Merge commit 'linus/master' into merge-linus

Conflicts:

	arch/x86/kvm/i8254.c

8 files changed, 163 insertions, 50 deletions

diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 8d53106a0a9..95ed42951e0 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -3,7 +3,6 @@
 #
 config TICK_ONESHOT
 	bool
-	default n
 
 config NO_HZ
 	bool "Tickless System (Dynamic Ticks)"
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 3d1e3e1a197..f8d968063ce 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -72,6 +72,16 @@ void clockevents_set_mode(struct clock_event_device *dev,
 }
 
 /**
+ * clockevents_shutdown - shutdown the device and clear next_event
+ * @dev:	device to shutdown
+ */
+void clockevents_shutdown(struct clock_event_device *dev)
+{
+	clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+	dev->next_event.tv64 = KTIME_MAX;
+}
+
+/**
  * clockevents_program_event - Reprogram the clock event device.
  * @expires:	absolute expiry time (monotonic clock)
  *
@@ -177,7 +187,7 @@ void clockevents_register_device(struct clock_event_device *dev)
 /*
  * Noop handler when we shut down an event device
  */
-static void clockevents_handle_noop(struct clock_event_device *dev)
+void clockevents_handle_noop(struct clock_event_device *dev)
 {
 }
 
@@ -199,7 +209,6 @@ void clockevents_exchange_device(struct clock_event_device *old,
 	 * 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);
@@ -207,7 +216,7 @@ void clockevents_exchange_device(struct clock_event_device *old,
 
 	if (new) {
 		BUG_ON(new->mode != CLOCK_EVT_MODE_UNUSED);
-		clockevents_set_mode(new, CLOCK_EVT_MODE_SHUTDOWN);
+		clockevents_shutdown(new);
 	}
 	local_irq_restore(flags);
 }
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 4c8d85421d2..9c114b726ab 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -244,7 +244,7 @@ static void sync_cmos_clock(unsigned long dummy)
 	if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2)
 		fail = update_persistent_clock(now);
 
-	next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec;
+	next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec - (TICK_NSEC / 2);
 	if (next.tv_nsec <= 0)
 		next.tv_nsec += NSEC_PER_SEC;
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 31463d370b9..cb01cd8f919 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -175,6 +175,8 @@ static void tick_do_periodic_broadcast(void)
  */
 static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 {
+	ktime_t next;
+
 	tick_do_periodic_broadcast();
 
 	/*
@@ -185,10 +187,13 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 
 	/*
 	 * Setup the next period for devices, which do not have
-	 * periodic mode:
+	 * periodic mode. We read dev->next_event first and add to it
+	 * when the event alrady expired. clockevents_program_event()
+	 * sets dev->next_event only when the event is really
+	 * programmed to the device.
 	 */
-	for (;;) {
-		ktime_t next = ktime_add(dev->next_event, tick_period);
+	for (next = dev->next_event; ;) {
+		next = ktime_add(next, tick_period);
 
 		if (!clockevents_program_event(dev, next, ktime_get()))
 			return;
@@ -205,7 +210,7 @@ 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;
+	int cpu, bc_stopped;
 
 	spin_lock_irqsave(&tick_broadcast_lock, flags);
 
@@ -223,14 +228,16 @@ static void tick_do_broadcast_on_off(void *why)
 	if (!tick_device_is_functional(dev))
 		goto out;
 
+	bc_stopped = cpus_empty(tick_broadcast_mask);
+
 	switch (*reason) {
 	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
 	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
 		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);
+			if (tick_broadcast_device.mode ==
+			    TICKDEV_MODE_PERIODIC)
+				clockevents_shutdown(dev);
 		}
 		if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
 			tick_broadcast_force = 1;
@@ -239,15 +246,17 @@ static void tick_do_broadcast_on_off(void *why)
 		if (!tick_broadcast_force &&
 		    cpu_isset(cpu, tick_broadcast_mask)) {
 			cpu_clear(cpu, tick_broadcast_mask);
-			if (td->mode == TICKDEV_MODE_PERIODIC)
+			if (tick_broadcast_device.mode ==
+			    TICKDEV_MODE_PERIODIC)
 				tick_setup_periodic(dev, 0);
 		}
 		break;
 	}
 
-	if (cpus_empty(tick_broadcast_mask))
-		clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
-	else {
+	if (cpus_empty(tick_broadcast_mask)) {
+		if (!bc_stopped)
+			clockevents_shutdown(bc);
+	} else if (bc_stopped) {
 		if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
 			tick_broadcast_start_periodic(bc);
 		else
@@ -298,7 +307,7 @@ void tick_shutdown_broadcast(unsigned int *cpup)
 
 	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
 		if (bc && cpus_empty(tick_broadcast_mask))
-			clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+			clockevents_shutdown(bc);
 	}
 
 	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
@@ -313,7 +322,7 @@ void tick_suspend_broadcast(void)
 
 	bc = tick_broadcast_device.evtdev;
 	if (bc)
-		clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+		clockevents_shutdown(bc);
 
 	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
@@ -364,16 +373,8 @@ cpumask_t *tick_get_broadcast_oneshot_mask(void)
 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));
-	}
+
+	return tick_dev_program_event(bc, expires, force);
 }
 
 int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
@@ -491,14 +492,52 @@ static void tick_broadcast_clear_oneshot(int cpu)
 	cpu_clear(cpu, tick_broadcast_oneshot_mask);
 }
 
+static void tick_broadcast_init_next_event(cpumask_t *mask, ktime_t expires)
+{
+	struct tick_device *td;
+	int cpu;
+
+	for_each_cpu_mask_nr(cpu, *mask) {
+		td = &per_cpu(tick_cpu_device, cpu);
+		if (td->evtdev)
+			td->evtdev->next_event = expires;
+	}
+}
+
 /**
  * tick_broadcast_setup_oneshot - setup the broadcast device
  */
 void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
-	bc->event_handler = tick_handle_oneshot_broadcast;
-	clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
-	bc->next_event.tv64 = KTIME_MAX;
+	/* Set it up only once ! */
+	if (bc->event_handler != tick_handle_oneshot_broadcast) {
+		int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
+		int cpu = smp_processor_id();
+		cpumask_t mask;
+
+		bc->event_handler = tick_handle_oneshot_broadcast;
+		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+
+		/* Take the do_timer update */
+		tick_do_timer_cpu = cpu;
+
+		/*
+		 * We must be careful here. There might be other CPUs
+		 * waiting for periodic broadcast. We need to set the
+		 * oneshot_mask bits for those and program the
+		 * broadcast device to fire.
+		 */
+		mask = tick_broadcast_mask;
+		cpu_clear(cpu, mask);
+		cpus_or(tick_broadcast_oneshot_mask,
+			tick_broadcast_oneshot_mask, mask);
+
+		if (was_periodic && !cpus_empty(mask)) {
+			tick_broadcast_init_next_event(&mask, tick_next_period);
+			tick_broadcast_set_event(tick_next_period, 1);
+		} else
+			bc->next_event.tv64 = KTIME_MAX;
+	}
 }
 
 /*
@@ -538,4 +577,12 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
 	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
+/*
+ * Check, whether the broadcast device is in one shot mode
+ */
+int tick_broadcast_oneshot_active(void)
+{
+	return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT;
+}
+
 #endif
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 80c4336f418..df12434b43c 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -33,7 +33,7 @@ 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 = -1;
+int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
 DEFINE_SPINLOCK(tick_device_lock);
 
 /*
@@ -109,7 +109,8 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 	if (!tick_device_is_functional(dev))
 		return;
 
-	if (dev->features & CLOCK_EVT_FEAT_PERIODIC) {
+	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
+	    !tick_broadcast_oneshot_active()) {
 		clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC);
 	} else {
 		unsigned long seq;
@@ -148,7 +149,7 @@ static void tick_setup_device(struct tick_device *td,
 		 * If no cpu took the do_timer update, assign it to
 		 * this cpu:
 		 */
-		if (tick_do_timer_cpu == -1) {
+		if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
 			tick_do_timer_cpu = cpu;
 			tick_next_period = ktime_get();
 			tick_period = ktime_set(0, NSEC_PER_SEC / HZ);
@@ -161,6 +162,7 @@ static void tick_setup_device(struct tick_device *td,
 	} else {
 		handler = td->evtdev->event_handler;
 		next_event = td->evtdev->next_event;
+		td->evtdev->event_handler = clockevents_handle_noop;
 	}
 
 	td->evtdev = newdev;
@@ -248,7 +250,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 	 * not give it back to the clockevents layer !
 	 */
 	if (tick_is_broadcast_device(curdev)) {
-		clockevents_set_mode(curdev, CLOCK_EVT_MODE_SHUTDOWN);
+		clockevents_shutdown(curdev);
 		curdev = NULL;
 	}
 	clockevents_exchange_device(curdev, newdev);
@@ -299,7 +301,8 @@ static void tick_shutdown(unsigned int *cpup)
 	if (*cpup == tick_do_timer_cpu) {
 		int cpu = first_cpu(cpu_online_map);
 
-		tick_do_timer_cpu = (cpu != NR_CPUS) ? cpu : -1;
+		tick_do_timer_cpu = (cpu != NR_CPUS) ? cpu :
+			TICK_DO_TIMER_NONE;
 	}
 	spin_unlock_irqrestore(&tick_device_lock, flags);
 }
@@ -310,7 +313,7 @@ static void tick_suspend(void)
 	unsigned long flags;
 
 	spin_lock_irqsave(&tick_device_lock, flags);
-	clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_SHUTDOWN);
+	clockevents_shutdown(td->evtdev);
 	spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index f13f2b7f4fd..469248782c2 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -1,6 +1,10 @@
 /*
  * tick internal variable and functions used by low/high res code
  */
+
+#define TICK_DO_TIMER_NONE	-1
+#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;
@@ -10,6 +14,8 @@ extern int tick_do_timer_cpu __read_mostly;
 extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast);
 extern void tick_handle_periodic(struct clock_event_device *dev);
 
+extern void clockevents_shutdown(struct clock_event_device *dev);
+
 /*
  * NO_HZ / high resolution timer shared code
  */
@@ -17,6 +23,8 @@ extern void tick_handle_periodic(struct clock_event_device *dev);
 extern void tick_setup_oneshot(struct clock_event_device *newdev,
 			       void (*handler)(struct clock_event_device *),
 			       ktime_t nextevt);
+extern int tick_dev_program_event(struct clock_event_device *dev,
+				  ktime_t expires, int force);
 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 *));
@@ -27,6 +35,7 @@ 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);
 extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
+extern int tick_broadcast_oneshot_active(void);
 # else /* BROADCAST */
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
@@ -35,6 +44,7 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 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) { }
+static inline int tick_broadcast_oneshot_active(void) { return 0; }
 # endif /* !BROADCAST */
 
 #else /* !ONESHOT */
@@ -64,6 +74,7 @@ static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 {
 	return 0;
 }
+static inline int tick_broadcast_oneshot_active(void) { return 0; }
 #endif /* !TICK_ONESHOT */
 
 /*
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 450c04935b6..2e8de678e76 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -23,24 +23,56 @@
 #include "tick-internal.h"
 
 /**
- * tick_program_event
+ * tick_program_event internal worker function
  */
-int tick_program_event(ktime_t expires, int force)
+int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires,
+			   int force)
 {
-	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
 	ktime_t now = ktime_get();
+	int i;
 
-	while (1) {
+	for (i = 0;;) {
 		int ret = clockevents_program_event(dev, expires, now);
 
 		if (!ret || !force)
 			return ret;
+
+		/*
+		 * We tried 2 times to program the device with the given
+		 * min_delta_ns. If that's not working then we double it
+		 * and emit a warning.
+		 */
+		if (++i > 2) {
+			/* Increase the min. delta and try again */
+			if (!dev->min_delta_ns)
+				dev->min_delta_ns = 5000;
+			else
+				dev->min_delta_ns += dev->min_delta_ns >> 1;
+
+			printk(KERN_WARNING
+			       "CE: %s increasing min_delta_ns to %lu nsec\n",
+			       dev->name ? dev->name : "?",
+			       dev->min_delta_ns << 1);
+
+			i = 0;
+		}
+
 		now = ktime_get();
-		expires = ktime_add(now, ktime_set(0, dev->min_delta_ns));
+		expires = ktime_add_ns(now, dev->min_delta_ns);
 	}
 }
 
 /**
+ * tick_program_event
+ */
+int tick_program_event(ktime_t expires, int force)
+{
+	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+
+	return tick_dev_program_event(dev, expires, force);
+}
+
+/**
  * tick_resume_onshot - resume oneshot mode
  */
 void tick_resume_oneshot(void)
@@ -61,7 +93,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev,
 {
 	newdev->event_handler = handler;
 	clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT);
-	clockevents_program_event(newdev, next_event, ktime_get());
+	tick_dev_program_event(newdev, next_event, 1);
 }
 
 /**
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index b33be61c0f6..a547be11cf9 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -20,6 +20,7 @@
 #include <linux/profile.h>
 #include <linux/sched.h>
 #include <linux/tick.h>
+#include <linux/module.h>
 
 #include <asm/irq_regs.h>
 
@@ -75,6 +76,9 @@ static void tick_do_update_jiffies64(ktime_t now)
 							   incr * ticks);
 		}
 		do_timer(++ticks);
+
+		/* Keep the tick_next_period variable up to date */
+		tick_next_period = ktime_add(last_jiffies_update, tick_period);
 	}
 	write_sequnlock(&xtime_lock);
 }
@@ -187,9 +191,17 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 
-	*last_update_time = ktime_to_us(ts->idle_lastupdate);
+	if (!tick_nohz_enabled)
+		return -1;
+
+	if (ts->idle_active)
+		*last_update_time = ktime_to_us(ts->idle_lastupdate);
+	else
+		*last_update_time = ktime_to_us(ktime_get());
+
 	return ktime_to_us(ts->idle_sleeptime);
 }
+EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
 
 /**
  * tick_nohz_stop_sched_tick - stop the idle tick from the idle task
@@ -221,7 +233,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 	 */
 	if (unlikely(!cpu_online(cpu))) {
 		if (cpu == tick_do_timer_cpu)
-			tick_do_timer_cpu = -1;
+			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
 	}
 
 	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
@@ -258,7 +270,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 	next_jiffies = get_next_timer_interrupt(last_jiffies);
 	delta_jiffies = next_jiffies - last_jiffies;
 
-	if (rcu_needs_cpu(cpu))
+	if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu))
 		delta_jiffies = 1;
 	/*
 	 * Do not stop the tick, if we are only one off
@@ -303,7 +315,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 		 * invoked.
 		 */
 		if (cpu == tick_do_timer_cpu)
-			tick_do_timer_cpu = -1;
+			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
 
 		ts->idle_sleeps++;
 
@@ -468,7 +480,7 @@ static void tick_nohz_handler(struct clock_event_device *dev)
 	 * this duty, then the jiffies update is still serialized by
 	 * xtime_lock.
 	 */
-	if (unlikely(tick_do_timer_cpu == -1))
+	if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
 		tick_do_timer_cpu = cpu;
 
 	/* Check, if the jiffies need an update */
@@ -570,7 +582,7 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
 	 * this duty, then the jiffies update is still serialized by
 	 * xtime_lock.
 	 */
-	if (unlikely(tick_do_timer_cpu == -1))
+	if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
 		tick_do_timer_cpu = cpu;
 #endif
 
@@ -622,7 +634,7 @@ void tick_setup_sched_timer(void)
 	 */
 	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;
+	ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 
 	/* Get the next period (per cpu) */
 	hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());