Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "A rather largish update for everything time and timer related:

   - Cache footprint optimizations for both hrtimers and timer wheel

   - Lower the NOHZ impact on systems which have NOHZ or timer migration
     disabled at runtime.

   - Optimize run time overhead of hrtimer interrupt by making the clock
     offset updates smarter

   - hrtimer cleanups and removal of restrictions to tackle some
     problems in sched/perf

   - Some more leap second tweaks

   - Another round of changes addressing the 2038 problem

   - First step to change the internals of clock event devices by
     introducing the necessary infrastructure

   - Allow constant folding for usecs/msecs_to_jiffies()

   - The usual pile of clockevent/clocksource driver updates

  The hrtimer changes contain updates to sched, perf and x86 as they
  depend on them plus changes all over the tree to cleanup API changes
  and redundant code, which got copied all over the place.  The y2038
  changes touch s390 to remove the last non 2038 safe code related to
  boot/persistant clock"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (114 commits)
  clocksource: Increase dependencies of timer-stm32 to limit build wreckage
  timer: Minimize nohz off overhead
  timer: Reduce timer migration overhead if disabled
  timer: Stats: Simplify the flags handling
  timer: Replace timer base by a cpu index
  timer: Use hlist for the timer wheel hash buckets
  timer: Remove FIFO "guarantee"
  timers: Sanitize catchup_timer_jiffies() usage
  hrtimer: Allow hrtimer::function() to free the timer
  seqcount: Introduce raw_write_seqcount_barrier()
  seqcount: Rename write_seqcount_barrier()
  hrtimer: Fix hrtimer_is_queued() hole
  hrtimer: Remove HRTIMER_STATE_MIGRATE
  selftest: Timers: Avoid signal deadlock in leap-a-day
  timekeeping: Copy the shadow-timekeeper over the real timekeeper last
  clockevents: Check state instead of mode in suspend/resume path
  selftests: timers: Add leap-second timer edge testing to leap-a-day.c
  ntp: Do leapsecond adjustment in adjtimex read path
  time: Prevent early expiry of hrtimers[CLOCK_REALTIME] at the leap second edge
  ntp: Introduce and use SECS_PER_DAY macro instead of 86400
  ...

22 files changed, 1018 insertions, 1061 deletions

diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 01f0312419b3..ffc4cc3dcd47 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -13,19 +13,4 @@ obj-$(CONFIG_TIMER_STATS)			+= timer_stats.o
 obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
 obj-$(CONFIG_TEST_UDELAY)			+= test_udelay.o
 
-$(obj)/time.o: $(obj)/timeconst.h
-
-quiet_cmd_hzfile = HZFILE  $@
-      cmd_hzfile = echo "hz=$(CONFIG_HZ)" > $@
-
-targets += hz.bc
-$(obj)/hz.bc: $(objtree)/include/config/hz.h FORCE
-	$(call if_changed,hzfile)
-
-quiet_cmd_bc  = BC      $@
-      cmd_bc  = bc -q $(filter-out FORCE,$^) > $@
-
-targets += timeconst.h
-$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE
-	$(call if_changed,bc)
-
+$(obj)/time.o: $(objtree)/include/config/
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 1b001ed1edb9..7fbba635a549 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -317,19 +317,16 @@ EXPORT_SYMBOL_GPL(alarm_init);
  * @alarm: ptr to alarm to set
  * @start: time to run the alarm
  */
-int alarm_start(struct alarm *alarm, ktime_t start)
+void alarm_start(struct alarm *alarm, ktime_t start)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
 	unsigned long flags;
-	int ret;
 
 	spin_lock_irqsave(&base->lock, flags);
 	alarm->node.expires = start;
 	alarmtimer_enqueue(base, alarm);
-	ret = hrtimer_start(&alarm->timer, alarm->node.expires,
-				HRTIMER_MODE_ABS);
+	hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS);
 	spin_unlock_irqrestore(&base->lock, flags);
-	return ret;
 }
 EXPORT_SYMBOL_GPL(alarm_start);
 
@@ -338,12 +335,12 @@ EXPORT_SYMBOL_GPL(alarm_start);
  * @alarm: ptr to alarm to set
  * @start: time relative to now to run the alarm
  */
-int alarm_start_relative(struct alarm *alarm, ktime_t start)
+void alarm_start_relative(struct alarm *alarm, ktime_t start)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
 
 	start = ktime_add(start, base->gettime());
-	return alarm_start(alarm, start);
+	alarm_start(alarm, start);
 }
 EXPORT_SYMBOL_GPL(alarm_start_relative);
 
@@ -495,12 +492,12 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
  */
 static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp)
 {
-	clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid;
-
 	if (!alarmtimer_get_rtcdev())
 		return -EINVAL;
 
-	return hrtimer_get_res(baseid, tp);
+	tp->tv_sec = 0;
+	tp->tv_nsec = hrtimer_resolution;
+	return 0;
 }
 
 /**
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 637a09461c1d..08ccc3da3ca0 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -94,8 +94,8 @@ u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
 }
 EXPORT_SYMBOL_GPL(clockevent_delta2ns);
 
-static int __clockevents_set_state(struct clock_event_device *dev,
-				   enum clock_event_state state)
+static int __clockevents_switch_state(struct clock_event_device *dev,
+				      enum clock_event_state state)
 {
 	/* Transition with legacy set_mode() callback */
 	if (dev->set_mode) {
@@ -134,32 +134,44 @@ static int __clockevents_set_state(struct clock_event_device *dev,
 			return -ENOSYS;
 		return dev->set_state_oneshot(dev);
 
+	case CLOCK_EVT_STATE_ONESHOT_STOPPED:
+		/* Core internal bug */
+		if (WARN_ONCE(!clockevent_state_oneshot(dev),
+			      "Current state: %d\n",
+			      clockevent_get_state(dev)))
+			return -EINVAL;
+
+		if (dev->set_state_oneshot_stopped)
+			return dev->set_state_oneshot_stopped(dev);
+		else
+			return -ENOSYS;
+
 	default:
 		return -ENOSYS;
 	}
 }
 
 /**
- * clockevents_set_state - set the operating state of a clock event device
+ * clockevents_switch_state - set the operating state of a clock event device
  * @dev:	device to modify
  * @state:	new state
  *
  * Must be called with interrupts disabled !
  */
-void clockevents_set_state(struct clock_event_device *dev,
-			   enum clock_event_state state)
+void clockevents_switch_state(struct clock_event_device *dev,
+			      enum clock_event_state state)
 {
-	if (dev->state != state) {
-		if (__clockevents_set_state(dev, state))
+	if (clockevent_get_state(dev) != state) {
+		if (__clockevents_switch_state(dev, state))
 			return;
 
-		dev->state = state;
+		clockevent_set_state(dev, state);
 
 		/*
 		 * A nsec2cyc multiplicator of 0 is invalid and we'd crash
 		 * on it, so fix it up and emit a warning:
 		 */
-		if (state == CLOCK_EVT_STATE_ONESHOT) {
+		if (clockevent_state_oneshot(dev)) {
 			if (unlikely(!dev->mult)) {
 				dev->mult = 1;
 				WARN_ON(1);
@@ -174,7 +186,7 @@ void clockevents_set_state(struct clock_event_device *dev,
  */
 void clockevents_shutdown(struct clock_event_device *dev)
 {
-	clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
+	clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 	dev->next_event.tv64 = KTIME_MAX;
 }
 
@@ -248,7 +260,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev)
 		delta = dev->min_delta_ns;
 		dev->next_event = ktime_add_ns(ktime_get(), delta);
 
-		if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
+		if (clockevent_state_shutdown(dev))
 			return 0;
 
 		dev->retries++;
@@ -285,7 +297,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev)
 	delta = dev->min_delta_ns;
 	dev->next_event = ktime_add_ns(ktime_get(), delta);
 
-	if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
+	if (clockevent_state_shutdown(dev))
 		return 0;
 
 	dev->retries++;
@@ -317,9 +329,13 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
 
 	dev->next_event = expires;
 
-	if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
+	if (clockevent_state_shutdown(dev))
 		return 0;
 
+	/* We must be in ONESHOT state here */
+	WARN_ONCE(!clockevent_state_oneshot(dev), "Current state: %d\n",
+		  clockevent_get_state(dev));
+
 	/* Shortcut for clockevent devices that can deal with ktime. */
 	if (dev->features & CLOCK_EVT_FEAT_KTIME)
 		return dev->set_next_ktime(expires, dev);
@@ -362,7 +378,7 @@ static int clockevents_replace(struct clock_event_device *ced)
 	struct clock_event_device *dev, *newdev = NULL;
 
 	list_for_each_entry(dev, &clockevent_devices, list) {
-		if (dev == ced || dev->state != CLOCK_EVT_STATE_DETACHED)
+		if (dev == ced || !clockevent_state_detached(dev))
 			continue;
 
 		if (!tick_check_replacement(newdev, dev))
@@ -388,7 +404,7 @@ static int clockevents_replace(struct clock_event_device *ced)
 static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu)
 {
 	/* Fast track. Device is unused */
-	if (ced->state == CLOCK_EVT_STATE_DETACHED) {
+	if (clockevent_state_detached(ced)) {
 		list_del_init(&ced->list);
 		return 0;
 	}
@@ -445,7 +461,8 @@ static int clockevents_sanity_check(struct clock_event_device *dev)
 	if (dev->set_mode) {
 		/* We shouldn't be supporting new modes now */
 		WARN_ON(dev->set_state_periodic || dev->set_state_oneshot ||
-			dev->set_state_shutdown || dev->tick_resume);
+			dev->set_state_shutdown || dev->tick_resume ||
+			dev->set_state_oneshot_stopped);
 
 		BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
 		return 0;
@@ -480,7 +497,7 @@ void clockevents_register_device(struct clock_event_device *dev)
 	BUG_ON(clockevents_sanity_check(dev));
 
 	/* Initialize state to DETACHED */
-	dev->state = CLOCK_EVT_STATE_DETACHED;
+	clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED);
 
 	if (!dev->cpumask) {
 		WARN_ON(num_possible_cpus() > 1);
@@ -545,11 +562,11 @@ int __clockevents_update_freq(struct clock_event_device *dev, u32 freq)
 {
 	clockevents_config(dev, freq);
 
-	if (dev->state == CLOCK_EVT_STATE_ONESHOT)
+	if (clockevent_state_oneshot(dev))
 		return clockevents_program_event(dev, dev->next_event, false);
 
-	if (dev->state == CLOCK_EVT_STATE_PERIODIC)
-		return __clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC);
+	if (clockevent_state_periodic(dev))
+		return __clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
 
 	return 0;
 }
@@ -603,13 +620,13 @@ void clockevents_exchange_device(struct clock_event_device *old,
 	 */
 	if (old) {
 		module_put(old->owner);
-		clockevents_set_state(old, CLOCK_EVT_STATE_DETACHED);
+		clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED);
 		list_del(&old->list);
 		list_add(&old->list, &clockevents_released);
 	}
 
 	if (new) {
-		BUG_ON(new->state != CLOCK_EVT_STATE_DETACHED);
+		BUG_ON(!clockevent_state_detached(new));
 		clockevents_shutdown(new);
 	}
 }
@@ -622,7 +639,7 @@ void clockevents_suspend(void)
 	struct clock_event_device *dev;
 
 	list_for_each_entry_reverse(dev, &clockevent_devices, list)
-		if (dev->suspend)
+		if (dev->suspend && !clockevent_state_detached(dev))
 			dev->suspend(dev);
 }
 
@@ -634,7 +651,7 @@ void clockevents_resume(void)
 	struct clock_event_device *dev;
 
 	list_for_each_entry(dev, &clockevent_devices, list)
-		if (dev->resume)
+		if (dev->resume && !clockevent_state_detached(dev))
 			dev->resume(dev);
 }
 
@@ -665,7 +682,7 @@ void tick_cleanup_dead_cpu(int cpu)
 		if (cpumask_test_cpu(cpu, dev->cpumask) &&
 		    cpumask_weight(dev->cpumask) == 1 &&
 		    !tick_is_broadcast_device(dev)) {
-			BUG_ON(dev->state != CLOCK_EVT_STATE_DETACHED);
+			BUG_ON(!clockevent_state_detached(dev));
 			list_del(&dev->list);
 		}
 	}
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 15facb1b9c60..841b72f720e8 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -23,6 +23,8 @@
  *   o Allow clocksource drivers to be unregistered
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/device.h>
 #include <linux/clocksource.h>
 #include <linux/init.h>
@@ -216,10 +218,11 @@ static void clocksource_watchdog(unsigned long data)
 
 		/* Check the deviation from the watchdog clocksource. */
 		if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) {
-			pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable, because the skew is too large:\n", cs->name);
-			pr_warn("	'%s' wd_now: %llx wd_last: %llx mask: %llx\n",
+			pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable because the skew is too large:\n",
+				cs->name);
+			pr_warn("                      '%s' wd_now: %llx wd_last: %llx mask: %llx\n",
 				watchdog->name, wdnow, wdlast, watchdog->mask);
-			pr_warn("	'%s' cs_now: %llx cs_last: %llx mask: %llx\n",
+			pr_warn("                      '%s' cs_now: %llx cs_last: %llx mask: %llx\n",
 				cs->name, csnow, cslast, cs->mask);
 			__clocksource_unstable(cs);
 			continue;
@@ -567,9 +570,8 @@ static void __clocksource_select(bool skipcur)
 		 */
 		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && oneshot) {
 			/* Override clocksource cannot be used. */
-			printk(KERN_WARNING "Override clocksource %s is not "
-			       "HRT compatible. Cannot switch while in "
-			       "HRT/NOHZ mode\n", cs->name);
+			pr_warn("Override clocksource %s is not HRT compatible - cannot switch while in HRT/NOHZ mode\n",
+				cs->name);
 			override_name[0] = 0;
 		} else
 			/* Override clocksource can be used. */
@@ -708,8 +710,8 @@ void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq
 
 	clocksource_update_max_deferment(cs);
 
-	pr_info("clocksource %s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n",
-			cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns);
+	pr_info("%s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n",
+		cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns);
 }
 EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale);
 
@@ -1008,12 +1010,10 @@ __setup("clocksource=", boot_override_clocksource);
 static int __init boot_override_clock(char* str)
 {
 	if (!strcmp(str, "pmtmr")) {
-		printk("Warning: clock=pmtmr is deprecated. "
-			"Use clocksource=acpi_pm.\n");
+		pr_warn("clock=pmtmr is deprecated - use clocksource=acpi_pm\n");
 		return boot_override_clocksource("acpi_pm");
 	}
-	printk("Warning! clock= boot option is deprecated. "
-		"Use clocksource=xyz\n");
+	pr_warn("clock= boot option is deprecated - use clocksource=xyz\n");
 	return boot_override_clocksource(str);
 }
 
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 93ef7190bdea..5c7ae4b641c4 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -66,33 +66,29 @@
  */
 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,
-			.resolution = KTIME_LOW_RES,
 		},
 		{
 			.index = HRTIMER_BASE_REALTIME,
 			.clockid = CLOCK_REALTIME,
 			.get_time = &ktime_get_real,
-			.resolution = KTIME_LOW_RES,
 		},
 		{
 			.index = HRTIMER_BASE_BOOTTIME,
 			.clockid = CLOCK_BOOTTIME,
 			.get_time = &ktime_get_boottime,
-			.resolution = KTIME_LOW_RES,
 		},
 		{
 			.index = HRTIMER_BASE_TAI,
 			.clockid = CLOCK_TAI,
 			.get_time = &ktime_get_clocktai,
-			.resolution = KTIME_LOW_RES,
 		},
 	}
 };
@@ -109,27 +105,6 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 	return hrtimer_clock_to_base_table[clock_id];
 }
 
-
-/*
- * Get the coarse grained time at the softirq based on xtime and
- * wall_to_monotonic.
- */
-static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
-{
-	ktime_t xtim, mono, boot, tai;
-	ktime_t off_real, off_boot, off_tai;
-
-	mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai);
-	boot = ktime_add(mono, off_boot);
-	xtim = ktime_add(mono, off_real);
-	tai = ktime_add(mono, off_tai);
-
-	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
-	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
-	base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot;
-	base->clock_base[HRTIMER_BASE_TAI].softirq_time = tai;
-}
-
 /*
  * Functions and macros which are different for UP/SMP systems are kept in a
  * single place
@@ -137,6 +112,18 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 #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.
@@ -145,8 +132,8 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
  * be found on the lists/queues.
  *
  * When the timer's base is locked, and the timer removed from list, it is
- * possible to set timer->base = NULL and drop the lock: the timer remains
- * locked.
+ * 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,
@@ -156,7 +143,7 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 
 	for (;;) {
 		base = timer->base;
-		if (likely(base != NULL)) {
+		if (likely(base != &migration_base)) {
 			raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
 			if (likely(base == timer->base))
 				return base;
@@ -190,6 +177,24 @@ hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
 #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 this_cpu_ptr(&hrtimer_bases);
+	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 this_cpu_ptr(&hrtimer_bases);
+}
+#endif
+
 /*
  * Switch the timer base to the current CPU when possible.
  */
@@ -197,14 +202,13 @@ 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_base;
 	struct hrtimer_clock_base *new_base;
-	struct hrtimer_cpu_base *new_cpu_base;
-	int this_cpu = smp_processor_id();
-	int cpu = get_nohz_timer_target(pinned);
 	int basenum = base->index;
 
+	this_base = this_cpu_ptr(&hrtimer_bases);
+	new_cpu_base = get_target_base(this_base, pinned);
 again:
-	new_cpu_base = &per_cpu(hrtimer_bases, cpu);
 	new_base = &new_cpu_base->clock_base[basenum];
 
 	if (base != new_base) {
@@ -220,22 +224,24 @@ again:
 		if (unlikely(hrtimer_callback_running(timer)))
 			return base;
 
-		/* See the comment in lock_timer_base() */
-		timer->base = NULL;
+		/* 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 (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
-			cpu = this_cpu;
+		if (new_cpu_base != this_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_base;
 			timer->base = base;
 			goto again;
 		}
 		timer->base = new_base;
 	} else {
-		if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
-			cpu = this_cpu;
+		if (new_cpu_base != this_base &&
+		    hrtimer_check_target(timer, new_base)) {
+			new_cpu_base = this_base;
 			goto again;
 		}
 	}
@@ -443,24 +449,35 @@ static inline void debug_deactivate(struct hrtimer *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 };
-	int i;
+	unsigned int active = cpu_base->active_bases;
 
-	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
+	hrtimer_update_next_timer(cpu_base, NULL);
+	for (; active; base++, active >>= 1) {
 		struct timerqueue_node *next;
 		struct hrtimer *timer;
 
-		next = timerqueue_getnext(&base->active);
-		if (!next)
+		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)
+		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
@@ -473,6 +490,16 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
 }
 #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
 
@@ -480,6 +507,8 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
  * 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
@@ -508,9 +537,14 @@ static inline int hrtimer_is_hres_enabled(void)
 /*
  * 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 __this_cpu_read(hrtimer_bases.hres_active);
+	return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases));
 }
 
 /*
@@ -521,7 +555,12 @@ static inline int hrtimer_hres_active(void)
 static void
 hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 {
-	ktime_t expires_next = __hrtimer_get_next_event(cpu_base);
+	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;
@@ -545,63 +584,53 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 	if (cpu_base->hang_detected)
 		return;
 
-	if (cpu_base->expires_next.tv64 != KTIME_MAX)
-		tick_program_event(cpu_base->expires_next, 1);
+	tick_program_event(cpu_base->expires_next, 1);
 }
 
 /*
- * Shared reprogramming for clock_realtime and clock_monotonic
- *
  * When a timer is enqueued and expires earlier than the already enqueued
  * timers, we have to check, whether it expires earlier than the timer for
  * which the clock event device was armed.
  *
- * Note, that in case the state has HRTIMER_STATE_CALLBACK set, no reprogramming
- * and no expiry check happens. The timer gets enqueued into the rbtree. The
- * reprogramming and expiry check is done in the hrtimer_interrupt or in the
- * softirq.
- *
  * Called with interrupts disabled and base->cpu_base.lock held
  */
-static int hrtimer_reprogram(struct hrtimer *timer,
-			     struct hrtimer_clock_base *base)
+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);
-	int res;
 
 	WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
 
 	/*
-	 * When the callback is running, we do not reprogram the clock event
-	 * device. The timer callback is either running on a different CPU or
-	 * the callback is executed in the hrtimer_interrupt context. The
-	 * reprogramming is handled either by the softirq, which called the
-	 * callback or at the end of the hrtimer_interrupt.
+	 * If the timer is not on the current cpu, we cannot reprogram
+	 * the other cpus clock event device.
 	 */
-	if (hrtimer_callback_running(timer))
-		return 0;
+	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;
 
 	/*
 	 * CLOCK_REALTIME timer might be requested with an absolute
-	 * expiry time which is less than base->offset. Nothing wrong
-	 * about that, just avoid to call into the tick code, which
-	 * has now objections against negative expiry values.
+	 * expiry time which is less than base->offset. Set it to 0.
 	 */
 	if (expires.tv64 < 0)
-		return -ETIME;
+		expires.tv64 = 0;
 
 	if (expires.tv64 >= cpu_base->expires_next.tv64)
-		return 0;
+		return;
 
-	/*
-	 * When the target cpu of the timer is currently executing
-	 * hrtimer_interrupt(), then we do not touch the clock event
-	 * device. hrtimer_interrupt() will reevaluate all clock bases
-	 * before reprogramming the device.
-	 */
-	if (cpu_base->in_hrtirq)
-		return 0;
+	/* 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
@@ -610,15 +639,14 @@ static int hrtimer_reprogram(struct hrtimer *timer,
 	 * to make progress.
 	 */
 	if (cpu_base->hang_detected)
-		return 0;
+		return;
 
 	/*
-	 * Clockevents returns -ETIME, when the event was in the past.
+	 * Program the timer hardware. We enforce the expiry for
+	 * events which are already in the past.
 	 */
-	res = tick_program_event(expires, 0);
-	if (!IS_ERR_VALUE(res))
-		cpu_base->expires_next = expires;
-	return res;
+	cpu_base->expires_next = expires;
+	tick_program_event(expires, 1);
 }
 
 /*
@@ -630,15 +658,6 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
 	base->hres_active = 0;
 }
 
-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(offs_real, offs_boot, offs_tai);
-}
-
 /*
  * Retrigger next event is called after clock was set
  *
@@ -648,7 +667,7 @@ static void retrigger_next_event(void *arg)
 {
 	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
-	if (!hrtimer_hres_active())
+	if (!base->hres_active)
 		return;
 
 	raw_spin_lock(&base->lock);
@@ -662,29 +681,19 @@ static void retrigger_next_event(void *arg)
  */
 static int hrtimer_switch_to_hres(void)
 {
-	int i, cpu = smp_processor_id();
-	struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu);
-	unsigned long flags;
-
-	if (base->hres_active)
-		return 1;
-
-	local_irq_save(flags);
+	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
 	if (tick_init_highres()) {
-		local_irq_restore(flags);
 		printk(KERN_WARNING "Could not switch to high resolution "
-				    "mode on CPU %d\n", cpu);
+				    "mode on CPU %d\n", base->cpu);
 		return 0;
 	}
 	base->hres_active = 1;
-	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
-		base->clock_base[i].resolution = KTIME_HIGH_RES;
+	hrtimer_resolution = HIGH_RES_NSEC;
 
 	tick_setup_sched_timer();
 	/* "Retrigger" the interrupt to get things going */
 	retrigger_next_event(NULL);
-	local_irq_restore(flags);
 	return 1;
 }
 
@@ -706,6 +715,7 @@ void clock_was_set_delayed(void)
 
 #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 int hrtimer_switch_to_hres(void) { return 0; }
@@ -803,6 +813,14 @@ void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
  *
  * 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)
 {
@@ -814,8 +832,11 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
 	if (delta.tv64 < 0)
 		return 0;
 
-	if (interval.tv64 < timer->base->resolution.tv64)
-		interval.tv64 = timer->base->resolution.tv64;
+	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);
@@ -849,16 +870,11 @@ static int enqueue_hrtimer(struct hrtimer *timer,
 {
 	debug_activate(timer);
 
-	timerqueue_add(&base->active, &timer->node);
 	base->cpu_base->active_bases |= 1 << base->index;
 
-	/*
-	 * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
-	 * state of a possibly running callback.
-	 */
-	timer->state |= HRTIMER_STATE_ENQUEUED;
+	timer->state = HRTIMER_STATE_