1 files changed, 248 insertions, 290 deletions

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index cdec83e722fa..bda9cb924276 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -442,22 +442,6 @@ static inline void debug_hrtimer_activate(struct hrtimer *timer) { }
 static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
 #endif
 
-/*
- * Check, whether the timer is on the callback pending list
- */
-static inline int hrtimer_cb_pending(const struct hrtimer *timer)
-{
-        return timer->state & HRTIMER_STATE_PENDING;
-}
-
-/*
- * Remove a timer from the callback pending list
- */
-static inline void hrtimer_remove_cb_pending(struct hrtimer *timer)
-{
-        list_del_init(&timer->cb_entry);
-}
-
 /* High resolution timer related functions */
 #ifdef CONFIG_HIGH_RES_TIMERS
 
@@ -517,7 +501,7 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
                 if (!base->first)
                         continue;
                 timer = rb_entry(base->first, struct hrtimer, node);
-                expires = ktime_sub(timer->expires, base->offset);
+                expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
                 if (expires.tv64 < cpu_base->expires_next.tv64)
                         cpu_base->expires_next = expires;
         }
@@ -539,10 +523,10 @@ static int hrtimer_reprogram(struct hrtimer *timer,
                              struct hrtimer_clock_base *base)
 {
         ktime_t *expires_next = &__get_cpu_var(hrtimer_bases).expires_next;
-        ktime_t expires = ktime_sub(timer->expires, base->offset);
+        ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
         int res;
 
-        WARN_ON_ONCE(timer->expires.tv64 < 0);
+        WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
 
         /*
          * When the callback is running, we do not reprogram the clock event
@@ -651,6 +635,8 @@ static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
 {
 }
 
+static void __run_hrtimer(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
@@ -661,40 +647,14 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
                                             struct hrtimer_clock_base *base)
 {
         if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
-
-                /* Timer is expired, act upon the callback mode */
-                switch(timer->cb_mode) {
-                case HRTIMER_CB_IRQSAFE_NO_RESTART:
-                        debug_hrtimer_deactivate(timer);
-                        /*
-                         * We can call the callback from here. No restart
-                         * happens, so no danger of recursion
-                         */
-                        BUG_ON(timer->function(timer) != HRTIMER_NORESTART);
-                        return 1;
-                case HRTIMER_CB_IRQSAFE_PERCPU:
-                case HRTIMER_CB_IRQSAFE_UNLOCKED:
-                        /*
-                         * This is solely for the sched tick emulation with
-                         * dynamic tick support to ensure that we do not
-                         * restart the tick right on the edge and end up with
-                         * the tick timer in the softirq ! The calling site
-                         * takes care of this. Also used for hrtimer sleeper !
-                         */
-                        debug_hrtimer_deactivate(timer);
-                        return 1;
-                case HRTIMER_CB_IRQSAFE:
-                case HRTIMER_CB_SOFTIRQ:
-                        /*
-                         * Move everything else into the softirq pending list !
-                         */
-                        list_add_tail(&timer->cb_entry,
-                                      &base->cpu_base->cb_pending);
-                        timer->state = HRTIMER_STATE_PENDING;
-                        return 1;
-                default:
-                        BUG();
-                }
+                /*
+                 * XXX: recursion check?
+                 * hrtimer_forward() should round up with timer granularity
+                 * so that we never get into inf recursion here,
+                 * it doesn't do that though
+                 */
+                __run_hrtimer(timer);
+                return 1;
         }
         return 0;
 }
@@ -733,11 +693,6 @@ static int hrtimer_switch_to_hres(void)
         return 1;
 }
 
-static inline void hrtimer_raise_softirq(void)
-{
-        raise_softirq(HRTIMER_SOFTIRQ);
-}
-
 #else
 
 static inline int hrtimer_hres_active(void) { return 0; }
@@ -756,7 +711,6 @@ static inline int hrtimer_reprogram(struct hrtimer *timer,
 {
         return 0;
 }
-static inline void hrtimer_raise_softirq(void) { }
 
 #endif /* CONFIG_HIGH_RES_TIMERS */
 
@@ -795,7 +749,7 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
         u64 orun = 1;
         ktime_t delta;
 
-        delta = ktime_sub(now, timer->expires);
+        delta = ktime_sub(now, hrtimer_get_expires(timer));
 
         if (delta.tv64 < 0)
                 return 0;
@@ -807,8 +761,8 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
                 s64 incr = ktime_to_ns(interval);
 
                 orun = ktime_divns(delta, incr);
-                timer->expires = ktime_add_ns(timer->expires, incr * orun);
-                if (timer->expires.tv64 > now.tv64)
+                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
@@ -816,7 +770,7 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
                  */
                 orun++;
         }
-        timer->expires = ktime_add_safe(timer->expires, interval);
+        hrtimer_add_expires(timer, interval);
 
         return orun;
 }
@@ -848,7 +802,8 @@ static void enqueue_hrtimer(struct hrtimer *timer,
                  * We dont care about collisions. Nodes with
                  * the same expiry time stay together.
                  */
-                if (timer->expires.tv64 < entry->expires.tv64) {
+                if (hrtimer_get_expires_tv64(timer) <
+                                hrtimer_get_expires_tv64(entry)) {
                         link = &(*link)->rb_left;
                 } else {
                         link = &(*link)->rb_right;
@@ -898,10 +853,7 @@ static void __remove_hrtimer(struct hrtimer *timer,
                              struct hrtimer_clock_base *base,
                              unsigned long newstate, int reprogram)
 {
-        /* High res. callback list. NOP for !HIGHRES */
-        if (hrtimer_cb_pending(timer))
-                hrtimer_remove_cb_pending(timer);
-        else {
+        if (timer->state & HRTIMER_STATE_ENQUEUED) {
                 /*
                  * Remove the timer from the rbtree and replace the
                  * first entry pointer if necessary.
@@ -945,9 +897,10 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 }
 
 /**
- * hrtimer_start - (re)start an relative timer on the current CPU
+ * 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:
@@ -955,11 +908,12 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
  *  1 when the timer was active
  */
 int
-hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
+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 ret, raise;
+        int ret;
 
         base = lock_hrtimer_base(timer, &flags);
 
@@ -983,7 +937,7 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 #endif
         }
 
-        timer->expires = tim;
+        hrtimer_set_expires_range_ns(timer, tim, delta_ns);
 
         timer_stats_hrtimer_set_start_info(timer);
 
@@ -994,30 +948,30 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
         enqueue_hrtimer(timer, new_base,
                         new_base->cpu_base == &__get_cpu_var(hrtimer_bases));
 
-        /*
-         * The timer may be expired and moved to the cb_pending
-         * list. We can not raise the softirq with base lock held due
-         * to a possible deadlock with runqueue lock.
-         */
-        raise = timer->state == HRTIMER_STATE_PENDING;
-
-        /*
-         * We use preempt_disable to prevent this task from migrating after
-         * setting up the softirq and raising it. Otherwise, if me migrate
-         * we will raise the softirq on the wrong CPU.
-         */
-        preempt_disable();
-
         unlock_hrtimer_base(timer, &flags);
 
-        if (raise)
-                hrtimer_raise_softirq();
-        preempt_enable();
-
         return ret;
 }
+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);
+}
 EXPORT_SYMBOL_GPL(hrtimer_start);
 
+
 /**
  * hrtimer_try_to_cancel - try to deactivate a timer
  * @timer:      hrtimer to stop
@@ -1077,7 +1031,7 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
         ktime_t rem;
 
         base = lock_hrtimer_base(timer, &flags);
-        rem = ktime_sub(timer->expires, base->get_time());
+        rem = hrtimer_expires_remaining(timer);
         unlock_hrtimer_base(timer, &flags);
 
         return rem;
@@ -1109,7 +1063,7 @@ ktime_t hrtimer_get_next_event(void)
                                 continue;
 
                         timer = rb_entry(base->first, struct hrtimer, node);
-                        delta.tv64 = timer->expires.tv64;
+                        delta.tv64 = hrtimer_get_expires_tv64(timer);
                         delta = ktime_sub(delta, base->get_time());
                         if (delta.tv64 < mindelta.tv64)
                                 mindelta.tv64 = delta.tv64;
@@ -1180,60 +1134,6 @@ int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 }
 EXPORT_SYMBOL_GPL(hrtimer_get_res);
 
-static void run_hrtimer_pending(struct hrtimer_cpu_base *cpu_base)
-{
-        spin_lock_irq(&cpu_base->lock);
-
-        while (!list_empty(&cpu_base->cb_pending)) {
-                enum hrtimer_restart (*fn)(struct hrtimer *);
-                struct hrtimer *timer;
-                int restart;
-
-                timer = list_entry(cpu_base->cb_pending.next,
-                                   struct hrtimer, cb_entry);
-
-                debug_hrtimer_deactivate(timer);
-                timer_stats_account_hrtimer(timer);
-
-                fn = timer->function;
-                __remove_hrtimer(timer, timer->base, HRTIMER_STATE_CALLBACK, 0);
-                spin_unlock_irq(&cpu_base->lock);
-
-                restart = fn(timer);
-
-                spin_lock_irq(&cpu_base->lock);
-
-                timer->state &= ~HRTIMER_STATE_CALLBACK;
-                if (restart == HRTIMER_RESTART) {
-                        BUG_ON(hrtimer_active(timer));
-                        /*
-                         * Enqueue the timer, allow reprogramming of the event
-                         * device
-                         */
-                        enqueue_hrtimer(timer, timer->base, 1);
-                } else if (hrtimer_active(timer)) {
-                        /*
-                         * If the timer was rearmed on another CPU, reprogram
-                         * the event device.
-                         */
-                        struct hrtimer_clock_base *base = timer->base;
-
-                        if (base->first == &timer->node &&
-                            hrtimer_reprogram(timer, base)) {
-                                /*
-                                 * Timer is expired. Thus move it from tree to
-                                 * pending list again.
-                                 */
-                                __remove_hrtimer(timer, base,
-                                                 HRTIMER_STATE_PENDING, 0);
-                                list_add_tail(&timer->cb_entry,
-                                              &base->cpu_base->cb_pending);
-                        }
-                }
-        }
-        spin_unlock_irq(&cpu_base->lock);
-}
-
 static void __run_hrtimer(struct hrtimer *timer)
 {
         struct hrtimer_clock_base *base = timer->base;
@@ -1241,25 +1141,21 @@ static void __run_hrtimer(struct hrtimer *timer)
         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;
-        if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU ||
-            timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED) {
-                /*
-                 * Used for scheduler timers, avoid lock inversion with
-                 * rq->lock and tasklist_lock.
-                 *
-                 * These timers are required to deal with enqueue expiry
-                 * themselves and are not allowed to migrate.
-                 */
-                spin_unlock(&cpu_base->lock);
-                restart = fn(timer);
-                spin_lock(&cpu_base->lock);
-        } else
-                restart = fn(timer);
+
+        /*
+         * 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 to avoid
@@ -1284,7 +1180,7 @@ 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 i, raise = 0;
+        int i;
 
         BUG_ON(!cpu_base->hres_active);
         cpu_base->nr_events++;
@@ -1310,26 +1206,29 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
                         timer = rb_entry(node, struct hrtimer, node);
 
-                        if (basenow.tv64 < timer->expires.tv64) {
+                        /*
+                         * 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(timer->expires,
+                                expires = ktime_sub(hrtimer_get_expires(timer),
                                                     base->offset);
                                 if (expires.tv64 < expires_next.tv64)
                                         expires_next = expires;
                                 break;
                         }
 
-                        /* Move softirq callbacks to the pending list */
-                        if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
-                                __remove_hrtimer(timer, base,
-                                                 HRTIMER_STATE_PENDING, 0);
-                                list_add_tail(&timer->cb_entry,
-                                              &base->cpu_base->cb_pending);
-                                raise = 1;
-                                continue;
-                        }
-
                         __run_hrtimer(timer);
                 }
                 spin_unlock(&cpu_base->lock);
@@ -1343,15 +1242,30 @@ void hrtimer_interrupt(struct clock_event_device *dev)
                 if (tick_program_event(expires_next, 0))
                         goto retry;
         }
-
-        /* Raise softirq ? */
-        if (raise)
-                raise_softirq(HRTIMER_SOFTIRQ);
 }
 
-static void run_hrtimer_softirq(struct softirq_action *h)
+/**
+ * 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)
 {
-        run_hrtimer_pending(&__get_cpu_var(hrtimer_bases));
+        struct tick_device *td;
+        unsigned long flags;
+
+        if (!hrtimer_hres_active())
+                return;
+
+        local_irq_save(flags);
+        td = &__get_cpu_var(tick_cpu_device);
+        if (td && td->evtdev)
+                hrtimer_interrupt(td->evtdev);
+        local_irq_restore(flags);
 }
 
 #endif  /* CONFIG_HIGH_RES_TIMERS */
@@ -1365,8 +1279,6 @@ static void run_hrtimer_softirq(struct softirq_action *h)
  */
 void hrtimer_run_pending(void)
 {
-        struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
-
         if (hrtimer_hres_active())
                 return;
 
@@ -1380,8 +1292,6 @@ void hrtimer_run_pending(void)
          */
         if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
                 hrtimer_switch_to_hres();
-
-        run_hrtimer_pending(cpu_base);
 }
 
 /*
@@ -1403,9 +1313,7 @@ void hrtimer_run_queues(void)
                 if (!base->first)
                         continue;
 
-                if (base->get_softirq_time)
-                        base->softirq_time = base->get_softirq_time();
-                else if (gettime) {
+                if (gettime) {
                         hrtimer_get_softirq_time(cpu_base);
                         gettime = 0;
                 }
@@ -1416,17 +1324,10 @@ void hrtimer_run_queues(void)
                         struct hrtimer *timer;
 
                         timer = rb_entry(node, struct hrtimer, node);
-                        if (base->softirq_time.tv64 <= timer->expires.tv64)
+                        if (base->softirq_time.tv64 <=
+                                        hrtimer_get_expires_tv64(timer))
                                 break;
 
-                        if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
-                                __remove_hrtimer(timer, base,
-                                        HRTIMER_STATE_PENDING, 0);
-                                list_add_tail(&timer->cb_entry,
-                                        &base->cpu_base->cb_pending);
-                                continue;
-                        }
-
                         __run_hrtimer(timer);
                 }
                 spin_unlock(&cpu_base->lock);
@@ -1453,9 +1354,6 @@ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
 {
         sl->timer.function = hrtimer_wakeup;
         sl->task = task;
-#ifdef CONFIG_HIGH_RES_TIMERS
-        sl->timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED;
-#endif
 }
 
 static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
@@ -1464,7 +1362,7 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 
         do {
                 set_current_state(TASK_INTERRUPTIBLE);
-                hrtimer_start(&t->timer, t->timer.expires, mode);
+                hrtimer_start_expires(&t->timer, mode);
                 if (!hrtimer_active(&t->timer))
                         t->task = NULL;
 
@@ -1486,7 +1384,7 @@ static int update_rmtp(struct hrtimer *timer, struct timespec __user *rmtp)
         struct timespec rmt;
         ktime_t rem;
 
-        rem = ktime_sub(timer->expires, timer->base->get_time());
+        rem = hrtimer_expires_remaining(timer);
         if (rem.tv64 <= 0)
                 return 0;
         rmt = ktime_to_timespec(rem);
@@ -1505,7 +1403,7 @@ long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
 
         hrtimer_init_on_stack(&t.timer, restart->nanosleep.index,
                                 HRTIMER_MODE_ABS);
-        t.timer.expires.tv64 = restart->nanosleep.expires;
+        hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);
 
         if (do_nanosleep(&t, HRTIMER_MODE_ABS))
                 goto out;
@@ -1530,9 +1428,14 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
         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);
-        t.timer.expires = timespec_to_ktime(*rqtp);
+        hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack);
         if (do_nanosleep(&t, mode))
                 goto out;
 
@@ -1552,7 +1455,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
         restart->fn = hrtimer_nanosleep_restart;
         restart->nanosleep.index = t.timer.base->index;
         restart->nanosleep.rmtp = rmtp;
-        restart->nanosleep.expires = t.timer.expires.tv64;
+        restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer);
 
         ret = -ERESTART_RESTARTBLOCK;
 out:
@@ -1587,18 +1490,16 @@ static void __cpuinit init_hrtimers_cpu(int cpu)
         for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
                 cpu_base->clock_base[i].cpu_base = cpu_base;
 
-        INIT_LIST_HEAD(&cpu_base->cb_pending);
         hrtimer_init_hres(cpu_base);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
-                                struct hrtimer_clock_base *new_base, int dcpu)
+static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
+                                struct hrtimer_clock_base *new_base)
 {
         struct hrtimer *timer;
         struct rb_node *node;
-        int raise = 0;
 
         while ((node = rb_first(&old_base->active))) {
                 timer = rb_entry(node, struct hrtimer, node);
@@ -1606,18 +1507,6 @@ static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
                 debug_hrtimer_deactivate(timer);
 
                 /*
-                 * Should not happen. Per CPU timers should be
-                 * canceled _before_ the migration code is called
-                 */
-                if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU) {
-                        __remove_hrtimer(timer, old_base,
-                                         HRTIMER_STATE_INACTIVE, 0);
-                        WARN(1, "hrtimer (%p %p)active but cpu %d dead\n",
-                             timer, timer->function, dcpu);
-                        continue;
-                }
-
-                /*
                  * Mark it as STATE_MIGRATE not INACTIVE otherwise the
                  * timer could be seen as !active and just vanish away
                  * under us on another CPU
@@ -1625,111 +1514,83 @@ static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
                 __remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0);
                 timer->base = new_base;
                 /*
-                 * Enqueue the timer. Allow reprogramming of the event device
+                 * Enqueue the timers on the new cpu, but do not reprogram 
+                 * the timer as that would enable a deadlock between
+                 * hrtimer_enqueue_reprogramm() running the timer and us still
+                 * holding a nested base lock.
+                 *
+                 * Instead we tickle the hrtimer interrupt after the migration
+                 * is done, which will run all expired timers and re-programm
+                 * the timer device.
                  */
-                enqueue_hrtimer(timer, new_base, 1);
+                enqueue_hrtimer(timer, new_base, 0);
 
-#ifdef CONFIG_HIGH_RES_TIMERS
-                /*
-                 * Happens with high res enabled when the timer was
-                 * already expired and the callback mode is
-                 * HRTIMER_CB_IRQSAFE_UNLOCKED (hrtimer_sleeper). The
-                 * enqueue code does not move them to the soft irq
-                 * pending list for performance/latency reasons, but
-                 * in the migration state, we need to do that
-                 * otherwise we end up with a stale timer.
-                 */
-                if (timer->state == HRTIMER_STATE_MIGRATE) {
-                        timer->state = HRTIMER_STATE_PENDING;
-                        list_add_tail(&timer->cb_entry,
-                                      &new_base->cpu_base->cb_pending);
-                        raise = 1;
-                }
-#endif
                 /* Clear the migration state bit */
                 timer->state &= ~HRTIMER_STATE_MIGRATE;
         }
-        return raise;
 }
 
-#ifdef CONFIG_HIGH_RES_TIMERS
-static int migrate_hrtimer_pending(struct hrtimer_cpu_base *old_base,
-                                   struct hrtimer_cpu_base *new_base)
-{
-        struct hrtimer *timer;
-        int raise = 0;
-
-        while (!list_empty(&old_base->cb_pending)) {
-                timer = list_entry(old_base->cb_pending.next,
-                                   struct hrtimer, cb_entry);
-
-                __remove_hrtimer(timer, timer->base, HRTIMER_STATE_PENDING, 0);
-                timer->base = &new_base->clock_base[timer->base->index];
-                list_add_tail(&timer->cb_entry, &new_base->cb_pending);
-                raise = 1;
-        }
-        return raise;
-}
-#else
-static int migrate_hrtimer_pending(struct hrtimer_cpu_base *old_base,
-                                   struct hrtimer_cpu_base *new_base)
-{
-        return 0;
-}
-#endif
-
-static void migrate_hrtimers(int cpu)
+static int migrate_hrtimers(int scpu)
 {
         struct hrtimer_cpu_base *old_base, *new_base;
-        int i, raise = 0;
+        int dcpu, i;
 
-        BUG_ON(cpu_online(cpu));
-        old_base = &per_cpu(hrtimer_bases, cpu);
+        BUG_ON(cpu_online(scpu));
+        old_base = &per_cpu(hrtimer_bases, scpu);
         new_base = &get_cpu_var(hrtimer_bases);
 
-        tick_cancel_sched_timer(cpu);
+        dcpu = smp_processor_id();
 
-        local_irq_disable();
-        spin_lock(&new_base->lock);
+        tick_cancel_sched_timer(scpu);
+        /*
+         * The caller is globally serialized and nobody else
+         * takes two locks at once, deadlock is not possible.
+         */
+        spin_lock_irq(&new_base->lock);
         spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
 
         for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
-                if (migrate_hrtimer_list(&old_base->clock_base[i],
-                                         &new_base->clock_base[i], cpu))
-                        raise = 1;
+                migrate_hrtimer_list(&old_base->clock_base[i],
+                                     &new_base->clock_base[i]);
         }
 
-        if (migrate_hrtimer_pending(old_base, new_base))
-                raise = 1;
-
         spin_unlock(&old_base->lock);
-        spin_unlock(&new_base->lock);
-        local_irq_enable();
+        spin_unlock_irq(&new_base->lock);
         put_cpu_var(hrtimer_bases);
 
-        if (raise)
-                hrtimer_raise_softirq();
+        return dcpu;
 }
+
+static void tickle_timers(void *arg)
+{
+        hrtimer_peek_ahead_timers();
+}
+
 #endif /* CONFIG_HOTPLUG_CPU */
 
 static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
                                         unsigned long action, void *hcpu)
 {
-        unsigned int cpu = (long)hcpu;
+        int scpu = (long)hcpu;
 
         switch (action) {
 
         case CPU_UP_PREPARE:
         case CPU_UP_PREPARE_FROZEN:
-                init_hrtimers_cpu(cpu);
+                init_hrtimers_cpu(scpu);
                 break;
 
 #ifdef CONFIG_HOTPLUG_CPU
         case CPU_DEAD:
         case CPU_DEAD_FROZEN:
-                clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &cpu);
-                migrate_hrtimers(cpu);
+        {
+                int dcpu;
+
+                clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu);
+                dcpu = migrate_hrtimers(scpu);
+                smp_call_function_single(dcpu, tickle_timers, NULL, 0);
                 break;
+        }
 #endif
 
         default:
@@ -1748,8 +1609,105 @@ 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_HIGH_RES_TIMERS
-        open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
-#endif
 }
 
+/**
+ * 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);