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

Pull timer core updates from Thomas Gleixner:
 "The timer changes contain:

   - posix timer code consolidation and fixes for odd corner cases

   - sched_clock implementation moved from ARM to core code to avoid
     duplication by other architectures

   - alarm timer updates

   - clocksource and clockevents unregistration facilities

   - clocksource/events support for new hardware

   - precise nanoseconds RTC readout (Xen feature)

   - generic support for Xen suspend/resume oddities

   - the usual lot of fixes and cleanups all over the place

  The parts which touch other areas (ARM/XEN) have been coordinated with
  the relevant maintainers.  Though this results in an handful of
  trivial to solve merge conflicts, which we preferred over nasty cross
  tree merge dependencies.

  The patches which have been committed in the last few days are bug
  fixes plus the posix timer lot.  The latter was in akpms queue and
  next for quite some time; they just got forgotten and Frederic
  collected them last minute."

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (59 commits)
  hrtimer: Remove unused variable
  hrtimers: Move SMP function call to thread context
  clocksource: Reselect clocksource when watchdog validated high-res capability
  posix-cpu-timers: don't account cpu timer after stopped thread runtime accounting
  posix_timers: fix racy timer delta caching on task exit
  posix-timers: correctly get dying task time sample in posix_cpu_timer_schedule()
  selftests: add basic posix timers selftests
  posix_cpu_timers: consolidate expired timers check
  posix_cpu_timers: consolidate timer list cleanups
  posix_cpu_timer: consolidate expiry time type
  tick: Sanitize broadcast control logic
  tick: Prevent uncontrolled switch to oneshot mode
  tick: Make oneshot broadcast robust vs. CPU offlining
  x86: xen: Sync the CMOS RTC as well as the Xen wallclock
  x86: xen: Sync the wallclock when the system time is set
  timekeeping: Indicate that clock was set in the pvclock gtod notifier
  timekeeping: Pass flags instead of multiple bools to timekeeping_update()
  xen: Remove clock_was_set() call in the resume path
  hrtimers: Support resuming with two or more CPUs online (but stopped)
  timer: Fix jiffies wrap behavior of round_jiffies_common()
  ...

15 files changed, 1223 insertions, 540 deletions

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 3ee4d06c6fc2..f0f4fe29cd21 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -722,17 +722,20 @@ static int hrtimer_switch_to_hres(void)
 	return 1;
 }
 
+static void clock_was_set_work(struct work_struct *work)
+{
+	clock_was_set();
+}
+
+static DECLARE_WORK(hrtimer_work, clock_was_set_work);
+
 /*
- * Called from timekeeping code to reprogramm the hrtimer interrupt
- * device. If called from the timer interrupt context we defer it to
- * softirq context.
+ * Called from timekeeping and resume code to reprogramm the hrtimer
+ * interrupt device on all cpus.
  */
 void clock_was_set_delayed(void)
 {
-	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
-
-	cpu_base->clock_was_set = 1;
-	__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+	schedule_work(&hrtimer_work);
 }
 
 #else
@@ -774,15 +777,19 @@ void clock_was_set(void)
 
 /*
  * During resume we might have to reprogram the high resolution timer
- * interrupt (on the local CPU):
+ * interrupt on all online CPUs.  However, all other CPUs will be
+ * stopped with IRQs interrupts disabled so the clock_was_set() call
+ * must be deferred.
  */
 void hrtimers_resume(void)
 {
 	WARN_ONCE(!irqs_disabled(),
 		  KERN_INFO "hrtimers_resume() called with IRQs enabled!");
 
+	/* Retrigger on the local CPU */
 	retrigger_next_event(NULL);
-	timerfd_clock_was_set();
+	/* And schedule a retrigger for all others */
+	clock_was_set_delayed();
 }
 
 static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
@@ -1433,13 +1440,6 @@ void hrtimer_peek_ahead_timers(void)
 
 static void run_hrtimer_softirq(struct softirq_action *h)
 {
-	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
-
-	if (cpu_base->clock_was_set) {
-		cpu_base->clock_was_set = 0;
-		clock_was_set();
-	}
-
 	hrtimer_peek_ahead_timers();
 }
 
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 42670e9b44e0..c7f31aa272f7 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -51,59 +51,28 @@ static int check_clock(const clockid_t which_clock)
 	return error;
 }
 
-static inline union cpu_time_count
+static inline unsigned long long
 timespec_to_sample(const clockid_t which_clock, const struct timespec *tp)
 {
-	union cpu_time_count ret;
-	ret.sched = 0;		/* high half always zero when .cpu used */
+	unsigned long long ret;
+
+	ret = 0;		/* high half always zero when .cpu used */
 	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
-		ret.sched = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec;
+		ret = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec;
 	} else {
-		ret.cpu = timespec_to_cputime(tp);
+		ret = cputime_to_expires(timespec_to_cputime(tp));
 	}
 	return ret;
 }
 
 static void sample_to_timespec(const clockid_t which_clock,
-			       union cpu_time_count cpu,
+			       unsigned long long expires,
 			       struct timespec *tp)
 {
 	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED)
-		*tp = ns_to_timespec(cpu.sched);
+		*tp = ns_to_timespec(expires);
 	else
-		cputime_to_timespec(cpu.cpu, tp);
-}
-
-static inline int cpu_time_before(const clockid_t which_clock,
-				  union cpu_time_count now,
-				  union cpu_time_count then)
-{
-	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
-		return now.sched < then.sched;
-	}  else {
-		return now.cpu < then.cpu;
-	}
-}
-static inline void cpu_time_add(const clockid_t which_clock,
-				union cpu_time_count *acc,
-			        union cpu_time_count val)
-{
-	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
-		acc->sched += val.sched;
-	}  else {
-		acc->cpu += val.cpu;
-	}
-}
-static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock,
-						union cpu_time_count a,
-						union cpu_time_count b)
-{
-	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
-		a.sched -= b.sched;
-	}  else {
-		a.cpu -= b.cpu;
-	}
-	return a;
+		cputime_to_timespec((__force cputime_t)expires, tp);
 }
 
 /*
@@ -111,47 +80,31 @@ static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock,
  * given the current clock sample.
  */
 static void bump_cpu_timer(struct k_itimer *timer,
-				  union cpu_time_count now)
+			   unsigned long long now)
 {
 	int i;
+	unsigned long long delta, incr;
 
-	if (timer->it.cpu.incr.sched == 0)
+	if (timer->it.cpu.incr == 0)
 		return;
 
-	if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
-		unsigned long long delta, incr;
+	if (now < timer->it.cpu.expires)
+		return;
 
-		if (now.sched < timer->it.cpu.expires.sched)
-			return;
-		incr = timer->it.cpu.incr.sched;
-		delta = now.sched + incr - timer->it.cpu.expires.sched;
-		/* Don't use (incr*2 < delta), incr*2 might overflow. */
-		for (i = 0; incr < delta - incr; i++)
-			incr = incr << 1;
-		for (; i >= 0; incr >>= 1, i--) {
-			if (delta < incr)
-				continue;
-			timer->it.cpu.expires.sched += incr;
-			timer->it_overrun += 1 << i;
-			delta -= incr;
-		}
-	} else {
-		cputime_t delta, incr;
+	incr = timer->it.cpu.incr;
+	delta = now + incr - timer->it.cpu.expires;
 
-		if (now.cpu < timer->it.cpu.expires.cpu)
-			return;
-		incr = timer->it.cpu.incr.cpu;
-		delta = now.cpu + incr - timer->it.cpu.expires.cpu;
-		/* Don't use (incr*2 < delta), incr*2 might overflow. */
-		for (i = 0; incr < delta - incr; i++)
-			     incr += incr;
-		for (; i >= 0; incr = incr >> 1, i--) {
-			if (delta < incr)
-				continue;
-			timer->it.cpu.expires.cpu += incr;
-			timer->it_overrun += 1 << i;
-			delta -= incr;
-		}
+	/* Don't use (incr*2 < delta), incr*2 might overflow. */
+	for (i = 0; incr < delta - incr; i++)
+		incr = incr << 1;
+
+	for (; i >= 0; incr >>= 1, i--) {
+		if (delta < incr)
+			continue;
+
+		timer->it.cpu.expires += incr;
+		timer->it_overrun += 1 << i;
+		delta -= incr;
 	}
 }
 
@@ -170,21 +123,21 @@ static inline int task_cputime_zero(const struct task_cputime *cputime)
 	return 0;
 }
 
-static inline cputime_t prof_ticks(struct task_struct *p)
+static inline unsigned long long prof_ticks(struct task_struct *p)
 {
 	cputime_t utime, stime;
 
 	task_cputime(p, &utime, &stime);
 
-	return utime + stime;
+	return cputime_to_expires(utime + stime);
 }
-static inline cputime_t virt_ticks(struct task_struct *p)
+static inline unsigned long long virt_ticks(struct task_struct *p)
 {
 	cputime_t utime;
 
 	task_cputime(p, &utime, NULL);
 
-	return utime;
+	return cputime_to_expires(utime);
 }
 
 static int
@@ -225,19 +178,19 @@ posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
  * Sample a per-thread clock for the given task.
  */
 static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
-			    union cpu_time_count *cpu)
+			    unsigned long long *sample)
 {
 	switch (CPUCLOCK_WHICH(which_clock)) {
 	default:
 		return -EINVAL;
 	case CPUCLOCK_PROF:
-		cpu->cpu = prof_ticks(p);
+		*sample = prof_ticks(p);
 		break;
 	case CPUCLOCK_VIRT:
-		cpu->cpu = virt_ticks(p);
+		*sample = virt_ticks(p);
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = task_sched_runtime(p);
+		*sample = task_sched_runtime(p);
 		break;
 	}
 	return 0;
@@ -284,7 +237,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
  */
 static int cpu_clock_sample_group(const clockid_t which_clock,
 				  struct task_struct *p,
-				  union cpu_time_count *cpu)
+				  unsigned long long *sample)
 {
 	struct task_cputime cputime;
 
@@ -293,15 +246,15 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 		return -EINVAL;
 	case CPUCLOCK_PROF:
 		thread_group_cputime(p, &cputime);
-		cpu->cpu = cputime.utime + cputime.stime;
+		*sample = cputime_to_expires(cputime.utime + cputime.stime);
 		break;
 	case CPUCLOCK_VIRT:
 		thread_group_cputime(p, &cputime);
-		cpu->cpu = cputime.utime;
+		*sample = cputime_to_expires(cputime.utime);
 		break;
 	case CPUCLOCK_SCHED:
 		thread_group_cputime(p, &cputime);
-		cpu->sched = cputime.sum_exec_runtime;
+		*sample = cputime.sum_exec_runtime;
 		break;
 	}
 	return 0;
@@ -312,7 +265,7 @@ static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 {
 	const pid_t pid = CPUCLOCK_PID(which_clock);
 	int error = -EINVAL;
-	union cpu_time_count rtn;
+	unsigned long long rtn;
 
 	if (pid == 0) {
 		/*
@@ -446,6 +399,15 @@ static int posix_cpu_timer_del(struct k_itimer *timer)
 	return ret;
 }
 
+static void cleanup_timers_list(struct list_head *head,
+				unsigned long long curr)
+{
+	struct cpu_timer_list *timer, *next;
+
+	list_for_each_entry_safe(timer, next, head, entry)
+		list_del_init(&timer->entry);
+}
+
 /*
  * Clean out CPU timers still ticking when a thread exited.  The task
  * pointer is cleared, and the expiry time is replaced with the residual
@@ -456,37 +418,12 @@ static void cleanup_timers(struct list_head *head,
 			   cputime_t utime, cputime_t stime,
 			   unsigned long long sum_exec_runtime)
 {
-	struct cpu_timer_list *timer, *next;
-	cputime_t ptime = utime + stime;
-
-	list_for_each_entry_safe(timer, next, head, entry) {
-		list_del_init(&timer->entry);
-		if (timer->expires.cpu < ptime) {
-			timer->expires.cpu = 0;
-		} else {
-			timer->expires.cpu -= ptime;
-		}
-	}
 
-	++head;
-	list_for_each_entry_safe(timer, next, head, entry) {
-		list_del_init(&timer->entry);
-		if (timer->expires.cpu < utime) {
-			timer->expires.cpu = 0;
-		} else {
-			timer->expires.cpu -= utime;
-		}
-	}
+	cputime_t ptime = utime + stime;
 
-	++head;
-	list_for_each_entry_safe(timer, next, head, entry) {
-		list_del_init(&timer->entry);
-		if (timer->expires.sched < sum_exec_runtime) {
-			timer->expires.sched = 0;
-		} else {
-			timer->expires.sched -= sum_exec_runtime;
-		}
-	}
+	cleanup_timers_list(head, cputime_to_expires(ptime));
+	cleanup_timers_list(++head, cputime_to_expires(utime));
+	cleanup_timers_list(++head, sum_exec_runtime);
 }
 
 /*
@@ -516,17 +453,21 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk)
 		       tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
 }
 
-static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
+static void clear_dead_task(struct k_itimer *itimer, unsigned long long now)
 {
+	struct cpu_timer_list *timer = &itimer->it.cpu;
+
 	/*
 	 * That's all for this thread or process.
 	 * We leave our residual in expires to be reported.
 	 */
-	put_task_struct(timer->it.cpu.task);
-	timer->it.cpu.task = NULL;
-	timer->it.cpu.expires = cpu_time_sub(timer->it_clock,
-					     timer->it.cpu.expires,
-					     now);
+	put_task_struct(timer->task);
+	timer->task = NULL;
+	if (timer->expires < now) {
+		timer->expires = 0;
+	} else {
+		timer->expires -= now;
+	}
 }
 
 static inline int expires_gt(cputime_t expires, cputime_t new_exp)
@@ -558,14 +499,14 @@ static void arm_timer(struct k_itimer *timer)
 
 	listpos = head;
 	list_for_each_entry(next, head, entry) {
-		if (cpu_time_before(timer->it_clock, nt->expires, next->expires))
+		if (nt->expires < next->expires)
 			break;
 		listpos = &next->entry;
 	}
 	list_add(&nt->entry, listpos);
 
 	if (listpos == head) {
-		union cpu_time_count *exp = &nt->expires;
+		unsigned long long exp = nt->expires;
 
 		/*
 		 * We are the new earliest-expiring POSIX 1.b timer, hence
@@ -576,17 +517,17 @@ static void arm_timer(struct k_itimer *timer)
 
 		switch (CPUCLOCK_WHICH(timer->it_clock)) {
 		case CPUCLOCK_PROF:
-			if (expires_gt(cputime_expires->prof_exp, exp->cpu))
-				cputime_expires->prof_exp = exp->cpu;
+			if (expires_gt(cputime_expires->prof_exp, expires_to_cputime(exp)))
+				cputime_expires->prof_exp = expires_to_cputime(exp);
 			break;
 		case CPUCLOCK_VIRT:
-			if (expires_gt(cputime_expires->virt_exp, exp->cpu))
-				cputime_expires->virt_exp = exp->cpu;
+			if (expires_gt(cputime_expires->virt_exp, expires_to_cputime(exp)))
+				cputime_expires->virt_exp = expires_to_cputime(exp);
 			break;
 		case CPUCLOCK_SCHED:
 			if (cputime_expires->sched_exp == 0 ||
-			    cputime_expires->sched_exp > exp->sched)
-				cputime_expires->sched_exp = exp->sched;
+			    cputime_expires->sched_exp > exp)
+				cputime_expires->sched_exp = exp;
 			break;
 		}
 	}
@@ -601,20 +542,20 @@ static void cpu_timer_fire(struct k_itimer *timer)
 		/*
 		 * User don't want any signal.
 		 */
-		timer->it.cpu.expires.sched = 0;
+		timer->it.cpu.expires = 0;
 	} else if (unlikely(timer->sigq == NULL)) {
 		/*
 		 * This a special case for clock_nanosleep,
 		 * not a normal timer from sys_timer_create.
 		 */
 		wake_up_process(timer->it_process);
-		timer->it.cpu.expires.sched = 0;
-	} else if (timer->it.cpu.incr.sched == 0) {
+		timer->it.cpu.expires = 0;
+	} else if (timer->it.cpu.incr == 0) {
 		/*
 		 * One-shot timer.  Clear it as soon as it's fired.
 		 */
 		posix_timer_event(timer, 0);
-		timer->it.cpu.expires.sched = 0;
+		timer->it.cpu.expires = 0;
 	} else if (posix_timer_event(timer, ++timer->it_requeue_pending)) {
 		/*
 		 * The signal did not get queued because the signal
@@ -632,7 +573,7 @@ static void cpu_timer_fire(struct k_itimer *timer)
  */
 static int cpu_timer_sample_group(const clockid_t which_clock,
 				  struct task_struct *p,
-				  union cpu_time_count *cpu)
+				  unsigned long long *sample)
 {
 	struct task_cputime cputime;
 
@@ -641,13 +582,13 @@ static int cpu_timer_sample_group(const clockid_t which_clock,
 	default:
 		return -EINVAL;
 	case CPUCLOCK_PROF:
-		cpu->cpu = cputime.utime + cputime.stime;
+		*sample = cputime_to_expires(cputime.utime + cputime.stime);
 		break;
 	case CPUCLOCK_VIRT:
-		cpu->cpu = cputime.utime;
+		*sample = cputime_to_expires(cputime.utime);
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
+		*sample = cputime.sum_exec_runtime + task_delta_exec(p);
 		break;
 	}
 	return 0;
@@ -694,7 +635,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 			       struct itimerspec *new, struct itimerspec *old)
 {
 	struct task_struct *p = timer->it.cpu.task;
-	union cpu_time_count old_expires, new_expires, old_incr, val;
+	unsigned long long old_expires, new_expires, old_incr, val;
 	int ret;
 
 	if (unlikely(p == NULL)) {
@@ -749,7 +690,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	}
 
 	if (old) {
-		if (old_expires.sched == 0) {
+		if (old_expires == 0) {
 			old->it_value.tv_sec = 0;
 			old->it_value.tv_nsec = 0;
 		} else {
@@ -764,11 +705,8 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 			 * new setting.
 			 */
 			bump_cpu_timer(timer, val);
-			if (cpu_time_before(timer->it_clock, val,
-					    timer->it.cpu.expires)) {
-				old_expires = cpu_time_sub(
-					timer->it_clock,
-					timer->it.cpu.expires, val);
+			if (val < timer->it.cpu.expires) {
+				old_expires = timer->it.cpu.expires - val;
 				sample_to_timespec(timer->it_clock,
 						   old_expires,
 						   &old->it_value);
@@ -791,8 +729,8 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 		goto out;
 	}
 
-	if (new_expires.sched != 0 && !(flags & TIMER_ABSTIME)) {
-		cpu_time_add(timer->it_clock, &new_expires, val);
+	if (new_expires != 0 && !(flags & TIMER_ABSTIME)) {
+		new_expires += val;
 	}
 
 	/*
@@ -801,8 +739,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	 * arm the timer (we'll just fake it for timer_gettime).
 	 */
 	timer->it.cpu.expires = new_expires;
-	if (new_expires.sched != 0 &&
-	    cpu_time_before(timer->it_clock, val, new_expires)) {
+	if (new_expires != 0 && val < new_expires) {
 		arm_timer(timer);
 	}
 
@@ -826,8 +763,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	timer->it_overrun_last = 0;
 	timer->it_overrun = -1;
 
-	if (new_expires.sched != 0 &&
-	    !cpu_time_before(timer->it_clock, val, new_expires)) {
+	if (new_expires != 0 && !(val < new_expires)) {
 		/*
 		 * The designated time already passed, so we notify
 		 * immediately, even if the thread never runs to
@@ -849,7 +785,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 
 static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 {
-	union cpu_time_count now;
+	unsigned long long now;
 	struct task_struct *p = timer->it.cpu.task;
 	int clear_dead;
 
@@ -859,7 +795,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 	sample_to_timespec(timer->it_clock,
 			   timer->it.cpu.incr, &itp->it_interval);
 
-	if (timer->it.cpu.expires.sched == 0) {	/* Timer not armed at all.  */
+	if (timer->it.cpu.expires == 0) {	/* Timer not armed at all.  */
 		itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
 		return;
 	}
@@ -891,7 +827,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 			 */
 			put_task_struct(p);
 			timer->it.cpu.task = NULL;
-			timer->it.cpu.expires.sched = 0;
+			timer->it.cpu.expires = 0;
 			read_unlock(&tasklist_lock);
 			goto dead;
 		} else {
@@ -912,10 +848,9 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 		goto dead;
 	}
 
-	if (cpu_time_before(timer->it_clock, now, timer->it.cpu.expires)) {
+	if (now < timer->it.cpu.expires) {
 		sample_to_timespec(timer->it_clock,
-				   cpu_time_sub(timer->it_clock,
-						timer->it.cpu.expires, now),
+				   timer->it.cpu.expires - now,
 				   &itp->it_value);
 	} else {
 		/*
@@ -927,6 +862,28 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 	}
 }
 
+static unsigned long long
+check_timers_list(struct list_head *timers,
+		  struct list_head *firing,
+		  unsigned long long curr)
+{
+	int maxfire = 20;
+
+	while (!list_empty(timers)) {
+		struct cpu_timer_list *t;
+
+		t = list_first_entry(timers, struct cpu_timer_list, entry);
+
+		if (!--maxfire || curr < t->expires)
+			return t->expires;
+
+		t->firing = 1;
+		list_move_tail(&t->entry, firing);
+	}
+
+	return 0;
+}
+
 /*
  * Check for any per-thread CPU timers that have fired and move them off
  * the tsk->cpu_timers[N] list onto the firing list.  Here we update the
@@ -935,54 +892,20 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 static void check_thread_timers(struct task_struct *tsk,
 				struct list_head *firing)
 {
-	int maxfire;
 	struct list_head *timers = tsk->cpu_timers;
 	struct signal_struct *const sig = tsk->signal;
+	struct task_cputime *tsk_expires = &tsk->cputime_expires;
+	unsigned long long expires;
 	unsigned long soft;
 
-	maxfire = 20;
-	tsk->cputime_expires.prof_exp = 0;
-	while (!list_empty(timers)) {
-		struct cpu_timer_list *t = list_first_entry(timers,
-						      struct cpu_timer_list,
-						      entry);
-		if (!--maxfire || prof_ticks(tsk) < t->expires.cpu) {
-			tsk->cputime_expires.prof_exp = t->expires.cpu;
-			break;
-		}
-		t->firing = 1;
-		list_move_tail(&t->entry, firing);
-	}
+	expires = check_timers_list(timers, firing, prof_ticks(tsk));
+	tsk_expires->prof_exp = expires_to_cputime(expires);
 
-	++timers;
-	maxfire = 20;
-	tsk->cputime_expires.virt_exp = 0;
-	while (!list_empty(timers)) {
-		struct cpu_timer_list *t = list_first_entry(timers,
-						      struct cpu_timer_list,
-						      entry);
-		if (!--maxfire || virt_ticks(tsk) < t->expires.cpu) {
-			tsk->cputime_expires.virt_exp = t->expires.cpu;
-			break;
-		}
-		t->firing = 1;
-		list_move_tail(&t->entry, firing);
-	}
+	expires = check_timers_list(++timers, firing, virt_ticks(tsk));
+	tsk_expires->virt_exp = expires_to_cputime(expires);
 
-	++timers;
-	maxfire = 20;
-	tsk->cputime_expires.sched_exp = 0;
-	while (!list_empty(timers)) {
-		struct cpu_timer_list *t = list_first_entry(timers,
-						      struct cpu_timer_list,
-						      entry);
-		if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) {
-			tsk->cputime_expires.sched_exp = t->expires.sched;
-			break;
-		}
-		t->firing = 1;
-		list_move_tail(&t->entry, firing);
-	}
+	tsk_expires->sched_exp = check_timers_list(++timers, firing,
+						   tsk->se.sum_exec_runtime);
 
 	/*
 	 * Check for the special case thread timers.
@@ -1030,7 +953,8 @@ static void stop_process_timers(struct signal_struct *sig)
 static u32 onecputick;
 
 static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
-			     cputime_t *expires, cputime_t cur_time, int signo)
+			     unsigned long long *expires,
+			     unsigned long long cur_time, int signo)
 {
 	if (!it->expires)
 		return;
@@ -1066,9 +990,8 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
 static void check_process_timers(struct task_struct *tsk,
 				 struct list_head *firing)
 {
-	int maxfire;
 	struct signal_struct *const sig = tsk->signal;
-	cputime_t utime, ptime, virt_expires, prof_expires;
+	unsigned long long utime, ptime, virt_expires, prof_expires;
 	unsigned long long sum_sched_runtime, sched_expires;
 	struct list_head *timers = sig->cpu_timers;
 	struct task_cputime cputime;
@@ -1078,52 +1001,13 @@ static void check_process_timers(struct task_struct *tsk,
 	 * Collect the current process totals.
 	 */
 	thread_group_cputimer(tsk, &cputime);
-	utime = cputime.utime;
-	ptime = utime + cputime.stime;
+	utime = cputime_to_expires(cputime.utime);
+	ptime = utime + cputime_to_expires(cputime.stime);
 	sum_sched_runtime = cputime.sum_exec_runtime;
-	maxfire = 20;
-	prof_expires = 0;
-	while (!list_empty(timers)) {
-		struct cpu_timer_list *tl = list_first_entry(timers,
-						      struct cpu_timer_list,
-						      entry);
-		if (!--maxfire || ptime < tl->expires.cpu) {
-			prof_expires = tl->expires.cpu;
-			break;
-		}
-		tl->firing = 1;
-		list_move_tail(&tl->entry, firing);
-	}
 
-	++timers;
-	maxfire = 20;
-	virt_expires = 0;
-	while (!list_empty(timers)) {
-		struct cpu_timer_list *tl = list_first_entry(timers,
-						      struct cpu_timer_list,
-						      entry);
-		if (!--maxfire || utime < tl->expires.cpu) {
-			virt_expires = tl->expires.cpu;
-			break;
-		}
-		tl->firing = 1;
-		list_move_tail(&tl->entry, firing);
-	}
-
-	++timers;
-	maxfire = 20;
-	sched_expires = 0;
-	while (!list_empty(timers)) {
-		struct cpu_timer_list *tl = list_first_entry(timers,
-						      struct cpu_timer_list,
-						      entry);
-		if (!--maxfire || sum_sched_runtime < tl->expires.sched) {
-			sched_expires = tl->expires.sched;
-			break;
-		}
-		tl->firing = 1;
-		list_move_tail(&tl->entry, firing);
-	}
+	prof_expires = check_timers_list(timers, firing, ptime);
+	virt_expires = check_timers_list(++timers, firing, utime);
+	sched_expires = check_timers_list(++timers, firing, sum_sched_runtime);
 
 	/*
 	 * Check for the special case process timers.
@@ -1162,8 +1046,8 @@ static void check_process_timers(struct task_struct *tsk,
 		}
 	}
 
-	sig->cputime_expires.prof_exp = prof_expires;
-	sig->cputime_expires.virt_exp = virt_expires;
+	sig->cputime_expires.prof_exp = expires_to_cputime(prof_expires);
+	sig->cputime_expires.virt_exp = expires_to_cputime(virt_expires);
 	sig->cputime_expires.sched_exp = sched_expires;
 	if (task_cputime_zero(&sig->cputime_expires))
 		stop_process_timers(sig);
@@ -1176,7 +1060,7 @@ static void check_process_timers(struct task_struct *tsk,
 void posix_cpu_timer_schedule(struct k_itimer *timer)
 {
 	struct task_struct *p = timer->it.cpu.task;
-	union cpu_time_count now;
+	unsigned long long now;
 
 	if (unlikely(p == NULL))
 		/*
@@ -1205,7 +1089,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			 */
 			put_task_struct(p);
 			timer->it.cpu.task = p = NULL;
-			timer->it.cpu.expires.sched = 0;
+			timer->it.cpu.expires = 0;
 			goto out_unlock;
 		} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
 			/*
@@ -1213,6 +1097,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			 * not yet reaped.  Take this opportunity to
 			 * drop our task ref.
 			 */
+			cpu_timer_sample_group(timer->it_clock, p, &now);
 			clear_dead_task(timer, now);
 			goto out_unlock;
 		}
@@ -1387,7 +1272,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 			   cputime_t *newval, cputime_t *oldval)
 {
-	union cpu_time_count now;
+	unsigned long long now;
 
 	BUG_ON(clock_idx == CPUCLOCK_SCHED);
 	cpu_timer_sample_group(clock_idx, tsk, &now);
@@ -1399,17 +1284,17 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 		 * it to be absolute.
 		 */
 		if (*oldval) {
-			if (*oldval <= now.cpu) {
+			if (*oldval <= now) {
 				/* Just about to fire. */
 				*oldval = cputime_one_jiffy;
 			} else {
-				*oldval -= now.cpu;
+				*oldval -= now;
 			}
 		}
 
 		if (!*newval)
 			goto out;
-		*newval += now.cpu;
+		*newval += now;
 	}
 
 	/*
@@ -1459,7 +1344,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 		}
 
 		while (!signal_pending(current)) {
-			if (timer.it.cpu.expires.sched == 0) {
+			if (timer.it.cpu.expires == 0) {
 				/*
 				 * Our timer fired and was reset, below
 				 * deletion can not fail.
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 17d7065c3872..5aef494fc8b4 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -162,6 +162,39 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next)
  */
 
 /**
+ * cputimer_running - return true if cputimer is running
+ *
+ * @tsk:	Pointer to target task.
+ */
+static inline bool cputimer_running(struct task_struct *tsk)
+
+{
+	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+
+	if (!cputimer->running)
+		return false;
+
+	/*
+	 * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime
+	 * in __exit_signal(), we won't account to the signal struct further
+	 * cputime consumed by that task, even though the task can still be
+	 * ticking after __exit_signal().
+	 *
+	 * In order to keep a consistent behaviour between thread group cputime
+	 * and thread group cputimer accounting, lets also ignore the cputime
+	 * elapsing after __exit_signal() in any thread group timer running.
+	 *
+	 * This makes sure that POSIX CPU clocks and timers are synchronized, so
+	 * that a POSIX CPU timer won't expire while the corresponding POSIX CPU
+	 * clock delta is behind the expiring timer value.
+	 */
+	if (unlikely(!tsk->sighand))
+		return false;
+
+	return true;
+}
+
+/**
  * account_group_user_time - Maintain utime for a thread group.
  *
  * @tsk:	Pointer to task structure.
@@ -176,7 +209,7 @@ static inline void account_group_user_time(struct task_struct *tsk,
 {
 	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
 
-	if (!cputimer->running)
+	if (!cputimer_running(tsk))
 		return;
 
 	raw_spin_lock(&cputimer->lock);
@@ -199,7 +232,7 @@ static inline void account_group_system_time(struct task_struct *tsk,
 {
 	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
 
-	if (!cputimer->running)
+	if (!cputimer_running(tsk))
 		return;
 
 	raw_spin_lock(&cputimer->lock);
@@ -222,7 +255,7 @@ static inline void account_group_exec_runtime(struct task_struct *tsk,
 {
 	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
 
-	if (!cputimer->running)
+	if (!cputimer_running(tsk))
 		return;
 
 	raw_spin_lock(&cputimer->lock);
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index ff7d9d2ab504..9250130646f5 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -4,6 +4,8 @@ obj-y += timeconv.o posix-clock.o alarmtimer.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)	+= tick-broadcast.o
+obj-$(CONFIG_GENERIC_SCHED_CLOCK)		+= sched_clock.o
 obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o
 obj-$(CONFIG_TICK_ONESHOT)			+= tick-sched.o
 obj-$(CONFIG_TIMER_STATS)			+= timer_stats.o
+obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index f11d83b12949..eec50fcef9e4 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -199,6 +199,13 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
 
 }
 
+ktime_t alarm_expires_remaining(const struct alarm *alarm)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
+	return ktime_sub(alarm->node.expires, base->gettime());
+}
+EXPORT_SYMBOL_GPL(alarm_expires_remaining);
+
 #ifdef CONFIG_RTC_CLASS
 /**
  * alarmtimer_suspend - Suspend time callback
@@ -303,9 +310,10 @@ void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
 	alarm->type = type;
 	alarm->state = ALARMTIMER_STATE_INACTIVE;
 }
+EXPORT_SYMBOL_GPL(alarm_init);
 
 /**
- * alarm_start - Sets an alarm to fire
+ * alarm_start - Sets an absolute alarm to fire
  * @alarm: ptr to alarm to set
  * @start: time to run the alarm
  */
@@ -323,6 +331,34 @@ int alarm_start(struct alarm *alarm, ktime_t start)
 	spin_unlock_irqrestore(&base->lock, flags);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(alarm_start);
+
+/**
+ * alarm_start_relative - Sets a relative alarm to fire
+ * @alarm: ptr to alarm to set
+ * @start: time relative to now to run the alarm
+ */
+int alarm_start_relative(struct alarm *alarm, ktime_t start)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
+
+	start = ktime_add(start, base->gettime());
+	return alarm_start(alarm, start);
+}
+EXPORT_SYMBOL_GPL(alarm_start_relative);
+
+void alarm_restart(struct alarm *alarm)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
+	unsigned long flags;
+
+	spin_lock_irqsave(&base->lock, flags);
+	hrtimer_set_expires(&alarm->timer, alarm->node.expires);
+	hrtimer_restart(&alarm->timer);
+	alarmtimer_enqueue(base, alarm);
+	spin_unlock_irqrestore(&base->lock, flags);
+}
+EXPORT_SYMBOL_GPL(alarm_restart);
 
 /**
  * alarm_try_to_cancel - Tries to cancel an alarm timer
@@ -344,6 +380,7 @@ int alarm_try_to_cancel(struct alarm *alarm)
 	spin_unlock_irqrestore(&base->lock, flags);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(alarm_try_to_cancel);
 
 
 /**
@@ -361,6 +398,7 @@ int alarm_cancel(struct alarm *alarm)
 		cpu_relax();
 	}
 }
+EXPORT_SYMBOL_GPL(alarm_cancel);
 
 
 u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval)
@@ -393,8 +431,15 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval)
 	alarm->node.expires = ktime_add(alarm->node.expires, interval);
 	return overrun;
 }
+EXPORT_SYMBOL_GPL(alarm_forward);
 
+u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
 
+	return alarm_forward(alarm, base->gettime(), interval);
+}
+EXPORT_SYMBOL_GPL(alarm_forward_now);
 
 
 /**
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index c6d6400ee137..38959c866789 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -15,20 +15,23 @@
 #include <linux/hrtimer.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/notifier.h>
 #include <linux/smp.h>
+#include <linux/device.h>
 
 #include "tick-internal.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_RAW_SPINLOCK(clockevents_lock);
+/* Protection for unbind operations */
+static DEFINE_MUTEX(clockevents_mutex);
+
+struct ce_unbind {
+	struct clock_event_device *ce;
+	int res;
+};
 
 /**
  * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds
@@ -232,47 +235,107 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
 	return (rc && force) ? clockevents_program_min_delta(dev) : rc;
 }
 
-/**
- * clockevents_register_notifier - register a clock events change listener
+/*
+ * Called after a notify add to make devices available which were
+ * released from the notifier call.
  */
-int clockevents_register_notifier(struct notifier_block *nb)
+static void clockevents_notify_released(void)
 {
-	unsigned long flags;
-	int ret;
+	struct clock_event_device *dev;
 
-	raw_spin_lock_irqsave(&clockevents_lock, flags);
-	ret = raw_notifier_chain_register(&clockevents_chain, nb);
-	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
+	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);
+		tick_check_new_device(dev);
+	}
+}
 
-	return ret;
+/*
+ * Try to install a replacement clock event device
+ */
+static int clockevents_replace(struct clock_event_device *ced)
+{
+	struct clock_event_device *dev, *newdev = NULL;
+
+	list_for_each_entry(dev, &clockevent_devices, list) {
+		if (dev == ced || dev->mode != CLOCK_EVT_MODE_UNUSED)
+			continue;
+
+		if (!tick_check_replacement(newdev, dev))
+			continue;
+
+		if (!try_module_get(dev->owner))
+			continue;
+
+		if (newdev)
+			module_put(newdev->owner);
+		newdev = dev;
+	}
+	if (newdev) {
+		tick_install_replacement(newdev);
+		list_del_init(&ced->list);
+	}
+	return newdev ? 0 : -EBUSY;
 }
 
 /*
- * Notify about a clock event change. Called with clockevents_lock
- * held.
+ * Called with clockevents_mutex and clockevents_lock held
  */
-static void clockevents_do_notify(unsigned long reason, void *dev)
+static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu)
 {
-	raw_notifier_call_chain(&clockevents_chain, reason, dev);
+	/* Fast track. Device is unused */
+	if (ced->mode == CLOCK_EVT_MODE_UNUSED) {
+		list_del_init(&ced->list);
+		return 0;
+	}
+
+	return ced == per_cpu(tick_cpu_device, cpu).evtdev ? -EAGAIN : -EBUSY;
 }
 
 /*
- * Called after a notify add to make devices available which were
- * released from the notifier call.
+ * SMP function call to unbind a device
  */
-static void clockevents_notify_released(void)
+static void __clockevents_unbind(void *arg)
 {
-	struct clock_event_device *dev;
+	struct ce_unbind *cu = arg;
+	int res;
+
+	raw_spin_lock(&clockevents_lock);
+	res = __clockevents_try_unbind(cu->ce, smp_processor_id());
+	if (res == -EAGAIN)
+		res = clockevents_replace(cu->ce);
+	cu->res = res;
+	raw_spin_unlock(&clockevents_lock);
+}
 
-	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);
-	}
+/*
+ * Issues smp function call to unbind a per cpu device. Called with
+ * clockevents_mutex held.
+ */
+static int clockevents_unbind(struct clock_event_device *ced, int cpu)
+{
+	struct ce_unbind cu = { .ce = ced, .res = -ENODEV };
+
+	smp_call_function_single(cpu, __clockevents_unbind, &cu, 1);
+	return cu.res;
 }
 
+/*
+ * Unbind a clockevents device.
+ */
+int clockevents_unbind_device(struct clock_event_device *ced, int cpu)
+{
+	int ret;
+
+	mutex_lock(&clockevents_mutex);
+	ret = clockevents_unbind(ced, cpu);
+	mutex_unlock(&clockevents_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clockevents_unbind);
+
 /**
  * clockevents_register_device - register a clock event device
  * @dev:	device to register
@@ -290,7 +353,7 @@ void clockevents_register_device(struct clock_event_device *dev)
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
 	list_add(&dev->list, &clockevent_devices);
-	clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+	tick_check_new_device(dev);
 	clockevents_notify_released();
 
 	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
@@ -386,6 +449,7 @@ void clockevents_exchange_device(struct clock_event_device *old,
 	 * released list and do a notify add later.
 	 */
 	if (old) {
+		module_put(old->owner);
 		clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
 		list_del(&old->list);
 		list_add(&old->list, &clockevents_released);
@@ -433,10 +497,36 @@ void clockevents_notify(unsigned long reason, void *arg)
 	int cpu;
 
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
-	clockevents_do_notify(reason, arg);
 
 	switch (reason) {
+	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
+	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
+	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
+		tick_broadcast_on_off(reason, arg);
+		break;
+
+	case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
+	case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
+		tick_broadcast_oneshot_control(reason);
+		break;
+
+	case CLOCK_EVT_NOTIFY_CPU_DYING:
+		tick_handover_do_timer(arg);
+		break;
+
+	case CLOCK_EVT_NOTIFY_SUSPEND:
+		tick_suspend();
+		tick_suspend_broadcast();
+		break;
+
+	case CLOCK_EVT_NOTIFY_RESUME:
+		tick_resume();
+		break;
+
 	case CLOCK_EVT_NOTIFY_CPU_DEAD:
+		tick_shutdown_broadcast_oneshot(arg);
+		tick_shutdown_broadcast(arg);
+		tick_shutdown(arg);
 		/*
 		 * Unregister the clock event devices which were
 		 * released from the users in the notify chain.
@@ -462,4 +552,123 @@ void clockevents_notify(unsigned long reason, void *arg)
 	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
 }
 EXPORT_SYMBOL_GPL(clockevents_notify);
+
+#ifdef CONFIG_SYSFS
+struct bus_type clockevents_subsys = {
+	.name		= "clockevents",
+	.dev_name       = "clockevent",
+};
+
+static DEFINE_PER_CPU(struct device, tick_percpu_dev);
+static struct tick_device *tick_get_tick_dev(struct device *dev);
+
+static ssize_t sysfs_show_current_tick_dev(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	struct tick_device *td;
+	ssize_t count = 0;
+
+	raw_spin_lock_irq(&clockevents_lock);
+	td = tick_get_tick_dev(dev);
+	if (td && td->evtdev)
+		count = snprintf(buf, PAGE_SIZE, "%s\n", td->evtdev->name);
+	raw_spin_unlock_irq(&clockevents_lock);
+	return count;
+}
+static DEVICE_ATTR(current_device, 0444, sysfs_show_current_tick_dev, NULL);
+
+/* We don't support the abomination of removable broadcast devices */
+static ssize_t sysfs_unbind_tick_dev(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	char name[CS_NAME_LEN];
+	size_t ret = sysfs_get_uname(buf, name, count);
+	struct clock_event_device *ce;
+
+	if (ret < 0)
+		return ret;
+
+	ret = -ENODEV;
+	mutex_lock(&clockevents_mutex);
+	raw_spin_lock_irq(&clockevents_lock);
+	list_for_each_entry(ce, &clockevent_devices, list) {
+		if (!strcmp(ce->name, name)) {
+			ret = __clockevents_try_unbind(ce, dev->id);
+			break;
+		}
+	}
+	raw_spin_unlock_irq(&clockevents_lock);
+	/*
+	 * We hold clockevents_mutex, so ce can't go away
+	 */
+	if (ret == -EAGAIN)
+		ret = clockevents_unbind(ce, dev->id);
+	mutex_unlock(&clockevents_mutex);
+	return ret ? ret : count;
+}
+static DEVICE_ATTR(unbind_device, 0200, NULL, sysfs_unbind_tick_dev);
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+static struct device tick_bc_dev = {
+	.init_name	= "broadcast",
+	.id		= 0,
+	.bus		= &clockevents_subsys,
+};
+
+static struct tick_device *tick_get_tick_dev(struct device *dev)
+{
+	return dev == &tick_bc_dev ? tick_get_broadcast_device() :
+		&per_cpu(tick_cpu_device, dev->id);
+}
+
+static __init int tick_broadcast_init_sysfs(void)
+{
+	int err = device_register(&tick_bc_dev);
+
+	if (!err)
+		err = device_create_file(&tick_bc_dev, &dev_attr_current_device);
+	return err;
+}
+#else
+static struct tick_device *tick_get_tick_dev(struct device *dev)
+{
+	return &per_cpu(tick_cpu_device, dev->id);
+}
+static inline int tick_broadcast_init_sysfs(void) { return 0; }
 #endif
+
+static int __init tick_init_sysfs(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct device *dev = &per_cpu(tick_percpu_dev, cpu);
+		int err;
+
+		dev->id = cpu;
+		dev->bus = &clockevents_subsys;
+		err = device_register(dev);
+		if (!err)
+			err = device_create_file(dev, &dev_attr_current_device);
+		if (!err)
+			err = device_create_file(dev, &dev_attr_unbind_device);
+		if (err)
+			return err;
+	}
+	return tick_broadcast_init_sysfs();
+}
+
+static int __init clockevents_init_sysfs(void)
+{
+	int err = subsys_system_register(&clockevents_subsys, NULL);
+
+	if (!err)
+		err = tick_init_sysfs();
+	return err;
+}
+device_initcall(clockevents_init_sysfs);
+#endif /* SYSFS */
+
+#endif /* GENERIC_CLOCK_EVENTS */
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index c9583382141a..50a8736757f3 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -31,6 +31,8 @@
 #include <linux/tick.h>
 #include <linux/kthread.h>
 
+#include "tick-internal.h"
+
 void timecounter_init(struct timecounter *tc,
 		      const struct cyclecounter *cc,
 		      u64 start_tstamp)
@@ -174,11 +176,12 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 maxsec)
 static struct clocksource *curr_clocksource;
 static LIST_HEAD(clocksource_list);
 static DEFINE_MUTEX(clocksource_mutex);
-static char override_name[32];
+static char override_name[CS_NAME_LEN];
 static int finished_booting;
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 static void clocksource_watchdog_work(struct work_struct *work);
+static void clocksource_select(void);
 
 static LIST_HEAD(watchdog_list);
 static struct clocksource *watchdog;
@@ -299,13 +302,30 @@ static void clocksource_watchdog(unsigned long data)
 		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
 		    (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) &&
 		    (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) {
+			/* Mark it valid for high-res. */
 			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+
+			/*
+			 * clocksource_done_booting() will sort it if
+			 * finished_booting is not set yet.
+			 */
+			if (!finished_booting)
+				continue;
+
 			/*
-			 * We just marked the clocksource as highres-capable,
-			 * notify the rest of the system as well so that we
-			 * transition into high-res mode:
+			 * If this is not the current clocksource let
+			 * the watchdog thread reselect it. Due to the
+			 * change to high res this clocksource might
+			 * be preferred now. If it is the current
+			 * clocksource let the tick code know about
+			 * that change.
 			 */
-			tick_clock_notify();
+			if (cs != curr_clocksource) {
+				cs->flags |= CLOCK_SOURCE_RESELECT;
+				schedule_work(&watchdog_work);
+			} else {
+				tick_clock_notify();
+			}
 		}
 	}
 
@@ -388,44 +408,39 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 
 static void clocksource_dequeue_watchdog(struct clocksource *cs)
 {
-	struct clocksource *tmp;
 	unsigned long flags;
 
 	spin_lock_irqsave(&watchdog_lock, flags);
-	if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
-		/* cs is a watched clocksource. */
-		list_del_init(&cs->wd_list);
-	} else if (cs == watchdog) {
-		/* Reset watchdog cycles */
-		clocksource_reset_watchdog();
-		/* Current watchdog is removed. Find an alternative. */
-		watchdog = NULL;
-		list_for_each_entry(tmp, &clocksource_list, list) {
-			if (tmp == cs || tmp->flags & CLOCK_SOURCE_MUST_VERIFY)
-				continue;
-			if (!watchdog || tmp->rating > watchdog->rating)
-				watchdog = tmp;
+	if (cs != watchdog) {
+		if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
+			/* cs is a watched clocksource. */
+			list_del_init(&cs->wd_list);
+			/* Check if the watchdog timer needs to be stopped. */
+			clocksource_stop_watchdog();
 		}
 	}
-	cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
-	/* Check if the watchdog timer needs to be stopped. */
-	clocksource_stop_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
-static int clocksource_watchdog_kthread(void *data)
+static int __clocksource_watchdog_kthread(void)
 {
 	struct clocksource *cs, *tmp;
 	unsigned long flags;
 	LIST_HEAD(unstable);
+	int select = 0;
 
-	mutex_lock(&clocksource_mutex);
 	spin_lock_irqsave(&watchdog_lock, flags);
-	list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list)
+	list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
 		if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
 			list_del_init(&cs->wd_list);
 			list_add(&cs->wd_list, &unstable);
+			select = 1;
 		}
+		if (cs->flags & CLOCK_SOURCE_RESELECT) {
+			cs->flags &= ~CLOCK_SOURCE_RESELECT;
+			select = 1;
+		}
+	}
 	/* Check if the watchdog timer needs to be stopped. */
 	clocksource_stop_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
@@ -435,10 +450,23 @@ static int clocksource_watchdog_kthread(void *data)
 		list_del_init(&cs->wd_list);
 		__clocksource_change_rating(cs, 0);
 	}
+	return select;
+}
+
+static int clocksource_watchdog_kthread(void *data)
+{
+	mutex_lock(&clocksource_mutex);
+	if (__clocksource_watchdog_kthread())
+		clocksource_select();
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
 
+static bool clocksource_is_watchdog(struct clocksource *cs)
+{
+	return cs == watchdog;
+}
+
 #else /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
 static void clocksource_enqueue_watchdog(struct clocksource *cs)
@@ -449,7 +477,8 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 
 static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
 static inline void clocksource_resume_watchdog(void) { }
-static inline int clocksource_watchdog_kthread(void *data) { return 0; }
+static inline int __clocksource_watchdog_kthread(void) { return 0; }
+static bool clocksource_is_watchdog(struct clocksource *cs) { return false; }
 
 #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
@@ -553,24 +582,42 @@ static u64 clocksource_max_deferment(struct clocksource *cs)
 
 #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
 
-/**
- * clocksource_select - Select the best clocksource available
- *
- * Private function. Must hold clocksource_mutex when called.
- *
- * Select the clocksource with the best rating, or the clocksource,
- * which is selected by userspace override.
- */
-static void clocksource_select(void)
+static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur)
 {
-	struct clocksource *best, *cs;
+	struct clocksource *cs;
 
 	if (!finished_booting || list_empty(&clocksource_list))
+		return NULL;
+
+	/*
+	 * We pick the clocksource with the highest rating. If oneshot
+	 * mode is active, we pick the highres valid clocksource with
+	 * the best rating.
+	 */
+	list_for_each_entry(cs, &clocksource_list, list) {
+		if (skipcur && cs == curr_clocksource)
+			continue;
+		if (oneshot && !(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES))
+			continue;
+		return cs;
+	}
+	return NULL;
+}
+
+static void __clocksource_select(bool skipcur)
+{
+	bool oneshot = tick_oneshot_mode_active();
+	struct clocksource *best, *cs;
+
+	/* Find the best suitable clocksource */
+	best = clocksource_find_best(oneshot, skipcur);
+	if (!best)
 		return;
-	/* First clocksource on the list has the best rating. */
-	best = list_first_entry(&clocksource_list, struct clocksource, list);
+
 	/* Check for the override clocksource. */
 	list_for_each_entry(cs, &clocksource_list, list) {
+		if (skipcur && cs == curr_clocksource)
+			continue;
 		if (strcmp(cs->name, override_name) != 0)
 			continue;
 		/*
@@ -578,8 +625,7 @@ static void clocksource_select(void)
 		 * capable clocksource if the tick code is in oneshot
 		 * mode (highres or nohz)
 		 */
-		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
-		    tick_oneshot_mode_active()) {
+		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && oneshot) {
 			/* Override clocksource cannot be used. */
 			printk(KERN_WARNING "Override clocksource %s is not "
 			       "HRT compatible. Cannot switch while in "
@@ -590,16 +636,35 @@ static void clocksource_select(void)
 			best = cs;
 		break;
 	}
-	if (curr_clocksource != best) {
-		printk(KERN_INFO "Switching to clocksource %s\n", best->name);
+
+	if (curr_clocksource != best && !timekeeping_notify(best)) {
+		pr_info("Switched to clocksource %s\n", best->name);
 		curr_clocksource = best;
-		timekeeping_notify(curr_clocksource);
 	}
 }
 
+/**
+ * clocksource_select - Select the best clocksource available
+ *
+ * Private function. Must hold clocksource_mutex when called.
+ *
+ * Select the clocksource with the best rating, or the clocksource,
+ * which is selected by userspace override.
+ */
+static void clocksource_select(void)
+{
+	return __clocksource_select(false);
+}
+
+static void clocksource_select_fallback(void)
+{
+	return __clocksource_select(true);
+}
+
 #else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */
 
 static inline void clocksource_select(void) { }
+static inline void clocksource_select_fallback(void) { }
 
 #endif
 
@@ -614,16 +679,11 @@ static int __init clocksource_done_booting(void)
 {
 	mutex_lock(&clocksource_mutex);
 	curr_clocksource = clocksource_default_clock();
-	mutex_unlock(&clocksource_mutex);
-
 	finished_booting = 1;
-
 	/*
 	 * Run the watchdog first to eliminate unstable clock sources
 	 */
-	clocksource_watchdog_kthread(NULL);
-
-	mutex_lock(&clocksource_mutex);
+	__clocksource_watchdog_kthread();
 	clocksource_select();
 	mutex_unlock(&clocksource_mutex);
 	return 0;
@@ -756,7 +816,6 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating)
 	list_del(&cs->list);
 	cs->rating = rating;
 	clocksource_enqueue(cs);
-	clocksource_select();
 }
 
 /**
@@ -768,21 +827,47 @@ void clocksource_change_rating(struct clocksource *cs, int rating)
 {
 	mutex_lock(&clocksource_mutex);
 	__clocksource_change_rating(cs, rating);
+	clocksource_select();
 	mutex_unlock(&clocksource_mutex);
 }
 EXPORT_SYMBOL(clocksource_change_rating);
 
+/*
+ * Unbind clocksource @cs. Called with clocksource_mutex held
+ */
+static int clocksource_unbind(struct clocksource *cs)
+{
+	/*
+	 * I really can't convince myself to support this on hardware
+	 * designed by lobotomized monkeys.
+	 */
+	if (clocksource_is_watchdog(cs))
+		return -EBUSY;
+
+	if (cs == curr_clocksource) {
+		/* Select and try to install a replacement clock source */
+		clocksource_select_fallback();
+		if (curr_clocksource == cs)
+			return -EBUSY;
+	}
+	clocksource_dequeue_watchdog(cs);
+	list_del_init(&cs->list);
+	return 0;
+}
+
 /**
  * clocksource_unregister - remove a registered clocksource
  * @cs:	clocksource to be unregistered
  */
-void clocksource_unregister(struct clocksource *cs)
+int clocksource_unregister(struct clocksource *cs)
 {
+	int ret = 0;
+
 	mutex_lock(&clocksource_mutex);
-	clocksource_dequeue_watchdog(cs);
-	list_del(&cs->list);
-	clocksource_select();
+	if (!list_empty(&cs->list))
+		ret = clocksource_unbind(cs);
 	mutex_unlock(&clocksource_mutex);
+	return ret;
 }
 EXPORT_SYMBOL(clocksource_unregister);
 
@@ -808,6 +893,23 @@ sysfs_show_current_clocksources(struct device *dev,
 	return count;
 }
 
+size_t sysfs_get_uname(const char *buf, char *dst, size_t cnt)
+{
+	size_t ret = cnt;
+
+	/* strings from sysfs write are not 0 terminated! */
+	if (!cnt || cnt >= CS_NAME_LEN)
+		return -EINVAL;
+
+	/* strip of \n: */
+	if (buf[cnt-1] == '\n')
+		cnt--;
+	if (cnt > 0)
+		memcpy(dst, buf, cnt);
+	dst[cnt] = 0;
+	return ret;
+}
+
 /**
  * sysfs_override_clocksource - interface for manually overriding clocksource
  * @dev:	unused
@@ -822,22 +924,13 @@ static ssize_t sysfs_override_clocksource(struct device *dev,
 					  struct device_attribute *attr,
 					  const char *buf, size_t count)
 {
-	size_t ret = count;
-
-	/* strings from sysfs write are not 0 terminated! */
-	if (count >= sizeof(override_name))
-		return -EINVAL;
-
-	/* strip of \n: */
-	if (buf[count-1] == '\n')
-		count--;
+	size_t ret;
 
 	mutex_lock(&clocksource_mutex);
 
-	if (count > 0)
-		memcpy(override_name, buf, count);
-	override_name[count] = 0;
-	clocksource_select();
+	ret = sysfs_get_uname(buf, override_name, count);
+	if (ret >= 0)
+		clocksource_select();
 
 	mutex_unlock(&clocksource_mutex);
 
@@ -845,6 +938,40 @@ static ssize_t sysfs_override_clocksource(struct device *dev,
 }
 
 /**
+ * sysfs_unbind_current_clocksource - interface for manually unbinding clocksource
+ * @dev:	unused
+ * @attr:	unused
+ * @buf:	unused
+ * @count:	length of buffer
+ *
+ * Takes input from sysfs interface for manually unbinding a clocksource.
+ */
+static ssize_t sysfs_unbind_clocksource(struct device *dev,
+					struct device_attribute *attr,
+					const char *buf, size_t count)
+{
+	struct clocksource *cs;
+	char name[CS_NAME_LEN];
+	size_t ret;
+
+	ret = sysfs_get_uname(buf, name, count);
+	if (ret < 0)
+		return ret;
+
+	ret = -ENODEV;
+	mutex_lock(&clocksource_mutex);
+	list_for_each_entry(cs, &clocksource_list, list) {
+		if (strcmp(cs->name, name))
+			continue;
+		ret = clocksource_unbind(cs);
+		break;
+	}
+	mutex_unlock(&clocksource_mutex);
+
+	return ret ? ret : count;
+}
+
+/**
  * sysfs_show_available_clocksources - sysfs interface for listing clocksource
  * @dev:	unused
  * @attr:	unused
@@ -886,6 +1013,8 @@ sysfs_show_available_clocksources(struct device *dev,
 static DEVICE_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources,
 		   sysfs_override_clocksource);
 
+static DEVICE_ATTR(unbind_clocksource, 0200, NULL, sysfs_unbind_clocksource);
+
 static DEVICE_ATTR(available_clocksource, 0444,
 		   sysfs_show_available_clocksources, NULL);
 
@@ -910,6 +1039,9 @@ static int __init init_clocksource_sysfs(void)
 				&device_clocksource,
 				&dev_attr_current_clocksource);
 	if (!error)
+		error = device_create_file(&device_clocksource,
+					   &dev_attr_unbind_clocksource);
+	if (!error)
 		error = device_create_file(
 				&device_clocksource,
 				&dev_attr_available_clocksource);
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
new file mode 100644
index 000000000000..a326f27d7f09
--- /dev/null
+++ b/kernel/time/sched_clock.c
@@ -0,0 +1,212 @@
+/*
+ * sched_clock.c: support for extending counters to full 64-bit ns counter
+ *
+ * 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/clocksource.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+#include <linux/sched.h>
+#include <linux/syscore_ops.h>
+#include <linux/timer.h>
+#include <linux/sched_clock.h>
+
+struct clock_data {
+	u64 epoch_ns;
+	u32 epoch_cyc;
+	u32 epoch_cyc_copy;
+	unsigned long rate;
+	u32 mult;
+	u32 shift;
+	bool suspended;
+};
+
+static void sched_clock_poll(unsigned long wrap_ticks);
+static DEFINE_TIMER(sched_clock_timer, sched_clock_poll, 0, 0);
+static int irqtime = -1;
+
+core_param(irqtime, irqtime, int, 0400);
+
+static struct clock_data cd = {
+	.mult	= NSEC_PER_SEC / HZ,
+};
+
+static u32 __read_mostly sched_clock_mask = 0xffffffff;
+
+static u32 notrace jiffy_sched_clock_read(void)
+{
+	return (u32)(jiffies - INITIAL_JIFFIES);
+}
+
+static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
+
+static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
+{
+	return (cyc * mult) >> shift;
+}
+
+static unsigned long long notrace sched_clock_32(void)
+{
+	u64 epoch_ns;
+	u32 epoch_cyc;
+	u32 cyc;
+
+	if (cd.suspended)
+		return cd.epoch_ns;
+
+	/*
+	 * Load the epoch_cyc and epoch_ns atomically.  We do this by
+	 * ensuring that we always write epoch_cyc, epoch_ns and
+	 * epoch_cyc_copy in strict order, and read them in strict order.
+	 * If epoch_cyc and epoch_cyc_copy are not equal, then we're in
+	 * the middle of an update, and we should repeat the load.
+	 */
+	do {
+		epoch_cyc = cd.epoch_cyc;
+		smp_rmb();
+		epoch_ns = cd.epoch_ns;
+		smp_rmb();
+	} while (epoch_cyc != cd.epoch_cyc_copy);
+
+	cyc = read_sched_clock();
+	cyc = (cyc - epoch_cyc) & sched_clock_mask;
+	return epoch_ns + cyc_to_ns(cyc, cd.mult, cd.shift);
+}
+
+/*
+ * Atomically update the sched_clock epoch.
+ */
+static void notrace update_sched_clock(void)
+{
+	unsigned long flags;
+	u32 cyc;
+	u64 ns;
+
+	cyc = read_sched_clock();
+	ns = cd.epoch_ns +
+		cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
+			  cd.mult, cd.shift);
+	/*
+	 * Write epoch_cyc and epoch_ns in a way that the update is
+	 * detectable in cyc_to_fixed_sched_clock().
+	 */
+	raw_local_irq_save(flags);
+	cd.epoch_cyc_copy = cyc;
+	smp_wmb();
+	cd.epoch_ns = ns;
+	smp_wmb();
+	cd.epoch_cyc = cyc;
+	raw_local_irq_restore(flags);
+}
+
+static void sched_clock_poll(unsigned long wrap_ticks)
+{
+	mod_timer(&sched_clock_timer, round_jiffies(jiffies + wrap_ticks));
+	update_sched_clock();
+}
+
+void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
+{
+	unsigned long r, w;
+	u64 res, wrap;
+	char r_unit;
+
+	if (cd.rate > rate)
+		return;
+
+	BUG_ON(bits > 32);
+	WARN_ON(!irqs_disabled());
+	read_sched_clock = read;
+	sched_clock_mask = (1 << bits) - 1;
+	cd.rate = rate;
+
+	/* calculate the mult/shift to convert counter ticks to ns. */
+	clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 0);
+
+	r = rate;
+	if (r >= 4000000) {
+		r /= 1000000;
+		r_unit = 'M';
+	} else if (r >= 1000) {
+		r /= 1000;
+		r_unit = 'k';
+	} else
+		r_unit = ' ';
+
+	/* calculate how many ns until we wrap */
+	wrap = cyc_to_ns((1ULL << bits) - 1, cd.mult, cd.shift);
+	do_div(wrap, NSEC_PER_MSEC);
+	w = wrap;
+
+	/* calculate the ns resolution of this counter */
+	res = cyc_to_ns(1ULL, cd.mult, cd.shift);
+	pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lums\n",
+		bits, r, r_unit, res, w);
+
+	/*
+	 * Start the timer to keep sched_clock() properly updated and
+	 * sets the initial epoch.
+	 */
+	sched_clock_timer.data = msecs_to_jiffies(w - (w / 10));
+	update_sched_clock();
+
+	/*
+	 * Ensure that sched_clock() starts off at 0ns
+	 */
+	cd.epoch_ns = 0;
+
+	/* Enable IRQ time accounting if we have a fast enough sched_clock */
+	if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
+		enable_sched_clock_irqtime();
+
+	pr_debug("Registered %pF as sched_clock source\n", read);
+}
+
+unsigned long long __read_mostly (*sched_clock_func)(void) = sched_clock_32;
+
+unsigned long long notrace sched_clock(void)
+{
+	return sched_clock_func();
+}
+
+void __init sched_clock_postinit(void)
+{
+	/*
+	 * If no sched_clock function has been provided at that point,
+	 * make it the final one one.
+	 */
+	if (read_sched_clock == jiffy_sched_clock_read)
+		setup_sched_clock(jiffy_sched_clock_read, 32, HZ);
+
+	sched_clock_poll(sched_clock_timer.data);
+}
+
+static int sched_clock_suspend(void)
+{
+	sched_clock_poll(sched_clock_timer.data);
+	cd.suspended = true;
+	return 0;
+}
+
+static void sched_clock_resume(void)
+{
+	cd.epoch_cyc = read_sched_clock();
+	cd.epoch_cyc_copy = cd.epoch_cyc;
+	cd.suspended = false;
+}
+
+static struct syscore_ops sched_clock_ops = {
+	.suspend = sched_clock_suspend,
+	.resume = sched_clock_resume,
+};
+
+static int __init sched_clock_syscore_init(void)
+{
+	register_syscore_ops(&sched_clock_ops);
+	return 0;
+}
+device_initcall(sched_clock_syscore_init);
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 20d6fba70652..6d3f91631de6 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -19,6 +19,7 @@
 #include <linux/profile.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/module.h>
 
 #include "tick-internal.h"
 
@@ -29,6 +30,7 @@
 
 static struct tick_device tick_broadcast_device;
 static cpumask_var_t tick_broadcast_mask;
+static cpumask_var_t tick_broadcast_on;
 static cpumask_var_t tmpmask;
 static DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
 static int tick_broadcast_force;
@@ -64,17 +66,34 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc)
 /*
  * Check, if the device can be utilized as broadcast device:
  */
-int tick_check_broadcast_device(struct clock_event_device *dev)
+static bool tick_check_broadcast_device(struct clock_event_device *curdev,
+					struct clock_event_device *newdev)
+{
+	if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) ||
+	    (newdev->features & CLOCK_EVT_FEAT_C3STOP))
+		return false;
+
+	if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT &&
+	    !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
+		return false;
+
+	return !curdev || newdev->rating > curdev->rating;
+}
+
+/*
+ * Conditionally install/replace broadcast device
+ */
+void tick_install_broadcast_device(struct clock_event_device *dev)
 {
 	struct clock_event_device *cur = tick_broadcast_device.evtdev;
 
-	if ((dev->features & CLOCK_EVT_FEAT_DUMMY) ||
-	    (tick_broadcast_device.evtdev &&
-	     tick_broadcast_device.evtdev->rating >= dev->rating) ||
-	     (dev->features & CLOCK_EVT_FEAT_C3STOP))
-		return 0;
+	if (!tick_check_broadcast_device(cur, dev))
+		return;
 
-	clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
+	if (!try_module_get(dev->owner))
+		return;
+
+	clockevents_exchange_device(cur, dev);
 	if (cur)
 		cur->event_handler = clockevents_handle_noop;
 	tick_broadcast_device.evtdev = dev;
@@ -90,7 +109,6 @@ int tick_check_broadcast_device(struct clock_event_device *dev)
 	 */
 	if (dev->features & CLOCK_EVT_FEAT_ONESHOT)
 		tick_clock_notify();
-	return 1;
 }
 
 /*
@@ -123,8 +141,9 @@ static void tick_device_setup_broadcast_func(struct clock_event_device *dev)
  */
 int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
 {
+	struct clock_event_device *bc = tick_broadcast_device.evtdev;
 	unsigned long flags;
-	int ret = 0;
+	int ret;
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
@@ -138,20 +157,59 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
 		dev->event_handler = tick_handle_periodic;
 		tick_device_setup_broadcast_func(dev);
 		cpumask_set_cpu(cpu, tick_broadcast_mask);
-		tick_broadcast_start_periodic(tick_broadcast_device.evtdev);
+		tick_broadcast_start_periodic(bc);
 		ret = 1;
 	} else {
 		/*
-		 * When the new device is not affected by the stop
-		 * feature and the cpu is marked in the broadcast mask
-		 * then clear the broadcast bit.
+		 * Clear the broadcast bit for this cpu if the
+		 * device is not power state affected.
 		 */
-		if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) {
-			int cpu = smp_processor_id();
+		if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
 			cpumask_clear_cpu(cpu, tick_broadcast_mask);
-			tick_broadcast_clear_oneshot(cpu);
-		} else {
+		else
 			tick_device_setup_broadcast_func(dev);
+
+		/*
+		 * Clear the broadcast bit if the CPU is not in
+		 * periodic broadcast on state.
+		 */
+		if (!cpumask_test_cpu(cpu, tick_broadcast_on))
+			cpumask_clear_cpu(cpu, tick_broadcast_mask);
+
+		switch (tick_broadcast_device.mode) {
+		case TICKDEV_MODE_ONESHOT:
+			/*
+			 * If the system is in oneshot mode we can
+			 * unconditionally clear the oneshot mask bit,
+			 * because the CPU is running and therefore
+			 * not in an idle state which causes the power
+			 * state affected device to stop. Let the
+			 * caller initialize the device.
+			 */
+			tick_broadcast_clear_oneshot(cpu);
+			ret = 0;
+			break;
+
+		case TICKDEV_MODE_PERIODIC:
+			/*
+			 * If the system is in periodic mode, check
+			 * whether the broadcast device can be
+			 * switched off now.
+			 */
+			if (cpumask_empty(tick_broadcast_mask) && bc)
+				clockevents_shutdown(bc);
+			/*
+			 * If we kept the cpu in the broadcast mask,
+			 * tell the caller to leave the per cpu device
+			 * in shutdown state. The periodic interrupt
+			 * is delivered by the broadcast device.
+			 */
+			ret = cpumask_test_cpu(cpu, tick_broadcast_mask);
+			break;
+		default:
+			/* Nothing to do */
+			ret = 0;
+			break;
 		}
 	}
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
@@ -281,6 +339,7 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
 	switch (*reason) {
 	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
 	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
+		cpumask_set_cpu(cpu, tick_broadcast_on);
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) {
 			if (tick_broadcast_device.mode ==
 			    TICKDEV_MODE_PERIODIC)
@@ -290,8 +349,12 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
 			tick_broadcast_force = 1;
 		break;
 	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
-		if (!tick_broadcast_force &&
-		    cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) {
+		if (tick_broadcast_force)
+			break;
+		cpumask_clear_cpu(cpu, tick_broadcast_on);
+		if (!tick_device_is_functional(dev))
+			break;
+		if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) {
 			if (tick_broadcast_device.mode ==
 			    TICKDEV_MODE_PERIODIC)
 				tick_setup_periodic(dev, 0);
@@ -349,6 +412,7 @@ void tick_shutdown_broadcast(unsigned int *cpup)
 
 	bc = tick_broadcast_device.evtdev;
 	cpumask_clear_cpu(cpu, tick_broadcast_mask);
+	cpumask_clear_cpu(cpu, tick_broadcast_on);
 
 	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
 		if (bc && cpumask_empty(tick_broadcast_mask))
@@ -475,7 +539,15 @@ void tick_check_oneshot_broadcast(int cpu)
 	if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) {
 		struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
 
-		clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT);
+		/*
+		 * We might be in the middle of switching over from
+		 * periodic to oneshot. If the CPU has not yet
+		 * switched over, leave the device alone.
+		 */
+		if (td->mode == TICKDEV_MODE_ONESHOT) {
+			clockevents_set_mode(td->evtdev,
+					     CLOCK_EVT_MODE_ONESHOT);
+		}
 	}
 }
 
@@ -522,6 +594,13 @@ again:
 	cpumask_clear(tick_broadcast_force_mask);
 
 	/*
+	 * Sanity check. Catch the case where we try to broadcast to
+	 * offline cpus.
+	 */
+	if (WARN_ON_ONCE(!cpumask_subset(tmpmask, cpu_online_mask)))
+		cpumask_and(tmpmask, tmpmask, cpu_online_mask);
+
+	/*
 	 * Wakeup the cpus which have an expired event.
 	 */
 	tick_do_broadcast(tmpmask);
@@ -761,10 +840,12 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
 	/*
-	 * Clear the broadcast mask flag for the dead cpu, but do not
-	 * stop the broadcast device!
+	 * Clear the broadcast masks for the dead cpu, but do not stop
+	 * the broadcast device!
 	 */
 	cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+	cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
+	cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
 
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
@@ -792,6 +873,7 @@ bool tick_broadcast_oneshot_available(void)
 void __init tick_broadcast_init(void)
 {
 	zalloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&tick_broadcast_on, GFP_NOWAIT);
 	zalloc_cpumask_var(&tmpmask, GFP_NOWAIT);
 #ifdef CONFIG_TICK_ONESHOT
 	zalloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT);
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 5d3fb100bc06..64522ecdfe0e 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -18,6 +18,7 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
+#include <linux/module.h>
 
 #include <asm/irq_regs.h>
 
@@ -33,7 +34,6 @@ 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;
-static DEFINE_RAW_SPINLOCK(tick_device_lock);
 
 /*
  * Debugging: see timer_list.c
@@ -194,7 +194,8 @@ static void tick_setup_device(struct tick_device *td,
 	 * 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.
+	 * way. This function also returns !=0 when we keep the
+	 * current active broadcast state for this CPU.
 	 */
 	if (tick_device_uses_broadcast(newdev, cpu))
 		return;
@@ -205,17 +206,75 @@ static void tick_setup_device(struct tick_device *td,
 		tick_setup_oneshot(newdev, handler, next_event);
 }
 
+void tick_install_replacement(struct clock_event_device *newdev)
+{
+	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	int cpu = smp_processor_id();
+
+	clockevents_exchange_device(td->evtdev, newdev);
+	tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
+	if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
+		tick_oneshot_notify();
+}
+
+static bool tick_check_percpu(struct clock_event_device *curdev,
+			      struct clock_event_device *newdev, int cpu)
+{
+	if (!cpumask_test_cpu(cpu, newdev->cpumask))
+		return false;
+	if (cpumask_equal(newdev->cpumask, cpumask_of(cpu)))
+		return true;
+	/* Check if irq affinity can be set */
+	if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq))
+		return false;
+	/* Prefer an existing cpu local device */
+	if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
+		return false;
+	return true;
+}
+
+static bool tick_check_preferred(struct clock_event_device *curdev,
+				 struct clock_event_device *newdev)
+{
+	/* Prefer oneshot capable device */
+	if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) {
+		if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT))
+			return false;
+		if (tick_oneshot_mode_active())
+			return false;
+	}
+
+	/*
+	 * Use the higher rated one, but prefer a CPU local device with a lower
+	 * rating than a non-CPU local device
+	 */
+	return !curdev ||
+		newdev->rating > curdev->rating ||
+	       !cpumask_equal(curdev->cpumask, newdev->cpumask);
+}
+
+/*
+ * Check whether the new device is a better fit than curdev. curdev
+ * can be NULL !
+ */
+bool tick_check_replacement(struct clock_event_device *curdev,
+			    struct clock_event_device *newdev)
+{
+	if (tick_check_percpu(curdev, newdev, smp_processor_id()))
+		return false;
+
+	return tick_check_preferred(curdev, newdev);
+}
+
 /*
- * Check, if the new registered device should be used.
+ * Check, if the new registered device should be used. Called with
+ * clockevents_lock held and interrupts disabled.
  */
-static int tick_check_new_device(struct clock_event_device *newdev)
+void 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;
-
-	raw_spin_lock_irqsave(&tick_device_lock, flags);
+	int cpu;
 
 	cpu = smp_processor_id();
 	if (!cpumask_test_cpu(cpu, newdev->cpumask))
@@ -225,40 +284,15 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 	curdev = td->evtdev;
 
 	/* cpu local device ? */
-	if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) {
-
-		/*
-		 * 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 (!tick_check_percpu(curdev, newdev, cpu))
+		goto out_bc;
 
-		/*
-		 * If we have a cpu local device already, do not replace it
-		 * by a non cpu local device
-		 */
-		if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
-			goto out_bc;
-	}
+	/* Preference decision */
+	if (!tick_check_preferred(curdev, newdev))
+		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;
-	}
+	if (!try_module_get(newdev->owner))
+		return;
 
 	/*
 	 * Replace the eventually existing device by the new
@@ -273,20 +307,13 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 	tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
 	if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
 		tick_oneshot_notify();
-
-	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
-	return NOTIFY_STOP;
+	return;
 
 out_bc:
 	/*
 	 * Can the new device be used as a broadcast device ?
 	 */
-	if (tick_check_broadcast_device(newdev))
-		ret = NOTIFY_STOP;
-
-	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
-
-	return ret;
+	tick_install_broadcast_device(newdev);
 }
 
 /*
@@ -294,7 +321,7 @@ out_bc:
  *
  * Called with interrupts disabled.
  */
-static void tick_handover_do_timer(int *cpup)
+void tick_handover_do_timer(int *cpup)
 {
 	if (*cpup == tick_do_timer_cpu) {
 		int cpu = cpumask_first(cpu_online_mask);
@@ -311,13 +338,11 @@ static void tick_handover_do_timer(int *cpup)
  * access the hardware device itself.
  * We just set the mode and remove it from the lists.
  */
-static void tick_shutdown(unsigned int *cpup)
+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;
 
-	raw_spin_lock_irqsave(&tick_device_lock, flags);
 	td->mode = TICKDEV_MODE_PERIODIC;
 	if (dev) {
 		/*
@@ -329,26 +354,20 @@ static void tick_shutdown(unsigned int *cpup)
 		dev->event_handler = clockevents_handle_noop;
 		td->evtdev = NULL;
 	}
-	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
-static void tick_suspend(void)
+void tick_suspend(void)
 {
 	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&tick_device_lock, flags);
 	clockevents_shutdown(td->evtdev);
-	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
-static void tick_resume(void)
+void tick_resume(void)
 {
 	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
-	unsigned long flags;
 	int broadcast = tick_resume_broadcast();
 
-	raw_spin_lock_irqsave(&tick_device_lock, flags);
 	clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME);
 
 	if (!broadcast) {
@@ -357,68 +376,12 @@ static void tick_resume(void)
 		else
 			tick_resume_oneshot();
 	}
-	raw_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:
-	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
-		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_DYING:
-		tick_handover_do_timer(dev);
-		break;
-
-	case CLOCK_EVT_NOTIFY_CPU_DEAD:
-		tick_shutdown_broadcast_oneshot(dev);
-		tick_shutdown_broadcast(dev);
-		tick_shutdown(dev);
-		break;
-
-	case CLOCK_EVT_NOTIFY_SUSPEND:
-		tick_suspend();
-		tick_suspend_broadcast();
-		break;
-
-	case CLOCK_EVT_NOTIFY_RESUME:
-		tick_resume();
-		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);
 	tick_broadcast_init();
 }
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index f0299eae4602..bc906cad709b 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -6,6 +6,8 @@
 
 extern seqlock_t jiffies_lock;
 
+#define CS_NAME_LEN	32
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD
 
 #define TICK_DO_TIMER_NONE	-1
@@ -18,9 +20,19 @@ 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 tick_check_new_device(struct clock_event_device *dev);
+extern void tick_handover_do_timer(int *cpup);
+extern void tick_shutdown(unsigned int *cpup);
+extern void tick_suspend(void);
+extern void tick_resume(void);
+extern bool tick_check_replacement(struct clock_event_device *curdev,
+				   struct clock_event_device *newdev);
+extern void tick_install_replacement(struct clock_event_device *dev);
 
 extern void clockevents_shutdown(struct clock_event_device *dev);
 
+extern size_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
+
 /*
  * NO_HZ / high resolution timer shared code
  */
@@ -90,7 +102,7 @@ static inline bool tick_broadcast_oneshot_available(void) { return false; }
  */
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 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 void tick_install_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);
@@ -102,9 +114,8 @@ 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)
+static inline void tick_install_broadcast_device(struct clock_event_device *dev)
 {
-	return 0;
 }
 
 static inline int tick_is_broadcast_device(struct clock_event_device *dev)
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index baeeb5c87cf1..48b9fffabdc2 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -25,6 +25,11 @@
 
 #include "tick-internal.h"
 #include "ntp_internal.h"
+#include "timekeeping_internal.h"
+
+#define TK_CLEAR_NTP		(1 << 0)
+#define TK_MIRROR		(1 << 1)
+#define TK_CLOCK_WAS_SET	(1 << 2)
 
 static struct timekeeper timekeeper;
 static DEFINE_RAW_SPINLOCK(timekeeper_lock);
@@ -200,9 +205,9 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
 
 static RAW_NOTIFIER_HEAD(pvclock_gtod_chain);
 
-static void update_pvclock_gtod(struct timekeeper *tk)
+static void update_pvclock_gtod(struct timekeeper *tk, bool was_set)
 {
-	raw_notifier_call_chain(&pvclock_gtod_chain, 0, tk);
+	raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk);
 }
 
 /**
@@ -216,7 +221,7 @@ int pvclock_gtod_register_notifier(struct notifier_block *nb)
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb);
-	update_pvclock_gtod(tk);
+	update_pvclock_gtod(tk, true);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
 	return ret;
@@ -241,16 +246,16 @@ int pvclock_gtod_unregister_notifier(struct notifier_block *nb)
 EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
 
 /* must hold timekeeper_lock */
-static void timekeeping_update(struct timekeeper *tk, bool clearntp, bool mirror)
+static void timekeeping_update(struct timekeeper *tk, unsigned int action)
 {
-	if (clearntp) {
+	if (action & TK_CLEAR_NTP) {
 		tk->ntp_error = 0;
 		ntp_clear();
 	}
 	update_vsyscall(tk);
-	update_pvclock_gtod(tk);
+	update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);
 
-	if (mirror)
+	if (action & TK_MIRROR)
 		memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper));
 }
 
@@ -508,7 +513,7 @@ int do_settimeofday(const struct timespec *tv)
 
 	tk_set_xtime(tk, tv);
 
-	timekeeping_update(tk, true, true);
+	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
 
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
@@ -552,7 +557,7 @@ int timekeeping_inject_offset(struct timespec *ts)
 	tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *ts));
 
 error: /* even if we error out, we forwarded the time, so call update */
-	timekeeping_update(tk, true, true);
+	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
 
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
@@ -627,13 +632,22 @@ static int change_clocksource(void *data)
 	write_seqcount_begin(&timekeeper_seq);
 
 	timekeeping_forward_now(tk);
-	if (!new->enable || new->enable(new) == 0) {
-		old = tk->clock;
-		tk_setup_internals(tk, new);
-		if (old->disable)
-			old->disable(old);
+	/*
+	 * If the cs is in module, get a module reference. Succeeds
+	 * for built-in code (owner == NULL) as well.
+	 */
+	if (try_module_get(new->owner)) {
+		if (!new->enable || new->enable(new) == 0) {
+			old = tk->clock;
+			tk_setup_internals(tk, new);
+			if (old->disable)
+				old->disable(old);
+			module_put(old->owner);
+		} else {
+			module_put(new->owner);
+		}
 	}
-	timekeeping_update(tk, true, true);
+	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
 
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
@@ -648,14 +662,15 @@ static int change_clocksource(void *data)
  * This function is called from clocksource.c after a new, better clock
  * source has been registered. The caller holds the clocksource_mutex.
  */
-void timekeeping_notify(struct clocksource *clock)
+int timekeeping_notify(struct clocksource *clock)
 {
 	struct timekeeper *tk = &timekeeper;
 
 	if (tk->clock == clock)
-		return;
+		return 0;
 	stop_machine(change_clocksource, clock, NULL);
 	tick_clock_notify();
+	return tk->clock == clock ? 0 : -1;
 }
 
 /**
@@ -841,6 +856,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
 	tk_xtime_add(tk, delta);
 	tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *delta));
 	tk_set_sleep_time(tk, timespec_add(tk->total_sleep_time, *delta));
+	tk_debug_account_sleep_time(delta);
 }
 
 /**
@@ -872,7 +888,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta)
 
 	__timekeeping_inject_sleeptime(tk, delta);
 
-	timekeeping_update(tk, true, true);
+	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
 
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
@@ -954,7 +970,7 @@ static void timekeeping_resume(void)
 	tk->cycle_last = clock->cycle_last = cycle_now;
 	tk->ntp_error = 0;
 	timekeeping_suspended = 0;
-	timekeeping_update(tk, false, true);
+	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
@@ -1236,9 +1252,10 @@ out_adjust:
  * It also calls into the NTP code to handle leapsecond processing.
  *
  */
-static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
+static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 {
 	u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
+	unsigned int action = 0;
 
 	while (tk->xtime_nsec >= nsecps) {
 		int leap;
@@ -1261,8 +1278,10 @@ static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
 			__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
 
 			clock_was_set_delayed();
+			action = TK_CLOCK_WAS_SET;
 		}
 	}
+	return action;
 }
 
 /**
@@ -1347,6 +1366,7 @@ static void update_wall_time(void)
 	struct timekeeper *tk = &shadow_timekeeper;
 	cycle_t offset;
 	int shift = 0, maxshift;
+	unsigned int action;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1399,7 +1419,7 @@ static void update_wall_time(void)
 	 * Finally, make sure that after the rounding
 	 * xtime_nsec isn't larger than NSEC_PER_SEC
 	 */
-	accumulate_nsecs_to_secs(tk);
+	action = accumulate_nsecs_to_secs(tk);
 
 	write_seqcount_begin(&timekeeper_seq);
 	/* Update clock->cycle_last with the new value */
@@ -1415,7 +1435,7 @@ static void update_wall_time(void)
 	 * updating.
 	 */
 	memcpy(real_tk, tk, sizeof(*tk));
-	timekeeping_update(real_tk, false, false);
+	timekeeping_update(real_tk, action);
 	write_seqcount_end(&timekeeper_seq);
 out:
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
@@ -1677,6 +1697,7 @@ int do_adjtimex(struct timex *txc)
 
 	if (tai != orig_tai) {
 		__timekeeping_set_tai_offset(tk, tai);
+		update_pvclock_gtod(tk, true);
 		clock_was_set_delayed();
 	}
 	write_seqcount_end(&timekeeper_seq);
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
new file mode 100644
index 000000000000..802433a4f5eb
--- /dev/null
+++ b/kernel/time/timekeeping_debug.c
@@ -0,0 +1,72 @@
+/*
+ * debugfs file to track time spent in suspend
+ *
+ * Copyright (c) 2011, Google, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/seq_file.h>
+#include <linux/time.h>
+
+static unsigned int sleep_time_bin[32] = {0};
+
+static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
+{
+	unsigned int bin;
+	seq_puts(s, "      time (secs)        count\n");
+	seq_puts(s, "------------------------------\n");
+	for (bin = 0; bin < 32; bin++) {
+		if (sleep_time_bin[bin] == 0)
+			continue;
+		seq_printf(s, "%10u - %-10u %4u\n",
+			bin ? 1 << (bin - 1) : 0, 1 << bin,
+				sleep_time_bin[bin]);
+	}
+	return 0;
+}
+
+static int tk_debug_sleep_time_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, tk_debug_show_sleep_time, NULL);
+}
+
+static const struct file_operations tk_debug_sleep_time_fops = {
+	.open		= tk_debug_sleep_time_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init tk_debug_sleep_time_init(void)
+{
+	struct dentry *d;
+
+	d = debugfs_create_file("sleep_time", 0444, NULL, NULL,
+		&tk_debug_sleep_time_fops);
+	if (!d) {
+		pr_err("Failed to create sleep_time debug file\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+late_initcall(tk_debug_sleep_time_init);
+
+void tk_debug_account_sleep_time(struct timespec *t)
+{
+	sleep_time_bin[fls(t->tv_sec)]++;
+}
+
diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h
new file mode 100644
index 000000000000..13323ea08ffa
--- /dev/null
+++ b/kernel/time/timekeeping_internal.h
@@ -0,0 +1,14 @@
+#ifndef _TIMEKEEPING_INTERNAL_H
+#define _TIMEKEEPING_INTERNAL_H
+/*
+ * timekeeping debug functions
+ */
+#include <linux/time.h>
+
+#ifdef CONFIG_DEBUG_FS
+extern void tk_debug_account_sleep_time(struct timespec *t);
+#else
+#define tk_debug_account_sleep_time(x)
+#endif
+
+#endif /* _TIMEKEEPING_INTERNAL_H */
diff --git a/kernel/timer.c b/kernel/timer.c
index 15ffdb3f1948..15bc1b41021d 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -149,9 +149,11 @@ static unsigned long round_jiffies_common(unsigned long j, int cpu,
 	/* now that we have rounded, subtract the extra skew again */
 	j -= cpu * 3;
 
-	if (j <= jiffies) /* rounding ate our timeout entirely; */
-		return original;
-	return j;
+	/*
+	 * Make sure j is still in the future. Otherwise return the
+	 * unmodified value.
+	 */
+	return time_is_after_jiffies(j) ? j : original;
 }
 
 /**