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

Pull timer updates from Ingo Molnar:
 "The main changes in this cycle were:

   - clockevents state machine cleanups and enhancements (Viresh Kumar)

   - clockevents broadcast notifier horror to state machine conversion
     and related cleanups (Thomas Gleixner, Rafael J Wysocki)

   - clocksource and timekeeping core updates (John Stultz)

   - clocksource driver updates and fixes (Ben Dooks, Dmitry Osipenko,
     Hans de Goede, Laurent Pinchart, Maxime Ripard, Xunlei Pang)

   - y2038 fixes (Xunlei Pang, John Stultz)

   - NMI-safe ktime_get_raw_fast() and general refactoring of the clock
     code, in preparation to perf's per event clock ID support (Peter
     Zijlstra)

   - generic sched/clock fixes, optimizations and cleanups (Daniel
     Thompson)

   - clockevents cpu_down() race fix (Preeti U Murthy)"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (94 commits)
  timers/PM: Drop unnecessary braces from tick_freeze()
  timers/PM: Fix up tick_unfreeze()
  timekeeping: Get rid of stale comment
  clockevents: Cleanup dead cpu explicitely
  clockevents: Make tick handover explicit
  clockevents: Remove broadcast oneshot control leftovers
  sched/idle: Use explicit broadcast oneshot control function
  ARM: Tegra: Use explicit broadcast oneshot control function
  ARM: OMAP: Use explicit broadcast oneshot control function
  intel_idle: Use explicit broadcast oneshot control function
  ACPI/idle: Use explicit broadcast control function
  ACPI/PAD: Use explicit broadcast oneshot control function
  x86/amd/idle, clockevents: Use explicit broadcast oneshot control functions
  clockevents: Provide explicit broadcast oneshot control functions
  clockevents: Remove the broadcast control leftovers
  ARM: OMAP: Use explicit broadcast control function
  intel_idle: Use explicit broadcast control function
  cpuidle: Use explicit broadcast control function
  ACPI/processor: Use explicit broadcast control function
  ACPI/PAD: Use explicit broadcast control function
  ...

20 files changed, 1174 insertions, 755 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 1972b161c61e..82eea9c5af61 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -20,6 +20,7 @@
 #include <linux/gfp.h>
 #include <linux/suspend.h>
 #include <linux/lockdep.h>
+#include <linux/tick.h>
 #include <trace/events/power.h>
 
 #include "smpboot.h"
@@ -338,6 +339,8 @@ static int __ref take_cpu_down(void *_param)
 		return err;
 
 	cpu_notify(CPU_DYING | param->mod, param->hcpu);
+	/* Give up timekeeping duties */
+	tick_handover_do_timer();
 	/* Park the stopper thread */
 	kthread_park(current);
 	return 0;
@@ -411,10 +414,12 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	while (!idle_cpu(cpu))
 		cpu_relax();
 
+	hotplug_cpu__broadcast_tick_pull(cpu);
 	/* This actually kills the CPU. */
 	__cpu_die(cpu);
 
 	/* CPU is completely dead: tell everyone.  Too late to complain. */
+	tick_cleanup_dead_cpu(cpu);
 	cpu_notify_nofail(CPU_DEAD | mod, hcpu);
 
 	check_for_tasks(cpu);
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 80014a178342..4d207d2abcbd 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -158,8 +158,7 @@ static void cpuidle_idle_call(void)
 	 * is used from another cpu as a broadcast timer, this call may
 	 * fail if it is not available
 	 */
-	if (broadcast &&
-	    clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
+	if (broadcast && tick_broadcast_enter())
 		goto use_default;
 
 	/* Take note of the planned idle state. */
@@ -176,7 +175,7 @@ static void cpuidle_idle_call(void)
 	idle_set_state(this_rq(), NULL);
 
 	if (broadcast)
-		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+		tick_broadcast_exit();
 
 	/*
 	 * Give the governor an opportunity to reflect on the outcome
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index d626dc98e8df..579ce1b929af 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -33,12 +33,6 @@ config ARCH_USES_GETTIMEOFFSET
 config GENERIC_CLOCKEVENTS
 	bool
 
-# Migration helper. Builds, but does not invoke
-config GENERIC_CLOCKEVENTS_BUILD
-	bool
-	default y
-	depends on GENERIC_CLOCKEVENTS
-
 # Architecture can handle broadcast in a driver-agnostic way
 config ARCH_HAS_TICK_BROADCAST
 	bool
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index c09c07817d7a..01f0312419b3 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -2,15 +2,13 @@ obj-y += time.o timer.o hrtimer.o itimer.o posix-timers.o posix-cpu-timers.o
 obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o
 obj-y += timeconv.o timecounter.o posix-clock.o alarmtimer.o
 
-obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
-obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
+obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= clockevents.o tick-common.o
 ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y)
  obj-y						+= tick-broadcast.o
  obj-$(CONFIG_TICK_ONESHOT)			+= tick-broadcast-hrtimer.o
 endif
 obj-$(CONFIG_GENERIC_SCHED_CLOCK)		+= sched_clock.o
-obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o
-obj-$(CONFIG_TICK_ONESHOT)			+= tick-sched.o
+obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o tick-sched.o
 obj-$(CONFIG_TIMER_STATS)			+= timer_stats.o
 obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
 obj-$(CONFIG_TEST_UDELAY)			+= test_udelay.o
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 55449909f114..25d942d1da27 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -94,25 +94,76 @@ u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
 }
 EXPORT_SYMBOL_GPL(clockevent_delta2ns);
 
+static int __clockevents_set_state(struct clock_event_device *dev,
+				   enum clock_event_state state)
+{
+	/* Transition with legacy set_mode() callback */
+	if (dev->set_mode) {
+		/* Legacy callback doesn't support new modes */
+		if (state > CLOCK_EVT_STATE_ONESHOT)
+			return -ENOSYS;
+		/*
+		 * 'clock_event_state' and 'clock_event_mode' have 1-to-1
+		 * mapping until *_ONESHOT, and so a simple cast will work.
+		 */
+		dev->set_mode((enum clock_event_mode)state, dev);
+		dev->mode = (enum clock_event_mode)state;
+		return 0;
+	}
+
+	if (dev->features & CLOCK_EVT_FEAT_DUMMY)
+		return 0;
+
+	/* Transition with new state-specific callbacks */
+	switch (state) {
+	case CLOCK_EVT_STATE_DETACHED:
+		/*
+		 * This is an internal state, which is guaranteed to go from
+		 * SHUTDOWN to DETACHED. No driver interaction required.
+		 */
+		return 0;
+
+	case CLOCK_EVT_STATE_SHUTDOWN:
+		return dev->set_state_shutdown(dev);
+
+	case CLOCK_EVT_STATE_PERIODIC:
+		/* Core internal bug */
+		if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC))
+			return -ENOSYS;
+		return dev->set_state_periodic(dev);
+
+	case CLOCK_EVT_STATE_ONESHOT:
+		/* Core internal bug */
+		if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+			return -ENOSYS;
+		return dev->set_state_oneshot(dev);
+
+	default:
+		return -ENOSYS;
+	}
+}
+
 /**
- * clockevents_set_mode - set the operating mode of a clock event device
+ * clockevents_set_state - set the operating state of a clock event device
  * @dev:	device to modify
- * @mode:	new mode
+ * @state:	new state
  *
  * Must be called with interrupts disabled !
  */
-void clockevents_set_mode(struct clock_event_device *dev,
-				 enum clock_event_mode mode)
+void clockevents_set_state(struct clock_event_device *dev,
+			   enum clock_event_state state)
 {
-	if (dev->mode != mode) {
-		dev->set_mode(mode, dev);
-		dev->mode = mode;
+	if (dev->state != state) {
+		if (__clockevents_set_state(dev, state))
+			return;
+
+		dev->state = state;
 
 		/*
 		 * A nsec2cyc multiplicator of 0 is invalid and we'd crash
 		 * on it, so fix it up and emit a warning:
 		 */
-		if (mode == CLOCK_EVT_MODE_ONESHOT) {
+		if (state == CLOCK_EVT_STATE_ONESHOT) {
 			if (unlikely(!dev->mult)) {
 				dev->mult = 1;
 				WARN_ON(1);
@@ -127,10 +178,28 @@ void clockevents_set_mode(struct clock_event_device *dev,
  */
 void clockevents_shutdown(struct clock_event_device *dev)
 {
-	clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+	clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 	dev->next_event.tv64 = KTIME_MAX;
 }
 
+/**
+ * clockevents_tick_resume -	Resume the tick device before using it again
+ * @dev:			device to resume
+ */
+int clockevents_tick_resume(struct clock_event_device *dev)
+{
+	int ret = 0;
+
+	if (dev->set_mode) {
+		dev->set_mode(CLOCK_EVT_MODE_RESUME, dev);
+		dev->mode = CLOCK_EVT_MODE_RESUME;
+	} else if (dev->tick_resume) {
+		ret = dev->tick_resume(dev);
+	}
+
+	return ret;
+}
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST
 
 /* Limit min_delta to a jiffie */
@@ -183,7 +252,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev)
 		delta = dev->min_delta_ns;
 		dev->next_event = ktime_add_ns(ktime_get(), delta);
 
-		if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN)
+		if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
 			return 0;
 
 		dev->retries++;
@@ -220,7 +289,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev)
 	delta = dev->min_delta_ns;
 	dev->next_event = ktime_add_ns(ktime_get(), delta);
 
-	if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN)
+	if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
 		return 0;
 
 	dev->retries++;
@@ -252,7 +321,7 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
 
 	dev->next_event = expires;
 
-	if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN)
+	if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
 		return 0;
 
 	/* Shortcut for clockevent devices that can deal with ktime. */
@@ -297,7 +366,7 @@ 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)
+		if (dev == ced || dev->state != CLOCK_EVT_STATE_DETACHED)
 			continue;
 
 		if (!tick_check_replacement(newdev, dev))
@@ -323,7 +392,7 @@ static int clockevents_replace(struct clock_event_device *ced)
 static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu)
 {
 	/* Fast track. Device is unused */
-	if (ced->mode == CLOCK_EVT_MODE_UNUSED) {
+	if (ced->state == CLOCK_EVT_STATE_DETACHED) {
 		list_del_init(&ced->list);
 		return 0;
 	}
@@ -373,6 +442,37 @@ int clockevents_unbind_device(struct clock_event_device *ced, int cpu)
 }
 EXPORT_SYMBOL_GPL(clockevents_unbind);
 
+/* Sanity check of state transition callbacks */
+static int clockevents_sanity_check(struct clock_event_device *dev)
+{
+	/* Legacy set_mode() callback */
+	if (dev->set_mode) {
+		/* We shouldn't be supporting new modes now */
+		WARN_ON(dev->set_state_periodic || dev->set_state_oneshot ||
+			dev->set_state_shutdown || dev->tick_resume);
+
+		BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
+		return 0;
+	}
+
+	if (dev->features & CLOCK_EVT_FEAT_DUMMY)
+		return 0;
+
+	/* New state-specific callbacks */
+	if (!dev->set_state_shutdown)
+		return -EINVAL;
+
+	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
+	    !dev->set_state_periodic)
+		return -EINVAL;
+
+	if ((dev->features & CLOCK_EVT_FEAT_ONESHOT) &&
+	    !dev->set_state_oneshot)
+		return -EINVAL;
+
+	return 0;
+}
+
 /**
  * clockevents_register_device - register a clock event device
  * @dev:	device to register
@@ -381,7 +481,11 @@ void clockevents_register_device(struct clock_event_device *dev)
 {
 	unsigned long flags;
 
-	BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
+	BUG_ON(clockevents_sanity_check(dev));
+
+	/* Initialize state to DETACHED */
+	dev->state = CLOCK_EVT_STATE_DETACHED;
+
 	if (!dev->cpumask) {
 		WARN_ON(num_possible_cpus() > 1);
 		dev->cpumask = cpumask_of(smp_processor_id());
@@ -445,11 +549,11 @@ int __clockevents_update_freq(struct clock_event_device *dev, u32 freq)
 {
 	clockevents_config(dev, freq);
 
-	if (dev->mode == CLOCK_EVT_MODE_ONESHOT)
+	if (dev->state == CLOCK_EVT_STATE_ONESHOT)
 		return clockevents_program_event(dev, dev->next_event, false);
 
-	if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
-		dev->set_mode(CLOCK_EVT_MODE_PERIODIC, dev);
+	if (dev->state == CLOCK_EVT_STATE_PERIODIC)
+		return __clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC);
 
 	return 0;
 }
@@ -491,30 +595,27 @@ void clockevents_handle_noop(struct clock_event_device *dev)
  * @old:	device to release (can be NULL)
  * @new:	device to request (can be NULL)
  *
- * Called from the notifier chain. clockevents_lock is held already
+ * Called from various tick functions with clockevents_lock held and
+ * interrupts disabled.
  */
 void clockevents_exchange_device(struct clock_event_device *old,
 				 struct clock_event_device *new)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
 	/*
 	 * Caller releases a clock event device. We queue it into the
 	 * released list and do a notify add later.
 	 */
 	if (old) {
 		module_put(old->owner);
-		clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
+		clockevents_set_state(old, CLOCK_EVT_STATE_DETACHED);
 		list_del(&old->list);
 		list_add(&old->list, &clockevents_released);
 	}
 
 	if (new) {
-		BUG_ON(new->mode != CLOCK_EVT_MODE_UNUSED);
+		BUG_ON(new->state != CLOCK_EVT_STATE_DETACHED);
 		clockevents_shutdown(new);
 	}
-	local_irq_restore(flags);
 }
 
 /**
@@ -541,74 +642,40 @@ void clockevents_resume(void)
 			dev->resume(dev);
 }
 
-#ifdef CONFIG_GENERIC_CLOCKEVENTS
+#ifdef CONFIG_HOTPLUG_CPU
 /**
- * clockevents_notify - notification about relevant events
- * Returns 0 on success, any other value on error
+ * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu
  */
-int clockevents_notify(unsigned long reason, void *arg)
+void tick_cleanup_dead_cpu(int cpu)
 {
 	struct clock_event_device *dev, *tmp;
 	unsigned long flags;
-	int cpu, ret = 0;
 
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
-	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:
-		ret = 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.
-		 */
-		list_for_each_entry_safe(dev, tmp, &clockevents_released, list)
+	tick_shutdown_broadcast_oneshot(cpu);
+	tick_shutdown_broadcast(cpu);
+	tick_shutdown(cpu);
+	/*
+	 * Unregister the clock event devices which were
+	 * released from the users in the notify chain.
+	 */
+	list_for_each_entry_safe(dev, tmp, &clockevents_released, list)
+		list_del(&dev->list);
+	/*
+	 * Now check whether the CPU has left unused per cpu devices
+	 */
+	list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) {
+		if (cpumask_test_cpu(cpu, dev->cpumask) &&
+		    cpumask_weight(dev->cpumask) == 1 &&
+		    !tick_is_broadcast_device(dev)) {
+			BUG_ON(dev->state != CLOCK_EVT_STATE_DETACHED);
 			list_del(&dev->list);
-		/*
-		 * Now check whether the CPU has left unused per cpu devices
-		 */
-		cpu = *((int *)arg);
-		list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) {
-			if (cpumask_test_cpu(cpu, dev->cpumask) &&
-			    cpumask_weight(dev->cpumask) == 1 &&
-			    !tick_is_broadcast_device(dev)) {
-				BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
-				list_del(&dev->list);
-			}
 		}
-		break;
-	default:
-		break;
 	}
 	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
-	return ret;
 }
-EXPORT_SYMBOL_GPL(clockevents_notify);
+#endif
 
 #ifdef CONFIG_SYSFS
 struct bus_type clockevents_subsys = {
@@ -727,5 +794,3 @@ static int __init clockevents_init_sysfs(void)
 }
 device_initcall(clockevents_init_sysfs);
 #endif /* SYSFS */
-
-#endif /* GENERIC_CLOCK_EVENTS */
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 4892352f0e49..15facb1b9c60 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -142,13 +142,6 @@ static void __clocksource_unstable(struct clocksource *cs)
 		schedule_work(&watchdog_work);
 }
 
-static void clocksource_unstable(struct clocksource *cs, int64_t delta)
-{
-	printk(KERN_WARNING "Clocksource %s unstable (delta = %Ld ns)\n",
-	       cs->name, delta);
-	__clocksource_unstable(cs);
-}
-
 /**
  * clocksource_mark_unstable - mark clocksource unstable via watchdog
  * @cs:		clocksource to be marked unstable
@@ -174,7 +167,7 @@ void clocksource_mark_unstable(struct clocksource *cs)
 static void clocksource_watchdog(unsigned long data)
 {
 	struct clocksource *cs;
-	cycle_t csnow, wdnow, delta;
+	cycle_t csnow, wdnow, cslast, wdlast, delta;
 	int64_t wd_nsec, cs_nsec;
 	int next_cpu, reset_pending;
 
@@ -213,6 +206,8 @@ static void clocksource_watchdog(unsigned long data)
 
 		delta = clocksource_delta(csnow, cs->cs_last, cs->mask);
 		cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift);
+		wdlast = cs->wd_last; /* save these in case we print them */
+		cslast = cs->cs_last;
 		cs->cs_last = csnow;
 		cs->wd_last = wdnow;
 
@@ -221,7 +216,12 @@ static void clocksource_watchdog(unsigned long data)
 
 		/* Check the deviation from the watchdog clocksource. */
 		if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) {
-			clocksource_unstable(cs, cs_nsec - wd_nsec);
+			pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable, because the skew is too large:\n", cs->name);
+			pr_warn("	'%s' wd_now: %llx wd_last: %llx mask: %llx\n",
+				watchdog->name, wdnow, wdlast, watchdog->mask);
+			pr_warn("	'%s' cs_now: %llx cs_last: %llx mask: %llx\n",
+				cs->name, csnow, cslast, cs->mask);
+			__clocksource_unstable(cs);
 			continue;
 		}
 
@@ -469,26 +469,25 @@ static u32 clocksource_max_adjustment(struct clocksource *cs)
  * @shift:	cycle to nanosecond divisor (power of two)
  * @maxadj:	maximum adjustment value to mult (~11%)
  * @mask:	bitmask for two's complement subtraction of non 64 bit counters
+ * @max_cyc:	maximum cycle value before potential overflow (does not include
+ *		any safety margin)
+ *
+ * NOTE: This function includes a safety margin of 50%, in other words, we
+ * return half the number of nanoseconds the hardware counter can technically
+ * cover. This is done so that we can potentially detect problems caused by
+ * delayed timers or bad hardware, which might result in time intervals that
+ * are larger then what the math used can handle without overflows.
  */
-u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask)
+u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cyc)
 {
 	u64 max_nsecs, max_cycles;
 
 	/*
 	 * Calculate the maximum number of cycles that we can pass to the
-	 * cyc2ns function without overflowing a 64-bit signed result. The
-	 * maximum number of cycles is equal to ULLONG_MAX/(mult+maxadj)
-	 * which is equivalent to the below.
-	 * max_cycles < (2^63)/(mult + maxadj)
-	 * max_cycles < 2^(log2((2^63)/(mult + maxadj)))
-	 * max_cycles < 2^(log2(2^63) - log2(mult + maxadj))
-	 * max_cycles < 2^(63 - log2(mult + maxadj))
-	 * max_cycles < 1 << (63 - log2(mult + maxadj))
-	 * Please note that we add 1 to the result of the log2 to account for
-	 * any rounding errors, ensure the above inequality is satisfied and
-	 * no overflow will occur.
+	 * cyc2ns() function without overflowing a 64-bit result.
 	 */
-	max_cycles = 1ULL << (63 - (ilog2(mult + maxadj) + 1));
+	max_cycles = ULLONG_MAX;
+	do_div(max_cycles, mult+maxadj);
 
 	/*
 	 * The actual maximum number of cycles we can defer the clocksource is
@@ -499,27 +498,26 @@ u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask)
 	max_cycles = min(max_cycles, mask);
 	max_nsecs = clocksource_cyc2ns(max_cycles, mult - maxadj, shift);
 
+	/* return the max_cycles value as well if requested */
+	if (max_cyc)
+		*max_cyc = max_cycles;
+
+	/* Return 50% of the actual maximum, so we can detect bad values */
+	max_nsecs >>= 1;
+
 	return max_nsecs;
 }
 
 /**
- * clocksource_max_deferment - Returns max time the clocksource can be deferred
- * @cs:         Pointer to clocksource
+ * clocksource_update_max_deferment - Updates the clocksource max_idle_ns & max_cycles
+ * @cs:         Pointer to clocksource to be updated
  *
  */
-static u64 clocksource_max_deferment(struct clocksource *cs)
+static inline void clocksource_update_max_deferment(struct clocksource *cs)
 {
-	u64 max_nsecs;
-
-	max_nsecs = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj,
-					  cs->mask);
-	/*
-	 * To ensure that the clocksource does not wrap whilst we are idle,
-	 * limit the time the clocksource can be deferred by 12.5%. Please
-	 * note a margin of 12.5% is used because this can be computed with
-	 * a shift, versus say 10% which would require division.
-	 */
-	return max_nsecs - (max_nsecs >> 3);
+	cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift,
+						cs->maxadj, cs->mask,
+						&cs->max_cycles);
 }
 
 #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
@@ -648,7 +646,7 @@ static void clocksource_enqueue(struct clocksource *cs)
 }
 
 /**
- * __clocksource_updatefreq_scale - Used update clocksource with new freq
+ * __clocksource_update_freq_scale - Used update clocksource with new freq
  * @cs:		clocksource to be registered
  * @scale:	Scale factor multiplied against freq to get clocksource hz
  * @freq:	clocksource frequency (cycles per second) divided by scale
@@ -656,48 +654,64 @@ static void clocksource_enqueue(struct clocksource *cs)
  * This should only be called from the clocksource->enable() method.
  *
  * This *SHOULD NOT* be called directly! Please use the
- * clocksource_updatefreq_hz() or clocksource_updatefreq_khz helper functions.
+ * __clocksource_update_freq_hz() or __clocksource_update_freq_khz() helper
+ * functions.
  */
-void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
+void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
 	u64 sec;
+
 	/*
-	 * Calc the maximum number of seconds which we can run before
-	 * wrapping around. For clocksources which have a mask > 32bit
-	 * we need to limit the max sleep time to have a good
-	 * conversion precision. 10 minutes is still a reasonable
-	 * amount. That results in a shift value of 24 for a
-	 * clocksource with mask >= 40bit and f >= 4GHz. That maps to
-	 * ~ 0.06ppm granularity for NTP. We apply the same 12.5%
-	 * margin as we do in clocksource_max_deferment()
+	 * Default clocksources are *special* and self-define their mult/shift.
+	 * But, you're not special, so you should specify a freq value.
 	 */
-	sec = (cs->mask - (cs->mask >> 3));
-	do_div(sec, freq);
-	do_div(sec, scale);
-	if (!sec)
-		sec = 1;
-	else if (sec > 600 && cs->mask > UINT_MAX)
-		sec = 600;
-
-	clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
-			       NSEC_PER_SEC / scale, sec * scale);
-
+	if (freq) {
+		/*
+		 * Calc the maximum number of seconds which we can run before
+		 * wrapping around. For clocksources which have a mask > 32-bit
+		 * we need to limit the max sleep time to have a good
+		 * conversion precision. 10 minutes is still a reasonable
+		 * amount. That results in a shift value of 24 for a
+		 * clocksource with mask >= 40-bit and f >= 4GHz. That maps to
+		 * ~ 0.06ppm granularity for NTP.
+		 */
+		sec = cs->mask;
+		do_div(sec, freq);
+		do_div(sec, scale);
+		if (!sec)
+			sec = 1;
+		else if (sec > 600 && cs->mask > UINT_MAX)
+			sec = 600;
+
+		clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
+				       NSEC_PER_SEC / scale, sec * scale);
+	}
 	/*
-	 * for clocksources that have large mults, to avoid overflow.
-	 * Since mult may be adjusted by ntp, add an safety extra margin
-	 *
+	 * Ensure clocksources that have large 'mult' values don't overflow
+	 * when adjusted.
 	 */
 	cs->maxadj = clocksource_max_adjustment(cs);
-	while ((cs->mult + cs->maxadj < cs->mult)
-		|| (cs->mult - cs->maxadj > cs->mult)) {
+	while (freq && ((cs->mult + cs->maxadj < cs->mult)
+		|| (cs->mult - cs->maxadj > cs->mult))) {
 		cs->mult >>= 1;
 		cs->shift--;
 		cs->maxadj = clocksource_max_adjustment(cs);
 	}
 
-	cs->max_idle_ns = clocksource_max_deferment(cs);
+	/*
+	 * Only warn for *special* clocksources that self-define
+	 * their mult/shift values and don't specify a freq.
+	 */
+	WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
+		"timekeeping: Clocksource %s might overflow on 11%% adjustment\n",
+		cs->name);
+
+	clocksource_update_max_deferment(cs);
+
+	pr_info("clocksource %s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n",
+			cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns);
 }
-EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
+EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale);
 
 /**
  * __clocksource_register_scale - Used to install new clocksources
@@ -714,7 +728,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
 
 	/* Initialize mult/shift and max_idle_ns */
-	__clocksource_updatefreq_scale(cs, scale, freq);
+	__clocksource_update_freq_scale(cs, scale, freq);
 
 	/* Add clocksource to the clocksource list */
 	mutex_lock(&clocksource_mutex);
@@ -726,33 +740,6 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 }
 EXPORT_SYMBOL_GPL(__clocksource_register_scale);
 
-
-/**
- * clocksource_register - Used to install new clocksources
- * @cs:		clocksource to be registered
- *
- * Returns -EBUSY if registration fails, zero otherwise.
- */
-int clocksource_register(struct clocksource *cs)
-{
-	/* calculate max adjustment for given mult/shift */
-	cs->maxadj = clocksource_max_adjustment(cs);
-	WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
-		"Clocksource %s might overflow on 11%% adjustment\n",
-		cs->name);
-
-	/* calculate max idle time permitted for this clocksource */
-	cs->max_idle_ns = clocksource_max_deferment(cs);
-
-	mutex_lock(&clocksource_mutex);
-	clocksource_enqueue(cs);
-	clocksource_enqueue_watchdog(cs);
-	clocksource_select();
-	mutex_unlock(&clocksource_mutex);
-	return 0;
-}
-EXPORT_SYMBOL(clocksource_register);
-
 static void __clocksource_change_rating(struct clocksource *cs, int rating)
 {
 	list_del(&cs->list);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index bee0c1f78091..76d4bd962b19 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -54,7 +54,7 @@
 
 #include <trace/events/timer.h>
 
-#include "timekeeping.h"
+#include "tick-internal.h"
 
 /*
  * The timer bases:
@@ -1707,17 +1707,10 @@ static int hrtimer_cpu_notify(struct notifier_block *self,
 		break;
 
 #ifdef CONFIG_HOTPLUG_CPU
-	case CPU_DYING:
-	case CPU_DYING_FROZEN:
-		clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu);
-		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-	{
-		clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu);
 		migrate_hrtimers(scpu);
 		break;
-	}
 #endif
 
 	default:
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index a6a5bf53e86d..347fecf86a3f 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -25,7 +25,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 
-#include "tick-internal.h"
+#include "timekeeping.h"
 
 /* The Jiffies based clocksource is the lowest common
  * denominator clock source which should function on
@@ -71,6 +71,7 @@ static struct clocksource clocksource_jiffies = {
 	.mask		= 0xffffffff, /*32bits*/
 	.mult		= NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
 	.shift		= JIFFIES_SHIFT,
+	.max_cycles	= 10,
 };
 
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock);
@@ -94,7 +95,7 @@ EXPORT_SYMBOL(jiffies);
 
 static int __init init_jiffies_clocksource(void)
 {
-	return clocksource_register(&clocksource_jiffies);
+	return __clocksource_register(&clocksource_jiffies);
 }
 
 core_initcall(init_jiffies_clocksource);
@@ -130,6 +131,6 @@ int register_refined_jiffies(long cycles_per_second)
 
 	refined_jiffies.mult = ((u32)nsec_per_tick) << JIFFIES_SHIFT;
 
-	clocksource_register(&refined_jiffies);
+	__clocksource_register(&refined_jiffies);
 	return 0;
 }
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 0f60b08a4f07..7a681003001c 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -17,7 +17,6 @@
 #include <linux/module.h>
 #include <linux/rtc.h>
 
-#include "tick-internal.h"
 #include "ntp_internal.h"
 
 /*
@@ -459,6 +458,16 @@ out:
 	return leap;
 }
 
+#ifdef CONFIG_GENERIC_CMOS_UPDATE
+int __weak update_persistent_clock64(struct timespec64 now64)
+{
+	struct timespec now;
+
+	now = timespec64_to_timespec(now64);
+	return update_persistent_clock(now);
+}
+#endif
+
 #if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC)
 static void sync_cmos_clock(struct work_struct *work);
 
@@ -494,8 +503,9 @@ static void sync_cmos_clock(struct work_struct *work)
 		if (persistent_clock_is_local)
 			adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
-		fail = update_persistent_clock(timespec64_to_timespec(adjust));
+		fail = update_persistent_clock64(adjust);
 #endif
+
 #ifdef CONFIG_RTC_SYSTOHC
 		if (fail == -ENODEV)
 			fail = rtc_set_ntp_time(adjust);
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 01d2d15aa662..a26036d37a38 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -1,5 +1,6 @@
 /*
- * sched_clock.c: support for extending counters to full 64-bit ns counter
+ * sched_clock.c: Generic sched_clock() support, to extend low level
+ *                hardware time counters to full 64-bit ns values.
  *
  * 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
@@ -18,15 +19,53 @@
 #include <linux/seqlock.h>
 #include <linux/bitops.h>
 
-struct clock_data {
-	ktime_t wrap_kt;
+/**
+ * struct clock_read_data - data required to read from sched_clock()
+ *
+ * @epoch_ns:		sched_clock() value at last update
+ * @epoch_cyc:		Clock cycle value at last update.
+ * @sched_clock_mask:   Bitmask for two's complement subtraction of non 64bit
+ *			clocks.
+ * @read_sched_clock:	Current clock source (or dummy source when suspended).
+ * @mult:		Multipler for scaled math conversion.
+ * @shift:		Shift value for scaled math conversion.
+ *
+ * Care must be taken when updating this structure; it is read by
+ * some very hot code paths. It occupies <=40 bytes and, when combined
+ * with the seqcount used to synchronize access, comfortably fits into
+ * a 64 byte cache line.
+ */
+struct clock_read_data {
 	u64 epoch_ns;
 	u64 epoch_cyc;
-	seqcount_t seq;
-	unsigned long rate;
+	u64 sched_clock_mask;
+	u64 (*read_sched_clock)(void);
 	u32 mult;
 	u32 shift;
-	bool suspended;
+};
+
+/**
+ * struct clock_data - all data needed for sched_clock() (including
+ *                     registration of a new clock source)
+ *
+ * @seq:		Sequence counter for protecting updates. The lowest
+ *			bit is the index for @read_data.
+ * @read_data:		Data required to read from sched_clock.
+ * @wrap_kt:		Duration for which clock can run before wrapping.
+ * @rate:		Tick rate of the registered clock.
+ * @actual_read_sched_clock: Registered hardware level clock read function.
+ *
+ * The ordering of this structure has been chosen to optimize cache
+ * performance. In particular 'seq' and 'read_data[0]' (combined) should fit
+ * into a single 64-byte cache line.
+ */
+struct clock_data {
+	seqcount_t		seq;
+	struct clock_read_data	read_data[2];
+	ktime_t			wrap_kt;
+	unsigned long		rate;
+
+	u64 (*actual_read_sched_clock)(void);
 };
 
 static struct hrtimer sched_clock_timer;
@@ -34,12 +73,6 @@ static int irqtime = -1;
 
 core_param(irqtime, irqtime, int, 0400);
 
-static struct clock_data cd = {
-	.mult	= NSEC_PER_SEC / HZ,
-};
-
-static u64 __read_mostly sched_clock_mask;
-
 static u64 notrace jiffy_sched_clock_read(void)
 {
 	/*
@@ -49,7 +82,11 @@ static u64 notrace jiffy_sched_clock_read(void)
 	return (u64)(jiffies - INITIAL_JIFFIES);
 }
 
-static u64 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
+static struct clock_data cd ____cacheline_aligned = {
+	.read_data[0] = { .mult = NSEC_PER_SEC / HZ,
+			  .read_sched_clock = jiffy_sched_clock_read, },
+	.actual_read_sched_clock = jiffy_sched_clock_read,
+};
 
 static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 {
@@ -58,111 +95,136 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 
 unsigned long long notrace sched_clock(void)
 {
-	u64 epoch_ns;
-	u64 epoch_cyc;
-	u64 cyc;
+	u64 cyc, res;
 	unsigned long seq;
-
-	if (cd.suspended)
-		return cd.epoch_ns;
+	struct clock_read_data *rd;
 
 	do {
-		seq = raw_read_seqcount_begin(&cd.seq);
-		epoch_cyc = cd.epoch_cyc;
-		epoch_ns = cd.epoch_ns;
+		seq = raw_read_seqcount(&cd.seq);
+		rd = cd.read_data + (seq & 1);
+
+		cyc = (rd->read_sched_clock() - rd->epoch_cyc) &
+		      rd->sched_clock_mask;
+		res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift);
 	} while (read_seqcount_retry(&cd.seq, seq));
 
-	cyc = read_sched_clock();
-	cyc = (cyc - epoch_cyc) & sched_clock_mask;
-	return epoch_ns + cyc_to_ns(cyc, cd.mult, cd.shift);
+	return res;
+}
+
+/*
+ * Updating the data required to read the clock.
+ *
+ * sched_clock() will never observe mis-matched data even if called from
+ * an NMI. We do this by maintaining an odd/even copy of the data and
+ * steering sched_clock() to one or the other using a sequence counter.
+ * In order to preserve the data cache profile of sched_clock() as much
+ * as possible the system reverts back to the even copy when the update
+ * completes; the odd copy is used *only* during an update.
+ */
+static void update_clock_read_data(struct clock_read_data *rd)
+{
+	/* update the backup (odd) copy with the new data */
+	cd.read_data[1] = *rd;
+
+	/* steer readers towards the odd copy */
+	raw_write_seqcount_latch(&cd.seq);
+
+	/* now its safe for us to update the normal (even) copy */
+	cd.read_data[0] = *rd;
+
+	/* switch readers back to the even copy */
+	raw_write_seqcount_latch(&cd.seq);
 }
 
 /*
- * Atomically update the sched_clock epoch.
+ * Atomically update the sched_clock() epoch.
  */
-static void notrace update_sched_clock(void)
+static void update_sched_clock(void)
 {
-	unsigned long flags;
 	u64 cyc;
 	u64 ns;
+	struct clock_read_data rd;
+
+	rd = cd.read_data[0];
+
+	cyc = cd.actual_read_sched_clock();
+	ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift);
+
+	rd.epoch_ns = ns;
+	rd.epoch_cyc = cyc;
 
-	cyc = read_sched_clock();
-	ns = cd.epoch_ns +
-		cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
-			  cd.mult, cd.shift);
-
-	raw_local_irq_save(flags);
-	raw_write_seqcount_begin(&cd.seq);
-	cd.epoch_ns = ns;
-	cd.epoch_cyc = cyc;
-	raw_write_seqcount_end(&cd.seq);
-	raw_local_irq_restore(flags);
+	update_clock_read_data(&rd);
 }
 
 static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt)
 {
 	update_sched_clock();
 	hrtimer_forward_now(hrt, cd.wrap_kt);
+
 	return HRTIMER_RESTART;
 }
 
-void __init sched_clock_register(u64 (*read)(void), int bits,
-				 unsigned long rate)
+void __init
+sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
 {
 	u64 res, wrap, new_mask, new_epoch, cyc, ns;
 	u32 new_mult, new_shift;
-	ktime_t new_wrap_kt;
 	unsigned long r;
 	char r_unit;
+	struct clock_read_data rd;
 
 	if (cd.rate > rate)
 		return;
 
 	WARN_ON(!irqs_disabled());
 
-	/* calculate the mult/shift to convert counter ticks to ns. */
+	/* Calculate the mult/shift to convert counter ticks to ns. */
 	clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
 
 	new_mask = CLOCKSOURCE_MASK(bits);
+	cd.rate = rate;
+
+	/* Calculate how many nanosecs until we risk wrapping */
+	wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask, NULL);
+	cd.wrap_kt = ns_to_ktime(wrap);
 
-	/* calculate how many ns until we wrap */
-	wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask);
-	new_wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
+	rd = cd.read_data[0];
 
-	/* update epoch for new counter and update epoch_ns from old counter*/
+	/* Update epoch for new counter and update 'epoch_ns' from old counter*/
 	new_epoch = read();
-	cyc = read_sched_clock();
-	ns = cd.epoch_ns + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
-			  cd.mult, cd.shift);
+	cyc = cd.actual_read_sched_clock();
+	ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift);
+	cd.actual_read_sched_clock = read;
 
-	raw_write_seqcount_begin(&cd.seq);
-	read_sched_clock = read;
-	sched_clock_mask = new_mask;
-	cd.rate = rate;
-	cd.wrap_kt = new_wrap_kt;
-	cd.mult = new_mult;
-	cd.shift = new_shift;
-	cd.epoch_cyc = new_epoch;
-	cd.epoch_ns = ns;
-	raw_write_seqcount_end(&cd.seq);
+	rd.read_sched_clock	= read;
+	rd.sched_clock_mask	= new_mask;
+	rd.mult			= new_mult;
+	rd.shift		= new_shift;
+	rd.epoch_cyc		= new_epoch;
+	rd.epoch_ns		= ns;
+
+	update_clock_read_data(&rd);
 
 	r = rate;
 	if (r >= 4000000) {
 		r /= 1000000;
 		r_unit = 'M';
-	} else if (r >= 1000) {
-		r /= 1000;
-		r_unit = 'k';
-	} else
-		r_unit = ' ';
-
-	/* calculate the ns resolution of this counter */
+	} else {
+		if (r >= 1000) {
+			r /= 1000;
+			r_unit = 'k';
+		} else {
+			r_unit = ' ';
+		}
+	}
+
+	/* Calculate the ns resolution of this counter */
 	res = cyc_to_ns(1ULL, new_mult, new_shift);
 
 	pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
 		bits, r, r_unit, res, wrap);
 
-	/* Enable IRQ time accounting if we have a fast enough sched_clock */
+	/* Enable IRQ time accounting if we have a fast enough sched_clock() */
 	if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
 		enable_sched_clock_irqtime();
 
@@ -172,10 +234,10 @@ void __init sched_clock_register(u64 (*read)(void), int bits,
 void __init sched_clock_postinit(void)
 {
 	/*
-	 * If no sched_clock function has been provided at that point,
+	 * 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)
+	if (cd.actual_read_sched_clock == jiffy_sched_clock_read)
 		sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ);
 
 	update_sched_clock();
@@ -189,29 +251,53 @@ void __init sched_clock_postinit(void)
 	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
 }
 
+/*
+ * Clock read function for use when the clock is suspended.
+ *
+ * This function makes it appear to sched_clock() as if the clock
+ * stopped counting at its last update.
+ *
+ * This function must only be called from the critical
+ * section in sched_clock(). It relies on the read_seqcount_retry()
+ * at the end of the critical section to be sure we observe the
+ * correct copy of 'epoch_cyc'.
+ */
+static u64 notrace suspended_sched_clock_read(void)
+{
+	unsigned long seq = raw_read_seqcount(&cd.seq);
+
+	return cd.read_data[seq & 1].epoch_cyc;
+}
+
 static int sched_clock_suspend(void)
 {
+	struct clock_read_data *rd = &cd.read_data[0];
+
 	update_sched_clock();
 	hrtimer_cancel(&sched_clock_timer);
-	cd.suspended = true;
+	rd->read_sched_clock = suspended_sched_clock_read;
+
 	return 0;
 }
 
 static void sched_clock_resume(void)
 {
-	cd.epoch_cyc = read_sched_clock();
+	struct clock_read_data *rd = &cd.read_data[0];
+
+	rd->epoch_cyc = cd.actual_read_sched_clock();
 	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
-	cd.suspended = false;
+	rd->read_sched_clock = cd.actual_read_sched_clock;
 }
 
 static struct syscore_ops sched_clock_ops = {
-	.suspend = sched_clock_suspend,
-	.resume = sched_clock_resume,
+	.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 066f0ec05e48..7e8ca4f448a8 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -33,12 +33,14 @@ 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;
+static int tick_broadcast_forced;
 
 #ifdef CONFIG_TICK_ONESHOT
 static void tick_broadcast_clear_oneshot(int cpu);
+static void tick_resume_broadcast_oneshot(struct clock_event_device *bc);
 #else
 static inline void tick_broadcast_clear_oneshot(int cpu) { }
+static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { }
 #endif
 
 /*
@@ -303,7 +305,7 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 	/*
 	 * The device is in periodic mode. No reprogramming necessary:
 	 */
-	if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
+	if (dev->state == CLOCK_EVT_STATE_PERIODIC)
 		goto unlock;
 
 	/*
@@ -324,49 +326,54 @@ unlock:
 	raw_spin_unlock(&tick_broadcast_lock);
 }
 
-/*
- * Powerstate information: The system enters/leaves a state, where
- * affected devices might stop
+/**
+ * tick_broadcast_control - Enable/disable or force broadcast mode
+ * @mode:	The selected broadcast mode
+ *
+ * Called when the system enters a state where affected tick devices
+ * might stop. Note: TICK_BROADCAST_FORCE cannot be undone.
+ *
+ * Called with interrupts disabled, so clockevents_lock is not
+ * required here because the local clock event device cannot go away
+ * under us.
  */
-static void tick_do_broadcast_on_off(unsigned long *reason)
+void tick_broadcast_control(enum tick_broadcast_mode mode)
 {
 	struct clock_event_device *bc, *dev;
 	struct tick_device *td;
-	unsigned long flags;
 	int cpu, bc_stopped;
 
-	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
-
-	cpu = smp_processor_id();
-	td = &per_cpu(tick_cpu_device, cpu);
+	td = this_cpu_ptr(&tick_cpu_device);
 	dev = td->evtdev;
-	bc = tick_broadcast_device.evtdev;
 
 	/*
 	 * Is the device not affected by the powerstate ?
 	 */
 	if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP))
-		goto out;
+		return;
 
 	if (!tick_device_is_functional(dev))
-		goto out;
+		return;
 
+	raw_spin_lock(&tick_broadcast_lock);
+	cpu = smp_processor_id();
+	bc = tick_broadcast_device.evtdev;
 	bc_stopped = cpumask_empty(tick_broadcast_mask);
 
-	switch (*reason) {
-	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
-	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
+	switch (mode) {
+	case TICK_BROADCAST_FORCE:
+		tick_broadcast_forced = 1;
+	case TICK_BROADCAST_ON:
 		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)
 				clockevents_shutdown(dev);
 		}
-		if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
-			tick_broadcast_force = 1;
 		break;
-	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
-		if (tick_broadcast_force)
+
+	case TICK_BROADCAST_OFF:
+		if (tick_broadcast_forced)
 			break;
 		cpumask_clear_cpu(cpu, tick_broadcast_on);
 		if (!tick_device_is_functional(dev))
@@ -388,22 +395,9 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
 		else
 			tick_broadcast_setup_oneshot(bc);
 	}
-out:
-	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
-}
-
-/*
- * Powerstate information: The system enters/leaves a state, where
- * affected devices might stop.
- */
-void tick_broadcast_on_off(unsigned long reason, int *oncpu)
-{
-	if (!cpumask_test_cpu(*oncpu, cpu_online_mask))
-		printk(KERN_ERR "tick-broadcast: ignoring broadcast for "
-		       "offline CPU #%d\n", *oncpu);
-	else
-		tick_do_broadcast_on_off(&reason);
+	raw_spin_unlock(&tick_broadcast_lock);
 }
+EXPORT_SYMBOL_GPL(tick_broadcast_control);
 
 /*
  * Set the periodic handler depending on broadcast on/off
@@ -416,14 +410,14 @@ void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast)
 		dev->event_handler = tick_handle_periodic_broadcast;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * Remove a CPU from broadcasting
  */
-void tick_shutdown_broadcast(unsigned int *cpup)
+void tick_shutdown_broadcast(unsigned int cpu)
 {
 	struct clock_event_device *bc;
 	unsigned long flags;
-	unsigned int cpu = *cpup;
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
@@ -438,6 +432,7 @@ void tick_shutdown_broadcast(unsigned int *cpup)
 
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
+#endif
 
 void tick_suspend_broadcast(void)
 {
@@ -453,38 +448,48 @@ void tick_suspend_broadcast(void)
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
-int tick_resume_broadcast(void)
+/*
+ * This is called from tick_resume_local() on a resuming CPU. That's
+ * called from the core resume function, tick_unfreeze() and the magic XEN
+ * resume hackery.
+ *
+ * In none of these cases the broadcast device mode can change and the
+ * bit of the resuming CPU in the broadcast mask is safe as well.
+ */
+bool tick_resume_check_broadcast(void)
+{
+	if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT)
+		return false;
+	else
+		return cpumask_test_cpu(smp_processor_id(), tick_broadcast_mask);
+}
+
+void tick_resume_broadcast(void)
 {
 	struct clock_event_device *bc;
 	unsigned long flags;
-	int broadcast = 0;
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
 	bc = tick_broadcast_device.evtdev;
 
 	if (bc) {
-		clockevents_set_mode(bc, CLOCK_EVT_MODE_RESUME);
+		clockevents_tick_resume(bc);
 
 		switch (tick_broadcast_device.mode) {
 		case TICKDEV_MODE_PERIODIC:
 			if (!cpumask_empty(tick_broadcast_mask))
 				tick_broadcast_start_periodic(bc);
-			broadcast = cpumask_test_cpu(smp_processor_id(),
-						     tick_broadcast_mask);
 			break;
 		case TICKDEV_MODE_ONESHOT:
 			if (!cpumask_empty(tick_broadcast_mask))
-				broadcast = tick_resume_broadcast_oneshot(bc);
+				tick_resume_broadcast_oneshot(bc);
 			break;
 		}
 	}
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
-
-	return broadcast;
 }
 
-
 #ifdef CONFIG_TICK_ONESHOT
 
 static cpumask_var_t tick_broadcast_oneshot_mask;
@@ -532,8 +537,8 @@ static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
 {
 	int ret;
 
-	if (bc->mode != CLOCK_EVT_MODE_ONESHOT)
-		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+	if (bc->state != CLOCK_EVT_STATE_ONESHOT)
+		clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
 
 	ret = clockevents_program_event(bc, expires, force);
 	if (!ret)
@@ -541,10 +546,9 @@ static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
 	return ret;
 }
 
-int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
+static void tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 {
-	clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
-	return 0;
+	clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
 }
 
 /*
@@ -562,8 +566,8 @@ void tick_check_oneshot_broadcast_this_cpu(void)
 		 * switched over, leave the device alone.
 		 */
 		if (td->mode == TICKDEV_MODE_ONESHOT) {
-			clockevents_set_mode(td->evtdev,
-					     CLOCK_EVT_MODE_ONESHOT);
+			clockevents_set_state(td->evtdev,
+					      CLOCK_EVT_STATE_ONESHOT);
 		}
 	}
 }
@@ -666,31 +670,26 @@ static void broadcast_shutdown_local(struct clock_event_device *bc,
 		if (dev->next_event.tv64 < bc->next_event.tv64)
 			return;
 	}
-	clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+	clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 }
 
-static void broadcast_move_bc(int deadcpu)
-{
-	struct clock_event_device *bc = tick_broadcast_device.evtdev;
-
-	if (!bc || !broadcast_needs_cpu(bc, deadcpu))
-		return;
-	/* This moves the broadcast assignment to this cpu */
-	clockevents_program_event(bc, bc->next_event, 1);
-}
-
-/*
- * Powerstate information: The system enters/leaves a state, where
- * affected devices might stop
+/**
+ * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode
+ * @state:	The target state (enter/exit)
+ *
+ * The system enters/leaves a state, where affected devices might stop
  * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
+ *
+ * Called with interrupts disabled, so clockevents_lock is not
+ * required here because the local clock event device cannot go away
+ * under us.
  */
-int tick_broadcast_oneshot_control(unsigned long reason)
+int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 {
 	struct clock_event_device *bc, *dev;
 	struct tick_device *td;
-	unsigned long flags;
-	ktime_t now;
 	int cpu, ret = 0;
+	ktime_t now;
 
 	/*
 	 * Periodic mode does not care about the enter/exit of power
@@ -703,17 +702,17 @@ int tick_broadcast_oneshot_control(unsigned long reason)
 	 * We are called with preemtion disabled from the depth of the
 	 * idle code, so we can't be moved away.
 	 */
-	cpu = smp_processor_id();
-	td = &per_cpu(tick_cpu_device, cpu);
+	td = this_cpu_ptr(&tick_cpu_device);
 	dev = td->evtdev;
 
 	if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
 		return 0;
 
+	raw_spin_lock(&tick_broadcast_lock);
 	bc = tick_broadcast_device.evtdev;
+	cpu = smp_processor_id();
 
-	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
-	if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
+	if (state == TICK_BROADCAST_ENTER) {
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
 			WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
 			broadcast_shutdown_local(bc, dev);
@@ -741,7 +740,7 @@ int tick_broadcast_oneshot_control(unsigned long reason)
 			cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
 	} else {
 		if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
-			clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+			clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
 			/*
 			 * The cpu which was handling the broadcast
 			 * timer marked this cpu in the broadcast
@@ -805,9 +804,10 @@ int tick_broadcast_oneshot_control(unsigned long reason)
 		}
 	}
 out:
-	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+	raw_spin_unlock(&tick_broadcast_lock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control);
 
 /*
  * Reset the one shot broadcast for a cpu
@@ -842,7 +842,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 
 	/* Set it up only once ! */
 	if (bc->event_handler != tick_handle_oneshot_broadcast) {
-		int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
+		int was_periodic = bc->state == CLOCK_EVT_STATE_PERIODIC;
 
 		bc->event_handler = tick_handle_oneshot_broadcast;
 
@@ -858,7 +858,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 			   tick_broadcast_oneshot_mask, tmpmask);
 
 		if (was_periodic && !cpumask_empty(tmpmask)) {
-			clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+			clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
 			tick_broadcast_init_next_event(tmpmask,
 						       tick_next_period);
 			tick_broadcast_set_event(bc, cpu, tick_next_period, 1);
@@ -894,14 +894,28 @@ void tick_broadcast_switch_to_oneshot(void)
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+void hotplug_cpu__broadcast_tick_pull(int deadcpu)
+{
+	struct clock_event_device *bc;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+	bc = tick_broadcast_device.evtdev;
+
+	if (bc && broadcast_needs_cpu(bc, deadcpu)) {
+		/* This moves the broadcast assignment to this CPU: */
+		clockevents_program_event(bc, bc->next_event, 1);
+	}
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
 
 /*
  * Remove a dead CPU from broadcasting
  */
-void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
+void tick_shutdown_broadcast_oneshot(unsigned int cpu)
 {
 	unsigned long flags;
-	unsigned int cpu = *cpup;
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
@@ -913,10 +927,9 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
 	cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
 	cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
 
-	broadcast_move_bc(cpu);
-
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
+#endif
 
 /*
  * Check, whether the broadcast device is in one shot mode
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index f7c515595b42..3ae6afa1eb98 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -102,7 +102,7 @@ void tick_handle_periodic(struct clock_event_device *dev)
 
 	tick_periodic(cpu);
 
-	if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
+	if (dev->state != CLOCK_EVT_STATE_ONESHOT)
 		return;
 	for (;;) {
 		/*
@@ -140,7 +140,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 
 	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
 	    !tick_broadcast_oneshot_active()) {
-		clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC);
+		clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC);
 	} else {
 		unsigned long seq;
 		ktime_t next;
@@ -150,7 +150,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 			next = tick_next_period;
 		} while (read_seqretry(&jiffies_lock, seq));
 
-		clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+		clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
 
 		for (;;) {
 			if (!clockevents_program_event(dev, next, false))
@@ -332,14 +332,16 @@ out_bc:
 	tick_install_broadcast_device(newdev);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * Transfer the do_timer job away from a dying cpu.
  *
- * Called with interrupts disabled.
+ * Called with interrupts disabled. Not locking required. If
+ * tick_do_timer_cpu is owned by this cpu, nothing can change it.
  */
-void tick_handover_do_timer(int *cpup)
+void tick_handover_do_timer(void)
 {
-	if (*cpup == tick_do_timer_cpu) {
+	if (tick_do_timer_cpu == smp_processor_id()) {
 		int cpu = cpumask_first(cpu_online_mask);
 
 		tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
@@ -354,9 +356,9 @@ void tick_handover_do_timer(int *cpup)
  * access the hardware device itself.
  * We just set the mode and remove it from the lists.
  */
-void tick_shutdown(unsigned int *cpup)
+void tick_shutdown(unsigned int cpu)
 {
-	struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
+	struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
 	struct clock_event_device *dev = td->evtdev;
 
 	td->mode = TICKDEV_MODE_PERIODIC;
@@ -365,27 +367,42 @@ void tick_shutdown(unsigned int *cpup)
 		 * Prevent that the clock events layer tries to call
 		 * the set mode function!
 		 */
+		dev->state = CLOCK_EVT_STATE_DETACHED;
 		dev->mode = CLOCK_EVT_MODE_UNUSED;
 		clockevents_exchange_device(dev, NULL);
 		dev->event_handler = clockevents_handle_noop;
 		td->evtdev = NULL;
 	}
 }
+#endif
 
-void tick_suspend(void)
+/**
+ * tick_suspend_local - Suspend the local tick device
+ *
+ * Called from the local cpu for freeze with interrupts disabled.
+ *
+ * No locks required. Nothing can change the per cpu device.
+ */
+void tick_suspend_local(void)
 {
 	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 
 	clockevents_shutdown(td->evtdev);
 }
 
-void tick_resume(void)
+/**
+ * tick_resume_local - Resume the local tick device
+ *
+ * Called from the local CPU for unfreeze or XEN resume magic.
+ *
+ * No locks required. Nothing can change the per cpu device.
+ */
+void tick_resume_local(void)
 {
 	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
-	int broadcast = tick_resume_broadcast();
-
-	clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME);
+	bool broadcast = tick_resume_check_broadcast();
 
+	clockevents_tick_resume(td->evtdev);
 	if (!broadcast) {
 		if (td->mode == TICKDEV_MODE_PERIODIC)
 			tick_setup_periodic(td->evtdev, 0);
@@ -394,6 +411,35 @@ void tick_resume(void)
 	}
 }
 
+/**
+ * tick_suspend - Suspend the tick and the broadcast device
+ *
+ * Called from syscore_suspend() via timekeeping_suspend with only one
+ * CPU online and interrupts disabled or from tick_unfreeze() under
+ * tick_freeze_lock.
+ *
+ * No locks required. Nothing can change the per cpu device.
+ */
+void tick_suspend(void)
+{
+	tick_suspend_local();
+	tick_suspend_broadcast();
+}
+
+/**
+ * tick_resume - Resume the tick and the broadcast device
+ *
+ * Called from syscore_resume() via timekeeping_resume with only one
+ * CPU online and interrupts disabled.
+ *
+ * No locks required. Nothing can change the per cpu device.
+ */
+void tick_resume(void)
+{
+	tick_resume_broadcast();
+	tick_resume_local();
+}
+
 static DEFINE_RAW_SPINLOCK(tick_freeze_lock);
 static unsigned int tick_freeze_depth;
 
@@ -411,12 +457,10 @@ void tick_freeze(void)
 	raw_spin_lock(&tick_freeze_lock);
 
 	tick_freeze_depth++;
-	if (tick_freeze_depth == num_online_cpus()) {
+	if (tick_freeze_depth == num_online_cpus())
 		timekeeping_suspend();
-	} else {
-		tick_suspend();
-		tick_suspend_broadcast();
-	}
+	else
+		tick_suspend_local();
 
 	raw_spin_unlock(&tick_freeze_lock);
 }
@@ -437,7 +481,7 @@ void tick_unfreeze(void)
 	if (tick_freeze_depth == num_online_cpus())
 		timekeeping_resume();
 	else
-		tick_resume();
+		tick_resume_local();
 
 	tick_freeze_depth--;
 
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 366aeb4f2c66..b64fdd8054c5 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -5,15 +5,12 @@
 #include <linux/tick.h>
 
 #include "timekeeping.h"
+#include "tick-sched.h"
 
-extern seqlock_t jiffies_lock;
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
 
-#define CS_NAME_LEN	32
-
-#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD
-
-#define TICK_DO_TIMER_NONE	-1
-#define TICK_DO_TIMER_BOOT	-2
+# define TICK_DO_TIMER_NONE	-1
+# define TICK_DO_TIMER_BOOT	-2
 
 DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
 extern ktime_t tick_next_period;
@@ -23,21 +20,72 @@ 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_shutdown(unsigned int cpu);
 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 int tick_is_oneshot_available(void);
+extern struct tick_device *tick_get_device(int cpu);
 
-extern void clockevents_shutdown(struct clock_event_device *dev);
+extern int clockevents_tick_resume(struct clock_event_device *dev);
+/* Check, if the device is functional or a dummy for broadcast */
+static inline int tick_device_is_functional(struct clock_event_device *dev)
+{
+	return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
+}
 
+extern void clockevents_shutdown(struct clock_event_device *dev);
+extern void clockevents_exchange_device(struct clock_event_device *old,
+					struct clock_event_device *new);
+extern void clockevents_set_state(struct clock_event_device *dev,
+				 enum clock_event_state state);
+extern int clockevents_program_event(struct clock_event_device *dev,
+				     ktime_t expires, bool force);
+extern void clockevents_handle_noop(struct clock_event_device *dev);
+extern int __clockevents_update_freq(struct clock_event_device *dev, u32 freq);
 extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
 
-/*
- * NO_HZ / high resolution timer shared code
- */
+/* Broadcasting support */
+# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
+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_shutdown_broadcast(unsigned int cpu);
+extern void tick_suspend_broadcast(void);
+extern void tick_resume_broadcast(void);
+extern bool tick_resume_check_broadcast(void);
+extern void tick_broadcast_init(void);
+extern void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
+extern int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq);
+extern struct tick_device *tick_get_broadcast_device(void);
+extern struct cpumask *tick_get_broadcast_mask(void);
+# else /* !CONFIG_GENERIC_CLOCKEVENTS_BROADCAST: */
+static inline void tick_install_broadcast_device(struct clock_event_device *dev) { }
+static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; }
+static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; }
+static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { }
+static inline void tick_shutdown_broadcast(unsigned int cpu) { }
+static inline void tick_suspend_broadcast(void) { }
+static inline void tick_resume_broadcast(void) { }
+static inline bool tick_resume_check_broadcast(void) { return false; }
+static inline void tick_broadcast_init(void) { }
+static inline int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq) { return -ENODEV; }
+
+/* Set the periodic handler in non broadcast mode */
+static inline void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast)
+{
+	dev->event_handler = tick_handle_periodic;
+}
+# endif /* !CONFIG_GENERIC_CLOCKEVENTS_BROADCAST */
+
+#else /* !GENERIC_CLOCKEVENTS: */
+static inline void tick_suspend(void) { }
+static inline void tick_resume(void) { }
+#endif /* !GENERIC_CLOCKEVENTS */
+
+/* Oneshot related functions */
 #ifdef CONFIG_TICK_ONESHOT
 extern void tick_setup_oneshot(struct clock_event_device *newdev,
 			       void (*handler)(struct clock_event_device *),
@@ -46,58 +94,42 @@ 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 *));
 extern void tick_resume_oneshot(void);
-# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+static inline bool tick_oneshot_possible(void) { return true; }
+extern int tick_oneshot_mode_active(void);
+extern void tick_clock_notify(void);
+extern int tick_check_oneshot_change(int allow_nohz);
+extern int tick_init_highres(void);
+#else /* !CONFIG_TICK_ONESHOT: */
+static inline
+void tick_setup_oneshot(struct clock_event_device *newdev,
+			void (*handler)(struct clock_event_device *),
+			ktime_t nextevt) { BUG(); }
+static inline void tick_resume_oneshot(void) { BUG(); }
+static inline int tick_program_event(ktime_t expires, int force) { return 0; }
+static inline void tick_oneshot_notify(void) { }
+static inline bool tick_oneshot_possible(void) { return false; }
+static inline int tick_oneshot_mode_active(void) { return 0; }
+static inline void tick_clock_notify(void) { }
+static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
+#endif /* !CONFIG_TICK_ONESHOT */
+
+/* Functions related to oneshot broadcasting */
+#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
 extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
-extern int 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 void tick_shutdown_broadcast_oneshot(unsigned int cpu);
 extern int tick_broadcast_oneshot_active(void);
 extern void tick_check_oneshot_broadcast_this_cpu(void);
 bool tick_broadcast_oneshot_available(void);
-# else /* BROADCAST */
-static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
-{
-	BUG();
-}
-static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
+extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
+#else /* !(BROADCAST && ONESHOT): */
+static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); }
 static inline void tick_broadcast_switch_to_oneshot(void) { }
-static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
+static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
 static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
-static inline bool tick_broadcast_oneshot_available(void) { return true; }
-# endif /* !BROADCAST */
-
-#else /* !ONESHOT */
-static inline
-void tick_setup_oneshot(struct clock_event_device *newdev,
-			void (*handler)(struct clock_event_device *),
-			ktime_t nextevt)
-{
-	BUG();
-}
-static inline void tick_resume_oneshot(void)
-{
-	BUG();
-}
-static inline int tick_program_event(ktime_t expires, int force)
-{
-	return 0;
-}
-static inline void tick_oneshot_notify(void) { }
-static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
-{
-	BUG();
-}
-static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
-static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
-static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
-{
-	return 0;
-}
-static inline int tick_broadcast_oneshot_active(void) { return 0; }
-static inline bool tick_broadcast_oneshot_available(void) { return false; }
-#endif /* !TICK_ONESHOT */
+static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); }
+#endif /* !(BROADCAST && ONESHOT) */
 
 /* NO_HZ_FULL internal */
 #ifdef CONFIG_NO_HZ_FULL
@@ -105,68 +137,3 @@ extern void tick_nohz_init(void);
 # else
 static inline void tick_nohz_init(void) { }
 #endif
-
-/*
- * Broadcasting support
- */
-#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
-extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
-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);
-extern void tick_suspend_broadcast(void);
-extern int tick_resume_broadcast(void);
-extern void tick_broadcast_init(void);
-extern void
-tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
-int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq);
-
-#else /* !BROADCAST */
-
-static inline void tick_install_broadcast_device(struct clock_event_device *dev)
-{
-}
-
-static inline int tick_is_broadcast_device(struct clock_event_device *dev)
-{
-	return 0;
-}
-static inline int tick_device_uses_broadcast(struct clock_event_device *dev,
-					     int cpu)
-{
-	return 0;
-}
-static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { }
-static inline void tick_broadcast_on_off(unsigned long reason, int *oncpu) { }
-static inline void tick_shutdown_broadcast(unsigned int *cpup) { }
-static inline void tick_suspend_broadcast(void) { }
-static inline int tick_resume_broadcast(void) { return 0; }
-static inline void tick_broadcast_init(void) { }
-static inline int tick_broadcast_update_freq(struct clock_event_device *dev,
-					     u32 freq) { return -ENODEV; }
-
-/*
- * Set the periodic handler in non broadcast mode
- */
-static inline void tick_set_periodic_handler(struct clock_event_device *dev,
-					     int broadcast)
-{
-	dev->event_handler = tick_handle_periodic;
-}
-#endif /* !BROADCAST */
-
-/*
- * Check, if the device is functional or a dummy for broadcast
- */
-static inline int tick_device_is_functional(struct clock_event_device *dev)
-{
-	return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
-}
-
-int __clockevents_update_freq(struct clock_event_device *dev, u32 freq);
-
-#endif
-
-extern void do_timer(unsigned long ticks);
-extern void update_wall_time(void);
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 7ce740e78e1b..67a64b1670bf 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -38,7 +38,7 @@ void tick_resume_oneshot(void)
 {
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 
-	clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+	clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
 	clockevents_program_event(dev, ktime_get(), true);
 }
 
@@ -50,7 +50,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev,
 			ktime_t next_event)
 {
 	newdev->event_handler = handler;
-	clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT);
+	clockevents_set_state(newdev, CLOCK_EVT_STATE_ONESHOT);
 	clockevents_program_event(newdev, next_event, true);
 }
 
@@ -81,7 +81,7 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
 
 	td->mode = TICKDEV_MODE_ONESHOT;
 	dev->event_handler = handler;
-	clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+	clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
 	tick_broadcast_switch_to_oneshot();
 	return 0;
 }
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index a4c4edac4528..914259128145 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -34,7 +34,7 @@
 /*
  * Per cpu nohz control structure
  */
-DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
+static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
 
 /*
  * The time, when the last jiffy update happened. Protected by jiffies_lock.
@@ -416,6 +416,11 @@ static int __init setup_tick_nohz(char *str)
 
 __setup("nohz=", setup_tick_nohz);
 
+int tick_nohz_tick_stopped(void)
+{
+	return __this_cpu_read(tick_cpu_sched.tick_stopped);
+}
+
 /**
  * tick_nohz_update_jiffies - update jiffies when idle was interrupted
  *
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
new file mode 100644
index 000000000000..28b5da3e1a17
--- /dev/null
+++ b/kernel/time/tick-sched.h
@@ -0,0 +1,74 @@
+#ifndef _TICK_SCHED_H
+#define _TICK_SCHED_H
+
+#include <linux/hrtimer.h>
+
+enum tick_device_mode {
+	TICKDEV_MODE_PERIODIC,
+	TICKDEV_MODE_ONESHOT,
+};
+
+struct tick_device {
+	struct clock_event_device *evtdev;
+	enum tick_device_mode mode;
+};
+
+enum tick_nohz_mode {
+	NOHZ_MODE_INACTIVE,
+	NOHZ_MODE_LOWRES,
+	NOHZ_MODE_HIGHRES,
+};
+
+/**
+ * struct tick_sched - sched tick emulation and no idle tick control/stats
+ * @sched_timer:	hrtimer to schedule the periodic tick in high
+ *			resolution mode
+ * @last_tick:		Store the last tick expiry time when the tick
+ *			timer is modified for nohz sleeps. This is necessary
+ *			to resume the tick timer operation in the timeline
+ *			when the CPU returns from nohz sleep.
+ * @tick_stopped:	Indicator that the idle tick has been stopped
+ * @idle_jiffies:	jiffies at the entry to idle for idle time accounting
+ * @idle_calls:		Total number of idle calls
+ * @idle_sleeps:	Number of idle calls, where the sched tick was stopped
+ * @idle_entrytime:	Time when the idle call was entered
+ * @idle_waketime:	Time when the idle was interrupted
+ * @idle_exittime:	Time when the idle state was left
+ * @idle_sleeptime:	Sum of the time slept in idle with sched tick stopped
+ * @iowait_sleeptime:	Sum of the time slept in idle with sched tick stopped, with IO outstanding
+ * @sleep_length:	Duration of the current idle sleep
+ * @do_timer_lst:	CPU was the last one doing do_timer before going idle
+ */
+struct tick_sched {
+	struct hrtimer			sched_timer;
+	unsigned long			check_clocks;
+	enum tick_nohz_mode		nohz_mode;
+	ktime_t				last_tick;
+	int				inidle;
+	int				tick_stopped;
+	unsigned long			idle_jiffies;
+	unsigned long			idle_calls;
+	unsigned long			idle_sleeps;
+	int				idle_active;
+	ktime_t				idle_entrytime;
+	ktime_t				idle_waketime;
+	ktime_t				idle_exittime;
+	ktime_t				idle_sleeptime;
+	ktime_t				iowait_sleeptime;
+	ktime_t				sleep_length;
+	unsigned long			last_jiffies;
+	unsigned long			next_jiffies;
+	ktime_t				idle_expires;
+	int				do_timer_last;
+};
+
+extern struct tick_sched *tick_get_tick_sched(int cpu);
+
+extern void tick_setup_sched_timer(void);
+#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS
+extern void tick_cancel_sched_timer(int cpu);
+#else
+static inline void tick_cancel_sched_timer(int cpu) { }
+#endif
+
+#endif
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 91db94136c10..946acb72179f 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -59,17 +59,15 @@ struct tk_fast {
 };
 
 static struct tk_fast tk_fast_mono ____cacheline_aligned;
+static struct tk_fast tk_fast_raw  ____cacheline_aligned;
 
 /* flag for if timekeeping is suspended */
 int __read_mostly timekeeping_suspended;
 
-/* Flag for if there is a persistent clock on this platform */
-bool __read_mostly persistent_clock_exist = false;
-
 static inline void tk_normalize_xtime(struct timekeeper *tk)
 {
-	while (tk->tkr.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr.shift)) {
-		tk->tkr.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr.shift;
+	while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) {
+		tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift;
 		tk->xtime_sec++;
 	}
 }
@@ -79,20 +77,20 @@ static inline struct timespec64 tk_xtime(struct timekeeper *tk)
 	struct timespec64 ts;
 
 	ts.tv_sec = tk->xtime_sec;
-	ts.tv_nsec = (long)(tk->tkr.xtime_nsec >> tk->tkr.shift);
+	ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
 	return ts;
 }
 
 static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts)
 {
 	tk->xtime_sec = ts->tv_sec;
-	tk->tkr.xtime_nsec = (u64)ts->tv_nsec << tk->tkr.shift;
+	tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift;
 }
 
 static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
 {
 	tk->xtime_sec += ts->tv_sec;
-	tk->tkr.xtime_nsec += (u64)ts->tv_nsec << tk->tkr.shift;
+	tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift;
 	tk_normalize_xtime(tk);
 }
 
@@ -118,6 +116,117 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
 	tk->offs_boot = ktime_add(tk->offs_boot, delta);
 }
 
+#ifdef CONFIG_DEBUG_TIMEKEEPING
+#define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */
+/*
+ * These simple flag variables are managed
+ * without locks, which is racy, but ok since
+ * we don't really care about being super
+ * precise about how many events were seen,
+ * just that a problem was observed.
+ */
+static int timekeeping_underflow_seen;
+static int timekeeping_overflow_seen;
+
+/* last_warning is only modified under the timekeeping lock */
+static long timekeeping_last_warning;
+
+static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset)
+{
+
+	cycle_t max_cycles = tk->tkr_mono.clock->max_cycles;
+	const char *name = tk->tkr_mono.clock->name;
+
+	if (offset > max_cycles) {
+		printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n",
+				offset, name, max_cycles);
+		printk_deferred("         timekeeping: Your kernel is sick, but tries to cope by capping time updates\n");
+	} else {
+		if (offset > (max_cycles >> 1)) {
+			printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the the '%s' clock's 50%% safety margin (%lld)\n",
+					offset, name, max_cycles >> 1);
+			printk_deferred("      timekeeping: Your kernel is still fine, but is feeling a bit nervous\n");
+		}
+	}
+
+	if (timekeeping_underflow_seen) {
+		if (jiffies - timekeeping_last_warning > WARNING_FREQ) {
+			printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name);
+			printk_deferred("         Please report this, consider using a different clocksource, if possible.\n");
+			printk_deferred("         Your kernel is probably still fine.\n");
+			timekeeping_last_warning = jiffies;
+		}
+		timekeeping_underflow_seen = 0;
+	}
+
+	if (timekeeping_overflow_seen) {
+		if (jiffies - timekeeping_last_warning > WARNING_FREQ) {
+			printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name);
+			printk_deferred("         Please report this, consider using a different clocksource, if possible.\n");
+			printk_deferred("         Your kernel is probably still fine.\n");
+			timekeeping_last_warning = jiffies;
+		}
+		timekeeping_overflow_seen = 0;
+	}
+}
+
+static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
+{
+	cycle_t now, last, mask, max, delta;
+	unsigned int seq;
+
+	/*
+	 * Since we're called holding a seqlock, the data may shift
+	 * under us while we're doing the calculation. This can cause
+	 * false positives, since we'd note a problem but throw the
+	 * results away. So nest another seqlock here to atomically
+	 * grab the points we are checking with.
+	 */
+	do {
+		seq = read_seqcount_begin(&tk_core.seq);
+		now = tkr->read(tkr->clock);
+		last = tkr->cycle_last;
+		mask = tkr->mask;
+		max = tkr->clock->max_cycles;
+	} while (read_seqcount_retry(&tk_core.seq, seq));
+
+	delta = clocksource_delta(now, last, mask);
+
+	/*
+	 * Try to catch underflows by checking if we are seeing small
+	 * mask-relative negative values.
+	 */
+	if (unlikely((~delta & mask) < (mask >> 3))) {
+		timekeeping_underflow_seen = 1;
+		delta = 0;
+	}
+
+	/* Cap delta value to the max_cycles values to avoid mult overflows */
+	if (unlikely(delta > max)) {
+		timekeeping_overflow_seen = 1;
+		delta = tkr->clock->max_cycles;
+	}
+
+	return delta;
+}
+#else
+static inline void timekeeping_check_update(struct timekeeper *tk, cycle_t offset)
+{
+}
+static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
+{
+	cycle_t cycle_now, delta;
+
+	/* read clocksource */
+	cycle_now = tkr->read(tkr->clock);
+
+	/* calculate the delta since the last update_wall_time */
+	delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask);
+
+	return delta;
+}
+#endif
+
 /**
  * tk_setup_internals - Set up internals to use clocksource clock.
  *
@@ -135,11 +244,16 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 	u64 tmp, ntpinterval;
 	struct clocksource *old_clock;
 
-	old_clock = tk->tkr.clock;
-	tk->tkr.clock = clock;
-	tk->tkr.read = clock->read;
-	tk->tkr.mask = clock->mask;
-	tk->tkr.cycle_last = tk->tkr.read(clock);
+	old_clock = tk->tkr_mono.clock;
+	tk->tkr_mono.clock = clock;
+	tk->tkr_mono.read = clock->read;
+	tk->tkr_mono.mask = clock->mask;
+	tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock);
+
+	tk->tkr_raw.clock = clock;
+	tk->tkr_raw.read = clock->read;
+	tk->tkr_raw.mask = clock->mask;
+	tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last;
 
 	/* Do the ns -> cycle conversion first, using original mult */
 	tmp = NTP_INTERVAL_LENGTH;
@@ -163,11 +277,14 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 	if (old_clock) {
 		int shift_change = clock->shift - old_clock->shift;
 		if (shift_change < 0)
-			tk->tkr.xtime_nsec >>= -shift_change;
+			tk->tkr_mono.xtime_nsec >>= -shift_change;
 		else
-			tk->tkr.xtime_nsec <<= shift_change;
+			tk->tkr_mono.xtime_nsec <<= shift_change;
 	}
-	tk->tkr.shift = clock->shift;
+	tk->tkr_raw.xtime_nsec = 0;
+
+	tk->tkr_mono.shift = clock->shift;
+	tk->tkr_raw.shift = clock->shift;
 
 	tk->ntp_error = 0;
 	tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift;
@@ -178,7 +295,8 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 	 * active clocksource. These value will be adjusted via NTP
 	 * to counteract clock drifting.
 	 */
-	tk->tkr.mult = clock->mult;
+	tk->tkr_mono.mult = clock->mult;
+	tk->tkr_raw.mult = clock->mult;
 	tk->ntp_err_mult = 0;
 }
 
@@ -193,14 +311,10 @@ static inline u32 arch_gettimeoffset(void) { return 0; }
 
 static inline s64 timekeeping_get_ns(struct tk_read_base *tkr)
 {
-	cycle_t cycle_now, delta;
+	cycle_t delta;
 	s64 nsec;
 
-	/* read clocksource: */
-	cycle_now = tkr->read(tkr->clock);
-
-	/* calculate the delta since the last update_wall_time: */
-	delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask);
+	delta = timekeeping_get_delta(tkr);
 
 	nsec = delta * tkr->mult + tkr->xtime_nsec;
 	nsec >>= tkr->shift;
@@ -209,25 +323,6 @@ static inline s64 timekeeping_get_ns(struct tk_read_base *tkr)
 	return nsec + arch_gettimeoffset();
 }
 
-static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
-{
-	struct clocksource *clock = tk->tkr.clock;
-	cycle_t cycle_now, delta;
-	s64 nsec;
-
-	/* read clocksource: */
-	cycle_now = tk->tkr.read(clock);
-
-	/* calculate the delta since the last update_wall_time: */
-	delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask);
-
-	/* convert delta to nanoseconds. */
-	nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift);
-
-	/* If arch requires, add in get_arch_timeoffset() */
-	return nsec + arch_gettimeoffset();
-}
-
 /**
  * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper.
  * @tkr: Timekeeping readout base from which we take the update
@@ -267,18 +362,18 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
  * slightly wrong timestamp (a few nanoseconds). See
  * @ktime_get_mono_fast_ns.
  */
-static void update_fast_timekeeper(struct tk_read_base *tkr)
+static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf)
 {
-	struct tk_read_base *base = tk_fast_mono.base;
+	struct tk_read_base *base = tkf->base;
 
 	/* Force readers off to base[1] */
-	raw_write_seqcount_latch(&tk_fast_mono.seq);
+	raw_write_seqcount_latch(&tkf->seq);
 
 	/* Update base[0] */
 	memcpy(base, tkr, sizeof(*base));
 
 	/* Force readers back to base[0] */
-	raw_write_seqcount_latch(&tk_fast_mono.seq);
+	raw_write_seqcount_latch(&tkf->seq);
 
 	/* Update base[1] */
 	memcpy(base + 1, base, sizeof(*base));
@@ -316,22 +411,33 @@ static void update_fast_timekeeper(struct tk_read_base *tkr)
  * of the following timestamps. Callers need to be aware of that and
  * deal with it.
  */
-u64 notrace ktime_get_mono_fast_ns(void)
+static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
 {
 	struct tk_read_base *tkr;
 	unsigned int seq;
 	u64 now;
 
 	do {
-		seq = raw_read_seqcount(&tk_fast_mono.seq);
-		tkr = tk_fast_mono.base + (seq & 0x01);
-		now = ktime_to_ns(tkr->base_mono) + timekeeping_get_ns(tkr);
+		seq = raw_read_seqcount(&tkf->seq);
+		tkr = tkf->base + (seq & 0x01);
+		now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr);
+	} while (read_seqcount_retry(&tkf->seq, seq));
 
-	} while (read_seqcount_retry(&tk_fast_mono.seq, seq));
 	return now;
 }
+
+u64 ktime_get_mono_fast_ns(void)
+{
+	return __ktime_get_fast_ns(&tk_fast_mono);
+}
 EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns);
 
+u64 ktime_get_raw_fast_ns(void)
+{
+	return __ktime_get_fast_ns(&tk_fast_raw);
+}
+EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns);
+
 /* Suspend-time cycles value for halted fast timekeeper. */
 static cycle_t cycles_at_suspend;
 
@@ -353,12 +459,17 @@ static cycle_t dummy_clock_read(struct clocksource *cs)
 static void halt_fast_timekeeper(struct timekeeper *tk)
 {
 	static struct tk_read_base tkr_dummy;
-	struct tk_read_base *tkr = &tk->tkr;
+	struct tk_read_base *tkr = &tk->tkr_mono;
 
 	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
 	cycles_at_suspend = tkr->read(tkr->clock);
 	tkr_dummy.read = dummy_clock_read;
-	update_fast_timekeeper(&tkr_dummy);
+	update_fast_timekeeper(&tkr_dummy, &tk_fast_mono);
+
+	tkr = &tk->tkr_raw;
+	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
+	tkr_dummy.read = dummy_clock_read;
+	update_fast_timekeeper(&tkr_dummy, &tk_fast_raw);
 }
 
 #ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD
@@ -369,8 +480,8 @@ static inline void update_vsyscall(struct timekeeper *tk)
 
 	xt = timespec64_to_timespec(tk_xtime(tk));
 	wm = timespec64_to_timespec(tk->wall_to_monotonic);
-	update_vsyscall_old(&xt, &wm, tk->tkr.clock, tk->tkr.mult,
-			    tk->tkr.cycle_last);
+	update_vsyscall_old(&xt, &wm, tk->tkr_mono.clock, tk->tkr_mono.mult,
+			    tk->tkr_mono.cycle_last);
 }
 
 static inline void old_vsyscall_fixup(struct timekeeper *tk)
@@ -387,11 +498,11 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
 	* (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD
 	* users are removed, this can be killed.
 	*/
-	remainder = tk->tkr.xtime_nsec & ((1ULL << tk->tkr.shift) - 1);
-	tk->tkr.xtime_nsec -= remainder;
-	tk->tkr.xtime_nsec += 1ULL << tk->tkr.shift;
+	remainder = tk->tkr_mono.xtime_nsec & ((1ULL << tk->tkr_mono.shift) - 1);
+	tk->tkr_mono.xtime_nsec -= remainder;
+	tk->tkr_mono.xtime_nsec += 1ULL << tk->tkr_mono.shift;
 	tk->ntp_error += remainder << tk->ntp_error_shift;
-	tk->ntp_error -= (1ULL << tk->tkr.shift) << tk->ntp_error_shift;
+	tk->ntp_error -= (1ULL << tk->tkr_mono.shift) << tk->ntp_error_shift;
 }
 #else
 #define old_vsyscall_fixup(tk)
@@ -456,17 +567,17 @@ static inline void tk_update_ktime_data(struct timekeeper *tk)
 	 */
 	seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec);
 	nsec = (u32) tk->wall_to_monotonic.tv_nsec;
-	tk->tkr.base_mono = ns_to_ktime(seconds * NSEC_PER_SEC + nsec);
+	tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec);
 
 	/* Update the monotonic raw base */
-	tk->base_raw = timespec64_to_ktime(tk->raw_time);
+	tk->tkr_raw.base = timespec64_to_ktime(tk->raw_time);
 
 	/*
 	 * The sum of the nanoseconds portions of xtime and
 	 * wall_to_monotonic can be greater/equal one second. Take
 	 * this into account before updating tk->ktime_sec.
 	 */
-	nsec += (u32)(tk->tkr.xtime_nsec >> tk->tkr.shift);
+	nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
 	if (nsec >= NSEC_PER_SEC)
 		seconds++;
 	tk->ktime_sec = seconds;
@@ -489,7 +600,8 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
 		memcpy(&shadow_timekeeper, &tk_core.timekeeper,
 		       sizeof(tk_core.timekeeper));
 
-	update_fast_timekeeper(&tk->tkr);
+	update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono);
+	update_fast_timekeeper(&tk->tkr_raw,  &tk_fast_raw);
 }
 
 /**
@@ -501,22 +613,23 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
  */
 static void timekeeping_forward_now(struct timekeeper *tk)
 {
-	struct clocksource *clock = tk->tkr.clock;
+	struct clocksource *clock = tk->tkr_mono.clock;
 	cycle_t cycle_now, delta;
 	s64 nsec;
 
-	cycle_now = tk->tkr.read(clock);
-	delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask);
-	tk->tkr.cycle_last = cycle_now;
+	cycle_now = tk->tkr_mono.read(clock);
+	delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
+	tk->tkr_mono.cycle_last = cycle_now;
+	tk->tkr_raw.cycle_last  = cycle_now;
 
-	tk->tkr.xtime_nsec += delta * tk->tkr.mult;
+	tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult;
 
 	/* If arch requires, add in get_arch_timeoffset() */
-	tk->tkr.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr.shift;
+	tk->tkr_mono.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_mono.shift;
 
 	tk_normalize_xtime(tk);
 
-	nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift);
+	nsec = clocksource_cyc2ns(delta, tk->tkr_raw.mult, tk->tkr_raw.shift);
 	timespec64_add_ns(&tk->raw_time, nsec);
 }
 
@@ -537,7 +650,7 @@ int __getnstimeofday64(struct timespec64 *ts)
 		seq = read_seqcount_begin(&tk_core.seq);
 
 		ts->tv_sec = tk->xtime_sec;
-		nsecs = timekeeping_get_ns(&tk->tkr);
+		nsecs = timekeeping_get_ns(&tk->tkr_mono);
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -577,8 +690,8 @@ ktime_t ktime_get(void)
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
-		base = tk->tkr.base_mono;
-		nsecs = timekeeping_get_ns(&tk->tkr);
+		base = tk->tkr_mono.base;
+		nsecs = timekeeping_get_ns(&tk->tkr_mono);
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -603,8 +716,8 @@ ktime_t ktime_get_with_offset(enum tk_offsets offs)
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
-		base = ktime_add(tk->tkr.base_mono, *offset);
-		nsecs = timekeeping_get_ns(&tk->tkr);
+		base = ktime_add(tk->tkr_mono.base, *offset);
+		nsecs = timekeeping_get_ns(&tk->tkr_mono);
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -645,8 +758,8 @@ ktime_t ktime_get_raw(void)
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
-		base = tk->base_raw;
-		nsecs = timekeeping_get_ns_raw(tk);
+		base = tk->tkr_raw.base;
+		nsecs = timekeeping_get_ns(&tk->tkr_raw);
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -674,7 +787,7 @@ void ktime_get_ts64(struct timespec64 *ts)
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 		ts->tv_sec = tk->xtime_sec;
-		nsec = timekeeping_get_ns(&tk->tkr);
+		nsec = timekeeping_get_ns(&tk->tkr_mono);
 		tomono = tk->wall_to_monotonic;
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
@@ -759,8 +872,8 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
 		ts_real->tv_sec = tk->xtime_sec;
 		ts_real->tv_nsec = 0;
 
-		nsecs_raw = timekeeping_get_ns_raw(tk);
-		nsecs_real = timekeeping_get_ns(&tk->tkr);
+		nsecs_raw  = timekeeping_get_ns(&tk->tkr_raw);
+		nsecs_real = timekeeping_get_ns(&tk->tkr_mono);
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -943,7 +1056,7 @@ static int change_clocksource(void *data)
 	 */
 	if (try_module_get(new->owner)) {
 		if (!new->enable || new->enable(new) == 0) {
-			old = tk->tkr.clock;
+			old = tk->tkr_mono.clock;
 			tk_setup_internals(tk, new);
 			if (old->disable)
 				old->disable(old);
@@ -971,11 +1084,11 @@ int timekeeping_notify(struct clocksource *clock)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 
-	if (tk->tkr.clock == clock)
+	if (tk->tkr_mono.clock == clock)
 		return 0;
 	stop_machine(change_clocksource, clock, NULL);
 	tick_clock_notify();
-	return tk->tkr.clock == clock ? 0 : -1;
+	return tk->tkr_mono.clock == clock ? 0 : -1;
 }
 
 /**
@@ -993,7 +1106,7 @@ void getrawmonotonic64(struct timespec64 *ts)
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
-		nsecs = timekeeping_get_ns_raw(tk);
+		nsecs = timekeeping_get_ns(&tk->tkr_raw);
 		ts64 = tk->raw_time;
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
@@ -1016,7 +1129,7 @@ int timekeeping_valid_for_hres(void)
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
-		ret = tk->tkr.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
+		ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -1035,7 +1148,7 @@ u64 timekeeping_max_deferment(void)
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
-		ret = tk->tkr.clock->max_idle_ns;
+		ret = tk->tkr_mono.clock->max_idle_ns;
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -1057,6 +1170,14 @@ void __weak read_persistent_clock(struct timespec *ts)
 	ts->tv_nsec = 0;
 }
 
+void __weak read_persistent_clock64(struct timespec64 *ts64)
+{
+	struct timespec ts;
+
+	read_persistent_clock(&ts);
+	*ts64 = timespec_to_timespec64(ts);
+}
+
 /**
  * read_boot_clock -  Return time of the system start.
  *
@@ -1072,6 +1193,20 @@ void __weak read_boot_clock(struct timespec *ts)
 	ts->tv_nsec = 0;
 }
 
+void __weak read_boot_clock64(struct timespec64 *ts64)
+{
+	struct timespec ts;
+
+	read_boot_clock(&ts);
+	*ts64 = timespec_to_timespec64(ts);
+}
+
+/* Flag for if timekeeping_resume() has injected sleeptime */
+static bool sleeptime_injected;
+
+/* Flag for if there is a persistent clock on this platform */
+static bool persistent_clock_exists;
+
 /*
  * timekeeping_init - Initializes the clocksource and common timekeeping values
  */
@@ -1081,20 +1216,17 @@ void __init timekeeping_init(void)
 	struct clocksource *clock;
 	unsigned long flags;
 	struct timespec64 now, boot, tmp;
-	struct timespec ts;
 
-	read_persistent_clock(&ts);
-	now = timespec_to_timespec64(ts);
+	read_persistent_clock64(&now);
 	if (!timespec64_valid_strict(&now)) {
 		pr_warn("WARNING: Persistent clock returned invalid value!\n"
 			"         Check your CMOS/BIOS settings.\n");
 		now.tv_sec = 0;
 		now.tv_nsec = 0;
 	} else if (now.tv_sec || now.tv_nsec)
-		persistent_clock_exist = true;
+		persistent_clock_exists = true;
 
-	read_boot_clock(&ts);
-	boot = timespec_to_timespec64(ts);
+	read_boot_clock64(&boot);
 	if (!timespec64_valid_strict(&boot)) {
 		pr_warn("WARNING: Boot clock returned invalid value!\n"
 			"         Check your CMOS/BIOS settings.\n");
@@ -1114,7 +1246,6 @@ void __init timekeeping_init(void)
 	tk_set_xtime(tk, &now);
 	tk->raw_time.tv_sec = 0;
 	tk->raw_time.tv_nsec = 0;
-	tk->base_raw.tv64 = 0;
 	if (boot.tv_sec == 0 && boot.tv_nsec == 0)
 		boot = tk_xtime(tk);
 
@@ -1127,7 +1258,7 @@ void __init timekeeping_init(void)
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 }
 
-/* time in seconds when suspend began */
+/* time in seconds when suspend began for persistent clock */
 static struct timespec64 timekeeping_suspend_time;
 
 /**
@@ -1152,12 +1283,49 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
 	tk_debug_account_sleep_time(delta);
 }
 
+#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE)
+/**
+ * We have three kinds of time sources to use for sleep time
+ * injection, the preference order is:
+ * 1) non-stop clocksource
+ * 2) persistent clock (ie: RTC accessible when irqs are off)
+ * 3) RTC
+ *
+ * 1) and 2) are used by timekeeping, 3) by RTC subsystem.
+ * If system has neither 1) nor 2), 3) will be used finally.
+ *
+ *
+ * If timekeeping has injected sleeptime via either 1) or 2),
+ * 3) becomes needless, so in this case we don't need to call
+ * rtc_resume(), and this is what timekeeping_rtc_skipresume()
+ * means.
+ */
+bool timekeeping_rtc_skipresume(void)
+{
+	return sleeptime_injected;
+}
+
+/**
+ * 1) can be determined whether to use or not only when doing
+ * timekeeping_resume() which is invoked after rtc_suspend(),
+ * so we can't skip rtc_suspend() surely if system has 1).
+ *
+ * But if system has 2), 2) will definitely be used, so in this
+ * case we don't need to call rtc_suspend(), and this is what
+ * timekeeping_rtc_skipsuspend() means.
+ */
+bool timekeeping_rtc_skipsuspend(void)
+{
+	return persistent_clock_exists;
+}
+
 /**
  * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values
  * @delta: pointer to a timespec64 delta value
  *
- * This hook is for architectures that cannot support read_persistent_clock
+ * This hook is for architectures that cannot support read_persistent_clock64
  * because their RTC/persistent clock is only accessible when irqs are enabled.
+ * and also don't have an effective nonstop clocksource.
  *
  * This function should only be called by rtc_resume(), and allows
  * a suspend offset to be injected into the timekeeping values.
@@ -1167,13 +1335,6 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta)
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long flags;
 
-	/*
-	 * Make sure we don't set the clock twice, as timekeeping_resume()
-	 * already did it
-	 */
-	if (has_persistent_clock())
-		return;
-
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 
@@ -1189,26 +1350,21 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta)
 	/* signal hrtimers about time change */
 	clock_was_set();
 }
+#endif
 
 /**
  * timekeeping_resume - Resumes the generic timekeeping subsystem.
- *
- * This is for the generic clocksource timekeeping.
- * xtime/wall_to_monotonic/jiffies/etc are
- * still managed by arch specific suspend/resume code.
  */
 void timekeeping_resume(void)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	struct clocksource *clock = tk->tkr.clock;
+	struct clocksource *clock = tk->tkr_mono.clock;
 	unsigned long flags;
 	struct timespec64 ts_new, ts_delta;
-	struct timespec tmp;
 	cycle_t cycle_now, cycle_delta;
-	bool suspendtime_found = false;
 
-	read_persistent_clock(&tmp);
-	ts_new = timespec_to_timespec64(tmp);
+	sleeptime_injected = false;
+	read_persistent_clock64(&ts_new);
 
 	clockevents_resume();
 	clocksource_resume();
@@ -1228,16 +1384,16 @@ void timekeeping_resume(void)
 	 * The less preferred source will only be tried if there is no better
 	 * usable source. The rtc part is handled separately in rtc core code.
 	 */
-	cycle_now = tk->tkr.read(clock);
+	cycle_now = tk->tkr_mono.read(clock);
 	if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
-		cycle_now > tk->tkr.cycle_last) {
+		cycle_now > tk->tkr_mono.cycle_last) {
 		u64 num, max = ULLONG_MAX;
 		u32 mult = clock->mult;
 		u32 shift = clock->shift;
 		s64 nsec = 0;
 
-		cycle_delta = clocksource_delta(cycle_now, tk->tkr.cycle_last,
-						tk->tkr.mask);
+		cycle_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last,
+						tk->tkr_mono.mask);
 
 		/*
 		 * "cycle_delta * mutl" may cause 64 bits overflow, if the
@@ -1253,17 +1409,19 @@ void timekeeping_resume(void)
 		nsec += ((u64) cycle_delta * mult) >> shift;
 
 		ts_delta = ns_to_timespec64(nsec);
-		suspendtime_found = true;
+		sleeptime_injected = true;
 	} else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) {
 		ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time);
-		suspendtime_found = true;
+		sleeptime_injected = true;
 	}
 
-	if (suspendtime_found)
+	if (sleeptime_injected)
 		__timekeeping_inject_sleeptime(tk, &ts_delta);
 
 	/* Re-base the last cycle value */
-	tk->tkr.cycle_last = cycle_now;
+	tk->tkr_mono.cycle_last = cycle_now;
+	tk->tkr_raw.cycle_last  = cycle_now;
+
 	tk->ntp_error = 0;
 	timekeeping_suspended = 0;
 	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
@@ -1272,9 +1430,7 @@ void timekeeping_resume(void)
 
 	touch_softlockup_watchdog();
 
-	clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL);
-
-	/* Resume hrtimers */
+	tick_resume();
 	hrtimers_resume();
 }
 
@@ -1284,10 +1440,8 @@ int timekeeping_suspend(void)
 	unsigned long flags;
 	struct timespec64		delta, delta_delta;
 	static struct timespec64	old_delta;
-	struct timespec tmp;
 
-	read_persistent_clock(&tmp);
-	timekeeping_suspend_time = timespec_to_timespec64(tmp);
+	read_persistent_clock64(&timekeeping_suspend_time);
 
 	/*
 	 * On some systems the persistent_clock can not be detected at
@@ -1295,31 +1449,33 @@ int timekeeping_suspend(void)
 	 * value returned, update the persistent_clock_exists flag.
 	 */
 	if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
-		persistent_clock_exist = true;
+		persistent_clock_exists = true;
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 	timekeeping_forward_now(tk);
 	timekeeping_suspended = 1;
 
-	/*
-	 * To avoid drift caused by repeated suspend/resumes,
-	 * which each can add ~1 second drift error,
-	 * try to compensate so the difference in system time
-	 * and persistent_clock time stays close to constant.
-	 */
-	delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time);
-	delta_delta = timespec64_sub(delta, old_delta);
-	if (abs(delta_delta.tv_sec)  >= 2) {
+	if (persistent_clock_exists) {
 		/*
-		 * if delta_delta is too large, assume time correction
-		 * has occured and set old_delta to the current delta.
+		 * To avoid drift caused by repeated suspend/resumes,
+		 * which each can add ~1 second drift error,
+		 * try to compensate so the difference in system time
+		 * and persistent_clock time stays close to constant.
 		 */
-		old_delta = delta;
-	} else {
-		/* Otherwise try to adjust old_system to compensate */
-		timekeeping_suspend_time =
-			timespec64_add(timekeeping_suspend_time, delta_delta);
+		delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time);
+		delta_delta = timespec64_sub(delta, old_delta);
+		if (abs(delta_delta.tv_sec) >= 2) {
+			/*
+			 * if delta_delta is too large, assume time correction
+			 * has occurred and set old_delta to the current delta.
+			 */
+			old_delta = delta;
+		} else {
+			/* Otherwise try to adjust old_system to compensate */
+			timekeeping_suspend_time =
+				timespec64_add(timekeeping_suspend_time, delta_delta);
+		}
 	}
 
 	timekeeping_update(tk, TK_MIRROR);
@@ -1327,7 +1483,7 @@ int timekeeping_suspend(void)
 	write_seqcount_end(&tk_core.seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
-	clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
+	tick_suspend();
 	clocksource_suspend();
 	clockevents_suspend();
 
@@ -1416,15 +1572,15 @@ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk,
 	 *
 	 * XXX - TODO: Doc ntp_error calculation.
 	 */
-	if ((mult_adj > 0) && (tk->tkr.mult + mult_adj < mult_adj)) {
+	if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) {
 		/* NTP adjustment caused clocksource mult overflow */
 		WARN_ON_ONCE(1);
 		return;
 	}
 
-	tk->tkr.mult += mult_adj;
+	tk->tkr_mono.mult += mult_adj;
 	tk->xtime_interval += interval;
-	tk->tkr.xtime_nsec -= offset;
+	tk->tkr_mono.xtime_nsec -= offset;
 	tk->ntp_error -= (interval - offset) << tk->ntp_error_shift;
 }
 
@@ -1486,13 +1642,13 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
 		tk->ntp_err_mult = 0;
 	}
 
-	if (unlikely(tk->tkr.clock->maxadj &&
-		(abs(tk->tkr.mult - tk->tkr.clock->mult)
-			> tk->tkr.clock->maxadj))) {
+	if (unlikely(tk->tkr_mono.clock->maxadj &&
+		(abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult)
+			> tk->tkr_mono.clock->maxadj))) {
 		printk_once(KERN_WARNING
 			"Adjusting %s more than 11%% (%ld vs %ld)\n",
-			tk->tkr.clock->name, (long)tk->tkr.mult,
-			(long)tk->tkr.clock->mult + tk->tkr.clock->maxadj);
+			tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult,
+			(long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj);
 	}
 
 	/*
@@ -1509,9 +1665,9 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
 	 * We'll correct this error next time through this function, when
 	 * xtime_nsec is not as small.
 	 */
-	if (unlikely((s64)tk->tkr.xtime_nsec < 0)) {
-		s64 neg = -(s64)tk->tkr.xtime_nsec;
-		tk->tkr.xtime_nsec = 0;
+	if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) {
+		s64 neg = -(s64)tk->tkr_mono.xtime_nsec;
+		tk->tkr_mono.xtime_nsec = 0;
 		tk->ntp_error += neg << tk->ntp_error_shift;
 	}
 }
@@ -1526,13 +1682,13 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
  */
 static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 {
-	u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr.shift;
+	u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift;
 	unsigned int clock_set = 0;
 
-	while (tk->tkr.xtime_nsec >= nsecps) {
+	while (tk->tkr_mono.xtime_nsec >= nsecps) {
 		int leap;
 
-		tk->tkr.xtime_nsec -= nsecps;
+		tk->tkr_mono.xtime_nsec -= nsecps;
 		tk->xtime_sec++;
 
 		/* Figure out if its a leap sec and apply if needed */
@@ -1577,9 +1733,10 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
 
 	/* Accumulate one shifted interval */
 	offset -= interval;
-	tk->tkr.cycle_last += interval;
+	tk->tkr_mono.cycle_last += interval;
+	tk->tkr_raw.cycle_last  += interval;
 
-	tk->tkr.xtime_nsec += tk->xtime_interval << shift;
+	tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift;
 	*clock_set |= accumulate_nsecs_to_secs(tk);
 
 	/* Accumulate raw time */
@@ -1622,14 +1779,17 @@ void update_wall_time(void)
 #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
 	offset = real_tk->cycle_interval;
 #else
-	offset = clocksource_delta(tk->tkr.read(tk->tkr.clock),
-				   tk->tkr.cycle_last, tk->tkr.mask);
+	offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock),
+				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
 #endif
 
 	/* Check if there's really nothing to do */
 	if (offset < real_tk->cycle_interval)
 		goto out;
 
+	/* Do some additional sanity checking */
+	timekeeping_check_update(real_tk, offset);
+
 	/*
 	 * With NO_HZ we may have to accumulate many cycle_intervals
 	 * (think "ticks") worth of time at once. To do this efficiently,
@@ -1784,8 +1944,8 @@ ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot,
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
-		base = tk->tkr.base_mono;
-		nsecs = tk->tkr.xtime_nsec >> tk->tkr.shift;
+		base = tk->tkr_mono.base;
+		nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
 
 		*offs_real = tk->offs_real;
 		*offs_boot = tk->offs_boot;
@@ -1816,8 +1976,8 @@ ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot,
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
-		base = tk->tkr.base_mono;
-		nsecs = timekeeping_get_ns(&tk->tkr);
+		base = tk->tkr_mono.base;
+		nsecs = timekeeping_get_ns(&tk->tkr_mono);
 
 		*offs_real = tk->offs_real;
 		*offs_boot = tk->offs_boot;
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index 1d91416055d5..ead8794b9a4e 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -19,4 +19,11 @@ extern void timekeeping_clocktai(struct timespec *ts);
 extern int timekeeping_suspend(void);
 extern void timekeeping_resume(void);
 
+extern void do_timer(unsigned long ticks);
+extern void update_wall_time(void);
+
+extern seqlock_t jiffies_lock;
+
+#define CS_NAME_LEN	32
+
 #endif
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 2d3f5c504939..2ece3aa5069c 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -90,8 +90,18 @@ struct tvec_base {
 	struct tvec tv5;
 } ____cacheline_aligned;
 
+/*
+ * __TIMER_INITIALIZER() needs to set ->base to a valid pointer (because we've
+ * made NULL special, hint: lock_timer_base()) and we cannot get a compile time
+ * pointer to per-cpu entries because we don't know where we'll map the section,
+ * even for the boot cpu.
+ *
+ * And so we use boot_tvec_bases for boot CPU and per-cpu __tvec_bases for the
+ * rest of them.
+ */
 struct tvec_base boot_tvec_bases;
 EXPORT_SYMBOL(boot_tvec_bases);
+
 static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
 
 /* Functions below help us manage 'deferrable' flag */
@@ -1027,6 +1037,8 @@ int try_to_del_timer_sync(struct timer_list *timer)
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
 #ifdef CONFIG_SMP
+static DEFINE_PER_CPU(struct tvec_base, __tvec_bases);
+
 /**
  * del_timer_sync - deactivate a timer and wait for the handler to finish.
  * @timer: the timer to be deactivated
@@ -1532,64 +1544,6 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout)
 }
 EXPORT_SYMBOL(schedule_timeout_uninterruptible);
 
-static int init_timers_cpu(int cpu)
-{
-	int j;
-	struct tvec_base *base;
-	static char tvec_base_done[NR_CPUS];
-
-	if (!tvec_base_done[cpu]) {
-		static char boot_done;
-
-		if (boot_done) {
-			/*
-			 * The APs use this path later in boot
-			 */
-			base = kzalloc_node(sizeof(*base), GFP_KERNEL,
-					    cpu_to_node(cpu));
-			if (!base)
-				return -ENOMEM;
-
-			/* Make sure tvec_base has TIMER_FLAG_MASK bits free */
-			if (WARN_ON(base != tbase_get_base(base))) {
-				kfree(base);
-				return -ENOMEM;
-			}
-			per_cpu(tvec_bases, cpu) = base;
-		} else {
-			/*
-			 * This is for the boot CPU - we use compile-time
-			 * static initialisation because per-cpu memory isn't
-			 * ready yet and because the memory allocators are not
-			 * initialised either.
-			 */
-			boot_done = 1;
-			base = &boot_tvec_bases;
-		}
-		spin_lock_init(&base->lock);
-		tvec_base_done[cpu] = 1;
-		base->cpu = cpu;
-	} else {
-		base = per_cpu(tvec_bases, cpu);
-	}
-
-
-	for (j = 0; j < TVN_SIZE; j++) {
-		INIT_LIST_HEAD(base->tv5.vec + j);
-		INIT_LIST_HEAD(base->tv4.vec + j);
-		INIT_LIST_HEAD(base->tv3.vec + j);
-		INIT_LIST_HEAD(base->tv2.vec + j);
-	}
-	for (j = 0; j < TVR_SIZE; j++)
-		INIT_LIST_HEAD(base->tv1.vec + j);
-
-	base->timer_jiffies = jiffies;
-	base->next_timer = base->timer_jiffies;
-	base->active_timers = 0;
-	base->all_timers = 0;
-	return 0;
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head)
 {
@@ -1631,55 +1585,86 @@ static void migrate_timers(int cpu)
 		migrate_timer_list(new_base, old_base->tv5.vec + i);
 	}
 
+	old_base->active_timers = 0;
+	old_base->all_timers = 0;
+
 	spin_unlock(&old_base->lock);
 	spin_unlock_irq(&new_base->lock);
 	put_cpu_var(tvec_bases);
 }
-#endif /* CONFIG_HOTPLUG_CPU */
 
 static int timer_cpu_notify(struct notifier_block *self,
 				unsigned long action, void *hcpu)
 {
-	long cpu = (long)hcpu;
-	int err;
-
-	switch(action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		err = init_timers_cpu(cpu);
-		if (err < 0)
-			return notifier_from_errno(err);
-		break;
-#ifdef CONFIG_HOTPLUG_CPU
+	switch (action) {
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		migrate_timers(cpu);
+		migrate_timers((long)hcpu);
 		break;
-#endif
 	default:
 		break;
 	}
+
 	return NOTIFY_OK;
 }
 
-static struct notifier_block timers_nb = {
-	.notifier_call	= timer_cpu_notify,
-};
+static inline void timer_register_cpu_notifier(void)
+{
+	cpu_notifier(timer_cpu_notify, 0);
+}
+#else
+static inline void timer_register_cpu_notifier(void) { }
+#endif /* CONFIG_HOTPLUG_CPU */
 
+static void __init init_timer_cpu(struct tvec_base *base, int cpu)
+{
+	int j;
 
-void __init init_timers(void)
+	BUG_ON(base != tbase_get_base(base));
+
+	base->cpu = cpu;
+	per_cpu(tvec_bases, cpu) = base;
+	spin_lock_init(&base->lock);
+
+	for (j = 0; j < TVN_SIZE; j++) {
+		INIT_LIST_HEAD(base->tv5.vec + j);
+		INIT_LIST_HEAD(base->tv4.vec + j);
+		INIT_LIST_HEAD(base->tv3.vec + j);
+		INIT_LIST_HEAD(base->tv2.vec + j);
+	}
+	for (j = 0; j < TVR_SIZE; j++)
+		INIT_LIST_HEAD(base->tv1.vec + j);
+
+	base->timer_jiffies = jiffies;
+	base->next_timer = base->timer_jiffies;
+}
+
+static void __init init_timer_cpus(void)
 {
-	int err;
+	struct tvec_base *base;
+	int local_cpu = smp_processor_id();
+	int cpu;
 
+	for_each_possible_cpu(cpu) {
+		if (cpu == local_cpu)
+			base = &boot_tvec_bases;
+#ifdef CONFIG_SMP
+		else
+			base = per_cpu_ptr(&__tvec_bases, cpu);
+#endif
+
+		init_timer_cpu(base, cpu);
+	}
+}
+
+void __init init_timers(void)
+{
 	/* ensure there are enough low bits for flags in timer->base pointer */
 	BUILD_BUG_ON(__alignof__(struct tvec_base) & TIMER_FLAG_MASK);
 
-	err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
-			       (void *)(long)smp_processor_id());
-	BUG_ON(err != NOTIFY_OK);
-
+	init_timer_cpus();
 	init_timer_stats();
-	register_cpu_notifier(&timers_nb);
+	timer_register_cpu_notifier();
 	open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
 }
 
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 61ed862cdd37..e878c2e0ba45 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -16,10 +16,10 @@
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
-#include <linux/tick.h>
 
 #include <asm/uaccess.h>
 
+#include "tick-internal.h"
 
 struct timer_list_iter {
 	int cpu;
@@ -228,9 +228,35 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
 	print_name_offset(m, dev->set_next_event);
 	SEQ_printf(m, "\n");
 
-	SEQ_printf(m, " set_mode:       ");
-	print_name_offset(m, dev->set_mode);
-	SEQ_printf(m, "\n");
+	if (dev->set_mode) {
+		SEQ_printf(m, " set_mode:       ");
+		print_name_offset(m, dev->set_mode);
+		SEQ_printf(m, "\n");
+	} else {
+		if (dev->set_state_shutdown) {
+			SEQ_printf(m, " shutdown: ");
+			print_name_offset(m, dev->set_state_shutdown);
+			SEQ_printf(m, "\n");
+		}
+
+		if (dev->set_state_periodic) {
+			SEQ_printf(m, " periodic: ");
+			print_name_offset(m, dev->set_state_periodic);
+			SEQ_printf(m, "\n");
+		}
+
+		if (dev->set_state_oneshot) {
+			SEQ_printf(m, " oneshot:  ");
+			print_name_offset(m, dev->set_state_oneshot);
+			SEQ_printf(m, "\n");
+		}
+
+		if (dev->tick_resume) {
+			SEQ_printf(m, " resume:   ");
+			print_name_offset(m, dev->tick_resume);
+			SEQ_printf(m, "\n");
+		}
+	}
 
 	SEQ_printf(m, " event_handler:  ");
 	print_name_offset(m, dev->event_handler);