL, CLOCK_MONOTONIC,
                            TASK_UNINTERRUPTIBLE);
        if (!freeze_flag)
                current->flags &= ~PF_NOFREEZE;
}
EXPORT_SYMBOL(cpu_chill);
#endif

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

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

        cpu_base->cpu = cpu;
        hrtimer_init_hres(cpu_base);
#ifdef CONFIG_PREEMPT_RT_BASE
        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 timerqueue_node *node;

        while ((node = timerqueue_getnext(&old_base->active))) {
                timer = container_of(node, struct hrtimer, node);
                BUG_ON(hrtimer_callback_running(timer));
                debug_deactivate(timer);

                /*
                 * Mark it as ENQUEUED 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_ENQUEUED, 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);
        }
}

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 = this_cpu_ptr(&hrtimer_bases);
        /*
         * The caller is globally serialized and nobody else
         * takes two locks at once, deadlock is not possible.
         */
        raw_spin_lock(&new_base->lock);
        raw_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]);
        }

        raw_spin_unlock(&old_base->lock);
        raw_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 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_DEAD:
        case CPU_DEAD_FROZEN:
                migrate_hrtimers(scpu);
                break;
#endif

        default:
                break;
        }

        return NOTIFY_OK;
}

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

#ifdef CONFIG_PREEMPT_RT_BASE
static void run_hrtimer_softirq(struct softirq_action *h)
{
        hrtimer_rt_run_pending();
}
#endif

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);
#ifdef CONFIG_PREEMPT_RT_BASE
        open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
#endif
}

/**
 * schedule_hrtimeout_range_clock - 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
 * @clock:      timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME
 */
int __sched
schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
                               const enum hrtimer_mode mode, int clock)
{
        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 "infinite"
         */
        if (!expires) {
                schedule();
                return -EINTR;
        }

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

        hrtimer_init_sleeper(&t, current);

        hrtimer_start_expires(&t.timer, mode);

        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;
}

/**
 * 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)
{
        return schedule_hrtimeout_range_clock(expires, delta, mode,
                                              CLOCK_MONOTONIC);
}
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);