Initial commit; kernel source import

kernel/time/Kconfig

@@ -0,0 +1,167 @@
+#
+# Timer subsystem related configuration options
+#
+
+# Options selectable by arch Kconfig
+
+# Watchdog function for clocksources to detect instabilities
+config CLOCKSOURCE_WATCHDOG
+	bool
+
+# Architecture has extra clocksource data
+config ARCH_CLOCKSOURCE_DATA
+	bool
+
+# Clocksources require validation of the clocksource against the last
+# cycle update - x86/TSC misfeature
+config CLOCKSOURCE_VALIDATE_LAST_CYCLE
+	bool
+
+# Timekeeping vsyscall support
+config GENERIC_TIME_VSYSCALL
+	bool
+
+# Timekeeping vsyscall support
+config GENERIC_TIME_VSYSCALL_OLD
+	bool
+
+# ktime_t scalar 64bit nsec representation
+config KTIME_SCALAR
+	bool
+
+# Old style timekeeping
+config ARCH_USES_GETTIMEOFFSET
+	bool
+
+# The generic clock events infrastructure
+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
+
+# Clockevents broadcasting infrastructure
+config GENERIC_CLOCKEVENTS_BROADCAST
+	bool
+	depends on GENERIC_CLOCKEVENTS
+
+# Automatically adjust the min. reprogramming time for
+# clock event device
+config GENERIC_CLOCKEVENTS_MIN_ADJUST
+	bool
+
+# Generic update of CMOS clock
+config GENERIC_CMOS_UPDATE
+	bool
+
+if GENERIC_CLOCKEVENTS
+menu "Timers subsystem"
+
+# Core internal switch. Selected by NO_HZ_COMMON / HIGH_RES_TIMERS. This is
+# only related to the tick functionality. Oneshot clockevent devices
+# are supported independ of this.
+config TICK_ONESHOT
+	bool
+
+config NO_HZ_COMMON
+	bool
+	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
+	select TICK_ONESHOT
+
+choice
+	prompt "Timer tick handling"
+	default NO_HZ_IDLE if NO_HZ
+
+config HZ_PERIODIC
+	bool "Periodic timer ticks (constant rate, no dynticks)"
+	help
+	  This option keeps the tick running periodically at a constant
+	  rate, even when the CPU doesn't need it.
+
+config NO_HZ_IDLE
+	bool "Idle dynticks system (tickless idle)"
+	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
+	select NO_HZ_COMMON
+	help
+	  This option enables a tickless idle system: timer interrupts
+	  will only trigger on an as-needed basis when the system is idle.
+	  This is usually interesting for energy saving.
+
+	  Most of the time you want to say Y here.
+
+config NO_HZ_FULL
+	bool "Full dynticks system (tickless)"
+	# NO_HZ_COMMON dependency
+	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
+	# We need at least one periodic CPU for timekeeping
+	depends on SMP
+	# RCU_USER_QS dependency
+	depends on HAVE_CONTEXT_TRACKING
+	# VIRT_CPU_ACCOUNTING_GEN dependency
+	depends on 64BIT
+	select NO_HZ_COMMON
+	select RCU_USER_QS
+	select RCU_NOCB_CPU
+	select VIRT_CPU_ACCOUNTING_GEN
+	select CONTEXT_TRACKING_FORCE
+	select IRQ_WORK
+	help
+	 Adaptively try to shutdown the tick whenever possible, even when
+	 the CPU is running tasks. Typically this requires running a single
+	 task on the CPU. Chances for running tickless are maximized when
+	 the task mostly runs in userspace and has few kernel activity.
+
+	 You need to fill up the nohz_full boot parameter with the
+	 desired range of dynticks CPUs.
+
+	 This is implemented at the expense of some overhead in user <-> kernel
+	 transitions: syscalls, exceptions and interrupts. Even when it's
+	 dynamically off.
+
+	 Say N.
+
+endchoice
+
+config NO_HZ_FULL_ALL
+       bool "Full dynticks system on all CPUs by default"
+       depends on NO_HZ_FULL
+       help
+         If the user doesn't pass the nohz_full boot option to
+	 define the range of full dynticks CPUs, consider that all
+	 CPUs in the system are full dynticks by default.
+	 Note the boot CPU will still be kept outside the range to
+	 handle the timekeeping duty.
+
+config NO_HZ
+	bool "Old Idle dynticks config"
+	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
+	help
+	  This is the old config entry that enables dynticks idle.
+	  We keep it around for a little while to enforce backward
+	  compatibility with older config files.
+
+config HIGH_RES_TIMERS
+	bool "High Resolution Timer Support"
+	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
+	select TICK_ONESHOT
+	help
+	  This option enables high resolution timer support. If your
+	  hardware is not capable then this option only increases
+	  the size of the kernel image.
+
+endmenu
+endif
+
+config UDELAY_TEST
+	tristate "udelay test driver"
+	default n
+	help
+	  This builds the "udelay_test" module that helps to make sure
+	  that udelay() is working properly.

kernel/time/Makefile

@@ -0,0 +1,10 @@
+obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o
+obj-y += timeconv.o posix-clock.o alarmtimer.o
+
+obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
+obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
+obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)	+= tick-broadcast.o
+obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o
+obj-$(CONFIG_TICK_ONESHOT)			+= tick-sched.o
+obj-$(CONFIG_TIMER_STATS)			+= timer_stats.o
+obj-$(CONFIG_UDELAY_TEST)			+= udelay_test.o

kernel/time/alarmtimer.c

@@ -0,0 +1,800 @@
+/*
+ * Alarmtimer interface
+ *
+ * This interface provides a timer which is similarto hrtimers,
+ * but triggers a RTC alarm if the box is suspend.
+ *
+ * This interface is influenced by the Android RTC Alarm timer
+ * interface.
+ *
+ * Copyright (C) 2010 IBM Corperation
+ *
+ * Author: John Stultz <john.stultz@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/time.h>
+#include <linux/hrtimer.h>
+#include <linux/timerqueue.h>
+#include <linux/rtc.h>
+#include <linux/alarmtimer.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <linux/posix-timers.h>
+#include <linux/workqueue.h>
+#include <linux/freezer.h>
+
+/**
+ * struct alarm_base - Alarm timer bases
+ * @lock:		Lock for syncrhonized access to the base
+ * @timerqueue:		Timerqueue head managing the list of events
+ * @timer: 		hrtimer used to schedule events while running
+ * @gettime:		Function to read the time correlating to the base
+ * @base_clockid:	clockid for the base
+ */
+static struct alarm_base {
+	spinlock_t		lock;
+	struct timerqueue_head	timerqueue;
+	ktime_t			(*gettime)(void);
+	clockid_t		base_clockid;
+} alarm_bases[ALARM_NUMTYPE];
+
+/* freezer delta & lock used to handle clock_nanosleep triggered wakeups */
+static ktime_t freezer_delta;
+static DEFINE_SPINLOCK(freezer_delta_lock);
+
+static struct wakeup_source *ws;
+
+#ifdef CONFIG_RTC_CLASS
+/* rtc timer and device for setting alarm wakeups at suspend */
+static struct rtc_timer		rtctimer;
+static struct rtc_device	*rtcdev;
+static DEFINE_SPINLOCK(rtcdev_lock);
+
+/**
+ * alarmtimer_get_rtcdev - Return selected rtcdevice
+ *
+ * This function returns the rtc device to use for wakealarms.
+ * If one has not already been chosen, it checks to see if a
+ * functional rtc device is available.
+ */
+struct rtc_device *alarmtimer_get_rtcdev(void)
+{
+	unsigned long flags;
+	struct rtc_device *ret;
+
+	spin_lock_irqsave(&rtcdev_lock, flags);
+	ret = rtcdev;
+	spin_unlock_irqrestore(&rtcdev_lock, flags);
+
+	return ret;
+}
+
+
+static int alarmtimer_rtc_add_device(struct device *dev,
+				struct class_interface *class_intf)
+{
+	unsigned long flags;
+	struct rtc_device *rtc = to_rtc_device(dev);
+
+	if (rtcdev)
+		return -EBUSY;
+
+	if (!rtc->ops->set_alarm)
+		return -1;
+	if (!device_may_wakeup(rtc->dev.parent))
+		return -1;
+
+	spin_lock_irqsave(&rtcdev_lock, flags);
+	if (!rtcdev) {
+		rtcdev = rtc;
+		/* hold a reference so it doesn't go away */
+		get_device(dev);
+	}
+	spin_unlock_irqrestore(&rtcdev_lock, flags);
+	return 0;
+}
+
+static inline void alarmtimer_rtc_timer_init(void)
+{
+	rtc_timer_init(&rtctimer, NULL, NULL);
+}
+
+static struct class_interface alarmtimer_rtc_interface = {
+	.add_dev = &alarmtimer_rtc_add_device,
+};
+
+static int alarmtimer_rtc_interface_setup(void)
+{
+	alarmtimer_rtc_interface.class = rtc_class;
+	return class_interface_register(&alarmtimer_rtc_interface);
+}
+static void alarmtimer_rtc_interface_remove(void)
+{
+	class_interface_unregister(&alarmtimer_rtc_interface);
+}
+#else
+struct rtc_device *alarmtimer_get_rtcdev(void)
+{
+	return NULL;
+}
+#define rtcdev (NULL)
+static inline int alarmtimer_rtc_interface_setup(void) { return 0; }
+static inline void alarmtimer_rtc_interface_remove(void) { }
+static inline void alarmtimer_rtc_timer_init(void) { }
+#endif
+
+/**
+ * alarmtimer_enqueue - Adds an alarm timer to an alarm_base timerqueue
+ * @base: pointer to the base where the timer is being run
+ * @alarm: pointer to alarm being enqueued.
+ *
+ * Adds alarm to a alarm_base timerqueue
+ *
+ * Must hold base->lock when calling.
+ */
+static void alarmtimer_enqueue(struct alarm_base *base, struct alarm *alarm)
+{
+	if (alarm->state & ALARMTIMER_STATE_ENQUEUED)
+		timerqueue_del(&base->timerqueue, &alarm->node);
+
+	timerqueue_add(&base->timerqueue, &alarm->node);
+	alarm->state |= ALARMTIMER_STATE_ENQUEUED;
+}
+
+/**
+ * alarmtimer_dequeue - Removes an alarm timer from an alarm_base timerqueue
+ * @base: pointer to the base where the timer is running
+ * @alarm: pointer to alarm being removed
+ *
+ * Removes alarm to a alarm_base timerqueue
+ *
+ * Must hold base->lock when calling.
+ */
+static void alarmtimer_dequeue(struct alarm_base *base, struct alarm *alarm)
+{
+	if (!(alarm->state & ALARMTIMER_STATE_ENQUEUED))
+		return;
+
+	timerqueue_del(&base->timerqueue, &alarm->node);
+	alarm->state &= ~ALARMTIMER_STATE_ENQUEUED;
+}
+
+
+/**
+ * alarmtimer_fired - Handles alarm hrtimer being fired.
+ * @timer: pointer to hrtimer being run
+ *
+ * When a alarm timer fires, this runs through the timerqueue to
+ * see which alarms expired, and runs those. If there are more alarm
+ * timers queued for the future, we set the hrtimer to fire when
+ * when the next future alarm timer expires.
+ */
+static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
+{
+	struct alarm *alarm = container_of(timer, struct alarm, timer);
+	struct alarm_base *base = &alarm_bases[alarm->type];
+	unsigned long flags;
+	int ret = HRTIMER_NORESTART;
+	int restart = ALARMTIMER_NORESTART;
+
+	spin_lock_irqsave(&base->lock, flags);
+	alarmtimer_dequeue(base, alarm);
+	spin_unlock_irqrestore(&base->lock, flags);
+
+	if (alarm->function)
+		restart = alarm->function(alarm, base->gettime());
+
+	spin_lock_irqsave(&base->lock, flags);
+	if (restart != ALARMTIMER_NORESTART) {
+		hrtimer_set_expires(&alarm->timer, alarm->node.expires);
+		alarmtimer_enqueue(base, alarm);
+		ret = HRTIMER_RESTART;
+	}
+	spin_unlock_irqrestore(&base->lock, flags);
+
+	return ret;
+
+}
+
+#ifdef CONFIG_RTC_CLASS
+/**
+ * alarmtimer_suspend - Suspend time callback
+ * @dev: unused
+ * @state: unused
+ *
+ * When we are going into suspend, we look through the bases
+ * to see which is the soonest timer to expire. We then
+ * set an rtc timer to fire that far into the future, which
+ * will wake us from suspend.
+ */
+static int alarmtimer_suspend(struct device *dev)
+{
+	struct rtc_time tm;
+	ktime_t min, now;
+	unsigned long flags;
+	struct rtc_device *rtc;
+	int i;
+	int ret;
+
+	spin_lock_irqsave(&freezer_delta_lock, flags);
+	min = freezer_delta;
+	freezer_delta = ktime_set(0, 0);
+	spin_unlock_irqrestore(&freezer_delta_lock, flags);
+
+	rtc = alarmtimer_get_rtcdev();
+	/* If we have no rtcdev, just return */
+	if (!rtc)
+		return 0;
+
+	/* Find the soonest timer to expire*/
+	for (i = 0; i < ALARM_NUMTYPE; i++) {
+		struct alarm_base *base = &alarm_bases[i];
+		struct timerqueue_node *next;
+		ktime_t delta;
+
+		spin_lock_irqsave(&base->lock, flags);
+		next = timerqueue_getnext(&base->timerqueue);
+		spin_unlock_irqrestore(&base->lock, flags);
+		if (!next)
+			continue;
+		delta = ktime_sub(next->expires, base->gettime());
+		if (!min.tv64 || (delta.tv64 < min.tv64))
+			min = delta;
+	}
+	if (min.tv64 == 0)
+		return 0;
+
+	if (ktime_to_ns(min) < 2 * NSEC_PER_SEC) {
+		__pm_wakeup_event(ws, 2 * MSEC_PER_SEC);
+		return -EBUSY;
+	}
+
+	/* Setup an rtc timer to fire that far in the future */
+	rtc_timer_cancel(rtc, &rtctimer);
+	rtc_read_time(rtc, &tm);
+	now = rtc_tm_to_ktime(tm);
+	now = ktime_add(now, min);
+
+	/* Set alarm, if in the past reject suspend briefly to handle */
+	ret = rtc_timer_start(rtc, &rtctimer, now, ktime_set(0, 0));
+	if (ret < 0)
+		__pm_wakeup_event(ws, MSEC_PER_SEC);
+	return ret;
+}
+#else
+static int alarmtimer_suspend(struct device *dev)
+{
+	return 0;
+}
+#endif
+
+static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type)
+{
+	ktime_t delta;
+	unsigned long flags;
+	struct alarm_base *base = &alarm_bases[type];
+
+	delta = ktime_sub(absexp, base->gettime());
+
+	spin_lock_irqsave(&freezer_delta_lock, flags);
+	if (!freezer_delta.tv64 || (delta.tv64 < freezer_delta.tv64))
+		freezer_delta = delta;
+	spin_unlock_irqrestore(&freezer_delta_lock, flags);
+}
+
+
+/**
+ * alarm_init - Initialize an alarm structure
+ * @alarm: ptr to alarm to be initialized
+ * @type: the type of the alarm
+ * @function: callback that is run when the alarm fires
+ */
+void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
+		enum alarmtimer_restart (*function)(struct alarm *, ktime_t))
+{
+	timerqueue_init(&alarm->node);
+	hrtimer_init(&alarm->timer, alarm_bases[type].base_clockid,
+			HRTIMER_MODE_ABS);
+	alarm->timer.function = alarmtimer_fired;
+	alarm->function = function;
+	alarm->type = type;
+	alarm->state = ALARMTIMER_STATE_INACTIVE;
+}
+
+/**
+ * alarm_start - Sets an alarm to fire
+ * @alarm: ptr to alarm to set
+ * @start: time to run the alarm
+ */
+int alarm_start(struct alarm *alarm, ktime_t start)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&base->lock, flags);
+	alarm->node.expires = start;
+	alarmtimer_enqueue(base, alarm);
+	ret = hrtimer_start(&alarm->timer, alarm->node.expires,
+				HRTIMER_MODE_ABS);
+	spin_unlock_irqrestore(&base->lock, flags);
+	return ret;
+}
+
+/**
+ * alarm_try_to_cancel - Tries to cancel an alarm timer
+ * @alarm: ptr to alarm to be canceled
+ *
+ * Returns 1 if the timer was canceled, 0 if it was not running,
+ * and -1 if the callback was running
+ */
+int alarm_try_to_cancel(struct alarm *alarm)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&base->lock, flags);
+	ret = hrtimer_try_to_cancel(&alarm->timer);
+	if (ret >= 0)
+		alarmtimer_dequeue(base, alarm);
+	spin_unlock_irqrestore(&base->lock, flags);
+	return ret;
+}
+
+
+/**
+ * alarm_cancel - Spins trying to cancel an alarm timer until it is done
+ * @alarm: ptr to alarm to be canceled
+ *
+ * Returns 1 if the timer was canceled, 0 if it was not active.
+ */
+int alarm_cancel(struct alarm *alarm)
+{
+	for (;;) {
+		int ret = alarm_try_to_cancel(alarm);
+		if (ret >= 0)
+			return ret;
+		cpu_relax();
+	}
+}
+
+
+u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval)
+{
+	u64 overrun = 1;
+	ktime_t delta;
+
+	delta = ktime_sub(now, alarm->node.expires);
+
+	if (delta.tv64 < 0)
+		return 0;
+
+	if (unlikely(delta.tv64 >= interval.tv64)) {
+		s64 incr = ktime_to_ns(interval);
+
+		overrun = ktime_divns(delta, incr);
+
+		alarm->node.expires = ktime_add_ns(alarm->node.expires,
+							incr*overrun);
+
+		if (alarm->node.expires.tv64 > now.tv64)
+			return overrun;
+		/*
+		 * This (and the ktime_add() below) is the
+		 * correction for exact:
+		 */
+		overrun++;
+	}
+
+	alarm->node.expires = ktime_add(alarm->node.expires, interval);
+	return overrun;
+}
+
+
+
+
+/**
+ * clock2alarm - helper that converts from clockid to alarmtypes
+ * @clockid: clockid.
+ */
+static enum alarmtimer_type clock2alarm(clockid_t clockid)
+{
+	if (clockid == CLOCK_REALTIME_ALARM)
+		return ALARM_REALTIME;
+	if (clockid == CLOCK_BOOTTIME_ALARM)
+		return ALARM_BOOTTIME;
+	return -1;
+}
+
+/**
+ * alarm_handle_timer - Callback for posix timers
+ * @alarm: alarm that fired
+ *
+ * Posix timer callback for expired alarm timers.
+ */
+static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
+							ktime_t now)
+{
+	struct k_itimer *ptr = container_of(alarm, struct k_itimer,
+						it.alarm.alarmtimer);
+	if (posix_timer_event(ptr, 0) != 0)
+		ptr->it_overrun++;
+
+	/* Re-add periodic timers */
+	if (ptr->it.alarm.interval.tv64) {
+		ptr->it_overrun += alarm_forward(alarm, now,
+						ptr->it.alarm.interval);
+		return ALARMTIMER_RESTART;
+	}
+	return ALARMTIMER_NORESTART;
+}
+
+/**
+ * alarm_clock_getres - posix getres interface
+ * @which_clock: clockid
+ * @tp: timespec to fill
+ *
+ * Returns the granularity of underlying alarm base clock
+ */
+static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp)
+{
+	clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid;
+
+	if (!alarmtimer_get_rtcdev())
+		return -ENOTSUPP;
+
+	return hrtimer_get_res(baseid, tp);
+}
+
+/**
+ * alarm_clock_get - posix clock_get interface
+ * @which_clock: clockid
+ * @tp: timespec to fill.
+ *
+ * Provides the underlying alarm base time.
+ */
+static int alarm_clock_get(clockid_t which_clock, struct timespec *tp)
+{
+	struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
+
+	if (!alarmtimer_get_rtcdev())
+		return -ENOTSUPP;
+
+	*tp = ktime_to_timespec(base->gettime());
+	return 0;
+}
+
+/**
+ * alarm_timer_create - posix timer_create interface
+ * @new_timer: k_itimer pointer to manage
+ *
+ * Initializes the k_itimer structure.
+ */
+static int alarm_timer_create(struct k_itimer *new_timer)
+{
+	enum  alarmtimer_type type;
+	struct alarm_base *base;
+
+	if (!alarmtimer_get_rtcdev())
+		return -ENOTSUPP;
+
+	if (!capable(CAP_WAKE_ALARM))
+		return -EPERM;
+
+	type = clock2alarm(new_timer->it_clock);
+	base = &alarm_bases[type];
+	alarm_init(&new_timer->it.alarm.alarmtimer, type, alarm_handle_timer);
+	return 0;
+}
+
+/**
+ * alarm_timer_get - posix timer_get interface
+ * @new_timer: k_itimer pointer
+ * @cur_setting: itimerspec data to fill
+ *
+ * Copies the itimerspec data out from the k_itimer
+ */
+static void alarm_timer_get(struct k_itimer *timr,
+				struct itimerspec *cur_setting)
+{
+	memset(cur_setting, 0, sizeof(struct itimerspec));
+
+	cur_setting->it_interval =
+			ktime_to_timespec(timr->it.alarm.interval);
+	cur_setting->it_value =
+		ktime_to_timespec(timr->it.alarm.alarmtimer.node.expires);
+	return;
+}
+
+/**
+ * alarm_timer_del - posix timer_del interface
+ * @timr: k_itimer pointer to be deleted
+ *
+ * Cancels any programmed alarms for the given timer.
+ */
+static int alarm_timer_del(struct k_itimer *timr)
+{
+	if (!rtcdev)
+		return -ENOTSUPP;
+
+	if (alarm_try_to_cancel(&timr->it.alarm.alarmtimer) < 0)
+		return TIMER_RETRY;
+
+	return 0;
+}
+
+/**
+ * alarm_timer_set - posix timer_set interface
+ * @timr: k_itimer pointer to be deleted
+ * @flags: timer flags
+ * @new_setting: itimerspec to be used
+ * @old_setting: itimerspec being replaced
+ *
+ * Sets the timer to new_setting, and starts the timer.
+ */
+static int alarm_timer_set(struct k_itimer *timr, int flags,
+				struct itimerspec *new_setting,
+				struct itimerspec *old_setting)
+{
+	if (!rtcdev)
+		return -ENOTSUPP;
+
+	if (old_setting)
+		alarm_timer_get(timr, old_setting);
+
+	/* If the timer was already set, cancel it */
+	if (alarm_try_to_cancel(&timr->it.alarm.alarmtimer) < 0)
+		return TIMER_RETRY;
+
+	/* start the timer */
+	timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval);
+	alarm_start(&timr->it.alarm.alarmtimer,
+			timespec_to_ktime(new_setting->it_value));
+	return 0;
+}
+
+/**
+ * alarmtimer_nsleep_wakeup - Wakeup function for alarm_timer_nsleep
+ * @alarm: ptr to alarm that fired
+ *
+ * Wakes up the task that set the alarmtimer
+ */
+static enum alarmtimer_restart alarmtimer_nsleep_wakeup(struct alarm *alarm,
+								ktime_t now)
+{
+	struct task_struct *task = (struct task_struct *)alarm->data;
+
+	alarm->data = NULL;
+	if (task)
+		wake_up_process(task);
+	return ALARMTIMER_NORESTART;
+}
+
+/**
+ * alarmtimer_do_nsleep - Internal alarmtimer nsleep implementation
+ * @alarm: ptr to alarmtimer
+ * @absexp: absolute expiration time
+ *
+ * Sets the alarm timer and sleeps until it is fired or interrupted.
+ */
+static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp)
+{
+	alarm->data = (void *)current;
+	do {
+		set_current_state(TASK_INTERRUPTIBLE);
+		alarm_start(alarm, absexp);
+		if (likely(alarm->data))
+			schedule();
+
+		alarm_cancel(alarm);
+	} while (alarm->data && !signal_pending(current));
+
+	__set_current_state(TASK_RUNNING);
+
+	return (alarm->data == NULL);
+}
+
+
+/**
+ * update_rmtp - Update remaining timespec value
+ * @exp: expiration time
+ * @type: timer type
+ * @rmtp: user pointer to remaining timepsec value
+ *
+ * Helper function that fills in rmtp value with time between
+ * now and the exp value
+ */
+static int update_rmtp(ktime_t exp, enum  alarmtimer_type type,
+			struct timespec __user *rmtp)
+{
+	struct timespec rmt;
+	ktime_t rem;
+
+	rem = ktime_sub(exp, alarm_bases[type].gettime());
+
+	if (rem.tv64 <= 0)
+		return 0;
+	rmt = ktime_to_timespec(rem);
+
+	if (copy_to_user(rmtp, &rmt, sizeof(*rmtp)))
+		return -EFAULT;
+
+	return 1;
+
+}
+
+/**
+ * alarm_timer_nsleep_restart - restartblock alarmtimer nsleep
+ * @restart: ptr to restart block
+ *
+ * Handles restarted clock_nanosleep calls
+ */
+static long __sched alarm_timer_nsleep_restart(struct restart_block *restart)
+{
+	enum  alarmtimer_type type = restart->nanosleep.clockid;
+	ktime_t exp;
+	struct timespec __user  *rmtp;
+	struct alarm alarm;
+	int ret = 0;
+
+	exp.tv64 = restart->nanosleep.expires;
+	alarm_init(&alarm, type, alarmtimer_nsleep_wakeup);
+
+	if (alarmtimer_do_nsleep(&alarm, exp))
+		goto out;
+
+	if (freezing(current))
+		alarmtimer_freezerset(exp, type);
+
+	rmtp = restart->nanosleep.rmtp;
+	if (rmtp) {
+		ret = update_rmtp(exp, type, rmtp);
+		if (ret <= 0)
+			goto out;
+	}
+
+
+	/* The other values in restart are already filled in */
+	ret = -ERESTART_RESTARTBLOCK;
+out:
+	return ret;
+}
+
+/**
+ * alarm_timer_nsleep - alarmtimer nanosleep
+ * @which_clock: clockid
+ * @flags: determins abstime or relative
+ * @tsreq: requested sleep time (abs or rel)
+ * @rmtp: remaining sleep time saved
+ *
+ * Handles clock_nanosleep calls against _ALARM clockids
+ */
+static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
+		     struct timespec *tsreq, struct timespec __user *rmtp)
+{
+	enum  alarmtimer_type type = clock2alarm(which_clock);
+	struct alarm alarm;
+	ktime_t exp;
+	int ret = 0;
+	struct restart_block *restart;
+
+	if (!alarmtimer_get_rtcdev())
+		return -ENOTSUPP;
+
+	if (!capable(CAP_WAKE_ALARM))
+		return -EPERM;
+
+	alarm_init(&alarm, type, alarmtimer_nsleep_wakeup);
+
+	exp = timespec_to_ktime(*tsreq);
+	/* Convert (if necessary) to absolute time */
+	if (flags != TIMER_ABSTIME) {
+		ktime_t now = alarm_bases[type].gettime();
+		exp = ktime_add(now, exp);
+	}
+
+	if (alarmtimer_do_nsleep(&alarm, exp))
+		goto out;
+
+	if (freezing(current))
+		alarmtimer_freezerset(exp, type);
+
+	/* abs timers don't set remaining time or restart */
+	if (flags == TIMER_ABSTIME) {
+		ret = -ERESTARTNOHAND;
+		goto out;
+	}
+
+	if (rmtp) {
+		ret = update_rmtp(exp, type, rmtp);
+		if (ret <= 0)
+			goto out;
+	}
+
+	restart = &current_thread_info()->restart_block;
+	restart->fn = alarm_timer_nsleep_restart;
+	restart->nanosleep.clockid = type;
+	restart->nanosleep.expires = exp.tv64;
+	restart->nanosleep.rmtp = rmtp;
+	ret = -ERESTART_RESTARTBLOCK;
+
+out:
+	return ret;
+}
+
+
+/* Suspend hook structures */
+static const struct dev_pm_ops alarmtimer_pm_ops = {
+	.suspend = alarmtimer_suspend,
+};
+
+static struct platform_driver alarmtimer_driver = {
+	.driver = {
+		.name = "alarmtimer",
+		.pm = &alarmtimer_pm_ops,
+	}
+};
+
+/**
+ * alarmtimer_init - Initialize alarm timer code
+ *
+ * This function initializes the alarm bases and registers
+ * the posix clock ids.
+ */
+static int __init alarmtimer_init(void)
+{
+	struct platform_device *pdev;
+	int error = 0;
+	int i;
+	struct k_clock alarm_clock = {
+		.clock_getres	= alarm_clock_getres,
+		.clock_get	= alarm_clock_get,
+		.timer_create	= alarm_timer_create,
+		.timer_set	= alarm_timer_set,
+		.timer_del	= alarm_timer_del,
+		.timer_get	= alarm_timer_get,
+		.nsleep		= alarm_timer_nsleep,
+	};
+
+	alarmtimer_rtc_timer_init();
+
+	posix_timers_register_clock(CLOCK_REALTIME_ALARM, &alarm_clock);
+	posix_timers_register_clock(CLOCK_BOOTTIME_ALARM, &alarm_clock);
+
+	/* Initialize alarm bases */
+	alarm_bases[ALARM_REALTIME].base_clockid = CLOCK_REALTIME;
+	alarm_bases[ALARM_REALTIME].gettime = &ktime_get_real;
+	alarm_bases[ALARM_BOOTTIME].base_clockid = CLOCK_BOOTTIME;
+	alarm_bases[ALARM_BOOTTIME].gettime = &ktime_get_boottime;
+	for (i = 0; i < ALARM_NUMTYPE; i++) {
+		timerqueue_init_head(&alarm_bases[i].timerqueue);
+		spin_lock_init(&alarm_bases[i].lock);
+	}
+
+	error = alarmtimer_rtc_interface_setup();
+	if (error)
+		return error;
+
+	error = platform_driver_register(&alarmtimer_driver);
+	if (error)
+		goto out_if;
+
+	pdev = platform_device_register_simple("alarmtimer", -1, NULL, 0);
+	if (IS_ERR(pdev)) {
+		error = PTR_ERR(pdev);
+		goto out_drv;
+	}
+	ws = wakeup_source_register("alarmtimer");
+	return 0;
+
+out_drv:
+	platform_driver_unregister(&alarmtimer_driver);
+out_if:
+	alarmtimer_rtc_interface_remove();
+	return error;
+}
+device_initcall(alarmtimer_init);

kernel/time/clockevents.c

@@ -0,0 +1,465 @@
+/*
+ * linux/kernel/time/clockevents.c
+ *
+ * This file contains functions which manage clock event devices.
+ *
+ * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
+ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
+ *
+ * This code is licenced under the GPL version 2. For details see
+ * kernel-base/COPYING.
+ */
+
+#include <linux/clockchips.h>
+#include <linux/hrtimer.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/smp.h>
+
+#include "tick-internal.h"
+
+/* The registered clock event devices */
+static LIST_HEAD(clockevent_devices);
+static LIST_HEAD(clockevents_released);
+
+/* Notification for clock events */
+static RAW_NOTIFIER_HEAD(clockevents_chain);
+
+/* Protection for the above */
+static DEFINE_RAW_SPINLOCK(clockevents_lock);
+
+/**
+ * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds
+ * @latch:	value to convert
+ * @evt:	pointer to clock event device descriptor
+ *
+ * Math helper, returns latch value converted to nanoseconds (bound checked)
+ */
+u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
+{
+	u64 clc = (u64) latch << evt->shift;
+
+	if (unlikely(!evt->mult)) {
+		evt->mult = 1;
+		WARN_ON(1);
+	}
+
+	do_div(clc, evt->mult);
+	if (clc < 1000)
+		clc = 1000;
+	if (clc > KTIME_MAX)
+		clc = KTIME_MAX;
+
+	return clc;
+}
+EXPORT_SYMBOL_GPL(clockevent_delta2ns);
+
+/**
+ * clockevents_set_mode - set the operating mode of a clock event device
+ * @dev:	device to modify
+ * @mode:	new mode
+ *
+ * Must be called with interrupts disabled !
+ */
+void clockevents_set_mode(struct clock_event_device *dev,
+				 enum clock_event_mode mode)
+{
+	if (dev->mode != mode) {
+		dev->set_mode(mode, dev);
+		dev->mode = mode;
+
+		/*
+		 * 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 (unlikely(!dev->mult)) {
+				dev->mult = 1;
+				WARN_ON(1);
+			}
+		}
+	}
+}
+
+/**
+ * clockevents_shutdown - shutdown the device and clear next_event
+ * @dev:	device to shutdown
+ */
+void clockevents_shutdown(struct clock_event_device *dev)
+{
+	clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+	dev->next_event.tv64 = KTIME_MAX;
+}
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST
+
+/* Limit min_delta to a jiffie */
+#define MIN_DELTA_LIMIT		(NSEC_PER_SEC / HZ)
+
+/**
+ * clockevents_increase_min_delta - raise minimum delta of a clock event device
+ * @dev:       device to increase the minimum delta
+ *
+ * Returns 0 on success, -ETIME when the minimum delta reached the limit.
+ */
+static int clockevents_increase_min_delta(struct clock_event_device *dev)
+{
+	/* Nothing to do if we already reached the limit */
+	if (dev->min_delta_ns >= MIN_DELTA_LIMIT) {
+		printk(KERN_WARNING "CE: Reprogramming failure. Giving up\n");
+		dev->next_event.tv64 = KTIME_MAX;
+		return -ETIME;
+	}
+
+	if (dev->min_delta_ns < 5000)
+		dev->min_delta_ns = 5000;
+	else
+		dev->min_delta_ns += dev->min_delta_ns >> 1;
+
+	if (dev->min_delta_ns > MIN_DELTA_LIMIT)
+		dev->min_delta_ns = MIN_DELTA_LIMIT;
+
+	printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n",
+	       dev->name ? dev->name : "?",
+	       (unsigned long long) dev->min_delta_ns);
+	return 0;
+}
+
+/**
+ * clockevents_program_min_delta - Set clock event device to the minimum delay.
+ * @dev:	device to program
+ *
+ * Returns 0 on success, -ETIME when the retry loop failed.
+ */
+static int clockevents_program_min_delta(struct clock_event_device *dev)
+{
+	unsigned long long clc;
+	int64_t delta;
+	int i;
+
+	for (i = 0;;) {
+		delta = dev->min_delta_ns;
+		dev->next_event = ktime_add_ns(ktime_get(), delta);
+
+		if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN)
+			return 0;
+
+		dev->retries++;
+		clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
+		if (dev->set_next_event((unsigned long) clc, dev) == 0)
+			return 0;
+
+		if (++i > 2) {
+			/*
+			 * We tried 3 times to program the device with the
+			 * given min_delta_ns. Try to increase the minimum
+			 * delta, if that fails as well get out of here.
+			 */
+			if (clockevents_increase_min_delta(dev))
+				return -ETIME;
+			i = 0;
+		}
+	}
+}
+
+#else  /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */
+
+/**
+ * clockevents_program_min_delta - Set clock event device to the minimum delay.
+ * @dev:	device to program
+ *
+ * Returns 0 on success, -ETIME when the retry loop failed.
+ */
+static int clockevents_program_min_delta(struct clock_event_device *dev)
+{
+	unsigned long long clc;
+	int64_t delta;
+
+	delta = dev->min_delta_ns;
+	dev->next_event = ktime_add_ns(ktime_get(), delta);
+
+	if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN)
+		return 0;
+
+	dev->retries++;
+	clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
+	return dev->set_next_event((unsigned long) clc, dev);
+}
+
+#endif /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */
+
+/**
+ * clockevents_program_event - Reprogram the clock event device.
+ * @dev:	device to program
+ * @expires:	absolute expiry time (monotonic clock)
+ * @force:	program minimum delay if expires can not be set
+ *
+ * Returns 0 on success, -ETIME when the event is in the past.
+ */
+int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
+			      bool force)
+{
+	unsigned long long clc;
+	int64_t delta;
+	int rc;
+
+	if (unlikely(expires.tv64 < 0)) {
+		WARN_ON_ONCE(1);
+		return -ETIME;
+	}
+
+	dev->next_event = expires;
+
+	if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN)
+		return 0;
+
+	/* Shortcut for clockevent devices that can deal with ktime. */
+	if (dev->features & CLOCK_EVT_FEAT_KTIME)
+		return dev->set_next_ktime(expires, dev);
+
+	delta = ktime_to_ns(ktime_sub(expires, ktime_get()));
+	if (delta <= 0)
+		return force ? clockevents_program_min_delta(dev) : -ETIME;
+
+	delta = min(delta, (int64_t) dev->max_delta_ns);
+	delta = max(delta, (int64_t) dev->min_delta_ns);
+
+	clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
+	rc = dev->set_next_event((unsigned long) clc, dev);
+
+	return (rc && force) ? clockevents_program_min_delta(dev) : rc;
+}
+
+/**
+ * clockevents_register_notifier - register a clock events change listener
+ */
+int clockevents_register_notifier(struct notifier_block *nb)
+{
+	unsigned long flags;
+	int ret;
+
+	raw_spin_lock_irqsave(&clockevents_lock, flags);
+	ret = raw_notifier_chain_register(&clockevents_chain, nb);
+	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
+
+	return ret;
+}
+
+/*
+ * Notify about a clock event change. Called with clockevents_lock
+ * held.
+ */
+static void clockevents_do_notify(unsigned long reason, void *dev)
+{
+	raw_notifier_call_chain(&clockevents_chain, reason, dev);
+}
+
+/*
+ * Called after a notify add to make devices available which were
+ * released from the notifier call.
+ */
+static void clockevents_notify_released(void)
+{
+	struct clock_event_device *dev;
+
+	while (!list_empty(&clockevents_released)) {
+		dev = list_entry(clockevents_released.next,
+				 struct clock_event_device, list);
+		list_del(&dev->list);
+		list_add(&dev->list, &clockevent_devices);
+		clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+	}
+}
+
+/**
+ * clockevents_register_device - register a clock event device
+ * @dev:	device to register
+ */
+void clockevents_register_device(struct clock_event_device *dev)
+{
+	unsigned long flags;
+
+	BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
+	if (!dev->cpumask) {
+		WARN_ON(num_possible_cpus() > 1);
+		dev->cpumask = cpumask_of(smp_processor_id());
+	}
+
+	raw_spin_lock_irqsave(&clockevents_lock, flags);
+
+	list_add(&dev->list, &clockevent_devices);
+	clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+	clockevents_notify_released();
+
+	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
+}
+EXPORT_SYMBOL_GPL(clockevents_register_device);
+
+void clockevents_config(struct clock_event_device *dev, u32 freq)
+{
+	u64 sec;
+
+	if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+		return;
+
+	/*
+	 * Calculate the maximum number of seconds we can sleep. Limit
+	 * to 10 minutes for hardware which can program more than
+	 * 32bit ticks so we still get reasonable conversion values.
+	 */
+	sec = dev->max_delta_ticks;
+	do_div(sec, freq);
+	if (!sec)
+		sec = 1;
+	else if (sec > 600 && dev->max_delta_ticks > UINT_MAX)
+		sec = 600;
+
+	clockevents_calc_mult_shift(dev, freq, sec);
+	dev->min_delta_ns = clockevent_delta2ns(dev->min_delta_ticks, dev);
+	dev->max_delta_ns = clockevent_delta2ns(dev->max_delta_ticks, dev);
+}
+
+/**
+ * clockevents_config_and_register - Configure and register a clock event device
+ * @dev:	device to register
+ * @freq:	The clock frequency
+ * @min_delta:	The minimum clock ticks to program in oneshot mode
+ * @max_delta:	The maximum clock ticks to program in oneshot mode
+ *
+ * min/max_delta can be 0 for devices which do not support oneshot mode.
+ */
+void clockevents_config_and_register(struct clock_event_device *dev,
+				     u32 freq, unsigned long min_delta,
+				     unsigned long max_delta)
+{
+	dev->min_delta_ticks = min_delta;
+	dev->max_delta_ticks = max_delta;
+	clockevents_config(dev, freq);
+	clockevents_register_device(dev);
+}
+EXPORT_SYMBOL_GPL(clockevents_config_and_register);
+
+/**
+ * clockevents_update_freq - Update frequency and reprogram a clock event device.
+ * @dev:	device to modify
+ * @freq:	new device frequency
+ *
+ * Reconfigure and reprogram a clock event device in oneshot
+ * mode. Must be called on the cpu for which the device delivers per
+ * cpu timer events with interrupts disabled!  Returns 0 on success,
+ * -ETIME when the event is in the past.
+ */
+int clockevents_update_freq(struct clock_event_device *dev, u32 freq)
+{
+	clockevents_config(dev, freq);
+
+	if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
+		return 0;
+
+	return clockevents_program_event(dev, dev->next_event, false);
+}
+
+/*
+ * Noop handler when we shut down an event device
+ */
+void clockevents_handle_noop(struct clock_event_device *dev)
+{
+}
+
+/**
+ * clockevents_exchange_device - release and request clock devices
+ * @old:	device to release (can be NULL)
+ * @new:	device to request (can be NULL)
+ *
+ * Called from the notifier chain. clockevents_lock is held already
+ */
+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) {
+		clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
+		list_del(&old->list);
+		list_add(&old->list, &clockevents_released);
+	}
+
+	if (new) {
+		BUG_ON(new->mode != CLOCK_EVT_MODE_UNUSED);
+		clockevents_shutdown(new);
+	}
+	local_irq_restore(flags);
+}
+
+/**
+ * clockevents_suspend - suspend clock devices
+ */
+void clockevents_suspend(void)
+{
+	struct clock_event_device *dev;
+
+	list_for_each_entry_reverse(dev, &clockevent_devices, list)
+		if (dev->suspend)
+			dev->suspend(dev);
+}
+
+/**
+ * clockevents_resume - resume clock devices
+ */
+void clockevents_resume(void)
+{
+	struct clock_event_device *dev;
+
+	list_for_each_entry(dev, &clockevent_devices, list)
+		if (dev->resume)
+			dev->resume(dev);
+}
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+/**
+ * clockevents_notify - notification about relevant events
+ */
+void clockevents_notify(unsigned long reason, void *arg)
+{
+	struct clock_event_device *dev, *tmp;
+	unsigned long flags;
+	int cpu;
+
+	raw_spin_lock_irqsave(&clockevents_lock, flags);
+	clockevents_do_notify(reason, arg);
+
+	switch (reason) {
+	case CLOCK_EVT_NOTIFY_CPU_DEAD:
+		/*
+		 * 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
+		 */
+		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);
+}
+EXPORT_SYMBOL_GPL(clockevents_notify);
+#endif

kernel/time/clocksource.c

@@ -0,0 +1,962 @@
+/*
+ * linux/kernel/time/clocksource.c
+ *
+ * This file contains the functions which manage clocksource drivers.
+ *
+ * Copyright (C) 2004, 2005 IBM, John Stultz (johnstul@us.ibm.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * TODO WishList:
+ *   o Allow clocksource drivers to be unregistered
+ */
+
+#include <linux/device.h>
+#include <linux/clocksource.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */
+#include <linux/tick.h>
+#include <linux/kthread.h>
+
+#include "timekeeping_internal.h"
+
+void timecounter_init(struct timecounter *tc,
+		      const struct cyclecounter *cc,
+		      u64 start_tstamp)
+{
+	tc->cc = cc;
+	tc->cycle_last = cc->read(cc);
+	tc->nsec = start_tstamp;
+}
+EXPORT_SYMBOL_GPL(timecounter_init);
+
+/**
+ * timecounter_read_delta - get nanoseconds since last call of this function
+ * @tc:         Pointer to time counter
+ *
+ * When the underlying cycle counter runs over, this will be handled
+ * correctly as long as it does not run over more than once between
+ * calls.
+ *
+ * The first call to this function for a new time counter initializes
+ * the time tracking and returns an undefined result.
+ */
+static u64 timecounter_read_delta(struct timecounter *tc)
+{
+	cycle_t cycle_now, cycle_delta;
+	u64 ns_offset;
+
+	/* read cycle counter: */
+	cycle_now = tc->cc->read(tc->cc);
+
+	/* calculate the delta since the last timecounter_read_delta(): */
+	cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask;
+
+	/* convert to nanoseconds: */
+	ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta);
+
+	/* update time stamp of timecounter_read_delta() call: */
+	tc->cycle_last = cycle_now;
+
+	return ns_offset;
+}
+
+u64 timecounter_read(struct timecounter *tc)
+{
+	u64 nsec;
+
+	/* increment time by nanoseconds since last call */
+	nsec = timecounter_read_delta(tc);
+	nsec += tc->nsec;
+	tc->nsec = nsec;
+
+	return nsec;
+}
+EXPORT_SYMBOL_GPL(timecounter_read);
+
+u64 timecounter_cyc2time(struct timecounter *tc,
+			 cycle_t cycle_tstamp)
+{
+	u64 cycle_delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
+	u64 nsec;
+
+	/*
+	 * Instead of always treating cycle_tstamp as more recent
+	 * than tc->cycle_last, detect when it is too far in the
+	 * future and treat it as old time stamp instead.
+	 */
+	if (cycle_delta > tc->cc->mask / 2) {
+		cycle_delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask;
+		nsec = tc->nsec - cyclecounter_cyc2ns(tc->cc, cycle_delta);
+	} else {
+		nsec = cyclecounter_cyc2ns(tc->cc, cycle_delta) + tc->nsec;
+	}
+
+	return nsec;
+}
+EXPORT_SYMBOL_GPL(timecounter_cyc2time);
+
+/**
+ * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks
+ * @mult:	pointer to mult variable
+ * @shift:	pointer to shift variable
+ * @from:	frequency to convert from
+ * @to:		frequency to convert to
+ * @maxsec:	guaranteed runtime conversion range in seconds
+ *
+ * The function evaluates the shift/mult pair for the scaled math
+ * operations of clocksources and clockevents.
+ *
+ * @to and @from are frequency values in HZ. For clock sources @to is
+ * NSEC_PER_SEC == 1GHz and @from is the counter frequency. For clock
+ * event @to is the counter frequency and @from is NSEC_PER_SEC.
+ *
+ * The @maxsec conversion range argument controls the time frame in
+ * seconds which must be covered by the runtime conversion with the
+ * calculated mult and shift factors. This guarantees that no 64bit
+ * overflow happens when the input value of the conversion is
+ * multiplied with the calculated mult factor. Larger ranges may
+ * reduce the conversion accuracy by chosing smaller mult and shift
+ * factors.
+ */
+void
+clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 maxsec)
+{
+	u64 tmp;
+	u32 sft, sftacc= 32;
+
+	/*
+	 * Calculate the shift factor which is limiting the conversion
+	 * range:
+	 */
+	tmp = ((u64)maxsec * from) >> 32;
+	while (tmp) {
+		tmp >>=1;
+		sftacc--;
+	}
+
+	/*
+	 * Find the conversion shift/mult pair which has the best
+	 * accuracy and fits the maxsec conversion range:
+	 */
+	for (sft = 32; sft > 0; sft--) {
+		tmp = (u64) to << sft;
+		tmp += from / 2;
+		do_div(tmp, from);
+		if ((tmp >> sftacc) == 0)
+			break;
+	}
+	*mult = tmp;
+	*shift = sft;
+}
+
+/*[Clocksource internal variables]---------
+ * curr_clocksource:
+ *	currently selected clocksource.
+ * clocksource_list:
+ *	linked list with the registered clocksources
+ * clocksource_mutex:
+ *	protects manipulations to curr_clocksource and the clocksource_list
+ * override_name:
+ *	Name of the user-specified clocksource.
+ */
+static struct clocksource *curr_clocksource;
+static LIST_HEAD(clocksource_list);
+static DEFINE_MUTEX(clocksource_mutex);
+static char override_name[32];
+static int finished_booting;
+
+#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
+static void clocksource_watchdog_work(struct work_struct *work);
+
+static LIST_HEAD(watchdog_list);
+static struct clocksource *watchdog;
+static struct timer_list watchdog_timer;
+static DECLARE_WORK(watchdog_work, clocksource_watchdog_work);
+static DEFINE_SPINLOCK(watchdog_lock);
+static int watchdog_running;
+static atomic_t watchdog_reset_pending;
+
+static int clocksource_watchdog_kthread(void *data);
+static void __clocksource_change_rating(struct clocksource *cs, int rating);
+
+/*
+ * Interval: 0.5sec Threshold: 0.0625s
+ */
+#define WATCHDOG_INTERVAL (HZ >> 1)
+#define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4)
+
+static void clocksource_watchdog_work(struct work_struct *work)
+{
+	/*
+	 * If kthread_run fails the next watchdog scan over the
+	 * watchdog_list will find the unstable clock again.
+	 */
+	kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog");
+}
+
+static void __clocksource_unstable(struct clocksource *cs)
+{
+	cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
+	cs->flags |= CLOCK_SOURCE_UNSTABLE;
+	if (finished_booting)
+		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
+ *
+ * This function is called instead of clocksource_change_rating from
+ * cpu hotplug code to avoid a deadlock between the clocksource mutex
+ * and the cpu hotplug mutex. It defers the update of the clocksource
+ * to the watchdog thread.
+ */
+void clocksource_mark_unstable(struct clocksource *cs)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&watchdog_lock, flags);
+	if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) {
+		if (list_empty(&cs->wd_list))
+			list_add(&cs->wd_list, &watchdog_list);
+		__clocksource_unstable(cs);
+	}
+	spin_unlock_irqrestore(&watchdog_lock, flags);
+}
+
+static void clocksource_watchdog(unsigned long data)
+{
+	struct clocksource *cs;
+	cycle_t csnow, wdnow, delta;
+	int64_t wd_nsec, cs_nsec;
+	int next_cpu, reset_pending;
+
+	spin_lock(&watchdog_lock);
+	if (!watchdog_running)
+		goto out;
+
+	reset_pending = atomic_read(&watchdog_reset_pending);
+
+	list_for_each_entry(cs, &watchdog_list, wd_list) {
+
+		/* Clocksource already marked unstable? */
+		if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
+			if (finished_booting)
+				schedule_work(&watchdog_work);
+			continue;
+		}
+
+		local_irq_disable();
+		csnow = cs->read(cs);
+		wdnow = watchdog->read(watchdog);
+		local_irq_enable();
+
+		/* Clocksource initialized ? */
+		if (!(cs->flags & CLOCK_SOURCE_WATCHDOG) ||
+		    atomic_read(&watchdog_reset_pending)) {
+			cs->flags |= CLOCK_SOURCE_WATCHDOG;
+			cs->wd_last = wdnow;
+			cs->cs_last = csnow;
+			continue;
+		}
+
+		delta = clocksource_delta(wdnow, cs->wd_last, watchdog->mask);
+		wd_nsec = clocksource_cyc2ns(delta, watchdog->mult,
+					     watchdog->shift);
+
+		delta = clocksource_delta(csnow, cs->cs_last, cs->mask);
+		cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift);
+		cs->cs_last = csnow;
+		cs->wd_last = wdnow;
+
+		if (atomic_read(&watchdog_reset_pending))
+			continue;
+
+		/* Check the deviation from the watchdog clocksource. */
+		if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) {
+			clocksource_unstable(cs, cs_nsec - wd_nsec);
+			continue;
+		}
+
+		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
+		    (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) &&
+		    (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) {
+			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+			/*
+			 * We just marked the clocksource as highres-capable,
+			 * notify the rest of the system as well so that we
+			 * transition into high-res mode:
+			 */
+			tick_clock_notify();
+		}
+	}
+
+	/*
+	 * We only clear the watchdog_reset_pending, when we did a
+	 * full cycle through all clocksources.
+	 */
+	if (reset_pending)
+		atomic_dec(&watchdog_reset_pending);
+
+	/*
+	 * Cycle through CPUs to check if the CPUs stay synchronized
+	 * to each other.
+	 */
+	next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
+	if (next_cpu >= nr_cpu_ids)
+		next_cpu = cpumask_first(cpu_online_mask);
+	watchdog_timer.expires += WATCHDOG_INTERVAL;
+	add_timer_on(&watchdog_timer, next_cpu);
+out:
+	spin_unlock(&watchdog_lock);
+}
+
+static inline void clocksource_start_watchdog(void)
+{
+	if (watchdog_running || !watchdog || list_empty(&watchdog_list))
+		return;
+	init_timer(&watchdog_timer);
+	watchdog_timer.function = clocksource_watchdog;
+	watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
+	add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask));
+	watchdog_running = 1;
+}
+
+static inline void clocksource_stop_watchdog(void)
+{
+	if (!watchdog_running || (watchdog && !list_empty(&watchdog_list)))
+		return;
+	del_timer(&watchdog_timer);
+	watchdog_running = 0;
+}
+
+static inline void clocksource_reset_watchdog(void)
+{
+	struct clocksource *cs;
+
+	list_for_each_entry(cs, &watchdog_list, wd_list)
+		cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
+}
+
+static void clocksource_resume_watchdog(void)
+{
+	atomic_inc(&watchdog_reset_pending);
+}
+
+static void clocksource_enqueue_watchdog(struct clocksource *cs)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&watchdog_lock, flags);
+	if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
+		/* cs is a clocksource to be watched. */
+		list_add(&cs->wd_list, &watchdog_list);
+		cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
+	} else {
+		/* cs is a watchdog. */
+		if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
+			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+		/* Pick the best watchdog. */
+		if (!watchdog || cs->rating > watchdog->rating) {
+			watchdog = cs;
+			/* Reset watchdog cycles */
+			clocksource_reset_watchdog();
+		}
+	}
+	/* Check if the watchdog timer needs to be started. */
+	clocksource_start_watchdog();
+	spin_unlock_irqrestore(&watchdog_lock, flags);
+}
+
+static void clocksource_dequeue_watchdog(struct clocksource *cs)
+{
+	struct clocksource *tmp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&watchdog_lock, flags);
+	if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
+		/* cs is a watched clocksource. */
+		list_del_init(&cs->wd_list);
+	} else if (cs == watchdog) {
+		/* Reset watchdog cycles */
+		clocksource_reset_watchdog();
+		/* Current watchdog is removed. Find an alternative. */
+		watchdog = NULL;
+		list_for_each_entry(tmp, &clocksource_list, list) {
+			if (tmp == cs || tmp->flags & CLOCK_SOURCE_MUST_VERIFY)
+				continue;
+			if (!watchdog || tmp->rating > watchdog->rating)
+				watchdog = tmp;
+		}
+	}
+	cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
+	/* Check if the watchdog timer needs to be stopped. */
+	clocksource_stop_watchdog();
+	spin_unlock_irqrestore(&watchdog_lock, flags);
+}
+
+static int clocksource_watchdog_kthread(void *data)
+{
+	struct clocksource *cs, *tmp;
+	unsigned long flags;
+	LIST_HEAD(unstable);
+
+	mutex_lock(&clocksource_mutex);
+	spin_lock_irqsave(&watchdog_lock, flags);
+	list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list)
+		if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
+			list_del_init(&cs->wd_list);
+			list_add(&cs->wd_list, &unstable);
+		}
+	/* Check if the watchdog timer needs to be stopped. */
+	clocksource_stop_watchdog();
+	spin_unlock_irqrestore(&watchdog_lock, flags);
+
+	/* Needs to be done outside of watchdog lock */
+	list_for_each_entry_safe(cs, tmp, &unstable, wd_list) {
+		list_del_init(&cs->wd_list);
+		__clocksource_change_rating(cs, 0);
+	}
+	mutex_unlock(&clocksource_mutex);
+	return 0;
+}
+
+#else /* CONFIG_CLOCKSOURCE_WATCHDOG */
+
+static void clocksource_enqueue_watchdog(struct clocksource *cs)
+{
+	if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
+		cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+}
+
+static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
+static inline void clocksource_resume_watchdog(void) { }
+static inline int clocksource_watchdog_kthread(void *data) { return 0; }
+
+#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
+
+/**
+ * clocksource_suspend - suspend the clocksource(s)
+ */
+void clocksource_suspend(void)
+{
+	struct clocksource *cs;
+
+	list_for_each_entry_reverse(cs, &clocksource_list, list)
+		if (cs->suspend)
+			cs->suspend(cs);
+}
+
+/**
+ * clocksource_resume - resume the clocksource(s)
+ */
+void clocksource_resume(void)
+{
+	struct clocksource *cs;
+
+	list_for_each_entry(cs, &clocksource_list, list)
+		if (cs->resume)
+			cs->resume(cs);
+
+	clocksource_resume_watchdog();
+}
+
+/**
+ * clocksource_touch_watchdog - Update watchdog
+ *
+ * Update the watchdog after exception contexts such as kgdb so as not
+ * to incorrectly trip the watchdog. This might fail when the kernel
+ * was stopped in code which holds watchdog_lock.
+ */
+void clocksource_touch_watchdog(void)
+{
+	clocksource_resume_watchdog();
+}
+
+/**
+ * clocksource_max_adjustment- Returns max adjustment amount
+ * @cs:         Pointer to clocksource
+ *
+ */
+static u32 clocksource_max_adjustment(struct clocksource *cs)
+{
+	u64 ret;
+	/*
+	 * We won't try to correct for more than 11% adjustments (110,000 ppm),
+	 */
+	ret = (u64)cs->mult * 11;
+	do_div(ret,100);
+	return (u32)ret;
+}
+
+/**
+ * clocksource_max_deferment - Returns max time the clocksource can be deferred
+ * @cs:         Pointer to clocksource
+ *
+ */
+static u64 clocksource_max_deferment(struct clocksource *cs)
+{
+	u64 max_nsecs, max_cycles;
+
+	/*
+	 * Calculate the maximum number of cycles that we can pass to the
+	 * cyc2ns function without overflowing a 64-bit signed result. The
+	 * maximum number of cycles is equal to ULLONG_MAX/(cs->mult+cs->maxadj)
+	 * which is equivalent to the below.
+	 * max_cycles < (2^63)/(cs->mult + cs->maxadj)
+	 * max_cycles < 2^(log2((2^63)/(cs->mult + cs->maxadj)))
+	 * max_cycles < 2^(log2(2^63) - log2(cs->mult + cs->maxadj))
+	 * max_cycles < 2^(63 - log2(cs->mult + cs->maxadj))
+	 * max_cycles < 1 << (63 - log2(cs->mult + cs->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.
+	 */
+	max_cycles = 1ULL << (63 - (ilog2(cs->mult + cs->maxadj) + 1));
+
+	/*
+	 * The actual maximum number of cycles we can defer the clocksource is
+	 * determined by the minimum of max_cycles and cs->mask.
+	 * Note: Here we subtract the maxadj to make sure we don't sleep for
+	 * too long if there's a large negative adjustment.
+	 */
+	max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
+	max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult - cs->maxadj,
+					cs->shift);
+
+	/*
+	 * To ensure that the clocksource does not wrap whilst we are idle,
+	 * limit the time the clocksource can be deferred by 12.5%. Please
+	 * note a margin of 12.5% is used because this can be computed with
+	 * a shift, versus say 10% which would require division.
+	 */
+	return max_nsecs - (max_nsecs >> 3);
+}
+
+#ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
+
+/**
+ * clocksource_select - Select the best clocksource available
+ *
+ * Private function. Must hold clocksource_mutex when called.
+ *
+ * Select the clocksource with the best rating, or the clocksource,
+ * which is selected by userspace override.
+ */
+static void clocksource_select(void)
+{
+	struct clocksource *best, *cs;
+
+	if (!finished_booting || list_empty(&clocksource_list))
+		return;
+	/* First clocksource on the list has the best rating. */
+	best = list_first_entry(&clocksource_list, struct clocksource, list);
+	/* Check for the override clocksource. */
+	list_for_each_entry(cs, &clocksource_list, list) {
+		if (strcmp(cs->name, override_name) != 0)
+			continue;
+		/*
+		 * Check to make sure we don't switch to a non-highres
+		 * capable clocksource if the tick code is in oneshot
+		 * mode (highres or nohz)
+		 */
+		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
+		    tick_oneshot_mode_active()) {
+			/* Override clocksource cannot be used. */
+			printk(KERN_WARNING "Override clocksource %s is not "
+			       "HRT compatible. Cannot switch while in "
+			       "HRT/NOHZ mode\n", cs->name);
+			override_name[0] = 0;
+		} else
+			/* Override clocksource can be used. */
+			best = cs;
+		break;
+	}
+
+	if (curr_clocksource != best && !timekeeping_notify(best)) {
+		pr_info("Switched to clocksource %s\n", best->name);
+		curr_clocksource = best;
+	}
+}
+
+#else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */
+
+static inline void clocksource_select(void) { }
+
+#endif
+
+/*
+ * clocksource_done_booting - Called near the end of core bootup
+ *
+ * Hack to avoid lots of clocksource churn at boot time.
+ * We use arch_initcall because we want this to start before
+ * device_initcall but after SMP init.
+ */
+static int __init clocksource_done_booting(void)
+{
+	mutex_lock(&clocksource_mutex);
+	curr_clocksource = clocksource_default_clock();
+	mutex_unlock(&clocksource_mutex);
+
+	finished_booting = 1;
+
+	/*
+	 * Run the watchdog first to eliminate unstable clock sources
+	 */
+	clocksource_watchdog_kthread(NULL);
+
+	mutex_lock(&clocksource_mutex);
+	clocksource_select();
+	mutex_unlock(&clocksource_mutex);
+	return 0;
+}
+arch_initcall(clocksource_done_booting);
+
+/*
+ * Enqueue the clocksource sorted by rating
+ */
+static void clocksource_enqueue(struct clocksource *cs)
+{
+	struct list_head *entry = &clocksource_list;
+	struct clocksource *tmp;
+
+	list_for_each_entry(tmp, &clocksource_list, list)
+		/* Keep track of the place, where to insert */
+		if (tmp->rating >= cs->rating)
+			entry = &tmp->list;
+	list_add(&cs->list, entry);
+}
+
+/**
+ * __clocksource_updatefreq_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
+ *
+ * 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.
+ */
+void __clocksource_updatefreq_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()
+	 */
+	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);
+
+	/*
+	 * for clocksources that have large mults, to avoid overflow.
+	 * Since mult may be adjusted by ntp, add an safety extra margin
+	 *
+	 */
+	cs->maxadj = clocksource_max_adjustment(cs);
+	while ((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);
+}
+EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
+
+/**
+ * __clocksource_register_scale - Used to install new clocksources
+ * @cs:		clocksource to be registered
+ * @scale:	Scale factor multiplied against freq to get clocksource hz
+ * @freq:	clocksource frequency (cycles per second) divided by scale
+ *
+ * Returns -EBUSY if registration fails, zero otherwise.
+ *
+ * This *SHOULD NOT* be called directly! Please use the
+ * clocksource_register_hz() or clocksource_register_khz helper functions.
+ */
+int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
+{
+
+	/* Initialize mult/shift and max_idle_ns */
+	__clocksource_updatefreq_scale(cs, scale, freq);
+
+	/* Add clocksource to the clcoksource list */
+	mutex_lock(&clocksource_mutex);
+	clocksource_enqueue(cs);
+	clocksource_enqueue_watchdog(cs);
+	clocksource_select();
+	mutex_unlock(&clocksource_mutex);
+	return 0;
+}
+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);
+	cs->rating = rating;
+	clocksource_enqueue(cs);
+	clocksource_select();
+}
+
+/**
+ * clocksource_change_rating - Change the rating of a registered clocksource
+ * @cs:		clocksource to be changed
+ * @rating:	new rating
+ */
+void clocksource_change_rating(struct clocksource *cs, int rating)
+{
+	mutex_lock(&clocksource_mutex);
+	__clocksource_change_rating(cs, rating);
+	mutex_unlock(&clocksource_mutex);
+}
+EXPORT_SYMBOL(clocksource_change_rating);
+
+/**
+ * clocksource_unregister - remove a registered clocksource
+ * @cs:	clocksource to be unregistered
+ */
+void clocksource_unregister(struct clocksource *cs)
+{
+	mutex_lock(&clocksource_mutex);
+	clocksource_dequeue_watchdog(cs);
+	list_del(&cs->list);
+	clocksource_select();
+	mutex_unlock(&clocksource_mutex);
+}
+EXPORT_SYMBOL(clocksource_unregister);
+
+#ifdef CONFIG_SYSFS
+/**
+ * sysfs_show_current_clocksources - sysfs interface for current clocksource
+ * @dev:	unused
+ * @attr:	unused
+ * @buf:	char buffer to be filled with clocksource list
+ *
+ * Provides sysfs interface for listing current clocksource.
+ */
+static ssize_t
+sysfs_show_current_clocksources(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	ssize_t count = 0;
+
+	mutex_lock(&clocksource_mutex);
+	count = snprintf(buf, PAGE_SIZE, "%s\n", curr_clocksource->name);
+	mutex_unlock(&clocksource_mutex);
+
+	return count;
+}
+
+/**
+ * sysfs_override_clocksource - interface for manually overriding clocksource
+ * @dev:	unused
+ * @attr:	unused
+ * @buf:	name of override clocksource
+ * @count:	length of buffer
+ *
+ * Takes input from sysfs interface for manually overriding the default
+ * clocksource selection.
+ */
+static ssize_t sysfs_override_clocksource(struct device *dev,
+					  struct device_attribute *attr,
+					  const char *buf, size_t count)
+{
+	size_t ret = count;
+
+	/* strings from sysfs write are not 0 terminated! */
+	if (count >= sizeof(override_name))
+		return -EINVAL;
+
+	/* strip of \n: */
+	if (buf[count-1] == '\n')
+		count--;
+
+	mutex_lock(&clocksource_mutex);
+
+	if (count > 0)
+		memcpy(override_name, buf, count);
+	override_name[count] = 0;
+	clocksource_select();
+
+	mutex_unlock(&clocksource_mutex);
+
+	return ret;
+}
+
+/**
+ * sysfs_show_available_clocksources - sysfs interface for listing clocksource
+ * @dev:	unused
+ * @attr:	unused
+ * @buf:	char buffer to be filled with clocksource list
+ *
+ * Provides sysfs interface for listing registered clocksources
+ */
+static ssize_t
+sysfs_show_available_clocksources(struct device *dev,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	struct clocksource *src;
+	ssize_t count = 0;
+
+	mutex_lock(&clocksource_mutex);
+	list_for_each_entry(src, &clocksource_list, list) {
+		/*
+		 * Don't show non-HRES clocksource if the tick code is
+		 * in one shot mode (highres=on or nohz=on)
+		 */
+		if (!tick_oneshot_mode_active() ||
+		    (src->flags & CLOCK_SOURCE_VALID_FOR_HRES))
+			count += snprintf(buf + count,
+				  max((ssize_t)PAGE_SIZE - count, (ssize_t)0),
+				  "%s ", src->name);
+	}
+	mutex_unlock(&clocksource_mutex);
+
+	count += snprintf(buf + count,
+			  max((ssize_t)PAGE_SIZE - count, (ssize_t)0), "\n");
+
+	return count;
+}
+
+/*
+ * Sysfs setup bits:
+ */
+static DEVICE_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources,
+		   sysfs_override_clocksource);
+
+static DEVICE_ATTR(available_clocksource, 0444,
+		   sysfs_show_available_clocksources, NULL);
+
+static struct bus_type clocksource_subsys = {
+	.name = "clocksource",
+	.dev_name = "clocksource",
+};
+
+static struct device device_clocksource = {
+	.id	= 0,
+	.bus	= &clocksource_subsys,
+};
+
+static int __init init_clocksource_sysfs(void)
+{
+	int error = subsys_system_register(&clocksource_subsys, NULL);
+
+	if (!error)
+		error = device_register(&device_clocksource);
+	if (!error)
+		error = device_create_file(
+				&device_clocksource,
+				&dev_attr_current_clocksource);
+	if (!error)
+		error = device_create_file(
+				&device_clocksource,
+				&dev_attr_available_clocksource);
+	return error;
+}
+
+device_initcall(init_clocksource_sysfs);
+#endif /* CONFIG_SYSFS */
+
+/**
+ * boot_override_clocksource - boot clock override
+ * @str:	override name
+ *
+ * Takes a clocksource= boot argument and uses it
+ * as the clocksource override name.
+ */
+static int __init boot_override_clocksource(char* str)
+{
+	mutex_lock(&clocksource_mutex);
+	if (str)
+		strlcpy(override_name, str, sizeof(override_name));
+	mutex_unlock(&clocksource_mutex);
+	return 1;
+}
+
+__setup("clocksource=", boot_override_clocksource);
+
+/**
+ * boot_override_clock - Compatibility layer for deprecated boot option
+ * @str:	override name
+ *
+ * DEPRECATED! Takes a clock= boot argument and uses it
+ * as the clocksource override name
+ */
+static int __init boot_override_clock(char* str)
+{
+	if (!strcmp(str, "pmtmr")) {
+		printk("Warning: clock=pmtmr is deprecated. "
+			"Use clocksource=acpi_pm.\n");
+		return boot_override_clocksource("acpi_pm");
+	}
+	printk("Warning! clock= boot option is deprecated. "
+		"Use clocksource=xyz\n");
+	return boot_override_clocksource(str);
+}
+
+__setup("clock=", boot_override_clock);

kernel/time/jiffies.c

@@ -0,0 +1,129 @@
+/***********************************************************************
+* linux/kernel/time/jiffies.c
+*
+* This file contains the jiffies based clocksource.
+*
+* Copyright (C) 2004, 2005 IBM, John Stultz (johnstul@us.ibm.com)
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License as published by
+* the Free Software Foundation; either version 2 of the License, or
+* (at your option) any later version.
+*
+* This program is distributed in the hope that it will be useful,
+* but WITHOUT ANY WARRANTY; without even the implied warranty of
+* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+* GNU General Public License for more details.
+*
+* You should have received a copy of the GNU General Public License
+* along with this program; if not, write to the Free Software
+* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+*
+************************************************************************/
+#include <linux/clocksource.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include "tick-internal.h"
+
+/* The Jiffies based clocksource is the lowest common
+ * denominator clock source which should function on
+ * all systems. It has the same coarse resolution as
+ * the timer interrupt frequency HZ and it suffers
+ * inaccuracies caused by missed or lost timer
+ * interrupts and the inability for the timer
+ * interrupt hardware to accuratly tick at the
+ * requested HZ value. It is also not recommended
+ * for "tick-less" systems.
+ */
+#define NSEC_PER_JIFFY	((NSEC_PER_SEC+HZ/2)/HZ)
+
+/* Since jiffies uses a simple NSEC_PER_JIFFY multiplier
+ * conversion, the .shift value could be zero. However
+ * this would make NTP adjustments impossible as they are
+ * in units of 1/2^.shift. Thus we use JIFFIES_SHIFT to
+ * shift both the nominator and denominator the same
+ * amount, and give ntp adjustments in units of 1/2^8
+ *
+ * The value 8 is somewhat carefully chosen, as anything
+ * larger can result in overflows. NSEC_PER_JIFFY grows as
+ * HZ shrinks, so values greater than 8 overflow 32bits when
+ * HZ=100.
+ */
+#define JIFFIES_SHIFT	8
+
+static cycle_t jiffies_read(struct clocksource *cs)
+{
+	return (cycle_t) jiffies;
+}
+
+static struct clocksource clocksource_jiffies = {
+	.name		= "jiffies",
+	.rating		= 1, /* lowest valid rating*/
+	.read		= jiffies_read,
+	.mask		= 0xffffffff, /*32bits*/
+	.mult		= NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
+	.shift		= JIFFIES_SHIFT,
+};
+
+__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock);
+
+#if (BITS_PER_LONG < 64)
+u64 get_jiffies_64(void)
+{
+	unsigned long seq;
+	u64 ret;
+
+	do {
+		seq = read_seqbegin(&jiffies_lock);
+		ret = jiffies_64;
+	} while (read_seqretry(&jiffies_lock, seq));
+	return ret;
+}
+EXPORT_SYMBOL(get_jiffies_64);
+#endif
+
+EXPORT_SYMBOL(jiffies);
+
+static int __init init_jiffies_clocksource(void)
+{
+	return clocksource_register(&clocksource_jiffies);
+}
+
+core_initcall(init_jiffies_clocksource);
+
+struct clocksource * __init __weak clocksource_default_clock(void)
+{
+	return &clocksource_jiffies;
+}
+
+struct clocksource refined_jiffies;
+
+int register_refined_jiffies(long cycles_per_second)
+{
+	u64 nsec_per_tick, shift_hz;
+	long cycles_per_tick;
+
+
+
+	refined_jiffies = clocksource_jiffies;
+	refined_jiffies.name = "refined-jiffies";
+	refined_jiffies.rating++;
+
+	/* Calc cycles per tick */
+	cycles_per_tick = (cycles_per_second + HZ/2)/HZ;
+	/* shift_hz stores hz<<8 for extra accuracy */
+	shift_hz = (u64)cycles_per_second << 8;
+	shift_hz += cycles_per_tick/2;
+	do_div(shift_hz, cycles_per_tick);
+	/* Calculate nsec_per_tick using shift_hz */
+	nsec_per_tick = (u64)NSEC_PER_SEC << 8;
+	nsec_per_tick += (u32)shift_hz/2;
+	do_div(nsec_per_tick, (u32)shift_hz);
+
+	refined_jiffies.mult = ((u32)nsec_per_tick) << JIFFIES_SHIFT;
+
+	clocksource_register(&refined_jiffies);
+	return 0;
+}

kernel/time/ntp.c

@@ -0,0 +1,935 @@
+/*
+ * NTP state machine interfaces and logic.
+ *
+ * This code was mainly moved from kernel/timer.c and kernel/time.c
+ * Please see those files for relevant copyright info and historical
+ * changelogs.
+ */
+#include <linux/capability.h>
+#include <linux/clocksource.h>
+#include <linux/workqueue.h>
+#include <linux/hrtimer.h>
+#include <linux/jiffies.h>
+#include <linux/math64.h>
+#include <linux/timex.h>
+#include <linux/time.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/rtc.h>
+
+#include "tick-internal.h"
+#include "ntp_internal.h"
+
+/*
+ * NTP timekeeping variables:
+ *
+ * Note: All of the NTP state is protected by the timekeeping locks.
+ */
+
+
+/* USER_HZ period (usecs): */
+unsigned long			tick_usec = TICK_USEC;
+
+/* SHIFTED_HZ period (nsecs): */
+unsigned long			tick_nsec;
+
+static u64			tick_length;
+static u64			tick_length_base;
+
+#define MAX_TICKADJ		500LL		/* usecs */
+#define MAX_TICKADJ_SCALED \
+	(((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
+
+/*
+ * phase-lock loop variables
+ */
+
+/*
+ * clock synchronization status
+ *
+ * (TIME_ERROR prevents overwriting the CMOS clock)
+ */
+static int			time_state = TIME_OK;
+
+/* clock status bits:							*/
+static int			time_status = STA_UNSYNC;
+
+/* time adjustment (nsecs):						*/
+static s64			time_offset;
+
+/* pll time constant:							*/
+static long			time_constant = 2;
+
+/* maximum error (usecs):						*/
+static long			time_maxerror = NTP_PHASE_LIMIT;
+
+/* estimated error (usecs):						*/
+static long			time_esterror = NTP_PHASE_LIMIT;
+
+/* frequency offset (scaled nsecs/secs):				*/
+static s64			time_freq;
+
+/* time at last adjustment (secs):					*/
+static long			time_reftime;
+
+static long			time_adjust;
+
+/* constant (boot-param configurable) NTP tick adjustment (upscaled)	*/
+static s64			ntp_tick_adj;
+
+#ifdef CONFIG_NTP_PPS
+
+/*
+ * The following variables are used when a pulse-per-second (PPS) signal
+ * is available. They establish the engineering parameters of the clock
+ * discipline loop when controlled by the PPS signal.
+ */
+#define PPS_VALID	10	/* PPS signal watchdog max (s) */
+#define PPS_POPCORN	4	/* popcorn spike threshold (shift) */
+#define PPS_INTMIN	2	/* min freq interval (s) (shift) */
+#define PPS_INTMAX	8	/* max freq interval (s) (shift) */
+#define PPS_INTCOUNT	4	/* number of consecutive good intervals to
+				   increase pps_shift or consecutive bad
+				   intervals to decrease it */
+#define PPS_MAXWANDER	100000	/* max PPS freq wander (ns/s) */
+
+static int pps_valid;		/* signal watchdog counter */
+static long pps_tf[3];		/* phase median filter */
+static long pps_jitter;		/* current jitter (ns) */
+static struct timespec pps_fbase; /* beginning of the last freq interval */
+static int pps_shift;		/* current interval duration (s) (shift) */
+static int pps_intcnt;		/* interval counter */
+static s64 pps_freq;		/* frequency offset (scaled ns/s) */
+static long pps_stabil;		/* current stability (scaled ns/s) */
+
+/*
+ * PPS signal quality monitors
+ */
+static long pps_calcnt;		/* calibration intervals */
+static long pps_jitcnt;		/* jitter limit exceeded */
+static long pps_stbcnt;		/* stability limit exceeded */
+static long pps_errcnt;		/* calibration errors */
+
+
+/* PPS kernel consumer compensates the whole phase error immediately.
+ * Otherwise, reduce the offset by a fixed factor times the time constant.
+ */
+static inline s64 ntp_offset_chunk(s64 offset)
+{
+	if (time_status & STA_PPSTIME && time_status & STA_PPSSIGNAL)
+		return offset;
+	else
+		return shift_right(offset, SHIFT_PLL + time_constant);
+}
+
+static inline void pps_reset_freq_interval(void)
+{
+	/* the PPS calibration interval may end
+	   surprisingly early */
+	pps_shift = PPS_INTMIN;
+	pps_intcnt = 0;
+}
+
+/**
+ * pps_clear - Clears the PPS state variables
+ */
+static inline void pps_clear(void)
+{
+	pps_reset_freq_interval();
+	pps_tf[0] = 0;
+	pps_tf[1] = 0;
+	pps_tf[2] = 0;
+	pps_fbase.tv_sec = pps_fbase.tv_nsec = 0;
+	pps_freq = 0;
+}
+
+/* Decrease pps_valid to indicate that another second has passed since
+ * the last PPS signal. When it reaches 0, indicate that PPS signal is
+ * missing.
+ */
+static inline void pps_dec_valid(void)
+{
+	if (pps_valid > 0)
+		pps_valid--;
+	else {
+		time_status &= ~(STA_PPSSIGNAL | STA_PPSJITTER |
+				 STA_PPSWANDER | STA_PPSERROR);
+		pps_clear();
+	}
+}
+
+static inline void pps_set_freq(s64 freq)
+{
+	pps_freq = freq;
+}
+
+static inline int is_error_status(int status)
+{
+	return (time_status & (STA_UNSYNC|STA_CLOCKERR))
+		/* PPS signal lost when either PPS time or
+		 * PPS frequency synchronization requested
+		 */
+		|| ((time_status & (STA_PPSFREQ|STA_PPSTIME))
+			&& !(time_status & STA_PPSSIGNAL))
+		/* PPS jitter exceeded when
+		 * PPS time synchronization requested */
+		|| ((time_status & (STA_PPSTIME|STA_PPSJITTER))
+			== (STA_PPSTIME|STA_PPSJITTER))
+		/* PPS wander exceeded or calibration error when
+		 * PPS frequency synchronization requested
+		 */
+		|| ((time_status & STA_PPSFREQ)
+			&& (time_status & (STA_PPSWANDER|STA_PPSERROR)));
+}
+
+static inline void pps_fill_timex(struct timex *txc)
+{
+	txc->ppsfreq	   = shift_right((pps_freq >> PPM_SCALE_INV_SHIFT) *
+					 PPM_SCALE_INV, NTP_SCALE_SHIFT);
+	txc->jitter	   = pps_jitter;
+	if (!(time_status & STA_NANO))
+		txc->jitter /= NSEC_PER_USEC;
+	txc->shift	   = pps_shift;
+	txc->stabil	   = pps_stabil;
+	txc->jitcnt	   = pps_jitcnt;
+	txc->calcnt	   = pps_calcnt;
+	txc->errcnt	   = pps_errcnt;
+	txc->stbcnt	   = pps_stbcnt;
+}
+
+#else /* !CONFIG_NTP_PPS */
+
+static inline s64 ntp_offset_chunk(s64 offset)
+{
+	return shift_right(offset, SHIFT_PLL + time_constant);
+}
+
+static inline void pps_reset_freq_interval(void) {}
+static inline void pps_clear(void) {}
+static inline void pps_dec_valid(void) {}
+static inline void pps_set_freq(s64 freq) {}
+
+static inline int is_error_status(int status)
+{
+	return status & (STA_UNSYNC|STA_CLOCKERR);
+}
+
+static inline void pps_fill_timex(struct timex *txc)
+{
+	/* PPS is not implemented, so these are zero */
+	txc->ppsfreq	   = 0;
+	txc->jitter	   = 0;
+	txc->shift	   = 0;
+	txc->stabil	   = 0;
+	txc->jitcnt	   = 0;
+	txc->calcnt	   = 0;
+	txc->errcnt	   = 0;
+	txc->stbcnt	   = 0;
+}
+
+#endif /* CONFIG_NTP_PPS */
+
+
+/**
+ * ntp_synced - Returns 1 if the NTP status is not UNSYNC
+ *
+ */
+static inline int ntp_synced(void)
+{
+	return !(time_status & STA_UNSYNC);
+}
+
+
+/*
+ * NTP methods:
+ */
+
+/*
+ * Update (tick_length, tick_length_base, tick_nsec), based
+ * on (tick_usec, ntp_tick_adj, time_freq):
+ */
+static void ntp_update_frequency(void)
+{
+	u64 second_length;
+	u64 new_base;
+
+	second_length		 = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ)
+						<< NTP_SCALE_SHIFT;
+
+	second_length		+= ntp_tick_adj;
+	second_length		+= time_freq;
+
+	tick_nsec		 = div_u64(second_length, HZ) >> NTP_SCALE_SHIFT;
+	new_base		 = div_u64(second_length, NTP_INTERVAL_FREQ);
+
+	/*
+	 * Don't wait for the next second_overflow, apply
+	 * the change to the tick length immediately:
+	 */
+	tick_length		+= new_base - tick_length_base;
+	tick_length_base	 = new_base;
+}
+
+static inline s64 ntp_update_offset_fll(s64 offset64, long secs)
+{
+	time_status &= ~STA_MODE;
+
+	if (secs < MINSEC)
+		return 0;
+
+	if (!(time_status & STA_FLL) && (secs <= MAXSEC))
+		return 0;
+
+	time_status |= STA_MODE;
+
+	return div64_long(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs);
+}
+
+static void ntp_update_offset(long offset)
+{
+	s64 freq_adj;
+	s64 offset64;
+	long secs;
+
+	if (!(time_status & STA_PLL))
+		return;
+
+	if (!(time_status & STA_NANO))
+		offset *= NSEC_PER_USEC;
+
+	/*
+	 * Scale the phase adjustment and
+	 * clamp to the operating range.
+	 */
+	offset = min(offset, MAXPHASE);
+	offset = max(offset, -MAXPHASE);
+
+	/*
+	 * Select how the frequency is to be controlled
+	 * and in which mode (PLL or FLL).
+	 */
+	secs = get_seconds() - time_reftime;
+	if (unlikely(time_status & STA_FREQHOLD))
+		secs = 0;
+
+	time_reftime = get_seconds();
+
+	offset64    = offset;
+	freq_adj    = ntp_update_offset_fll(offset64, secs);
+
+	/*
+	 * Clamp update interval to reduce PLL gain with low
+	 * sampling rate (e.g. intermittent network connection)
+	 * to avoid instability.
+	 */
+	if (unlikely(secs > 1 << (SHIFT_PLL + 1 + time_constant)))
+		secs = 1 << (SHIFT_PLL + 1 + time_constant);
+
+	freq_adj    += (offset64 * secs) <<
+			(NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant));
+
+	freq_adj    = min(freq_adj + time_freq, MAXFREQ_SCALED);
+
+	time_freq   = max(freq_adj, -MAXFREQ_SCALED);
+
+	time_offset = div_s64(offset64 << NTP_SCALE_SHIFT, NTP_INTERVAL_FREQ);
+}
+
+/**
+ * ntp_clear - Clears the NTP state variables
+ */
+void ntp_clear(void)
+{
+	time_adjust	= 0;		/* stop active adjtime() */
+	time_status	|= STA_UNSYNC;
+	time_maxerror	= NTP_PHASE_LIMIT;
+	time_esterror	= NTP_PHASE_LIMIT;
+
+	ntp_update_frequency();
+
+	tick_length	= tick_length_base;
+	time_offset	= 0;
+
+	/* Clear PPS state variables */
+	pps_clear();
+}
+
+
+u64 ntp_tick_length(void)
+{
+	return tick_length;
+}
+
+
+/*
+ * this routine handles the overflow of the microsecond field
+ *
+ * The tricky bits of code to handle the accurate clock support
+ * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
+ * They were originally developed for SUN and DEC kernels.
+ * All the kudos should go to Dave for this stuff.
+ *
+ * Also handles leap second processing, and returns leap offset
+ */
+int second_overflow(unsigned long secs)
+{
+	s64 delta;
+	int leap = 0;
+
+	/*
+	 * Leap second processing. If in leap-insert state at the end of the
+	 * day, the system clock is set back one second; if in leap-delete
+	 * state, the system clock is set ahead one second.
+	 */
+	switch (time_state) {
+	case TIME_OK:
+		if (time_status & STA_INS)
+			time_state = TIME_INS;
+		else if (time_status & STA_DEL)
+			time_state = TIME_DEL;
+		break;
+	case TIME_INS:
+		if (!(time_status & STA_INS))
+			time_state = TIME_OK;
+		else if (secs % 86400 == 0) {
+			leap = -1;
+			time_state = TIME_OOP;
+			printk(KERN_NOTICE
+				"Clock: inserting leap second 23:59:60 UTC\n");
+		}
+		break;
+	case TIME_DEL:
+		if (!(time_status & STA_DEL))
+			time_state = TIME_OK;
+		else if ((secs + 1) % 86400 == 0) {
+			leap = 1;
+			time_state = TIME_WAIT;
+			printk(KERN_NOTICE
+				"Clock: deleting leap second 23:59:59 UTC\n");
+		}
+		break;
+	case TIME_OOP:
+		time_state = TIME_WAIT;
+		break;
+
+	case TIME_WAIT:
+		if (!(time_status & (STA_INS | STA_DEL)))
+			time_state = TIME_OK;
+		break;
+	}
+
+
+	/* Bump the maxerror field */
+	time_maxerror += MAXFREQ / NSEC_PER_USEC;
+	if (time_maxerror > NTP_PHASE_LIMIT) {
+		time_maxerror = NTP_PHASE_LIMIT;
+		time_status |= STA_UNSYNC;
+	}
+
+	/* Compute the phase adjustment for the next second */
+	tick_length	 = tick_length_base;
+
+	delta		 = ntp_offset_chunk(time_offset);
+	time_offset	-= delta;
+	tick_length	+= delta;
+
+	/* Check PPS signal */
+	pps_dec_valid();
+
+	if (!time_adjust)
+		goto out;
+
+	if (time_adjust > MAX_TICKADJ) {
+		time_adjust -= MAX_TICKADJ;
+		tick_length += MAX_TICKADJ_SCALED;
+		goto out;
+	}
+
+	if (time_adjust < -MAX_TICKADJ) {
+		time_adjust += MAX_TICKADJ;
+		tick_length -= MAX_TICKADJ_SCALED;
+		goto out;
+	}
+
+	tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ)
+							 << NTP_SCALE_SHIFT;
+	time_adjust = 0;
+
+out:
+	return leap;
+}
+
+#if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC)
+static void sync_cmos_clock(struct work_struct *work);
+
+static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock);
+
+static void sync_cmos_clock(struct work_struct *work)
+{
+	struct timespec now, next;
+	int fail = 1;
+
+	/*
+	 * If we have an externally synchronized Linux clock, then update
+	 * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be
+	 * called as close as possible to 500 ms before the new second starts.
+	 * This code is run on a timer.  If the clock is set, that timer
+	 * may not expire at the correct time.  Thus, we adjust...
+	 */
+	if (!ntp_synced()) {
+		/*
+		 * Not synced, exit, do not restart a timer (if one is
+		 * running, let it run out).
+		 */
+		return;
+	}
+
+	getnstimeofday(&now);
+	if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2) {
+		struct timespec adjust = now;
+
+		fail = -ENODEV;
+		if (persistent_clock_is_local)
+			adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
+#ifdef CONFIG_GENERIC_CMOS_UPDATE
+		fail = update_persistent_clock(adjust);
+#endif
+#ifdef CONFIG_RTC_SYSTOHC
+		if (fail == -ENODEV)
+			fail = rtc_set_ntp_time(adjust);
+#endif
+	}
+
+	next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec - (TICK_NSEC / 2);
+	if (next.tv_nsec <= 0)
+		next.tv_nsec += NSEC_PER_SEC;
+
+	if (!fail || fail == -ENODEV)
+		next.tv_sec = 659;
+	else
+		next.tv_sec = 0;
+
+	if (next.tv_nsec >= NSEC_PER_SEC) {
+		next.tv_sec++;
+		next.tv_nsec -= NSEC_PER_SEC;
+	}
+	schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
+}
+
+void ntp_notify_cmos_timer(void)
+{
+	schedule_delayed_work(&sync_cmos_work, 0);
+}
+
+#else
+void ntp_notify_cmos_timer(void) { }
+#endif
+
+
+/*
+ * Propagate a new txc->status value into the NTP state:
+ */
+static inline void process_adj_status(struct timex *txc, struct timespec *ts)
+{
+	if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) {
+		time_state = TIME_OK;
+		time_status = STA_UNSYNC;
+		/* restart PPS frequency calibration */
+		pps_reset_freq_interval();
+	}
+
+	/*
+	 * If we turn on PLL adjustments then reset the
+	 * reference time to current time.
+	 */
+	if (!(time_status & STA_PLL) && (txc->status & STA_PLL))
+		time_reftime = get_seconds();
+
+	/* only set allowed bits */
+	time_status &= STA_RONLY;
+	time_status |= txc->status & ~STA_RONLY;
+}
+
+
+static inline void process_adjtimex_modes(struct timex *txc,
+						struct timespec *ts,
+						s32 *time_tai)
+{
+	if (txc->modes & ADJ_STATUS)
+		process_adj_status(txc, ts);
+
+	if (txc->modes & ADJ_NANO)
+		time_status |= STA_NANO;
+
+	if (txc->modes & ADJ_MICRO)
+		time_status &= ~STA_NANO;
+
+	if (txc->modes & ADJ_FREQUENCY) {
+		time_freq = txc->freq * PPM_SCALE;
+		time_freq = min(time_freq, MAXFREQ_SCALED);
+		time_freq = max(time_freq, -MAXFREQ_SCALED);
+		/* update pps_freq */
+		pps_set_freq(time_freq);
+	}
+
+	if (txc->modes & ADJ_MAXERROR)
+		time_maxerror = txc->maxerror;
+
+	if (txc->modes & ADJ_ESTERROR)
+		time_esterror = txc->esterror;
+
+	if (txc->modes & ADJ_TIMECONST) {
+		time_constant = txc->constant;
+		if (!(time_status & STA_NANO))
+			time_constant += 4;
+		time_constant = min(time_constant, (long)MAXTC);
+		time_constant = max(time_constant, 0l);
+	}
+
+	if (txc->modes & ADJ_TAI && txc->constant > 0)
+		*time_tai = txc->constant;
+
+	if (txc->modes & ADJ_OFFSET)
+		ntp_update_offset(txc->offset);
+
+	if (txc->modes & ADJ_TICK)
+		tick_usec = txc->tick;
+
+	if (txc->modes & (ADJ_TICK|ADJ_FREQUENCY|ADJ_OFFSET))
+		ntp_update_frequency();
+}
+
+
+
+/**
+ * ntp_validate_timex - Ensures the timex is ok for use in do_adjtimex
+ */
+int ntp_validate_timex(struct timex *txc)
+{
+	if (txc->modes & ADJ_ADJTIME) {
+		/* singleshot must not be used with any other mode bits */
+		if (!(txc->modes & ADJ_OFFSET_SINGLESHOT))
+			return -EINVAL;
+		if (!(txc->modes & ADJ_OFFSET_READONLY) &&
+		    !capable(CAP_SYS_TIME))
+			return -EPERM;
+	} else {
+		/* In order to modify anything, you gotta be super-user! */
+		 if (txc->modes && !capable(CAP_SYS_TIME))
+			return -EPERM;
+		/*
+		 * if the quartz is off by more than 10% then
+		 * something is VERY wrong!
+		 */
+		if (txc->modes & ADJ_TICK &&
+		    (txc->tick <  900000/USER_HZ ||
+		     txc->tick > 1100000/USER_HZ))
+			return -EINVAL;
+	}
+
+	if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
+		return -EPERM;
+
+	return 0;
+}
+
+
+/*
+ * adjtimex mainly allows reading (and writing, if superuser) of
+ * kernel time-keeping variables. used by xntpd.
+ */
+int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai)
+{
+	int result;
+
+	if (txc->modes & ADJ_ADJTIME) {
+		long save_adjust = time_adjust;
+
+		if (!(txc->modes & ADJ_OFFSET_READONLY)) {
+			/* adjtime() is independent from ntp_adjtime() */
+			time_adjust = txc->offset;
+			ntp_update_frequency();
+		}
+		txc->offset = save_adjust;
+	} else {
+
+		/* If there are input parameters, then process them: */
+		if (txc->modes)
+			process_adjtimex_modes(txc, ts, time_tai);
+
+		txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
+				  NTP_SCALE_SHIFT);
+		if (!(time_status & STA_NANO))
+			txc->offset /= NSEC_PER_USEC;
+	}
+
+	result = time_state;	/* mostly `TIME_OK' */
+	/* check for errors */
+	if (is_error_status(time_status))
+		result = TIME_ERROR;
+
+	txc->freq	   = shift_right((time_freq >> PPM_SCALE_INV_SHIFT) *
+					 PPM_SCALE_INV, NTP_SCALE_SHIFT);
+	txc->maxerror	   = time_maxerror;
+	txc->esterror	   = time_esterror;
+	txc->status	   = time_status;
+	txc->constant	   = time_constant;
+	txc->precision	   = 1;
+	txc->tolerance	   = MAXFREQ_SCALED / PPM_SCALE;
+	txc->tick	   = tick_usec;
+	txc->tai	   = *time_tai;
+
+	/* fill PPS status fields */
+	pps_fill_timex(txc);
+
+	txc->time.tv_sec = ts->tv_sec;
+	txc->time.tv_usec = ts->tv_nsec;
+	if (!(time_status & STA_NANO))
+		txc->time.tv_usec /= NSEC_PER_USEC;
+
+	return result;
+}
+
+#ifdef	CONFIG_NTP_PPS
+
+/* actually struct pps_normtime is good old struct timespec, but it is
+ * semantically different (and it is the reason why it was invented):
+ * pps_normtime.nsec has a range of ( -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ]
+ * while timespec.tv_nsec has a range of [0, NSEC_PER_SEC) */
+struct pps_normtime {
+	__kernel_time_t	sec;	/* seconds */
+	long		nsec;	/* nanoseconds */
+};
+
+/* normalize the timestamp so that nsec is in the
+   ( -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ] interval */
+static inline struct pps_normtime pps_normalize_ts(struct timespec ts)
+{
+	struct pps_normtime norm = {
+		.sec = ts.tv_sec,
+		.nsec = ts.tv_nsec
+	};
+
+	if (norm.nsec > (NSEC_PER_SEC >> 1)) {
+		norm.nsec -= NSEC_PER_SEC;
+		norm.sec++;
+	}
+
+	return norm;
+}
+
+/* get current phase correction and jitter */
+static inline long pps_phase_filter_get(long *jitter)
+{
+	*jitter = pps_tf[0] - pps_tf[1];
+	if (*jitter < 0)
+		*jitter = -*jitter;
+
+	/* TODO: test various filters */
+	return pps_tf[0];
+}
+
+/* add the sample to the phase filter */
+static inline void pps_phase_filter_add(long err)
+{
+	pps_tf[2] = pps_tf[1];
+	pps_tf[1] = pps_tf[0];
+	pps_tf[0] = err;
+}
+
+/* decrease frequency calibration interval length.
+ * It is halved after four consecutive unstable intervals.
+ */
+static inline void pps_dec_freq_interval(void)
+{
+	if (--pps_intcnt <= -PPS_INTCOUNT) {
+		pps_intcnt = -PPS_INTCOUNT;
+		if (pps_shift > PPS_INTMIN) {
+			pps_shift--;
+			pps_intcnt = 0;
+		}
+	}
+}
+
+/* increase frequency calibration interval length.
+ * It is doubled after four consecutive stable intervals.
+ */
+static inline void pps_inc_freq_interval(void)
+{
+	if (++pps_intcnt >= PPS_INTCOUNT) {
+		pps_intcnt = PPS_INTCOUNT;
+		if (pps_shift < PPS_INTMAX) {
+			pps_shift++;
+			pps_intcnt = 0;
+		}
+	}
+}
+
+/* update clock frequency based on MONOTONIC_RAW clock PPS signal
+ * timestamps
+ *
+ * At the end of the calibration interval the difference between the
+ * first and last MONOTONIC_RAW clock timestamps divided by the length
+ * of the interval becomes the frequency update. If the interval was
+ * too long, the data are discarded.
+ * Returns the difference between old and new frequency values.
+ */
+static long hardpps_update_freq(struct pps_normtime freq_norm)
+{
+	long delta, delta_mod;
+	s64 ftemp;
+
+	/* check if the frequency interval was too long */
+	if (freq_norm.sec > (2 << pps_shift)) {
+		time_status |= STA_PPSERROR;
+		pps_errcnt++;
+		pps_dec_freq_interval();
+		pr_err("hardpps: PPSERROR: interval too long - %ld s\n",
+				freq_norm.sec);
+		return 0;
+	}
+
+	/* here the raw frequency offset and wander (stability) is
+	 * calculated. If the wander is less than the wander threshold
+	 * the interval is increased; otherwise it is decreased.
+	 */
+	ftemp = div_s64(((s64)(-freq_norm.nsec)) << NTP_SCALE_SHIFT,
+			freq_norm.sec);
+	delta = shift_right(ftemp - pps_freq, NTP_SCALE_SHIFT);
+	pps_freq = ftemp;
+	if (delta > PPS_MAXWANDER || delta < -PPS_MAXWANDER) {
+		pr_warning("hardpps: PPSWANDER: change=%ld\n", delta);
+		time_status |= STA_PPSWANDER;
+		pps_stbcnt++;
+		pps_dec_freq_interval();
+	} else {	/* good sample */
+		pps_inc_freq_interval();
+	}
+
+	/* the stability metric is calculated as the average of recent
+	 * frequency changes, but is used only for performance
+	 * monitoring
+	 */
+	delta_mod = delta;
+	if (delta_mod < 0)
+		delta_mod = -delta_mod;
+	pps_stabil += (div_s64(((s64)delta_mod) <<
+				(NTP_SCALE_SHIFT - SHIFT_USEC),
+				NSEC_PER_USEC) - pps_stabil) >> PPS_INTMIN;
+
+	/* if enabled, the system clock frequency is updated */
+	if ((time_status & STA_PPSFREQ) != 0 &&
+	    (time_status & STA_FREQHOLD) == 0) {
+		time_freq = pps_freq;
+		ntp_update_frequency();
+	}
+
+	return delta;
+}
+
+/* correct REALTIME clock phase error against PPS signal */
+static void hardpps_update_phase(long error)
+{
+	long correction = -error;
+	long jitter;
+
+	/* add the sample to the median filter */
+	pps_phase_filter_add(correction);
+	correction = pps_phase_filter_get(&jitter);
+
+	/* Nominal jitter is due to PPS signal noise. If it exceeds the
+	 * threshold, the sample is discarded; otherwise, if so enabled,
+	 * the time offset is updated.
+	 */
+	if (jitter > (pps_jitter << PPS_POPCORN)) {
+		pr_warning("hardpps: PPSJITTER: jitter=%ld, limit=%ld\n",
+		       jitter, (pps_jitter << PPS_POPCORN));
+		time_status |= STA_PPSJITTER;
+		pps_jitcnt++;
+	} else if (time_status & STA_PPSTIME) {
+		/* correct the time using the phase offset */
+		time_offset = div_s64(((s64)correction) << NTP_SCALE_SHIFT,
+				NTP_INTERVAL_FREQ);
+		/* cancel running adjtime() */
+		time_adjust = 0;
+	}
+	/* update jitter */
+	pps_jitter += (jitter - pps_jitter) >> PPS_INTMIN;
+}
+
+/*
+ * __hardpps() - discipline CPU clock oscillator to external PPS signal
+ *
+ * This routine is called at each PPS signal arrival in order to
+ * discipline the CPU clock oscillator to the PPS signal. It takes two
+ * parameters: REALTIME and MONOTONIC_RAW clock timestamps. The former
+ * is used to correct clock phase error and the latter is used to
+ * correct the frequency.
+ *
+ * This code is based on David Mills's reference nanokernel
+ * implementation. It was mostly rewritten but keeps the same idea.
+ */
+void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
+{
+	struct pps_normtime pts_norm, freq_norm;
+
+	pts_norm = pps_normalize_ts(*phase_ts);
+
+	/* clear the error bits, they will be set again if needed */
+	time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR);
+
+	/* indicate signal presence */
+	time_status |= STA_PPSSIGNAL;
+	pps_valid = PPS_VALID;
+
+	/* when called for the first time,
+	 * just start the frequency interval */
+	if (unlikely(pps_fbase.tv_sec == 0)) {
+		pps_fbase = *raw_ts;
+		return;
+	}
+
+	/* ok, now we have a base for frequency calculation */
+	freq_norm = pps_normalize_ts(timespec_sub(*raw_ts, pps_fbase));
+
+	/* check that the signal is in the range
+	 * [1s - MAXFREQ us, 1s + MAXFREQ us], otherwise reject it */
+	if ((freq_norm.sec == 0) ||
+			(freq_norm.nsec > MAXFREQ * freq_norm.sec) ||
+			(freq_norm.nsec < -MAXFREQ * freq_norm.sec)) {
+		time_status |= STA_PPSJITTER;
+		/* restart the frequency calibration interval */
+		pps_fbase = *raw_ts;
+		pr_err("hardpps: PPSJITTER: bad pulse\n");
+		return;
+	}
+
+	/* signal is ok */
+
+	/* check if the current frequency interval is finished */
+	if (freq_norm.sec >= (1 << pps_shift)) {
+		pps_calcnt++;
+		/* restart the frequency calibration interval */
+		pps_fbase = *raw_ts;
+		hardpps_update_freq(freq_norm);
+	}
+
+	hardpps_update_phase(pts_norm.nsec);
+
+}
+#endif	/* CONFIG_NTP_PPS */
+
+static int __init ntp_tick_adj_setup(char *str)
+{
+	ntp_tick_adj = simple_strtol(str, NULL, 0);
+	ntp_tick_adj <<= NTP_SCALE_SHIFT;
+
+	return 1;
+}
+
+__setup("ntp_tick_adj=", ntp_tick_adj_setup);
+
+void __init ntp_init(void)
+{
+	ntp_clear();
+}

kernel/time/ntp_internal.h

@@ -0,0 +1,12 @@
+#ifndef _LINUX_NTP_INTERNAL_H
+#define _LINUX_NTP_INTERNAL_H
+
+extern void ntp_init(void);
+extern void ntp_clear(void);
+/* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */
+extern u64 ntp_tick_length(void);
+extern int second_overflow(unsigned long secs);
+extern int ntp_validate_timex(struct timex *);
+extern int __do_adjtimex(struct timex *, struct timespec *, s32 *);
+extern void __hardpps(const struct timespec *, const struct timespec *);
+#endif /* _LINUX_NTP_INTERNAL_H */

kernel/time/posix-clock.c

@@ -0,0 +1,446 @@
+/*
+ * posix-clock.c - support for dynamic clock devices
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/file.h>
+#include <linux/posix-clock.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/uaccess.h>
+
+static void delete_clock(struct kref *kref);
+
+/*
+ * Returns NULL if the posix_clock instance attached to 'fp' is old and stale.
+ */
+static struct posix_clock *get_posix_clock(struct file *fp)
+{
+	struct posix_clock *clk = fp->private_data;
+
+	down_read(&clk->rwsem);
+
+	if (!clk->zombie)
+		return clk;
+
+	up_read(&clk->rwsem);
+
+	return NULL;
+}
+
+static void put_posix_clock(struct posix_clock *clk)
+{
+	up_read(&clk->rwsem);
+}
+
+static ssize_t posix_clock_read(struct file *fp, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -EINVAL;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.read)
+		err = clk->ops.read(clk, fp->f_flags, buf, count);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+static unsigned int posix_clock_poll(struct file *fp, poll_table *wait)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int result = 0;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.poll)
+		result = clk->ops.poll(clk, fp, wait);
+
+	put_posix_clock(clk);
+
+	return result;
+}
+
+static int posix_clock_fasync(int fd, struct file *fp, int on)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = 0;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.fasync)
+		err = clk->ops.fasync(clk, fd, fp, on);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+static int posix_clock_mmap(struct file *fp, struct vm_area_struct *vma)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -ENODEV;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.mmap)
+		err = clk->ops.mmap(clk, vma);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+static long posix_clock_ioctl(struct file *fp,
+			      unsigned int cmd, unsigned long arg)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -ENOTTY;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.ioctl)
+		err = clk->ops.ioctl(clk, cmd, arg);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+#ifdef CONFIG_COMPAT
+static long posix_clock_compat_ioctl(struct file *fp,
+				     unsigned int cmd, unsigned long arg)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -ENOTTY;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.ioctl)
+		err = clk->ops.ioctl(clk, cmd, arg);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+#endif
+
+static int posix_clock_open(struct inode *inode, struct file *fp)
+{
+	int err;
+	struct posix_clock *clk =
+		container_of(inode->i_cdev, struct posix_clock, cdev);
+
+	down_read(&clk->rwsem);
+
+	if (clk->zombie) {
+		err = -ENODEV;
+		goto out;
+	}
+	if (clk->ops.open)
+		err = clk->ops.open(clk, fp->f_mode);
+	else
+		err = 0;
+
+	if (!err) {
+		kref_get(&clk->kref);
+		fp->private_data = clk;
+	}
+out:
+	up_read(&clk->rwsem);
+	return err;
+}
+
+static int posix_clock_release(struct inode *inode, struct file *fp)
+{
+	struct posix_clock *clk = fp->private_data;
+	int err = 0;
+
+	if (clk->ops.release)
+		err = clk->ops.release(clk);
+
+	kref_put(&clk->kref, delete_clock);
+
+	fp->private_data = NULL;
+
+	return err;
+}
+
+static const struct file_operations posix_clock_file_operations = {
+	.owner		= THIS_MODULE,
+	.llseek		= no_llseek,
+	.read		= posix_clock_read,
+	.poll		= posix_clock_poll,
+	.unlocked_ioctl	= posix_clock_ioctl,
+	.open		= posix_clock_open,
+	.release	= posix_clock_release,
+	.fasync		= posix_clock_fasync,
+	.mmap		= posix_clock_mmap,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= posix_clock_compat_ioctl,
+#endif
+};
+
+int posix_clock_register(struct posix_clock *clk, dev_t devid)
+{
+	int err;
+
+	kref_init(&clk->kref);
+	init_rwsem(&clk->rwsem);
+
+	cdev_init(&clk->cdev, &posix_clock_file_operations);
+	clk->cdev.owner = clk->ops.owner;
+	err = cdev_add(&clk->cdev, devid, 1);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(posix_clock_register);
+
+static void delete_clock(struct kref *kref)
+{
+	struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
+
+	if (clk->release)
+		clk->release(clk);
+}
+
+void posix_clock_unregister(struct posix_clock *clk)
+{
+	cdev_del(&clk->cdev);
+
+	down_write(&clk->rwsem);
+	clk->zombie = true;
+	up_write(&clk->rwsem);
+
+	kref_put(&clk->kref, delete_clock);
+}
+EXPORT_SYMBOL_GPL(posix_clock_unregister);
+
+struct posix_clock_desc {
+	struct file *fp;
+	struct posix_clock *clk;
+};
+
+static int get_clock_desc(const clockid_t id, struct posix_clock_desc *cd)
+{
+	struct file *fp = fget(CLOCKID_TO_FD(id));
+	int err = -EINVAL;
+
+	if (!fp)
+		return err;
+
+	if (fp->f_op->open != posix_clock_open || !fp->private_data)
+		goto out;
+
+	cd->fp = fp;
+	cd->clk = get_posix_clock(fp);
+
+	err = cd->clk ? 0 : -ENODEV;
+out:
+	if (err)
+		fput(fp);
+	return err;
+}
+
+static void put_clock_desc(struct posix_clock_desc *cd)
+{
+	put_posix_clock(cd->clk);
+	fput(cd->fp);
+}
+
+static int pc_clock_adjtime(clockid_t id, struct timex *tx)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if ((cd.fp->f_mode & FMODE_WRITE) == 0) {
+		err = -EACCES;
+		goto out;
+	}
+
+	if (cd.clk->ops.clock_adjtime)
+		err = cd.clk->ops.clock_adjtime(cd.clk, tx);
+	else
+		err = -EOPNOTSUPP;
+out:
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_gettime(clockid_t id, struct timespec *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.clock_gettime)
+		err = cd.clk->ops.clock_gettime(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_getres(clockid_t id, struct timespec *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.clock_getres)
+		err = cd.clk->ops.clock_getres(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_settime(clockid_t id, const struct timespec *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if ((cd.fp->f_mode & FMODE_WRITE) == 0) {
+		err = -EACCES;
+		goto out;
+	}
+
+	if (cd.clk->ops.clock_settime)
+		err = cd.clk->ops.clock_settime(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+out:
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_timer_create(struct k_itimer *kit)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.timer_create)
+		err = cd.clk->ops.timer_create(cd.clk, kit);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_timer_delete(struct k_itimer *kit)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.timer_delete)
+		err = cd.clk->ops.timer_delete(cd.clk, kit);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static void pc_timer_gettime(struct k_itimer *kit, struct itimerspec *ts)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+
+	if (get_clock_desc(id, &cd))
+		return;
+
+	if (cd.clk->ops.timer_gettime)
+		cd.clk->ops.timer_gettime(cd.clk, kit, ts);
+
+	put_clock_desc(&cd);
+}
+
+static int pc_timer_settime(struct k_itimer *kit, int flags,
+			    struct itimerspec *ts, struct itimerspec *old)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.timer_settime)
+		err = cd.clk->ops.timer_settime(cd.clk, kit, flags, ts, old);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+struct k_clock clock_posix_dynamic = {
+	.clock_getres	= pc_clock_getres,
+	.clock_set	= pc_clock_settime,
+	.clock_get	= pc_clock_gettime,
+	.clock_adj	= pc_clock_adjtime,
+	.timer_create	= pc_timer_create,
+	.timer_set	= pc_timer_settime,
+	.timer_del	= pc_timer_delete,
+	.timer_get	= pc_timer_gettime,
+};

kernel/time/tick-broadcast.c

@@ -0,0 +1,857 @@
+/*
+ * linux/kernel/time/tick-broadcast.c
+ *
+ * This file contains functions which emulate a local clock-event
+ * device via a broadcast event source.
+ *
+ * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
+ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
+ *
+ * This code is licenced under the GPL version 2. For details see
+ * kernel-base/COPYING.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+
+#include "tick-internal.h"
+
+/*
+ * Broadcast support for broken x86 hardware, where the local apic
+ * timer stops in C3 state.
+ */
+
+static struct tick_device tick_broadcast_device;
+static cpumask_var_t tick_broadcast_mask;
+static cpumask_var_t tick_broadcast_on;
+static cpumask_var_t tmpmask;
+static DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
+static int tick_broadcast_force;
+
+#ifdef CONFIG_TICK_ONESHOT
+static void tick_broadcast_clear_oneshot(int cpu);
+#else
+static inline void tick_broadcast_clear_oneshot(int cpu) { }
+#endif
+
+/*
+ * Debugging: see timer_list.c
+ */
+struct tick_device *tick_get_broadcast_device(void)
+{
+	return &tick_broadcast_device;
+}
+
+struct cpumask *tick_get_broadcast_mask(void)
+{
+	return tick_broadcast_mask;
+}
+
+/*
+ * Start the device in periodic mode
+ */
+static void tick_broadcast_start_periodic(struct clock_event_device *bc)
+{
+	if (bc)
+		tick_setup_periodic(bc, 1);
+}
+
+/*
+ * Check, if the device can be utilized as broadcast device:
+ */
+int tick_check_broadcast_device(struct clock_event_device *dev)
+{
+	struct clock_event_device *cur = tick_broadcast_device.evtdev;
+
+	if ((dev->features & CLOCK_EVT_FEAT_DUMMY) ||
+	    (tick_broadcast_device.evtdev &&
+	     tick_broadcast_device.evtdev->rating >= dev->rating) ||
+	     (dev->features & CLOCK_EVT_FEAT_C3STOP))
+		return 0;
+
+	clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
+	if (cur)
+		cur->event_handler = clockevents_handle_noop;
+	tick_broadcast_device.evtdev = dev;
+	if (!cpumask_empty(tick_broadcast_mask))
+		tick_broadcast_start_periodic(dev);
+	/*
+	 * Inform all cpus about this. We might be in a situation
+	 * where we did not switch to oneshot mode because the per cpu
+	 * devices are affected by CLOCK_EVT_FEAT_C3STOP and the lack
+	 * of a oneshot capable broadcast device. Without that
+	 * notification the systems stays stuck in periodic mode
+	 * forever.
+	 */
+	if (dev->features & CLOCK_EVT_FEAT_ONESHOT)
+		tick_clock_notify();
+	return 1;
+}
+
+/*
+ * Check, if the device is the broadcast device
+ */
+int tick_is_broadcast_device(struct clock_event_device *dev)
+{
+	return (dev && tick_broadcast_device.evtdev == dev);
+}
+
+static void err_broadcast(const struct cpumask *mask)
+{
+	pr_crit_once("Failed to broadcast timer tick. Some CPUs may be unresponsive.\n");
+}
+
+static void tick_device_setup_broadcast_func(struct clock_event_device *dev)
+{
+	if (!dev->broadcast)
+		dev->broadcast = tick_broadcast;
+	if (!dev->broadcast) {
+		pr_warn_once("%s depends on broadcast, but no broadcast function available\n",
+			     dev->name);
+		dev->broadcast = err_broadcast;
+	}
+}
+
+/*
+ * Check, if the device is disfunctional and a place holder, which
+ * needs to be handled by the broadcast device.
+ */
+int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
+{
+	struct clock_event_device *bc = tick_broadcast_device.evtdev;
+	unsigned long flags;
+	int ret;
+
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+	/*
+	 * Devices might be registered with both periodic and oneshot
+	 * mode disabled. This signals, that the device needs to be
+	 * operated from the broadcast device and is a placeholder for
+	 * the cpu local device.
+	 */
+	if (!tick_device_is_functional(dev)) {
+		dev->event_handler = tick_handle_periodic;
+		tick_device_setup_broadcast_func(dev);
+		cpumask_set_cpu(cpu, tick_broadcast_mask);
+		tick_broadcast_start_periodic(bc);
+		ret = 1;
+	} else {
+		/*
+		 * Clear the broadcast bit for this cpu if the
+		 * device is not power state affected.
+		 */
+		if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
+			cpumask_clear_cpu(cpu, tick_broadcast_mask);
+		else
+			tick_device_setup_broadcast_func(dev);
+
+		/*
+		 * Clear the broadcast bit if the CPU is not in
+		 * periodic broadcast on state.
+		 */
+		if (!cpumask_test_cpu(cpu, tick_broadcast_on))
+			cpumask_clear_cpu(cpu, tick_broadcast_mask);
+
+		switch (tick_broadcast_device.mode) {
+		case TICKDEV_MODE_ONESHOT:
+			/*
+			 * If the system is in oneshot mode we can
+			 * unconditionally clear the oneshot mask bit,
+			 * because the CPU is running and therefore
+			 * not in an idle state which causes the power
+			 * state affected device to stop. Let the
+			 * caller initialize the device.
+			 */
+			tick_broadcast_clear_oneshot(cpu);
+			ret = 0;
+			break;
+
+		case TICKDEV_MODE_PERIODIC:
+			/*
+			 * If the system is in periodic mode, check
+			 * whether the broadcast device can be
+			 * switched off now.
+			 */
+			if (cpumask_empty(tick_broadcast_mask) && bc)
+				clockevents_shutdown(bc);
+			/*
+			 * If we kept the cpu in the broadcast mask,
+			 * tell the caller to leave the per cpu device
+			 * in shutdown state. The periodic interrupt
+			 * is delivered by the broadcast device.
+			 */
+			ret = cpumask_test_cpu(cpu, tick_broadcast_mask);
+			break;
+		default:
+			/* Nothing to do */
+			ret = 0;
+			break;
+		}
+	}
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+	return ret;
+}
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+int tick_receive_broadcast(void)
+{
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+	struct clock_event_device *evt = td->evtdev;
+
+	if (!evt)
+		return -ENODEV;
+
+	if (!evt->event_handler)
+		return -EINVAL;
+
+	evt->event_handler(evt);
+	return 0;
+}
+#endif
+
+/*
+ * Broadcast the event to the cpus, which are set in the mask (mangled).
+ */
+static void tick_do_broadcast(struct cpumask *mask)
+{
+	int cpu = smp_processor_id();
+	struct tick_device *td;
+
+	/*
+	 * Check, if the current cpu is in the mask
+	 */
+	if (cpumask_test_cpu(cpu, mask)) {
+		cpumask_clear_cpu(cpu, mask);
+		td = &per_cpu(tick_cpu_device, cpu);
+		td->evtdev->event_handler(td->evtdev);
+	}
+
+	if (!cpumask_empty(mask)) {
+		/*
+		 * It might be necessary to actually check whether the devices
+		 * have different broadcast functions. For now, just use the
+		 * one of the first device. This works as long as we have this
+		 * misfeature only on x86 (lapic)
+		 */
+		td = &per_cpu(tick_cpu_device, cpumask_first(mask));
+		td->evtdev->broadcast(mask);
+	}
+}
+
+/*
+ * Periodic broadcast:
+ * - invoke the broadcast handlers
+ */
+static void tick_do_periodic_broadcast(void)
+{
+	raw_spin_lock(&tick_broadcast_lock);
+
+	cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask);
+	tick_do_broadcast(tmpmask);
+
+	raw_spin_unlock(&tick_broadcast_lock);
+}
+
+/*
+ * Event handler for periodic broadcast ticks
+ */
+static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
+{
+	ktime_t next;
+
+	tick_do_periodic_broadcast();
+
+	/*
+	 * The device is in periodic mode. No reprogramming necessary:
+	 */
+	if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
+		return;
+
+	/*
+	 * Setup the next period for devices, which do not have
+	 * periodic mode. We read dev->next_event first and add to it
+	 * when the event already expired. clockevents_program_event()
+	 * sets dev->next_event only when the event is really
+	 * programmed to the device.
+	 */
+	for (next = dev->next_event; ;) {
+		next = ktime_add(next, tick_period);
+
+		if (!clockevents_program_event(dev, next, false))
+			return;
+		tick_do_periodic_broadcast();
+	}
+}
+
+/*
+ * Powerstate information: The system enters/leaves a state, where
+ * affected devices might stop
+ */
+static void tick_do_broadcast_on_off(unsigned long *reason)
+{
+	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);
+	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;
+
+	if (!tick_device_is_functional(dev))
+		goto out;
+
+	bc_stopped = cpumask_empty(tick_broadcast_mask);
+
+	switch (*reason) {
+	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
+	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
+		cpumask_set_cpu(cpu, tick_broadcast_on);
+		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) {
+			if (tick_broadcast_device.mode ==
+			    TICKDEV_MODE_PERIODIC)
+				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)
+			break;
+		cpumask_clear_cpu(cpu, tick_broadcast_on);
+		if (!tick_device_is_functional(dev))
+			break;
+		if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) {
+			if (tick_broadcast_device.mode ==
+			    TICKDEV_MODE_PERIODIC)
+				tick_setup_periodic(dev, 0);
+		}
+		break;
+	}
+
+	if (cpumask_empty(tick_broadcast_mask)) {
+		if (!bc_stopped)
+			clockevents_shutdown(bc);
+	} else if (bc_stopped) {
+		if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
+			tick_broadcast_start_periodic(bc);
+		else
+			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);
+}
+
+/*
+ * Set the periodic handler depending on broadcast on/off
+ */
+void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast)
+{
+	if (!broadcast)
+		dev->event_handler = tick_handle_periodic;
+	else
+		dev->event_handler = tick_handle_periodic_broadcast;
+}
+
+/*
+ * Remove a CPU from broadcasting
+ */
+void tick_shutdown_broadcast(unsigned int *cpup)
+{
+	struct clock_event_device *bc;
+	unsigned long flags;
+	unsigned int cpu = *cpup;
+
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+	bc = tick_broadcast_device.evtdev;
+	cpumask_clear_cpu(cpu, tick_broadcast_mask);
+	cpumask_clear_cpu(cpu, tick_broadcast_on);
+
+	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
+		if (bc && cpumask_empty(tick_broadcast_mask))
+			clockevents_shutdown(bc);
+	}
+
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+void tick_suspend_broadcast(void)
+{
+	struct clock_event_device *bc;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+	bc = tick_broadcast_device.evtdev;
+	if (bc)
+		clockevents_shutdown(bc);
+
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+int 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);
+
+		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);
+			break;
+		}
+	}
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+
+	return broadcast;
+}
+
+
+#ifdef CONFIG_TICK_ONESHOT
+
+static cpumask_var_t tick_broadcast_oneshot_mask;
+static cpumask_var_t tick_broadcast_pending_mask;
+static cpumask_var_t tick_broadcast_force_mask;
+
+/*
+ * Exposed for debugging: see timer_list.c
+ */
+struct cpumask *tick_get_broadcast_oneshot_mask(void)
+{
+	return tick_broadcast_oneshot_mask;
+}
+
+/*
+ * Called before going idle with interrupts disabled. Checks whether a
+ * broadcast event from the other core is about to happen. We detected
+ * that in tick_broadcast_oneshot_control(). The callsite can use this
+ * to avoid a deep idle transition as we are about to get the
+ * broadcast IPI right away.
+ */
+int tick_check_broadcast_expired(void)
+{
+	return cpumask_test_cpu(smp_processor_id(), tick_broadcast_force_mask);
+}
+
+/*
+ * Set broadcast interrupt affinity
+ */
+static void tick_broadcast_set_affinity(struct clock_event_device *bc,
+					const struct cpumask *cpumask)
+{
+	if (!(bc->features & CLOCK_EVT_FEAT_DYNIRQ))
+		return;
+
+	if (cpumask_equal(bc->cpumask, cpumask))
+		return;
+
+	bc->cpumask = cpumask;
+	irq_set_affinity(bc->irq, bc->cpumask);
+}
+
+static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
+				    ktime_t expires, int force)
+{
+	int ret;
+
+	if (bc->mode != CLOCK_EVT_MODE_ONESHOT)
+		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+
+	ret = clockevents_program_event(bc, expires, force);
+	if (!ret)
+		tick_broadcast_set_affinity(bc, cpumask_of(cpu));
+	return ret;
+}
+
+int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
+{
+	clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+	return 0;
+}
+
+/*
+ * Called from irq_enter() when idle was interrupted to reenable the
+ * per cpu device.
+ */
+void tick_check_oneshot_broadcast(int cpu)
+{
+	if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) {
+		struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
+
+		/*
+		 * We might be in the middle of switching over from
+		 * periodic to oneshot. If the CPU has not yet
+		 * switched over, leave the device alone.
+		 */
+		if (td->mode == TICKDEV_MODE_ONESHOT) {
+			clockevents_set_mode(td->evtdev,
+					     CLOCK_EVT_MODE_ONESHOT);
+		}
+	}
+}
+
+/*
+ * Handle oneshot mode broadcasting
+ */
+static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
+{
+	struct tick_device *td;
+	ktime_t now, next_event;
+	int cpu, next_cpu = 0;
+
+	raw_spin_lock(&tick_broadcast_lock);
+again:
+	dev->next_event.tv64 = KTIME_MAX;
+	next_event.tv64 = KTIME_MAX;
+	cpumask_clear(tmpmask);
+	now = ktime_get();
+	/* Find all expired events */
+	for_each_cpu(cpu, tick_broadcast_oneshot_mask) {
+		td = &per_cpu(tick_cpu_device, cpu);
+		if (td->evtdev->next_event.tv64 <= now.tv64) {
+			cpumask_set_cpu(cpu, tmpmask);
+			/*
+			 * Mark the remote cpu in the pending mask, so
+			 * it can avoid reprogramming the cpu local
+			 * timer in tick_broadcast_oneshot_control().
+			 */
+			cpumask_set_cpu(cpu, tick_broadcast_pending_mask);
+		} else if (td->evtdev->next_event.tv64 < next_event.tv64) {
+			next_event.tv64 = td->evtdev->next_event.tv64;
+			next_cpu = cpu;
+		}
+	}
+
+	/*
+	 * Remove the current cpu from the pending mask. The event is
+	 * delivered immediately in tick_do_broadcast() !
+	 */
+	cpumask_clear_cpu(smp_processor_id(), tick_broadcast_pending_mask);
+
+	/* Take care of enforced broadcast requests */
+	cpumask_or(tmpmask, tmpmask, tick_broadcast_force_mask);
+	cpumask_clear(tick_broadcast_force_mask);
+
+	/*
+	 * Wakeup the cpus which have an expired event.
+	 */
+	tick_do_broadcast(tmpmask);
+
+	/*
+	 * Two reasons for reprogram:
+	 *
+	 * - The global event did not expire any CPU local
+	 * events. This happens in dyntick mode, as the maximum PIT
+	 * delta is quite small.
+	 *
+	 * - There are pending events on sleeping CPUs which were not
+	 * in the event mask
+	 */
+	if (next_event.tv64 != KTIME_MAX) {
+		/*
+		 * Rearm the broadcast device. If event expired,
+		 * repeat the above
+		 */
+		if (tick_broadcast_set_event(dev, next_cpu, next_event, 0))
+			goto again;
+	}
+	raw_spin_unlock(&tick_broadcast_lock);
+}
+
+/*
+ * Powerstate information: The system enters/leaves a state, where
+ * affected devices might stop
+ */
+void tick_broadcast_oneshot_control(unsigned long reason)
+{
+	struct clock_event_device *bc, *dev;
+	struct tick_device *td;
+	unsigned long flags;
+	ktime_t now;
+	int cpu;
+
+	/*
+	 * Periodic mode does not care about the enter/exit of power
+	 * states
+	 */
+	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
+		return;
+
+	/*
+	 * 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);
+	dev = td->evtdev;
+
+	if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
+		return;
+
+	bc = tick_broadcast_device.evtdev;
+
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+	if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
+		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
+			WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
+			clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+			/*
+			 * We only reprogram the broadcast timer if we
+			 * did not mark ourself in the force mask and
+			 * if the cpu local event is earlier than the
+			 * broadcast event. If the current CPU is in
+			 * the force mask, then we are going to be
+			 * woken by the IPI right away.
+			 */
+			if (!cpumask_test_cpu(cpu, tick_broadcast_force_mask) &&
+			    dev->next_event.tv64 < bc->next_event.tv64)
+				tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
+		}
+	} else {
+		if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
+			clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+			/*
+			 * The cpu which was handling the broadcast
+			 * timer marked this cpu in the broadcast
+			 * pending mask and fired the broadcast
+			 * IPI. So we are going to handle the expired
+			 * event anyway via the broadcast IPI
+			 * handler. No need to reprogram the timer
+			 * with an already expired event.
+			 */
+			if (cpumask_test_and_clear_cpu(cpu,
+				       tick_broadcast_pending_mask))
+				goto out;
+
+			/*
+			 * Bail out if there is no next event.
+			 */
+			if (dev->next_event.tv64 == KTIME_MAX)
+				goto out;
+			/*
+			 * If the pending bit is not set, then we are
+			 * either the CPU handling the broadcast
+			 * interrupt or we got woken by something else.
+			 *
+			 * We are not longer in the broadcast mask, so
+			 * if the cpu local expiry time is already
+			 * reached, we would reprogram the cpu local
+			 * timer with an already expired event.
+			 *
+			 * This can lead to a ping-pong when we return
+			 * to idle and therefor rearm the broadcast
+			 * timer before the cpu local timer was able
+			 * to fire. This happens because the forced
+			 * reprogramming makes sure that the event
+			 * will happen in the future and depending on
+			 * the min_delta setting this might be far
+			 * enough out that the ping-pong starts.
+			 *
+			 * If the cpu local next_event has expired
+			 * then we know that the broadcast timer
+			 * next_event has expired as well and
+			 * broadcast is about to be handled. So we
+			 * avoid reprogramming and enforce that the
+			 * broadcast handler, which did not run yet,
+			 * will invoke the cpu local handler.
+			 *
+			 * We cannot call the handler directly from
+			 * here, because we might be in a NOHZ phase
+			 * and we did not go through the irq_enter()
+			 * nohz fixups.
+			 */
+			now = ktime_get();
+			if (dev->next_event.tv64 <= now.tv64) {
+				cpumask_set_cpu(cpu, tick_broadcast_force_mask);
+				goto out;
+			}
+			/*
+			 * We got woken by something else. Reprogram
+			 * the cpu local timer device.
+			 */
+			tick_program_event(dev->next_event, 1);
+		}
+	}
+out:
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+/*
+ * Reset the one shot broadcast for a cpu
+ *
+ * Called with tick_broadcast_lock held
+ */
+static void tick_broadcast_clear_oneshot(int cpu)
+{
+	cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+}
+
+static void tick_broadcast_init_next_event(struct cpumask *mask,
+					   ktime_t expires)
+{
+	struct tick_device *td;
+	int cpu;
+
+	for_each_cpu(cpu, mask) {
+		td = &per_cpu(tick_cpu_device, cpu);
+		if (td->evtdev)
+			td->evtdev->next_event = expires;
+	}
+}
+
+/**
+ * tick_broadcast_setup_oneshot - setup the broadcast device
+ */
+void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
+{
+	int cpu = smp_processor_id();
+
+	/* Set it up only once ! */
+	if (bc->event_handler != tick_handle_oneshot_broadcast) {
+		int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
+
+		bc->event_handler = tick_handle_oneshot_broadcast;
+
+		/*
+		 * We must be careful here. There might be other CPUs
+		 * waiting for periodic broadcast. We need to set the
+		 * oneshot_mask bits for those and program the
+		 * broadcast device to fire.
+		 */
+		cpumask_copy(tmpmask, tick_broadcast_mask);
+		cpumask_clear_cpu(cpu, tmpmask);
+		cpumask_or(tick_broadcast_oneshot_mask,
+			   tick_broadcast_oneshot_mask, tmpmask);
+
+		if (was_periodic && !cpumask_empty(tmpmask)) {
+			clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+			tick_broadcast_init_next_event(tmpmask,
+						       tick_next_period);
+			tick_broadcast_set_event(bc, cpu, tick_next_period, 1);
+		} else
+			bc->next_event.tv64 = KTIME_MAX;
+	} else {
+		/*
+		 * The first cpu which switches to oneshot mode sets
+		 * the bit for all other cpus which are in the general
+		 * (periodic) broadcast mask. So the bit is set and
+		 * would prevent the first broadcast enter after this
+		 * to program the bc device.
+		 */
+		tick_broadcast_clear_oneshot(cpu);
+	}
+}
+
+/*
+ * Select oneshot operating mode for the broadcast device
+ */
+void tick_broadcast_switch_to_oneshot(void)
+{
+	struct clock_event_device *bc;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+	tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT;
+	bc = tick_broadcast_device.evtdev;
+	if (bc)
+		tick_broadcast_setup_oneshot(bc);
+
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+
+/*
+ * Remove a dead CPU from broadcasting
+ */
+void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
+{
+	unsigned long flags;
+	unsigned int cpu = *cpup;
+
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+	/*
+	 * Clear the broadcast mask flag for the dead cpu, but do not
+	 * stop the broadcast device!
+	 */
+	cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+/*
+ * Check, whether the broadcast device is in one shot mode
+ */
+int tick_broadcast_oneshot_active(void)
+{
+	return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT;
+}
+
+/*
+ * Check whether the broadcast device supports oneshot.
+ */
+bool tick_broadcast_oneshot_available(void)
+{
+	struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+	return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false;
+}
+
+#endif
+
+void __init tick_broadcast_init(void)
+{
+	zalloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&tick_broadcast_on, GFP_NOWAIT);
+	zalloc_cpumask_var(&tmpmask, GFP_NOWAIT);
+#ifdef CONFIG_TICK_ONESHOT
+	zalloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&tick_broadcast_pending_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&tick_broadcast_force_mask, GFP_NOWAIT);
+#endif
+}

kernel/time/tick-common.c

@@ -0,0 +1,425 @@
+/*
+ * linux/kernel/time/tick-common.c
+ *
+ * This file contains the base functions to manage periodic tick
+ * related events.
+ *
+ * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
+ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
+ *
+ * This code is licenced under the GPL version 2. For details see
+ * kernel-base/COPYING.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+
+#include <asm/irq_regs.h>
+
+#include "tick-internal.h"
+
+/*
+ * Tick devices
+ */
+DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
+/*
+ * Tick next event: keeps track of the tick time
+ */
+ktime_t tick_next_period;
+ktime_t tick_period;
+int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
+static DEFINE_RAW_SPINLOCK(tick_device_lock);
+
+/*
+ * Debugging: see timer_list.c
+ */
+struct tick_device *tick_get_device(int cpu)
+{
+	return &per_cpu(tick_cpu_device, cpu);
+}
+
+/**
+ * tick_is_oneshot_available - check for a oneshot capable event device
+ */
+int tick_is_oneshot_available(void)
+{
+	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
+
+	if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+		return 0;
+	if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
+		return 1;
+	return tick_broadcast_oneshot_available();
+}
+
+/*
+ * Periodic tick
+ */
+static void tick_periodic(int cpu)
+{
+	if (tick_do_timer_cpu == cpu) {
+		write_seqlock(&jiffies_lock);
+
+		/* Keep track of the next tick event */
+		tick_next_period = ktime_add(tick_next_period, tick_period);
+
+		do_timer(1);
+		write_sequnlock(&jiffies_lock);
+	}
+
+	update_process_times(user_mode(get_irq_regs()));
+	profile_tick(CPU_PROFILING);
+}
+
+/*
+ * Event handler for periodic ticks
+ */
+void tick_handle_periodic(struct clock_event_device *dev)
+{
+	int cpu = smp_processor_id();
+	ktime_t next;
+
+	tick_periodic(cpu);
+
+	if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
+		return;
+	/*
+	 * Setup the next period for devices, which do not have
+	 * periodic mode:
+	 */
+	next = ktime_add(dev->next_event, tick_period);
+	for (;;) {
+		if (!clockevents_program_event(dev, next, false))
+			return;
+		/*
+		 * Have to be careful here. If we're in oneshot mode,
+		 * before we call tick_periodic() in a loop, we need
+		 * to be sure we're using a real hardware clocksource.
+		 * Otherwise we could get trapped in an infinite
+		 * loop, as the tick_periodic() increments jiffies,
+		 * when then will increment time, posibly causing
+		 * the loop to trigger again and again.
+		 */
+		if (timekeeping_valid_for_hres())
+			tick_periodic(cpu);
+		next = ktime_add(next, tick_period);
+	}
+}
+
+/*
+ * Setup the device for a periodic tick
+ */
+void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
+{
+	tick_set_periodic_handler(dev, broadcast);
+
+	/* Broadcast setup ? */
+	if (!tick_device_is_functional(dev))
+		return;
+
+	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
+	    !tick_broadcast_oneshot_active()) {
+		clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC);
+	} else {
+		unsigned long seq;
+		ktime_t next;
+
+		do {
+			seq = read_seqbegin(&jiffies_lock);
+			next = tick_next_period;
+		} while (read_seqretry(&jiffies_lock, seq));
+
+		clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+
+		for (;;) {
+			if (!clockevents_program_event(dev, next, false))
+				return;
+			next = ktime_add(next, tick_period);
+		}
+	}
+}
+
+/*
+ * Setup the tick device
+ */
+static void tick_setup_device(struct tick_device *td,
+			      struct clock_event_device *newdev, int cpu,
+			      const struct cpumask *cpumask)
+{
+	ktime_t next_event;
+	void (*handler)(struct clock_event_device *) = NULL;
+
+	/*
+	 * First device setup ?
+	 */
+	if (!td->evtdev) {
+		/*
+		 * If no cpu took the do_timer update, assign it to
+		 * this cpu:
+		 */
+		if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
+			if (!tick_nohz_full_cpu(cpu))
+				tick_do_timer_cpu = cpu;
+			else
+				tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+			tick_next_period = ktime_get();
+			tick_period = ktime_set(0, NSEC_PER_SEC / HZ);
+		}
+
+		/*
+		 * Startup in periodic mode first.
+		 */
+		td->mode = TICKDEV_MODE_PERIODIC;
+	} else {
+		handler = td->evtdev->event_handler;
+		next_event = td->evtdev->next_event;
+		td->evtdev->event_handler = clockevents_handle_noop;
+	}
+
+	td->evtdev = newdev;
+
+	/*
+	 * When the device is not per cpu, pin the interrupt to the
+	 * current cpu:
+	 */
+	if (!cpumask_equal(newdev->cpumask, cpumask))
+		irq_set_affinity(newdev->irq, cpumask);
+
+	/*
+	 * When global broadcasting is active, check if the current
+	 * device is registered as a placeholder for broadcast mode.
+	 * This allows us to handle this x86 misfeature in a generic
+	 * way. This function also returns !=0 when we keep the
+	 * current active broadcast state for this CPU.
+	 */
+	if (tick_device_uses_broadcast(newdev, cpu))
+		return;
+
+	if (td->mode == TICKDEV_MODE_PERIODIC)
+		tick_setup_periodic(newdev, 0);
+	else
+		tick_setup_oneshot(newdev, handler, next_event);
+}
+
+/*
+ * Check, if the new registered device should be used.
+ */
+static int tick_check_new_device(struct clock_event_device *newdev)
+{
+	struct clock_event_device *curdev;
+	struct tick_device *td;
+	int cpu, ret = NOTIFY_OK;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&tick_device_lock, flags);
+
+	cpu = smp_processor_id();
+	if (!cpumask_test_cpu(cpu, newdev->cpumask))
+		goto out_bc;
+
+	td = &per_cpu(tick_cpu_device, cpu);
+	curdev = td->evtdev;
+
+	/* cpu local device ? */
+	if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) {
+
+		/*
+		 * If the cpu affinity of the device interrupt can not
+		 * be set, ignore it.
+		 */
+		if (!irq_can_set_affinity(newdev->irq))
+			goto out_bc;
+
+		/*
+		 * If we have a cpu local device already, do not replace it
+		 * by a non cpu local device
+		 */
+		if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
+			goto out_bc;
+	}
+
+	/*
+	 * If we have an active device, then check the rating and the oneshot
+	 * feature.
+	 */
+	if (curdev) {
+		/*
+		 * Prefer one shot capable devices !
+		 */
+		if ((curdev->features & CLOCK_EVT_FEAT_ONESHOT) &&
+		    !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
+			goto out_bc;
+		/*
+		 * Check the rating
+		 */
+		if (curdev->rating >= newdev->rating)
+			goto out_bc;
+	}
+
+	/*
+	 * Replace the eventually existing device by the new
+	 * device. If the current device is the broadcast device, do
+	 * not give it back to the clockevents layer !
+	 */
+	if (tick_is_broadcast_device(curdev)) {
+		clockevents_shutdown(curdev);
+		curdev = NULL;
+	}
+	clockevents_exchange_device(curdev, newdev);
+	tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
+	if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
+		tick_oneshot_notify();
+
+	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
+	return NOTIFY_STOP;
+
+out_bc:
+	/*
+	 * Can the new device be used as a broadcast device ?
+	 */
+	if (tick_check_broadcast_device(newdev))
+		ret = NOTIFY_STOP;
+
+	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
+
+	return ret;
+}
+
+/*
+ * Transfer the do_timer job away from a dying cpu.
+ *
+ * Called with interrupts disabled.
+ */
+static void tick_handover_do_timer(int *cpup)
+{
+	if (*cpup == tick_do_timer_cpu) {
+		int cpu = cpumask_first(cpu_online_mask);
+
+		tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
+			TICK_DO_TIMER_NONE;
+	}
+}
+
+/*
+ * Shutdown an event device on a given cpu:
+ *
+ * This is called on a life CPU, when a CPU is dead. So we cannot
+ * access the hardware device itself.
+ * We just set the mode and remove it from the lists.
+ */
+static void tick_shutdown(unsigned int *cpup)
+{
+	struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
+	struct clock_event_device *dev = td->evtdev;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&tick_device_lock, flags);
+	td->mode = TICKDEV_MODE_PERIODIC;
+	if (dev) {
+		/*
+		 * Prevent that the clock events layer tries to call
+		 * the set mode function!
+		 */
+		dev->mode = CLOCK_EVT_MODE_UNUSED;
+		clockevents_exchange_device(dev, NULL);
+		dev->event_handler = clockevents_handle_noop;
+		td->evtdev = NULL;
+	}
+	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
+}
+
+static void tick_suspend(void)
+{
+	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&tick_device_lock, flags);
+	clockevents_shutdown(td->evtdev);
+	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
+}
+
+static void tick_resume(void)
+{
+	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	unsigned long flags;
+	int broadcast = tick_resume_broadcast();
+
+	raw_spin_lock_irqsave(&tick_device_lock, flags);
+	clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME);
+
+	if (!broadcast) {
+		if (td->mode == TICKDEV_MODE_PERIODIC)
+			tick_setup_periodic(td->evtdev, 0);
+		else
+			tick_resume_oneshot();
+	}
+	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
+}
+
+/*
+ * Notification about clock event devices
+ */
+static int tick_notify(struct notifier_block *nb, unsigned long reason,
+			       void *dev)
+{
+	switch (reason) {
+
+	case CLOCK_EVT_NOTIFY_ADD:
+		return tick_check_new_device(dev);
+
+	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
+	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
+	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
+		tick_broadcast_on_off(reason, dev);
+		break;
+
+	case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
+	case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
+		tick_broadcast_oneshot_control(reason);
+		break;
+
+	case CLOCK_EVT_NOTIFY_CPU_DYING:
+		tick_handover_do_timer(dev);
+		break;
+
+	case CLOCK_EVT_NOTIFY_CPU_DEAD:
+		tick_shutdown_broadcast_oneshot(dev);
+		tick_shutdown_broadcast(dev);
+		tick_shutdown(dev);
+		break;
+
+	case CLOCK_EVT_NOTIFY_SUSPEND:
+		tick_suspend();
+		tick_suspend_broadcast();
+		break;
+
+	case CLOCK_EVT_NOTIFY_RESUME:
+		tick_resume();
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block tick_notifier = {
+	.notifier_call = tick_notify,
+};
+
+/**
+ * tick_init - initialize the tick control
+ *
+ * Register the notifier with the clockevents framework
+ */
+void __init tick_init(void)
+{
+	clockevents_register_notifier(&tick_notifier);
+	tick_broadcast_init();
+}

kernel/time/tick-internal.h

@@ -0,0 +1,146 @@
+/*
+ * tick internal variable and functions used by low/high res code
+ */
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+
+extern seqlock_t jiffies_lock;
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD
+
+#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;
+extern ktime_t tick_period;
+extern int tick_do_timer_cpu __read_mostly;
+
+extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast);
+extern void tick_handle_periodic(struct clock_event_device *dev);
+
+extern void clockevents_shutdown(struct clock_event_device *dev);
+
+/*
+ * NO_HZ / high resolution timer shared code
+ */
+#ifdef CONFIG_TICK_ONESHOT
+extern void tick_setup_oneshot(struct clock_event_device *newdev,
+			       void (*handler)(struct clock_event_device *),
+			       ktime_t nextevt);
+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
+extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
+extern void tick_broadcast_oneshot_control(unsigned long reason);
+extern void tick_broadcast_switch_to_oneshot(void);
+extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
+extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
+extern int tick_broadcast_oneshot_active(void);
+extern void tick_check_oneshot_broadcast(int cpu);
+bool tick_broadcast_oneshot_available(void);
+# else /* BROADCAST */
+static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
+{
+	BUG();
+}
+static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline void tick_broadcast_switch_to_oneshot(void) { }
+static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
+static inline int tick_broadcast_oneshot_active(void) { return 0; }
+static inline void tick_check_oneshot_broadcast(int cpu) { }
+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 void tick_broadcast_oneshot_control(unsigned long reason) { }
+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 */
+
+/*
+ * Broadcasting support
+ */
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
+extern int tick_check_broadcast_device(struct clock_event_device *dev);
+extern 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);
+
+#else /* !BROADCAST */
+
+static inline int tick_check_broadcast_device(struct clock_event_device *dev)
+{
+	return 0;
+}
+
+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) { }
+
+/*
+ * 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);
+}
+
+#endif
+
+extern void do_timer(unsigned long ticks);

kernel/time/tick-oneshot.c

@@ -0,0 +1,116 @@
+/*
+ * linux/kernel/time/tick-oneshot.c
+ *
+ * This file contains functions which manage high resolution tick
+ * related events.
+ *
+ * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
+ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
+ *
+ * This code is licenced under the GPL version 2. For details see
+ * kernel-base/COPYING.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+
+#include "tick-internal.h"
+
+/**
+ * tick_program_event
+ */
+int tick_program_event(ktime_t expires, int force)
+{
+	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
+
+	return clockevents_program_event(dev, expires, force);
+}
+
+/**
+ * tick_resume_onshot - resume oneshot mode
+ */
+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_program_event(dev, ktime_get(), true);
+}
+
+/**
+ * tick_setup_oneshot - setup the event device for oneshot mode (hres or nohz)
+ */
+void tick_setup_oneshot(struct clock_event_device *newdev,
+			void (*handler)(struct clock_event_device *),
+			ktime_t next_event)
+{
+	newdev->event_handler = handler;
+	clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT);
+	clockevents_program_event(newdev, next_event, true);
+}
+
+/**
+ * tick_switch_to_oneshot - switch to oneshot mode
+ */
+int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
+{
+	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	struct clock_event_device *dev = td->evtdev;
+
+	if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) ||
+		    !tick_device_is_functional(dev)) {
+
+		printk(KERN_INFO "Clockevents: "
+		       "could not switch to one-shot mode:");
+		if (!dev) {
+			printk(" no tick device\n");
+		} else {
+			if (!tick_device_is_functional(dev))
+				printk(" %s is not functional.\n", dev->name);
+			else
+				printk(" %s does not support one-shot mode.\n",
+				       dev->name);
+		}
+		return -EINVAL;
+	}
+
+	td->mode = TICKDEV_MODE_ONESHOT;
+	dev->event_handler = handler;
+	clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+	tick_broadcast_switch_to_oneshot();
+	return 0;
+}
+
+/**
+ * tick_check_oneshot_mode - check whether the system is in oneshot mode
+ *
+ * returns 1 when either nohz or highres are enabled. otherwise 0.
+ */
+int tick_oneshot_mode_active(void)
+{
+	unsigned long flags;
+	int ret;
+
+	local_irq_save(flags);
+	ret = __this_cpu_read(tick_cpu_device.mode) == TICKDEV_MODE_ONESHOT;
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+/**
+ * tick_init_highres - switch to high resolution mode
+ *
+ * Called with interrupts disabled.
+ */
+int tick_init_highres(void)
+{
+	return tick_switch_to_oneshot(hrtimer_interrupt);
+}
+#endif

kernel/time/timeconv.c

@@ -0,0 +1,127 @@
+/*
+ * Copyright (C) 1993, 1994, 1995, 1996, 1997 Free Software Foundation, Inc.
+ * This file is part of the GNU C Library.
+ * Contributed by Paul Eggert (eggert@twinsun.com).
+ *
+ * The GNU C Library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Library General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * The GNU C Library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Library General Public License for more details.
+ *
+ * You should have received a copy of the GNU Library General Public
+ * License along with the GNU C Library; see the file COPYING.LIB.  If not,
+ * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ */
+
+/*
+ * Converts the calendar time to broken-down time representation
+ * Based on code from glibc-2.6
+ *
+ * 2009-7-14:
+ *   Moved from glibc-2.6 to kernel by Zhaolei<zhaolei@cn.fujitsu.com>
+ */
+
+#include <linux/time.h>
+#include <linux/module.h>
+
+/*
+ * Nonzero if YEAR is a leap year (every 4 years,
+ * except every 100th isn't, and every 400th is).
+ */
+static int __isleap(long year)
+{
+	return (year) % 4 == 0 && ((year) % 100 != 0 || (year) % 400 == 0);
+}
+
+/* do a mathdiv for long type */
+static long math_div(long a, long b)
+{
+	return a / b - (a % b < 0);
+}
+
+/* How many leap years between y1 and y2, y1 must less or equal to y2 */
+static long leaps_between(long y1, long y2)
+{
+	long leaps1 = math_div(y1 - 1, 4) - math_div(y1 - 1, 100)
+		+ math_div(y1 - 1, 400);
+	long leaps2 = math_div(y2 - 1, 4) - math_div(y2 - 1, 100)
+		+ math_div(y2 - 1, 400);
+	return leaps2 - leaps1;
+}
+
+/* How many days come before each month (0-12). */
+static const unsigned short __mon_yday[2][13] = {
+	/* Normal years. */
+	{0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365},
+	/* Leap years. */
+	{0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366}
+};
+
+#define SECS_PER_HOUR	(60 * 60)
+#define SECS_PER_DAY	(SECS_PER_HOUR * 24)
+
+/**
+ * time_to_tm - converts the calendar time to local broken-down time
+ *
+ * @totalsecs	the number of seconds elapsed since 00:00:00 on January 1, 1970,
+ *		Coordinated Universal Time (UTC).
+ * @offset	offset seconds adding to totalsecs.
+ * @result	pointer to struct tm variable to receive broken-down time
+ */
+void time_to_tm(time_t totalsecs, int offset, struct tm *result)
+{
+	long days, rem, y;
+	const unsigned short *ip;
+
+	days = totalsecs / SECS_PER_DAY;
+	rem = totalsecs % SECS_PER_DAY;
+	rem += offset;
+	while (rem < 0) {
+		rem += SECS_PER_DAY;
+		--days;
+	}
+	while (rem >= SECS_PER_DAY) {
+		rem -= SECS_PER_DAY;
+		++days;
+	}
+
+	result->tm_hour = rem / SECS_PER_HOUR;
+	rem %= SECS_PER_HOUR;
+	result->tm_min = rem / 60;
+	result->tm_sec = rem % 60;
+
+	/* January 1, 1970 was a Thursday. */
+	result->tm_wday = (4 + days) % 7;
+	if (result->tm_wday < 0)
+		result->tm_wday += 7;
+
+	y = 1970;
+
+	while (days < 0 || days >= (__isleap(y) ? 366 : 365)) {
+		/* Guess a corrected year, assuming 365 days per year. */
+		long yg = y + math_div(days, 365);
+
+		/* Adjust DAYS and Y to match the guessed year. */
+		days -= (yg - y) * 365 + leaps_between(y, yg);
+		y = yg;
+	}
+
+	result->tm_year = y - 1900;
+
+	result->tm_yday = days;
+
+	ip = __mon_yday[__isleap(y)];
+	for (y = 11; days < ip[y]; y--)
+		continue;
+	days -= ip[y];
+
+	result->tm_mon = y;
+	result->tm_mday = days + 1;
+}
+EXPORT_SYMBOL(time_to_tm);

kernel/time/timekeeping_internal.h

@@ -0,0 +1,23 @@
+#ifndef _TIMEKEEPING_INTERNAL_H
+#define _TIMEKEEPING_INTERNAL_H
+/*
+ * timekeeping debug functions
+ */
+#include <linux/clocksource.h>
+#include <linux/time.h>
+
+#ifdef CONFIG_CLOCKSOURCE_VALIDATE_LAST_CYCLE
+static inline cycle_t clocksource_delta(cycle_t now, cycle_t last, cycle_t mask)
+{
+	cycle_t ret = (now - last) & mask;
+
+	return (s64) ret > 0 ? ret : 0;
+}
+#else
+static inline cycle_t clocksource_delta(cycle_t now, cycle_t last, cycle_t mask)
+{
+	return (now - last) & mask;
+}
+#endif
+
+#endif /* _TIMEKEEPING_INTERNAL_H */

kernel/time/timer_list.c

@@ -0,0 +1,370 @@
+/*
+ * kernel/time/timer_list.c
+ *
+ * List pending timers
+ *
+ * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/proc_fs.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/kallsyms.h>
+#include <linux/tick.h>
+
+#include <asm/uaccess.h>
+
+
+struct timer_list_iter {
+	int cpu;
+	bool second_pass;
+	u64 now;
+};
+
+typedef void (*print_fn_t)(struct seq_file *m, unsigned int *classes);
+
+DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
+
+/*
+ * This allows printing both to /proc/timer_list and
+ * to the console (on SysRq-Q):
+ */
+#define SEQ_printf(m, x...)			\
+ do {						\
+	if (m)					\
+		seq_printf(m, x);		\
+	else					\
+		printk(x);			\
+ } while (0)
+
+static void print_name_offset(struct seq_file *m, void *sym)
+{
+	char symname[KSYM_NAME_LEN];
+
+	if (lookup_symbol_name((unsigned long)sym, symname) < 0)
+		SEQ_printf(m, "<%pK>", sym);
+	else
+		SEQ_printf(m, "%s", symname);
+}
+
+static void
+print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer,
+	    int idx, u64 now)
+{
+#ifdef CONFIG_TIMER_STATS
+	char tmp[TASK_COMM_LEN + 1];
+#endif
+	SEQ_printf(m, " #%d: ", idx);
+	print_name_offset(m, taddr);
+	SEQ_printf(m, ", ");
+	print_name_offset(m, timer->function);
+	SEQ_printf(m, ", S:%02lx", timer->state);
+#ifdef CONFIG_TIMER_STATS
+	SEQ_printf(m, ", ");
+	print_name_offset(m, timer->start_site);
+	memcpy(tmp, timer->start_comm, TASK_COMM_LEN);
+	tmp[TASK_COMM_LEN] = 0;
+	SEQ_printf(m, ", %s/%d", tmp, timer->start_pid);
+#endif
+	SEQ_printf(m, "\n");
+	SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n",
+		(unsigned long long)ktime_to_ns(hrtimer_get_softexpires(timer)),
+		(unsigned long long)ktime_to_ns(hrtimer_get_expires(timer)),
+		(long long)(ktime_to_ns(hrtimer_get_softexpires(timer)) - now),
+		(long long)(ktime_to_ns(hrtimer_get_expires(timer)) - now));
+}
+
+static void
+print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base,
+		    u64 now)
+{
+	struct hrtimer *timer, tmp;
+	unsigned long next = 0, i;
+	struct timerqueue_node *curr;
+	unsigned long flags;
+
+next_one:
+	i = 0;
+	raw_spin_lock_irqsave(&base->cpu_base->lock, flags);
+
+	curr = timerqueue_getnext(&base->active);
+	/*
+	 * Crude but we have to do this O(N*N) thing, because
+	 * we have to unlock the base when printing:
+	 */
+	while (curr && i < next) {
+		curr = timerqueue_iterate_next(curr);
+		i++;
+	}
+
+	if (curr) {
+
+		timer = container_of(curr, struct hrtimer, node);
+		tmp = *timer;
+		raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags);
+
+		print_timer(m, timer, &tmp, i, now);
+		next++;
+		goto next_one;
+	}
+	raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags);
+}
+
+static void
+print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
+{
+	SEQ_printf(m, "  .base:       %pK\n", base);
+	SEQ_printf(m, "  .index:      %d\n",
+			base->index);
+	SEQ_printf(m, "  .resolution: %Lu nsecs\n",
+			(unsigned long long)ktime_to_ns(base->resolution));
+	SEQ_printf(m,   "  .get_time:   ");
+	print_name_offset(m, base->get_time);
+	SEQ_printf(m,   "\n");
+#ifdef CONFIG_HIGH_RES_TIMERS
+	SEQ_printf(m, "  .offset:     %Lu nsecs\n",
+		   (unsigned long long) ktime_to_ns(base->offset));
+#endif
+	SEQ_printf(m,   "active timers:\n");
+	print_active_timers(m, base, now);
+}
+
+static void print_cpu(struct seq_file *m, int cpu, u64 now)
+{
+	struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
+	int i;
+
+	SEQ_printf(m, "cpu: %d\n", cpu);
+	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
+		SEQ_printf(m, " clock %d:\n", i);
+		print_base(m, cpu_base->clock_base + i, now);
+	}
+#define P(x) \
+	SEQ_printf(m, "  .%-15s: %Lu\n", #x, \
+		   (unsigned long long)(cpu_base->x))
+#define P_ns(x) \
+	SEQ_printf(m, "  .%-15s: %Lu nsecs\n", #x, \
+		   (unsigned long long)(ktime_to_ns(cpu_base->x)))
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+	P_ns(expires_next);
+	P(hres_active);
+	P(nr_events);
+	P(nr_retries);
+	P(nr_hangs);
+	P_ns(max_hang_time);
+#endif
+#undef P
+#undef P_ns
+
+#ifdef CONFIG_TICK_ONESHOT
+# define P(x) \
+	SEQ_printf(m, "  .%-15s: %Lu\n", #x, \
+		   (unsigned long long)(ts->x))
+# define P_ns(x) \
+	SEQ_printf(m, "  .%-15s: %Lu nsecs\n", #x, \
+		   (unsigned long long)(ktime_to_ns(ts->x)))
+	{
+		struct tick_sched *ts = tick_get_tick_sched(cpu);
+		P(nohz_mode);
+		P_ns(last_tick);
+		P(tick_stopped);
+		P(idle_jiffies);
+		P(idle_calls);
+		P(idle_sleeps);
+		P_ns(idle_entrytime);
+		P_ns(idle_waketime);
+		P_ns(idle_exittime);
+		P_ns(idle_sleeptime);
+		P_ns(iowait_sleeptime);
+		P(last_jiffies);
+		P(next_jiffies);
+		P_ns(idle_expires);
+		SEQ_printf(m, "jiffies: %Lu\n",
+			   (unsigned long long)jiffies);
+	}
+#endif
+
+#undef P
+#undef P_ns
+	SEQ_printf(m, "\n");
+}
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+static void
+print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
+{
+	struct clock_event_device *dev = td->evtdev;
+
+	SEQ_printf(m, "Tick Device: mode:     %d\n", td->mode);
+	if (cpu < 0)
+		SEQ_printf(m, "Broadcast device\n");
+	else
+		SEQ_printf(m, "Per CPU device: %d\n", cpu);
+
+	SEQ_printf(m, "Clock Event Device: ");
+	if (!dev) {
+		SEQ_printf(m, "<NULL>\n");
+		return;
+	}
+	SEQ_printf(m, "%s\n", dev->name);
+	SEQ_printf(m, " max_delta_ns:   %llu\n",
+		   (unsigned long long) dev->max_delta_ns);
+	SEQ_printf(m, " min_delta_ns:   %llu\n",
+		   (unsigned long long) dev->min_delta_ns);
+	SEQ_printf(m, " mult:           %u\n", dev->mult);
+	SEQ_printf(m, " shift:          %u\n", dev->shift);
+	SEQ_printf(m, " mode:           %d\n", dev->mode);
+	SEQ_printf(m, " next_event:     %Ld nsecs\n",
+		   (unsigned long long) ktime_to_ns(dev->next_event));
+
+	SEQ_printf(m, " set_next_event: ");
+	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");
+
+	SEQ_printf(m, " event_handler:  ");
+	print_name_offset(m, dev->event_handler);
+	SEQ_printf(m, "\n");
+	SEQ_printf(m, " retries:        %lu\n", dev->retries);
+	SEQ_printf(m, "\n");
+}
+
+static void timer_list_show_tickdevices_header(struct seq_file *m)
+{
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+	print_tickdevice(m, tick_get_broadcast_device(), -1);
+	SEQ_printf(m, "tick_broadcast_mask: %08lx\n",
+		   cpumask_bits(tick_get_broadcast_mask())[0]);
+#ifdef CONFIG_TICK_ONESHOT
+	SEQ_printf(m, "tick_broadcast_oneshot_mask: %08lx\n",
+		   cpumask_bits(tick_get_broadcast_oneshot_mask())[0]);
+#endif
+	SEQ_printf(m, "\n");
+#endif
+}
+#endif
+
+static inline void timer_list_header(struct seq_file *m, u64 now)
+{
+	SEQ_printf(m, "Timer List Version: v0.7\n");
+	SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
+	SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
+	SEQ_printf(m, "\n");
+}
+
+static int timer_list_show(struct seq_file *m, void *v)
+{
+	struct timer_list_iter *iter = v;
+
+	if (iter->cpu == -1 && !iter->second_pass)
+		timer_list_header(m, iter->now);
+	else if (!iter->second_pass)
+		print_cpu(m, iter->cpu, iter->now);
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+	else if (iter->cpu == -1 && iter->second_pass)
+		timer_list_show_tickdevices_header(m);
+	else
+		print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu);
+#endif
+	return 0;
+}
+
+void sysrq_timer_list_show(void)
+{
+	u64 now = ktime_to_ns(ktime_get());
+	int cpu;
+
+	timer_list_header(NULL, now);
+
+	for_each_online_cpu(cpu)
+		print_cpu(NULL, cpu, now);
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+	timer_list_show_tickdevices_header(NULL);
+	for_each_online_cpu(cpu)
+		print_tickdevice(NULL, tick_get_device(cpu), cpu);
+#endif
+	return;
+}
+
+static void *move_iter(struct timer_list_iter *iter, loff_t offset)
+{
+	for (; offset; offset--) {
+		iter->cpu = cpumask_next(iter->cpu, cpu_online_mask);
+		if (iter->cpu >= nr_cpu_ids) {
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+			if (!iter->second_pass) {
+				iter->cpu = -1;
+				iter->second_pass = true;
+			} else
+				return NULL;
+#else
+			return NULL;
+#endif
+		}
+	}
+	return iter;
+}
+
+static void *timer_list_start(struct seq_file *file, loff_t *offset)
+{
+	struct timer_list_iter *iter = file->private;
+
+	if (!*offset)
+		iter->now = ktime_to_ns(ktime_get());
+	iter->cpu = -1;
+	iter->second_pass = false;
+	return move_iter(iter, *offset);
+}
+
+static void *timer_list_next(struct seq_file *file, void *v, loff_t *offset)
+{
+	struct timer_list_iter *iter = file->private;
+	++*offset;
+	return move_iter(iter, 1);
+}
+
+static void timer_list_stop(struct seq_file *seq, void *v)
+{
+}
+
+static const struct seq_operations timer_list_sops = {
+	.start = timer_list_start,
+	.next = timer_list_next,
+	.stop = timer_list_stop,
+	.show = timer_list_show,
+};
+
+static int timer_list_open(struct inode *inode, struct file *filp)
+{
+	return seq_open_private(filp, &timer_list_sops,
+			sizeof(struct timer_list_iter));
+}
+
+static const struct file_operations timer_list_fops = {
+	.open		= timer_list_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+static int __init init_timer_list_procfs(void)
+{
+	struct proc_dir_entry *pe;
+
+	pe = proc_create("timer_list", 0444, NULL, &timer_list_fops);
+	if (!pe)
+		return -ENOMEM;
+	return 0;
+}
+__initcall(init_timer_list_procfs);

kernel/time/timer_stats.c

@@ -0,0 +1,425 @@
+/*
+ * kernel/time/timer_stats.c
+ *
+ * Collect timer usage statistics.
+ *
+ * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * timer_stats is based on timer_top, a similar functionality which was part of
+ * Con Kolivas dyntick patch set. It was developed by Daniel Petrini at the
+ * Instituto Nokia de Tecnologia - INdT - Manaus. timer_top's design was based
+ * on dynamic allocation of the statistics entries and linear search based
+ * lookup combined with a global lock, rather than the static array, hash
+ * and per-CPU locking which is used by timer_stats. It was written for the
+ * pre hrtimer kernel code and therefore did not take hrtimers into account.
+ * Nevertheless it provided the base for the timer_stats implementation and
+ * was a helpful source of inspiration. Kudos to Daniel and the Nokia folks
+ * for this effort.
+ *
+ * timer_top.c is
+ *	Copyright (C) 2005 Instituto Nokia de Tecnologia - INdT - Manaus
+ *	Written by Daniel Petrini <d.pensator@gmail.com>
+ *	timer_top.c was released under the GNU General Public License version 2
+ *
+ * We export the addresses and counting of timer functions being called,
+ * the pid and cmdline from the owner process if applicable.
+ *
+ * Start/stop data collection:
+ * # echo [1|0] >/proc/timer_stats
+ *
+ * Display the information collected so far:
+ * # cat /proc/timer_stats
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/proc_fs.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/kallsyms.h>
+
+#include <asm/uaccess.h>
+
+/*
+ * This is our basic unit of interest: a timer expiry event identified
+ * by the timer, its start/expire functions and the PID of the task that
+ * started the timer. We count the number of times an event happens:
+ */
+struct entry {
+	/*
+	 * Hash list:
+	 */
+	struct entry		*next;
+
+	/*
+	 * Hash keys:
+	 */
+	void			*timer;
+	void			*start_func;
+	void			*expire_func;
+	pid_t			pid;
+
+	/*
+	 * Number of timeout events:
+	 */
+	unsigned long		count;
+	unsigned int		timer_flag;
+
+	/*
+	 * We save the command-line string to preserve
+	 * this information past task exit:
+	 */
+	char			comm[TASK_COMM_LEN + 1];
+
+} ____cacheline_aligned_in_smp;
+
+/*
+ * Spinlock protecting the tables - not taken during lookup:
+ */
+static DEFINE_RAW_SPINLOCK(table_lock);
+
+/*
+ * Per-CPU lookup locks for fast hash lookup:
+ */
+static DEFINE_PER_CPU(raw_spinlock_t, tstats_lookup_lock);
+
+/*
+ * Mutex to serialize state changes with show-stats activities:
+ */
+static DEFINE_MUTEX(show_mutex);
+
+/*
+ * Collection status, active/inactive:
+ */
+int __read_mostly timer_stats_active;
+
+/*
+ * Beginning/end timestamps of measurement:
+ */
+static ktime_t time_start, time_stop;
+
+/*
+ * tstat entry structs only get allocated while collection is
+ * active and never freed during that time - this simplifies
+ * things quite a bit.
+ *
+ * They get freed when a new collection period is started.
+ */
+#define MAX_ENTRIES_BITS	10
+#define MAX_ENTRIES		(1UL << MAX_ENTRIES_BITS)
+
+static unsigned long nr_entries;
+static struct entry entries[MAX_ENTRIES];
+
+static atomic_t overflow_count;
+
+/*
+ * The entries are in a hash-table, for fast lookup:
+ */
+#define TSTAT_HASH_BITS		(MAX_ENTRIES_BITS - 1)
+#define TSTAT_HASH_SIZE		(1UL << TSTAT_HASH_BITS)
+#define TSTAT_HASH_MASK		(TSTAT_HASH_SIZE - 1)
+
+#define __tstat_hashfn(entry)						\
+	(((unsigned long)(entry)->timer       ^				\
+	  (unsigned long)(entry)->start_func  ^				\
+	  (unsigned long)(entry)->expire_func ^				\
+	  (unsigned long)(entry)->pid		) & TSTAT_HASH_MASK)
+
+#define tstat_hashentry(entry)	(tstat_hash_table + __tstat_hashfn(entry))
+
+static struct entry *tstat_hash_table[TSTAT_HASH_SIZE] __read_mostly;
+
+static void reset_entries(void)
+{
+	nr_entries = 0;
+	memset(entries, 0, sizeof(entries));
+	memset(tstat_hash_table, 0, sizeof(tstat_hash_table));
+	atomic_set(&overflow_count, 0);
+}
+
+static struct entry *alloc_entry(void)
+{
+	if (nr_entries >= MAX_ENTRIES)
+		return NULL;
+
+	return entries + nr_entries++;
+}
+
+static int match_entries(struct entry *entry1, struct entry *entry2)
+{
+	return entry1->timer       == entry2->timer	  &&
+	       entry1->start_func  == entry2->start_func  &&
+	       entry1->expire_func == entry2->expire_func &&
+	       entry1->pid	   == entry2->pid;
+}
+
+/*
+ * Look up whether an entry matching this item is present
+ * in the hash already. Must be called with irqs off and the
+ * lookup lock held:
+ */
+static struct entry *tstat_lookup(struct entry *entry, char *comm)
+{
+	struct entry **head, *curr, *prev;
+
+	head = tstat_hashentry(entry);
+	curr = *head;
+
+	/*
+	 * The fastpath is when the entry is already hashed,
+	 * we do this with the lookup lock held, but with the
+	 * table lock not held:
+	 */
+	while (curr) {
+		if (match_entries(curr, entry))
+			return curr;
+
+		curr = curr->next;
+	}
+	/*
+	 * Slowpath: allocate, set up and link a new hash entry:
+	 */
+	prev = NULL;
+	curr = *head;
+
+	raw_spin_lock(&table_lock);
+	/*
+	 * Make sure we have not raced with another CPU:
+	 */
+	while (curr) {
+		if (match_entries(curr, entry))
+			goto out_unlock;
+
+		prev = curr;
+		curr = curr->next;
+	}
+
+	curr = alloc_entry();
+	if (curr) {
+		*curr = *entry;
+		curr->count = 0;
+		curr->next = NULL;
+		memcpy(curr->comm, comm, TASK_COMM_LEN);
+
+		smp_mb(); /* Ensure that curr is initialized before insert */
+
+		if (prev)
+			prev->next = curr;
+		else
+			*head = curr;
+	}
+ out_unlock:
+	raw_spin_unlock(&table_lock);
+
+	return curr;
+}
+
+/**
+ * timer_stats_update_stats - Update the statistics for a timer.
+ * @timer:	pointer to either a timer_list or a hrtimer
+ * @pid:	the pid of the task which set up the timer
+ * @startf:	pointer to the function which did the timer setup
+ * @timerf:	pointer to the timer callback function of the timer
+ * @comm:	name of the process which set up the timer
+ *
+ * When the timer is already registered, then the event counter is
+ * incremented. Otherwise the timer is registered in a free slot.
+ */
+void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
+			      void *timerf, char *comm,
+			      unsigned int timer_flag)
+{
+	/*
+	 * It doesn't matter which lock we take:
+	 */
+	raw_spinlock_t *lock;
+	struct entry *entry, input;
+	unsigned long flags;
+
+	if (likely(!timer_stats_active))
+		return;
+
+	lock = &per_cpu(tstats_lookup_lock, raw_smp_processor_id());
+
+	input.timer = timer;
+	input.start_func = startf;
+	input.expire_func = timerf;
+	input.pid = pid;
+	input.timer_flag = timer_flag;
+
+	raw_spin_lock_irqsave(lock, flags);
+	if (!timer_stats_active)
+		goto out_unlock;
+
+	entry = tstat_lookup(&input, comm);
+	if (likely(entry))
+		entry->count++;
+	else
+		atomic_inc(&overflow_count);
+
+ out_unlock:
+	raw_spin_unlock_irqrestore(lock, flags);
+}
+
+static void print_name_offset(struct seq_file *m, unsigned long addr)
+{
+	char symname[KSYM_NAME_LEN];
+
+	if (lookup_symbol_name(addr, symname) < 0)
+		seq_printf(m, "<%p>", (void *)addr);
+	else
+		seq_printf(m, "%s", symname);
+}
+
+static int tstats_show(struct seq_file *m, void *v)
+{
+	struct timespec period;
+	struct entry *entry;
+	unsigned long ms;
+	long events = 0;
+	ktime_t time;
+	int i;
+
+	mutex_lock(&show_mutex);
+	/*
+	 * If still active then calculate up to now:
+	 */
+	if (timer_stats_active)
+		time_stop = ktime_get();
+
+	time = ktime_sub(time_stop, time_start);
+
+	period = ktime_to_timespec(time);
+	ms = period.tv_nsec / 1000000;
+
+	seq_puts(m, "Timer Stats Version: v0.2\n");
+	seq_printf(m, "Sample period: %ld.%03ld s\n", period.tv_sec, ms);
+	if (atomic_read(&overflow_count))
+		seq_printf(m, "Overflow: %d entries\n",
+			atomic_read(&overflow_count));
+
+	for (i = 0; i < nr_entries; i++) {
+		entry = entries + i;
+ 		if (entry->timer_flag & TIMER_STATS_FLAG_DEFERRABLE) {
+			seq_printf(m, "%4luD, %5d %-16s ",
+				entry->count, entry->pid, entry->comm);
+		} else {
+			seq_printf(m, " %4lu, %5d %-16s ",
+				entry->count, entry->pid, entry->comm);
+		}
+
+		print_name_offset(m, (unsigned long)entry->start_func);
+		seq_puts(m, " (");
+		print_name_offset(m, (unsigned long)entry->expire_func);
+		seq_puts(m, ")\n");
+
+		events += entry->count;
+	}
+
+	ms += period.tv_sec * 1000;
+	if (!ms)
+		ms = 1;
+
+	if (events && period.tv_sec)
+		seq_printf(m, "%ld total events, %ld.%03ld events/sec\n",
+			   events, events * 1000 / ms,
+			   (events * 1000000 / ms) % 1000);
+	else
+		seq_printf(m, "%ld total events\n", events);
+
+	mutex_unlock(&show_mutex);
+
+	return 0;
+}
+
+/*
+ * After a state change, make sure all concurrent lookup/update
+ * activities have stopped:
+ */
+static void sync_access(void)
+{
+	unsigned long flags;
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		raw_spinlock_t *lock = &per_cpu(tstats_lookup_lock, cpu);
+
+		raw_spin_lock_irqsave(lock, flags);
+		/* nothing */
+		raw_spin_unlock_irqrestore(lock, flags);
+	}
+}
+
+static ssize_t tstats_write(struct file *file, const char __user *buf,
+			    size_t count, loff_t *offs)
+{
+	char ctl[2];
+
+	if (count != 2 || *offs)
+		return -EINVAL;
+
+	if (copy_from_user(ctl, buf, count))
+		return -EFAULT;
+
+	mutex_lock(&show_mutex);
+	switch (ctl[0]) {
+	case '0':
+		if (timer_stats_active) {
+			timer_stats_active = 0;
+			time_stop = ktime_get();
+			sync_access();
+		}
+		break;
+	case '1':
+		if (!timer_stats_active) {
+			reset_entries();
+			time_start = ktime_get();
+			smp_mb();
+			timer_stats_active = 1;
+		}
+		break;
+	default:
+		count = -EINVAL;
+	}
+	mutex_unlock(&show_mutex);
+
+	return count;
+}
+
+static int tstats_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, tstats_show, NULL);
+}
+
+static const struct file_operations tstats_fops = {
+	.open		= tstats_open,
+	.read		= seq_read,
+	.write		= tstats_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+void __init init_timer_stats(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		raw_spin_lock_init(&per_cpu(tstats_lookup_lock, cpu));
+}
+
+static int __init init_tstats_procfs(void)
+{
+	struct proc_dir_entry *pe;
+
+	pe = proc_create("timer_stats", 0644, NULL, &tstats_fops);
+	if (!pe)
+		return -ENOMEM;
+	return 0;
+}
+__initcall(init_tstats_procfs);

kernel/time/udelay_test.c

@@ -0,0 +1,169 @@
+/*
+ * udelay() test kernel module
+ *
+ * Test is executed by writing and reading to /sys/kernel/debug/udelay_test
+ * Tests are configured by writing: USECS ITERATIONS
+ * Tests are executed by reading from the same file.
+ * Specifying usecs of 0 or negative values will run multiples tests.
+ *
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/ktime.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+
+#define DEFAULT_ITERATIONS 100
+
+#define DEBUGFS_FILENAME "udelay_test"
+
+static DEFINE_MUTEX(udelay_test_lock);
+static struct dentry *udelay_test_debugfs_file;
+static int udelay_test_usecs;
+static int udelay_test_iterations = DEFAULT_ITERATIONS;
+
+static int udelay_test_single(struct seq_file *s, int usecs, int iters)
+{
+	int min, max, fail_count = 0;
+	long long sum = 0;
+	long long avg;
+	int i;
+	/* Allow udelay to be up to 0.5% fast */
+	int allowed_error_ns = usecs * 5;
+
+	if (iters <= 0)
+		return 0;
+
+	for (i = 0; i < iters; ++i) {
+		struct timespec ts1, ts2;
+		int time_passed;
+
+		ktime_get_ts(&ts1);
+		udelay(usecs);
+		ktime_get_ts(&ts2);
+		time_passed = timespec_to_ns(&ts2) - timespec_to_ns(&ts1);
+
+		if (i == 0 || time_passed < min)
+			min = time_passed;
+		if (i == 0 || time_passed > max)
+			max = time_passed;
+		if ((time_passed + allowed_error_ns) / 1000 < usecs)
+			++fail_count;
+		sum += time_passed;
+	}
+
+	avg = sum;
+	do_div(avg, iters);
+	seq_printf(s, "%d usecs x %d: exp=%d allowed=%d min=%d avg=%lld max=%d",
+			usecs, iters, usecs * 1000,
+			(usecs * 1000) - allowed_error_ns, min, avg, max);
+	if (fail_count)
+		seq_printf(s, " FAIL=%d", fail_count);
+	seq_puts(s, "\n");
+
+	return 0;
+}
+
+static int udelay_test_show(struct seq_file *s, void *v)
+{
+	int usecs;
+	int iters;
+	int ret = 0;
+
+	mutex_lock(&udelay_test_lock);
+	usecs = udelay_test_usecs;
+	iters = udelay_test_iterations;
+	mutex_unlock(&udelay_test_lock);
+
+	if (usecs > 0) {
+		return udelay_test_single(s, usecs, iters);
+	} else if (usecs == 0) {
+		struct timespec ts;
+		ktime_get_ts(&ts);
+		seq_printf(s, "udelay() test (lpj=%ld kt=%ld.%09ld)\n",
+				loops_per_jiffy, ts.tv_sec, ts.tv_nsec);
+		seq_puts(s, "usage:\n");
+		seq_puts(s, "echo USECS [ITERS] > " DEBUGFS_FILENAME "\n");
+		seq_puts(s, "cat " DEBUGFS_FILENAME "\n");
+	}
+
+	return ret;
+}
+
+static int udelay_test_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, udelay_test_show, inode->i_private);
+}
+
+static ssize_t udelay_test_write(struct file *file, const char __user *buf,
+		size_t count, loff_t *pos)
+{
+	char lbuf[32];
+	int ret;
+	int usecs;
+	int iters;
+
+	if (count >= sizeof(lbuf))
+		return -EINVAL;
+
+	if (copy_from_user(lbuf, buf, count))
+		return -EFAULT;
+	lbuf[count] = '\0';
+
+	ret = sscanf(lbuf, "%d %d", &usecs, &iters);
+	if (ret < 1)
+		return -EINVAL;
+	else if (ret < 2)
+		iters = DEFAULT_ITERATIONS;
+
+	mutex_lock(&udelay_test_lock);
+	udelay_test_usecs = usecs;
+	udelay_test_iterations = iters;
+	mutex_unlock(&udelay_test_lock);
+
+	return count;
+}
+
+static const struct file_operations udelay_test_debugfs_ops = {
+	.owner = THIS_MODULE,
+	.open = udelay_test_open,
+	.read = seq_read,
+	.write = udelay_test_write,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init udelay_test_init(void)
+{
+	mutex_lock(&udelay_test_lock);
+	udelay_test_debugfs_file = debugfs_create_file(DEBUGFS_FILENAME,
+			S_IRUSR, NULL, NULL, &udelay_test_debugfs_ops);
+	mutex_unlock(&udelay_test_lock);
+
+	return 0;
+}
+
+module_init(udelay_test_init);
+
+static void __exit udelay_test_exit(void)
+{
+	mutex_lock(&udelay_test_lock);
+	debugfs_remove(udelay_test_debugfs_file);
+	mutex_unlock(&udelay_test_lock);
+}
+
+module_exit(udelay_test_exit);
+
+MODULE_AUTHOR("David Riley <davidriley@chromium.org>");
+MODULE_LICENSE("GPL");