1 files changed, 682 insertions, 142 deletions

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index f44e499e8fca..476cb0c0b4a4 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1,8 +1,9 @@
 /*
  *  linux/kernel/hrtimer.c
  *
- *  Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de>
- *  Copyright(C) 2005, Red Hat, Inc., Ingo Molnar
+ *  Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
+ *  Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ *  Copyright(C) 2006-2007  Timesys Corp., Thomas Gleixner
  *
  *  High-resolution kernel timers
  *
@@ -31,12 +32,17 @@
  */
 
 #include <linux/cpu.h>
+#include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/hrtimer.h>
 #include <linux/notifier.h>
 #include <linux/syscalls.h>
+#include <linux/kallsyms.h>
 #include <linux/interrupt.h>
+#include <linux/tick.h>
+#include <linux/seq_file.h>
+#include <linux/err.h>
 
 #include <asm/uaccess.h>
 
@@ -45,7 +51,7 @@
  *
  * returns the time in ktime_t format
  */
-static ktime_t ktime_get(void)
+ktime_t ktime_get(void)
 {
 	struct timespec now;
 
@@ -59,7 +65,7 @@ static ktime_t ktime_get(void)
  *
  * returns the time in ktime_t format
  */
-static ktime_t ktime_get_real(void)
+ktime_t ktime_get_real(void)
 {
 	struct timespec now;
 
@@ -79,21 +85,22 @@ EXPORT_SYMBOL_GPL(ktime_get_real);
  * This ensures that we capture erroneous accesses to these clock ids
  * rather than moving them into the range of valid clock id's.
  */
-
-#define MAX_HRTIMER_BASES 2
-
-static DEFINE_PER_CPU(struct hrtimer_base, hrtimer_bases[MAX_HRTIMER_BASES]) =
+DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
+
+	.clock_base =
 	{
-		.index = CLOCK_REALTIME,
-		.get_time = &ktime_get_real,
-		.resolution = KTIME_REALTIME_RES,
-	},
-	{
-		.index = CLOCK_MONOTONIC,
-		.get_time = &ktime_get,
-		.resolution = KTIME_MONOTONIC_RES,
-	},
+		{
+			.index = CLOCK_REALTIME,
+			.get_time = &ktime_get_real,
+			.resolution = KTIME_LOW_RES,
+		},
+		{
+			.index = CLOCK_MONOTONIC,
+			.get_time = &ktime_get,
+			.resolution = KTIME_LOW_RES,
+		},
+	}
 };
 
 /**
@@ -125,20 +132,35 @@ EXPORT_SYMBOL_GPL(ktime_get_ts);
  * Get the coarse grained time at the softirq based on xtime and
  * wall_to_monotonic.
  */
-static void hrtimer_get_softirq_time(struct hrtimer_base *base)
+static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 {
 	ktime_t xtim, tomono;
+	struct timespec xts;
 	unsigned long seq;
 
 	do {
 		seq = read_seqbegin(&xtime_lock);
-		xtim = timespec_to_ktime(xtime);
-		tomono = timespec_to_ktime(wall_to_monotonic);
-
+#ifdef CONFIG_NO_HZ
+		getnstimeofday(&xts);
+#else
+		xts = xtime;
+#endif
 	} while (read_seqretry(&xtime_lock, seq));
 
-	base[CLOCK_REALTIME].softirq_time = xtim;
-	base[CLOCK_MONOTONIC].softirq_time = ktime_add(xtim, tomono);
+	xtim = timespec_to_ktime(xts);
+	tomono = timespec_to_ktime(wall_to_monotonic);
+	base->clock_base[CLOCK_REALTIME].softirq_time = xtim;
+	base->clock_base[CLOCK_MONOTONIC].softirq_time =
+		ktime_add(xtim, tomono);
+}
+
+/*
+ * Helper function to check, whether the timer is running the callback
+ * function
+ */
+static inline int hrtimer_callback_running(struct hrtimer *timer)
+{
+	return timer->state & HRTIMER_STATE_CALLBACK;
 }
 
 /*
@@ -147,8 +169,6 @@ static void hrtimer_get_softirq_time(struct hrtimer_base *base)
  */
 #ifdef CONFIG_SMP
 
-#define set_curr_timer(b, t)		do { (b)->curr_timer = (t); } while (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
@@ -161,19 +181,20 @@ static void hrtimer_get_softirq_time(struct hrtimer_base *base)
  * possible to set timer->base = NULL and drop the lock: the timer remains
  * locked.
  */
-static struct hrtimer_base *lock_hrtimer_base(const struct hrtimer *timer,
-					      unsigned long *flags)
+static
+struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
+					     unsigned long *flags)
 {
-	struct hrtimer_base *base;
+	struct hrtimer_clock_base *base;
 
 	for (;;) {
 		base = timer->base;
 		if (likely(base != NULL)) {
-			spin_lock_irqsave(&base->lock, *flags);
+			spin_lock_irqsave(&base->cpu_base->lock, *flags);
 			if (likely(base == timer->base))
 				return base;
 			/* The timer has migrated to another CPU: */
-			spin_unlock_irqrestore(&base->lock, *flags);
+			spin_unlock_irqrestore(&base->cpu_base->lock, *flags);
 		}
 		cpu_relax();
 	}
@@ -182,12 +203,14 @@ static struct hrtimer_base *lock_hrtimer_base(const struct hrtimer *timer,
 /*
  * Switch the timer base to the current CPU when possible.
  */
-static inline struct hrtimer_base *
-switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_base *base)
+static inline struct hrtimer_clock_base *
+switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base)
 {
-	struct hrtimer_base *new_base;
+	struct hrtimer_clock_base *new_base;
+	struct hrtimer_cpu_base *new_cpu_base;
 
-	new_base = &__get_cpu_var(hrtimer_bases)[base->index];
+	new_cpu_base = &__get_cpu_var(hrtimer_bases);
+	new_base = &new_cpu_base->clock_base[base->index];
 
 	if (base != new_base) {
 		/*
@@ -199,13 +222,13 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_base *base)
 		 * completed. There is no conflict as we hold the lock until
 		 * the timer is enqueued.
 		 */
-		if (unlikely(base->curr_timer == timer))
+		if (unlikely(hrtimer_callback_running(timer)))
 			return base;
 
 		/* See the comment in lock_timer_base() */
 		timer->base = NULL;
-		spin_unlock(&base->lock);
-		spin_lock(&new_base->lock);
+		spin_unlock(&base->cpu_base->lock);
+		spin_lock(&new_base->cpu_base->lock);
 		timer->base = new_base;
 	}
 	return new_base;
@@ -213,19 +236,17 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_base *base)
 
 #else /* CONFIG_SMP */
 
-#define set_curr_timer(b, t)		do { } while (0)
-
-static inline struct hrtimer_base *
+static inline struct hrtimer_clock_base *
 lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
 {
-	struct hrtimer_base *base = timer->base;
+	struct hrtimer_clock_base *base = timer->base;
 
-	spin_lock_irqsave(&base->lock, *flags);
+	spin_lock_irqsave(&base->cpu_base->lock, *flags);
 
 	return base;
 }
 
-#define switch_hrtimer_base(t, b)	(b)
+# define switch_hrtimer_base(t, b)	(b)
 
 #endif	/* !CONFIG_SMP */
 
@@ -256,15 +277,12 @@ ktime_t ktime_add_ns(const ktime_t kt, u64 nsec)
 
 	return ktime_add(kt, tmp);
 }
-
-#else /* CONFIG_KTIME_SCALAR */
-
 # endif /* !CONFIG_KTIME_SCALAR */
 
 /*
  * Divide a ktime value by a nanosecond value
  */
-static unsigned long ktime_divns(const ktime_t kt, s64 div)
+unsigned long ktime_divns(const ktime_t kt, s64 div)
 {
 	u64 dclc, inc, dns;
 	int sft = 0;
@@ -281,18 +299,311 @@ static unsigned long ktime_divns(const ktime_t kt, s64 div)
 
 	return (unsigned long) dclc;
 }
-
-#else /* BITS_PER_LONG < 64 */
-# define ktime_divns(kt, div)		(unsigned long)((kt).tv64 / (div))
 #endif /* BITS_PER_LONG >= 64 */
 
+/* High resolution timer related functions */
+#ifdef CONFIG_HIGH_RES_TIMERS
+
+/*
+ * High resolution timer enabled ?
+ */
+static int hrtimer_hres_enabled __read_mostly  = 1;
+
+/*
+ * Enable / Disable high resolution mode
+ */
+static int __init setup_hrtimer_hres(char *str)
+{
+	if (!strcmp(str, "off"))
+		hrtimer_hres_enabled = 0;
+	else if (!strcmp(str, "on"))
+		hrtimer_hres_enabled = 1;
+	else
+		return 0;
+	return 1;
+}
+
+__setup("highres=", setup_hrtimer_hres);
+
+/*
+ * hrtimer_high_res_enabled - query, if the highres mode is enabled
+ */
+static inline int hrtimer_is_hres_enabled(void)
+{
+	return hrtimer_hres_enabled;
+}
+
+/*
+ * Is the high resolution mode active ?
+ */
+static inline int hrtimer_hres_active(void)
+{
+	return __get_cpu_var(hrtimer_bases).hres_active;
+}
+
+/*
+ * Reprogram the event source with checking both queues for the
+ * next event
+ * Called with interrupts disabled and base->lock held
+ */
+static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
+{
+	int i;
+	struct hrtimer_clock_base *base = cpu_base->clock_base;
+	ktime_t expires;
+
+	cpu_base->expires_next.tv64 = KTIME_MAX;
+
+	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
+		struct hrtimer *timer;
+
+		if (!base->first)
+			continue;
+		timer = rb_entry(base->first, struct hrtimer, node);
+		expires = ktime_sub(timer->expires, base->offset);
+		if (expires.tv64 < cpu_base->expires_next.tv64)
+			cpu_base->expires_next = expires;
+	}
+
+	if (cpu_base->expires_next.tv64 != KTIME_MAX)
+		tick_program_event(cpu_base->expires_next, 1);
+}
+
+/*
+ * Shared reprogramming for clock_realtime and clock_monotonic
+ *
+ * When a timer is enqueued and expires earlier than the already enqueued
+ * timers, we have to check, whether it expires earlier than the timer for
+ * which the clock event device was armed.
+ *
+ * Called with interrupts disabled and base->cpu_base.lock held
+ */
+static int hrtimer_reprogram(struct hrtimer *timer,
+			     struct hrtimer_clock_base *base)
+{
+	ktime_t *expires_next = &__get_cpu_var(hrtimer_bases).expires_next;
+	ktime_t expires = ktime_sub(timer->expires, base->offset);
+	int res;
+
+	/*
+	 * 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_interupt context. The
+	 * reprogramming is handled either by the softirq, which called the
+	 * callback or at the end of the hrtimer_interrupt.
+	 */
+	if (hrtimer_callback_running(timer))
+		return 0;
+
+	if (expires.tv64 >= expires_next->tv64)
+		return 0;
+
+	/*
+	 * Clockevents returns -ETIME, when the event was in the past.
+	 */
+	res = tick_program_event(expires, 0);
+	if (!IS_ERR_VALUE(res))
+		*expires_next = expires;
+	return res;
+}
+
+
+/*
+ * Retrigger next event is called after clock was set
+ *
+ * Called with interrupts disabled via on_each_cpu()
+ */
+static void retrigger_next_event(void *arg)
+{
+	struct hrtimer_cpu_base *base;
+	struct timespec realtime_offset;
+	unsigned long seq;
+
+	if (!hrtimer_hres_active())
+		return;
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		set_normalized_timespec(&realtime_offset,
+					-wall_to_monotonic.tv_sec,
+					-wall_to_monotonic.tv_nsec);
+	} while (read_seqretry(&xtime_lock, seq));
+
+	base = &__get_cpu_var(hrtimer_bases);
+
+	/* Adjust CLOCK_REALTIME offset */
+	spin_lock(&base->lock);
+	base->clock_base[CLOCK_REALTIME].offset =
+		timespec_to_ktime(realtime_offset);
+
+	hrtimer_force_reprogram(base);
+	spin_unlock(&base->lock);
+}
+
+/*
+ * Clock realtime was set
+ *
+ * Change the offset of the realtime clock vs. the monotonic
+ * clock.
+ *
+ * We might have to reprogram the high resolution timer interrupt. On
+ * SMP we call the architecture specific code to retrigger _all_ high
+ * resolution timer interrupts. On UP we just disable interrupts and
+ * call the high resolution interrupt code.
+ */
+void clock_was_set(void)
+{
+	/* Retrigger the CPU local events everywhere */
+	on_each_cpu(retrigger_next_event, NULL, 0, 1);
+}
+
+/*
+ * Check, whether the timer is on the callback pending list
+ */
+static inline int hrtimer_cb_pending(const struct hrtimer *timer)
+{
+	return timer->state & HRTIMER_STATE_PENDING;
+}
+
+/*
+ * Remove a timer from the callback pending list
+ */
+static inline void hrtimer_remove_cb_pending(struct hrtimer *timer)
+{
+	list_del_init(&timer->cb_entry);
+}
+
+/*
+ * Initialize the high resolution related parts of cpu_base
+ */
+static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
+{
+	base->expires_next.tv64 = KTIME_MAX;
+	base->hres_active = 0;
+	INIT_LIST_HEAD(&base->cb_pending);
+}
+
+/*
+ * Initialize the high resolution related parts of a hrtimer
+ */
+static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
+{
+	INIT_LIST_HEAD(&timer->cb_entry);
+}
+
+/*
+ * When High resolution timers are active, try to reprogram. Note, that in case
+ * the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry
+ * check happens. The timer gets enqueued into the rbtree. The reprogramming
+ * and expiry check is done in the hrtimer_interrupt or in the softirq.
+ */
+static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
+					    struct hrtimer_clock_base *base)
+{
+	if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
+
+		/* Timer is expired, act upon the callback mode */
+		switch(timer->cb_mode) {
+		case HRTIMER_CB_IRQSAFE_NO_RESTART:
+			/*
+			 * We can call the callback from here. No restart
+			 * happens, so no danger of recursion
+			 */
+			BUG_ON(timer->function(timer) != HRTIMER_NORESTART);
+			return 1;
+		case HRTIMER_CB_IRQSAFE_NO_SOFTIRQ:
+			/*
+			 * This is solely for the sched tick emulation with
+			 * dynamic tick support to ensure that we do not
+			 * restart the tick right on the edge and end up with
+			 * the tick timer in the softirq ! The calling site
+			 * takes care of this.
+			 */
+			return 1;
+		case HRTIMER_CB_IRQSAFE:
+		case HRTIMER_CB_SOFTIRQ:
+			/*
+			 * Move everything else into the softirq pending list !
+			 */
+			list_add_tail(&timer->cb_entry,
+				      &base->cpu_base->cb_pending);
+			timer->state = HRTIMER_STATE_PENDING;
+			raise_softirq(HRTIMER_SOFTIRQ);
+			return 1;
+		default:
+			BUG();
+		}
+	}
+	return 0;
+}
+
+/*
+ * Switch to high resolution mode
+ */
+static void hrtimer_switch_to_hres(void)
+{
+	struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
+	unsigned long flags;
+
+	if (base->hres_active)
+		return;
+
+	local_irq_save(flags);
+
+	if (tick_init_highres()) {
+		local_irq_restore(flags);
+		return;
+	}
+	base->hres_active = 1;
+	base->clock_base[CLOCK_REALTIME].resolution = KTIME_HIGH_RES;
+	base->clock_base[CLOCK_MONOTONIC].resolution = KTIME_HIGH_RES;
+
+	tick_setup_sched_timer();
+
+	/* "Retrigger" the interrupt to get things going */
+	retrigger_next_event(NULL);
+	local_irq_restore(flags);
+	printk(KERN_INFO "Switched to high resolution mode on CPU %d\n",
+	       smp_processor_id());
+}
+
+#else
+
+static inline int hrtimer_hres_active(void) { return 0; }
+static inline int hrtimer_is_hres_enabled(void) { return 0; }
+static inline void hrtimer_switch_to_hres(void) { }
+static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base) { }
+static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
+					    struct hrtimer_clock_base *base)
+{
+	return 0;
+}
+static inline int hrtimer_cb_pending(struct hrtimer *timer) { return 0; }
+static inline void hrtimer_remove_cb_pending(struct hrtimer *timer) { }
+static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
+static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { }
+
+#endif /* CONFIG_HIGH_RES_TIMERS */
+
+#ifdef CONFIG_TIMER_STATS
+void __timer_stats_hrtimer_set_start_info(struct hrtimer *timer, void *addr)
+{
+	if (timer->start_site)
+		return;
+
+	timer->start_site = addr;
+	memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
+	timer->start_pid = current->pid;
+}
+#endif
+
 /*
  * Counterpart to lock_timer_base above:
  */
 static inline
 void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
 {
-	spin_unlock_irqrestore(&timer->base->lock, *flags);
+	spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags);
 }
 
 /**
@@ -342,7 +653,8 @@ hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
  * The timer is inserted in expiry order. Insertion into the
  * red black tree is O(log(n)). Must hold the base lock.
  */
-static void enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_base *base)
+static void enqueue_hrtimer(struct hrtimer *timer,
+			    struct hrtimer_clock_base *base, int reprogram)
 {
 	struct rb_node **link = &base->active.rb_node;
 	struct rb_node *parent = NULL;
@@ -368,39 +680,85 @@ static void enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_base *base)
 	 * Insert the timer to the rbtree and check whether it
 	 * replaces the first pending timer
 	 */
-	rb_link_node(&timer->node, parent, link);
-	rb_insert_color(&timer->node, &base->active);
-
 	if (!base->first || timer->expires.tv64 <
-	    rb_entry(base->first, struct hrtimer, node)->expires.tv64)
+	    rb_entry(base->first, struct hrtimer, node)->expires.tv64) {
+		/*
+		 * Reprogram the clock event device. When the timer is already
+		 * expired hrtimer_enqueue_reprogram has either called the
+		 * callback or added it to the pending list and raised the
+		 * softirq.
+		 *
+		 * This is a NOP for !HIGHRES
+		 */
+		if (reprogram && hrtimer_enqueue_reprogram(timer, base))
+			return;
+
 		base->first = &timer->node;
+	}
+
+	rb_link_node(&timer->node, parent, link);
+	rb_insert_color(&timer->node, &base->active);
+	/*
+	 * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
+	 * state of a possibly running callback.
+	 */
+	timer->state |= HRTIMER_STATE_ENQUEUED;
 }
 
 /*
  * __remove_hrtimer - internal function to remove a timer
  *
  * Caller must hold the base lock.
+ *
+ * High resolution timer mode reprograms the clock event device when the
+ * timer is the one which expires next. The caller can disable this by setting
+ * reprogram to zero. This is useful, when the context does a reprogramming
+ * anyway (e.g. timer interrupt)
  */
-static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_base *base)
+static void __remove_hrtimer(struct hrtimer *timer,
+			     struct hrtimer_clock_base *base,
+			     unsigned long newstate, int reprogram)
 {
-	/*
-	 * Remove the timer from the rbtree and replace the
-	 * first entry pointer if necessary.
-	 */
-	if (base->first == &timer->node)
-		base->first = rb_next(&timer->node);
-	rb_erase(&timer->node, &base->active);
-	rb_set_parent(&timer->node, &timer->node);
+	/* High res. callback list. NOP for !HIGHRES */
+	if (hrtimer_cb_pending(timer))
+		hrtimer_remove_cb_pending(timer);
+	else {
+		/*
+		 * Remove the timer from the rbtree and replace the
+		 * first entry pointer if necessary.
+		 */
+		if (base->first == &timer->node) {
+			base->first = rb_next(&timer->node);
+			/* Reprogram the clock event device. if enabled */
+			if (reprogram && hrtimer_hres_active())
+				hrtimer_force_reprogram(base->cpu_base);
+		}
+		rb_erase(&timer->node, &base->active);
+	}
+	timer->state = newstate;
 }
 
 /*
  * remove hrtimer, called with base lock held
  */
 static inline int
-remove_hrtimer(struct hrtimer *timer, struct hrtimer_base *base)
+remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 {
-	if (hrtimer_active(timer)) {
-		__remove_hrtimer(timer, base);
+	if (hrtimer_is_queued(timer)) {
+		int reprogram;
+
+		/*
+		 * Remove the timer and force reprogramming when high
+		 * resolution mode is active and the timer is on the current
+		 * CPU. If we remove a timer on another CPU, reprogramming is
+		 * skipped. The interrupt event on this CPU is fired and
+		 * reprogramming happens in the interrupt handler. This is a
+		 * rare case and less expensive than a smp call.
+		 */
+		timer_stats_hrtimer_clear_start_info(timer);
+		reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
+		__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE,
+				 reprogram);
 		return 1;
 	}
 	return 0;
@@ -419,7 +777,7 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_base *base)
 int
 hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 {
-	struct hrtimer_base *base, *new_base;
+	struct hrtimer_clock_base *base, *new_base;
 	unsigned long flags;
 	int ret;
 
@@ -431,7 +789,7 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 	/* Switch the timer base, if necessary: */
 	new_base = switch_hrtimer_base(timer, base);
 
-	if (mode == HRTIMER_REL) {
+	if (mode == HRTIMER_MODE_REL) {
 		tim = ktime_add(tim, new_base->get_time());
 		/*
 		 * CONFIG_TIME_LOW_RES is a temporary way for architectures
@@ -446,7 +804,9 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 	}
 	timer->expires = tim;
 
-	enqueue_hrtimer(timer, new_base);
+	timer_stats_hrtimer_set_start_info(timer);
+
+	enqueue_hrtimer(timer, new_base, base == new_base);
 
 	unlock_hrtimer_base(timer, &flags);
 
@@ -466,13 +826,13 @@ EXPORT_SYMBOL_GPL(hrtimer_start);
  */
 int hrtimer_try_to_cancel(struct hrtimer *timer)
 {
-	struct hrtimer_base *base;
+	struct hrtimer_clock_base *base;
 	unsigned long flags;
 	int ret = -1;
 
 	base = lock_hrtimer_base(timer, &flags);
 
-	if (base->curr_timer != timer)
+	if (!hrtimer_callback_running(timer))
 		ret = remove_hrtimer(timer, base);
 
 	unlock_hrtimer_base(timer, &flags);
@@ -508,19 +868,19 @@ EXPORT_SYMBOL_GPL(hrtimer_cancel);
  */
 ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
 {
-	struct hrtimer_base *base;
+	struct hrtimer_clock_base *base;
 	unsigned long flags;
 	ktime_t rem;
 
 	base = lock_hrtimer_base(timer, &flags);
-	rem = ktime_sub(timer->expires, timer->base->get_time());
+	rem = ktime_sub(timer->expires, base->get_time());
 	unlock_hrtimer_base(timer, &flags);
 
 	return rem;
 }
 EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
 
-#ifdef CONFIG_NO_IDLE_HZ
+#if defined(CONFIG_NO_IDLE_HZ) || defined(CONFIG_NO_HZ)
 /**
  * hrtimer_get_next_event - get the time until next expiry event
  *
@@ -529,26 +889,31 @@ EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
  */
 ktime_t hrtimer_get_next_event(void)
 {
-	struct hrtimer_base *base = __get_cpu_var(hrtimer_bases);
+	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+	struct hrtimer_clock_base *base = cpu_base->clock_base;
 	ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
 	unsigned long flags;
 	int i;
 
-	for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) {
-		struct hrtimer *timer;
+	spin_lock_irqsave(&cpu_base->lock, flags);
 
-		spin_lock_irqsave(&base->lock, flags);
-		if (!base->first) {
-			spin_unlock_irqrestore(&base->lock, flags);
-			continue;
+	if (!hrtimer_hres_active()) {
+		for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
+			struct hrtimer *timer;
+
+			if (!base->first)
+				continue;
+
+			timer = rb_entry(base->first, struct hrtimer, node);
+			delta.tv64 = timer->expires.tv64;
+			delta = ktime_sub(delta, base->get_time());
+			if (delta.tv64 < mindelta.tv64)
+				mindelta.tv64 = delta.tv64;
 		}
-		timer = rb_entry(base->first, struct hrtimer, node);
-		delta.tv64 = timer->expires.tv64;
-		spin_unlock_irqrestore(&base->lock, flags);
-		delta = ktime_sub(delta, base->get_time());
-		if (delta.tv64 < mindelta.tv64)
-			mindelta.tv64 = delta.tv64;
 	}
+
+	spin_unlock_irqrestore(&cpu_base->lock, flags);
+
 	if (mindelta.tv64 < 0)
 		mindelta.tv64 = 0;
 	return mindelta;
@@ -564,17 +929,23 @@ ktime_t hrtimer_get_next_event(void)
 void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 		  enum hrtimer_mode mode)
 {
-	struct hrtimer_base *bases;
+	struct hrtimer_cpu_base *cpu_base;
 
 	memset(timer, 0, sizeof(struct hrtimer));
 
-	bases = __raw_get_cpu_var(hrtimer_bases);
+	cpu_base = &__raw_get_cpu_var(hrtimer_bases);
 
-	if (clock_id == CLOCK_REALTIME && mode != HRTIMER_ABS)
+	if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
 		clock_id = CLOCK_MONOTONIC;
 
-	timer->base = &bases[clock_id];
-	rb_set_parent(&timer->node, &timer->node);
+	timer->base = &cpu_base->clock_base[clock_id];
+	hrtimer_init_timer_hres(timer);
+
+#ifdef CONFIG_TIMER_STATS
+	timer->start_site = NULL;
+	timer->start_pid = -1;
+	memset(timer->start_comm, 0, TASK_COMM_LEN);
+#endif
 }
 EXPORT_SYMBOL_GPL(hrtimer_init);
 
@@ -588,21 +959,159 @@ EXPORT_SYMBOL_GPL(hrtimer_init);
  */
 int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 {
-	struct hrtimer_base *bases;
+	struct hrtimer_cpu_base *cpu_base;
 
-	bases = __raw_get_cpu_var(hrtimer_bases);
-	*tp = ktime_to_timespec(bases[which_clock].resolution);
+	cpu_base = &__raw_get_cpu_var(hrtimer_bases);
+	*tp = ktime_to_timespec(cpu_base->clock_base[which_clock].resolution);
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(hrtimer_get_res);
 
+#ifdef CONFIG_HIGH_RES_TIMERS
+
+/*
+ * High resolution timer interrupt
+ * Called with interrupts disabled
+ */
+void hrtimer_interrupt(struct clock_event_device *dev)
+{
+	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+	struct hrtimer_clock_base *base;
+	ktime_t expires_next, now;
+	int i, raise = 0;
+
+	BUG_ON(!cpu_base->hres_active);
+	cpu_base->nr_events++;
+	dev->next_event.tv64 = KTIME_MAX;
+
+ retry:
+	now = ktime_get();
+
+	expires_next.tv64 = KTIME_MAX;
+
+	base = cpu_base->clock_base;
+
+	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
+		ktime_t basenow;
+		struct rb_node *node;
+
+		spin_lock(&cpu_base->lock);
+
+		basenow = ktime_add(now, base->offset);
+
+		while ((node = base->first)) {
+			struct hrtimer *timer;
+
+			timer = rb_entry(node, struct hrtimer, node);
+
+			if (basenow.tv64 < timer->expires.tv64) {
+				ktime_t expires;
+
+				expires = ktime_sub(timer->expires,
+						    base->offset);
+				if (expires.tv64 < expires_next.tv64)
+					expires_next = expires;
+				break;
+			}
+
+			/* Move softirq callbacks to the pending list */
+			if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
+				__remove_hrtimer(timer, base,
+						 HRTIMER_STATE_PENDING, 0);
+				list_add_tail(&timer->cb_entry,
+					      &base->cpu_base->cb_pending);
+				raise = 1;
+				continue;
+			}
+
+			__remove_hrtimer(timer, base,
+					 HRTIMER_STATE_CALLBACK, 0);
+			timer_stats_account_hrtimer(timer);
+
+			/*
+			 * Note: We clear the CALLBACK bit after
+			 * enqueue_hrtimer to avoid reprogramming of
+			 * the event hardware. This happens at the end
+			 * of this function anyway.
+			 */
+			if (timer->function(timer) != HRTIMER_NORESTART) {
+				BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
+				enqueue_hrtimer(timer, base, 0);
+			}
+			timer->state &= ~HRTIMER_STATE_CALLBACK;
+		}
+		spin_unlock(&cpu_base->lock);
+		base++;
+	}
+
+	cpu_base->expires_next = expires_next;
+
+	/* Reprogramming necessary ? */
+	if (expires_next.tv64 != KTIME_MAX) {
+		if (tick_program_event(expires_next, 0))
+			goto retry;
+	}
+
+	/* Raise softirq ? */
+	if (raise)
+		raise_softirq(HRTIMER_SOFTIRQ);
+}
+
+static void run_hrtimer_softirq(struct softirq_action *h)
+{
+	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+
+	spin_lock_irq(&cpu_base->lock);
+
+	while (!list_empty(&cpu_base->cb_pending)) {
+		enum hrtimer_restart (*fn)(struct hrtimer *);
+		struct hrtimer *timer;
+		int restart;
+
+		timer = list_entry(cpu_base->cb_pending.next,
+				   struct hrtimer, cb_entry);
+
+		timer_stats_account_hrtimer(timer);
+
+		fn = timer->function;
+		__remove_hrtimer(timer, timer->base, HRTIMER_STATE_CALLBACK, 0);
+		spin_unlock_irq(&cpu_base->lock);
+
+		restart = fn(timer);
+
+		spin_lock_irq(&cpu_base->lock);
+
+		timer->state &= ~HRTIMER_STATE_CALLBACK;
+		if (restart == HRTIMER_RESTART) {
+			BUG_ON(hrtimer_active(timer));
+			/*
+			 * Enqueue the timer, allow reprogramming of the event
+			 * device
+			 */
+			enqueue_hrtimer(timer, timer->base, 1);
+		} else if (hrtimer_active(timer)) {
+			/*
+			 * If the timer was rearmed on another CPU, reprogram
+			 * the event device.
+			 */
+			if (timer->base->first == &timer->node)
+				hrtimer_reprogram(timer, timer->base);
+		}
+	}
+	spin_unlock_irq(&cpu_base->lock);
+}
+
+#endif	/* CONFIG_HIGH_RES_TIMERS */
+
 /*
  * Expire the per base hrtimer-queue:
  */
-static inline void run_hrtimer_queue(struct hrtimer_base *base)
+static inline void run_hrtimer_queue(struct hrtimer_cpu_base *cpu_base,
+				     int index)
 {
 	struct rb_node *node;
+	struct hrtimer_clock_base *base = &cpu_base->clock_base[index];
 
 	if (!base->first)
 		return;
@@ -610,53 +1119,72 @@ static inline void run_hrtimer_queue(struct hrtimer_base *base)
 	if (base->get_softirq_time)
 		base->softirq_time = base->get_softirq_time();
 
-	spin_lock_irq(&base->lock);
+	spin_lock_irq(&cpu_base->lock);
 
 	while ((node = base->first)) {
 		struct hrtimer *timer;
-		int (*fn)(struct hrtimer *);
+		enum hrtimer_restart (*fn)(struct hrtimer *);
 		int restart;
 
 		timer = rb_entry(node, struct hrtimer, node);
 		if (base->softirq_time.tv64 <= timer->expires.tv64)
 			break;
 
+		timer_stats_account_hrtimer(timer);
+
 		fn = timer->function;
-		set_curr_timer(base, timer);
-		__remove_hrtimer(timer, base);
-		spin_unlock_irq(&base->lock);
+		__remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
+		spin_unlock_irq(&cpu_base->lock);
 
 		restart = fn(timer);
 
-		spin_lock_irq(&base->lock);
+		spin_lock_irq(&cpu_base->lock);
 
+		timer->state &= ~HRTIMER_STATE_CALLBACK;
 		if (restart != HRTIMER_NORESTART) {
 			BUG_ON(hrtimer_active(timer));
-			enqueue_hrtimer(timer, base);
+			enqueue_hrtimer(timer, base, 0);
 		}
 	}
-	set_curr_timer(base, NULL);
-	spin_unlock_irq(&base->lock);
+	spin_unlock_irq(&cpu_base->lock);
 }
 
 /*
  * Called from timer softirq every jiffy, expire hrtimers:
+ *
+ * For HRT its the fall back code to run the softirq in the timer
+ * softirq context in case the hrtimer initialization failed or has
+ * not been done yet.
  */
 void hrtimer_run_queues(void)
 {
-	struct hrtimer_base *base = __get_cpu_var(hrtimer_bases);
+	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
 	int i;
 
-	hrtimer_get_softirq_time(base);
+	if (hrtimer_hres_active())
+		return;
+
+	/*
+	 * This _is_ ugly: We have to check in the softirq context,
+	 * whether we can switch to highres and / or nohz mode. The
+	 * clocksource switch happens in the timer interrupt with
+	 * xtime_lock held. Notification from there only sets the
+	 * check bit in the tick_oneshot code, otherwise we might
+	 * deadlock vs. xtime_lock.
+	 */
+	if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
+		hrtimer_switch_to_hres();
 
-	for (i = 0; i < MAX_HRTIMER_BASES; i++)
-		run_hrtimer_queue(&base[i]);
+	hrtimer_get_softirq_time(cpu_base);
+
+	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
+		run_hrtimer_queue(cpu_base, i);
 }
 
 /*
  * Sleep related functions:
  */
-static int hrtimer_wakeup(struct hrtimer *timer)
+static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer)
 {
 	struct hrtimer_sleeper *t =
 		container_of(timer, struct hrtimer_sleeper, timer);
@@ -673,6 +1201,9 @@ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
 {
 	sl->timer.function = hrtimer_wakeup;
 	sl->task = task;
+#ifdef CONFIG_HIGH_RES_TIMERS
+	sl->timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_RESTART;
+#endif
 }
 
 static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
@@ -683,10 +1214,11 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 		set_current_state(TASK_INTERRUPTIBLE);
 		hrtimer_start(&t->timer, t->timer.expires, mode);
 
-		schedule();
+		if (likely(t->task))
+			schedule();
 
 		hrtimer_cancel(&t->timer);
-		mode = HRTIMER_ABS;
+		mode = HRTIMER_MODE_ABS;
 
 	} while (t->task && !signal_pending(current));
 
@@ -702,10 +1234,10 @@ long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
 
 	restart->fn = do_no_restart_syscall;
 
-	hrtimer_init(&t.timer, restart->arg0, HRTIMER_ABS);
+	hrtimer_init(&t.timer, restart->arg0, HRTIMER_MODE_ABS);
 	t.timer.expires.tv64 = ((u64)restart->arg3 << 32) | (u64) restart->arg2;
 
-	if (do_nanosleep(&t, HRTIMER_ABS))
+	if (do_nanosleep(&t, HRTIMER_MODE_ABS))
 		return 0;
 
 	rmtp = (struct timespec __user *) restart->arg1;
@@ -738,7 +1270,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 		return 0;
 
 	/* Absolute timers do not update the rmtp value and restart: */
-	if (mode == HRTIMER_ABS)
+	if (mode == HRTIMER_MODE_ABS)
 		return -ERESTARTNOHAND;
 
 	if (rmtp) {
@@ -771,7 +1303,7 @@ sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp)
 	if (!timespec_valid(&tu))
 		return -EINVAL;
 
-	return hrtimer_nanosleep(&tu, rmtp, HRTIMER_REL, CLOCK_MONOTONIC);
+	return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
 }
 
 /*
@@ -779,56 +1311,60 @@ sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp)
  */
 static void __devinit init_hrtimers_cpu(int cpu)
 {
-	struct hrtimer_base *base = per_cpu(hrtimer_bases, cpu);
+	struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
 	int i;
 
-	for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) {
-		spin_lock_init(&base->lock);
-		lockdep_set_class(&base->lock, &base->lock_key);
-	}
+	spin_lock_init(&cpu_base->lock);
+	lockdep_set_class(&cpu_base->lock, &cpu_base->lock_key);
+
+	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
+		cpu_base->clock_base[i].cpu_base = cpu_base;
+
+	hrtimer_init_hres(cpu_base);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static void migrate_hrtimer_list(struct hrtimer_base *old_base,
-				struct hrtimer_base *new_base)
+static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
+				struct hrtimer_clock_base *new_base)
 {
 	struct hrtimer *timer;
 	struct rb_node *node;
 
 	while ((node = rb_first(&old_base->active))) {
 		timer = rb_entry(node, struct hrtimer, node);
-		__remove_hrtimer(timer, old_base);
+		BUG_ON(hrtimer_callback_running(timer));
+		__remove_hrtimer(timer, old_base, HRTIMER_STATE_INACTIVE, 0);
 		timer->base = new_base;
-		enqueue_hrtimer(timer, new_base);
+		/*
+		 * Enqueue the timer. Allow reprogramming of the event device
+		 */
+		enqueue_hrtimer(timer, new_base, 1);
 	}
 }
 
 static void migrate_hrtimers(int cpu)
 {
-	struct hrtimer_base *old_base, *new_base;
+	struct hrtimer_cpu_base *old_base, *new_base;
 	int i;
 
 	BUG_ON(cpu_online(cpu));
-	old_base = per_cpu(hrtimer_bases, cpu);
-	new_base = get_cpu_var(hrtimer_bases);
-
-	local_irq_disable();
+	old_base = &per_cpu(hrtimer_bases, cpu);
+	new_base = &get_cpu_var(hrtimer_bases);
 
-	for (i = 0; i < MAX_HRTIMER_BASES; i++) {
+	tick_cancel_sched_timer(cpu);
 
-		spin_lock(&new_base->lock);
-		spin_lock(&old_base->lock);
-
-		BUG_ON(old_base->curr_timer);
+	local_irq_disable();
 
-		migrate_hrtimer_list(old_base, new_base);
+	spin_lock(&new_base->lock);
+	spin_lock(&old_base->lock);
 
-		spin_unlock(&old_base->lock);
-		spin_unlock(&new_base->lock);
-		old_base++;
-		new_base++;
+	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
+		migrate_hrtimer_list(&old_base->clock_base[i],
+				     &new_base->clock_base[i]);
 	}
+	spin_unlock(&old_base->lock);
+	spin_unlock(&new_base->lock);
 
 	local_irq_enable();
 	put_cpu_var(hrtimer_bases);
@@ -848,6 +1384,7 @@ static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
 
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_DEAD:
+		clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &cpu);
 		migrate_hrtimers(cpu);
 		break;
 #endif
@@ -868,5 +1405,8 @@ void __init hrtimers_init(void)
 	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
 			  (void *)(long)smp_processor_id());
 	register_cpu_notifier(&hrtimers_nb);
+#ifdef CONFIG_HIGH_RES_TIMERS
+	open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq, NULL);
+#endif
 }