Merge commit 'v2.6.33-rc5' into secretlab/test-devicetree

11 files changed, 354 insertions, 157 deletions

diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 620b58abdc3..6f740d9f094 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -20,6 +20,8 @@
 #include <linux/sysdev.h>
 #include <linux/tick.h>
 
+#include "tick-internal.h"
+
 /* The registered clock event devices */
 static LIST_HEAD(clockevent_devices);
 static LIST_HEAD(clockevents_released);
@@ -28,7 +30,7 @@ static LIST_HEAD(clockevents_released);
 static RAW_NOTIFIER_HEAD(clockevents_chain);
 
 /* Protection for the above */
-static DEFINE_SPINLOCK(clockevents_lock);
+static DEFINE_RAW_SPINLOCK(clockevents_lock);
 
 /**
  * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds
@@ -37,10 +39,9 @@ static DEFINE_SPINLOCK(clockevents_lock);
  *
  * Math helper, returns latch value converted to nanoseconds (bound checked)
  */
-unsigned long clockevent_delta2ns(unsigned long latch,
-				  struct clock_event_device *evt)
+u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
 {
-	u64 clc = ((u64) latch << evt->shift);
+	u64 clc = (u64) latch << evt->shift;
 
 	if (unlikely(!evt->mult)) {
 		evt->mult = 1;
@@ -50,10 +51,10 @@ unsigned long clockevent_delta2ns(unsigned long latch,
 	do_div(clc, evt->mult);
 	if (clc < 1000)
 		clc = 1000;
-	if (clc > LONG_MAX)
-		clc = LONG_MAX;
+	if (clc > KTIME_MAX)
+		clc = KTIME_MAX;
 
-	return (unsigned long) clc;
+	return clc;
 }
 EXPORT_SYMBOL_GPL(clockevent_delta2ns);
 
@@ -140,9 +141,9 @@ int clockevents_register_notifier(struct notifier_block *nb)
 	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(&clockevents_lock, flags);
+	raw_spin_lock_irqsave(&clockevents_lock, flags);
 	ret = raw_notifier_chain_register(&clockevents_chain, nb);
-	spin_unlock_irqrestore(&clockevents_lock, flags);
+	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
 
 	return ret;
 }
@@ -184,13 +185,13 @@ void clockevents_register_device(struct clock_event_device *dev)
 	BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
 	BUG_ON(!dev->cpumask);
 
-	spin_lock_irqsave(&clockevents_lock, flags);
+	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
 	list_add(&dev->list, &clockevent_devices);
 	clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
 	clockevents_notify_released();
 
-	spin_unlock_irqrestore(&clockevents_lock, flags);
+	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
 }
 EXPORT_SYMBOL_GPL(clockevents_register_device);
 
@@ -237,10 +238,11 @@ void clockevents_exchange_device(struct clock_event_device *old,
  */
 void clockevents_notify(unsigned long reason, void *arg)
 {
-	struct list_head *node, *tmp;
+	struct clock_event_device *dev, *tmp;
 	unsigned long flags;
+	int cpu;
 
-	spin_lock_irqsave(&clockevents_lock, flags);
+	raw_spin_lock_irqsave(&clockevents_lock, flags);
 	clockevents_do_notify(reason, arg);
 
 	switch (reason) {
@@ -249,13 +251,24 @@ void clockevents_notify(unsigned long reason, void *arg)
 		 * Unregister the clock event devices which were
 		 * released from the users in the notify chain.
 		 */
-		list_for_each_safe(node, tmp, &clockevents_released)
-			list_del(node);
+		list_for_each_entry_safe(dev, tmp, &clockevents_released, list)
+			list_del(&dev->list);
+		/*
+		 * Now check whether the CPU has left unused per cpu devices
+		 */
+		cpu = *((int *)arg);
+		list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) {
+			if (cpumask_test_cpu(cpu, dev->cpumask) &&
+			    cpumask_weight(dev->cpumask) == 1) {
+				BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
+				list_del(&dev->list);
+			}
+		}
 		break;
 	default:
 		break;
 	}
-	spin_unlock_irqrestore(&clockevents_lock, flags);
+	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
 }
 EXPORT_SYMBOL_GPL(clockevents_notify);
 #endif
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 5e18c6ab2c6..e85c23404d3 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -39,7 +39,7 @@ void timecounter_init(struct timecounter *tc,
 	tc->cycle_last = cc->read(cc);
 	tc->nsec = start_tstamp;
 }
-EXPORT_SYMBOL(timecounter_init);
+EXPORT_SYMBOL_GPL(timecounter_init);
 
 /**
  * timecounter_read_delta - get nanoseconds since last call of this function
@@ -83,7 +83,7 @@ u64 timecounter_read(struct timecounter *tc)
 
 	return nsec;
 }
-EXPORT_SYMBOL(timecounter_read);
+EXPORT_SYMBOL_GPL(timecounter_read);
 
 u64 timecounter_cyc2time(struct timecounter *tc,
 			 cycle_t cycle_tstamp)
@@ -105,7 +105,60 @@ u64 timecounter_cyc2time(struct timecounter *tc,
 
 	return nsec;
 }
-EXPORT_SYMBOL(timecounter_cyc2time);
+EXPORT_SYMBOL_GPL(timecounter_cyc2time);
+
+/**
+ * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks
+ * @mult:	pointer to mult variable
+ * @shift:	pointer to shift variable
+ * @from:	frequency to convert from
+ * @to:		frequency to convert to
+ * @minsec:	guaranteed runtime conversion range in seconds
+ *
+ * The function evaluates the shift/mult pair for the scaled math
+ * operations of clocksources and clockevents.
+ *
+ * @to and @from are frequency values in HZ. For clock sources @to is
+ * NSEC_PER_SEC == 1GHz and @from is the counter frequency. For clock
+ * event @to is the counter frequency and @from is NSEC_PER_SEC.
+ *
+ * The @minsec conversion range argument controls the time frame in
+ * seconds which must be covered by the runtime conversion with the
+ * calculated mult and shift factors. This guarantees that no 64bit
+ * overflow happens when the input value of the conversion is
+ * multiplied with the calculated mult factor. Larger ranges may
+ * reduce the conversion accuracy by chosing smaller mult and shift
+ * factors.
+ */
+void
+clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec)
+{
+	u64 tmp;
+	u32 sft, sftacc= 32;
+
+	/*
+	 * Calculate the shift factor which is limiting the conversion
+	 * range:
+	 */
+	tmp = ((u64)minsec * from) >> 32;
+	while (tmp) {
+		tmp >>=1;
+		sftacc--;
+	}
+
+	/*
+	 * Find the conversion shift/mult pair which has the best
+	 * accuracy and fits the maxsec conversion range:
+	 */
+	for (sft = 32; sft > 0; sft--) {
+		tmp = (u64) to << sft;
+		do_div(tmp, from);
+		if ((tmp >> sftacc) == 0)
+			break;
+	}
+	*mult = tmp;
+	*shift = sft;
+}
 
 /*[Clocksource internal variables]---------
  * curr_clocksource:
@@ -413,6 +466,47 @@ void clocksource_touch_watchdog(void)
 	clocksource_resume_watchdog();
 }
 
+/**
+ * clocksource_max_deferment - Returns max time the clocksource can be deferred
+ * @cs:         Pointer to clocksource
+ *
+ */
+static u64 clocksource_max_deferment(struct clocksource *cs)
+{
+	u64 max_nsecs, max_cycles;
+
+	/*
+	 * Calculate the maximum number of cycles that we can pass to the
+	 * cyc2ns function without overflowing a 64-bit signed result. The
+	 * maximum number of cycles is equal to ULLONG_MAX/cs->mult which
+	 * is equivalent to the below.
+	 * max_cycles < (2^63)/cs->mult
+	 * max_cycles < 2^(log2((2^63)/cs->mult))
+	 * max_cycles < 2^(log2(2^63) - log2(cs->mult))
+	 * max_cycles < 2^(63 - log2(cs->mult))
+	 * max_cycles < 1 << (63 - log2(cs->mult))
+	 * Please note that we add 1 to the result of the log2 to account for
+	 * any rounding errors, ensure the above inequality is satisfied and
+	 * no overflow will occur.
+	 */
+	max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1));
+
+	/*
+	 * The actual maximum number of cycles we can defer the clocksource is
+	 * determined by the minimum of max_cycles and cs->mask.
+	 */
+	max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
+	max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift);
+
+	/*
+	 * To ensure that the clocksource does not wrap whilst we are idle,
+	 * limit the time the clocksource can be deferred by 12.5%. Please
+	 * note a margin of 12.5% is used because this can be computed with
+	 * a shift, versus say 10% which would require division.
+	 */
+	return max_nsecs - (max_nsecs >> 5);
+}
+
 #ifdef CONFIG_GENERIC_TIME
 
 /**
@@ -511,6 +605,9 @@ static void clocksource_enqueue(struct clocksource *cs)
  */
 int clocksource_register(struct clocksource *cs)
 {
+	/* calculate max idle time permitted for this clocksource */
+	cs->max_idle_ns = clocksource_max_deferment(cs);
+
 	mutex_lock(&clocksource_mutex);
 	clocksource_enqueue(cs);
 	clocksource_select();
@@ -580,7 +677,7 @@ sysfs_show_current_clocksources(struct sys_device *dev,
  * @count:	length of buffer
  *
  * Takes input from sysfs interface for manually overriding the default
- * clocksource selction.
+ * clocksource selection.
  */
 static ssize_t sysfs_override_clocksource(struct sys_device *dev,
 					  struct sysdev_attribute *attr,
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index c2ec25087a3..b3bafd5fc66 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -31,7 +31,7 @@ static struct tick_device tick_broadcast_device;
 /* FIXME: Use cpumask_var_t. */
 static DECLARE_BITMAP(tick_broadcast_mask, NR_CPUS);
 static DECLARE_BITMAP(tmpmask, NR_CPUS);
-static DEFINE_SPINLOCK(tick_broadcast_lock);
+static DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
 static int tick_broadcast_force;
 
 #ifdef CONFIG_TICK_ONESHOT
@@ -96,7 +96,7 @@ 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);
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
 	/*
 	 * Devices might be registered with both periodic and oneshot
@@ -122,7 +122,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
 			tick_broadcast_clear_oneshot(cpu);
 		}
 	}
-	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 	return ret;
 }
 
@@ -161,13 +161,13 @@ static void tick_do_broadcast(struct cpumask *mask)
  */
 static void tick_do_periodic_broadcast(void)
 {
-	spin_lock(&tick_broadcast_lock);
+	raw_spin_lock(&tick_broadcast_lock);
 
 	cpumask_and(to_cpumask(tmpmask),
 		    cpu_online_mask, tick_get_broadcast_mask());
 	tick_do_broadcast(to_cpumask(tmpmask));
 
-	spin_unlock(&tick_broadcast_lock);
+	raw_spin_unlock(&tick_broadcast_lock);
 }
 
 /*
@@ -212,7 +212,7 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
 	unsigned long flags;
 	int cpu, bc_stopped;
 
-	spin_lock_irqsave(&tick_broadcast_lock, flags);
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
 	cpu = smp_processor_id();
 	td = &per_cpu(tick_cpu_device, cpu);
@@ -263,7 +263,7 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
 			tick_broadcast_setup_oneshot(bc);
 	}
 out:
-	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
 /*
@@ -299,7 +299,7 @@ void tick_shutdown_broadcast(unsigned int *cpup)
 	unsigned long flags;
 	unsigned int cpu = *cpup;
 
-	spin_lock_irqsave(&tick_broadcast_lock, flags);
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
 	bc = tick_broadcast_device.evtdev;
 	cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
@@ -309,7 +309,7 @@ void tick_shutdown_broadcast(unsigned int *cpup)
 			clockevents_shutdown(bc);
 	}
 
-	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
 void tick_suspend_broadcast(void)
@@ -317,13 +317,13 @@ void tick_suspend_broadcast(void)
 	struct clock_event_device *bc;
 	unsigned long flags;
 
-	spin_lock_irqsave(&tick_broadcast_lock, flags);
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
 	bc = tick_broadcast_device.evtdev;
 	if (bc)
 		clockevents_shutdown(bc);
 
-	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
 int tick_resume_broadcast(void)
@@ -332,7 +332,7 @@ int tick_resume_broadcast(void)
 	unsigned long flags;
 	int broadcast = 0;
 
-	spin_lock_irqsave(&tick_broadcast_lock, flags);
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
 	bc = tick_broadcast_device.evtdev;
 
@@ -351,7 +351,7 @@ int tick_resume_broadcast(void)
 			break;
 		}
 	}
-	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 
 	return broadcast;
 }
@@ -405,7 +405,7 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
 	ktime_t now, next_event;
 	int cpu;
 
-	spin_lock(&tick_broadcast_lock);
+	raw_spin_lock(&tick_broadcast_lock);
 again:
 	dev->next_event.tv64 = KTIME_MAX;
 	next_event.tv64 = KTIME_MAX;
@@ -443,7 +443,7 @@ again:
 		if (tick_broadcast_set_event(next_event, 0))
 			goto again;
 	}
-	spin_unlock(&tick_broadcast_lock);
+	raw_spin_unlock(&tick_broadcast_lock);
 }
 
 /*
@@ -457,7 +457,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
 	unsigned long flags;
 	int cpu;
 
-	spin_lock_irqsave(&tick_broadcast_lock, flags);
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
 	/*
 	 * Periodic mode does not care about the enter/exit of power
@@ -492,7 +492,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
 	}
 
 out:
-	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
 /*
@@ -563,13 +563,13 @@ void tick_broadcast_switch_to_oneshot(void)
 	struct clock_event_device *bc;
 	unsigned long flags;
 
-	spin_lock_irqsave(&tick_broadcast_lock, flags);
+	raw_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);
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
 
@@ -581,7 +581,7 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
 	unsigned long flags;
 	unsigned int cpu = *cpup;
 
-	spin_lock_irqsave(&tick_broadcast_lock, flags);
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
 	/*
 	 * Clear the broadcast mask flag for the dead cpu, but do not
@@ -589,7 +589,7 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
 	 */
 	cpumask_clear_cpu(cpu, tick_get_broadcast_oneshot_mask());
 
-	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
 /*
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 83c4417b6a3..b6b898d2eee 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -34,7 +34,7 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
 ktime_t tick_next_period;
 ktime_t tick_period;
 int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
-DEFINE_SPINLOCK(tick_device_lock);
+static DEFINE_RAW_SPINLOCK(tick_device_lock);
 
 /*
  * Debugging: see timer_list.c
@@ -209,7 +209,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 	int cpu, ret = NOTIFY_OK;
 	unsigned long flags;
 
-	spin_lock_irqsave(&tick_device_lock, flags);
+	raw_spin_lock_irqsave(&tick_device_lock, flags);
 
 	cpu = smp_processor_id();
 	if (!cpumask_test_cpu(cpu, newdev->cpumask))
@@ -268,7 +268,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 	if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
 		tick_oneshot_notify();
 
-	spin_unlock_irqrestore(&tick_device_lock, flags);
+	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
 	return NOTIFY_STOP;
 
 out_bc:
@@ -278,7 +278,7 @@ out_bc:
 	if (tick_check_broadcast_device(newdev))
 		ret = NOTIFY_STOP;
 
-	spin_unlock_irqrestore(&tick_device_lock, flags);
+	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
 
 	return ret;
 }
@@ -311,7 +311,7 @@ static void tick_shutdown(unsigned int *cpup)
 	struct clock_event_device *dev = td->evtdev;
 	unsigned long flags;
 
-	spin_lock_irqsave(&tick_device_lock, flags);
+	raw_spin_lock_irqsave(&tick_device_lock, flags);
 	td->mode = TICKDEV_MODE_PERIODIC;
 	if (dev) {
 		/*
@@ -322,7 +322,7 @@ static void tick_shutdown(unsigned int *cpup)
 		clockevents_exchange_device(dev, NULL);
 		td->evtdev = NULL;
 	}
-	spin_unlock_irqrestore(&tick_device_lock, flags);
+	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
 static void tick_suspend(void)
@@ -330,9 +330,9 @@ static void tick_suspend(void)
 	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
 	unsigned long flags;
 
-	spin_lock_irqsave(&tick_device_lock, flags);
+	raw_spin_lock_irqsave(&tick_device_lock, flags);
 	clockevents_shutdown(td->evtdev);
-	spin_unlock_irqrestore(&tick_device_lock, flags);
+	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
 static void tick_resume(void)
@@ -341,7 +341,7 @@ static void tick_resume(void)
 	unsigned long flags;
 	int broadcast = tick_resume_broadcast();
 
-	spin_lock_irqsave(&tick_device_lock, flags);
+	raw_spin_lock_irqsave(&tick_device_lock, flags);
 	clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME);
 
 	if (!broadcast) {
@@ -350,7 +350,7 @@ static void tick_resume(void)
 		else
 			tick_resume_oneshot();
 	}
-	spin_unlock_irqrestore(&tick_device_lock, flags);
+	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
 /*
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index b1c05bf75ee..290eefbc1f6 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -6,7 +6,6 @@
 #define TICK_DO_TIMER_BOOT	-2
 
 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 int tick_do_timer_cpu __read_mostly;
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index a96c0e2b89c..0a8a213016f 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -50,9 +50,9 @@ int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires,
 				dev->min_delta_ns += dev->min_delta_ns >> 1;
 
 			printk(KERN_WARNING
-			       "CE: %s increasing min_delta_ns to %lu nsec\n",
+			       "CE: %s increasing min_delta_ns to %llu nsec\n",
 			       dev->name ? dev->name : "?",
-			       dev->min_delta_ns << 1);
+			       (unsigned long long) dev->min_delta_ns << 1);
 
 			i = 0;
 		}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 89aed5933ed..f992762d7f5 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -134,18 +134,13 @@ __setup("nohz=", setup_tick_nohz);
  * 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.
  */
-static void tick_nohz_update_jiffies(void)
+static void tick_nohz_update_jiffies(ktime_t now)
 {
 	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;
 
 	cpumask_clear_cpu(cpu, nohz_cpu_mask);
-	now = ktime_get();
 	ts->idle_waketime = now;
 
 	local_irq_save(flags);
@@ -155,20 +150,17 @@ static void tick_nohz_update_jiffies(void)
 	touch_softlockup_watchdog();
 }
 
-static void tick_nohz_stop_idle(int cpu)
+static void tick_nohz_stop_idle(int cpu, ktime_t now)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	ktime_t delta;
 
-	if (ts->idle_active) {
-		ktime_t now, delta;
-		now = ktime_get();
-		delta = ktime_sub(now, ts->idle_entrytime);
-		ts->idle_lastupdate = now;
-		ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
-		ts->idle_active = 0;
+	delta = ktime_sub(now, ts->idle_entrytime);
+	ts->idle_lastupdate = now;
+	ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+	ts->idle_active = 0;
 
-		sched_clock_idle_wakeup_event(0);
-	}
+	sched_clock_idle_wakeup_event(0);
 }
 
 static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
@@ -216,6 +208,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 	struct tick_sched *ts;
 	ktime_t last_update, expires, now;
 	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+	u64 time_delta;
 	int cpu;
 
 	local_irq_save(flags);
@@ -263,7 +256,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 
 		if (ratelimit < 10) {
 			printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
-			       local_softirq_pending());
+			       (unsigned int) local_softirq_pending());
 			ratelimit++;
 		}
 		goto end;
@@ -275,14 +268,18 @@ void tick_nohz_stop_sched_tick(int inidle)
 		seq = read_seqbegin(&xtime_lock);
 		last_update = last_jiffies_update;
 		last_jiffies = jiffies;
+		time_delta = timekeeping_max_deferment();
 	} 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;
-
-	if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu))
+	if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
+	    arch_needs_cpu(cpu)) {
+		next_jiffies = last_jiffies + 1;
 		delta_jiffies = 1;
+	} else {
+		/* 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
@@ -294,22 +291,51 @@ void tick_nohz_stop_sched_tick(int inidle)
 	if ((long)delta_jiffies >= 1) {
 
 		/*
-		* calculate the expiry time for the next timer wheel
-		* timer
-		*/
-		expires = ktime_add_ns(last_update, tick_period.tv64 *
-				   delta_jiffies);
-
-		/*
 		 * If this cpu is the one which updates jiffies, then
 		 * give up the assignment and let it be taken by the
 		 * cpu which runs the tick timer next, which might be
 		 * this cpu as well. If we don't drop this here the
 		 * jiffies might be stale and do_timer() never
-		 * invoked.
+		 * invoked. Keep track of the fact that it was the one
+		 * which had the do_timer() duty last. If this cpu is
+		 * the one which had the do_timer() duty last, we
+		 * limit the sleep time to the timekeeping
+		 * max_deferement value which we retrieved
+		 * above. Otherwise we can sleep as long as we want.
 		 */
-		if (cpu == tick_do_timer_cpu)
+		if (cpu == tick_do_timer_cpu) {
 			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+			ts->do_timer_last = 1;
+		} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
+			time_delta = KTIME_MAX;
+			ts->do_timer_last = 0;
+		} else if (!ts->do_timer_last) {
+			time_delta = KTIME_MAX;
+		}
+
+		/*
+		 * calculate the expiry time for the next timer wheel
+		 * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals
+		 * that there is no timer pending or at least extremely
+		 * far into the future (12 days for HZ=1000). In this
+		 * case we set the expiry to the end of time.
+		 */
+		if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
+			/*
+			 * Calculate the time delta for the next timer event.
+			 * If the time delta exceeds the maximum time delta
+			 * permitted by the current clocksource then adjust
+			 * the time delta accordingly to ensure the
+			 * clocksource does not wrap.
+			 */
+			time_delta = min_t(u64, time_delta,
+					   tick_period.tv64 * delta_jiffies);
+		}
+
+		if (time_delta < KTIME_MAX)
+			expires = ktime_add_ns(last_update, time_delta);
+		else
+			expires.tv64 = KTIME_MAX;
 
 		if (delta_jiffies > 1)
 			cpumask_set_cpu(cpu, nohz_cpu_mask);
@@ -342,22 +368,19 @@ void tick_nohz_stop_sched_tick(int inidle)
 
 		ts->idle_sleeps++;
 
+		/* Mark expires */
+		ts->idle_expires = expires;
+
 		/*
-		 * delta_jiffies >= NEXT_TIMER_MAX_DELTA signals that
-		 * there is no timer pending or at least extremly far
-		 * into the future (12 days for HZ=1000). In this case
-		 * we simply stop the tick timer:
+		 * If the expiration time == KTIME_MAX, then
+		 * in this case we simply stop the tick timer.
 		 */
-		if (unlikely(delta_jiffies >= NEXT_TIMER_MAX_DELTA)) {
-			ts->idle_expires.tv64 = KTIME_MAX;
+		 if (unlikely(expires.tv64 == KTIME_MAX)) {
 			if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
 				hrtimer_cancel(&ts->sched_timer);
 			goto out;
 		}
 
-		/* Mark expiries */
-		ts->idle_expires = expires;
-
 		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
 			hrtimer_start(&ts->sched_timer, expires,
 				      HRTIMER_MODE_ABS_PINNED);
@@ -436,7 +459,11 @@ void tick_nohz_restart_sched_tick(void)
 	ktime_t now;
 
 	local_irq_disable();
-	tick_nohz_stop_idle(cpu);
+	if (ts->idle_active || (ts->inidle && ts->tick_stopped))
+		now = ktime_get();
+
+	if (ts->idle_active)
+		tick_nohz_stop_idle(cpu, now);
 
 	if (!ts->inidle || !ts->tick_stopped) {
 		ts->inidle = 0;
@@ -450,7 +477,6 @@ void tick_nohz_restart_sched_tick(void)
 
 	/* Update jiffies first */
 	select_nohz_load_balancer(0);
-	now = ktime_get();
 	tick_do_update_jiffies64(now);
 	cpumask_clear_cpu(cpu, nohz_cpu_mask);
 
@@ -584,22 +610,18 @@ static void tick_nohz_switch_to_nohz(void)
  * timer and do not touch the other magic bits which need to be done
  * when idle is left.
  */
-static void tick_nohz_kick_tick(int cpu)
+static void tick_nohz_kick_tick(int cpu, ktime_t now)
 {
 #if 0
 	/* Switch back to 2.6.27 behaviour */
 
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-	ktime_t delta, now;
-
-	if (!ts->tick_stopped)
-		return;
+	ktime_t delta;
 
 	/*
 	 * Do not touch the tick device, when the next expiry is either
 	 * already reached or less/equal than the tick period.
 	 */
-	now = ktime_get();
 	delta =	ktime_sub(hrtimer_get_expires(&ts->sched_timer), now);
 	if (delta.tv64 <= tick_period.tv64)
 		return;
@@ -608,9 +630,26 @@ static void tick_nohz_kick_tick(int cpu)
 #endif
 }
 
+static inline void tick_check_nohz(int cpu)
+{
+	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	ktime_t now;
+
+	if (!ts->idle_active && !ts->tick_stopped)
+		return;
+	now = ktime_get();
+	if (ts->idle_active)
+		tick_nohz_stop_idle(cpu, now);
+	if (ts->tick_stopped) {
+		tick_nohz_update_jiffies(now);
+		tick_nohz_kick_tick(cpu, now);
+	}
+}
+
 #else
 
 static inline void tick_nohz_switch_to_nohz(void) { }
+static inline void tick_check_nohz(int cpu) { }
 
 #endif /* NO_HZ */
 
@@ -620,11 +659,7 @@ static inline void tick_nohz_switch_to_nohz(void) { }
 void tick_check_idle(int cpu)
 {
 	tick_check_oneshot_broadcast(cpu);
-#ifdef CONFIG_NO_HZ
-	tick_nohz_stop_idle(cpu);
-	tick_nohz_update_jiffies();
-	tick_nohz_kick_tick(cpu);
-#endif
+	tick_check_nohz(cpu);
 }
 
 /*
diff --git a/kernel/time/timecompare.c b/kernel/time/timecompare.c
index 71e7f1a1915..12f5c55090b 100644
--- a/kernel/time/timecompare.c
+++ b/kernel/time/timecompare.c
@@ -40,7 +40,7 @@ ktime_t timecompare_transform(struct timecompare *sync,
 
 	return ns_to_ktime(nsec);
 }
-EXPORT_SYMBOL(timecompare_transform);
+EXPORT_SYMBOL_GPL(timecompare_transform);
 
 int timecompare_offset(struct timecompare *sync,
 		       s64 *offset,
@@ -89,7 +89,7 @@ int timecompare_offset(struct timecompare *sync,
 			 * source time
 			 */
 			sample.offset =
-				ktime_to_ns(ktime_add(end, start)) / 2 -
+				(ktime_to_ns(end) + ktime_to_ns(start)) / 2 -
 				ts;
 
 			/* simple insertion sort based on duration */
@@ -131,7 +131,7 @@ int timecompare_offset(struct timecompare *sync,
 
 	return used;
 }
-EXPORT_SYMBOL(timecompare_offset);
+EXPORT_SYMBOL_GPL(timecompare_offset);
 
 void __timecompare_update(struct timecompare *sync,
 			  u64 source_tstamp)
@@ -188,4 +188,4 @@ void __timecompare_update(struct timecompare *sync,
 		}
 	}
 }
-EXPORT_SYMBOL(__timecompare_update);
+EXPORT_SYMBOL_GPL(__timecompare_update);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index c3a4e2907ea..7faaa32fbf4 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -177,7 +177,7 @@ void timekeeping_leap_insert(int leapsecond)
 {
 	xtime.tv_sec += leapsecond;
 	wall_to_monotonic.tv_sec -= leapsecond;
-	update_vsyscall(&xtime, timekeeper.clock);
+	update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
 }
 
 #ifdef CONFIG_GENERIC_TIME
@@ -337,7 +337,7 @@ int do_settimeofday(struct timespec *tv)
 	timekeeper.ntp_error = 0;
 	ntp_clear();
 
-	update_vsyscall(&xtime, timekeeper.clock);
+	update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
 
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 
@@ -488,6 +488,17 @@ int timekeeping_valid_for_hres(void)
 }
 
 /**
+ * timekeeping_max_deferment - Returns max time the clocksource can be deferred
+ *
+ * Caller must observe xtime_lock via read_seqbegin/read_seqretry to
+ * ensure that the clocksource does not change!
+ */
+u64 timekeeping_max_deferment(void)
+{
+	return timekeeper.clock->max_idle_ns;
+}
+
+/**
  * read_persistent_clock -  Return time from the persistent clock.
  *
  * Weak dummy function for arches that do not yet support it.
@@ -722,6 +733,51 @@ static void timekeeping_adjust(s64 offset)
 				timekeeper.ntp_error_shift;
 }
 
+
+/**
+ * logarithmic_accumulation - shifted accumulation of cycles
+ *
+ * This functions accumulates a shifted interval of cycles into
+ * into a shifted interval nanoseconds. Allows for O(log) accumulation
+ * loop.
+ *
+ * Returns the unconsumed cycles.
+ */
+static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
+{
+	u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
+
+	/* If the offset is smaller then a shifted interval, do nothing */
+	if (offset < timekeeper.cycle_interval<<shift)
+		return offset;
+
+	/* Accumulate one shifted interval */
+	offset -= timekeeper.cycle_interval << shift;
+	timekeeper.clock->cycle_last += timekeeper.cycle_interval << shift;
+
+	timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
+	while (timekeeper.xtime_nsec >= nsecps) {
+		timekeeper.xtime_nsec -= nsecps;
+		xtime.tv_sec++;
+		second_overflow();
+	}
+
+	/* Accumulate into raw time */
+	raw_time.tv_nsec += timekeeper.raw_interval << shift;;
+	while (raw_time.tv_nsec >= NSEC_PER_SEC) {
+		raw_time.tv_nsec -= NSEC_PER_SEC;
+		raw_time.tv_sec++;
+	}
+
+	/* Accumulate error between NTP and clock interval */
+	timekeeper.ntp_error += tick_length << shift;
+	timekeeper.ntp_error -= timekeeper.xtime_interval <<
+				(timekeeper.ntp_error_shift + shift);
+
+	return offset;
+}
+
+
 /**
  * update_wall_time - Uses the current clocksource to increment the wall time
  *
@@ -732,6 +788,7 @@ void update_wall_time(void)
 	struct clocksource *clock;
 	cycle_t offset;
 	u64 nsecs;
+	int shift = 0, maxshift;
 
 	/* Make sure we're fully resumed: */
 	if (unlikely(timekeeping_suspended))
@@ -745,33 +802,22 @@ void update_wall_time(void)
 #endif
 	timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;
 
-	/* normally this loop will run just once, however in the
-	 * case of lost or late ticks, it will accumulate correctly.
+	/*
+	 * With NO_HZ we may have to accumulate many cycle_intervals
+	 * (think "ticks") worth of time at once. To do this efficiently,
+	 * we calculate the largest doubling multiple of cycle_intervals
+	 * that is smaller then the offset. We then accumulate that
+	 * chunk in one go, and then try to consume the next smaller
+	 * doubled multiple.
 	 */
+	shift = ilog2(offset) - ilog2(timekeeper.cycle_interval);
+	shift = max(0, shift);
+	/* Bound shift to one less then what overflows tick_length */
+	maxshift = (8*sizeof(tick_length) - (ilog2(tick_length)+1)) - 1;
+	shift = min(shift, maxshift);
 	while (offset >= timekeeper.cycle_interval) {
-		u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
-
-		/* accumulate one interval */
-		offset -= timekeeper.cycle_interval;
-		clock->cycle_last += timekeeper.cycle_interval;
-
-		timekeeper.xtime_nsec += timekeeper.xtime_interval;
-		if (timekeeper.xtime_nsec >= nsecps) {
-			timekeeper.xtime_nsec -= nsecps;
-			xtime.tv_sec++;
-			second_overflow();
-		}
-
-		raw_time.tv_nsec += timekeeper.raw_interval;
-		if (raw_time.tv_nsec >= NSEC_PER_SEC) {
-			raw_time.tv_nsec -= NSEC_PER_SEC;
-			raw_time.tv_sec++;
-		}
-
-		/* accumulate error between NTP and clock interval */
-		timekeeper.ntp_error += tick_length;
-		timekeeper.ntp_error -= timekeeper.xtime_interval <<
-					timekeeper.ntp_error_shift;
+		offset = logarithmic_accumulation(offset, shift);
+		shift--;
 	}
 
 	/* correct the clock when NTP error is too big */
@@ -811,7 +857,7 @@ void update_wall_time(void)
 	update_xtime_cache(nsecs);
 
 	/* check to see if there is a new clocksource to use */
-	update_vsyscall(&xtime, timekeeper.clock);
+	update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
 }
 
 /**
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 1b5b7aa2fdf..bdfb8dd1050 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -84,7 +84,7 @@ print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base,
 
 next_one:
 	i = 0;
-	spin_lock_irqsave(&base->cpu_base->lock, flags);
+	raw_spin_lock_irqsave(&base->cpu_base->lock, flags);
 
 	curr = base->first;
 	/*
@@ -100,13 +100,13 @@ next_one:
 
 		timer = rb_entry(curr, struct hrtimer, node);
 		tmp = *timer;
-		spin_unlock_irqrestore(&base->cpu_base->lock, flags);
+		raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags);
 
 		print_timer(m, timer, &tmp, i, now);
 		next++;
 		goto next_one;
 	}
-	spin_unlock_irqrestore(&base->cpu_base->lock, flags);
+	raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags);
 }
 
 static void
@@ -150,6 +150,9 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 	P_ns(expires_next);
 	P(hres_active);
 	P(nr_events);
+	P(nr_retries);
+	P(nr_hangs);
+	P_ns(max_hang_time);
 #endif
 #undef P
 #undef P_ns
@@ -204,10 +207,12 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
 		return;
 	}
 	SEQ_printf(m, "%s\n", dev->name);
-	SEQ_printf(m, " max_delta_ns:   %lu\n", dev->max_delta_ns);
-	SEQ_printf(m, " min_delta_ns:   %lu\n", dev->min_delta_ns);
-	SEQ_printf(m, " mult:           %lu\n", dev->mult);
-	SEQ_printf(m, " shift:          %d\n", dev->shift);
+	SEQ_printf(m, " max_delta_ns:   %llu\n",
+		   (unsigned long long) dev->max_delta_ns);
+	SEQ_printf(m, " min_delta_ns:   %llu\n",
+		   (unsigned long long) dev->min_delta_ns);
+	SEQ_printf(m, " mult:           %u\n", dev->mult);
+	SEQ_printf(m, " shift:          %u\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));
@@ -232,10 +237,10 @@ static void timer_list_show_tickdevices(struct seq_file *m)
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 	print_tickdevice(m, tick_get_broadcast_device(), -1);
 	SEQ_printf(m, "tick_broadcast_mask: %08lx\n",
-		   tick_get_broadcast_mask()->bits[0]);
+		   cpumask_bits(tick_get_broadcast_mask())[0]);
 #ifdef CONFIG_TICK_ONESHOT
 	SEQ_printf(m, "tick_broadcast_oneshot_mask: %08lx\n",
-		   tick_get_broadcast_oneshot_mask()->bits[0]);
+		   cpumask_bits(tick_get_broadcast_oneshot_mask())[0]);
 #endif
 	SEQ_printf(m, "\n");
 #endif
@@ -252,7 +257,7 @@ 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: v0.4\n");
+	SEQ_printf(m, "Timer List Version: v0.5\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);
 
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index ee5681f8d7e..2f3b585b8d7 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -86,7 +86,7 @@ static DEFINE_SPINLOCK(table_lock);
 /*
  * Per-CPU lookup locks for fast hash lookup:
  */
-static DEFINE_PER_CPU(spinlock_t, lookup_lock);
+static DEFINE_PER_CPU(raw_spinlock_t, tstats_lookup_lock);
 
 /*
  * Mutex to serialize state changes with show-stats activities:
@@ -238,14 +238,14 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
 	/*
 	 * It doesnt matter which lock we take:
 	 */
-	spinlock_t *lock;
+	raw_spinlock_t *lock;
 	struct entry *entry, input;
 	unsigned long flags;
 
 	if (likely(!timer_stats_active))
 		return;
 
-	lock = &per_cpu(lookup_lock, raw_smp_processor_id());
+	lock = &per_cpu(tstats_lookup_lock, raw_smp_processor_id());
 
 	input.timer = timer;
 	input.start_func = startf;
@@ -253,7 +253,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
 	input.pid = pid;
 	input.timer_flag = timer_flag;
 
-	spin_lock_irqsave(lock, flags);
+	raw_spin_lock_irqsave(lock, flags);
 	if (!timer_stats_active)
 		goto out_unlock;
 
@@ -264,7 +264,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
 		atomic_inc(&overflow_count);
 
  out_unlock:
-	spin_unlock_irqrestore(lock, flags);
+	raw_spin_unlock_irqrestore(lock, flags);
 }
 
 static void print_name_offset(struct seq_file *m, unsigned long addr)
@@ -348,9 +348,11 @@ static void sync_access(void)
 	int cpu;
 
 	for_each_online_cpu(cpu) {
-		spin_lock_irqsave(&per_cpu(lookup_lock, cpu), flags);
+		raw_spinlock_t *lock = &per_cpu(tstats_lookup_lock, cpu);
+
+		raw_spin_lock_irqsave(lock, flags);
 		/* nothing */
-		spin_unlock_irqrestore(&per_cpu(lookup_lock, cpu), flags);
+		raw_spin_unlock_irqrestore(lock, flags);
 	}
 }
 
@@ -408,7 +410,7 @@ void __init init_timer_stats(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		spin_lock_init(&per_cpu(lookup_lock, cpu));
+		raw_spin_lock_init(&per_cpu(tstats_lookup_lock, cpu));
 }
 
 static int __init init_tstats_procfs(void)