Merge branch 'master' into upstream

13 files changed, 2862 insertions, 75 deletions

diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
new file mode 100644
index 00000000000..f6635112654
--- /dev/null
+++ b/kernel/time/Kconfig
@@ -0,0 +1,25 @@
+#
+# Timer subsystem related configuration options
+#
+config TICK_ONESHOT
+	bool
+	default n
+
+config NO_HZ
+	bool "Tickless System (Dynamic Ticks)"
+	depends on GENERIC_TIME && GENERIC_CLOCKEVENTS
+	select TICK_ONESHOT
+	help
+	  This option enables a tickless system: timer interrupts will
+	  only trigger on an as-needed basis both when the system is
+	  busy and when the system is idle.
+
+config HIGH_RES_TIMERS
+	bool "High Resolution Timer Support"
+	depends on GENERIC_TIME && GENERIC_CLOCKEVENTS
+	select TICK_ONESHOT
+	help
+	  This option enables high resolution timer support. If your
+	  hardware is not capable then this option only increases
+	  the size of the kernel image.
+
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 61a3907d16f..93bccba1f26 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1 +1,8 @@
-obj-y += ntp.o clocksource.o jiffies.o
+obj-y += ntp.o clocksource.o jiffies.o timer_list.o
+
+obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= clockevents.o
+obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
+obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)	+= tick-broadcast.o
+obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o
+obj-$(CONFIG_TICK_ONESHOT)			+= tick-sched.o
+obj-$(CONFIG_TIMER_STATS)			+= timer_stats.o
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
new file mode 100644
index 00000000000..67932ea78c1
--- /dev/null
+++ b/kernel/time/clockevents.c
@@ -0,0 +1,345 @@
+/*
+ * linux/kernel/time/clockevents.c
+ *
+ * This file contains functions which manage clock event devices.
+ *
+ * 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
+ *
+ * This code is licenced under the GPL version 2. For details see
+ * kernel-base/COPYING.
+ */
+
+#include <linux/clockchips.h>
+#include <linux/hrtimer.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/smp.h>
+#include <linux/sysdev.h>
+
+/* The registered clock event devices */
+static LIST_HEAD(clockevent_devices);
+static LIST_HEAD(clockevents_released);
+
+/* Notification for clock events */
+static RAW_NOTIFIER_HEAD(clockevents_chain);
+
+/* Protection for the above */
+static DEFINE_SPINLOCK(clockevents_lock);
+
+/**
+ * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds
+ * @latch:	value to convert
+ * @evt:	pointer to clock event device descriptor
+ *
+ * Math helper, returns latch value converted to nanoseconds (bound checked)
+ */
+unsigned long clockevent_delta2ns(unsigned long latch,
+				  struct clock_event_device *evt)
+{
+	u64 clc = ((u64) latch << evt->shift);
+
+	do_div(clc, evt->mult);
+	if (clc < 1000)
+		clc = 1000;
+	if (clc > LONG_MAX)
+		clc = LONG_MAX;
+
+	return (unsigned long) clc;
+}
+
+/**
+ * clockevents_set_mode - set the operating mode of a clock event device
+ * @dev:	device to modify
+ * @mode:	new mode
+ *
+ * Must be called with interrupts disabled !
+ */
+void clockevents_set_mode(struct clock_event_device *dev,
+				 enum clock_event_mode mode)
+{
+	if (dev->mode != mode) {
+		dev->set_mode(mode, dev);
+		dev->mode = mode;
+	}
+}
+
+/**
+ * clockevents_program_event - Reprogram the clock event device.
+ * @expires:	absolute expiry time (monotonic clock)
+ *
+ * Returns 0 on success, -ETIME when the event is in the past.
+ */
+int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
+			      ktime_t now)
+{
+	unsigned long long clc;
+	int64_t delta;
+
+	delta = ktime_to_ns(ktime_sub(expires, now));
+
+	if (delta <= 0)
+		return -ETIME;
+
+	dev->next_event = expires;
+
+	if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN)
+		return 0;
+
+	if (delta > dev->max_delta_ns)
+		delta = dev->max_delta_ns;
+	if (delta < dev->min_delta_ns)
+		delta = dev->min_delta_ns;
+
+	clc = delta * dev->mult;
+	clc >>= dev->shift;
+
+	return dev->set_next_event((unsigned long) clc, dev);
+}
+
+/**
+ * clockevents_register_notifier - register a clock events change listener
+ */
+int clockevents_register_notifier(struct notifier_block *nb)
+{
+	int ret;
+
+	spin_lock(&clockevents_lock);
+	ret = raw_notifier_chain_register(&clockevents_chain, nb);
+	spin_unlock(&clockevents_lock);
+
+	return ret;
+}
+
+/**
+ * clockevents_unregister_notifier - unregister a clock events change listener
+ */
+void clockevents_unregister_notifier(struct notifier_block *nb)
+{
+	spin_lock(&clockevents_lock);
+	raw_notifier_chain_unregister(&clockevents_chain, nb);
+	spin_unlock(&clockevents_lock);
+}
+
+/*
+ * Notify about a clock event change. Called with clockevents_lock
+ * held.
+ */
+static void clockevents_do_notify(unsigned long reason, void *dev)
+{
+	raw_notifier_call_chain(&clockevents_chain, reason, dev);
+}
+
+/*
+ * Called after a notify add to make devices availble which were
+ * released from the notifier call.
+ */
+static void clockevents_notify_released(void)
+{
+	struct clock_event_device *dev;
+
+	while (!list_empty(&clockevents_released)) {
+		dev = list_entry(clockevents_released.next,
+				 struct clock_event_device, list);
+		list_del(&dev->list);
+		list_add(&dev->list, &clockevent_devices);
+		clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+	}
+}
+
+/**
+ * clockevents_register_device - register a clock event device
+ * @dev:	device to register
+ */
+void clockevents_register_device(struct clock_event_device *dev)
+{
+	BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
+
+	spin_lock(&clockevents_lock);
+
+	list_add(&dev->list, &clockevent_devices);
+	clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+	clockevents_notify_released();
+
+	spin_unlock(&clockevents_lock);
+}
+
+/*
+ * Noop handler when we shut down an event device
+ */
+static void clockevents_handle_noop(struct clock_event_device *dev)
+{
+}
+
+/**
+ * clockevents_exchange_device - release and request clock devices
+ * @old:	device to release (can be NULL)
+ * @new:	device to request (can be NULL)
+ *
+ * Called from the notifier chain. clockevents_lock is held already
+ */
+void clockevents_exchange_device(struct clock_event_device *old,
+				 struct clock_event_device *new)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	/*
+	 * Caller releases a clock event device. We queue it into the
+	 * released list and do a notify add later.
+	 */
+	if (old) {
+		old->event_handler = clockevents_handle_noop;
+		clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
+		list_del(&old->list);
+		list_add(&old->list, &clockevents_released);
+	}
+
+	if (new) {
+		BUG_ON(new->mode != CLOCK_EVT_MODE_UNUSED);
+		clockevents_set_mode(new, CLOCK_EVT_MODE_SHUTDOWN);
+	}
+	local_irq_restore(flags);
+}
+
+/**
+ * clockevents_request_device
+ */
+struct clock_event_device *clockevents_request_device(unsigned int features,
+						      cpumask_t cpumask)
+{
+	struct clock_event_device *cur, *dev = NULL;
+	struct list_head *tmp;
+
+	spin_lock(&clockevents_lock);
+
+	list_for_each(tmp, &clockevent_devices) {
+		cur = list_entry(tmp, struct clock_event_device, list);
+
+		if ((cur->features & features) == features &&
+		    cpus_equal(cpumask, cur->cpumask)) {
+			if (!dev || dev->rating < cur->rating)
+				dev = cur;
+		}
+	}
+
+	clockevents_exchange_device(NULL, dev);
+
+	spin_unlock(&clockevents_lock);
+
+	return dev;
+}
+
+/**
+ * clockevents_release_device
+ */
+void clockevents_release_device(struct clock_event_device *dev)
+{
+	spin_lock(&clockevents_lock);
+
+	clockevents_exchange_device(dev, NULL);
+	clockevents_notify_released();
+
+	spin_unlock(&clockevents_lock);
+}
+
+/**
+ * clockevents_notify - notification about relevant events
+ */
+void clockevents_notify(unsigned long reason, void *arg)
+{
+	spin_lock(&clockevents_lock);
+	clockevents_do_notify(reason, arg);
+
+	switch (reason) {
+	case CLOCK_EVT_NOTIFY_CPU_DEAD:
+		/*
+		 * Unregister the clock event devices which were
+		 * released from the users in the notify chain.
+		 */
+		while (!list_empty(&clockevents_released)) {
+			struct clock_event_device *dev;
+
+			dev = list_entry(clockevents_released.next,
+					 struct clock_event_device, list);
+			list_del(&dev->list);
+		}
+		break;
+	default:
+		break;
+	}
+	spin_unlock(&clockevents_lock);
+}
+EXPORT_SYMBOL_GPL(clockevents_notify);
+
+#ifdef CONFIG_SYSFS
+
+/**
+ * clockevents_show_registered - sysfs interface for listing clockevents
+ * @dev:	unused
+ * @buf:	char buffer to be filled with clock events list
+ *
+ * Provides sysfs interface for listing registered clock event devices
+ */
+static ssize_t clockevents_show_registered(struct sys_device *dev, char *buf)
+{
+	struct list_head *tmp;
+	char *p = buf;
+	int cpu;
+
+	spin_lock(&clockevents_lock);
+
+	list_for_each(tmp, &clockevent_devices) {
+		struct clock_event_device *ce;
+
+		ce = list_entry(tmp, struct clock_event_device, list);
+		p += sprintf(p, "%-20s F:%04x M:%d", ce->name,
+			     ce->features, ce->mode);
+		p += sprintf(p, " C:");
+		if (!cpus_equal(ce->cpumask, cpu_possible_map)) {
+			for_each_cpu_mask(cpu, ce->cpumask)
+				p += sprintf(p, " %d", cpu);
+		} else {
+			/*
+			 * FIXME: Add the cpu which is handling this sucker
+			 */
+		}
+		p += sprintf(p, "\n");
+	}
+
+	spin_unlock(&clockevents_lock);
+
+	return p - buf;
+}
+
+/*
+ * Sysfs setup bits:
+ */
+static SYSDEV_ATTR(registered, 0600,
+		   clockevents_show_registered, NULL);
+
+static struct sysdev_class clockevents_sysclass = {
+	set_kset_name("clockevents"),
+};
+
+static struct sys_device clockevents_sys_device = {
+	.id	= 0,
+	.cls	= &clockevents_sysclass,
+};
+
+static int __init clockevents_sysfs_init(void)
+{
+	int error = sysdev_class_register(&clockevents_sysclass);
+
+	if (!error)
+		error = sysdev_register(&clockevents_sys_device);
+	if (!error)
+		error = sysdev_create_file(
+				&clockevents_sys_device,
+				&attr_registered);
+	return error;
+}
+device_initcall(clockevents_sysfs_init);
+#endif
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index d9ef176c4e0..193a0793af9 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -29,6 +29,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */
+#include <linux/tick.h>
 
 /* XXX - Would like a better way for initializing curr_clocksource */
 extern struct clocksource clocksource_jiffies;
@@ -48,6 +49,7 @@ extern struct clocksource clocksource_jiffies;
  */
 static struct clocksource *curr_clocksource = &clocksource_jiffies;
 static struct clocksource *next_clocksource;
+static struct clocksource *clocksource_override;
 static LIST_HEAD(clocksource_list);
 static DEFINE_SPINLOCK(clocksource_lock);
 static char override_name[32];
@@ -62,9 +64,123 @@ static int __init clocksource_done_booting(void)
 	finished_booting = 1;
 	return 0;
 }
-
 late_initcall(clocksource_done_booting);
 
+#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
+static LIST_HEAD(watchdog_list);
+static struct clocksource *watchdog;
+static struct timer_list watchdog_timer;
+static DEFINE_SPINLOCK(watchdog_lock);
+static cycle_t watchdog_last;
+/*
+ * Interval: 0.5sec Treshold: 0.0625s
+ */
+#define WATCHDOG_INTERVAL (HZ >> 1)
+#define WATCHDOG_TRESHOLD (NSEC_PER_SEC >> 4)
+
+static void clocksource_ratewd(struct clocksource *cs, int64_t delta)
+{
+	if (delta > -WATCHDOG_TRESHOLD && delta < WATCHDOG_TRESHOLD)
+		return;
+
+	printk(KERN_WARNING "Clocksource %s unstable (delta = %Ld ns)\n",
+	       cs->name, delta);
+	cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
+	clocksource_change_rating(cs, 0);
+	cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
+	list_del(&cs->wd_list);
+}
+
+static void clocksource_watchdog(unsigned long data)
+{
+	struct clocksource *cs, *tmp;
+	cycle_t csnow, wdnow;
+	int64_t wd_nsec, cs_nsec;
+
+	spin_lock(&watchdog_lock);
+
+	wdnow = watchdog->read();
+	wd_nsec = cyc2ns(watchdog, (wdnow - watchdog_last) & watchdog->mask);
+	watchdog_last = wdnow;
+
+	list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
+		csnow = cs->read();
+		/* Initialized ? */
+		if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) {
+			if ((cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) &&
+			    (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) {
+				cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+				/*
+				 * We just marked the clocksource as
+				 * highres-capable, notify the rest of the
+				 * system as well so that we transition
+				 * into high-res mode:
+				 */
+				tick_clock_notify();
+			}
+			cs->flags |= CLOCK_SOURCE_WATCHDOG;
+			cs->wd_last = csnow;
+		} else {
+			cs_nsec = cyc2ns(cs, (csnow - cs->wd_last) & cs->mask);
+			cs->wd_last = csnow;
+			/* Check the delta. Might remove from the list ! */
+			clocksource_ratewd(cs, cs_nsec - wd_nsec);
+		}
+	}
+
+	if (!list_empty(&watchdog_list)) {
+		__mod_timer(&watchdog_timer,
+			    watchdog_timer.expires + WATCHDOG_INTERVAL);
+	}
+	spin_unlock(&watchdog_lock);
+}
+static void clocksource_check_watchdog(struct clocksource *cs)
+{
+	struct clocksource *cse;
+	unsigned long flags;
+
+	spin_lock_irqsave(&watchdog_lock, flags);
+	if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
+		int started = !list_empty(&watchdog_list);
+
+		list_add(&cs->wd_list, &watchdog_list);
+		if (!started && watchdog) {
+			watchdog_last = watchdog->read();
+			watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
+			add_timer(&watchdog_timer);
+		}
+	} else if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) {
+			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+
+		if (!watchdog || cs->rating > watchdog->rating) {
+			if (watchdog)
+				del_timer(&watchdog_timer);
+			watchdog = cs;
+			init_timer(&watchdog_timer);
+			watchdog_timer.function = clocksource_watchdog;
+
+			/* Reset watchdog cycles */
+			list_for_each_entry(cse, &watchdog_list, wd_list)
+				cse->flags &= ~CLOCK_SOURCE_WATCHDOG;
+			/* Start if list is not empty */
+			if (!list_empty(&watchdog_list)) {
+				watchdog_last = watchdog->read();
+				watchdog_timer.expires =
+					jiffies + WATCHDOG_INTERVAL;
+				add_timer(&watchdog_timer);
+			}
+		}
+	}
+	spin_unlock_irqrestore(&watchdog_lock, flags);
+}
+#else
+static void clocksource_check_watchdog(struct clocksource *cs)
+{
+	if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
+		cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+}
+#endif
+
 /**
  * clocksource_get_next - Returns the selected clocksource
  *
@@ -84,60 +200,54 @@ struct clocksource *clocksource_get_next(void)
 }
 
 /**
- * select_clocksource - Finds the best registered clocksource.
+ * select_clocksource - Selects the best registered clocksource.
  *
  * Private function. Must hold clocksource_lock when called.
  *
- * Looks through the list of registered clocksources, returning
- * the one with the highest rating value. If there is a clocksource
- * name that matches the override string, it returns that clocksource.
+ * Select the clocksource with the best rating, or the clocksource,
+ * which is selected by userspace override.
  */
 static struct clocksource *select_clocksource(void)
 {
-	struct clocksource *best = NULL;
-	struct list_head *tmp;
+	struct clocksource *next;
 
-	list_for_each(tmp, &clocksource_list) {
-		struct clocksource *src;
+	if (list_empty(&clocksource_list))
+		return NULL;
 
-		src = list_entry(tmp, struct clocksource, list);
-		if (!best)
-			best = src;
-
-		/* check for override: */
-		if (strlen(src->name) == strlen(override_name) &&
-		    !strcmp(src->name, override_name)) {
-			best = src;
-			break;
-		}
-		/* pick the highest rating: */
-		if (src->rating > best->rating)
-		 	best = src;
-	}
+	if (clocksource_override)
+		next = clocksource_override;
+	else
+		next = list_entry(clocksource_list.next, struct clocksource,
+				  list);
+
+	if (next == curr_clocksource)
+		return NULL;
 
-	return best;
+	return next;
 }
 
-/**
- * is_registered_source - Checks if clocksource is registered
- * @c:		pointer to a clocksource
- *
- * Private helper function. Must hold clocksource_lock when called.
- *
- * Returns one if the clocksource is already registered, zero otherwise.
+/*
+ * Enqueue the clocksource sorted by rating
  */
-static int is_registered_source(struct clocksource *c)
+static int clocksource_enqueue(struct clocksource *c)
 {
-	int len = strlen(c->name);
-	struct list_head *tmp;
+	struct list_head *tmp, *entry = &clocksource_list;
 
 	list_for_each(tmp, &clocksource_list) {
-		struct clocksource *src;
-
-		src = list_entry(tmp, struct clocksource, list);
-		if (strlen(src->name) == len &&	!strcmp(src->name, c->name))
-			return 1;
+		struct clocksource *cs;
+
+		cs = list_entry(tmp, struct clocksource, list);
+		if (cs == c)
+			return -EBUSY;
+		/* Keep track of the place, where to insert */
+		if (cs->rating >= c->rating)
+			entry = tmp;
 	}
+	list_add(&c->list, entry);
+
+	if (strlen(c->name) == strlen(override_name) &&
+	    !strcmp(c->name, override_name))
+		clocksource_override = c;
 
 	return 0;
 }
@@ -150,42 +260,35 @@ static int is_registered_source(struct clocksource *c)
  */
 int clocksource_register(struct clocksource *c)
 {
-	int ret = 0;
 	unsigned long flags;
+	int ret;
 
 	spin_lock_irqsave(&clocksource_lock, flags);
-	/* check if clocksource is already registered */
-	if (is_registered_source(c)) {
-		printk("register_clocksource: Cannot register %s. "
-		       "Already registered!", c->name);
-		ret = -EBUSY;
-	} else {
-		/* register it */
- 		list_add(&c->list, &clocksource_list);
-		/* scan the registered clocksources, and pick the best one */
+	ret = clocksource_enqueue(c);
+	if (!ret)
 		next_clocksource = select_clocksource();
-	}
 	spin_unlock_irqrestore(&clocksource_lock, flags);
+	if (!ret)
+		clocksource_check_watchdog(c);
 	return ret;
 }
 EXPORT_SYMBOL(clocksource_register);
 
 /**
- * clocksource_reselect - Rescan list for next clocksource
+ * clocksource_change_rating - Change the rating of a registered clocksource
  *
- * A quick helper function to be used if a clocksource changes its
- * rating. Forces the clocksource list to be re-scanned for the best
- * clocksource.
  */
-void clocksource_reselect(void)
+void clocksource_change_rating(struct clocksource *cs, int rating)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&clocksource_lock, flags);
+	list_del(&cs->list);
+	cs->rating = rating;
+	clocksource_enqueue(cs);
 	next_clocksource = select_clocksource();
 	spin_unlock_irqrestore(&clocksource_lock, flags);
 }
-EXPORT_SYMBOL(clocksource_reselect);
 
 #ifdef CONFIG_SYSFS
 /**
@@ -221,7 +324,11 @@ sysfs_show_current_clocksources(struct sys_device *dev, char *buf)
 static ssize_t sysfs_override_clocksource(struct sys_device *dev,
 					  const char *buf, size_t count)
 {
+	struct clocksource *ovr = NULL;
+	struct list_head *tmp;
 	size_t ret = count;
+	int len;
+
 	/* strings from sysfs write are not 0 terminated! */
 	if (count >= sizeof(override_name))
 		return -EINVAL;
@@ -229,17 +336,32 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev,
 	/* strip of \n: */
 	if (buf[count-1] == '\n')
 		count--;
-	if (count < 1)
-		return -EINVAL;
 
 	spin_lock_irq(&clocksource_lock);
 
-	/* copy the name given: */
-	memcpy(override_name, buf, count);
+	if (count > 0)
+		memcpy(override_name, buf, count);
 	override_name[count] = 0;
 
-	/* try to select it: */
-	next_clocksource = select_clocksource();
+	len = strlen(override_name);
+	if (len) {
+		ovr = clocksource_override;
+		/* try to select it: */
+		list_for_each(tmp, &clocksource_list) {
+			struct clocksource *cs;
+
+			cs = list_entry(tmp, struct clocksource, list);
+			if (strlen(cs->name) == len &&
+			    !strcmp(cs->name, override_name))
+				ovr = cs;
+		}
+	}
+
+	/* Reselect, when the override name has changed */
+	if (ovr != clocksource_override) {
+		clocksource_override = ovr;
+		next_clocksource = select_clocksource();
+	}
 
 	spin_unlock_irq(&clocksource_lock);
 
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index a99b2a6e6a0..3be8da8fed7 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -62,7 +62,6 @@ struct clocksource clocksource_jiffies = {
 	.mask		= 0xffffffff, /*32bits*/
 	.mult		= NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
 	.shift		= JIFFIES_SHIFT,
-	.is_continuous	= 0, /* tick based, not free running */
 };
 
 static int __init init_jiffies_clocksource(void)
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 3afeaa3a73f..eb12509e00b 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -24,7 +24,7 @@ static u64 tick_length, tick_length_base;
 
 #define MAX_TICKADJ		500		/* microsecs */
 #define MAX_TICKADJ_SCALED	(((u64)(MAX_TICKADJ * NSEC_PER_USEC) << \
-				  TICK_LENGTH_SHIFT) / HZ)
+				  TICK_LENGTH_SHIFT) / NTP_INTERVAL_FREQ)
 
 /*
  * phase-lock loop variables
@@ -46,13 +46,17 @@ long time_adjust;
 
 static void ntp_update_frequency(void)
 {
-	tick_length_base = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ) << TICK_LENGTH_SHIFT;
-	tick_length_base += (s64)CLOCK_TICK_ADJUST << TICK_LENGTH_SHIFT;
-	tick_length_base += (s64)time_freq << (TICK_LENGTH_SHIFT - SHIFT_NSEC);
+	u64 second_length = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ)
+				<< TICK_LENGTH_SHIFT;
+	second_length += (s64)CLOCK_TICK_ADJUST << TICK_LENGTH_SHIFT;
+	second_length += (s64)time_freq << (TICK_LENGTH_SHIFT - SHIFT_NSEC);
 
-	do_div(tick_length_base, HZ);
+	tick_length_base = second_length;
 
-	tick_nsec = tick_length_base >> TICK_LENGTH_SHIFT;
+	do_div(second_length, HZ);
+	tick_nsec = second_length >> TICK_LENGTH_SHIFT;
+
+	do_div(tick_length_base, NTP_INTERVAL_FREQ);
 }
 
 /**
@@ -162,7 +166,7 @@ void second_overflow(void)
 			tick_length -= MAX_TICKADJ_SCALED;
 		} else {
 			tick_length += (s64)(time_adjust * NSEC_PER_USEC /
-					     HZ) << TICK_LENGTH_SHIFT;
+					NTP_INTERVAL_FREQ) << TICK_LENGTH_SHIFT;
 			time_adjust = 0;
 		}
 	}
@@ -239,7 +243,8 @@ int do_adjtimex(struct timex *txc)
 		    result = -EINVAL;
 		    goto leave;
 		}
-		time_freq = ((s64)txc->freq * NSEC_PER_USEC) >> (SHIFT_USEC - SHIFT_NSEC);
+		time_freq = ((s64)txc->freq * NSEC_PER_USEC)
+				>> (SHIFT_USEC - SHIFT_NSEC);
 	    }
 
 	    if (txc->modes & ADJ_MAXERROR) {
@@ -309,7 +314,8 @@ int do_adjtimex(struct timex *txc)
 		    freq_adj += time_freq;
 		    freq_adj = min(freq_adj, (s64)MAXFREQ_NSEC);
 		    time_freq = max(freq_adj, (s64)-MAXFREQ_NSEC);
-		    time_offset = (time_offset / HZ) << SHIFT_UPDATE;
+		    time_offset = (time_offset / NTP_INTERVAL_FREQ)
+		    			<< SHIFT_UPDATE;
 		} /* STA_PLL */
 	    } /* txc->modes & ADJ_OFFSET */
 	    if (txc->modes & ADJ_TICK)
@@ -324,8 +330,10 @@ leave:	if ((time_status & (STA_UNSYNC|STA_CLOCKERR)) != 0)
 	if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT)
 	    txc->offset	   = save_adjust;
 	else
-	    txc->offset    = shift_right(time_offset, SHIFT_UPDATE) * HZ / 1000;
-	txc->freq	   = (time_freq / NSEC_PER_USEC) << (SHIFT_USEC - SHIFT_NSEC);
+	    txc->offset    = shift_right(time_offset, SHIFT_UPDATE)
+	    			* NTP_INTERVAL_FREQ / 1000;
+	txc->freq	   = (time_freq / NSEC_PER_USEC)
+				<< (SHIFT_USEC - SHIFT_NSEC);
 	txc->maxerror	   = time_maxerror;
 	txc->esterror	   = time_esterror;
 	txc->status	   = time_status;
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
new file mode 100644
index 00000000000..12b3efeb9f6
--- /dev/null
+++ b/kernel/time/tick-broadcast.c
@@ -0,0 +1,480 @@
+/*
+ * linux/kernel/time/tick-broadcast.c
+ *
+ * This file contains functions which emulate a local clock-event
+ * device via a broadcast event source.
+ *
+ * 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
+ *
+ * This code is licenced under the GPL version 2. For details see
+ * kernel-base/COPYING.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/irq.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+#include <linux/tick.h>
+
+#include "tick-internal.h"
+
+/*
+ * Broadcast support for broken x86 hardware, where the local apic
+ * timer stops in C3 state.
+ */
+
+struct tick_device tick_broadcast_device;
+static cpumask_t tick_broadcast_mask;
+static DEFINE_SPINLOCK(tick_broadcast_lock);
+
+/*
+ * Debugging: see timer_list.c
+ */
+struct tick_device *tick_get_broadcast_device(void)
+{
+	return &tick_broadcast_device;
+}
+
+cpumask_t *tick_get_broadcast_mask(void)
+{
+	return &tick_broadcast_mask;
+}
+
+/*
+ * Start the device in periodic mode
+ */
+static void tick_broadcast_start_periodic(struct clock_event_device *bc)
+{
+	if (bc && bc->mode == CLOCK_EVT_MODE_SHUTDOWN)
+		tick_setup_periodic(bc, 1);
+}
+
+/*
+ * Check, if the device can be utilized as broadcast device:
+ */
+int tick_check_broadcast_device(struct clock_event_device *dev)
+{
+	if (tick_broadcast_device.evtdev ||
+	    (dev->features & CLOCK_EVT_FEAT_C3STOP))
+		return 0;
+
+	clockevents_exchange_device(NULL, dev);
+	tick_broadcast_device.evtdev = dev;
+	if (!cpus_empty(tick_broadcast_mask))
+		tick_broadcast_start_periodic(dev);
+	return 1;
+}
+
+/*
+ * Check, if the device is the broadcast device
+ */
+int tick_is_broadcast_device(struct clock_event_device *dev)
+{
+	return (dev && tick_broadcast_device.evtdev == dev);
+}
+
+/*
+ * Check, if the device is disfunctional and a place holder, which
+ * needs to be handled by the broadcast device.
+ */
+int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+	/*
+	 * Devices might be registered with both periodic and oneshot
+	 * mode disabled. This signals, that the device needs to be
+	 * operated from the broadcast device and is a placeholder for
+	 * the cpu local device.
+	 */
+	if (!tick_device_is_functional(dev)) {
+		dev->event_handler = tick_handle_periodic;
+		cpu_set(cpu, tick_broadcast_mask);
+		tick_broadcast_start_periodic(tick_broadcast_device.evtdev);
+		ret = 1;
+	}
+
+	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+	return ret;
+}
+
+/*
+ * Broadcast the event to the cpus, which are set in the mask
+ */
+int tick_do_broadcast(cpumask_t mask)
+{
+	int ret = 0, cpu = smp_processor_id();
+	struct tick_device *td;
+
+	/*
+	 * Check, if the current cpu is in the mask
+	 */
+	if (cpu_isset(cpu, mask)) {
+		cpu_clear(cpu, mask);
+		td = &per_cpu(tick_cpu_device, cpu);
+		td->evtdev->event_handler(td->evtdev);
+		ret = 1;
+	}
+
+	if (!cpus_empty(mask)) {
+		/*
+		 * It might be necessary to actually check whether the devices
+		 * have different broadcast functions. For now, just use the
+		 * one of the first device. This works as long as we have this
+		 * misfeature only on x86 (lapic)
+		 */
+		cpu = first_cpu(mask);
+		td = &per_cpu(tick_cpu_device, cpu);
+		td->evtdev->broadcast(mask);
+		ret = 1;
+	}
+	return ret;
+}
+
+/*
+ * Periodic broadcast:
+ * - invoke the broadcast handlers
+ */
+static void tick_do_periodic_broadcast(void)
+{
+	cpumask_t mask;
+
+	spin_lock(&tick_broadcast_lock);
+
+	cpus_and(mask, cpu_online_map, tick_broadcast_mask);
+	tick_do_broadcast(mask);
+
+	spin_unlock(&tick_broadcast_lock);
+}
+
+/*
+ * Event handler for periodic broadcast ticks
+ */
+static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
+{
+	dev->next_event.tv64 = KTIME_MAX;
+
+	tick_do_periodic_broadcast();
+
+	/*
+	 * The device is in periodic mode. No reprogramming necessary:
+	 */
+	if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
+		return;
+
+	/*
+	 * Setup the next period for devices, which do not have
+	 * periodic mode:
+	 */
+	for (;;) {
+		ktime_t next = ktime_add(dev->next_event, tick_period);
+
+		if (!clockevents_program_event(dev, next, ktime_get()))
+			return;
+		tick_do_periodic_broadcast();
+	}
+}
+
+/*
+ * Powerstate information: The system enters/leaves a state, where
+ * affected devices might stop
+ */
+static void tick_do_broadcast_on_off(void *why)
+{
+	struct clock_event_device *bc, *dev;
+	struct tick_device *td;
+	unsigned long flags, *reason = why;
+	int cpu;
+
+	spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+	cpu = smp_processor_id();
+	td = &per_cpu(tick_cpu_device, cpu);
+	dev = td->evtdev;
+	bc = tick_broadcast_device.evtdev;
+
+	/*
+	 * Is the device in broadcast mode forever or is it not
+	 * affected by the powerstate ?
+	 */
+	if (!dev || !tick_device_is_functional(dev) ||
+	    !(dev->features & CLOCK_EVT_FEAT_C3STOP))
+		goto out;
+
+	if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_ON) {
+		if (!cpu_isset(cpu, tick_broadcast_mask)) {
+			cpu_set(cpu, tick_broadcast_mask);
+			if (td->mode == TICKDEV_MODE_PERIODIC)
+				clockevents_set_mode(dev,
+						     CLOCK_EVT_MODE_SHUTDOWN);
+		}
+	} else {
+		if (cpu_isset(cpu, tick_broadcast_mask)) {
+			cpu_clear(cpu, tick_broadcast_mask);
+			if (td->mode == TICKDEV_MODE_PERIODIC)
+				tick_setup_periodic(dev, 0);
+		}
+	}
+
+	if (cpus_empty(tick_broadcast_mask))
+		clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+	else {
+		if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
+			tick_broadcast_start_periodic(bc);
+		else
+			tick_broadcast_setup_oneshot(bc);
+	}
+out:
+	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+/*
+ * Powerstate information: The system enters/leaves a state, where
+ * affected devices might stop.
+ */
+void tick_broadcast_on_off(unsigned long reason, int *oncpu)
+{
+	int cpu = get_cpu();
+
+	if (cpu == *oncpu)
+		tick_do_broadcast_on_off(&reason);
+	else
+		smp_call_function_single(*oncpu, tick_do_broadcast_on_off,
+					 &reason, 1, 1);
+	put_cpu();
+}
+
+/*
+ * Set the periodic handler depending on broadcast on/off
+ */
+void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast)
+{
+	if (!broadcast)
+		dev->event_handler = tick_handle_periodic;
+	else
+		dev->event_handler = tick_handle_periodic_broadcast;
+}
+
+/*
+ * Remove a CPU from broadcasting
+ */
+void tick_shutdown_broadcast(unsigned int *cpup)
+{
+	struct clock_event_device *bc;
+	unsigned long flags;
+	unsigned int cpu = *cpup;
+
+	spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+	bc = tick_broadcast_device.evtdev;
+	cpu_clear(cpu, tick_broadcast_mask);
+
+	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
+		if (bc && cpus_empty(tick_broadcast_mask))
+			clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+	}
+
+	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+#ifdef CONFIG_TICK_ONESHOT
+
+static cpumask_t tick_broadcast_oneshot_mask;
+
+/*
+ * Debugging: see timer_list.c
+ */
+cpumask_t *tick_get_broadcast_oneshot_mask(void)
+{
+	return &tick_broadcast_oneshot_mask;
+}
+
+static int tick_broadcast_set_event(ktime_t expires, int force)
+{
+	struct clock_event_device *bc = tick_broadcast_device.evtdev;
+	ktime_t now = ktime_get();
+	int res;
+
+	for(;;) {
+		res = clockevents_program_event(bc, expires, now);
+		if (!res || !force)
+			return res;
+		now = ktime_get();
+		expires = ktime_add(now, ktime_set(0, bc->min_delta_ns));
+	}
+}
+
+/*
+ * Reprogram the broadcast device:
+ *
+ * Called with tick_broadcast_lock held and interrupts disabled.
+ */
+static int tick_broadcast_reprogram(void)
+{
+	ktime_t expires = { .tv64 = KTIME_MAX };
+	struct tick_device *td;
+	int cpu;
+
+	/*
+	 * Find the event which expires next:
+	 */
+	for (cpu = first_cpu(tick_broadcast_oneshot_mask); cpu != NR_CPUS;
+	     cpu = next_cpu(cpu, tick_broadcast_oneshot_mask)) {
+		td = &per_cpu(tick_cpu_device, cpu);
+		if (td->evtdev->next_event.tv64 < expires.tv64)
+			expires = td->evtdev->next_event;
+	}
+
+	if (expires.tv64 == KTIME_MAX)
+		return 0;
+
+	return tick_broadcast_set_event(expires, 0);
+}
+
+/*
+ * Handle oneshot mode broadcasting
+ */
+static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
+{
+	struct tick_device *td;
+	cpumask_t mask;
+	ktime_t now;
+	int cpu;
+
+	spin_lock(&tick_broadcast_lock);
+again:
+	dev->next_event.tv64 = KTIME_MAX;
+	mask = CPU_MASK_NONE;
+	now = ktime_get();
+	/* Find all expired events */
+	for (cpu = first_cpu(tick_broadcast_oneshot_mask); cpu != NR_CPUS;
+	     cpu = next_cpu(cpu, tick_broadcast_oneshot_mask)) {
+		td = &per_cpu(tick_cpu_device, cpu);
+		if (td->evtdev->next_event.tv64 <= now.tv64)
+			cpu_set(cpu, mask);
+	}
+
+	/*
+	 * Wakeup the cpus which have an expired event. The broadcast
+	 * device is reprogrammed in the return from idle code.
+	 */
+	if (!tick_do_broadcast(mask)) {
+		/*
+		 * The global event did not expire any CPU local
+		 * events. This happens in dyntick mode, as the
+		 * maximum PIT delta is quite small.
+		 */
+		if (tick_broadcast_reprogram())
+			goto again;
+	}
+	spin_unlock(&tick_broadcast_lock);
+}
+
+/*
+ * Powerstate information: The system enters/leaves a state, where
+ * affected devices might stop
+ */
+void tick_broadcast_oneshot_control(unsigned long reason)
+{
+	struct clock_event_device *bc, *dev;
+	struct tick_device *td;
+	unsigned long flags;
+	int cpu;
+
+	spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+	/*
+	 * Periodic mode does not care about the enter/exit of power
+	 * states
+	 */
+	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
+		goto out;
+
+	bc = tick_broadcast_device.evtdev;
+	cpu = smp_processor_id();
+	td = &per_cpu(tick_cpu_device, cpu);
+	dev = td->evtdev;
+
+	if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
+		goto out;
+
+	if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
+		if (!cpu_isset(cpu, tick_broadcast_oneshot_mask)) {
+			cpu_set(cpu, tick_broadcast_oneshot_mask);
+			clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+			if (dev->next_event.tv64 < bc->next_event.tv64)
+				tick_broadcast_set_event(dev->next_event, 1);
+		}
+	} else {
+		if (cpu_isset(cpu, tick_broadcast_oneshot_mask)) {
+			cpu_clear(cpu, tick_broadcast_oneshot_mask);
+			clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+			if (dev->next_event.tv64 != KTIME_MAX)
+				tick_program_event(dev->next_event, 1);
+		}
+	}
+
+out:
+	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+/**
+ * tick_broadcast_setup_highres - setup the broadcast device for highres
+ */
+void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
+{
+	if (bc->mode != CLOCK_EVT_MODE_ONESHOT) {
+		bc->event_handler = tick_handle_oneshot_broadcast;
+		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+		bc->next_event.tv64 = KTIME_MAX;
+	}
+}
+
+/*
+ * Select oneshot operating mode for the broadcast device
+ */
+void tick_broadcast_switch_to_oneshot(void)
+{
+	struct clock_event_device *bc;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+	tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT;
+	bc = tick_broadcast_device.evtdev;
+	if (bc)
+		tick_broadcast_setup_oneshot(bc);
+	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+
+/*
+ * Remove a dead CPU from broadcasting
+ */
+void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
+{
+	struct clock_event_device *bc;
+	unsigned long flags;
+	unsigned int cpu = *cpup;
+
+	spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+	bc = tick_broadcast_device.evtdev;
+	cpu_clear(cpu, tick_broadcast_oneshot_mask);
+
+	if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT) {
+		if (bc && cpus_empty(tick_broadcast_oneshot_mask))
+			clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+	}
+
+	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+#endif
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
new file mode 100644
index 00000000000..4500e347f1b
--- /dev/null
+++ b/kernel/time/tick-common.c
@@ -0,0 +1,346 @@
+/*
+ * linux/kernel/time/tick-common.c
+ *
+ * This file contains the base functions to manage periodic tick
+ * related events.
+ *
+ * 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
+ *
+ * This code is licenced under the GPL version 2. For details see
+ * kernel-base/COPYING.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/irq.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+#include <linux/tick.h>
+
+#include "tick-internal.h"
+
+/*
+ * Tick devices
+ */
+DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
+/*
+ * Tick next event: keeps track of the tick time
+ */
+ktime_t tick_next_period;
+ktime_t tick_period;
+static int tick_do_timer_cpu = -1;
+DEFINE_SPINLOCK(tick_device_lock);
+
+/*
+ * Debugging: see timer_list.c
+ */
+struct tick_device *tick_get_device(int cpu)
+{
+	return &per_cpu(tick_cpu_device, cpu);
+}
+
+/**
+ * tick_is_oneshot_available - check for a oneshot capable event device
+ */
+int tick_is_oneshot_available(void)
+{
+	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+
+	return dev && (dev->features & CLOCK_EVT_FEAT_ONESHOT);
+}
+
+/*
+ * Periodic tick
+ */
+static void tick_periodic(int cpu)
+{
+	if (tick_do_timer_cpu == cpu) {
+		write_seqlock(&xtime_lock);
+
+		/* Keep track of the next tick event */
+		tick_next_period = ktime_add(tick_next_period, tick_period);
+
+		do_timer(1);
+		write_sequnlock(&xtime_lock);
+	}
+
+	update_process_times(user_mode(get_irq_regs()));
+	profile_tick(CPU_PROFILING);
+}
+
+/*
+ * Event handler for periodic ticks
+ */
+void tick_handle_periodic(struct clock_event_device *dev)
+{
+	int cpu = smp_processor_id();
+
+	tick_periodic(cpu);
+
+	if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
+		return;
+	/*
+	 * Setup the next period for devices, which do not have
+	 * periodic mode:
+	 */
+	for (;;) {
+		ktime_t next = ktime_add(dev->next_event, tick_period);
+
+		if (!clockevents_program_event(dev, next, ktime_get()))
+			return;
+		tick_periodic(cpu);
+	}
+}
+
+/*
+ * Setup the device for a periodic tick
+ */
+void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
+{
+	tick_set_periodic_handler(dev, broadcast);
+
+	/* Broadcast setup ? */
+	if (!tick_device_is_functional(dev))
+		return;
+
+	if (dev->features & CLOCK_EVT_FEAT_PERIODIC) {
+		clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC);
+	} else {
+		unsigned long seq;
+		ktime_t next;
+
+		do {
+			seq = read_seqbegin(&xtime_lock);
+			next = tick_next_period;
+		} while (read_seqretry(&xtime_lock, seq));
+
+		clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+
+		for (;;) {
+			if (!clockevents_program_event(dev, next, ktime_get()))
+				return;
+			next = ktime_add(next, tick_period);
+		}
+	}
+}
+
+/*
+ * Setup the tick device
+ */
+static void tick_setup_device(struct tick_device *td,
+			      struct clock_event_device *newdev, int cpu,
+			      cpumask_t cpumask)
+{
+	ktime_t next_event;
+	void (*handler)(struct clock_event_device *) = NULL;
+
+	/*
+	 * First device setup ?
+	 */
+	if (!td->evtdev) {
+		/*
+		 * If no cpu took the do_timer update, assign it to
+		 * this cpu:
+		 */
+		if (tick_do_timer_cpu == -1) {
+			tick_do_timer_cpu = cpu;
+			tick_next_period = ktime_get();
+			tick_period = ktime_set(0, NSEC_PER_SEC / HZ);
+		}
+
+		/*
+		 * Startup in periodic mode first.
+		 */
+		td->mode = TICKDEV_MODE_PERIODIC;
+	} else {
+		handler = td->evtdev->event_handler;
+		next_event = td->evtdev->next_event;
+	}
+
+	td->evtdev = newdev;
+
+	/*
+	 * When the device is not per cpu, pin the interrupt to the
+	 * current cpu:
+	 */
+	if (!cpus_equal(newdev->cpumask, cpumask))
+		irq_set_affinity(newdev->irq, cpumask);
+
+	/*
+	 * When global broadcasting is active, check if the current
+	 * device is registered as a placeholder for broadcast mode.
+	 * This allows us to handle this x86 misfeature in a generic
+	 * way.
+	 */
+	if (tick_device_uses_broadcast(newdev, cpu))
+		return;
+
+	if (td->mode == TICKDEV_MODE_PERIODIC)
+		tick_setup_periodic(newdev, 0);
+	else
+		tick_setup_oneshot(newdev, handler, next_event);
+}
+
+/*
+ * Check, if the new registered device should be used.
+ */
+static int tick_check_new_device(struct clock_event_device *newdev)
+{
+	struct clock_event_device *curdev;
+	struct tick_device *td;
+	int cpu, ret = NOTIFY_OK;
+	unsigned long flags;
+	cpumask_t cpumask;
+
+	spin_lock_irqsave(&tick_device_lock, flags);
+
+	cpu = smp_processor_id();
+	if (!cpu_isset(cpu, newdev->cpumask))
+		goto out;
+
+	td = &per_cpu(tick_cpu_device, cpu);
+	curdev = td->evtdev;
+	cpumask = cpumask_of_cpu(cpu);
+
+	/* cpu local device ? */
+	if (!cpus_equal(newdev->cpumask, cpumask)) {
+
+		/*
+		 * If the cpu affinity of the device interrupt can not
+		 * be set, ignore it.
+		 */
+		if (!irq_can_set_affinity(newdev->irq))
+			goto out_bc;
+
+		/*
+		 * If we have a cpu local device already, do not replace it
+		 * by a non cpu local device
+		 */
+		if (curdev && cpus_equal(curdev->cpumask, cpumask))
+			goto out_bc;
+	}
+
+	/*
+	 * If we have an active device, then check the rating and the oneshot
+	 * feature.
+	 */
+	if (curdev) {
+		/*
+		 * Prefer one shot capable devices !
+		 */
+		if ((curdev->features & CLOCK_EVT_FEAT_ONESHOT) &&
+		    !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
+			goto out_bc;
+		/*
+		 * Check the rating
+		 */
+		if (curdev->rating >= newdev->rating)
+			goto out_bc;
+	}
+
+	/*
+	 * Replace the eventually existing device by the new
+	 * device. If the current device is the broadcast device, do
+	 * not give it back to the clockevents layer !
+	 */
+	if (tick_is_broadcast_device(curdev)) {
+		clockevents_set_mode(curdev, CLOCK_EVT_MODE_SHUTDOWN);
+		curdev = NULL;
+	}
+	clockevents_exchange_device(curdev, newdev);
+	tick_setup_device(td, newdev, cpu, cpumask);
+	if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
+		tick_oneshot_notify();
+
+	spin_unlock_irqrestore(&tick_device_lock, flags);
+	return NOTIFY_STOP;
+
+out_bc:
+	/*
+	 * Can the new device be used as a broadcast device ?
+	 */
+	if (tick_check_broadcast_device(newdev))
+		ret = NOTIFY_STOP;
+out:
+	spin_unlock_irqrestore(&tick_device_lock, flags);
+
+	return ret;
+}
+
+/*
+ * Shutdown an event device on a given cpu:
+ *
+ * This is called on a life CPU, when a CPU is dead. So we cannot
+ * access the hardware device itself.
+ * We just set the mode and remove it from the lists.
+ */
+static void tick_shutdown(unsigned int *cpup)
+{
+	struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
+	struct clock_event_device *dev = td->evtdev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tick_device_lock, flags);
+	td->mode = TICKDEV_MODE_PERIODIC;
+	if (dev) {
+		/*
+		 * Prevent that the clock events layer tries to call
+		 * the set mode function!
+		 */
+		dev->mode = CLOCK_EVT_MODE_UNUSED;
+		clockevents_exchange_device(dev, NULL);
+		td->evtdev = NULL;
+	}
+	spin_unlock_irqrestore(&tick_device_lock, flags);
+}
+
+/*
+ * Notification about clock event devices
+ */
+static int tick_notify(struct notifier_block *nb, unsigned long reason,
+			       void *dev)
+{
+	switch (reason) {
+
+	case CLOCK_EVT_NOTIFY_ADD:
+		return tick_check_new_device(dev);
+
+	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
+	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
+		tick_broadcast_on_off(reason, dev);
+		break;
+
+	case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
+	case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
+		tick_broadcast_oneshot_control(reason);
+		break;
+
+	case CLOCK_EVT_NOTIFY_CPU_DEAD:
+		tick_shutdown_broadcast_oneshot(dev);
+		tick_shutdown_broadcast(dev);
+		tick_shutdown(dev);
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block tick_notifier = {
+	.notifier_call = tick_notify,
+};
+
+/**
+ * tick_init - initialize the tick control
+ *
+ * Register the notifier with the clockevents framework
+ */
+void __init tick_init(void)
+{
+	clockevents_register_notifier(&tick_notifier);
+}
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
new file mode 100644
index 00000000000..54861a0f29f
--- /dev/null
+++ b/kernel/time/tick-internal.h
@@ -0,0 +1,110 @@
+/*
+ * tick internal variable and functions used by low/high res code
+ */
+DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
+extern spinlock_t tick_device_lock;
+extern ktime_t tick_next_period;
+extern ktime_t tick_period;
+
+extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast);
+extern void tick_handle_periodic(struct clock_event_device *dev);
+
+/*
+ * NO_HZ / high resolution timer shared code
+ */
+#ifdef CONFIG_TICK_ONESHOT
+extern void tick_setup_oneshot(struct clock_event_device *newdev,
+			       void (*handler)(struct clock_event_device *),
+			       ktime_t nextevt);
+extern int tick_program_event(ktime_t expires, int force);
+extern void tick_oneshot_notify(void);
+extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));
+
+# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
+extern void tick_broadcast_oneshot_control(unsigned long reason);
+extern void tick_broadcast_switch_to_oneshot(void);
+extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
+# else /* BROADCAST */
+static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
+{
+	BUG();
+}
+static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline void tick_broadcast_switch_to_oneshot(void) { }
+static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
+# endif /* !BROADCAST */
+
+#else /* !ONESHOT */
+static inline
+void tick_setup_oneshot(struct clock_event_device *newdev,
+			void (*handler)(struct clock_event_device *),
+			ktime_t nextevt)
+{
+	BUG();
+}
+static inline int tick_program_event(ktime_t expires, int force)
+{
+	return 0;
+}
+static inline void tick_oneshot_notify(void) { }
+static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
+{
+	BUG();
+}
+static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
+#endif /* !TICK_ONESHOT */
+
+/*
+ * Broadcasting support
+ */
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+extern int tick_do_broadcast(cpumask_t mask);
+
+extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
+extern int tick_check_broadcast_device(struct clock_event_device *dev);
+extern int tick_is_broadcast_device(struct clock_event_device *dev);
+extern void tick_broadcast_on_off(unsigned long reason, int *oncpu);
+extern void tick_shutdown_broadcast(unsigned int *cpup);
+
+extern void
+tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
+
+#else /* !BROADCAST */
+
+static inline int tick_check_broadcast_device(struct clock_event_device *dev)
+{
+	return 0;
+}
+
+static inline int tick_is_broadcast_device(struct clock_event_device *dev)
+{
+	return 0;
+}
+static inline int tick_device_uses_broadcast(struct clock_event_device *dev,
+					     int cpu)
+{
+	return 0;
+}
+static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { }
+static inline void tick_broadcast_on_off(unsigned long reason, int *oncpu) { }
+static inline void tick_shutdown_broadcast(unsigned int *cpup) { }
+
+/*
+ * Set the periodic handler in non broadcast mode
+ */
+static inline void tick_set_periodic_handler(struct clock_event_device *dev,
+					     int broadcast)
+{
+	dev->event_handler = tick_handle_periodic;
+}
+#endif /* !BROADCAST */
+
+/*
+ * Check, if the device is functional or a dummy for broadcast
+ */
+static inline int tick_device_is_functional(struct clock_event_device *dev)
+{
+	return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
+}
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
new file mode 100644
index 00000000000..2e8b7ff863c
--- /dev/null
+++ b/kernel/time/tick-oneshot.c
@@ -0,0 +1,84 @@
+/*
+ * linux/kernel/time/tick-oneshot.c
+ *
+ * This file contains functions which manage high resolution tick
+ * related events.
+ *
+ * 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
+ *
+ * This code is licenced under the GPL version 2. For details see
+ * kernel-base/COPYING.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/irq.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+#include <linux/tick.h>
+
+#include "tick-internal.h"
+
+/**
+ * tick_program_event
+ */
+int tick_program_event(ktime_t expires, int force)
+{
+	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+	ktime_t now = ktime_get();
+
+	while (1) {
+		int ret = clockevents_program_event(dev, expires, now);
+
+		if (!ret || !force)
+			return ret;
+		now = ktime_get();
+		expires = ktime_add(now, ktime_set(0, dev->min_delta_ns));
+	}
+}
+
+/**
+ * tick_setup_oneshot - setup the event device for oneshot mode (hres or nohz)
+ */
+void tick_setup_oneshot(struct clock_event_device *newdev,
+			void (*handler)(struct clock_event_device *),
+			ktime_t next_event)
+{
+	newdev->event_handler = handler;
+	clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT);
+	clockevents_program_event(newdev, next_event, ktime_get());
+}
+
+/**
+ * tick_switch_to_oneshot - switch to oneshot mode
+ */
+int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
+{
+	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	struct clock_event_device *dev = td->evtdev;
+
+	if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) ||
+	    !tick_device_is_functional(dev))
+		return -EINVAL;
+
+	td->mode = TICKDEV_MODE_ONESHOT;
+	dev->event_handler = handler;
+	clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+	tick_broadcast_switch_to_oneshot();
+	return 0;
+}
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+/**
+ * tick_init_highres - switch to high resolution mode
+ *
+ * Called with interrupts disabled.
+ */
+int tick_init_highres(void)
+{
+	return tick_switch_to_oneshot(hrtimer_interrupt);
+}
+#endif
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
new file mode 100644
index 00000000000..95e41f7f850
--- /dev/null
+++ b/kernel/time/tick-sched.c
@@ -0,0 +1,563 @@
+/*
+ *  linux/kernel/time/tick-sched.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
+ *
+ *  No idle tick implementation for low and high resolution timers
+ *
+ *  Started by: Thomas Gleixner and Ingo Molnar
+ *
+ *  For licencing details see kernel-base/COPYING
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+#include <linux/tick.h>
+
+#include "tick-internal.h"
+
+/*
+ * Per cpu nohz control structure
+ */
+static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
+
+/*
+ * The time, when the last jiffy update happened. Protected by xtime_lock.
+ */
+static ktime_t last_jiffies_update;
+
+struct tick_sched *tick_get_tick_sched(int cpu)
+{
+	return &per_cpu(tick_cpu_sched, cpu);
+}
+
+/*
+ * Must be called with interrupts disabled !
+ */
+static void tick_do_update_jiffies64(ktime_t now)
+{
+	unsigned long ticks = 0;
+	ktime_t delta;
+
+	/* Reevalute with xtime_lock held */
+	write_seqlock(&xtime_lock);
+
+	delta = ktime_sub(now, last_jiffies_update);
+	if (delta.tv64 >= tick_period.tv64) {
+
+		delta = ktime_sub(delta, tick_period);
+		last_jiffies_update = ktime_add(last_jiffies_update,
+						tick_period);
+
+		/* Slow path for long timeouts */
+		if (unlikely(delta.tv64 >= tick_period.tv64)) {
+			s64 incr = ktime_to_ns(tick_period);
+
+			ticks = ktime_divns(delta, incr);
+
+			last_jiffies_update = ktime_add_ns(last_jiffies_update,
+							   incr * ticks);
+		}
+		do_timer(++ticks);
+	}
+	write_sequnlock(&xtime_lock);
+}
+
+/*
+ * Initialize and return retrieve the jiffies update.
+ */
+static ktime_t tick_init_jiffy_update(void)
+{
+	ktime_t period;
+
+	write_seqlock(&xtime_lock);
+	/* Did we start the jiffies update yet ? */
+	if (last_jiffies_update.tv64 == 0)
+		last_jiffies_update = tick_next_period;
+	period = last_jiffies_update;
+	write_sequnlock(&xtime_lock);
+	return period;
+}
+
+/*
+ * NOHZ - aka dynamic tick functionality
+ */
+#ifdef CONFIG_NO_HZ
+/*
+ * NO HZ enabled ?
+ */
+static int tick_nohz_enabled __read_mostly  = 1;
+
+/*
+ * Enable / Disable tickless mode
+ */
+static int __init setup_tick_nohz(char *str)
+{
+	if (!strcmp(str, "off"))
+		tick_nohz_enabled = 0;
+	else if (!strcmp(str, "on"))
+		tick_nohz_enabled = 1;
+	else
+		return 0;
+	return 1;
+}
+
+__setup("nohz=", setup_tick_nohz);
+
+/**
+ * tick_nohz_update_jiffies - update jiffies when idle was interrupted
+ *
+ * Called from interrupt entry when the CPU was idle
+ *
+ * In case the sched_tick was stopped on this CPU, we have to check if jiffies
+ * must be updated. Otherwise an interrupt handler could use a stale jiffy
+ * value. We do this unconditionally on any cpu, as we don't know whether the
+ * cpu, which has the update task assigned is in a long sleep.
+ */
+void tick_nohz_update_jiffies(void)
+{
+	int cpu = smp_processor_id();
+	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	unsigned long flags;
+	ktime_t now;
+
+	if (!ts->tick_stopped)
+		return;
+
+	cpu_clear(cpu, nohz_cpu_mask);
+	now = ktime_get();
+
+	local_irq_save(flags);
+	tick_do_update_jiffies64(now);
+	local_irq_restore(flags);
+}
+
+/**
+ * tick_nohz_stop_sched_tick - stop the idle tick from the idle task
+ *
+ * When the next event is more than a tick into the future, stop the idle tick
+ * Called either from the idle loop or from irq_exit() when an idle period was
+ * just interrupted by an interrupt which did not cause a reschedule.
+ */
+void tick_nohz_stop_sched_tick(void)
+{
+	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
+	struct tick_sched *ts;
+	ktime_t last_update, expires, now, delta;
+	int cpu;
+
+	local_irq_save(flags);
+
+	cpu = smp_processor_id();
+	ts = &per_cpu(tick_cpu_sched, cpu);
+
+	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
+		goto end;
+
+	if (need_resched())
+		goto end;
+
+	cpu = smp_processor_id();
+	BUG_ON(local_softirq_pending());
+
+	now = ktime_get();
+	/*
+	 * When called from irq_exit we need to account the idle sleep time
+	 * correctly.
+	 */
+	if (ts->tick_stopped) {
+		delta = ktime_sub(now, ts->idle_entrytime);
+		ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+	}
+
+	ts->idle_entrytime = now;
+	ts->idle_calls++;
+
+	/* Read jiffies and the time when jiffies were updated last */
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		last_update = last_jiffies_update;
+		last_jiffies = jiffies;
+	} while (read_seqretry(&xtime_lock, seq));
+
+	/* Get the next timer wheel timer */
+	next_jiffies = get_next_timer_interrupt(last_jiffies);
+	delta_jiffies = next_jiffies - last_jiffies;
+
+	/*
+	 * Do not stop the tick, if we are only one off
+	 * or if the cpu is required for rcu
+	 */
+	if (!ts->tick_stopped && (delta_jiffies == 1 || rcu_needs_cpu(cpu)))
+		goto out;
+
+	/* Schedule the tick, if we are at least one jiffie off */
+	if ((long)delta_jiffies >= 1) {
+
+		if (rcu_needs_cpu(cpu))
+			delta_jiffies = 1;
+		else
+			cpu_set(cpu, nohz_cpu_mask);
+		/*
+		 * nohz_stop_sched_tick can be called several times before
+		 * the nohz_restart_sched_tick is called. This happens when
+		 * interrupts arrive which do not cause a reschedule. In the
+		 * first call we save the current tick time, so we can restart
+		 * the scheduler tick in nohz_restart_sched_tick.
+		 */
+		if (!ts->tick_stopped) {
+			ts->idle_tick = ts->sched_timer.expires;
+			ts->tick_stopped = 1;
+			ts->idle_jiffies = last_jiffies;
+		}
+		/*
+		 * calculate the expiry time for the next timer wheel
+		 * timer
+		 */
+		expires = ktime_add_ns(last_update, tick_period.tv64 *
+				       delta_jiffies);
+		ts->idle_expires = expires;
+		ts->idle_sleeps++;
+
+		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
+			hrtimer_start(&ts->sched_timer, expires,
+				      HRTIMER_MODE_ABS);
+			/* Check, if the timer was already in the past */
+			if (hrtimer_active(&ts->sched_timer))
+				goto out;
+		} else if(!tick_program_event(expires, 0))
+				goto out;
+		/*
+		 * We are past the event already. So we crossed a
+		 * jiffie boundary. Update jiffies and raise the
+		 * softirq.
+		 */
+		tick_do_update_jiffies64(ktime_get());
+		cpu_clear(cpu, nohz_cpu_mask);
+	}
+	raise_softirq_irqoff(TIMER_SOFTIRQ);
+out:
+	ts->next_jiffies = next_jiffies;
+	ts->last_jiffies = last_jiffies;
+end:
+	local_irq_restore(flags);
+}
+
+/**
+ * nohz_restart_sched_tick - restart the idle tick from the idle task
+ *
+ * Restart the idle tick when the CPU is woken up from idle
+ */
+void tick_nohz_restart_sched_tick(void)
+{
+	int cpu = smp_processor_id();
+	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	unsigned long ticks;
+	ktime_t now, delta;
+
+	if (!ts->tick_stopped)
+		return;
+
+	/* Update jiffies first */
+	now = ktime_get();
+
+	local_irq_disable();
+	tick_do_update_jiffies64(now);
+	cpu_clear(cpu, nohz_cpu_mask);
+
+	/* Account the idle time */
+	delta = ktime_sub(now, ts->idle_entrytime);
+	ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+
+	/*
+	 * We stopped the tick in idle. Update process times would miss the
+	 * time we slept as update_process_times does only a 1 tick
+	 * accounting. Enforce that this is accounted to idle !
+	 */
+	ticks = jiffies - ts->idle_jiffies;
+	/*
+	 * We might be one off. Do not randomly account a huge number of ticks!
+	 */
+	if (ticks && ticks < LONG_MAX) {
+		add_preempt_count(HARDIRQ_OFFSET);
+		account_system_time(current, HARDIRQ_OFFSET,
+				    jiffies_to_cputime(ticks));
+		sub_preempt_count(HARDIRQ_OFFSET);
+	}
+
+	/*
+	 * Cancel the scheduled timer and restore the tick
+	 */
+	ts->tick_stopped  = 0;
+	hrtimer_cancel(&ts->sched_timer);
+	ts->sched_timer.expires = ts->idle_tick;
+
+	while (1) {
+		/* Forward the time to expire in the future */
+		hrtimer_forward(&ts->sched_timer, now, tick_period);
+
+		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
+			hrtimer_start(&ts->sched_timer,
+				      ts->sched_timer.expires,
+				      HRTIMER_MODE_ABS);
+			/* Check, if the timer was already in the past */
+			if (hrtimer_active(&ts->sched_timer))
+				break;
+		} else {
+			if (!tick_program_event(ts->sched_timer.expires, 0))
+				break;
+		}
+		/* Update jiffies and reread time */
+		tick_do_update_jiffies64(now);
+		now = ktime_get();
+	}
+	local_irq_enable();
+}
+
+static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now)
+{
+	hrtimer_forward(&ts->sched_timer, now, tick_period);
+	return tick_program_event(ts->sched_timer.expires, 0);
+}
+
+/*
+ * The nohz low res interrupt handler
+ */
+static void tick_nohz_handler(struct clock_event_device *dev)
+{
+	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct pt_regs *regs = get_irq_regs();
+	ktime_t now = ktime_get();
+
+	dev->next_event.tv64 = KTIME_MAX;
+
+	/* Check, if the jiffies need an update */
+	tick_do_update_jiffies64(now);
+
+	/*
+	 * When we are idle and the tick is stopped, we have to touch
+	 * the watchdog as we might not schedule for a really long
+	 * time. This happens on complete idle SMP systems while
+	 * waiting on the login prompt. We also increment the "start
+	 * of idle" jiffy stamp so the idle accounting adjustment we
+	 * do when we go busy again does not account too much ticks.
+	 */
+	if (ts->tick_stopped) {
+		touch_softlockup_watchdog();
+		ts->idle_jiffies++;
+	}
+
+	update_process_times(user_mode(regs));
+	profile_tick(CPU_PROFILING);
+
+	/* Do not restart, when we are in the idle loop */
+	if (ts->tick_stopped)
+		return;
+
+	while (tick_nohz_reprogram(ts, now)) {
+		now = ktime_get();
+		tick_do_update_jiffies64(now);
+	}
+}
+
+/**
+ * tick_nohz_switch_to_nohz - switch to nohz mode
+ */
+static void tick_nohz_switch_to_nohz(void)
+{
+	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	ktime_t next;
+
+	if (!tick_nohz_enabled)
+		return;
+
+	local_irq_disable();
+	if (tick_switch_to_oneshot(tick_nohz_handler)) {
+		local_irq_enable();
+		return;
+	}
+
+	ts->nohz_mode = NOHZ_MODE_LOWRES;
+
+	/*
+	 * Recycle the hrtimer in ts, so we can share the
+	 * hrtimer_forward with the highres code.
+	 */
+	hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	/* Get the next period */
+	next = tick_init_jiffy_update();
+
+	for (;;) {
+		ts->sched_timer.expires = next;
+		if (!tick_program_event(next, 0))
+			break;
+		next = ktime_add(next, tick_period);
+	}
+	local_irq_enable();
+
+	printk(KERN_INFO "Switched to NOHz mode on CPU #%d\n",
+	       smp_processor_id());
+}
+
+#else
+
+static inline void tick_nohz_switch_to_nohz(void) { }
+
+#endif /* NO_HZ */
+
+/*
+ * High resolution timer specific code
+ */
+#ifdef CONFIG_HIGH_RES_TIMERS
+/*
+ * We rearm the timer until we get disabled by the idle code
+ * Called with interrupts disabled and timer->base->cpu_base->lock held.
+ */
+static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
+{
+	struct tick_sched *ts =
+		container_of(timer, struct tick_sched, sched_timer);
+	struct hrtimer_cpu_base *base = timer->base->cpu_base;
+	struct pt_regs *regs = get_irq_regs();
+	ktime_t now = ktime_get();
+
+	/* Check, if the jiffies need an update */
+	tick_do_update_jiffies64(now);
+
+	/*
+	 * Do not call, when we are not in irq context and have
+	 * no valid regs pointer
+	 */
+	if (regs) {
+		/*
+		 * When we are idle and the tick is stopped, we have to touch
+		 * the watchdog as we might not schedule for a really long
+		 * time. This happens on complete idle SMP systems while
+		 * waiting on the login prompt. We also increment the "start of
+		 * idle" jiffy stamp so the idle accounting adjustment we do
+		 * when we go busy again does not account too much ticks.
+		 */
+		if (ts->tick_stopped) {
+			touch_softlockup_watchdog();
+			ts->idle_jiffies++;
+		}
+		/*
+		 * update_process_times() might take tasklist_lock, hence
+		 * drop the base lock. sched-tick hrtimers are per-CPU and
+		 * never accessible by userspace APIs, so this is safe to do.
+		 */
+		spin_unlock(&base->lock);
+		update_process_times(user_mode(regs));
+		profile_tick(CPU_PROFILING);
+		spin_lock(&base->lock);
+	}
+
+	/* Do not restart, when we are in the idle loop */
+	if (ts->tick_stopped)
+		return HRTIMER_NORESTART;
+
+	hrtimer_forward(timer, now, tick_period);
+
+	return HRTIMER_RESTART;
+}
+
+/**
+ * tick_setup_sched_timer - setup the tick emulation timer
+ */
+void tick_setup_sched_timer(void)
+{
+	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	ktime_t now = ktime_get();
+
+	/*
+	 * Emulate tick processing via per-CPU hrtimers:
+	 */
+	hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	ts->sched_timer.function = tick_sched_timer;
+	ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+
+	/* Get the next period */
+	ts->sched_timer.expires = tick_init_jiffy_update();
+
+	for (;;) {
+		hrtimer_forward(&ts->sched_timer, now, tick_period);
+		hrtimer_start(&ts->sched_timer, ts->sched_timer.expires,
+			      HRTIMER_MODE_ABS);
+		/* Check, if the timer was already in the past */
+		if (hrtimer_active(&ts->sched_timer))
+			break;
+		now = ktime_get();
+	}
+
+#ifdef CONFIG_NO_HZ
+	if (tick_nohz_enabled)
+		ts->nohz_mode = NOHZ_MODE_HIGHRES;
+#endif
+}
+
+void tick_cancel_sched_timer(int cpu)
+{
+	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+	if (ts->sched_timer.base)
+		hrtimer_cancel(&ts->sched_timer);
+	ts->tick_stopped = 0;
+	ts->nohz_mode = NOHZ_MODE_INACTIVE;
+}
+#endif /* HIGH_RES_TIMERS */
+
+/**
+ * Async notification about clocksource changes
+ */
+void tick_clock_notify(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		set_bit(0, &per_cpu(tick_cpu_sched, cpu).check_clocks);
+}
+
+/*
+ * Async notification about clock event changes
+ */
+void tick_oneshot_notify(void)
+{
+	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+
+	set_bit(0, &ts->check_clocks);
+}
+
+/**
+ * Check, if a change happened, which makes oneshot possible.
+ *
+ * Called cyclic from the hrtimer softirq (driven by the timer
+ * softirq) allow_nohz signals, that we can switch into low-res nohz
+ * mode, because high resolution timers are disabled (either compile
+ * or runtime).
+ */
+int tick_check_oneshot_change(int allow_nohz)
+{
+	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+
+	if (!test_and_clear_bit(0, &ts->check_clocks))
+		return 0;
+
+	if (ts->nohz_mode != NOHZ_MODE_INACTIVE)
+		return 0;
+
+	if (!timekeeping_is_continuous() || !tick_is_oneshot_available())
+		return 0;
+
+	if (!allow_nohz)
+		return 1;
+
+	tick_nohz_switch_to_nohz();
+	return 0;
+}
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
new file mode 100644
index 00000000000..f82c635c3d5
--- /dev/null
+++ b/kernel/time/timer_list.c
@@ -0,0 +1,287 @@
+/*
+ * kernel/time/timer_list.c
+ *
+ * List pending timers
+ *
+ * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/proc_fs.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/kallsyms.h>
+#include <linux/tick.h>
+
+#include <asm/uaccess.h>
+
+typedef void (*print_fn_t)(struct seq_file *m, unsigned int *classes);
+
+DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
+
+/*
+ * This allows printing both to /proc/timer_list and
+ * to the console (on SysRq-Q):
+ */
+#define SEQ_printf(m, x...)			\
+ do {						\
+	if (m)					\
+		seq_printf(m, x);		\
+	else					\
+		printk(x);			\
+ } while (0)
+
+static void print_name_offset(struct seq_file *m, void *sym)
+{
+	unsigned long addr = (unsigned long)sym;
+	char namebuf[KSYM_NAME_LEN+1];
+	unsigned long size, offset;
+	const char *sym_name;
+	char *modname;
+
+	sym_name = kallsyms_lookup(addr, &size, &offset, &modname, namebuf);
+	if (sym_name)
+		SEQ_printf(m, "%s", sym_name);
+	else
+		SEQ_printf(m, "<%p>", sym);
+}
+
+static void
+print_timer(struct seq_file *m, struct hrtimer *timer, int idx, u64 now)
+{
+#ifdef CONFIG_TIMER_STATS
+	char tmp[TASK_COMM_LEN + 1];
+#endif
+	SEQ_printf(m, " #%d: ", idx);
+	print_name_offset(m, timer);
+	SEQ_printf(m, ", ");
+	print_name_offset(m, timer->function);
+	SEQ_printf(m, ", S:%02lx", timer->state);
+#ifdef CONFIG_TIMER_STATS
+	SEQ_printf(m, ", ");
+	print_name_offset(m, timer->start_site);
+	memcpy(tmp, timer->start_comm, TASK_COMM_LEN);
+	tmp[TASK_COMM_LEN] = 0;
+	SEQ_printf(m, ", %s/%d", tmp, timer->start_pid);
+#endif
+	SEQ_printf(m, "\n");
+	SEQ_printf(m, " # expires at %Ld nsecs [in %Ld nsecs]\n",
+		(unsigned long long)ktime_to_ns(timer->expires),
+		(unsigned long long)(ktime_to_ns(timer->expires) - now));
+}
+
+static void
+print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base,
+		    u64 now)
+{
+	struct hrtimer *timer, tmp;
+	unsigned long next = 0, i;
+	struct rb_node *curr;
+	unsigned long flags;
+
+next_one:
+	i = 0;
+	spin_lock_irqsave(&base->cpu_base->lock, flags);
+
+	curr = base->first;
+	/*
+	 * Crude but we have to do this O(N*N) thing, because
+	 * we have to unlock the base when printing:
+	 */
+	while (curr && i < next) {
+		curr = rb_next(curr);
+		i++;
+	}
+
+	if (curr) {
+
+		timer = rb_entry(curr, struct hrtimer, node);
+		tmp = *timer;
+		spin_unlock_irqrestore(&base->cpu_base->lock, flags);
+
+		print_timer(m, &tmp, i, now);
+		next++;
+		goto next_one;
+	}
+	spin_unlock_irqrestore(&base->cpu_base->lock, flags);
+}
+
+static void
+print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
+{
+	SEQ_printf(m, "  .index:      %d\n",
+			base->index);
+	SEQ_printf(m, "  .resolution: %Ld nsecs\n",
+			(unsigned long long)ktime_to_ns(base->resolution));
+	SEQ_printf(m,   "  .get_time:   ");
+	print_name_offset(m, base->get_time);
+	SEQ_printf(m,   "\n");
+#ifdef CONFIG_HIGH_RES_TIMERS
+	SEQ_printf(m, "  .offset:     %Ld nsecs\n",
+			ktime_to_ns(base->offset));
+#endif
+	SEQ_printf(m,   "active timers:\n");
+	print_active_timers(m, base, now);
+}
+
+static void print_cpu(struct seq_file *m, int cpu, u64 now)
+{
+	struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
+	int i;
+
+	SEQ_printf(m, "\ncpu: %d\n", cpu);
+	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
+		SEQ_printf(m, " clock %d:\n", i);
+		print_base(m, cpu_base->clock_base + i, now);
+	}
+#define P(x) \
+	SEQ_printf(m, "  .%-15s: %Ld\n", #x, (u64)(cpu_base->x))
+#define P_ns(x) \
+	SEQ_printf(m, "  .%-15s: %Ld nsecs\n", #x, \
+		(u64)(ktime_to_ns(cpu_base->x)))
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+	P_ns(expires_next);
+	P(hres_active);
+	P(nr_events);
+#endif
+#undef P
+#undef P_ns
+
+#ifdef CONFIG_TICK_ONESHOT
+# define P(x) \
+	SEQ_printf(m, "  .%-15s: %Ld\n", #x, (u64)(ts->x))
+# define P_ns(x) \
+	SEQ_printf(m, "  .%-15s: %Ld nsecs\n", #x, \
+		(u64)(ktime_to_ns(ts->x)))
+	{
+		struct tick_sched *ts = tick_get_tick_sched(cpu);
+		P(nohz_mode);
+		P_ns(idle_tick);
+		P(tick_stopped);
+		P(idle_jiffies);
+		P(idle_calls);
+		P(idle_sleeps);
+		P_ns(idle_entrytime);
+		P_ns(idle_sleeptime);
+		P(last_jiffies);
+		P(next_jiffies);
+		P_ns(idle_expires);
+		SEQ_printf(m, "jiffies: %Ld\n", (u64)jiffies);
+	}
+#endif
+
+#undef P
+#undef P_ns
+}
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+static void
+print_tickdevice(struct seq_file *m, struct tick_device *td)
+{
+	struct clock_event_device *dev = td->evtdev;
+
+	SEQ_printf(m, "\nTick Device: mode:     %d\n", td->mode);
+
+	SEQ_printf(m, "Clock Event Device: ");
+	if (!dev) {
+		SEQ_printf(m, "<NULL>\n");
+		return;
+	}
+	SEQ_printf(m, "%s\n", dev->name);
+	SEQ_printf(m, " max_delta_ns:   %ld\n", dev->max_delta_ns);
+	SEQ_printf(m, " min_delta_ns:   %ld\n", dev->min_delta_ns);
+	SEQ_printf(m, " mult:           %ld\n", dev->mult);
+	SEQ_printf(m, " shift:          %d\n", dev->shift);
+	SEQ_printf(m, " mode:           %d\n", dev->mode);
+	SEQ_printf(m, " next_event:     %Ld nsecs\n",
+		   (unsigned long long) ktime_to_ns(dev->next_event));
+
+	SEQ_printf(m, " set_next_event: ");
+	print_name_offset(m, dev->set_next_event);
+	SEQ_printf(m, "\n");
+
+	SEQ_printf(m, " set_mode:       ");
+	print_name_offset(m, dev->set_mode);
+	SEQ_printf(m, "\n");
+
+	SEQ_printf(m, " event_handler:  ");
+	print_name_offset(m, dev->event_handler);
+	SEQ_printf(m, "\n");
+}
+
+static void timer_list_show_tickdevices(struct seq_file *m)
+{
+	int cpu;
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+	print_tickdevice(m, tick_get_broadcast_device());
+	SEQ_printf(m, "tick_broadcast_mask: %08lx\n",
+		   tick_get_broadcast_mask()->bits[0]);
+#ifdef CONFIG_TICK_ONESHOT
+	SEQ_printf(m, "tick_broadcast_oneshot_mask: %08lx\n",
+		   tick_get_broadcast_oneshot_mask()->bits[0]);
+#endif
+	SEQ_printf(m, "\n");
+#endif
+	for_each_online_cpu(cpu)
+		   print_tickdevice(m, tick_get_device(cpu));
+	SEQ_printf(m, "\n");
+}
+#else
+static void timer_list_show_tickdevices(struct seq_file *m) { }
+#endif
+
+static int timer_list_show(struct seq_file *m, void *v)
+{
+	u64 now = ktime_to_ns(ktime_get());
+	int cpu;
+
+	SEQ_printf(m, "Timer List Version: v0.3\n");
+	SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
+	SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
+
+	for_each_online_cpu(cpu)
+		print_cpu(m, cpu, now);
+
+	SEQ_printf(m, "\n");
+	timer_list_show_tickdevices(m);
+
+	return 0;
+}
+
+void sysrq_timer_list_show(void)
+{
+	timer_list_show(NULL, NULL);
+}
+
+static int timer_list_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, timer_list_show, NULL);
+}
+
+static struct file_operations timer_list_fops = {
+	.open		= timer_list_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int __init init_timer_list_procfs(void)
+{
+	struct proc_dir_entry *pe;
+
+	pe = create_proc_entry("timer_list", 0644, NULL);
+	if (!pe)
+		return -ENOMEM;
+
+	pe->proc_fops = &timer_list_fops;
+
+	return 0;
+}
+__initcall(init_timer_list_procfs);
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
new file mode 100644
index 00000000000..1bc4882e28e
--- /dev/null
+++ b/kernel/time/timer_stats.c
@@ -0,0 +1,411 @@
+/*
+ * kernel/time/timer_stats.c
+ *
+ * Collect timer usage statistics.
+ *
+ * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * timer_stats is based on timer_top, a similar functionality which was part of
+ * Con Kolivas dyntick patch set. It was developed by Daniel Petrini at the
+ * Instituto Nokia de Tecnologia - INdT - Manaus. timer_top's design was based
+ * on dynamic allocation of the statistics entries and linear search based
+ * lookup combined with a global lock, rather than the static array, hash
+ * and per-CPU locking which is used by timer_stats. It was written for the
+ * pre hrtimer kernel code and therefore did not take hrtimers into account.
+ * Nevertheless it provided the base for the timer_stats implementation and
+ * was a helpful source of inspiration. Kudos to Daniel and the Nokia folks
+ * for this effort.
+ *
+ * timer_top.c is
+ *	Copyright (C) 2005 Instituto Nokia de Tecnologia - INdT - Manaus
+ *	Written by Daniel Petrini <d.pensator@gmail.com>
+ *	timer_top.c was released under the GNU General Public License version 2
+ *
+ * We export the addresses and counting of timer functions being called,
+ * the pid and cmdline from the owner process if applicable.
+ *
+ * Start/stop data collection:
+ * # echo 1[0] >/proc/timer_stats
+ *
+ * Display the information collected so far:
+ * # cat /proc/timer_stats
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/proc_fs.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/kallsyms.h>
+
+#include <asm/uaccess.h>
+
+/*
+ * This is our basic unit of interest: a timer expiry event identified
+ * by the timer, its start/expire functions and the PID of the task that
+ * started the timer. We count the number of times an event happens:
+ */
+struct entry {
+	/*
+	 * Hash list:
+	 */
+	struct entry		*next;
+
+	/*
+	 * Hash keys:
+	 */
+	void			*timer;
+	void			*start_func;
+	void			*expire_func;
+	pid_t			pid;
+
+	/*
+	 * Number of timeout events:
+	 */
+	unsigned long		count;
+
+	/*
+	 * We save the command-line string to preserve
+	 * this information past task exit:
+	 */
+	char			comm[TASK_COMM_LEN + 1];
+
+} ____cacheline_aligned_in_smp;
+
+/*
+ * Spinlock protecting the tables - not taken during lookup:
+ */
+static DEFINE_SPINLOCK(table_lock);
+
+/*
+ * Per-CPU lookup locks for fast hash lookup:
+ */
+static DEFINE_PER_CPU(spinlock_t, lookup_lock);
+
+/*
+ * Mutex to serialize state changes with show-stats activities:
+ */
+static DEFINE_MUTEX(show_mutex);
+
+/*
+ * Collection status, active/inactive:
+ */
+static int __read_mostly active;
+
+/*
+ * Beginning/end timestamps of measurement:
+ */
+static ktime_t time_start, time_stop;
+
+/*
+ * tstat entry structs only get allocated while collection is
+ * active and never freed during that time - this simplifies
+ * things quite a bit.
+ *
+ * They get freed when a new collection period is started.
+ */
+#define MAX_ENTRIES_BITS	10
+#define MAX_ENTRIES		(1UL << MAX_ENTRIES_BITS)
+
+static unsigned long nr_entries;
+static struct entry entries[MAX_ENTRIES];
+
+static atomic_t overflow_count;
+
+static void reset_entries(void)
+{
+	nr_entries = 0;
+	memset(entries, 0, sizeof(entries));
+	atomic_set(&overflow_count, 0);
+}
+
+static struct entry *alloc_entry(void)
+{
+	if (nr_entries >= MAX_ENTRIES)
+		return NULL;
+
+	return entries + nr_entries++;
+}
+
+/*
+ * The entries are in a hash-table, for fast lookup:
+ */
+#define TSTAT_HASH_BITS		(MAX_ENTRIES_BITS - 1)
+#define TSTAT_HASH_SIZE		(1UL << TSTAT_HASH_BITS)
+#define TSTAT_HASH_MASK		(TSTAT_HASH_SIZE - 1)
+
+#define __tstat_hashfn(entry)						\
+	(((unsigned long)(entry)->timer       ^				\
+	  (unsigned long)(entry)->start_func  ^				\
+	  (unsigned long)(entry)->expire_func ^				\
+	  (unsigned long)(entry)->pid		) & TSTAT_HASH_MASK)
+
+#define tstat_hashentry(entry)	(tstat_hash_table + __tstat_hashfn(entry))
+
+static struct entry *tstat_hash_table[TSTAT_HASH_SIZE] __read_mostly;
+
+static int match_entries(struct entry *entry1, struct entry *entry2)
+{
+	return entry1->timer       == entry2->timer	  &&
+	       entry1->start_func  == entry2->start_func  &&
+	       entry1->expire_func == entry2->expire_func &&
+	       entry1->pid	   == entry2->pid;
+}
+
+/*
+ * Look up whether an entry matching this item is present
+ * in the hash already. Must be called with irqs off and the
+ * lookup lock held:
+ */
+static struct entry *tstat_lookup(struct entry *entry, char *comm)
+{
+	struct entry **head, *curr, *prev;
+
+	head = tstat_hashentry(entry);
+	curr = *head;
+
+	/*
+	 * The fastpath is when the entry is already hashed,
+	 * we do this with the lookup lock held, but with the
+	 * table lock not held:
+	 */
+	while (curr) {
+		if (match_entries(curr, entry))
+			return curr;
+
+		curr = curr->next;
+	}
+	/*
+	 * Slowpath: allocate, set up and link a new hash entry:
+	 */
+	prev = NULL;
+	curr = *head;
+
+	spin_lock(&table_lock);
+	/*
+	 * Make sure we have not raced with another CPU:
+	 */
+	while (curr) {
+		if (match_entries(curr, entry))
+			goto out_unlock;
+
+		prev = curr;
+		curr = curr->next;
+	}
+
+	curr = alloc_entry();
+	if (curr) {
+		*curr = *entry;
+		curr->count = 0;
+		memcpy(curr->comm, comm, TASK_COMM_LEN);
+		if (prev)
+			prev->next = curr;
+		else
+			*head = curr;
+		curr->next = NULL;
+	}
+ out_unlock:
+	spin_unlock(&table_lock);
+
+	return curr;
+}
+
+/**
+ * timer_stats_update_stats - Update the statistics for a timer.
+ * @timer:	pointer to either a timer_list or a hrtimer
+ * @pid:	the pid of the task which set up the timer
+ * @startf:	pointer to the function which did the timer setup
+ * @timerf:	pointer to the timer callback function of the timer
+ * @comm:	name of the process which set up the timer
+ *
+ * When the timer is already registered, then the event counter is
+ * incremented. Otherwise the timer is registered in a free slot.
+ */
+void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
+			      void *timerf, char * comm)
+{
+	/*
+	 * It doesnt matter which lock we take:
+	 */
+	spinlock_t *lock = &per_cpu(lookup_lock, raw_smp_processor_id());
+	struct entry *entry, input;
+	unsigned long flags;
+
+	input.timer = timer;
+	input.start_func = startf;
+	input.expire_func = timerf;
+	input.pid = pid;
+
+	spin_lock_irqsave(lock, flags);
+	if (!active)
+		goto out_unlock;
+
+	entry = tstat_lookup(&input, comm);
+	if (likely(entry))
+		entry->count++;
+	else
+		atomic_inc(&overflow_count);
+
+ out_unlock:
+	spin_unlock_irqrestore(lock, flags);
+}
+
+static void print_name_offset(struct seq_file *m, unsigned long addr)
+{
+	char namebuf[KSYM_NAME_LEN+1];
+	unsigned long size, offset;
+	const char *sym_name;
+	char *modname;
+
+	sym_name = kallsyms_lookup(addr, &size, &offset, &modname, namebuf);
+	if (sym_name)
+		seq_printf(m, "%s", sym_name);
+	else
+		seq_printf(m, "<%p>", (void *)addr);
+}
+
+static int tstats_show(struct seq_file *m, void *v)
+{
+	struct timespec period;
+	struct entry *entry;
+	unsigned long ms;
+	long events = 0;
+	ktime_t time;
+	int i;
+
+	mutex_lock(&show_mutex);
+	/*
+	 * If still active then calculate up to now:
+	 */
+	if (active)
+		time_stop = ktime_get();
+
+	time = ktime_sub(time_stop, time_start);
+
+	period = ktime_to_timespec(time);
+	ms = period.tv_nsec / 1000000;
+
+	seq_puts(m, "Timer Stats Version: v0.1\n");
+	seq_printf(m, "Sample period: %ld.%03ld s\n", period.tv_sec, ms);
+	if (atomic_read(&overflow_count))
+		seq_printf(m, "Overflow: %d entries\n",
+			atomic_read(&overflow_count));
+
+	for (i = 0; i < nr_entries; i++) {
+		entry = entries + i;
+		seq_printf(m, "%4lu, %5d %-16s ",
+				entry->count, entry->pid, entry->comm);
+
+		print_name_offset(m, (unsigned long)entry->start_func);
+		seq_puts(m, " (");
+		print_name_offset(m, (unsigned long)entry->expire_func);
+		seq_puts(m, ")\n");
+
+		events += entry->count;
+	}
+
+	ms += period.tv_sec * 1000;
+	if (!ms)
+		ms = 1;
+
+	if (events && period.tv_sec)
+		seq_printf(m, "%ld total events, %ld.%ld events/sec\n", events,
+			   events / period.tv_sec, events * 1000 / ms);
+	else
+		seq_printf(m, "%ld total events\n", events);
+
+	mutex_unlock(&show_mutex);
+
+	return 0;
+}
+
+/*
+ * After a state change, make sure all concurrent lookup/update
+ * activities have stopped:
+ */
+static void sync_access(void)
+{
+	unsigned long flags;
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		spin_lock_irqsave(&per_cpu(lookup_lock, cpu), flags);
+		/* nothing */
+		spin_unlock_irqrestore(&per_cpu(lookup_lock, cpu), flags);
+	}
+}
+
+static ssize_t tstats_write(struct file *file, const char __user *buf,
+			    size_t count, loff_t *offs)
+{
+	char ctl[2];
+
+	if (count != 2 || *offs)
+		return -EINVAL;
+
+	if (copy_from_user(ctl, buf, count))
+		return -EFAULT;
+
+	mutex_lock(&show_mutex);
+	switch (ctl[0]) {
+	case '0':
+		if (active) {
+			active = 0;
+			time_stop = ktime_get();
+			sync_access();
+		}
+		break;
+	case '1':
+		if (!active) {
+			reset_entries();
+			time_start = ktime_get();
+			active = 1;
+		}
+		break;
+	default:
+		count = -EINVAL;
+	}
+	mutex_unlock(&show_mutex);
+
+	return count;
+}
+
+static int tstats_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, tstats_show, NULL);
+}
+
+static struct file_operations tstats_fops = {
+	.open		= tstats_open,
+	.read		= seq_read,
+	.write		= tstats_write,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+void __init init_timer_stats(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		spin_lock_init(&per_cpu(lookup_lock, cpu));
+}
+
+static int __init init_tstats_procfs(void)
+{
+	struct proc_dir_entry *pe;
+
+	pe = create_proc_entry("timer_stats", 0644, NULL);
+	if (!pe)
+		return -ENOMEM;
+
+	pe->proc_fops = &tstats_fops;
+
+	return 0;
+}
+__initcall(init_tstats_procfs);