aboutsummaryrefslogtreecommitdiff
path: root/kernel/time
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/time')
-rw-r--r--kernel/time/Kconfig195
-rw-r--r--kernel/time/Makefile10
-rw-r--r--kernel/time/alarmtimer.c861
-rw-r--r--kernel/time/clockevents.c578
-rw-r--r--kernel/time/clocksource.c510
-rw-r--r--kernel/time/jiffies.c64
-rw-r--r--kernel/time/ntp.c675
-rw-r--r--kernel/time/ntp_internal.h12
-rw-r--r--kernel/time/posix-clock.c446
-rw-r--r--kernel/time/sched_clock.c217
-rw-r--r--kernel/time/tick-broadcast-hrtimer.c106
-rw-r--r--kernel/time/tick-broadcast.c544
-rw-r--r--kernel/time/tick-common.c257
-rw-r--r--kernel/time/tick-internal.h51
-rw-r--r--kernel/time/tick-oneshot.c82
-rw-r--r--kernel/time/tick-sched.c837
-rw-r--r--kernel/time/timecompare.c192
-rw-r--r--kernel/time/timekeeping.c1478
-rw-r--r--kernel/time/timekeeping_debug.c74
-rw-r--r--kernel/time/timekeeping_internal.h14
-rw-r--r--kernel/time/timer_list.c125
-rw-r--r--kernel/time/timer_stats.c16
22 files changed, 5850 insertions, 1494 deletions
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index f06a8a36564..f448513a45e 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -1,17 +1,195 @@
#
# 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
+
+# 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
- bool "Tickless System (Dynamic Ticks)"
+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 HAVE_VIRT_CPU_ACCOUNTING_GEN
+ select NO_HZ_COMMON
+ select RCU_USER_QS
+ select RCU_NOCB_CPU
+ select VIRT_CPU_ACCOUNTING_GEN
+ 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 (except CPU 0)"
+ 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_FULL_SYSIDLE
+ bool "Detect full-system idle state for full dynticks system"
+ depends on NO_HZ_FULL
+ default n
+ help
+ At least one CPU must keep the scheduling-clock tick running for
+ timekeeping purposes whenever there is a non-idle CPU, where
+ "non-idle" also includes dynticks CPUs as long as they are
+ running non-idle tasks. Because the underlying adaptive-tick
+ support cannot distinguish between all CPUs being idle and
+ all CPUs each running a single task in dynticks mode, the
+ underlying support simply ensures that there is always a CPU
+ handling the scheduling-clock tick, whether or not all CPUs
+ are idle. This Kconfig option enables scalable detection of
+ the all-CPUs-idle state, thus allowing the scheduling-clock
+ tick to be disabled when all CPUs are idle. Note that scalable
+ detection of the all-CPUs-idle state means that larger systems
+ will be slower to declare the all-CPUs-idle state.
+
+ Say Y if you would like to help debug all-CPUs-idle detection.
+
+ Say N if you are unsure.
+
+config NO_HZ_FULL_SYSIDLE_SMALL
+ int "Number of CPUs above which large-system approach is used"
+ depends on NO_HZ_FULL_SYSIDLE
+ range 1 NR_CPUS
+ default 8
help
- This option enables a tickless system: timer interrupts will
- only trigger on an as-needed basis both when the system is
- busy and when the system is idle.
+ The full-system idle detection mechanism takes a lazy approach
+ on large systems, as is required to attain decent scalability.
+ However, on smaller systems, scalability is not anywhere near as
+ large a concern as is energy efficiency. The sysidle subsystem
+ therefore uses a fast but non-scalable algorithm for small
+ systems and a lazier but scalable algorithm for large systems.
+ This Kconfig parameter defines the number of CPUs in the largest
+ system that will be considered to be "small".
+
+ The default value will be fine in most cases. Battery-powered
+ systems that (1) enable NO_HZ_FULL_SYSIDLE, (2) have larger
+ numbers of CPUs, and (3) are suffering from battery-lifetime
+ problems due to long sysidle latencies might wish to experiment
+ with larger values for this Kconfig parameter. On the other
+ hand, they might be even better served by disabling NO_HZ_FULL
+ entirely, given that NO_HZ_FULL is intended for HPC and
+ real-time workloads that at present do not tend to be run on
+ battery-powered systems.
+
+ Take the default if you are unsure.
+
+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"
@@ -22,8 +200,5 @@ config HIGH_RES_TIMERS
hardware is not capable then this option only increases
the size of the kernel image.
-config GENERIC_CLOCKEVENTS_BUILD
- bool
- default y
- depends on GENERIC_CLOCKEVENTS || GENERIC_CLOCKEVENTS_MIGR
-
+endmenu
+endif
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index ee266620b06..57a413fd0eb 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,8 +1,14 @@
-obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o timeconv.o
+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-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) += tick-broadcast.o
+ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y)
+ obj-y += tick-broadcast.o
+ obj-$(CONFIG_TICK_ONESHOT) += tick-broadcast-hrtimer.o
+endif
+obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o
obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o
obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o
obj-$(CONFIG_TIMER_STATS) += timer_stats.o
+obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
new file mode 100644
index 00000000000..fe75444ae7e
--- /dev/null
+++ b/kernel/time/alarmtimer.c
@@ -0,0 +1,861 @@
+/*
+ * 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;
+
+}
+
+ktime_t alarm_expires_remaining(const struct alarm *alarm)
+{
+ struct alarm_base *base = &alarm_bases[alarm->type];
+ return ktime_sub(alarm->node.expires, base->gettime());
+}
+EXPORT_SYMBOL_GPL(alarm_expires_remaining);
+
+#ifdef CONFIG_RTC_CLASS
+/**
+ * alarmtimer_suspend - Suspend time callback
+ * @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;
+}
+EXPORT_SYMBOL_GPL(alarm_init);
+
+/**
+ * alarm_start - Sets an absolute 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;
+}
+EXPORT_SYMBOL_GPL(alarm_start);
+
+/**
+ * alarm_start_relative - Sets a relative alarm to fire
+ * @alarm: ptr to alarm to set
+ * @start: time relative to now to run the alarm
+ */
+int alarm_start_relative(struct alarm *alarm, ktime_t start)
+{
+ struct alarm_base *base = &alarm_bases[alarm->type];
+
+ start = ktime_add(start, base->gettime());
+ return alarm_start(alarm, start);
+}
+EXPORT_SYMBOL_GPL(alarm_start_relative);
+
+void alarm_restart(struct alarm *alarm)
+{
+ struct alarm_base *base = &alarm_bases[alarm->type];
+ unsigned long flags;
+
+ spin_lock_irqsave(&base->lock, flags);
+ hrtimer_set_expires(&alarm->timer, alarm->node.expires);
+ hrtimer_restart(&alarm->timer);
+ alarmtimer_enqueue(base, alarm);
+ spin_unlock_irqrestore(&base->lock, flags);
+}
+EXPORT_SYMBOL_GPL(alarm_restart);
+
+/**
+ * alarm_try_to_cancel - Tries to cancel an alarm timer
+ * @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;
+}
+EXPORT_SYMBOL_GPL(alarm_try_to_cancel);
+
+
+/**
+ * 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();
+ }
+}
+EXPORT_SYMBOL_GPL(alarm_cancel);
+
+
+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;
+}
+EXPORT_SYMBOL_GPL(alarm_forward);
+
+u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+{
+ struct alarm_base *base = &alarm_bases[alarm->type];
+
+ return alarm_forward(alarm, base->gettime(), interval);
+}
+EXPORT_SYMBOL_GPL(alarm_forward_now);
+
+
+/**
+ * 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 -EINVAL;
+
+ 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 -EINVAL;
+
+ *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)
+{
+ ktime_t exp;
+
+ if (!rtcdev)
+ return -ENOTSUPP;
+
+ if (flags & ~TIMER_ABSTIME)
+ return -EINVAL;
+
+ 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);
+ exp = timespec_to_ktime(new_setting->it_value);
+ /* Convert (if necessary) to absolute time */
+ if (flags != TIMER_ABSTIME) {
+ ktime_t now;
+
+ now = alarm_bases[timr->it.alarm.alarmtimer.type].gettime();
+ exp = ktime_add(now, exp);
+ }
+
+ alarm_start(&timr->it.alarm.alarmtimer, exp);
+ 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 (flags & ~TIMER_ABSTIME)
+ return -EINVAL;
+
+ 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);
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index d7395fdfb9f..9c94c19f130 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -15,46 +15,82 @@
#include <linux/hrtimer.h>
#include <linux/init.h>
#include <linux/module.h>
-#include <linux/notifier.h>
#include <linux/smp.h>
-#include <linux/sysdev.h>
-#include <linux/tick.h>
+#include <linux/device.h>
#include "tick-internal.h"
/* The registered clock event devices */
static LIST_HEAD(clockevent_devices);
static LIST_HEAD(clockevents_released);
-
-/* Notification for clock events */
-static RAW_NOTIFIER_HEAD(clockevents_chain);
-
/* Protection for the above */
static DEFINE_RAW_SPINLOCK(clockevents_lock);
+/* Protection for unbind operations */
+static DEFINE_MUTEX(clockevents_mutex);
-/**
- * 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)
+struct ce_unbind {
+ struct clock_event_device *ce;
+ int res;
+};
+
+static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt,
+ bool ismax)
{
u64 clc = (u64) latch << evt->shift;
+ u64 rnd;
if (unlikely(!evt->mult)) {
evt->mult = 1;
WARN_ON(1);
}
+ rnd = (u64) evt->mult - 1;
+
+ /*
+ * Upper bound sanity check. If the backwards conversion is
+ * not equal latch, we know that the above shift overflowed.
+ */
+ if ((clc >> evt->shift) != (u64)latch)
+ clc = ~0ULL;
+
+ /*
+ * Scaled math oddities:
+ *
+ * For mult <= (1 << shift) we can safely add mult - 1 to
+ * prevent integer rounding loss. So the backwards conversion
+ * from nsec to device ticks will be correct.
+ *
+ * For mult > (1 << shift), i.e. device frequency is > 1GHz we
+ * need to be careful. Adding mult - 1 will result in a value
+ * which when converted back to device ticks can be larger
+ * than latch by up to (mult - 1) >> shift. For the min_delta
+ * calculation we still want to apply this in order to stay
+ * above the minimum device ticks limit. For the upper limit
+ * we would end up with a latch value larger than the upper
+ * limit of the device, so we omit the add to stay below the
+ * device upper boundary.
+ *
+ * Also omit the add if it would overflow the u64 boundary.
+ */
+ if ((~0ULL - clc > rnd) &&
+ (!ismax || evt->mult <= (1U << evt->shift)))
+ clc += rnd;
do_div(clc, evt->mult);
- if (clc < 1000)
- clc = 1000;
- if (clc > KTIME_MAX)
- clc = KTIME_MAX;
- return clc;
+ /* Deltas less than 1usec are pointless noise */
+ return clc > 1000 ? clc : 1000;
+}
+
+/**
+ * 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)
+{
+ return cev_delta2ns(latch, evt, false);
}
EXPORT_SYMBOL_GPL(clockevent_delta2ns);
@@ -95,66 +131,145 @@ void clockevents_shutdown(struct clock_event_device *dev)
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_deferred(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_deferred(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,
- ktime_t now)
+ bool force)
{
unsigned long long clc;
int64_t delta;
+ int rc;
if (unlikely(expires.tv64 < 0)) {
WARN_ON_ONCE(1);
return -ETIME;
}
- delta = ktime_to_ns(ktime_sub(expires, now));
-
- if (delta <= 0)
- return -ETIME;
-
dev->next_event = expires;
if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN)
return 0;
- if (delta > dev->max_delta_ns)
- delta = dev->max_delta_ns;
- if (delta < dev->min_delta_ns)
- delta = dev->min_delta_ns;
-
- clc = delta * dev->mult;
- clc >>= dev->shift;
-
- return dev->set_next_event((unsigned long) clc, dev);
-}
+ /* Shortcut for clockevent devices that can deal with ktime. */
+ if (dev->features & CLOCK_EVT_FEAT_KTIME)
+ return dev->set_next_ktime(expires, dev);
-/**
- * clockevents_register_notifier - register a clock events change listener
- */
-int clockevents_register_notifier(struct notifier_block *nb)
-{
- unsigned long flags;
- int ret;
+ delta = ktime_to_ns(ktime_sub(expires, ktime_get()));
+ if (delta <= 0)
+ return force ? clockevents_program_min_delta(dev) : -ETIME;
- raw_spin_lock_irqsave(&clockevents_lock, flags);
- ret = raw_notifier_chain_register(&clockevents_chain, nb);
- raw_spin_unlock_irqrestore(&clockevents_lock, flags);
+ delta = min(delta, (int64_t) dev->max_delta_ns);
+ delta = max(delta, (int64_t) dev->min_delta_ns);
- return ret;
-}
+ clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
+ rc = dev->set_next_event((unsigned long) clc, dev);
-/*
- * 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);
+ return (rc && force) ? clockevents_program_min_delta(dev) : rc;
}
/*
@@ -170,9 +285,93 @@ static void clockevents_notify_released(void)
struct clock_event_device, list);
list_del(&dev->list);
list_add(&dev->list, &clockevent_devices);
- clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+ tick_check_new_device(dev);
+ }
+}
+
+/*
+ * Try to install a replacement clock event device
+ */
+static int clockevents_replace(struct clock_event_device *ced)
+{
+ struct clock_event_device *dev, *newdev = NULL;
+
+ list_for_each_entry(dev, &clockevent_devices, list) {
+ if (dev == ced || dev->mode != CLOCK_EVT_MODE_UNUSED)
+ continue;
+
+ if (!tick_check_replacement(newdev, dev))
+ continue;
+
+ if (!try_module_get(dev->owner))
+ continue;
+
+ if (newdev)
+ module_put(newdev->owner);
+ newdev = dev;
+ }
+ if (newdev) {
+ tick_install_replacement(newdev);
+ list_del_init(&ced->list);
+ }
+ return newdev ? 0 : -EBUSY;
+}
+
+/*
+ * Called with clockevents_mutex and clockevents_lock held
+ */
+static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu)
+{
+ /* Fast track. Device is unused */
+ if (ced->mode == CLOCK_EVT_MODE_UNUSED) {
+ list_del_init(&ced->list);
+ return 0;
}
+
+ return ced == per_cpu(tick_cpu_device, cpu).evtdev ? -EAGAIN : -EBUSY;
+}
+
+/*
+ * SMP function call to unbind a device
+ */
+static void __clockevents_unbind(void *arg)
+{
+ struct ce_unbind *cu = arg;
+ int res;
+
+ raw_spin_lock(&clockevents_lock);
+ res = __clockevents_try_unbind(cu->ce, smp_processor_id());
+ if (res == -EAGAIN)
+ res = clockevents_replace(cu->ce);
+ cu->res = res;
+ raw_spin_unlock(&clockevents_lock);
+}
+
+/*
+ * Issues smp function call to unbind a per cpu device. Called with
+ * clockevents_mutex held.
+ */
+static int clockevents_unbind(struct clock_event_device *ced, int cpu)
+{
+ struct ce_unbind cu = { .ce = ced, .res = -ENODEV };
+
+ smp_call_function_single(cpu, __clockevents_unbind, &cu, 1);
+ return cu.res;
+}
+
+/*
+ * Unbind a clockevents device.
+ */
+int clockevents_unbind_device(struct clock_event_device *ced, int cpu)
+{
+ int ret;
+
+ mutex_lock(&clockevents_mutex);
+ ret = clockevents_unbind(ced, cpu);
+ mutex_unlock(&clockevents_mutex);
+ return ret;
}
+EXPORT_SYMBOL_GPL(clockevents_unbind);
/**
* clockevents_register_device - register a clock event device
@@ -183,18 +382,103 @@ void clockevents_register_device(struct clock_event_device *dev)
unsigned long flags;
BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
- BUG_ON(!dev->cpumask);
+ 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);
+ tick_check_new_device(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 = cev_delta2ns(dev->min_delta_ticks, dev, false);
+ dev->max_delta_ns = cev_delta2ns(dev->max_delta_ticks, dev, true);
+}
+
+/**
+ * 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);
+
+int __clockevents_update_freq(struct clock_event_device *dev, u32 freq)
+{
+ clockevents_config(dev, freq);
+
+ if (dev->mode == CLOCK_EVT_MODE_ONESHOT)
+ return clockevents_program_event(dev, dev->next_event, false);
+
+ if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
+ dev->set_mode(CLOCK_EVT_MODE_PERIODIC, dev);
+
+ return 0;
+}
+
+/**
+ * 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. If called for the broadcast device the core takes
+ * care of serialization.
+ *
+ * Returns 0 on success, -ETIME when the event is in the past.
+ */
+int clockevents_update_freq(struct clock_event_device *dev, u32 freq)
+{
+ unsigned long flags;
+ int ret;
+
+ local_irq_save(flags);
+ ret = tick_broadcast_update_freq(dev, freq);
+ if (ret == -ENODEV)
+ ret = __clockevents_update_freq(dev, freq);
+ local_irq_restore(flags);
+ return ret;
+}
+
/*
* Noop handler when we shut down an event device
*/
@@ -220,6 +504,7 @@ void clockevents_exchange_device(struct clock_event_device *old,
* released list and do a notify add later.
*/
if (old) {
+ module_put(old->owner);
clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
list_del(&old->list);
list_add(&old->list, &clockevents_released);
@@ -232,21 +517,72 @@ void clockevents_exchange_device(struct clock_event_device *old,
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
+ * Returns 0 on success, any other value on error
*/
-void clockevents_notify(unsigned long reason, void *arg)
+int clockevents_notify(unsigned long reason, void *arg)
{
struct clock_event_device *dev, *tmp;
unsigned long flags;
- int cpu;
+ int cpu, ret = 0;
raw_spin_lock_irqsave(&clockevents_lock, flags);
- clockevents_do_notify(reason, arg);
switch (reason) {
+ case CLOCK_EVT_NOTIFY_BROADCAST_ON:
+ case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
+ case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
+ tick_broadcast_on_off(reason, arg);
+ break;
+
+ case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
+ case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
+ ret = tick_broadcast_oneshot_control(reason);
+ break;
+
+ case CLOCK_EVT_NOTIFY_CPU_DYING:
+ tick_handover_do_timer(arg);
+ break;
+
+ case CLOCK_EVT_NOTIFY_SUSPEND:
+ tick_suspend();
+ tick_suspend_broadcast();
+ break;
+
+ case CLOCK_EVT_NOTIFY_RESUME:
+ tick_resume();
+ break;
+
case CLOCK_EVT_NOTIFY_CPU_DEAD:
+ tick_shutdown_broadcast_oneshot(arg);
+ tick_shutdown_broadcast(arg);
+ tick_shutdown(arg);
/*
* Unregister the clock event devices which were
* released from the users in the notify chain.
@@ -270,6 +606,126 @@ void clockevents_notify(unsigned long reason, void *arg)
break;
}
raw_spin_unlock_irqrestore(&clockevents_lock, flags);
+ return ret;
}
EXPORT_SYMBOL_GPL(clockevents_notify);
+
+#ifdef CONFIG_SYSFS
+struct bus_type clockevents_subsys = {
+ .name = "clockevents",
+ .dev_name = "clockevent",
+};
+
+static DEFINE_PER_CPU(struct device, tick_percpu_dev);
+static struct tick_device *tick_get_tick_dev(struct device *dev);
+
+static ssize_t sysfs_show_current_tick_dev(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct tick_device *td;
+ ssize_t count = 0;
+
+ raw_spin_lock_irq(&clockevents_lock);
+ td = tick_get_tick_dev(dev);
+ if (td && td->evtdev)
+ count = snprintf(buf, PAGE_SIZE, "%s\n", td->evtdev->name);
+ raw_spin_unlock_irq(&clockevents_lock);
+ return count;
+}
+static DEVICE_ATTR(current_device, 0444, sysfs_show_current_tick_dev, NULL);
+
+/* We don't support the abomination of removable broadcast devices */
+static ssize_t sysfs_unbind_tick_dev(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ char name[CS_NAME_LEN];
+ ssize_t ret = sysfs_get_uname(buf, name, count);
+ struct clock_event_device *ce;
+
+ if (ret < 0)
+ return ret;
+
+ ret = -ENODEV;
+ mutex_lock(&clockevents_mutex);
+ raw_spin_lock_irq(&clockevents_lock);
+ list_for_each_entry(ce, &clockevent_devices, list) {
+ if (!strcmp(ce->name, name)) {
+ ret = __clockevents_try_unbind(ce, dev->id);
+ break;
+ }
+ }
+ raw_spin_unlock_irq(&clockevents_lock);
+ /*
+ * We hold clockevents_mutex, so ce can't go away
+ */
+ if (ret == -EAGAIN)
+ ret = clockevents_unbind(ce, dev->id);
+ mutex_unlock(&clockevents_mutex);
+ return ret ? ret : count;
+}
+static DEVICE_ATTR(unbind_device, 0200, NULL, sysfs_unbind_tick_dev);
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+static struct device tick_bc_dev = {
+ .init_name = "broadcast",
+ .id = 0,
+ .bus = &clockevents_subsys,
+};
+
+static struct tick_device *tick_get_tick_dev(struct device *dev)
+{
+ return dev == &tick_bc_dev ? tick_get_broadcast_device() :
+ &per_cpu(tick_cpu_device, dev->id);
+}
+
+static __init int tick_broadcast_init_sysfs(void)
+{
+ int err = device_register(&tick_bc_dev);
+
+ if (!err)
+ err = device_create_file(&tick_bc_dev, &dev_attr_current_device);
+ return err;
+}
+#else
+static struct tick_device *tick_get_tick_dev(struct device *dev)
+{
+ return &per_cpu(tick_cpu_device, dev->id);
+}
+static inline int tick_broadcast_init_sysfs(void) { return 0; }
#endif
+
+static int __init tick_init_sysfs(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct device *dev = &per_cpu(tick_percpu_dev, cpu);
+ int err;
+
+ dev->id = cpu;
+ dev->bus = &clockevents_subsys;
+ err = device_register(dev);
+ if (!err)
+ err = device_create_file(dev, &dev_attr_current_device);
+ if (!err)
+ err = device_create_file(dev, &dev_attr_unbind_device);
+ if (err)
+ return err;
+ }
+ return tick_broadcast_init_sysfs();
+}
+
+static int __init clockevents_init_sysfs(void)
+{
+ int err = subsys_system_register(&clockevents_subsys, NULL);
+
+ if (!err)
+ err = tick_init_sysfs();
+ return err;
+}
+device_initcall(clockevents_init_sysfs);
+#endif /* SYSFS */
+
+#endif /* GENERIC_CLOCK_EVENTS */
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index c18d7efa1b4..ba3e502c955 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -23,14 +23,16 @@
* o Allow clocksource drivers to be unregistered
*/
+#include <linux/device.h>
#include <linux/clocksource.h>
-#include <linux/sysdev.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 "tick-internal.h"
+
void timecounter_init(struct timecounter *tc,
const struct cyclecounter *cc,
u64 start_tstamp)
@@ -113,7 +115,7 @@ EXPORT_SYMBOL_GPL(timecounter_cyc2time);
* @shift: pointer to shift variable
* @from: frequency to convert from
* @to: frequency to convert to
- * @minsec: guaranteed runtime conversion range in seconds
+ * @maxsec: guaranteed runtime conversion range in seconds
*
* The function evaluates the shift/mult pair for the scaled math
* operations of clocksources and clockevents.
@@ -122,7 +124,7 @@ EXPORT_SYMBOL_GPL(timecounter_cyc2time);
* NSEC_PER_SEC == 1GHz and @from is the counter frequency. For clock
* event @to is the counter frequency and @from is NSEC_PER_SEC.
*
- * The @minsec conversion range argument controls the time frame in
+ * 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
@@ -131,7 +133,7 @@ EXPORT_SYMBOL_GPL(timecounter_cyc2time);
* factors.
*/
void
-clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec)
+clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 maxsec)
{
u64 tmp;
u32 sft, sftacc= 32;
@@ -140,7 +142,7 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec)
* Calculate the shift factor which is limiting the conversion
* range:
*/
- tmp = ((u64)minsec * from) >> 32;
+ tmp = ((u64)maxsec * from) >> 32;
while (tmp) {
tmp >>=1;
sftacc--;
@@ -152,6 +154,7 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec)
*/
for (sft = 32; sft > 0; sft--) {
tmp = (u64) to << sft;
+ tmp += from / 2;
do_div(tmp, from);
if ((tmp >> sftacc) == 0)
break;
@@ -173,19 +176,20 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec)
static struct clocksource *curr_clocksource;
static LIST_HEAD(clocksource_list);
static DEFINE_MUTEX(clocksource_mutex);
-static char override_name[32];
+static char override_name[CS_NAME_LEN];
static int finished_booting;
#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
static void clocksource_watchdog_work(struct work_struct *work);
+static void clocksource_select(void);
static LIST_HEAD(watchdog_list);
static struct clocksource *watchdog;
static struct timer_list watchdog_timer;
static DECLARE_WORK(watchdog_work, clocksource_watchdog_work);
static DEFINE_SPINLOCK(watchdog_lock);
-static cycle_t watchdog_last;
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);
@@ -247,16 +251,13 @@ static void clocksource_watchdog(unsigned long data)
struct clocksource *cs;
cycle_t csnow, wdnow;
int64_t wd_nsec, cs_nsec;
- int next_cpu;
+ int next_cpu, reset_pending;
spin_lock(&watchdog_lock);
if (!watchdog_running)
goto out;
- wdnow = watchdog->read(watchdog);
- wd_nsec = clocksource_cyc2ns((wdnow - watchdog_last) & watchdog->mask,
- watchdog->mult, watchdog->shift);
- watchdog_last = wdnow;
+ reset_pending = atomic_read(&watchdog_reset_pending);
list_for_each_entry(cs, &watchdog_list, wd_list) {
@@ -267,20 +268,33 @@ static void clocksource_watchdog(unsigned long data)
continue;
}
+ local_irq_disable();
csnow = cs->read(cs);
+ wdnow = watchdog->read(watchdog);
+ local_irq_enable();
/* Clocksource initialized ? */
- if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) {
+ if (!(cs->flags & CLOCK_SOURCE_WATCHDOG) ||
+ atomic_read(&watchdog_reset_pending)) {
cs->flags |= CLOCK_SOURCE_WATCHDOG;
- cs->wd_last = csnow;
+ cs->wd_last = wdnow;
+ cs->cs_last = csnow;
continue;
}
- /* Check the deviation from the watchdog clocksource. */
- cs_nsec = clocksource_cyc2ns((csnow - cs->wd_last) &
+ wd_nsec = clocksource_cyc2ns((wdnow - cs->wd_last) & watchdog->mask,
+ watchdog->mult, watchdog->shift);
+
+ cs_nsec = clocksource_cyc2ns((csnow - cs->cs_last) &
cs->mask, cs->mult, cs->shift);
- cs->wd_last = csnow;
- if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) {
+ 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;
}
@@ -288,17 +302,41 @@ static void clocksource_watchdog(unsigned long data)
if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
(cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) &&
(watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) {
+ /* Mark it valid for high-res. */
cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+
+ /*
+ * clocksource_done_booting() will sort it if
+ * finished_booting is not set yet.
+ */
+ if (!finished_booting)
+ continue;
+
/*
- * We just marked the clocksource as highres-capable,
- * notify the rest of the system as well so that we
- * transition into high-res mode:
+ * If this is not the current clocksource let
+ * the watchdog thread reselect it. Due to the
+ * change to high res this clocksource might
+ * be preferred now. If it is the current
+ * clocksource let the tick code know about
+ * that change.
*/
- tick_clock_notify();
+ if (cs != curr_clocksource) {
+ cs->flags |= CLOCK_SOURCE_RESELECT;
+ schedule_work(&watchdog_work);
+ } else {
+ tick_clock_notify();
+ }
}
}
/*
+ * 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.
*/
@@ -317,7 +355,6 @@ static inline void clocksource_start_watchdog(void)
return;
init_timer(&watchdog_timer);
watchdog_timer.function = clocksource_watchdog;
- watchdog_last = watchdog->read(watchdog);
watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask));
watchdog_running = 1;
@@ -341,23 +378,7 @@ static inline void clocksource_reset_watchdog(void)
static void clocksource_resume_watchdog(void)
{
- unsigned long flags;
-
- /*
- * We use trylock here to avoid a potential dead lock when
- * kgdb calls this code after the kernel has been stopped with
- * watchdog_lock held. When watchdog_lock is held we just
- * return and accept, that the watchdog might trigger and mark
- * the monitored clock source (usually TSC) unstable.
- *
- * This does not affect the other caller clocksource_resume()
- * because at this point the kernel is UP, interrupts are
- * disabled and nothing can hold watchdog_lock.
- */
- if (!spin_trylock_irqsave(&watchdog_lock, flags))
- return;
- clocksource_reset_watchdog();
- spin_unlock_irqrestore(&watchdog_lock, flags);
+ atomic_inc(&watchdog_reset_pending);
}
static void clocksource_enqueue_watchdog(struct clocksource *cs)
@@ -387,44 +408,39 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
static void clocksource_dequeue_watchdog(struct clocksource *cs)
{
- struct clocksource *tmp;
unsigned long flags;
spin_lock_irqsave(&watchdog_lock, flags);
- if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
- /* cs is a watched clocksource. */
- list_del_init(&cs->wd_list);
- } else if (cs == watchdog) {
- /* Reset watchdog cycles */
- clocksource_reset_watchdog();
- /* Current watchdog is removed. Find an alternative. */
- watchdog = NULL;
- list_for_each_entry(tmp, &clocksource_list, list) {
- if (tmp == cs || tmp->flags & CLOCK_SOURCE_MUST_VERIFY)
- continue;
- if (!watchdog || tmp->rating > watchdog->rating)
- watchdog = tmp;
+ if (cs != watchdog) {
+ if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
+ /* cs is a watched clocksource. */
+ list_del_init(&cs->wd_list);
+ /* Check if the watchdog timer needs to be stopped. */
+ clocksource_stop_watchdog();
}
}
- cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
- /* Check if the watchdog timer needs to be stopped. */
- clocksource_stop_watchdog();
spin_unlock_irqrestore(&watchdog_lock, flags);
}
-static int clocksource_watchdog_kthread(void *data)
+static int __clocksource_watchdog_kthread(void)
{
struct clocksource *cs, *tmp;
unsigned long flags;
LIST_HEAD(unstable);
+ int select = 0;
- mutex_lock(&clocksource_mutex);
spin_lock_irqsave(&watchdog_lock, flags);
- list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list)
+ list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
list_del_init(&cs->wd_list);
list_add(&cs->wd_list, &unstable);
+ select = 1;
}
+ if (cs->flags & CLOCK_SOURCE_RESELECT) {
+ cs->flags &= ~CLOCK_SOURCE_RESELECT;
+ select = 1;
+ }
+ }
/* Check if the watchdog timer needs to be stopped. */
clocksource_stop_watchdog();
spin_unlock_irqrestore(&watchdog_lock, flags);
@@ -434,10 +450,23 @@ static int clocksource_watchdog_kthread(void *data)
list_del_init(&cs->wd_list);
__clocksource_change_rating(cs, 0);
}
+ return select;
+}
+
+static int clocksource_watchdog_kthread(void *data)
+{
+ mutex_lock(&clocksource_mutex);
+ if (__clocksource_watchdog_kthread())
+ clocksource_select();
mutex_unlock(&clocksource_mutex);
return 0;
}
+static bool clocksource_is_watchdog(struct clocksource *cs)
+{
+ return cs == watchdog;
+}
+
#else /* CONFIG_CLOCKSOURCE_WATCHDOG */
static void clocksource_enqueue_watchdog(struct clocksource *cs)
@@ -448,7 +477,9 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
static inline void clocksource_resume_watchdog(void) { }
-static inline int clocksource_watchdog_kthread(void *data) { return 0; }
+static inline int __clocksource_watchdog_kthread(void) { return 0; }
+static bool clocksource_is_watchdog(struct clocksource *cs) { return false; }
+void clocksource_mark_unstable(struct clocksource *cs) { }
#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
@@ -491,66 +522,118 @@ void clocksource_touch_watchdog(void)
}
/**
- * clocksource_max_deferment - Returns max time the clocksource can be deferred
+ * clocksource_max_adjustment- Returns max adjustment amount
* @cs: Pointer to clocksource
*
*/
-static u64 clocksource_max_deferment(struct clocksource *cs)
+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;
+}
+
+/**
+ * clocks_calc_max_nsecs - Returns maximum nanoseconds that can be converted
+ * @mult: cycle to nanosecond multiplier
+ * @shift: cycle to nanosecond divisor (power of two)
+ * @maxadj: maximum adjustment value to mult (~11%)
+ * @mask: bitmask for two's complement subtraction of non 64 bit counters
+ */
+u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask)
{
u64 max_nsecs, max_cycles;
/*
* Calculate the maximum number of cycles that we can pass to the
* cyc2ns function without overflowing a 64-bit signed result. The
- * maximum number of cycles is equal to ULLONG_MAX/cs->mult which
- * is equivalent to the below.
- * max_cycles < (2^63)/cs->mult
- * max_cycles < 2^(log2((2^63)/cs->mult))
- * max_cycles < 2^(log2(2^63) - log2(cs->mult))
- * max_cycles < 2^(63 - log2(cs->mult))
- * max_cycles < 1 << (63 - log2(cs->mult))
+ * maximum number of cycles is equal to ULLONG_MAX/(mult+maxadj)
+ * which is equivalent to the below.
+ * max_cycles < (2^63)/(mult + maxadj)
+ * max_cycles < 2^(log2((2^63)/(mult + maxadj)))
+ * max_cycles < 2^(log2(2^63) - log2(mult + maxadj))
+ * max_cycles < 2^(63 - log2(mult + maxadj))
+ * max_cycles < 1 << (63 - log2(mult + maxadj))
* Please note that we add 1 to the result of the log2 to account for
* any rounding errors, ensure the above inequality is satisfied and
* no overflow will occur.
*/
- max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1));
+ max_cycles = 1ULL << (63 - (ilog2(mult + maxadj) + 1));
/*
* The actual maximum number of cycles we can defer the clocksource is
- * determined by the minimum of max_cycles and cs->mask.
+ * determined by the minimum of max_cycles and 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->shift);
+ max_cycles = min(max_cycles, mask);
+ max_nsecs = clocksource_cyc2ns(max_cycles, mult - maxadj, shift);
+
+ return max_nsecs;
+}
+
+/**
+ * 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_nsecs = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj,
+ cs->mask);
/*
* To ensure that the clocksource does not wrap whilst we are idle,
* limit the time the clocksource can be deferred by 12.5%. Please
* note a margin of 12.5% is used because this can be computed with
* a shift, versus say 10% which would require division.
*/
- return max_nsecs - (max_nsecs >> 5);
+ 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)
+static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur)
{
- struct clocksource *best, *cs;
+ struct clocksource *cs;
if (!finished_booting || list_empty(&clocksource_list))
+ return NULL;
+
+ /*
+ * We pick the clocksource with the highest rating. If oneshot
+ * mode is active, we pick the highres valid clocksource with
+ * the best rating.
+ */
+ list_for_each_entry(cs, &clocksource_list, list) {
+ if (skipcur && cs == curr_clocksource)
+ continue;
+ if (oneshot && !(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES))
+ continue;
+ return cs;
+ }
+ return NULL;
+}
+
+static void __clocksource_select(bool skipcur)
+{
+ bool oneshot = tick_oneshot_mode_active();
+ struct clocksource *best, *cs;
+
+ /* Find the best suitable clocksource */
+ best = clocksource_find_best(oneshot, skipcur);
+ if (!best)
return;
- /* First clocksource on the list has the best rating. */
- best = list_first_entry(&clocksource_list, struct clocksource, list);
+
/* Check for the override clocksource. */
list_for_each_entry(cs, &clocksource_list, list) {
+ if (skipcur && cs == curr_clocksource)
+ continue;
if (strcmp(cs->name, override_name) != 0)
continue;
/*
@@ -558,8 +641,7 @@ static void clocksource_select(void)
* capable clocksource if the tick code is in oneshot
* mode (highres or nohz)
*/
- if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
- tick_oneshot_mode_active()) {
+ if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && oneshot) {
/* Override clocksource cannot be used. */
printk(KERN_WARNING "Override clocksource %s is not "
"HRT compatible. Cannot switch while in "
@@ -570,16 +652,35 @@ static void clocksource_select(void)
best = cs;
break;
}
- if (curr_clocksource != best) {
- printk(KERN_INFO "Switching to clocksource %s\n", best->name);
+
+ if (curr_clocksource != best && !timekeeping_notify(best)) {
+ pr_info("Switched to clocksource %s\n", best->name);
curr_clocksource = best;
- timekeeping_notify(curr_clocksource);
}
}
+/**
+ * clocksource_select - Select the best clocksource available
+ *
+ * Private function. Must hold clocksource_mutex when called.
+ *
+ * Select the clocksource with the best rating, or the clocksource,
+ * which is selected by userspace override.
+ */
+static void clocksource_select(void)
+{
+ return __clocksource_select(false);
+}
+
+static void clocksource_select_fallback(void)
+{
+ return __clocksource_select(true);
+}
+
#else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */
static inline void clocksource_select(void) { }
+static inline void clocksource_select_fallback(void) { }
#endif
@@ -594,16 +695,11 @@ static int __init clocksource_done_booting(void)
{
mutex_lock(&clocksource_mutex);
curr_clocksource = clocksource_default_clock();
- mutex_unlock(&clocksource_mutex);
-
finished_booting = 1;
-
/*
* Run the watchdog first to eliminate unstable clock sources
*/
- clocksource_watchdog_kthread(NULL);
-
- mutex_lock(&clocksource_mutex);
+ __clocksource_watchdog_kthread();
clocksource_select();
mutex_unlock(&clocksource_mutex);
return 0;
@@ -625,22 +721,9 @@ static void clocksource_enqueue(struct clocksource *cs)
list_add(&cs->list, entry);
}
-
-/*
- * Maximum time we expect to go between ticks. This includes idle
- * tickless time. It provides the trade off between selecting a
- * mult/shift pair that is very precise but can only handle a short
- * period of time, vs. a mult/shift pair that can handle long periods
- * of time but isn't as precise.
- *
- * This is a subsystem constant, and actual hardware limitations
- * may override it (ie: clocksources that wrap every 3 seconds).
- */
-#define MAX_UPDATE_LENGTH 5 /* Seconds */
-
/**
* __clocksource_updatefreq_scale - Used update clocksource with new freq
- * @t: clocksource to be registered
+ * @cs: clocksource to be registered
* @scale: Scale factor multiplied against freq to get clocksource hz
* @freq: clocksource frequency (cycles per second) divided by scale
*
@@ -651,22 +734,48 @@ static void clocksource_enqueue(struct clocksource *cs)
*/
void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
{
+ u64 sec;
/*
- * Ideally we want to use some of the limits used in
- * clocksource_max_deferment, to provide a more informed
- * MAX_UPDATE_LENGTH. But for now this just gets the
- * register interface working properly.
+ * 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,
- MAX_UPDATE_LENGTH*scale);
+ 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
- * @t: clocksource to be registered
+ * @cs: clocksource to be registered
* @scale: Scale factor multiplied against freq to get clocksource hz
* @freq: clocksource frequency (cycles per second) divided by scale
*
@@ -678,14 +787,14 @@ EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
{
- /* Intialize mult/shift and max_idle_ns */
+ /* 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_select();
clocksource_enqueue_watchdog(cs);
+ clocksource_select();
mutex_unlock(&clocksource_mutex);
return 0;
}
@@ -694,19 +803,25 @@ EXPORT_SYMBOL_GPL(__clocksource_register_scale);
/**
* clocksource_register - Used to install new clocksources
- * @t: clocksource to be registered
+ * @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_select();
clocksource_enqueue_watchdog(cs);
+ clocksource_select();
mutex_unlock(&clocksource_mutex);
return 0;
}
@@ -717,30 +832,58 @@ 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);
+ clocksource_select();
mutex_unlock(&clocksource_mutex);
}
EXPORT_SYMBOL(clocksource_change_rating);
+/*
+ * Unbind clocksource @cs. Called with clocksource_mutex held
+ */
+static int clocksource_unbind(struct clocksource *cs)
+{
+ /*
+ * I really can't convince myself to support this on hardware
+ * designed by lobotomized monkeys.
+ */
+ if (clocksource_is_watchdog(cs))
+ return -EBUSY;
+
+ if (cs == curr_clocksource) {
+ /* Select and try to install a replacement clock source */
+ clocksource_select_fallback();
+ if (curr_clocksource == cs)
+ return -EBUSY;
+ }
+ clocksource_dequeue_watchdog(cs);
+ list_del_init(&cs->list);
+ return 0;
+}
+
/**
* clocksource_unregister - remove a registered clocksource
+ * @cs: clocksource to be unregistered
*/
-void clocksource_unregister(struct clocksource *cs)
+int clocksource_unregister(struct clocksource *cs)
{
+ int ret = 0;
+
mutex_lock(&clocksource_mutex);
- clocksource_dequeue_watchdog(cs);
- list_del(&cs->list);
- clocksource_select();
+ if (!list_empty(&cs->list))
+ ret = clocksource_unbind(cs);
mutex_unlock(&clocksource_mutex);
+ return ret;
}
EXPORT_SYMBOL(clocksource_unregister);
@@ -748,13 +891,14 @@ EXPORT_SYMBOL(clocksource_unregister);
/**
* 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 sys_device *dev,
- struct sysdev_attribute *attr, char *buf)
+sysfs_show_current_clocksources(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
ssize_t count = 0;
@@ -765,35 +909,44 @@ sysfs_show_current_clocksources(struct sys_device *dev,
return count;
}
+ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt)
+{
+ size_t ret = cnt;
+
+ /* strings from sysfs write are not 0 terminated! */
+ if (!cnt || cnt >= CS_NAME_LEN)
+ return -EINVAL;
+
+ /* strip of \n: */
+ if (buf[cnt-1] == '\n')
+ cnt--;
+ if (cnt > 0)
+ memcpy(dst, buf, cnt);
+ dst[cnt] = 0;
+ return ret;
+}
+
/**
* sysfs_override_clocksource - interface for manually overriding clocksource
* @dev: unused
+ * @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 sys_device *dev,
- struct sysdev_attribute *attr,
+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--;
+ ssize_t ret;
mutex_lock(&clocksource_mutex);
- if (count > 0)
- memcpy(override_name, buf, count);
- override_name[count] = 0;
- clocksource_select();
+ ret = sysfs_get_uname(buf, override_name, count);
+ if (ret >= 0)
+ clocksource_select();
mutex_unlock(&clocksource_mutex);
@@ -801,15 +954,50 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev,
}
/**
+ * sysfs_unbind_current_clocksource - interface for manually unbinding clocksource
+ * @dev: unused
+ * @attr: unused
+ * @buf: unused
+ * @count: length of buffer
+ *
+ * Takes input from sysfs interface for manually unbinding a clocksource.
+ */
+static ssize_t sysfs_unbind_clocksource(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct clocksource *cs;
+ char name[CS_NAME_LEN];
+ ssize_t ret;
+
+ ret = sysfs_get_uname(buf, name, count);
+ if (ret < 0)
+ return ret;
+
+ ret = -ENODEV;
+ mutex_lock(&clocksource_mutex);
+ list_for_each_entry(cs, &clocksource_list, list) {
+ if (strcmp(cs->name, name))
+ continue;
+ ret = clocksource_unbind(cs);
+ break;
+ }
+ mutex_unlock(&clocksource_mutex);
+
+ return ret ? ret : count;
+}
+
+/**
* sysfs_show_available_clocksources - sysfs interface for listing clocksource
* @dev: unused
+ * @attr: unused
* @buf: char buffer to be filled with clocksource list
*
* Provides sysfs interface for listing registered clocksources
*/
static ssize_t
-sysfs_show_available_clocksources(struct sys_device *dev,
- struct sysdev_attribute *attr,
+sysfs_show_available_clocksources(struct device *dev,
+ struct device_attribute *attr,
char *buf)
{
struct clocksource *src;
@@ -838,35 +1026,41 @@ sysfs_show_available_clocksources(struct sys_device *dev,
/*
* Sysfs setup bits:
*/
-static SYSDEV_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources,
+static DEVICE_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources,
sysfs_override_clocksource);
-static SYSDEV_ATTR(available_clocksource, 0444,
+static DEVICE_ATTR(unbind_clocksource, 0200, NULL, sysfs_unbind_clocksource);
+
+static DEVICE_ATTR(available_clocksource, 0444,
sysfs_show_available_clocksources, NULL);
-static struct sysdev_class clocksource_sysclass = {
+static struct bus_type clocksource_subsys = {
.name = "clocksource",
+ .dev_name = "clocksource",
};
-static struct sys_device device_clocksource = {
+static struct device device_clocksource = {
.id = 0,
- .cls = &clocksource_sysclass,
+ .bus = &clocksource_subsys,
};
static int __init init_clocksource_sysfs(void)
{
- int error = sysdev_class_register(&clocksource_sysclass);
+ int error = subsys_system_register(&clocksource_subsys, NULL);
if (!error)
- error = sysdev_register(&device_clocksource);
+ error = device_register(&device_clocksource);
if (!error)
- error = sysdev_create_file(
+ error = device_create_file(
&device_clocksource,
- &attr_current_clocksource);
+ &dev_attr_current_clocksource);
+ if (!error)
+ error = device_create_file(&device_clocksource,
+ &dev_attr_unbind_clocksource);
if (!error)
- error = sysdev_create_file(
+ error = device_create_file(
&device_clocksource,
- &attr_available_clocksource);
+ &dev_attr_available_clocksource);
return error;
}
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 5404a845690..a6a5bf53e86 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -22,8 +22,11 @@
************************************************************************/
#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
@@ -31,10 +34,10 @@
* 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 reccomended
+ * requested HZ value. It is also not recommended
* for "tick-less" systems.
*/
-#define NSEC_PER_JIFFY ((u32)((((u64)NSEC_PER_SEC)<<8)/ACTHZ))
+#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
@@ -48,14 +51,20 @@
* HZ shrinks, so values greater than 8 overflow 32bits when
* HZ=100.
*/
+#if HZ < 34
+#define JIFFIES_SHIFT 6
+#elif HZ < 67
+#define JIFFIES_SHIFT 7
+#else
#define JIFFIES_SHIFT 8
+#endif
static cycle_t jiffies_read(struct clocksource *cs)
{
return (cycle_t) jiffies;
}
-struct clocksource clocksource_jiffies = {
+static struct clocksource clocksource_jiffies = {
.name = "jiffies",
.rating = 1, /* lowest valid rating*/
.read = jiffies_read,
@@ -64,6 +73,25 @@ struct clocksource clocksource_jiffies = {
.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);
@@ -75,3 +103,33 @@ 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;
+}
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index d2321891538..33db43a3951 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -14,22 +14,28 @@
#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;
-/* ACTHZ period (nsecs): */
+/* SHIFTED_HZ period (nsecs): */
unsigned long tick_nsec;
-u64 tick_length;
+static u64 tick_length;
static u64 tick_length_base;
-static struct hrtimer leap_timer;
-
#define MAX_TICKADJ 500LL /* usecs */
#define MAX_TICKADJ_SCALED \
(((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
@@ -46,10 +52,7 @@ static struct hrtimer leap_timer;
static int time_state = TIME_OK;
/* clock status bits: */
-int time_status = STA_UNSYNC;
-
-/* TAI offset (secs): */
-static long time_tai;
+static int time_status = STA_UNSYNC;
/* time adjustment (nsecs): */
static s64 time_offset;
@@ -74,6 +77,169 @@ 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 (status & (STA_UNSYNC|STA_CLOCKERR))
+ /* PPS signal lost when either PPS time or
+ * PPS frequency synchronization requested
+ */
+ || ((status & (STA_PPSFREQ|STA_PPSTIME))
+ && !(status & STA_PPSSIGNAL))
+ /* PPS jitter exceeded when
+ * PPS time synchronization requested */
+ || ((status & (STA_PPSTIME|STA_PPSJITTER))
+ == (STA_PPSTIME|STA_PPSJITTER))
+ /* PPS wander exceeded or calibration error when
+ * PPS frequency synchronization requested
+ */
+ || ((status & STA_PPSFREQ)
+ && (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:
*/
@@ -116,7 +282,7 @@ static inline s64 ntp_update_offset_fll(s64 offset64, long secs)
time_status |= STA_MODE;
- return div_s64(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs);
+ return div64_long(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs);
}
static void ntp_update_offset(long offset)
@@ -171,8 +337,6 @@ static void ntp_update_offset(long offset)
/**
* ntp_clear - Clears the NTP state variables
- *
- * Must be called while holding a write on the xtime_lock
*/
void ntp_clear(void)
{
@@ -185,63 +349,75 @@ void ntp_clear(void)
tick_length = tick_length_base;
time_offset = 0;
+
+ /* Clear PPS state variables */
+ pps_clear();
+}
+
+
+u64 ntp_tick_length(void)
+{
+ return tick_length;
}
+
/*
- * 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.
+ * 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
*/
-static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
+int second_overflow(unsigned long secs)
{
- enum hrtimer_restart res = HRTIMER_NORESTART;
-
- write_seqlock(&xtime_lock);
+ 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:
- timekeeping_leap_insert(-1);
- time_state = TIME_OOP;
- printk(KERN_NOTICE
- "Clock: inserting leap second 23:59:60 UTC\n");
- hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC);
- res = HRTIMER_RESTART;
+ 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:
- timekeeping_leap_insert(1);
- time_tai--;
- time_state = TIME_WAIT;
- printk(KERN_NOTICE
- "Clock: deleting leap second 23:59:59 UTC\n");
+ 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_tai++;
time_state = TIME_WAIT;
- /* fall through */
+ break;
+
case TIME_WAIT:
if (!(time_status & (STA_INS | STA_DEL)))
time_state = TIME_OK;
break;
}
- write_sequnlock(&xtime_lock);
-
- return res;
-}
-
-/*
- * 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.
- */
-void second_overflow(void)
-{
- s64 delta;
/* Bump the maxerror field */
time_maxerror += MAXFREQ / NSEC_PER_USEC;
@@ -250,41 +426,40 @@ void second_overflow(void)
time_status |= STA_UNSYNC;
}
- /*
- * Compute the phase adjustment for the next second. The offset is
- * reduced by a fixed factor times the time constant.
- */
+ /* Compute the phase adjustment for the next second */
tick_length = tick_length_base;
- delta = shift_right(time_offset, SHIFT_PLL + time_constant);
+ delta = ntp_offset_chunk(time_offset);
time_offset -= delta;
tick_length += delta;
+ /* Check PPS signal */
+ pps_dec_valid();
+
if (!time_adjust)
- return;
+ goto out;
if (time_adjust > MAX_TICKADJ) {
time_adjust -= MAX_TICKADJ;
tick_length += MAX_TICKADJ_SCALED;
- return;
+ goto out;
}
if (time_adjust < -MAX_TICKADJ) {
time_adjust += MAX_TICKADJ;
tick_length -= MAX_TICKADJ_SCALED;
- return;
+ goto out;
}
tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ)
<< NTP_SCALE_SHIFT;
time_adjust = 0;
-}
-
-#ifdef CONFIG_GENERIC_CMOS_UPDATE
-/* Disable the cmos update - used by virtualization and embedded */
-int no_sync_cmos_clock __read_mostly;
+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);
@@ -300,6 +475,7 @@ static void sync_cmos_clock(struct work_struct *work)
* 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...
+ * We want the clock to be within a couple of ticks from the target.
*/
if (!ntp_synced()) {
/*
@@ -310,14 +486,26 @@ static void sync_cmos_clock(struct work_struct *work)
}
getnstimeofday(&now);
- if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2)
- fail = update_persistent_clock(now);
+ if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) {
+ 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)
+ if (!fail || fail == -ENODEV)
next.tv_sec = 659;
else
next.tv_sec = 0;
@@ -326,40 +514,19 @@ static void sync_cmos_clock(struct work_struct *work)
next.tv_sec++;
next.tv_nsec -= NSEC_PER_SEC;
}
- schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
+ queue_delayed_work(system_power_efficient_wq,
+ &sync_cmos_work, timespec_to_jiffies(&next));
}
-static void notify_cmos_timer(void)
+void ntp_notify_cmos_timer(void)
{
- if (!no_sync_cmos_clock)
- schedule_delayed_work(&sync_cmos_work, 0);
+ queue_delayed_work(system_power_efficient_wq, &sync_cmos_work, 0);
}
#else
-static inline void notify_cmos_timer(void) { }
+void ntp_notify_cmos_timer(void) { }
#endif
-/*
- * Start the leap seconds timer:
- */
-static inline void ntp_start_leap_timer(struct timespec *ts)
-{
- long now = ts->tv_sec;
-
- if (time_status & STA_INS) {
- time_state = TIME_INS;
- now += 86400 - now % 86400;
- hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS);
-
- return;
- }
-
- if (time_status & STA_DEL) {
- time_state = TIME_DEL;
- now += 86400 - (now + 1) % 86400;
- hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS);
- }
-}
/*
* Propagate a new txc->status value into the NTP state:
@@ -369,6 +536,8 @@ 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();
}
/*
@@ -381,29 +550,12 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts)
/* only set allowed bits */
time_status &= STA_RONLY;
time_status |= txc->status & ~STA_RONLY;
-
- switch (time_state) {
- case TIME_OK:
- ntp_start_leap_timer(ts);
- break;
- case TIME_INS:
- case TIME_DEL:
- time_state = TIME_OK;
- ntp_start_leap_timer(ts);
- case TIME_WAIT:
- if (!(time_status & (STA_INS | STA_DEL)))
- time_state = TIME_OK;
- break;
- case TIME_OOP:
- hrtimer_restart(&leap_timer);
- break;
- }
}
-/*
- * Called with the xtime lock held, so we can access and modify
- * all the global NTP state:
- */
-static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts)
+
+
+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);
@@ -418,6 +570,8 @@ static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts
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)
@@ -435,7 +589,7 @@ static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts
}
if (txc->modes & ADJ_TAI && txc->constant > 0)
- time_tai = txc->constant;
+ *time_tai = txc->constant;
if (txc->modes & ADJ_OFFSET)
ntp_update_offset(txc->offset);
@@ -447,16 +601,13 @@ static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts
ntp_update_frequency();
}
-/*
- * adjtimex mainly allows reading (and writing, if superuser) of
- * kernel time-keeping variables. used by xntpd.
+
+
+/**
+ * ntp_validate_timex - Ensures the timex is ok for use in do_adjtimex
*/
-int do_adjtimex(struct timex *txc)
+int ntp_validate_timex(struct timex *txc)
{
- struct timespec ts;
- int result;
-
- /* Validate the data before disabling interrupts */
if (txc->modes & ADJ_ADJTIME) {
/* singleshot must not be used with any other mode bits */
if (!(txc->modes & ADJ_OFFSET_SINGLESHOT))
@@ -468,7 +619,6 @@ int do_adjtimex(struct timex *txc)
/* 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!
@@ -477,14 +627,22 @@ int do_adjtimex(struct timex *txc)
(txc->tick < 900000/USER_HZ ||
txc->tick > 1100000/USER_HZ))
return -EINVAL;
-
- if (txc->modes & ADJ_STATUS && time_state != TIME_OK)
- hrtimer_cancel(&leap_timer);
}
- getnstimeofday(&ts);
+ if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
+ return -EPERM;
+
+ return 0;
+}
+
- write_seqlock_irq(&xtime_lock);
+/*
+ * 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;
@@ -499,7 +657,7 @@ int do_adjtimex(struct timex *txc)
/* If there are input parameters, then process them: */
if (txc->modes)
- process_adjtimex_modes(txc, &ts);
+ process_adjtimex_modes(txc, ts, time_tai);
txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
NTP_SCALE_SHIFT);
@@ -508,7 +666,8 @@ int do_adjtimex(struct timex *txc)
}
result = time_state; /* mostly `TIME_OK' */
- if (time_status & (STA_UNSYNC|STA_CLOCKERR))
+ /* check for errors */
+ if (is_error_status(time_status))
result = TIME_ERROR;
txc->freq = shift_right((time_freq >> PPM_SCALE_INV_SHIFT) *
@@ -520,33 +679,257 @@ int do_adjtimex(struct timex *txc)
txc->precision = 1;
txc->tolerance = MAXFREQ_SCALED / PPM_SCALE;
txc->tick = tick_usec;
- txc->tai = time_tai;
-
- /* 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;
+ txc->tai = *time_tai;
- write_sequnlock_irq(&xtime_lock);
+ /* fill PPS status fields */
+ pps_fill_timex(txc);
- txc->time.tv_sec = ts.tv_sec;
- txc->time.tv_usec = ts.tv_nsec;
+ 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;
- notify_cmos_timer();
-
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();
+ printk_deferred(KERN_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) {
+ printk_deferred(KERN_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)) {
+ printk_deferred(KERN_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;
+ printk_deferred(KERN_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);
+ int rc = kstrtol(str, 0, (long *)&ntp_tick_adj);
+
+ if (rc)
+ return rc;
ntp_tick_adj <<= NTP_SCALE_SHIFT;
return 1;
@@ -557,6 +940,4 @@ __setup("ntp_tick_adj=", ntp_tick_adj_setup);
void __init ntp_init(void)
{
ntp_clear();
- hrtimer_init(&leap_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
- leap_timer.function = ntp_leap_second;
}
diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h
new file mode 100644
index 00000000000..1950cb4ca2a
--- /dev/null
+++ b/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 */
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
new file mode 100644
index 00000000000..ce033c7aa2e
--- /dev/null
+++ b/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,
+};
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
new file mode 100644
index 00000000000..01d2d15aa66
--- /dev/null
+++ b/kernel/time/sched_clock.c
@@ -0,0 +1,217 @@
+/*
+ * sched_clock.c: support for extending counters to full 64-bit ns counter
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/clocksource.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/ktime.h>
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+#include <linux/sched.h>
+#include <linux/syscore_ops.h>
+#include <linux/hrtimer.h>
+#include <linux/sched_clock.h>
+#include <linux/seqlock.h>
+#include <linux/bitops.h>
+
+struct clock_data {
+ ktime_t wrap_kt;
+ u64 epoch_ns;
+ u64 epoch_cyc;
+ seqcount_t seq;
+ unsigned long rate;
+ u32 mult;
+ u32 shift;
+ bool suspended;
+};
+
+static struct hrtimer sched_clock_timer;
+static int irqtime = -1;
+
+core_param(irqtime, irqtime, int, 0400);
+
+static struct clock_data cd = {
+ .mult = NSEC_PER_SEC / HZ,
+};
+
+static u64 __read_mostly sched_clock_mask;
+
+static u64 notrace jiffy_sched_clock_read(void)
+{
+ /*
+ * We don't need to use get_jiffies_64 on 32-bit arches here
+ * because we register with BITS_PER_LONG
+ */
+ return (u64)(jiffies - INITIAL_JIFFIES);
+}
+
+static u64 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
+
+static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
+{
+ return (cyc * mult) >> shift;
+}
+
+unsigned long long notrace sched_clock(void)
+{
+ u64 epoch_ns;
+ u64 epoch_cyc;
+ u64 cyc;
+ unsigned long seq;
+
+ if (cd.suspended)
+ return cd.epoch_ns;
+
+ do {
+ seq = raw_read_seqcount_begin(&cd.seq);
+ epoch_cyc = cd.epoch_cyc;
+ epoch_ns = cd.epoch_ns;
+ } while (read_seqcount_retry(&cd.seq, seq));
+
+ cyc = read_sched_clock();
+ cyc = (cyc - epoch_cyc) & sched_clock_mask;
+ return epoch_ns + cyc_to_ns(cyc, cd.mult, cd.shift);
+}
+
+/*
+ * Atomically update the sched_clock epoch.
+ */
+static void notrace update_sched_clock(void)
+{
+ unsigned long flags;
+ u64 cyc;
+ u64 ns;
+
+ cyc = read_sched_clock();
+ ns = cd.epoch_ns +
+ cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
+ cd.mult, cd.shift);
+
+ raw_local_irq_save(flags);
+ raw_write_seqcount_begin(&cd.seq);
+ cd.epoch_ns = ns;
+ cd.epoch_cyc = cyc;
+ raw_write_seqcount_end(&cd.seq);
+ raw_local_irq_restore(flags);
+}
+
+static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt)
+{
+ update_sched_clock();
+ hrtimer_forward_now(hrt, cd.wrap_kt);
+ return HRTIMER_RESTART;
+}
+
+void __init sched_clock_register(u64 (*read)(void), int bits,
+ unsigned long rate)
+{
+ u64 res, wrap, new_mask, new_epoch, cyc, ns;
+ u32 new_mult, new_shift;
+ ktime_t new_wrap_kt;
+ unsigned long r;
+ char r_unit;
+
+ if (cd.rate > rate)
+ return;
+
+ WARN_ON(!irqs_disabled());
+
+ /* calculate the mult/shift to convert counter ticks to ns. */
+ clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
+
+ new_mask = CLOCKSOURCE_MASK(bits);
+
+ /* calculate how many ns until we wrap */
+ wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask);
+ new_wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
+
+ /* update epoch for new counter and update epoch_ns from old counter*/
+ new_epoch = read();
+ cyc = read_sched_clock();
+ ns = cd.epoch_ns + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
+ cd.mult, cd.shift);
+
+ raw_write_seqcount_begin(&cd.seq);
+ read_sched_clock = read;
+ sched_clock_mask = new_mask;
+ cd.rate = rate;
+ cd.wrap_kt = new_wrap_kt;
+ cd.mult = new_mult;
+ cd.shift = new_shift;
+ cd.epoch_cyc = new_epoch;
+ cd.epoch_ns = ns;
+ raw_write_seqcount_end(&cd.seq);
+
+ r = rate;
+ if (r >= 4000000) {
+ r /= 1000000;
+ r_unit = 'M';
+ } else if (r >= 1000) {
+ r /= 1000;
+ r_unit = 'k';
+ } else
+ r_unit = ' ';
+
+ /* calculate the ns resolution of this counter */
+ res = cyc_to_ns(1ULL, new_mult, new_shift);
+
+ pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
+ bits, r, r_unit, res, wrap);
+
+ /* Enable IRQ time accounting if we have a fast enough sched_clock */
+ if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
+ enable_sched_clock_irqtime();
+
+ pr_debug("Registered %pF as sched_clock source\n", read);
+}
+
+void __init sched_clock_postinit(void)
+{
+ /*
+ * If no sched_clock function has been provided at that point,
+ * make it the final one one.
+ */
+ if (read_sched_clock == jiffy_sched_clock_read)
+ sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ);
+
+ update_sched_clock();
+
+ /*
+ * Start the timer to keep sched_clock() properly updated and
+ * sets the initial epoch.
+ */
+ hrtimer_init(&sched_clock_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ sched_clock_timer.function = sched_clock_poll;
+ hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+}
+
+static int sched_clock_suspend(void)
+{
+ update_sched_clock();
+ hrtimer_cancel(&sched_clock_timer);
+ cd.suspended = true;
+ return 0;
+}
+
+static void sched_clock_resume(void)
+{
+ cd.epoch_cyc = read_sched_clock();
+ hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+ cd.suspended = false;
+}
+
+static struct syscore_ops sched_clock_ops = {
+ .suspend = sched_clock_suspend,
+ .resume = sched_clock_resume,
+};
+
+static int __init sched_clock_syscore_init(void)
+{
+ register_syscore_ops(&sched_clock_ops);
+ return 0;
+}
+device_initcall(sched_clock_syscore_init);
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
new file mode 100644
index 00000000000..eb682d5c697
--- /dev/null
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -0,0 +1,106 @@
+/*
+ * linux/kernel/time/tick-broadcast-hrtimer.c
+ * This file emulates a local clock event device
+ * via a pseudo clock device.
+ */
+#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/clockchips.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+
+#include "tick-internal.h"
+
+static struct hrtimer bctimer;
+
+static void bc_set_mode(enum clock_event_mode mode,
+ struct clock_event_device *bc)
+{
+ switch (mode) {
+ case CLOCK_EVT_MODE_SHUTDOWN:
+ /*
+ * Note, we cannot cancel the timer here as we might
+ * run into the following live lock scenario:
+ *
+ * cpu 0 cpu1
+ * lock(broadcast_lock);
+ * hrtimer_interrupt()
+ * bc_handler()
+ * tick_handle_oneshot_broadcast();
+ * lock(broadcast_lock);
+ * hrtimer_cancel()
+ * wait_for_callback()
+ */
+ hrtimer_try_to_cancel(&bctimer);
+ break;
+ default:
+ break;
+ }
+}
+
+/*
+ * This is called from the guts of the broadcast code when the cpu
+ * which is about to enter idle has the earliest broadcast timer event.
+ */
+static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
+{
+ /*
+ * We try to cancel the timer first. If the callback is on
+ * flight on some other cpu then we let it handle it. If we
+ * were able to cancel the timer nothing can rearm it as we
+ * own broadcast_lock.
+ *
+ * However we can also be called from the event handler of
+ * ce_broadcast_hrtimer itself when it expires. We cannot
+ * restart the timer because we are in the callback, but we
+ * can set the expiry time and let the callback return
+ * HRTIMER_RESTART.
+ */
+ if (hrtimer_try_to_cancel(&bctimer) >= 0) {
+ hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+ /* Bind the "device" to the cpu */
+ bc->bound_on = smp_processor_id();
+ } else if (bc->bound_on == smp_processor_id()) {
+ hrtimer_set_expires(&bctimer, expires);
+ }
+ return 0;
+}
+
+static struct clock_event_device ce_broadcast_hrtimer = {
+ .set_mode = bc_set_mode,
+ .set_next_ktime = bc_set_next,
+ .features = CLOCK_EVT_FEAT_ONESHOT |
+ CLOCK_EVT_FEAT_KTIME |
+ CLOCK_EVT_FEAT_HRTIMER,
+ .rating = 0,
+ .bound_on = -1,
+ .min_delta_ns = 1,
+ .max_delta_ns = KTIME_MAX,
+ .min_delta_ticks = 1,
+ .max_delta_ticks = ULONG_MAX,
+ .mult = 1,
+ .shift = 0,
+ .cpumask = cpu_all_mask,
+};
+
+static enum hrtimer_restart bc_handler(struct hrtimer *t)
+{
+ ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
+
+ if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX)
+ return HRTIMER_NORESTART;
+
+ return HRTIMER_RESTART;
+}
+
+void tick_setup_hrtimer_broadcast(void)
+{
+ hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ bctimer.function = bc_handler;
+ clockevents_register_device(&ce_broadcast_hrtimer);
+}
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 48b2761b566..64c5990fd50 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -18,7 +18,8 @@
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
-#include <linux/tick.h>
+#include <linux/smp.h>
+#include <linux/module.h>
#include "tick-internal.h"
@@ -28,9 +29,9 @@
*/
static struct tick_device tick_broadcast_device;
-/* FIXME: Use cpumask_var_t. */
-static DECLARE_BITMAP(tick_broadcast_mask, NR_CPUS);
-static DECLARE_BITMAP(tmpmask, NR_CPUS);
+static 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;
@@ -50,7 +51,7 @@ struct tick_device *tick_get_broadcast_device(void)
struct cpumask *tick_get_broadcast_mask(void)
{
- return to_cpumask(tick_broadcast_mask);
+ return tick_broadcast_mask;
}
/*
@@ -65,18 +66,50 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc)
/*
* Check, if the device can be utilized as broadcast device:
*/
-int tick_check_broadcast_device(struct clock_event_device *dev)
+static bool tick_check_broadcast_device(struct clock_event_device *curdev,
+ struct clock_event_device *newdev)
{
- if ((tick_broadcast_device.evtdev &&
- tick_broadcast_device.evtdev->rating >= dev->rating) ||
- (dev->features & CLOCK_EVT_FEAT_C3STOP))
- return 0;
+ if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) ||
+ (newdev->features & CLOCK_EVT_FEAT_PERCPU) ||
+ (newdev->features & CLOCK_EVT_FEAT_C3STOP))
+ return false;
+
+ if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT &&
+ !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
+ return false;
+
+ return !curdev || newdev->rating > curdev->rating;
+}
+
+/*
+ * Conditionally install/replace broadcast device
+ */
+void tick_install_broadcast_device(struct clock_event_device *dev)
+{
+ struct clock_event_device *cur = tick_broadcast_device.evtdev;
+
+ if (!tick_check_broadcast_device(cur, dev))
+ return;
- clockevents_exchange_device(NULL, dev);
+ if (!try_module_get(dev->owner))
+ return;
+
+ clockevents_exchange_device(cur, dev);
+ if (cur)
+ cur->event_handler = clockevents_handle_noop;
tick_broadcast_device.evtdev = dev;
- if (!cpumask_empty(tick_get_broadcast_mask()))
+ if (!cpumask_empty(tick_broadcast_mask))
tick_broadcast_start_periodic(dev);
- return 1;
+ /*
+ * 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();
}
/*
@@ -87,14 +120,44 @@ int tick_is_broadcast_device(struct clock_event_device *dev)
return (dev && tick_broadcast_device.evtdev == dev);
}
+int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq)
+{
+ int ret = -ENODEV;
+
+ if (tick_is_broadcast_device(dev)) {
+ raw_spin_lock(&tick_broadcast_lock);
+ ret = __clockevents_update_freq(dev, freq);
+ raw_spin_unlock(&tick_broadcast_lock);
+ }
+ return ret;
+}
+
+
+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 = 0;
+ int ret;
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
@@ -106,26 +169,87 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
*/
if (!tick_device_is_functional(dev)) {
dev->event_handler = tick_handle_periodic;
- cpumask_set_cpu(cpu, tick_get_broadcast_mask());
- tick_broadcast_start_periodic(tick_broadcast_device.evtdev);
+ tick_device_setup_broadcast_func(dev);
+ cpumask_set_cpu(cpu, tick_broadcast_mask);
+ if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
+ tick_broadcast_start_periodic(bc);
+ else
+ tick_broadcast_setup_oneshot(bc);
ret = 1;
} else {
/*
- * When the new device is not affected by the stop
- * feature and the cpu is marked in the broadcast mask
- * then clear the broadcast bit.
+ * Clear the broadcast bit for this cpu if the
+ * device is not power state affected.
*/
- if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) {
- int cpu = smp_processor_id();
+ if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
+ cpumask_clear_cpu(cpu, tick_broadcast_mask);
+ else
+ tick_device_setup_broadcast_func(dev);
- cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
+ /*
+ * 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).
*/
@@ -161,13 +285,8 @@ static void tick_do_broadcast(struct cpumask *mask)
*/
static void tick_do_periodic_broadcast(void)
{
- raw_spin_lock(&tick_broadcast_lock);
-
- cpumask_and(to_cpumask(tmpmask),
- cpu_online_mask, tick_get_broadcast_mask());
- tick_do_broadcast(to_cpumask(tmpmask));
-
- raw_spin_unlock(&tick_broadcast_lock);
+ cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask);
+ tick_do_broadcast(tmpmask);
}
/*
@@ -177,13 +296,15 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
{
ktime_t next;
+ raw_spin_lock(&tick_broadcast_lock);
+
tick_do_periodic_broadcast();
/*
* The device is in periodic mode. No reprogramming necessary:
*/
if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
- return;
+ goto unlock;
/*
* Setup the next period for devices, which do not have
@@ -195,10 +316,12 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
for (next = dev->next_event; ;) {
next = ktime_add(next, tick_period);
- if (!clockevents_program_event(dev, next, ktime_get()))
- return;
+ if (!clockevents_program_event(dev, next, false))
+ goto unlock;
tick_do_periodic_broadcast();
}
+unlock:
+ raw_spin_unlock(&tick_broadcast_lock);
}
/*
@@ -228,13 +351,13 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
if (!tick_device_is_functional(dev))
goto out;
- bc_stopped = cpumask_empty(tick_get_broadcast_mask());
+ bc_stopped = cpumask_empty(tick_broadcast_mask);
switch (*reason) {
case CLOCK_EVT_NOTIFY_BROADCAST_ON:
case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
- if (!cpumask_test_cpu(cpu, tick_get_broadcast_mask())) {
- cpumask_set_cpu(cpu, tick_get_broadcast_mask());
+ 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);
@@ -243,9 +366,12 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
tick_broadcast_force = 1;
break;
case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
- if (!tick_broadcast_force &&
- cpumask_test_cpu(cpu, tick_get_broadcast_mask())) {
- cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
+ if (tick_broadcast_force)
+ break;
+ cpumask_clear_cpu(cpu, tick_broadcast_on);
+ if (!tick_device_is_functional(dev))
+ break;
+ if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) {
if (tick_broadcast_device.mode ==
TICKDEV_MODE_PERIODIC)
tick_setup_periodic(dev, 0);
@@ -253,7 +379,7 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
break;
}
- if (cpumask_empty(tick_get_broadcast_mask())) {
+ if (cpumask_empty(tick_broadcast_mask)) {
if (!bc_stopped)
clockevents_shutdown(bc);
} else if (bc_stopped) {
@@ -302,10 +428,11 @@ void tick_shutdown_broadcast(unsigned int *cpup)
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
bc = tick_broadcast_device.evtdev;
- cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
+ 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_get_broadcast_mask()))
+ if (bc && cpumask_empty(tick_broadcast_mask))
clockevents_shutdown(bc);
}
@@ -341,13 +468,14 @@ int tick_resume_broadcast(void)
switch (tick_broadcast_device.mode) {
case TICKDEV_MODE_PERIODIC:
- if (!cpumask_empty(tick_get_broadcast_mask()))
+ if (!cpumask_empty(tick_broadcast_mask))
tick_broadcast_start_periodic(bc);
broadcast = cpumask_test_cpu(smp_processor_id(),
- tick_get_broadcast_mask());
+ tick_broadcast_mask);
break;
case TICKDEV_MODE_ONESHOT:
- broadcast = tick_resume_broadcast_oneshot(bc);
+ if (!cpumask_empty(tick_broadcast_mask))
+ broadcast = tick_resume_broadcast_oneshot(bc);
break;
}
}
@@ -359,22 +487,58 @@ int tick_resume_broadcast(void)
#ifdef CONFIG_TICK_ONESHOT
-/* FIXME: use cpumask_var_t. */
-static DECLARE_BITMAP(tick_broadcast_oneshot_mask, NR_CPUS);
+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 to_cpumask(tick_broadcast_oneshot_mask);
+ return tick_broadcast_oneshot_mask;
}
-static int tick_broadcast_set_event(ktime_t expires, int force)
+/*
+ * 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)
{
- struct clock_event_device *bc = tick_broadcast_device.evtdev;
+ 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);
- return tick_dev_program_event(bc, expires, force);
+ 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)
@@ -387,12 +551,20 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
* Called from irq_enter() when idle was interrupted to reenable the
* per cpu device.
*/
-void tick_check_oneshot_broadcast(int cpu)
+void tick_check_oneshot_broadcast_this_cpu(void)
{
- if (cpumask_test_cpu(cpu, to_cpumask(tick_broadcast_oneshot_mask))) {
- struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
+ if (cpumask_test_cpu(smp_processor_id(), tick_broadcast_oneshot_mask)) {
+ struct tick_device *td = &__get_cpu_var(tick_cpu_device);
- clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT);
+ /*
+ * We might be in the middle of switching over from
+ * periodic to oneshot. If the CPU has not yet
+ * switched over, leave the device alone.
+ */
+ if (td->mode == TICKDEV_MODE_ONESHOT) {
+ clockevents_set_mode(td->evtdev,
+ CLOCK_EVT_MODE_ONESHOT);
+ }
}
}
@@ -403,27 +575,52 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
{
struct tick_device *td;
ktime_t now, next_event;
- int cpu;
+ 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(to_cpumask(tmpmask));
+ cpumask_clear(tmpmask);
now = ktime_get();
/* Find all expired events */
- for_each_cpu(cpu, tick_get_broadcast_oneshot_mask()) {
+ 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, to_cpumask(tmpmask));
- else if (td->evtdev->next_event.tv64 < next_event.tv64)
+ 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);
+
+ /*
+ * Sanity check. Catch the case where we try to broadcast to
+ * offline cpus.
+ */
+ if (WARN_ON_ONCE(!cpumask_subset(tmpmask, cpu_online_mask)))
+ cpumask_and(tmpmask, tmpmask, cpu_online_mask);
+
+ /*
* Wakeup the cpus which have an expired event.
*/
- tick_do_broadcast(to_cpumask(tmpmask));
+ tick_do_broadcast(tmpmask);
/*
* Two reasons for reprogram:
@@ -440,59 +637,176 @@ again:
* Rearm the broadcast device. If event expired,
* repeat the above
*/
- if (tick_broadcast_set_event(next_event, 0))
+ if (tick_broadcast_set_event(dev, next_cpu, next_event, 0))
goto again;
}
raw_spin_unlock(&tick_broadcast_lock);
}
+static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu)
+{
+ if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER))
+ return 0;
+ if (bc->next_event.tv64 == KTIME_MAX)
+ return 0;
+ return bc->bound_on == cpu ? -EBUSY : 0;
+}
+
+static void broadcast_shutdown_local(struct clock_event_device *bc,
+ struct clock_event_device *dev)
+{
+ /*
+ * For hrtimer based broadcasting we cannot shutdown the cpu
+ * local device if our own event is the first one to expire or
+ * if we own the broadcast timer.
+ */
+ if (bc->features & CLOCK_EVT_FEAT_HRTIMER) {
+ if (broadcast_needs_cpu(bc, smp_processor_id()))
+ return;
+ if (dev->next_event.tv64 < bc->next_event.tv64)
+ return;
+ }
+ clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+}
+
+static void broadcast_move_bc(int deadcpu)
+{
+ struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+ if (!bc || !broadcast_needs_cpu(bc, deadcpu))
+ return;
+ /* This moves the broadcast assignment to this cpu */
+ clockevents_program_event(bc, bc->next_event, 1);
+}
+
/*
* Powerstate information: The system enters/leaves a state, where
* affected devices might stop
+ * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
*/
-void tick_broadcast_oneshot_control(unsigned long reason)
+int tick_broadcast_oneshot_control(unsigned long reason)
{
struct clock_event_device *bc, *dev;
struct tick_device *td;
unsigned long flags;
- int cpu;
-
- raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+ ktime_t now;
+ int cpu, ret = 0;
/*
* Periodic mode does not care about the enter/exit of power
* states
*/
if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
- goto out;
+ return 0;
- bc = tick_broadcast_device.evtdev;
+ /*
+ * 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))
- goto out;
+ return 0;
+ bc = tick_broadcast_device.evtdev;
+
+ raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
- if (!cpumask_test_cpu(cpu, tick_get_broadcast_oneshot_mask())) {
- cpumask_set_cpu(cpu, tick_get_broadcast_oneshot_mask());
- clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
- if (dev->next_event.tv64 < bc->next_event.tv64)
- tick_broadcast_set_event(dev->next_event, 1);
+ if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
+ WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
+ broadcast_shutdown_local(bc, dev);
+ /*
+ * 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);
}
+ /*
+ * If the current CPU owns the hrtimer broadcast
+ * mechanism, it cannot go deep idle and we remove the
+ * CPU from the broadcast mask. We don't have to go
+ * through the EXIT path as the local timer is not
+ * shutdown.
+ */
+ ret = broadcast_needs_cpu(bc, cpu);
+ if (ret)
+ cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
} else {
- if (cpumask_test_cpu(cpu, tick_get_broadcast_oneshot_mask())) {
- cpumask_clear_cpu(cpu,
- tick_get_broadcast_oneshot_mask());
+ if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
- if (dev->next_event.tv64 != KTIME_MAX)
- tick_program_event(dev->next_event, 1);
+ /*
+ * 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);
+ return ret;
}
/*
@@ -502,7 +816,8 @@ out:
*/
static void tick_broadcast_clear_oneshot(int cpu)
{
- cpumask_clear_cpu(cpu, tick_get_broadcast_oneshot_mask());
+ cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
}
static void tick_broadcast_init_next_event(struct cpumask *mask,
@@ -523,16 +838,13 @@ static void tick_broadcast_init_next_event(struct cpumask *mask,
*/
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;
- int cpu = smp_processor_id();
bc->event_handler = tick_handle_oneshot_broadcast;
- clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
-
- /* Take the do_timer update */
- tick_do_timer_cpu = cpu;
/*
* We must be careful here. There might be other CPUs
@@ -540,18 +852,27 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
* oneshot_mask bits for those and program the
* broadcast device to fire.
*/
- cpumask_copy(to_cpumask(tmpmask), tick_get_broadcast_mask());
- cpumask_clear_cpu(cpu, to_cpumask(tmpmask));
- cpumask_or(tick_get_broadcast_oneshot_mask(),
- tick_get_broadcast_oneshot_mask(),
- to_cpumask(tmpmask));
-
- if (was_periodic && !cpumask_empty(to_cpumask(tmpmask))) {
- tick_broadcast_init_next_event(to_cpumask(tmpmask),
+ 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(tick_next_period, 1);
+ 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);
}
}
@@ -569,6 +890,7 @@ void tick_broadcast_switch_to_oneshot(void)
bc = tick_broadcast_device.evtdev;
if (bc)
tick_broadcast_setup_oneshot(bc);
+
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
@@ -584,10 +906,14 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
/*
- * Clear the broadcast mask flag for the dead cpu, but do not
- * stop the broadcast device!
+ * Clear the broadcast masks for the dead cpu, but do not stop
+ * the broadcast device!
*/
- cpumask_clear_cpu(cpu, tick_get_broadcast_oneshot_mask());
+ cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
+
+ broadcast_move_bc(cpu);
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
@@ -600,4 +926,26 @@ 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
+}
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index b6b898d2eee..0a0608edeb2 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -18,7 +18,7 @@
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
-#include <linux/tick.h>
+#include <linux/module.h>
#include <asm/irq_regs.h>
@@ -33,8 +33,22 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
*/
ktime_t tick_next_period;
ktime_t tick_period;
+
+/*
+ * tick_do_timer_cpu is a timer core internal variable which holds the CPU NR
+ * which is responsible for calling do_timer(), i.e. the timekeeping stuff. This
+ * variable has two functions:
+ *
+ * 1) Prevent a thundering herd issue of a gazillion of CPUs trying to grab the
+ * timekeeping lock all at once. Only the CPU which is assigned to do the
+ * update is handling it.
+ *
+ * 2) Hand off the duty in the NOHZ idle case by setting the value to
+ * TICK_DO_TIMER_NONE, i.e. a non existing CPU. So the next cpu which looks
+ * at it will take over and keep the time keeping alive. The handover
+ * procedure also covers cpu hotplug.
+ */
int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
-static DEFINE_RAW_SPINLOCK(tick_device_lock);
/*
* Debugging: see timer_list.c
@@ -49,9 +63,13 @@ struct tick_device *tick_get_device(int cpu)
*/
int tick_is_oneshot_available(void)
{
- struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+ struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
- return dev && (dev->features & CLOCK_EVT_FEAT_ONESHOT);
+ if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+ return 0;
+ if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
+ return 1;
+ return tick_broadcast_oneshot_available();
}
/*
@@ -60,13 +78,14 @@ int tick_is_oneshot_available(void)
static void tick_periodic(int cpu)
{
if (tick_do_timer_cpu == cpu) {
- write_seqlock(&xtime_lock);
+ 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(&xtime_lock);
+ write_sequnlock(&jiffies_lock);
+ update_wall_time();
}
update_process_times(user_mode(get_irq_regs()));
@@ -79,19 +98,20 @@ static void tick_periodic(int cpu)
void tick_handle_periodic(struct clock_event_device *dev)
{
int cpu = smp_processor_id();
- ktime_t next;
+ ktime_t next = dev->next_event;
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, ktime_get()))
+ /*
+ * Setup the next period for devices, which do not have
+ * periodic mode:
+ */
+ next = ktime_add(next, tick_period);
+
+ if (!clockevents_program_event(dev, next, false))
return;
/*
* Have to be careful here. If we're in oneshot mode,
@@ -99,12 +119,11 @@ void tick_handle_periodic(struct clock_event_device *dev)
* 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
+ * which then will increment time, possibly causing
* the loop to trigger again and again.
*/
if (timekeeping_valid_for_hres())
tick_periodic(cpu);
- next = ktime_add(next, tick_period);
}
}
@@ -127,14 +146,14 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
ktime_t next;
do {
- seq = read_seqbegin(&xtime_lock);
+ seq = read_seqbegin(&jiffies_lock);
next = tick_next_period;
- } while (read_seqretry(&xtime_lock, seq));
+ } while (read_seqretry(&jiffies_lock, seq));
clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
for (;;) {
- if (!clockevents_program_event(dev, next, ktime_get()))
+ if (!clockevents_program_event(dev, next, false))
return;
next = ktime_add(next, tick_period);
}
@@ -160,7 +179,10 @@ static void tick_setup_device(struct tick_device *td,
* this cpu:
*/
if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
- tick_do_timer_cpu = cpu;
+ 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);
}
@@ -188,7 +210,8 @@ static void tick_setup_device(struct tick_device *td,
* When global broadcasting is active, check if the current
* device is registered as a placeholder for broadcast mode.
* This allows us to handle this x86 misfeature in a generic
- * way.
+ * way. This function also returns !=0 when we keep the
+ * current active broadcast state for this CPU.
*/
if (tick_device_uses_broadcast(newdev, cpu))
return;
@@ -199,17 +222,75 @@ static void tick_setup_device(struct tick_device *td,
tick_setup_oneshot(newdev, handler, next_event);
}
+void tick_install_replacement(struct clock_event_device *newdev)
+{
+ struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+ int cpu = smp_processor_id();
+
+ clockevents_exchange_device(td->evtdev, newdev);
+ tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
+ if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
+ tick_oneshot_notify();
+}
+
+static bool tick_check_percpu(struct clock_event_device *curdev,
+ struct clock_event_device *newdev, int cpu)
+{
+ if (!cpumask_test_cpu(cpu, newdev->cpumask))
+ return false;
+ if (cpumask_equal(newdev->cpumask, cpumask_of(cpu)))
+ return true;
+ /* Check if irq affinity can be set */
+ if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq))
+ return false;
+ /* Prefer an existing cpu local device */
+ if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
+ return false;
+ return true;
+}
+
+static bool tick_check_preferred(struct clock_event_device *curdev,
+ struct clock_event_device *newdev)
+{
+ /* Prefer oneshot capable device */
+ if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) {
+ if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT))
+ return false;
+ if (tick_oneshot_mode_active())
+ return false;
+ }
+
+ /*
+ * Use the higher rated one, but prefer a CPU local device with a lower
+ * rating than a non-CPU local device
+ */
+ return !curdev ||
+ newdev->rating > curdev->rating ||
+ !cpumask_equal(curdev->cpumask, newdev->cpumask);
+}
+
/*
- * Check, if the new registered device should be used.
+ * Check whether the new device is a better fit than curdev. curdev
+ * can be NULL !
*/
-static int tick_check_new_device(struct clock_event_device *newdev)
+bool tick_check_replacement(struct clock_event_device *curdev,
+ struct clock_event_device *newdev)
+{
+ if (!tick_check_percpu(curdev, newdev, smp_processor_id()))
+ return false;
+
+ return tick_check_preferred(curdev, newdev);
+}
+
+/*
+ * Check, if the new registered device should be used. Called with
+ * clockevents_lock held and interrupts disabled.
+ */
+void tick_check_new_device(struct clock_event_device *newdev)
{
struct clock_event_device *curdev;
struct tick_device *td;
- int cpu, ret = NOTIFY_OK;
- unsigned long flags;
-
- raw_spin_lock_irqsave(&tick_device_lock, flags);
+ int cpu;
cpu = smp_processor_id();
if (!cpumask_test_cpu(cpu, newdev->cpumask))
@@ -219,40 +300,15 @@ static int tick_check_new_device(struct clock_event_device *newdev)
curdev = td->evtdev;
/* cpu local device ? */
- if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) {
-
- /*
- * If the cpu affinity of the device interrupt can not
- * be set, ignore it.
- */
- if (!irq_can_set_affinity(newdev->irq))
- goto out_bc;
+ if (!tick_check_percpu(curdev, newdev, cpu))
+ goto out_bc;
- /*
- * If we have a cpu local device already, do not replace it
- * by a non cpu local device
- */
- if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
- goto out_bc;
- }
+ /* Preference decision */
+ if (!tick_check_preferred(curdev, newdev))
+ goto out_bc;
- /*
- * If we have an active device, then check the rating and the oneshot
- * feature.
- */
- if (curdev) {
- /*
- * Prefer one shot capable devices !
- */
- if ((curdev->features & CLOCK_EVT_FEAT_ONESHOT) &&
- !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
- goto out_bc;
- /*
- * Check the rating
- */
- if (curdev->rating >= newdev->rating)
- goto out_bc;
- }
+ if (!try_module_get(newdev->owner))
+ return;
/*
* Replace the eventually existing device by the new
@@ -267,20 +323,13 @@ static int tick_check_new_device(struct clock_event_device *newdev)
tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
tick_oneshot_notify();
-
- raw_spin_unlock_irqrestore(&tick_device_lock, flags);
- return NOTIFY_STOP;
+ return;
out_bc:
/*
* Can the new device be used as a broadcast device ?
*/
- if (tick_check_broadcast_device(newdev))
- ret = NOTIFY_STOP;
-
- raw_spin_unlock_irqrestore(&tick_device_lock, flags);
-
- return ret;
+ tick_install_broadcast_device(newdev);
}
/*
@@ -288,7 +337,7 @@ out_bc:
*
* Called with interrupts disabled.
*/
-static void tick_handover_do_timer(int *cpup)
+void tick_handover_do_timer(int *cpup)
{
if (*cpup == tick_do_timer_cpu) {
int cpu = cpumask_first(cpu_online_mask);
@@ -305,13 +354,11 @@ static void tick_handover_do_timer(int *cpup)
* access the hardware device itself.
* We just set the mode and remove it from the lists.
*/
-static void tick_shutdown(unsigned int *cpup)
+void tick_shutdown(unsigned int *cpup)
{
struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
struct clock_event_device *dev = td->evtdev;
- unsigned long flags;
- raw_spin_lock_irqsave(&tick_device_lock, flags);
td->mode = TICKDEV_MODE_PERIODIC;
if (dev) {
/*
@@ -320,28 +367,23 @@ static void tick_shutdown(unsigned int *cpup)
*/
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)
+void tick_suspend(void)
{
struct tick_device *td = &__get_cpu_var(tick_cpu_device);
- unsigned long flags;
- raw_spin_lock_irqsave(&tick_device_lock, flags);
clockevents_shutdown(td->evtdev);
- raw_spin_unlock_irqrestore(&tick_device_lock, flags);
}
-static void tick_resume(void)
+void tick_resume(void)
{
struct tick_device *td = &__get_cpu_var(tick_cpu_device);
- unsigned long flags;
int broadcast = tick_resume_broadcast();
- raw_spin_lock_irqsave(&tick_device_lock, flags);
clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME);
if (!broadcast) {
@@ -350,67 +392,12 @@ static void tick_resume(void)
else
tick_resume_oneshot();
}
- raw_spin_unlock_irqrestore(&tick_device_lock, flags);
-}
-
-/*
- * Notification about clock event devices
- */
-static int tick_notify(struct notifier_block *nb, unsigned long reason,
- void *dev)
-{
- switch (reason) {
-
- case CLOCK_EVT_NOTIFY_ADD:
- return tick_check_new_device(dev);
-
- case CLOCK_EVT_NOTIFY_BROADCAST_ON:
- case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
- case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
- tick_broadcast_on_off(reason, dev);
- break;
-
- case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
- case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
- tick_broadcast_oneshot_control(reason);
- break;
-
- case CLOCK_EVT_NOTIFY_CPU_DYING:
- tick_handover_do_timer(dev);
- break;
-
- case CLOCK_EVT_NOTIFY_CPU_DEAD:
- tick_shutdown_broadcast_oneshot(dev);
- tick_shutdown_broadcast(dev);
- tick_shutdown(dev);
- break;
-
- case CLOCK_EVT_NOTIFY_SUSPEND:
- tick_suspend();
- tick_suspend_broadcast();
- break;
-
- case CLOCK_EVT_NOTIFY_RESUME:
- tick_resume();
- break;
-
- default:
- break;
- }
-
- return NOTIFY_OK;
}
-static struct notifier_block tick_notifier = {
- .notifier_call = tick_notify,
-};
-
/**
* tick_init - initialize the tick control
- *
- * Register the notifier with the clockevents framework
*/
void __init tick_init(void)
{
- clockevents_register_notifier(&tick_notifier);
+ tick_broadcast_init();
}
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 290eefbc1f6..7ab92b19965 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -1,6 +1,14 @@
/*
* tick internal variable and functions used by low/high res code
*/
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+
+extern seqlock_t jiffies_lock;
+
+#define CS_NAME_LEN 32
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD
#define TICK_DO_TIMER_NONE -1
#define TICK_DO_TIMER_BOOT -2
@@ -12,9 +20,19 @@ extern int tick_do_timer_cpu __read_mostly;
extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast);
extern void tick_handle_periodic(struct clock_event_device *dev);
+extern void tick_check_new_device(struct clock_event_device *dev);
+extern void tick_handover_do_timer(int *cpup);
+extern void tick_shutdown(unsigned int *cpup);
+extern void tick_suspend(void);
+extern void tick_resume(void);
+extern bool tick_check_replacement(struct clock_event_device *curdev,
+ struct clock_event_device *newdev);
+extern void tick_install_replacement(struct clock_event_device *dev);
extern void clockevents_shutdown(struct clock_event_device *dev);
+extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
+
/*
* NO_HZ / high resolution timer shared code
*/
@@ -22,30 +40,30 @@ extern void clockevents_shutdown(struct clock_event_device *dev);
extern void tick_setup_oneshot(struct clock_event_device *newdev,
void (*handler)(struct clock_event_device *),
ktime_t nextevt);
-extern int tick_dev_program_event(struct clock_event_device *dev,
- ktime_t expires, int force);
extern int tick_program_event(ktime_t expires, int force);
extern void tick_oneshot_notify(void);
extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));
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 int tick_broadcast_oneshot_control(unsigned long reason);
extern void tick_broadcast_switch_to_oneshot(void);
extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
extern int tick_broadcast_oneshot_active(void);
-extern void tick_check_oneshot_broadcast(int cpu);
+extern void tick_check_oneshot_broadcast_this_cpu(void);
+bool tick_broadcast_oneshot_available(void);
# else /* BROADCAST */
static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
{
BUG();
}
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
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 void tick_check_oneshot_broadcast_this_cpu(void) { }
+static inline bool tick_broadcast_oneshot_available(void) { return true; }
# endif /* !BROADCAST */
#else /* !ONESHOT */
@@ -69,13 +87,14 @@ 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 int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
{
return 0;
}
static inline int tick_broadcast_oneshot_active(void) { return 0; }
+static inline bool tick_broadcast_oneshot_available(void) { return false; }
#endif /* !TICK_ONESHOT */
/*
@@ -83,21 +102,21 @@ static inline int tick_broadcast_oneshot_active(void) { return 0; }
*/
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
-extern int tick_check_broadcast_device(struct clock_event_device *dev);
+extern void tick_install_broadcast_device(struct clock_event_device *dev);
extern int tick_is_broadcast_device(struct clock_event_device *dev);
extern void tick_broadcast_on_off(unsigned long reason, int *oncpu);
extern void tick_shutdown_broadcast(unsigned int *cpup);
extern void tick_suspend_broadcast(void);
extern int tick_resume_broadcast(void);
-
+extern void tick_broadcast_init(void);
extern void
tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
+int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq);
#else /* !BROADCAST */
-static inline int tick_check_broadcast_device(struct clock_event_device *dev)
+static inline void tick_install_broadcast_device(struct clock_event_device *dev)
{
- return 0;
}
static inline int tick_is_broadcast_device(struct clock_event_device *dev)
@@ -114,6 +133,9 @@ static inline void tick_broadcast_on_off(unsigned long reason, int *oncpu) { }
static inline void tick_shutdown_broadcast(unsigned int *cpup) { }
static inline void tick_suspend_broadcast(void) { }
static inline int tick_resume_broadcast(void) { return 0; }
+static inline void tick_broadcast_init(void) { }
+static inline int tick_broadcast_update_freq(struct clock_event_device *dev,
+ u32 freq) { return -ENODEV; }
/*
* Set the periodic handler in non broadcast mode
@@ -132,3 +154,10 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
{
return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
}
+
+int __clockevents_update_freq(struct clock_event_device *dev, u32 freq);
+
+#endif
+
+extern void do_timer(unsigned long ticks);
+extern void update_wall_time(void);
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index aada0e52680..824109060a3 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -18,86 +18,17 @@
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
-#include <linux/tick.h>
#include "tick-internal.h"
-/* Limit min_delta to a jiffie */
-#define MIN_DELTA_LIMIT (NSEC_PER_SEC / HZ)
-
-static int tick_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)
- 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;
-}
-
-/**
- * tick_program_event internal worker function
- */
-int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires,
- int force)
-{
- ktime_t now = ktime_get();
- int i;
-
- for (i = 0;;) {
- int ret = clockevents_program_event(dev, expires, now);
-
- if (!ret || !force)
- return ret;
-
- dev->retries++;
- /*
- * We tried 3 times to program the device with the given
- * min_delta_ns. If that's not working then we increase it
- * and emit a warning.
- */
- if (++i > 2) {
- /* Increase the min. delta and try again */
- if (tick_increase_min_delta(dev)) {
- /*
- * Get out of the loop if min_delta_ns
- * hit the limit already. That's
- * better than staying here forever.
- *
- * We clear next_event so we have a
- * chance that the box survives.
- */
- printk(KERN_WARNING
- "CE: Reprogramming failure. Giving up\n");
- dev->next_event.tv64 = KTIME_MAX;
- return -ETIME;
- }
- i = 0;
- }
-
- now = ktime_get();
- expires = ktime_add_ns(now, dev->min_delta_ns);
- }
-}
-
/**
* tick_program_event
*/
int tick_program_event(ktime_t expires, int force)
{
- struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+ struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
- return tick_dev_program_event(dev, expires, force);
+ return clockevents_program_event(dev, expires, force);
}
/**
@@ -105,11 +36,10 @@ int tick_program_event(ktime_t expires, int force)
*/
void tick_resume_oneshot(void)
{
- struct tick_device *td = &__get_cpu_var(tick_cpu_device);
- struct clock_event_device *dev = td->evtdev;
+ struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
- tick_program_event(ktime_get(), 1);
+ clockevents_program_event(dev, ktime_get(), true);
}
/**
@@ -121,7 +51,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev,
{
newdev->event_handler = handler;
clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT);
- tick_dev_program_event(newdev, next_event, 1);
+ clockevents_program_event(newdev, next_event, true);
}
/**
@@ -167,7 +97,7 @@ int tick_oneshot_mode_active(void)
int ret;
local_irq_save(flags);
- ret = __get_cpu_var(tick_cpu_device).mode == TICKDEV_MODE_ONESHOT;
+ ret = __this_cpu_read(tick_cpu_device.mode) == TICKDEV_MODE_ONESHOT;
local_irq_restore(flags);
return ret;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3e216e01bbd..6558b7ac112 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -19,20 +19,25 @@
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
-#include <linux/tick.h>
#include <linux/module.h>
+#include <linux/irq_work.h>
+#include <linux/posix-timers.h>
+#include <linux/perf_event.h>
+#include <linux/context_tracking.h>
#include <asm/irq_regs.h>
#include "tick-internal.h"
+#include <trace/events/timer.h>
+
/*
* Per cpu nohz control structure
*/
-static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
+DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
/*
- * The time, when the last jiffy update happened. Protected by xtime_lock.
+ * The time, when the last jiffy update happened. Protected by jiffies_lock.
*/
static ktime_t last_jiffies_update;
@@ -50,14 +55,14 @@ static void tick_do_update_jiffies64(ktime_t now)
ktime_t delta;
/*
- * Do a quick check without holding xtime_lock:
+ * Do a quick check without holding jiffies_lock:
*/
delta = ktime_sub(now, last_jiffies_update);
if (delta.tv64 < tick_period.tv64)
return;
- /* Reevalute with xtime_lock held */
- write_seqlock(&xtime_lock);
+ /* Reevalute with jiffies_lock held */
+ write_seqlock(&jiffies_lock);
delta = ktime_sub(now, last_jiffies_update);
if (delta.tv64 >= tick_period.tv64) {
@@ -79,8 +84,12 @@ static void tick_do_update_jiffies64(ktime_t now)
/* Keep the tick_next_period variable up to date */
tick_next_period = ktime_add(last_jiffies_update, tick_period);
+ } else {
+ write_sequnlock(&jiffies_lock);
+ return;
}
- write_sequnlock(&xtime_lock);
+ write_sequnlock(&jiffies_lock);
+ update_wall_time();
}
/*
@@ -90,24 +99,274 @@ static ktime_t tick_init_jiffy_update(void)
{
ktime_t period;
- write_seqlock(&xtime_lock);
+ write_seqlock(&jiffies_lock);
/* Did we start the jiffies update yet ? */
if (last_jiffies_update.tv64 == 0)
last_jiffies_update = tick_next_period;
period = last_jiffies_update;
- write_sequnlock(&xtime_lock);
+ write_sequnlock(&jiffies_lock);
return period;
}
+
+static void tick_sched_do_timer(ktime_t now)
+{
+ int cpu = smp_processor_id();
+
+#ifdef CONFIG_NO_HZ_COMMON
+ /*
+ * Check if the do_timer duty was dropped. We don't care about
+ * concurrency: This happens only when the cpu in charge went
+ * into a long sleep. If two cpus happen to assign themself to
+ * this duty, then the jiffies update is still serialized by
+ * jiffies_lock.
+ */
+ if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)
+ && !tick_nohz_full_cpu(cpu))
+ tick_do_timer_cpu = cpu;
+#endif
+
+ /* Check, if the jiffies need an update */
+ if (tick_do_timer_cpu == cpu)
+ tick_do_update_jiffies64(now);
+}
+
+static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
+{
+#ifdef CONFIG_NO_HZ_COMMON
+ /*
+ * When we are idle and the tick is stopped, we have to touch
+ * the watchdog as we might not schedule for a really long
+ * time. This happens on complete idle SMP systems while
+ * waiting on the login prompt. We also increment the "start of
+ * idle" jiffy stamp so the idle accounting adjustment we do
+ * when we go busy again does not account too much ticks.
+ */
+ if (ts->tick_stopped) {
+ touch_softlockup_watchdog();
+ if (is_idle_task(current))
+ ts->idle_jiffies++;
+ }
+#endif
+ update_process_times(user_mode(regs));
+ profile_tick(CPU_PROFILING);
+}
+
+#ifdef CONFIG_NO_HZ_FULL
+cpumask_var_t tick_nohz_full_mask;
+bool tick_nohz_full_running;
+
+static bool can_stop_full_tick(void)
+{
+ WARN_ON_ONCE(!irqs_disabled());
+
+ if (!sched_can_stop_tick()) {
+ trace_tick_stop(0, "more than 1 task in runqueue\n");
+ return false;
+ }
+
+ if (!posix_cpu_timers_can_stop_tick(current)) {
+ trace_tick_stop(0, "posix timers running\n");
+ return false;
+ }
+
+ if (!perf_event_can_stop_tick()) {
+ trace_tick_stop(0, "perf events running\n");
+ return false;
+ }
+
+ /* sched_clock_tick() needs us? */
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+ /*
+ * TODO: kick full dynticks CPUs when
+ * sched_clock_stable is set.
+ */
+ if (!sched_clock_stable()) {
+ trace_tick_stop(0, "unstable sched clock\n");
+ /*
+ * Don't allow the user to think they can get
+ * full NO_HZ with this machine.
+ */
+ WARN_ONCE(tick_nohz_full_running,
+ "NO_HZ FULL will not work with unstable sched clock");
+ return false;
+ }
+#endif
+
+ return true;
+}
+
+static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now);
+
+/*
+ * Re-evaluate the need for the tick on the current CPU
+ * and restart it if necessary.
+ */
+void __tick_nohz_full_check(void)
+{
+ struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+
+ if (tick_nohz_full_cpu(smp_processor_id())) {
+ if (ts->tick_stopped && !is_idle_task(current)) {
+ if (!can_stop_full_tick())
+ tick_nohz_restart_sched_tick(ts, ktime_get());
+ }
+ }
+}
+
+static void nohz_full_kick_work_func(struct irq_work *work)
+{
+ __tick_nohz_full_check();
+}
+
+static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
+ .func = nohz_full_kick_work_func,
+};
+
+/*
+ * Kick the current CPU if it's full dynticks in order to force it to
+ * re-evaluate its dependency on the tick and restart it if necessary.
+ */
+void tick_nohz_full_kick(void)
+{
+ if (tick_nohz_full_cpu(smp_processor_id()))
+ irq_work_queue(&__get_cpu_var(nohz_full_kick_work));
+}
+
+static void nohz_full_kick_ipi(void *info)
+{
+ __tick_nohz_full_check();
+}
+
+/*
+ * Kick all full dynticks CPUs in order to force these to re-evaluate
+ * their dependency on the tick and restart it if necessary.
+ */
+void tick_nohz_full_kick_all(void)
+{
+ if (!tick_nohz_full_running)
+ return;
+
+ preempt_disable();
+ smp_call_function_many(tick_nohz_full_mask,
+ nohz_full_kick_ipi, NULL, false);
+ tick_nohz_full_kick();
+ preempt_enable();
+}
+
+/*
+ * Re-evaluate the need for the tick as we switch the current task.
+ * It might need the tick due to per task/process properties:
+ * perf events, posix cpu timers, ...
+ */
+void __tick_nohz_task_switch(struct task_struct *tsk)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+
+ if (!tick_nohz_full_cpu(smp_processor_id()))
+ goto out;
+
+ if (tick_nohz_tick_stopped() && !can_stop_full_tick())
+ tick_nohz_full_kick();
+
+out:
+ local_irq_restore(flags);
+}
+
+/* Parse the boot-time nohz CPU list from the kernel parameters. */
+static int __init tick_nohz_full_setup(char *str)
+{
+ int cpu;
+
+ alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
+ if (cpulist_parse(str, tick_nohz_full_mask) < 0) {
+ pr_warning("NOHZ: Incorrect nohz_full cpumask\n");
+ return 1;
+ }
+
+ cpu = smp_processor_id();
+ if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
+ pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu);
+ cpumask_clear_cpu(cpu, tick_nohz_full_mask);
+ }
+ tick_nohz_full_running = true;
+
+ return 1;
+}
+__setup("nohz_full=", tick_nohz_full_setup);
+
+static int tick_nohz_cpu_down_callback(struct notifier_block *nfb,
+ unsigned long action,
+ void *hcpu)
+{
+ unsigned int cpu = (unsigned long)hcpu;
+
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_DOWN_PREPARE:
+ /*
+ * If we handle the timekeeping duty for full dynticks CPUs,
+ * we can't safely shutdown that CPU.
+ */
+ if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
+ return NOTIFY_BAD;
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+/*
+ * Worst case string length in chunks of CPU range seems 2 steps
+ * separations: 0,2,4,6,...
+ * This is NR_CPUS + sizeof('\0')
+ */
+static char __initdata nohz_full_buf[NR_CPUS + 1];
+
+static int tick_nohz_init_all(void)
+{
+ int err = -1;
+
+#ifdef CONFIG_NO_HZ_FULL_ALL
+ if (!alloc_cpumask_var(&tick_nohz_full_mask, GFP_KERNEL)) {
+ pr_err("NO_HZ: Can't allocate full dynticks cpumask\n");
+ return err;
+ }
+ err = 0;
+ cpumask_setall(tick_nohz_full_mask);
+ cpumask_clear_cpu(smp_processor_id(), tick_nohz_full_mask);
+ tick_nohz_full_running = true;
+#endif
+ return err;
+}
+
+void __init tick_nohz_init(void)
+{
+ int cpu;
+
+ if (!tick_nohz_full_running) {
+ if (tick_nohz_init_all() < 0)
+ return;
+ }
+
+ for_each_cpu(cpu, tick_nohz_full_mask)
+ context_tracking_cpu_set(cpu);
+
+ cpu_notifier(tick_nohz_cpu_down_callback, 0);
+ cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), tick_nohz_full_mask);
+ pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf);
+}
+#endif
+
/*
* NOHZ - aka dynamic tick functionality
*/
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
/*
* NO HZ enabled ?
*/
static int tick_nohz_enabled __read_mostly = 1;
-
+int tick_nohz_active __read_mostly;
/*
* Enable / Disable tickless mode
*/
@@ -136,12 +395,9 @@ __setup("nohz=", setup_tick_nohz);
*/
static void tick_nohz_update_jiffies(ktime_t now)
{
- int cpu = smp_processor_id();
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
unsigned long flags;
- cpumask_clear_cpu(cpu, nohz_cpu_mask);
- ts->idle_waketime = now;
+ __this_cpu_write(tick_cpu_sched.idle_waketime, now);
local_irq_save(flags);
tick_do_update_jiffies64(now);
@@ -160,9 +416,10 @@ update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_upda
if (ts->idle_active) {
delta = ktime_sub(now, ts->idle_entrytime);
- ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
if (nr_iowait_cpu(cpu) > 0)
ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
+ else
+ ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
ts->idle_entrytime = now;
}
@@ -171,23 +428,17 @@ update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_upda
}
-static void tick_nohz_stop_idle(int cpu, ktime_t now)
+static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
{
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-
- update_ts_time_stats(cpu, ts, now, NULL);
+ update_ts_time_stats(smp_processor_id(), ts, now, NULL);
ts->idle_active = 0;
sched_clock_idle_wakeup_event(0);
}
-static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
+static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
{
- ktime_t now;
-
- now = ktime_get();
-
- update_ts_time_stats(cpu, ts, now, NULL);
+ ktime_t now = ktime_get();
ts->idle_entrytime = now;
ts->idle_active = 1;
@@ -198,11 +449,11 @@ static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
/**
* get_cpu_idle_time_us - get the total idle time of a cpu
* @cpu: CPU number to query
- * @last_update_time: variable to store update time in
+ * @last_update_time: variable to store update time in. Do not update
+ * counters if NULL.
*
* Return the cummulative idle time (since boot) for a given
- * CPU, in microseconds. The idle time returned includes
- * the iowait time (unlike what "top" and co report).
+ * CPU, in microseconds.
*
* This time is measured via accounting rather than sampling,
* and is as accurate as ktime_get() is.
@@ -212,20 +463,35 @@ static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ ktime_t now, idle;
- if (!tick_nohz_enabled)
+ if (!tick_nohz_active)
return -1;
- update_ts_time_stats(cpu, ts, ktime_get(), last_update_time);
+ now = ktime_get();
+ if (last_update_time) {
+ update_ts_time_stats(cpu, ts, now, last_update_time);
+ idle = ts->idle_sleeptime;
+ } else {
+ if (ts->idle_active && !nr_iowait_cpu(cpu)) {
+ ktime_t delta = ktime_sub(now, ts->idle_entrytime);
+
+ idle = ktime_add(ts->idle_sleeptime, delta);
+ } else {
+ idle = ts->idle_sleeptime;
+ }
+ }
+
+ return ktime_to_us(idle);
- return ktime_to_us(ts->idle_sleeptime);
}
EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
-/*
+/**
* get_cpu_iowait_time_us - get the total iowait time of a cpu
* @cpu: CPU number to query
- * @last_update_time: variable to store update time in
+ * @last_update_time: variable to store update time in. Do not update
+ * counters if NULL.
*
* Return the cummulative iowait time (since boot) for a given
* CPU, in microseconds.
@@ -238,106 +504,66 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ ktime_t now, iowait;
- if (!tick_nohz_enabled)
+ if (!tick_nohz_active)
return -1;
- update_ts_time_stats(cpu, ts, ktime_get(), last_update_time);
+ now = ktime_get();
+ if (last_update_time) {
+ update_ts_time_stats(cpu, ts, now, last_update_time);
+ iowait = ts->iowait_sleeptime;
+ } else {
+ if (ts->idle_active && nr_iowait_cpu(cpu) > 0) {
+ ktime_t delta = ktime_sub(now, ts->idle_entrytime);
+
+ iowait = ktime_add(ts->iowait_sleeptime, delta);
+ } else {
+ iowait = ts->iowait_sleeptime;
+ }
+ }
- return ktime_to_us(ts->iowait_sleeptime);
+ return ktime_to_us(iowait);
}
EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
-/**
- * tick_nohz_stop_sched_tick - stop the idle tick from the idle task
- *
- * When the next event is more than a tick into the future, stop the idle tick
- * Called either from the idle loop or from irq_exit() when an idle period was
- * just interrupted by an interrupt which did not cause a reschedule.
- */
-void tick_nohz_stop_sched_tick(int inidle)
+static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
+ ktime_t now, int cpu)
{
- unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
- struct tick_sched *ts;
- ktime_t last_update, expires, now;
+ unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
+ ktime_t last_update, expires, ret = { .tv64 = 0 };
+ unsigned long rcu_delta_jiffies;
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
u64 time_delta;
- int cpu;
-
- local_irq_save(flags);
-
- cpu = smp_processor_id();
- ts = &per_cpu(tick_cpu_sched, cpu);
-
- /*
- * Call to tick_nohz_start_idle stops the last_update_time from being
- * updated. Thus, it must not be called in the event we are called from
- * irq_exit() with the prior state different than idle.
- */
- if (!inidle && !ts->inidle)
- goto end;
-
- /*
- * Set ts->inidle unconditionally. Even if the system did not
- * switch to NOHZ mode the cpu frequency governers rely on the
- * update of the idle time accounting in tick_nohz_start_idle().
- */
- ts->inidle = 1;
-
- now = tick_nohz_start_idle(cpu, ts);
-
- /*
- * If this cpu is offline and it is the one which updates
- * jiffies, then give up the assignment and let it be taken by
- * the cpu which runs the tick timer next. If we don't drop
- * this here the jiffies might be stale and do_timer() never
- * invoked.
- */
- if (unlikely(!cpu_online(cpu))) {
- if (cpu == tick_do_timer_cpu)
- tick_do_timer_cpu = TICK_DO_TIMER_NONE;
- }
-
- if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
- goto end;
-
- if (need_resched())
- goto end;
-
- if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
- static int ratelimit;
- if (ratelimit < 10) {
- printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
- (unsigned int) local_softirq_pending());
- ratelimit++;
- }
- goto end;
- }
+ time_delta = timekeeping_max_deferment();
- ts->idle_calls++;
/* Read jiffies and the time when jiffies were updated last */
do {
- seq = read_seqbegin(&xtime_lock);
+ seq = read_seqbegin(&jiffies_lock);
last_update = last_jiffies_update;
last_jiffies = jiffies;
- time_delta = timekeeping_max_deferment();
- } while (read_seqretry(&xtime_lock, seq));
+ } while (read_seqretry(&jiffies_lock, seq));
- if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
- arch_needs_cpu(cpu)) {
+ if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) ||
+ arch_needs_cpu(cpu) || irq_work_needs_cpu()) {
next_jiffies = last_jiffies + 1;
delta_jiffies = 1;
} else {
/* Get the next timer wheel timer */
next_jiffies = get_next_timer_interrupt(last_jiffies);
delta_jiffies = next_jiffies - last_jiffies;
+ if (rcu_delta_jiffies < delta_jiffies) {
+ next_jiffies = last_jiffies + rcu_delta_jiffies;
+ delta_jiffies = rcu_delta_jiffies;
+ }
}
+
/*
- * Do not stop the tick, if we are only one off
- * or if the cpu is required for rcu
+ * Do not stop the tick, if we are only one off (or less)
+ * or if the cpu is required for RCU:
*/
- if (!ts->tick_stopped && delta_jiffies == 1)
+ if (!ts->tick_stopped && delta_jiffies <= 1)
goto out;
/* Schedule the tick, if we are at least one jiffie off */
@@ -366,6 +592,13 @@ void tick_nohz_stop_sched_tick(int inidle)
time_delta = KTIME_MAX;
}
+#ifdef CONFIG_NO_HZ_FULL
+ if (!ts->inidle) {
+ time_delta = min(time_delta,
+ scheduler_tick_max_deferment());
+ }
+#endif
+
/*
* calculate the expiry time for the next timer wheel
* timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals
@@ -390,13 +623,12 @@ void tick_nohz_stop_sched_tick(int inidle)
else
expires.tv64 = KTIME_MAX;
- if (delta_jiffies > 1)
- cpumask_set_cpu(cpu, nohz_cpu_mask);
-
/* Skip reprogram of event if its not changed */
if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
goto out;
+ ret = expires;
+
/*
* nohz_stop_sched_tick can be called several times before
* the nohz_restart_sched_tick is called. This happens when
@@ -405,19 +637,14 @@ void tick_nohz_stop_sched_tick(int inidle)
* the scheduler tick in nohz_restart_sched_tick.
*/
if (!ts->tick_stopped) {
- select_nohz_load_balancer(1);
+ nohz_balance_enter_idle(cpu);
+ calc_load_enter_idle();
- ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
+ ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
- ts->idle_jiffies = last_jiffies;
- rcu_enter_nohz();
+ trace_tick_stop(1, " ");
}
- ts->idle_sleeps++;
-
- /* Mark expires */
- ts->idle_expires = expires;
-
/*
* If the expiration time == KTIME_MAX, then
* in this case we simply stop the tick timer.
@@ -442,15 +669,162 @@ void tick_nohz_stop_sched_tick(int inidle)
* softirq.
*/
tick_do_update_jiffies64(ktime_get());
- cpumask_clear_cpu(cpu, nohz_cpu_mask);
}
raise_softirq_irqoff(TIMER_SOFTIRQ);
out:
ts->next_jiffies = next_jiffies;
ts->last_jiffies = last_jiffies;
ts->sleep_length = ktime_sub(dev->next_event, now);
-end:
- local_irq_restore(flags);
+
+ return ret;
+}
+
+static void tick_nohz_full_stop_tick(struct tick_sched *ts)
+{
+#ifdef CONFIG_NO_HZ_FULL
+ int cpu = smp_processor_id();
+
+ if (!tick_nohz_full_cpu(cpu) || is_idle_task(current))
+ return;
+
+ if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
+ return;
+
+ if (!can_stop_full_tick())
+ return;
+
+ tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
+#endif
+}
+
+static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
+{
+ /*
+ * If this cpu is offline and it is the one which updates
+ * jiffies, then give up the assignment and let it be taken by
+ * the cpu which runs the tick timer next. If we don't drop
+ * this here the jiffies might be stale and do_timer() never
+ * invoked.
+ */
+ if (unlikely(!cpu_online(cpu))) {
+ if (cpu == tick_do_timer_cpu)
+ tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+ return false;
+ }
+
+ if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) {
+ ts->sleep_length = (ktime_t) { .tv64 = NSEC_PER_SEC/HZ };
+ return false;
+ }
+
+ if (need_resched())
+ return false;
+
+ if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
+ static int ratelimit;
+
+ if (ratelimit < 10 &&
+ (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
+ pr_warn("NOHZ: local_softirq_pending %02x\n",
+ (unsigned int) local_softirq_pending());
+ ratelimit++;
+ }
+ return false;
+ }
+
+ if (tick_nohz_full_enabled()) {
+ /*
+ * Keep the tick alive to guarantee timekeeping progression
+ * if there are full dynticks CPUs around
+ */
+ if (tick_do_timer_cpu == cpu)
+ return false;
+ /*
+ * Boot safety: make sure the timekeeping duty has been
+ * assigned before entering dyntick-idle mode,
+ */
+ if (tick_do_timer_cpu == TICK_DO_TIMER_NONE)
+ return false;
+ }
+
+ return true;
+}
+
+static void __tick_nohz_idle_enter(struct tick_sched *ts)
+{
+ ktime_t now, expires;
+ int cpu = smp_processor_id();
+
+ now = tick_nohz_start_idle(ts);
+
+ if (can_stop_idle_tick(cpu, ts)) {
+ int was_stopped = ts->tick_stopped;
+
+ ts->idle_calls++;
+
+ expires = tick_nohz_stop_sched_tick(ts, now, cpu);
+ if (expires.tv64 > 0LL) {
+ ts->idle_sleeps++;
+ ts->idle_expires = expires;
+ }
+
+ if (!was_stopped && ts->tick_stopped)
+ ts->idle_jiffies = ts->last_jiffies;
+ }
+}
+
+/**
+ * tick_nohz_idle_enter - stop the idle tick from the idle task
+ *
+ * When the next event is more than a tick into the future, stop the idle tick
+ * Called when we start the idle loop.
+ *
+ * The arch is responsible of calling:
+ *
+ * - rcu_idle_enter() after its last use of RCU before the CPU is put
+ * to sleep.
+ * - rcu_idle_exit() before the first use of RCU after the CPU is woken up.
+ */
+void tick_nohz_idle_enter(void)
+{
+ struct tick_sched *ts;
+
+ WARN_ON_ONCE(irqs_disabled());
+
+ /*
+ * Update the idle state in the scheduler domain hierarchy
+ * when tick_nohz_stop_sched_tick() is called from the idle loop.
+ * State will be updated to busy during the first busy tick after
+ * exiting idle.
+ */
+ set_cpu_sd_state_idle();
+
+ local_irq_disable();
+
+ ts = &__get_cpu_var(tick_cpu_sched);
+ ts->inidle = 1;
+ __tick_nohz_idle_enter(ts);
+
+ local_irq_enable();
+}
+EXPORT_SYMBOL_GPL(tick_nohz_idle_enter);
+
+/**
+ * tick_nohz_irq_exit - update next tick event from interrupt exit
+ *
+ * When an interrupt fires while we are idle and it doesn't cause
+ * a reschedule, it may still add, modify or delete a timer, enqueue
+ * an RCU callback, etc...
+ * So we need to re-calculate and reprogram the next tick event.
+ */
+void tick_nohz_irq_exit(void)
+{
+ struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+
+ if (ts->inidle)
+ __tick_nohz_idle_enter(ts);
+ else
+ tick_nohz_full_stop_tick(ts);
}
/**
@@ -468,7 +842,7 @@ ktime_t tick_nohz_get_sleep_length(void)
static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
{
hrtimer_cancel(&ts->sched_timer);
- hrtimer_set_expires(&ts->sched_timer, ts->idle_tick);
+ hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
while (1) {
/* Forward the time to expire in the future */
@@ -485,49 +859,36 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
hrtimer_get_expires(&ts->sched_timer), 0))
break;
}
- /* Update jiffies and reread time */
- tick_do_update_jiffies64(now);
+ /* Reread time and update jiffies */
now = ktime_get();
+ tick_do_update_jiffies64(now);
}
}
-/**
- * tick_nohz_restart_sched_tick - restart the idle tick from the idle task
- *
- * Restart the idle tick when the CPU is woken up from idle
- */
-void tick_nohz_restart_sched_tick(void)
+static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
{
- int cpu = smp_processor_id();
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
- unsigned long ticks;
-#endif
- ktime_t now;
-
- local_irq_disable();
- if (ts->idle_active || (ts->inidle && ts->tick_stopped))
- now = ktime_get();
-
- if (ts->idle_active)
- tick_nohz_stop_idle(cpu, now);
-
- if (!ts->inidle || !ts->tick_stopped) {
- ts->inidle = 0;
- local_irq_enable();
- return;
- }
+ /* Update jiffies first */
+ tick_do_update_jiffies64(now);
+ update_cpu_load_nohz();
- ts->inidle = 0;
+ calc_load_exit_idle();
+ touch_softlockup_watchdog();
+ /*
+ * Cancel the scheduled timer and restore the tick
+ */
+ ts->tick_stopped = 0;
+ ts->idle_exittime = now;
- rcu_exit_nohz();
+ tick_nohz_restart(ts, now);
+}
- /* Update jiffies first */
- select_nohz_load_balancer(0);
- tick_do_update_jiffies64(now);
- cpumask_clear_cpu(cpu, nohz_cpu_mask);
+static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
+{
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+ unsigned long ticks;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+ if (vtime_accounting_enabled())
+ return;
/*
* We stopped the tick in idle. Update process times would miss the
* time we slept as update_process_times does only a 1 tick
@@ -540,18 +901,40 @@ void tick_nohz_restart_sched_tick(void)
if (ticks && ticks < LONG_MAX)
account_idle_ticks(ticks);
#endif
+}
- touch_softlockup_watchdog();
- /*
- * Cancel the scheduled timer and restore the tick
- */
- ts->tick_stopped = 0;
- ts->idle_exittime = now;
+/**
+ * tick_nohz_idle_exit - restart the idle tick from the idle task
+ *
+ * Restart the idle tick when the CPU is woken up from idle
+ * This also exit the RCU extended quiescent state. The CPU
+ * can use RCU again after this function is called.
+ */
+void tick_nohz_idle_exit(void)
+{
+ struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+ ktime_t now;
- tick_nohz_restart(ts, now);
+ local_irq_disable();
+
+ WARN_ON_ONCE(!ts->inidle);
+
+ ts->inidle = 0;
+
+ if (ts->idle_active || ts->tick_stopped)
+ now = ktime_get();
+
+ if (ts->idle_active)
+ tick_nohz_stop_idle(ts, now);
+
+ if (ts->tick_stopped) {
+ tick_nohz_restart_sched_tick(ts, now);
+ tick_nohz_account_idle_ticks(ts);
+ }
local_irq_enable();
}
+EXPORT_SYMBOL_GPL(tick_nohz_idle_exit);
static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now)
{
@@ -566,40 +949,12 @@ static void tick_nohz_handler(struct clock_event_device *dev)
{
struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
struct pt_regs *regs = get_irq_regs();
- int cpu = smp_processor_id();
ktime_t now = ktime_get();
dev->next_event.tv64 = KTIME_MAX;
- /*
- * Check if the do_timer duty was dropped. We don't care about
- * concurrency: This happens only when the cpu in charge went
- * into a long sleep. If two cpus happen to assign themself to
- * this duty, then the jiffies update is still serialized by
- * xtime_lock.
- */
- if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
- tick_do_timer_cpu = cpu;
-
- /* Check, if the jiffies need an update */
- if (tick_do_timer_cpu == cpu)
- tick_do_update_jiffies64(now);
-
- /*
- * When we are idle and the tick is stopped, we have to touch
- * the watchdog as we might not schedule for a really long
- * time. This happens on complete idle SMP systems while
- * waiting on the login prompt. We also increment the "start
- * of idle" jiffy stamp so the idle accounting adjustment we
- * do when we go busy again does not account too much ticks.
- */
- if (ts->tick_stopped) {
- touch_softlockup_watchdog();
- ts->idle_jiffies++;
- }
-
- update_process_times(user_mode(regs));
- profile_tick(CPU_PROFILING);
+ tick_sched_do_timer(now);
+ tick_sched_handle(ts, regs);
while (tick_nohz_reprogram(ts, now)) {
now = ktime_get();
@@ -623,7 +978,7 @@ static void tick_nohz_switch_to_nohz(void)
local_irq_enable();
return;
}
-
+ tick_nohz_active = 1;
ts->nohz_mode = NOHZ_MODE_LOWRES;
/*
@@ -641,9 +996,6 @@ static void tick_nohz_switch_to_nohz(void)
next = ktime_add(next, tick_period);
}
local_irq_enable();
-
- printk(KERN_INFO "Switched to NOHz mode on CPU #%d\n",
- smp_processor_id());
}
/*
@@ -657,12 +1009,10 @@ static void tick_nohz_switch_to_nohz(void)
* timer and do not touch the other magic bits which need to be done
* when idle is left.
*/
-static void tick_nohz_kick_tick(int cpu, ktime_t now)
+static void tick_nohz_kick_tick(struct tick_sched *ts, ktime_t now)
{
#if 0
/* Switch back to 2.6.27 behaviour */
-
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
ktime_t delta;
/*
@@ -677,36 +1027,36 @@ static void tick_nohz_kick_tick(int cpu, ktime_t now)
#endif
}
-static inline void tick_check_nohz(int cpu)
+static inline void tick_nohz_irq_enter(void)
{
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
ktime_t now;
if (!ts->idle_active && !ts->tick_stopped)
return;
now = ktime_get();
if (ts->idle_active)
- tick_nohz_stop_idle(cpu, now);
+ tick_nohz_stop_idle(ts, now);
if (ts->tick_stopped) {
tick_nohz_update_jiffies(now);
- tick_nohz_kick_tick(cpu, now);
+ tick_nohz_kick_tick(ts, now);
}
}
#else
static inline void tick_nohz_switch_to_nohz(void) { }
-static inline void tick_check_nohz(int cpu) { }
+static inline void tick_nohz_irq_enter(void) { }
-#endif /* NO_HZ */
+#endif /* CONFIG_NO_HZ_COMMON */
/*
* Called from irq_enter to notify about the possible interruption of idle()
*/
-void tick_check_idle(int cpu)
+void tick_irq_enter(void)
{
- tick_check_oneshot_broadcast(cpu);
- tick_check_nohz(cpu);
+ tick_check_oneshot_broadcast_this_cpu();
+ tick_nohz_irq_enter();
}
/*
@@ -715,7 +1065,7 @@ void tick_check_idle(int cpu)
#ifdef CONFIG_HIGH_RES_TIMERS
/*
* We rearm the timer until we get disabled by the idle code.
- * Called with interrupts disabled and timer->base->cpu_base->lock held.
+ * Called with interrupts disabled.
*/
static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
{
@@ -723,50 +1073,31 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
container_of(timer, struct tick_sched, sched_timer);
struct pt_regs *regs = get_irq_regs();
ktime_t now = ktime_get();
- int cpu = smp_processor_id();
-#ifdef CONFIG_NO_HZ
- /*
- * Check if the do_timer duty was dropped. We don't care about
- * concurrency: This happens only when the cpu in charge went
- * into a long sleep. If two cpus happen to assign themself to
- * this duty, then the jiffies update is still serialized by
- * xtime_lock.
- */
- if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
- tick_do_timer_cpu = cpu;
-#endif
-
- /* Check, if the jiffies need an update */
- if (tick_do_timer_cpu == cpu)
- tick_do_update_jiffies64(now);
+ tick_sched_do_timer(now);
/*
* Do not call, when we are not in irq context and have
* no valid regs pointer
*/
- if (regs) {
- /*
- * When we are idle and the tick is stopped, we have to touch
- * the watchdog as we might not schedule for a really long
- * time. This happens on complete idle SMP systems while
- * waiting on the login prompt. We also increment the "start of
- * idle" jiffy stamp so the idle accounting adjustment we do
- * when we go busy again does not account too much ticks.
- */
- if (ts->tick_stopped) {
- touch_softlockup_watchdog();
- ts->idle_jiffies++;
- }
- update_process_times(user_mode(regs));
- profile_tick(CPU_PROFILING);
- }
+ if (regs)
+ tick_sched_handle(ts, regs);
hrtimer_forward(timer, now, tick_period);
return HRTIMER_RESTART;
}
+static int sched_skew_tick;
+
+static int __init skew_tick(char *str)
+{
+ get_option(&str, &sched_skew_tick);
+
+ return 0;
+}
+early_param("skew_tick", skew_tick);
+
/**
* tick_setup_sched_timer - setup the tick emulation timer
*/
@@ -784,6 +1115,14 @@ void tick_setup_sched_timer(void)
/* Get the next period (per cpu) */
hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
+ /* Offset the tick to avert jiffies_lock contention. */
+ if (sched_skew_tick) {
+ u64 offset = ktime_to_ns(tick_period) >> 1;
+ do_div(offset, num_possible_cpus());
+ offset *= smp_processor_id();
+ hrtimer_add_expires_ns(&ts->sched_timer, offset);
+ }
+
for (;;) {
hrtimer_forward(&ts->sched_timer, now, tick_period);
hrtimer_start_expires(&ts->sched_timer,
@@ -794,14 +1133,16 @@ void tick_setup_sched_timer(void)
now = ktime_get();
}
-#ifdef CONFIG_NO_HZ
- if (tick_nohz_enabled)
+#ifdef CONFIG_NO_HZ_COMMON
+ if (tick_nohz_enabled) {
ts->nohz_mode = NOHZ_MODE_HIGHRES;
+ tick_nohz_active = 1;
+ }
#endif
}
#endif /* HIGH_RES_TIMERS */
-#if defined CONFIG_NO_HZ || defined CONFIG_HIGH_RES_TIMERS
+#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS
void tick_cancel_sched_timer(int cpu)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
@@ -811,7 +1152,7 @@ void tick_cancel_sched_timer(int cpu)
hrtimer_cancel(&ts->sched_timer);
# endif
- ts->nohz_mode = NOHZ_MODE_INACTIVE;
+ memset(ts, 0, sizeof(*ts));
}
#endif
diff --git a/kernel/time/timecompare.c b/kernel/time/timecompare.c
deleted file mode 100644
index ac38fbb176c..00000000000
--- a/kernel/time/timecompare.c
+++ /dev/null
@@ -1,192 +0,0 @@
-/*
- * Copyright (C) 2009 Intel Corporation.
- * Author: Patrick Ohly <patrick.ohly@intel.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/timecompare.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/math64.h>
-
-/*
- * fixed point arithmetic scale factor for skew
- *
- * Usually one would measure skew in ppb (parts per billion, 1e9), but
- * using a factor of 2 simplifies the math.
- */
-#define TIMECOMPARE_SKEW_RESOLUTION (((s64)1)<<30)
-
-ktime_t timecompare_transform(struct timecompare *sync,
- u64 source_tstamp)
-{
- u64 nsec;
-
- nsec = source_tstamp + sync->offset;
- nsec += (s64)(source_tstamp - sync->last_update) * sync->skew /
- TIMECOMPARE_SKEW_RESOLUTION;
-
- return ns_to_ktime(nsec);
-}
-EXPORT_SYMBOL_GPL(timecompare_transform);
-
-int timecompare_offset(struct timecompare *sync,
- s64 *offset,
- u64 *source_tstamp)
-{
- u64 start_source = 0, end_source = 0;
- struct {
- s64 offset;
- s64 duration_target;
- } buffer[10], sample, *samples;
- int counter = 0, i;
- int used;
- int index;
- int num_samples = sync->num_samples;
-
- if (num_samples > sizeof(buffer)/sizeof(buffer[0])) {
- samples = kmalloc(sizeof(*samples) * num_samples, GFP_ATOMIC);
- if (!samples) {
- samples = buffer;
- num_samples = sizeof(buffer)/sizeof(buffer[0]);
- }
- } else {
- samples = buffer;
- }
-
- /* run until we have enough valid samples, but do not try forever */
- i = 0;
- counter = 0;
- while (1) {
- u64 ts;
- ktime_t start, end;
-
- start = sync->target();
- ts = timecounter_read(sync->source);
- end = sync->target();
-
- if (!i)
- start_source = ts;
-
- /* ignore negative durations */
- sample.duration_target = ktime_to_ns(ktime_sub(end, start));
- if (sample.duration_target >= 0) {
- /*
- * assume symetric delay to and from source:
- * average target time corresponds to measured
- * source time
- */
- sample.offset =
- (ktime_to_ns(end) + ktime_to_ns(start)) / 2 -
- ts;
-
- /* simple insertion sort based on duration */
- index = counter - 1;
- while (index >= 0) {
- if (samples[index].duration_target <
- sample.duration_target)
- break;
- samples[index + 1] = samples[index];
- index--;
- }
- samples[index + 1] = sample;
- counter++;
- }
-
- i++;
- if (counter >= num_samples || i >= 100000) {
- end_source = ts;
- break;
- }
- }
-
- *source_tstamp = (end_source + start_source) / 2;
-
- /* remove outliers by only using 75% of the samples */
- used = counter * 3 / 4;
- if (!used)
- used = counter;
- if (used) {
- /* calculate average */
- s64 off = 0;
- for (index = 0; index < used; index++)
- off += samples[index].offset;
- *offset = div_s64(off, used);
- }
-
- if (samples && samples != buffer)
- kfree(samples);
-
- return used;
-}
-EXPORT_SYMBOL_GPL(timecompare_offset);
-
-void __timecompare_update(struct timecompare *sync,
- u64 source_tstamp)
-{
- s64 offset;
- u64 average_time;
-
- if (!timecompare_offset(sync, &offset, &average_time))
- return;
-
- if (!sync->last_update) {
- sync->last_update = average_time;
- sync->offset = offset;
- sync->skew = 0;
- } else {
- s64 delta_nsec = average_time - sync->last_update;
-
- /* avoid division by negative or small deltas */
- if (delta_nsec >= 10000) {
- s64 delta_offset_nsec = offset - sync->offset;
- s64 skew; /* delta_offset_nsec *
- TIMECOMPARE_SKEW_RESOLUTION /
- delta_nsec */
- u64 divisor;
-
- /* div_s64() is limited to 32 bit divisor */
- skew = delta_offset_nsec * TIMECOMPARE_SKEW_RESOLUTION;
- divisor = delta_nsec;
- while (unlikely(divisor >= ((s64)1) << 32)) {
- /* divide both by 2; beware, right shift
- of negative value has undefined
- behavior and can only be used for
- the positive divisor */
- skew = div_s64(skew, 2);
- divisor >>= 1;
- }
- skew = div_s64(skew, divisor);
-
- /*
- * Calculate new overall skew as 4/16 the
- * old value and 12/16 the new one. This is
- * a rather arbitrary tradeoff between
- * only using the latest measurement (0/16 and
- * 16/16) and even more weight on past measurements.
- */
-#define TIMECOMPARE_NEW_SKEW_PER_16 12
- sync->skew =
- div_s64((16 - TIMECOMPARE_NEW_SKEW_PER_16) *
- sync->skew +
- TIMECOMPARE_NEW_SKEW_PER_16 * skew,
- 16);
- sync->last_update = average_time;
- sync->offset = offset;
- }
- }
-}
-EXPORT_SYMBOL_GPL(__timecompare_update);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 49010d822f7..32d8d6aaedb 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -8,50 +8,92 @@
*
*/
+#include <linux/timekeeper_internal.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/sched.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/clocksource.h>
#include <linux/jiffies.h>
#include <linux/time.h>
#include <linux/tick.h>
#include <linux/stop_machine.h>
+#include <linux/pvclock_gtod.h>
+#include <linux/compiler.h>
-/* Structure holding internal timekeeping values. */
-struct timekeeper {
- /* Current clocksource used for timekeeping. */
- struct clocksource *clock;
- /* The shift value of the current clocksource. */
- int shift;
-
- /* Number of clock cycles in one NTP interval. */
- cycle_t cycle_interval;
- /* Number of clock shifted nano seconds in one NTP interval. */
- u64 xtime_interval;
- /* Raw nano seconds accumulated per NTP interval. */
- u32 raw_interval;
-
- /* Clock shifted nano seconds remainder not stored in xtime.tv_nsec. */
- u64 xtime_nsec;
- /* Difference between accumulated time and NTP time in ntp
- * shifted nano seconds. */
- s64 ntp_error;
- /* Shift conversion between clock shifted nano seconds and
- * ntp shifted nano seconds. */
- int ntp_error_shift;
- /* NTP adjusted clock multiplier */
- u32 mult;
-};
+#include "tick-internal.h"
+#include "ntp_internal.h"
+#include "timekeeping_internal.h"
+
+#define TK_CLEAR_NTP (1 << 0)
+#define TK_MIRROR (1 << 1)
+#define TK_CLOCK_WAS_SET (1 << 2)
+
+static struct timekeeper timekeeper;
+static DEFINE_RAW_SPINLOCK(timekeeper_lock);
+static seqcount_t timekeeper_seq;
+static struct timekeeper shadow_timekeeper;
+
+/* flag for if timekeeping is suspended */
+int __read_mostly timekeeping_suspended;
-struct timekeeper timekeeper;
+/* Flag for if there is a persistent clock on this platform */
+bool __read_mostly persistent_clock_exist = false;
+
+static inline void tk_normalize_xtime(struct timekeeper *tk)
+{
+ while (tk->xtime_nsec >= ((u64)NSEC_PER_SEC << tk->shift)) {
+ tk->xtime_nsec -= (u64)NSEC_PER_SEC << tk->shift;
+ tk->xtime_sec++;
+ }
+}
+
+static void tk_set_xtime(struct timekeeper *tk, const struct timespec *ts)
+{
+ tk->xtime_sec = ts->tv_sec;
+ tk->xtime_nsec = (u64)ts->tv_nsec << tk->shift;
+}
+
+static void tk_xtime_add(struct timekeeper *tk, const struct timespec *ts)
+{
+ tk->xtime_sec += ts->tv_sec;
+ tk->xtime_nsec += (u64)ts->tv_nsec << tk->shift;
+ tk_normalize_xtime(tk);
+}
+
+static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm)
+{
+ struct timespec tmp;
+
+ /*
+ * Verify consistency of: offset_real = -wall_to_monotonic
+ * before modifying anything
+ */
+ set_normalized_timespec(&tmp, -tk->wall_to_monotonic.tv_sec,
+ -tk->wall_to_monotonic.tv_nsec);
+ WARN_ON_ONCE(tk->offs_real.tv64 != timespec_to_ktime(tmp).tv64);
+ tk->wall_to_monotonic = wtm;
+ set_normalized_timespec(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
+ tk->offs_real = timespec_to_ktime(tmp);
+ tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0));
+}
+
+static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
+{
+ /* Verify consistency before modifying */
+ WARN_ON_ONCE(tk->offs_boot.tv64 != timespec_to_ktime(tk->total_sleep_time).tv64);
+
+ tk->total_sleep_time = t;
+ tk->offs_boot = timespec_to_ktime(t);
+}
/**
- * timekeeper_setup_internals - Set up internals to use clocksource clock.
+ * tk_setup_internals - Set up internals to use clocksource clock.
*
+ * @tk: The target timekeeper to setup.
* @clock: Pointer to clocksource.
*
* Calculates a fixed cycle/nsec interval for a given clocksource/adjustment
@@ -59,119 +101,164 @@ struct timekeeper timekeeper;
*
* Unless you're the timekeeping code, you should not be using this!
*/
-static void timekeeper_setup_internals(struct clocksource *clock)
+static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
{
cycle_t interval;
- u64 tmp;
+ u64 tmp, ntpinterval;
+ struct clocksource *old_clock;
- timekeeper.clock = clock;
- clock->cycle_last = clock->read(clock);
+ old_clock = tk->clock;
+ tk->clock = clock;
+ tk->cycle_last = clock->cycle_last = clock->read(clock);
/* Do the ns -> cycle conversion first, using original mult */
tmp = NTP_INTERVAL_LENGTH;
tmp <<= clock->shift;
+ ntpinterval = tmp;
tmp += clock->mult/2;
do_div(tmp, clock->mult);
if (tmp == 0)
tmp = 1;
interval = (cycle_t) tmp;
- timekeeper.cycle_interval = interval;
+ tk->cycle_interval = interval;
/* Go back from cycles -> shifted ns */
- timekeeper.xtime_interval = (u64) interval * clock->mult;
- timekeeper.raw_interval =
+ tk->xtime_interval = (u64) interval * clock->mult;
+ tk->xtime_remainder = ntpinterval - tk->xtime_interval;
+ tk->raw_interval =
((u64) interval * clock->mult) >> clock->shift;
- timekeeper.xtime_nsec = 0;
- timekeeper.shift = clock->shift;
+ /* if changing clocks, convert xtime_nsec shift units */
+ if (old_clock) {
+ int shift_change = clock->shift - old_clock->shift;
+ if (shift_change < 0)
+ tk->xtime_nsec >>= -shift_change;
+ else
+ tk->xtime_nsec <<= shift_change;
+ }
+ tk->shift = clock->shift;
- timekeeper.ntp_error = 0;
- timekeeper.ntp_error_shift = NTP_SCALE_SHIFT - clock->shift;
+ tk->ntp_error = 0;
+ tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift;
/*
* The timekeeper keeps its own mult values for the currently
* active clocksource. These value will be adjusted via NTP
* to counteract clock drifting.
*/
- timekeeper.mult = clock->mult;
+ tk->mult = clock->mult;
}
/* Timekeeper helper functions. */
-static inline s64 timekeeping_get_ns(void)
+
+#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
+u32 (*arch_gettimeoffset)(void);
+
+u32 get_arch_timeoffset(void)
+{
+ if (likely(arch_gettimeoffset))
+ return arch_gettimeoffset();
+ return 0;
+}
+#else
+static inline u32 get_arch_timeoffset(void) { return 0; }
+#endif
+
+static inline s64 timekeeping_get_ns(struct timekeeper *tk)
{
cycle_t cycle_now, cycle_delta;
struct clocksource *clock;
+ s64 nsec;
/* read clocksource: */
- clock = timekeeper.clock;
+ clock = tk->clock;
cycle_now = clock->read(clock);
/* calculate the delta since the last update_wall_time: */
cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
- /* return delta convert to nanoseconds using ntp adjusted mult. */
- return clocksource_cyc2ns(cycle_delta, timekeeper.mult,
- timekeeper.shift);
+ nsec = cycle_delta * tk->mult + tk->xtime_nsec;
+ nsec >>= tk->shift;
+
+ /* If arch requires, add in get_arch_timeoffset() */
+ return nsec + get_arch_timeoffset();
}
-static inline s64 timekeeping_get_ns_raw(void)
+static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
{
cycle_t cycle_now, cycle_delta;
struct clocksource *clock;
+ s64 nsec;
/* read clocksource: */
- clock = timekeeper.clock;
+ clock = tk->clock;
cycle_now = clock->read(clock);
/* calculate the delta since the last update_wall_time: */
cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
- /* return delta convert to nanoseconds using ntp adjusted mult. */
- return clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
+ /* convert delta to nanoseconds. */
+ nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
+
+ /* If arch requires, add in get_arch_timeoffset() */
+ return nsec + get_arch_timeoffset();
}
-/*
- * This read-write spinlock protects us from races in SMP while
- * playing with xtime.
- */
-__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
+static RAW_NOTIFIER_HEAD(pvclock_gtod_chain);
+static void update_pvclock_gtod(struct timekeeper *tk, bool was_set)
+{
+ raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk);
+}
-/*
- * The current time
- * wall_to_monotonic is what we need to add to xtime (or xtime corrected
- * for sub jiffie times) to get to monotonic time. Monotonic is pegged
- * at zero at system boot time, so wall_to_monotonic will be negative,
- * however, we will ALWAYS keep the tv_nsec part positive so we can use
- * the usual normalization.
- *
- * wall_to_monotonic is moved after resume from suspend for the monotonic
- * time not to jump. We need to add total_sleep_time to wall_to_monotonic
- * to get the real boot based time offset.
- *
- * - wall_to_monotonic is no longer the boot time, getboottime must be
- * used instead.
+/**
+ * pvclock_gtod_register_notifier - register a pvclock timedata update listener
*/
-static struct timespec xtime __attribute__ ((aligned (16)));
-static struct timespec wall_to_monotonic __attribute__ ((aligned (16)));
-static struct timespec total_sleep_time;
+int pvclock_gtod_register_notifier(struct notifier_block *nb)
+{
+ struct timekeeper *tk = &timekeeper;
+ unsigned long flags;
+ int ret;
-/*
- * The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock.
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb);
+ update_pvclock_gtod(tk, true);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier);
+
+/**
+ * pvclock_gtod_unregister_notifier - unregister a pvclock
+ * timedata update listener
*/
-struct timespec raw_time;
+int pvclock_gtod_unregister_notifier(struct notifier_block *nb)
+{
+ unsigned long flags;
+ int ret;
-/* flag for if timekeeping is suspended */
-int __read_mostly timekeeping_suspended;
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
-/* must hold xtime_lock */
-void timekeeping_leap_insert(int leapsecond)
+/* must hold timekeeper_lock */
+static void timekeeping_update(struct timekeeper *tk, unsigned int action)
{
- xtime.tv_sec += leapsecond;
- wall_to_monotonic.tv_sec -= leapsecond;
- update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
- timekeeper.mult);
+ if (action & TK_CLEAR_NTP) {
+ tk->ntp_error = 0;
+ ntp_clear();
+ }
+ update_vsyscall(tk);
+ update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);
+
+ if (action & TK_MIRROR)
+ memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper));
}
/**
@@ -181,72 +268,88 @@ void timekeeping_leap_insert(int leapsecond)
* update_wall_time(). This is useful before significant clock changes,
* as it avoids having to deal with this time offset explicitly.
*/
-static void timekeeping_forward_now(void)
+static void timekeeping_forward_now(struct timekeeper *tk)
{
cycle_t cycle_now, cycle_delta;
struct clocksource *clock;
s64 nsec;
- clock = timekeeper.clock;
+ clock = tk->clock;
cycle_now = clock->read(clock);
cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
- clock->cycle_last = cycle_now;
+ tk->cycle_last = clock->cycle_last = cycle_now;
- nsec = clocksource_cyc2ns(cycle_delta, timekeeper.mult,
- timekeeper.shift);
+ tk->xtime_nsec += cycle_delta * tk->mult;
- /* If arch requires, add in gettimeoffset() */
- nsec += arch_gettimeoffset();
+ /* If arch requires, add in get_arch_timeoffset() */
+ tk->xtime_nsec += (u64)get_arch_timeoffset() << tk->shift;
- timespec_add_ns(&xtime, nsec);
+ tk_normalize_xtime(tk);
nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
- timespec_add_ns(&raw_time, nsec);
+ timespec_add_ns(&tk->raw_time, nsec);
}
/**
- * getnstimeofday - Returns the time of day in a timespec
+ * __getnstimeofday - Returns the time of day in a timespec.
* @ts: pointer to the timespec to be set
*
- * Returns the time of day in a timespec.
+ * Updates the time of day in the timespec.
+ * Returns 0 on success, or -ve when suspended (timespec will be undefined).
*/
-void getnstimeofday(struct timespec *ts)
+int __getnstimeofday(struct timespec *ts)
{
+ struct timekeeper *tk = &timekeeper;
unsigned long seq;
- s64 nsecs;
-
- WARN_ON(timekeeping_suspended);
+ s64 nsecs = 0;
do {
- seq = read_seqbegin(&xtime_lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
- *ts = xtime;
- nsecs = timekeeping_get_ns();
+ ts->tv_sec = tk->xtime_sec;
+ nsecs = timekeeping_get_ns(tk);
- /* If arch requires, add in gettimeoffset() */
- nsecs += arch_gettimeoffset();
-
- } while (read_seqretry(&xtime_lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
+ ts->tv_nsec = 0;
timespec_add_ns(ts, nsecs);
+
+ /*
+ * Do not bail out early, in case there were callers still using
+ * the value, even in the face of the WARN_ON.
+ */
+ if (unlikely(timekeeping_suspended))
+ return -EAGAIN;
+ return 0;
}
+EXPORT_SYMBOL(__getnstimeofday);
+/**
+ * getnstimeofday - Returns the time of day in a timespec.
+ * @ts: pointer to the timespec to be set
+ *
+ * Returns the time of day in a timespec (WARN if suspended).
+ */
+void getnstimeofday(struct timespec *ts)
+{
+ WARN_ON(__getnstimeofday(ts));
+}
EXPORT_SYMBOL(getnstimeofday);
ktime_t ktime_get(void)
{
+ struct timekeeper *tk = &timekeeper;
unsigned int seq;
s64 secs, nsecs;
WARN_ON(timekeeping_suspended);
do {
- seq = read_seqbegin(&xtime_lock);
- secs = xtime.tv_sec + wall_to_monotonic.tv_sec;
- nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec;
- nsecs += timekeeping_get_ns();
+ seq = read_seqcount_begin(&timekeeper_seq);
+ secs = tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
+ nsecs = timekeeping_get_ns(tk) + tk->wall_to_monotonic.tv_nsec;
- } while (read_seqretry(&xtime_lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
/*
* Use ktime_set/ktime_add_ns to create a proper ktime on
* 32-bit architectures without CONFIG_KTIME_SCALAR.
@@ -265,25 +368,109 @@ EXPORT_SYMBOL_GPL(ktime_get);
*/
void ktime_get_ts(struct timespec *ts)
{
+ struct timekeeper *tk = &timekeeper;
struct timespec tomono;
+ s64 nsec;
unsigned int seq;
- s64 nsecs;
WARN_ON(timekeeping_suspended);
do {
- seq = read_seqbegin(&xtime_lock);
- *ts = xtime;
- tomono = wall_to_monotonic;
- nsecs = timekeeping_get_ns();
+ seq = read_seqcount_begin(&timekeeper_seq);
+ ts->tv_sec = tk->xtime_sec;
+ nsec = timekeeping_get_ns(tk);
+ tomono = tk->wall_to_monotonic;
- } while (read_seqretry(&xtime_lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
- set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec,
- ts->tv_nsec + tomono.tv_nsec + nsecs);
+ ts->tv_sec += tomono.tv_sec;
+ ts->tv_nsec = 0;
+ timespec_add_ns(ts, nsec + tomono.tv_nsec);
}
EXPORT_SYMBOL_GPL(ktime_get_ts);
+
+/**
+ * timekeeping_clocktai - Returns the TAI time of day in a timespec
+ * @ts: pointer to the timespec to be set
+ *
+ * Returns the time of day in a timespec.
+ */
+void timekeeping_clocktai(struct timespec *ts)
+{
+ struct timekeeper *tk = &timekeeper;
+ unsigned long seq;
+ u64 nsecs;
+
+ WARN_ON(timekeeping_suspended);
+
+ do {
+ seq = read_seqcount_begin(&timekeeper_seq);
+
+ ts->tv_sec = tk->xtime_sec + tk->tai_offset;
+ nsecs = timekeeping_get_ns(tk);
+
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
+
+ ts->tv_nsec = 0;
+ timespec_add_ns(ts, nsecs);
+
+}
+EXPORT_SYMBOL(timekeeping_clocktai);
+
+
+/**
+ * ktime_get_clocktai - Returns the TAI time of day in a ktime
+ *
+ * Returns the time of day in a ktime.
+ */
+ktime_t ktime_get_clocktai(void)
+{
+ struct timespec ts;
+
+ timekeeping_clocktai(&ts);
+ return timespec_to_ktime(ts);
+}
+EXPORT_SYMBOL(ktime_get_clocktai);
+
+#ifdef CONFIG_NTP_PPS
+
+/**
+ * getnstime_raw_and_real - get day and raw monotonic time in timespec format
+ * @ts_raw: pointer to the timespec to be set to raw monotonic time
+ * @ts_real: pointer to the timespec to be set to the time of day
+ *
+ * This function reads both the time of day and raw monotonic time at the
+ * same time atomically and stores the resulting timestamps in timespec
+ * format.
+ */
+void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
+{
+ struct timekeeper *tk = &timekeeper;
+ unsigned long seq;
+ s64 nsecs_raw, nsecs_real;
+
+ WARN_ON_ONCE(timekeeping_suspended);
+
+ do {
+ seq = read_seqcount_begin(&timekeeper_seq);
+
+ *ts_raw = tk->raw_time;
+ ts_real->tv_sec = tk->xtime_sec;
+ ts_real->tv_nsec = 0;
+
+ nsecs_raw = timekeeping_get_ns_raw(tk);
+ nsecs_real = timekeeping_get_ns(tk);
+
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
+
+ timespec_add_ns(ts_raw, nsecs_raw);
+ timespec_add_ns(ts_real, nsecs_real);
+}
+EXPORT_SYMBOL(getnstime_raw_and_real);
+
+#endif /* CONFIG_NTP_PPS */
+
/**
* do_gettimeofday - Returns the time of day in a timeval
* @tv: pointer to the timeval to be set
@@ -298,66 +485,176 @@ void do_gettimeofday(struct timeval *tv)
tv->tv_sec = now.tv_sec;
tv->tv_usec = now.tv_nsec/1000;
}
-
EXPORT_SYMBOL(do_gettimeofday);
+
/**
* do_settimeofday - Sets the time of day
* @tv: pointer to the timespec variable containing the new time
*
* Sets the time of day to the new time and update NTP and notify hrtimers
*/
-int do_settimeofday(struct timespec *tv)
+int do_settimeofday(const struct timespec *tv)
{
- struct timespec ts_delta;
+ struct timekeeper *tk = &timekeeper;
+ struct timespec ts_delta, xt;
unsigned long flags;
- if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
+ if (!timespec_valid_strict(tv))
return -EINVAL;
- write_seqlock_irqsave(&xtime_lock, flags);
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
- timekeeping_forward_now();
+ timekeeping_forward_now(tk);
- ts_delta.tv_sec = tv->tv_sec - xtime.tv_sec;
- ts_delta.tv_nsec = tv->tv_nsec - xtime.tv_nsec;
- wall_to_monotonic = timespec_sub(wall_to_monotonic, ts_delta);
+ xt = tk_xtime(tk);
+ ts_delta.tv_sec = tv->tv_sec - xt.tv_sec;
+ ts_delta.tv_nsec = tv->tv_nsec - xt.tv_nsec;
- xtime = *tv;
+ tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, ts_delta));
- timekeeper.ntp_error = 0;
- ntp_clear();
+ tk_set_xtime(tk, tv);
- update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
- timekeeper.mult);
+ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
- write_sequnlock_irqrestore(&xtime_lock, flags);
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
/* signal hrtimers about time change */
clock_was_set();
return 0;
}
-
EXPORT_SYMBOL(do_settimeofday);
/**
+ * timekeeping_inject_offset - Adds or subtracts from the current time.
+ * @tv: pointer to the timespec variable containing the offset
+ *
+ * Adds or subtracts an offset value from the current time.
+ */
+int timekeeping_inject_offset(struct timespec *ts)
+{
+ struct timekeeper *tk = &timekeeper;
+ unsigned long flags;
+ struct timespec tmp;
+ int ret = 0;
+
+ if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
+ return -EINVAL;
+
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
+
+ timekeeping_forward_now(tk);
+
+ /* Make sure the proposed value is valid */
+ tmp = timespec_add(tk_xtime(tk), *ts);
+ if (!timespec_valid_strict(&tmp)) {
+ ret = -EINVAL;
+ goto error;
+ }
+
+ tk_xtime_add(tk, ts);
+ tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *ts));
+
+error: /* even if we error out, we forwarded the time, so call update */
+ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
+
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+
+ /* signal hrtimers about time change */
+ clock_was_set();
+
+ return ret;
+}
+EXPORT_SYMBOL(timekeeping_inject_offset);
+
+
+/**
+ * timekeeping_get_tai_offset - Returns current TAI offset from UTC
+ *
+ */
+s32 timekeeping_get_tai_offset(void)
+{
+ struct timekeeper *tk = &timekeeper;
+ unsigned int seq;
+ s32 ret;
+
+ do {
+ seq = read_seqcount_begin(&timekeeper_seq);
+ ret = tk->tai_offset;
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
+
+ return ret;
+}
+
+/**
+ * __timekeeping_set_tai_offset - Lock free worker function
+ *
+ */
+static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
+{
+ tk->tai_offset = tai_offset;
+ tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0));
+}
+
+/**
+ * timekeeping_set_tai_offset - Sets the current TAI offset from UTC
+ *
+ */
+void timekeeping_set_tai_offset(s32 tai_offset)
+{
+ struct timekeeper *tk = &timekeeper;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
+ __timekeeping_set_tai_offset(tk, tai_offset);
+ timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ clock_was_set();
+}
+
+/**
* change_clocksource - Swaps clocksources if a new one is available
*
* Accumulates current time interval and initializes new clocksource
*/
static int change_clocksource(void *data)
{
+ struct timekeeper *tk = &timekeeper;
struct clocksource *new, *old;
+ unsigned long flags;
new = (struct clocksource *) data;
- timekeeping_forward_now();
- if (!new->enable || new->enable(new) == 0) {
- old = timekeeper.clock;
- timekeeper_setup_internals(new);
- if (old->disable)
- old->disable(old);
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
+
+ timekeeping_forward_now(tk);
+ /*
+ * If the cs is in module, get a module reference. Succeeds
+ * for built-in code (owner == NULL) as well.
+ */
+ if (try_module_get(new->owner)) {
+ if (!new->enable || new->enable(new) == 0) {
+ old = tk->clock;
+ tk_setup_internals(tk, new);
+ if (old->disable)
+ old->disable(old);
+ module_put(old->owner);
+ } else {
+ module_put(new->owner);
+ }
}
+ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
+
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+
return 0;
}
@@ -368,12 +665,15 @@ static int change_clocksource(void *data)
* This function is called from clocksource.c after a new, better clock
* source has been registered. The caller holds the clocksource_mutex.
*/
-void timekeeping_notify(struct clocksource *clock)
+int timekeeping_notify(struct clocksource *clock)
{
- if (timekeeper.clock == clock)
- return;
+ struct timekeeper *tk = &timekeeper;
+
+ if (tk->clock == clock)
+ return 0;
stop_machine(change_clocksource, clock, NULL);
tick_clock_notify();
+ return tk->clock == clock ? 0 : -1;
}
/**
@@ -399,48 +699,57 @@ EXPORT_SYMBOL_GPL(ktime_get_real);
*/
void getrawmonotonic(struct timespec *ts)
{
+ struct timekeeper *tk = &timekeeper;
unsigned long seq;
s64 nsecs;
do {
- seq = read_seqbegin(&xtime_lock);
- nsecs = timekeeping_get_ns_raw();
- *ts = raw_time;
+ seq = read_seqcount_begin(&timekeeper_seq);
+ nsecs = timekeeping_get_ns_raw(tk);
+ *ts = tk->raw_time;
- } while (read_seqretry(&xtime_lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
timespec_add_ns(ts, nsecs);
}
EXPORT_SYMBOL(getrawmonotonic);
-
/**
* timekeeping_valid_for_hres - Check if timekeeping is suitable for hres
*/
int timekeeping_valid_for_hres(void)
{
+ struct timekeeper *tk = &timekeeper;
unsigned long seq;
int ret;
do {
- seq = read_seqbegin(&xtime_lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
- ret = timekeeper.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
+ ret = tk->clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
- } while (read_seqretry(&xtime_lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
return ret;
}
/**
* timekeeping_max_deferment - Returns max time the clocksource can be deferred
- *
- * Caller must observe xtime_lock via read_seqbegin/read_seqretry to
- * ensure that the clocksource does not change!
*/
u64 timekeeping_max_deferment(void)
{
- return timekeeper.clock->max_idle_ns;
+ struct timekeeper *tk = &timekeeper;
+ unsigned long seq;
+ u64 ret;
+
+ do {
+ seq = read_seqcount_begin(&timekeeper_seq);
+
+ ret = tk->clock->max_idle_ns;
+
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
+
+ return ret;
}
/**
@@ -452,7 +761,7 @@ u64 timekeeping_max_deferment(void)
*
* XXX - Do be sure to remove it once all arches implement it.
*/
-void __attribute__((weak)) read_persistent_clock(struct timespec *ts)
+void __weak read_persistent_clock(struct timespec *ts)
{
ts->tv_sec = 0;
ts->tv_nsec = 0;
@@ -467,7 +776,7 @@ void __attribute__((weak)) read_persistent_clock(struct timespec *ts)
*
* XXX - Do be sure to remove it once all arches implement it.
*/
-void __attribute__((weak)) read_boot_clock(struct timespec *ts)
+void __weak read_boot_clock(struct timespec *ts)
{
ts->tv_sec = 0;
ts->tv_nsec = 0;
@@ -478,125 +787,278 @@ void __attribute__((weak)) read_boot_clock(struct timespec *ts)
*/
void __init timekeeping_init(void)
{
+ struct timekeeper *tk = &timekeeper;
struct clocksource *clock;
unsigned long flags;
- struct timespec now, boot;
+ struct timespec now, boot, tmp;
read_persistent_clock(&now);
- read_boot_clock(&boot);
- write_seqlock_irqsave(&xtime_lock, flags);
+ if (!timespec_valid_strict(&now)) {
+ pr_warn("WARNING: Persistent clock returned invalid value!\n"
+ " Check your CMOS/BIOS settings.\n");
+ now.tv_sec = 0;
+ now.tv_nsec = 0;
+ } else if (now.tv_sec || now.tv_nsec)
+ persistent_clock_exist = true;
+ read_boot_clock(&boot);
+ if (!timespec_valid_strict(&boot)) {
+ pr_warn("WARNING: Boot clock returned invalid value!\n"
+ " Check your CMOS/BIOS settings.\n");
+ boot.tv_sec = 0;
+ boot.tv_nsec = 0;
+ }
+
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
ntp_init();
clock = clocksource_default_clock();
if (clock->enable)
clock->enable(clock);
- timekeeper_setup_internals(clock);
-
- xtime.tv_sec = now.tv_sec;
- xtime.tv_nsec = now.tv_nsec;
- raw_time.tv_sec = 0;
- raw_time.tv_nsec = 0;
- if (boot.tv_sec == 0 && boot.tv_nsec == 0) {
- boot.tv_sec = xtime.tv_sec;
- boot.tv_nsec = xtime.tv_nsec;
- }
- set_normalized_timespec(&wall_to_monotonic,
- -boot.tv_sec, -boot.tv_nsec);
- total_sleep_time.tv_sec = 0;
- total_sleep_time.tv_nsec = 0;
- write_sequnlock_irqrestore(&xtime_lock, flags);
+ tk_setup_internals(tk, clock);
+
+ tk_set_xtime(tk, &now);
+ tk->raw_time.tv_sec = 0;
+ tk->raw_time.tv_nsec = 0;
+ if (boot.tv_sec == 0 && boot.tv_nsec == 0)
+ boot = tk_xtime(tk);
+
+ set_normalized_timespec(&tmp, -boot.tv_sec, -boot.tv_nsec);
+ tk_set_wall_to_mono(tk, tmp);
+
+ tmp.tv_sec = 0;
+ tmp.tv_nsec = 0;
+ tk_set_sleep_time(tk, tmp);
+
+ memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper));
+
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
}
/* time in seconds when suspend began */
static struct timespec timekeeping_suspend_time;
/**
+ * __timekeeping_inject_sleeptime - Internal function to add sleep interval
+ * @delta: pointer to a timespec delta value
+ *
+ * Takes a timespec offset measuring a suspend interval and properly
+ * adds the sleep offset to the timekeeping variables.
+ */
+static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
+ struct timespec *delta)
+{
+ if (!timespec_valid_strict(delta)) {
+ printk_deferred(KERN_WARNING
+ "__timekeeping_inject_sleeptime: Invalid "
+ "sleep delta value!\n");
+ return;
+ }
+ tk_xtime_add(tk, delta);
+ tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *delta));
+ tk_set_sleep_time(tk, timespec_add(tk->total_sleep_time, *delta));
+ tk_debug_account_sleep_time(delta);
+}
+
+/**
+ * timekeeping_inject_sleeptime - Adds suspend interval to timeekeeping values
+ * @delta: pointer to a timespec delta value
+ *
+ * This hook is for architectures that cannot support read_persistent_clock
+ * because their RTC/persistent clock is only accessible when irqs are enabled.
+ *
+ * This function should only be called by rtc_resume(), and allows
+ * a suspend offset to be injected into the timekeeping values.
+ */
+void timekeeping_inject_sleeptime(struct timespec *delta)
+{
+ struct timekeeper *tk = &timekeeper;
+ unsigned long flags;
+
+ /*
+ * Make sure we don't set the clock twice, as timekeeping_resume()
+ * already did it
+ */
+ if (has_persistent_clock())
+ return;
+
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
+
+ timekeeping_forward_now(tk);
+
+ __timekeeping_inject_sleeptime(tk, delta);
+
+ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
+
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+
+ /* signal hrtimers about time change */
+ clock_was_set();
+}
+
+/**
* timekeeping_resume - Resumes the generic timekeeping subsystem.
- * @dev: unused
*
* This is for the generic clocksource timekeeping.
* xtime/wall_to_monotonic/jiffies/etc are
* still managed by arch specific suspend/resume code.
*/
-static int timekeeping_resume(struct sys_device *dev)
+static void timekeeping_resume(void)
{
+ struct timekeeper *tk = &timekeeper;
+ struct clocksource *clock = tk->clock;
unsigned long flags;
- struct timespec ts;
+ struct timespec ts_new, ts_delta;
+ cycle_t cycle_now, cycle_delta;
+ bool suspendtime_found = false;
- read_persistent_clock(&ts);
+ read_persistent_clock(&ts_new);
+ clockevents_resume();
clocksource_resume();
- write_seqlock_irqsave(&xtime_lock, flags);
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
- if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) {
- ts = timespec_sub(ts, timekeeping_suspend_time);
- xtime = timespec_add(xtime, ts);
- wall_to_monotonic = timespec_sub(wall_to_monotonic, ts);
- total_sleep_time = timespec_add(total_sleep_time, ts);
+ /*
+ * After system resumes, we need to calculate the suspended time and
+ * compensate it for the OS time. There are 3 sources that could be
+ * used: Nonstop clocksource during suspend, persistent clock and rtc
+ * device.
+ *
+ * One specific platform may have 1 or 2 or all of them, and the
+ * preference will be:
+ * suspend-nonstop clocksource -> persistent clock -> rtc
+ * The less preferred source will only be tried if there is no better
+ * usable source. The rtc part is handled separately in rtc core code.
+ */
+ cycle_now = clock->read(clock);
+ if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
+ cycle_now > clock->cycle_last) {
+ u64 num, max = ULLONG_MAX;
+ u32 mult = clock->mult;
+ u32 shift = clock->shift;
+ s64 nsec = 0;
+
+ cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+
+ /*
+ * "cycle_delta * mutl" may cause 64 bits overflow, if the
+ * suspended time is too long. In that case we need do the
+ * 64 bits math carefully
+ */
+ do_div(max, mult);
+ if (cycle_delta > max) {
+ num = div64_u64(cycle_delta, max);
+ nsec = (((u64) max * mult) >> shift) * num;
+ cycle_delta -= num * max;
+ }
+ nsec += ((u64) cycle_delta * mult) >> shift;
+
+ ts_delta = ns_to_timespec(nsec);
+ suspendtime_found = true;
+ } else if (timespec_compare(&ts_new, &timekeeping_suspend_time) > 0) {
+ ts_delta = timespec_sub(ts_new, timekeeping_suspend_time);
+ suspendtime_found = true;
}
- /* re-base the last cycle value */
- timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
- timekeeper.ntp_error = 0;
+
+ if (suspendtime_found)
+ __timekeeping_inject_sleeptime(tk, &ts_delta);
+
+ /* Re-base the last cycle value */
+ tk->cycle_last = clock->cycle_last = cycle_now;
+ tk->ntp_error = 0;
timekeeping_suspended = 0;
- write_sequnlock_irqrestore(&xtime_lock, flags);
+ timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
touch_softlockup_watchdog();
clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL);
/* Resume hrtimers */
- hres_timers_resume();
-
- return 0;
+ hrtimers_resume();
}
-static int timekeeping_suspend(struct sys_device *dev, pm_message_t state)
+static int timekeeping_suspend(void)
{
+ struct timekeeper *tk = &timekeeper;
unsigned long flags;
+ struct timespec delta, delta_delta;
+ static struct timespec old_delta;
read_persistent_clock(&timekeeping_suspend_time);
- write_seqlock_irqsave(&xtime_lock, flags);
- timekeeping_forward_now();
+ /*
+ * On some systems the persistent_clock can not be detected at
+ * timekeeping_init by its return value, so if we see a valid
+ * value returned, update the persistent_clock_exists flag.
+ */
+ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
+ persistent_clock_exist = true;
+
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
+ timekeeping_forward_now(tk);
timekeeping_suspended = 1;
- write_sequnlock_irqrestore(&xtime_lock, flags);
+
+ /*
+ * To avoid drift caused by repeated suspend/resumes,
+ * which each can add ~1 second drift error,
+ * try to compensate so the difference in system time
+ * and persistent_clock time stays close to constant.
+ */
+ delta = timespec_sub(tk_xtime(tk), timekeeping_suspend_time);
+ delta_delta = timespec_sub(delta, old_delta);
+ if (abs(delta_delta.tv_sec) >= 2) {
+ /*
+ * if delta_delta is too large, assume time correction
+ * has occured and set old_delta to the current delta.
+ */
+ old_delta = delta;
+ } else {
+ /* Otherwise try to adjust old_system to compensate */
+ timekeeping_suspend_time =
+ timespec_add(timekeeping_suspend_time, delta_delta);
+ }
+
+ timekeeping_update(tk, TK_MIRROR);
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
clocksource_suspend();
+ clockevents_suspend();
return 0;
}
/* sysfs resume/suspend bits for timekeeping */
-static struct sysdev_class timekeeping_sysclass = {
- .name = "timekeeping",
+static struct syscore_ops timekeeping_syscore_ops = {
.resume = timekeeping_resume,
.suspend = timekeeping_suspend,
};
-static struct sys_device device_timer = {
- .id = 0,
- .cls = &timekeeping_sysclass,
-};
-
-static int __init timekeeping_init_device(void)
+static int __init timekeeping_init_ops(void)
{
- int error = sysdev_class_register(&timekeeping_sysclass);
- if (!error)
- error = sysdev_register(&device_timer);
- return error;
+ register_syscore_ops(&timekeeping_syscore_ops);
+ return 0;
}
-device_initcall(timekeeping_init_device);
+device_initcall(timekeeping_init_ops);
/*
* If the error is already larger, we look ahead even further
* to compensate for late or lost adjustments.
*/
-static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval,
+static __always_inline int timekeeping_bigadjust(struct timekeeper *tk,
+ s64 error, s64 *interval,
s64 *offset)
{
s64 tick_error, i;
@@ -612,7 +1074,7 @@ static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval,
* here. This is tuned so that an error of about 1 msec is adjusted
* within about 1 sec (or 2^20 nsec in 2^SHIFT_HZ ticks).
*/
- error2 = timekeeper.ntp_error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ);
+ error2 = tk->ntp_error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ);
error2 = abs(error2);
for (look_ahead = 0; error2 > 0; look_ahead++)
error2 >>= 2;
@@ -621,8 +1083,8 @@ static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval,
* Now calculate the error in (1 << look_ahead) ticks, but first
* remove the single look ahead already included in the error.
*/
- tick_error = tick_length >> (timekeeper.ntp_error_shift + 1);
- tick_error -= timekeeper.xtime_interval >> 1;
+ tick_error = ntp_tick_length() >> (tk->ntp_error_shift + 1);
+ tick_error -= tk->xtime_interval >> 1;
error = ((error - tick_error) >> look_ahead) + tick_error;
/* Finally calculate the adjustment shift value. */
@@ -647,36 +1109,175 @@ static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval,
* this is optimized for the most common adjustments of -1,0,1,
* for other values we can do a bit more work.
*/
-static void timekeeping_adjust(s64 offset)
+static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
{
- s64 error, interval = timekeeper.cycle_interval;
+ s64 error, interval = tk->cycle_interval;
int adj;
- error = timekeeper.ntp_error >> (timekeeper.ntp_error_shift - 1);
+ /*
+ * The point of this is to check if the error is greater than half
+ * an interval.
+ *
+ * First we shift it down from NTP_SHIFT to clocksource->shifted nsecs.
+ *
+ * Note we subtract one in the shift, so that error is really error*2.
+ * This "saves" dividing(shifting) interval twice, but keeps the
+ * (error > interval) comparison as still measuring if error is
+ * larger than half an interval.
+ *
+ * Note: It does not "save" on aggravation when reading the code.
+ */
+ error = tk->ntp_error >> (tk->ntp_error_shift - 1);
if (error > interval) {
+ /*
+ * We now divide error by 4(via shift), which checks if
+ * the error is greater than twice the interval.
+ * If it is greater, we need a bigadjust, if its smaller,
+ * we can adjust by 1.
+ */
error >>= 2;
if (likely(error <= interval))
adj = 1;
else
- adj = timekeeping_bigadjust(error, &interval, &offset);
- } else if (error < -interval) {
- error >>= 2;
- if (likely(error >= -interval)) {
- adj = -1;
- interval = -interval;
- offset = -offset;
- } else
- adj = timekeeping_bigadjust(error, &interval, &offset);
- } else
- return;
+ adj = timekeeping_bigadjust(tk, error, &interval, &offset);
+ } else {
+ if (error < -interval) {
+ /* See comment above, this is just switched for the negative */
+ error >>= 2;
+ if (likely(error >= -interval)) {
+ adj = -1;
+ interval = -interval;
+ offset = -offset;
+ } else {
+ adj = timekeeping_bigadjust(tk, error, &interval, &offset);
+ }
+ } else {
+ goto out_adjust;
+ }
+ }
+
+ if (unlikely(tk->clock->maxadj &&
+ (tk->mult + adj > tk->clock->mult + tk->clock->maxadj))) {
+ printk_deferred_once(KERN_WARNING
+ "Adjusting %s more than 11%% (%ld vs %ld)\n",
+ tk->clock->name, (long)tk->mult + adj,
+ (long)tk->clock->mult + tk->clock->maxadj);
+ }
+ /*
+ * So the following can be confusing.
+ *
+ * To keep things simple, lets assume adj == 1 for now.
+ *
+ * When adj != 1, remember that the interval and offset values
+ * have been appropriately scaled so the math is the same.
+ *
+ * The basic idea here is that we're increasing the multiplier
+ * by one, this causes the xtime_interval to be incremented by
+ * one cycle_interval. This is because:
+ * xtime_interval = cycle_interval * mult
+ * So if mult is being incremented by one:
+ * xtime_interval = cycle_interval * (mult + 1)
+ * Its the same as:
+ * xtime_interval = (cycle_interval * mult) + cycle_interval
+ * Which can be shortened to:
+ * xtime_interval += cycle_interval
+ *
+ * So offset stores the non-accumulated cycles. Thus the current
+ * time (in shifted nanoseconds) is:
+ * now = (offset * adj) + xtime_nsec
+ * Now, even though we're adjusting the clock frequency, we have
+ * to keep time consistent. In other words, we can't jump back
+ * in time, and we also want to avoid jumping forward in time.
+ *
+ * So given the same offset value, we need the time to be the same
+ * both before and after the freq adjustment.
+ * now = (offset * adj_1) + xtime_nsec_1
+ * now = (offset * adj_2) + xtime_nsec_2
+ * So:
+ * (offset * adj_1) + xtime_nsec_1 =
+ * (offset * adj_2) + xtime_nsec_2
+ * And we know:
+ * adj_2 = adj_1 + 1
+ * So:
+ * (offset * adj_1) + xtime_nsec_1 =
+ * (offset * (adj_1+1)) + xtime_nsec_2
+ * (offset * adj_1) + xtime_nsec_1 =
+ * (offset * adj_1) + offset + xtime_nsec_2
+ * Canceling the sides:
+ * xtime_nsec_1 = offset + xtime_nsec_2
+ * Which gives us:
+ * xtime_nsec_2 = xtime_nsec_1 - offset
+ * Which simplfies to:
+ * xtime_nsec -= offset
+ *
+ * XXX - TODO: Doc ntp_error calculation.
+ */
+ tk->mult += adj;
+ tk->xtime_interval += interval;
+ tk->xtime_nsec -= offset;
+ tk->ntp_error -= (interval - offset) << tk->ntp_error_shift;
+
+out_adjust:
+ /*
+ * It may be possible that when we entered this function, xtime_nsec
+ * was very small. Further, if we're slightly speeding the clocksource
+ * in the code above, its possible the required corrective factor to
+ * xtime_nsec could cause it to underflow.
+ *
+ * Now, since we already accumulated the second, cannot simply roll
+ * the accumulated second back, since the NTP subsystem has been
+ * notified via second_overflow. So instead we push xtime_nsec forward
+ * by the amount we underflowed, and add that amount into the error.
+ *
+ * We'll correct this error next time through this function, when
+ * xtime_nsec is not as small.
+ */
+ if (unlikely((s64)tk->xtime_nsec < 0)) {
+ s64 neg = -(s64)tk->xtime_nsec;
+ tk->xtime_nsec = 0;
+ tk->ntp_error += neg << tk->ntp_error_shift;
+ }
- timekeeper.mult += adj;
- timekeeper.xtime_interval += interval;
- timekeeper.xtime_nsec -= offset;
- timekeeper.ntp_error -= (interval - offset) <<
- timekeeper.ntp_error_shift;
}
+/**
+ * accumulate_nsecs_to_secs - Accumulates nsecs into secs
+ *
+ * Helper function that accumulates a the nsecs greater then a second
+ * from the xtime_nsec field to the xtime_secs field.
+ * It also calls into the NTP code to handle leapsecond processing.
+ *
+ */
+static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
+{
+ u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
+ unsigned int clock_set = 0;
+
+ while (tk->xtime_nsec >= nsecps) {
+ int leap;
+
+ tk->xtime_nsec -= nsecps;
+ tk->xtime_sec++;
+
+ /* Figure out if its a leap sec and apply if needed */
+ leap = second_overflow(tk->xtime_sec);
+ if (unlikely(leap)) {
+ struct timespec ts;
+
+ tk->xtime_sec += leap;
+
+ ts.tv_sec = leap;
+ ts.tv_nsec = 0;
+ tk_set_wall_to_mono(tk,
+ timespec_sub(tk->wall_to_monotonic, ts));
+
+ __timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
+
+ clock_set = TK_CLOCK_WAS_SET;
+ }
+ }
+ return clock_set;
+}
/**
* logarithmic_accumulation - shifted accumulation of cycles
@@ -687,143 +1288,164 @@ static void timekeeping_adjust(s64 offset)
*
* Returns the unconsumed cycles.
*/
-static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
+static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
+ u32 shift,
+ unsigned int *clock_set)
{
- u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
+ cycle_t interval = tk->cycle_interval << shift;
u64 raw_nsecs;
/* If the offset is smaller then a shifted interval, do nothing */
- if (offset < timekeeper.cycle_interval<<shift)
+ if (offset < interval)
return offset;
/* Accumulate one shifted interval */
- offset -= timekeeper.cycle_interval << shift;
- timekeeper.clock->cycle_last += timekeeper.cycle_interval << shift;
-
- timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
- while (timekeeper.xtime_nsec >= nsecps) {
- timekeeper.xtime_nsec -= nsecps;
- xtime.tv_sec++;
- second_overflow();
- }
+ offset -= interval;
+ tk->cycle_last += interval;
+
+ tk->xtime_nsec += tk->xtime_interval << shift;
+ *clock_set |= accumulate_nsecs_to_secs(tk);
/* Accumulate raw time */
- raw_nsecs = timekeeper.raw_interval << shift;
- raw_nsecs += raw_time.tv_nsec;
+ raw_nsecs = (u64)tk->raw_interval << shift;
+ raw_nsecs += tk->raw_time.tv_nsec;
if (raw_nsecs >= NSEC_PER_SEC) {
u64 raw_secs = raw_nsecs;
raw_nsecs = do_div(raw_secs, NSEC_PER_SEC);
- raw_time.tv_sec += raw_secs;
+ tk->raw_time.tv_sec += raw_secs;
}
- raw_time.tv_nsec = raw_nsecs;
+ tk->raw_time.tv_nsec = raw_nsecs;
/* Accumulate error between NTP and clock interval */
- timekeeper.ntp_error += tick_length << shift;
- timekeeper.ntp_error -= timekeeper.xtime_interval <<
- (timekeeper.ntp_error_shift + shift);
+ tk->ntp_error += ntp_tick_length() << shift;
+ tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) <<
+ (tk->ntp_error_shift + shift);
return offset;
}
+#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD
+static inline void old_vsyscall_fixup(struct timekeeper *tk)
+{
+ s64 remainder;
+
+ /*
+ * Store only full nanoseconds into xtime_nsec after rounding
+ * it up and add the remainder to the error difference.
+ * XXX - This is necessary to avoid small 1ns inconsistnecies caused
+ * by truncating the remainder in vsyscalls. However, it causes
+ * additional work to be done in timekeeping_adjust(). Once
+ * the vsyscall implementations are converted to use xtime_nsec
+ * (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD
+ * users are removed, this can be killed.
+ */
+ remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1);
+ tk->xtime_nsec -= remainder;
+ tk->xtime_nsec += 1ULL << tk->shift;
+ tk->ntp_error += remainder << tk->ntp_error_shift;
+ tk->ntp_error -= (1ULL << tk->shift) << tk->ntp_error_shift;
+}
+#else
+#define old_vsyscall_fixup(tk)
+#endif
+
+
/**
* update_wall_time - Uses the current clocksource to increment the wall time
*
- * Called from the timer interrupt, must hold a write on xtime_lock.
*/
void update_wall_time(void)
{
struct clocksource *clock;
+ struct timekeeper *real_tk = &timekeeper;
+ struct timekeeper *tk = &shadow_timekeeper;
cycle_t offset;
int shift = 0, maxshift;
+ unsigned int clock_set = 0;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
/* Make sure we're fully resumed: */
if (unlikely(timekeeping_suspended))
- return;
+ goto out;
- clock = timekeeper.clock;
+ clock = real_tk->clock;
#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
- offset = timekeeper.cycle_interval;
+ offset = real_tk->cycle_interval;
#else
offset = (clock->read(clock) - clock->cycle_last) & clock->mask;
#endif
- timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;
+
+ /* Check if there's really nothing to do */
+ if (offset < real_tk->cycle_interval)
+ goto out;
/*
* With NO_HZ we may have to accumulate many cycle_intervals
* (think "ticks") worth of time at once. To do this efficiently,
* we calculate the largest doubling multiple of cycle_intervals
- * that is smaller then the offset. We then accumulate that
+ * that is smaller than the offset. We then accumulate that
* chunk in one go, and then try to consume the next smaller
* doubled multiple.
*/
- shift = ilog2(offset) - ilog2(timekeeper.cycle_interval);
+ shift = ilog2(offset) - ilog2(tk->cycle_interval);
shift = max(0, shift);
- /* Bound shift to one less then what overflows tick_length */
- maxshift = (8*sizeof(tick_length) - (ilog2(tick_length)+1)) - 1;
+ /* Bound shift to one less than what overflows tick_length */
+ maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
shift = min(shift, maxshift);
- while (offset >= timekeeper.cycle_interval) {
- offset = logarithmic_accumulation(offset, shift);
- if(offset < timekeeper.cycle_interval<<shift)
+ while (offset >= tk->cycle_interval) {
+ offset = logarithmic_accumulation(tk, offset, shift,
+ &clock_set);
+ if (offset < tk->cycle_interval<<shift)
shift--;
}
/* correct the clock when NTP error is too big */
- timekeeping_adjust(offset);
+ timekeeping_adjust(tk, offset);
/*
- * Since in the loop above, we accumulate any amount of time
- * in xtime_nsec over a second into xtime.tv_sec, its possible for
- * xtime_nsec to be fairly small after the loop. Further, if we're
- * slightly speeding the clocksource up in timekeeping_adjust(),
- * its possible the required corrective factor to xtime_nsec could
- * cause it to underflow.
- *
- * Now, we cannot simply roll the accumulated second back, since
- * the NTP subsystem has been notified via second_overflow. So
- * instead we push xtime_nsec forward by the amount we underflowed,
- * and add that amount into the error.
- *
- * We'll correct this error next time through this function, when
- * xtime_nsec is not as small.
+ * XXX This can be killed once everyone converts
+ * to the new update_vsyscall.
*/
- if (unlikely((s64)timekeeper.xtime_nsec < 0)) {
- s64 neg = -(s64)timekeeper.xtime_nsec;
- timekeeper.xtime_nsec = 0;
- timekeeper.ntp_error += neg << timekeeper.ntp_error_shift;
- }
-
+ old_vsyscall_fixup(tk);
/*
- * Store full nanoseconds into xtime after rounding it up and
- * add the remainder to the error difference.
+ * Finally, make sure that after the rounding
+ * xtime_nsec isn't larger than NSEC_PER_SEC
*/
- xtime.tv_nsec = ((s64) timekeeper.xtime_nsec >> timekeeper.shift) + 1;
- timekeeper.xtime_nsec -= (s64) xtime.tv_nsec << timekeeper.shift;
- timekeeper.ntp_error += timekeeper.xtime_nsec <<
- timekeeper.ntp_error_shift;
+ clock_set |= accumulate_nsecs_to_secs(tk);
+ write_seqcount_begin(&timekeeper_seq);
+ /* Update clock->cycle_last with the new value */
+ clock->cycle_last = tk->cycle_last;
/*
- * Finally, make sure that after the rounding
- * xtime.tv_nsec isn't larger then NSEC_PER_SEC
+ * Update the real timekeeper.
+ *
+ * We could avoid this memcpy by switching pointers, but that
+ * requires changes to all other timekeeper usage sites as
+ * well, i.e. move the timekeeper pointer getter into the
+ * spinlocked/seqcount protected sections. And we trade this
+ * memcpy under the timekeeper_seq against one before we start
+ * updating.
*/
- if (unlikely(xtime.tv_nsec >= NSEC_PER_SEC)) {
- xtime.tv_nsec -= NSEC_PER_SEC;
- xtime.tv_sec++;
- second_overflow();
- }
-
- /* check to see if there is a new clocksource to use */
- update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
- timekeeper.mult);
+ memcpy(real_tk, tk, sizeof(*tk));
+ timekeeping_update(real_tk, clock_set);
+ write_seqcount_end(&timekeeper_seq);
+out:
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ if (clock_set)
+ /* Have to call _delayed version, since in irq context*/
+ clock_was_set_delayed();
}
/**
* getboottime - Return the real time of system boot.
* @ts: pointer to the timespec to be set
*
- * Returns the time of day in a timespec.
+ * Returns the wall-time of boot in a timespec.
*
* This is based on the wall_to_monotonic offset and the total suspend
* time. Calls to settimeofday will affect the value returned (which
@@ -832,9 +1454,12 @@ void update_wall_time(void)
*/
void getboottime(struct timespec *ts)
{
+ struct timekeeper *tk = &timekeeper;
struct timespec boottime = {
- .tv_sec = wall_to_monotonic.tv_sec + total_sleep_time.tv_sec,
- .tv_nsec = wall_to_monotonic.tv_nsec + total_sleep_time.tv_nsec
+ .tv_sec = tk->wall_to_monotonic.tv_sec +
+ tk->total_sleep_time.tv_sec,
+ .tv_nsec = tk->wall_to_monotonic.tv_nsec +
+ tk->total_sleep_time.tv_nsec
};
set_normalized_timespec(ts, -boottime.tv_sec, -boottime.tv_nsec);
@@ -842,41 +1467,93 @@ void getboottime(struct timespec *ts)
EXPORT_SYMBOL_GPL(getboottime);
/**
+ * get_monotonic_boottime - Returns monotonic time since boot
+ * @ts: pointer to the timespec to be set
+ *
+ * Returns the monotonic time since boot in a timespec.
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get_ts, but also
+ * includes the time spent in suspend.
+ */
+void get_monotonic_boottime(struct timespec *ts)
+{
+ struct timekeeper *tk = &timekeeper;
+ struct timespec tomono, sleep;
+ s64 nsec;
+ unsigned int seq;
+
+ WARN_ON(timekeeping_suspended);
+
+ do {
+ seq = read_seqcount_begin(&timekeeper_seq);
+ ts->tv_sec = tk->xtime_sec;
+ nsec = timekeeping_get_ns(tk);
+ tomono = tk->wall_to_monotonic;
+ sleep = tk->total_sleep_time;
+
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
+
+ ts->tv_sec += tomono.tv_sec + sleep.tv_sec;
+ ts->tv_nsec = 0;
+ timespec_add_ns(ts, nsec + tomono.tv_nsec + sleep.tv_nsec);
+}
+EXPORT_SYMBOL_GPL(get_monotonic_boottime);
+
+/**
+ * ktime_get_boottime - Returns monotonic time since boot in a ktime
+ *
+ * Returns the monotonic time since boot in a ktime
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get, but also
+ * includes the time spent in suspend.
+ */
+ktime_t ktime_get_boottime(void)
+{
+ struct timespec ts;
+
+ get_monotonic_boottime(&ts);
+ return timespec_to_ktime(ts);
+}
+EXPORT_SYMBOL_GPL(ktime_get_boottime);
+
+/**
* monotonic_to_bootbased - Convert the monotonic time to boot based.
* @ts: pointer to the timespec to be converted
*/
void monotonic_to_bootbased(struct timespec *ts)
{
- *ts = timespec_add(*ts, total_sleep_time);
+ struct timekeeper *tk = &timekeeper;
+
+ *ts = timespec_add(*ts, tk->total_sleep_time);
}
EXPORT_SYMBOL_GPL(monotonic_to_bootbased);
unsigned long get_seconds(void)
{
- return xtime.tv_sec;
+ struct timekeeper *tk = &timekeeper;
+
+ return tk->xtime_sec;
}
EXPORT_SYMBOL(get_seconds);
struct timespec __current_kernel_time(void)
{
- return xtime;
-}
+ struct timekeeper *tk = &timekeeper;
-struct timespec __get_wall_to_monotonic(void)
-{
- return wall_to_monotonic;
+ return tk_xtime(tk);
}
struct timespec current_kernel_time(void)
{
+ struct timekeeper *tk = &timekeeper;
struct timespec now;
unsigned long seq;
do {
- seq = read_seqbegin(&xtime_lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
- now = xtime;
- } while (read_seqretry(&xtime_lock, seq));
+ now = tk_xtime(tk);
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
return now;
}
@@ -884,17 +1561,184 @@ EXPORT_SYMBOL(current_kernel_time);
struct timespec get_monotonic_coarse(void)
{
+ struct timekeeper *tk = &timekeeper;
struct timespec now, mono;
unsigned long seq;
do {
- seq = read_seqbegin(&xtime_lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
- now = xtime;
- mono = wall_to_monotonic;
- } while (read_seqretry(&xtime_lock, seq));
+ now = tk_xtime(tk);
+ mono = tk->wall_to_monotonic;
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
set_normalized_timespec(&now, now.tv_sec + mono.tv_sec,
now.tv_nsec + mono.tv_nsec);
return now;
}
+
+/*
+ * Must hold jiffies_lock
+ */
+void do_timer(unsigned long ticks)
+{
+ jiffies_64 += ticks;
+ calc_global_load(ticks);
+}
+
+/**
+ * get_xtime_and_monotonic_and_sleep_offset() - get xtime, wall_to_monotonic,
+ * and sleep offsets.
+ * @xtim: pointer to timespec to be set with xtime
+ * @wtom: pointer to timespec to be set with wall_to_monotonic
+ * @sleep: pointer to timespec to be set with time in suspend
+ */
+void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
+ struct timespec *wtom, struct timespec *sleep)
+{
+ struct timekeeper *tk = &timekeeper;
+ unsigned long seq;
+
+ do {
+ seq = read_seqcount_begin(&timekeeper_seq);
+ *xtim = tk_xtime(tk);
+ *wtom = tk->wall_to_monotonic;
+ *sleep = tk->total_sleep_time;
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
+}
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+/**
+ * ktime_get_update_offsets - hrtimer helper
+ * @offs_real: pointer to storage for monotonic -> realtime offset
+ * @offs_boot: pointer to storage for monotonic -> boottime offset
+ * @offs_tai: pointer to storage for monotonic -> clock tai offset
+ *
+ * Returns current monotonic time and updates the offsets
+ * Called from hrtimer_interrupt() or retrigger_next_event()
+ */
+ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot,
+ ktime_t *offs_tai)
+{
+ struct timekeeper *tk = &timekeeper;
+ ktime_t now;
+ unsigned int seq;
+ u64 secs, nsecs;
+
+ do {
+ seq = read_seqcount_begin(&timekeeper_seq);
+
+ secs = tk->xtime_sec;
+ nsecs = timekeeping_get_ns(tk);
+
+ *offs_real = tk->offs_real;
+ *offs_boot = tk->offs_boot;
+ *offs_tai = tk->offs_tai;
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
+
+ now = ktime_add_ns(ktime_set(secs, 0), nsecs);
+ now = ktime_sub(now, *offs_real);
+ return now;
+}
+#endif
+
+/**
+ * ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format
+ */
+ktime_t ktime_get_monotonic_offset(void)
+{
+ struct timekeeper *tk = &timekeeper;
+ unsigned long seq;
+ struct timespec wtom;
+
+ do {
+ seq = read_seqcount_begin(&timekeeper_seq);
+ wtom = tk->wall_to_monotonic;
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
+
+ return timespec_to_ktime(wtom);
+}
+EXPORT_SYMBOL_GPL(ktime_get_monotonic_offset);
+
+/**
+ * do_adjtimex() - Accessor function to NTP __do_adjtimex function
+ */
+int do_adjtimex(struct timex *txc)
+{
+ struct timekeeper *tk = &timekeeper;
+ unsigned long flags;
+ struct timespec ts;
+ s32 orig_tai, tai;
+ int ret;
+
+ /* Validate the data before disabling interrupts */
+ ret = ntp_validate_timex(txc);
+ if (ret)
+ return ret;
+
+ if (txc->modes & ADJ_SETOFFSET) {
+ struct timespec delta;
+ delta.tv_sec = txc->time.tv_sec;
+ delta.tv_nsec = txc->time.tv_usec;
+ if (!(txc->modes & ADJ_NANO))
+ delta.tv_nsec *= 1000;
+ ret = timekeeping_inject_offset(&delta);
+ if (ret)
+ return ret;
+ }
+
+ getnstimeofday(&ts);
+
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
+
+ orig_tai = tai = tk->tai_offset;
+ ret = __do_adjtimex(txc, &ts, &tai);
+
+ if (tai != orig_tai) {
+ __timekeeping_set_tai_offset(tk, tai);
+ timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
+ }
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+
+ if (tai != orig_tai)
+ clock_was_set();
+
+ ntp_notify_cmos_timer();
+
+ return ret;
+}
+
+#ifdef CONFIG_NTP_PPS
+/**
+ * hardpps() - Accessor function to NTP __hardpps function
+ */
+void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
+
+ __hardpps(phase_ts, raw_ts);
+
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+}
+EXPORT_SYMBOL(hardpps);
+#endif
+
+/**
+ * xtime_update() - advances the timekeeping infrastructure
+ * @ticks: number of ticks, that have elapsed since the last call.
+ *
+ * Must be called with interrupts disabled.
+ */
+void xtime_update(unsigned long ticks)
+{
+ write_seqlock(&jiffies_lock);
+ do_timer(ticks);
+ write_sequnlock(&jiffies_lock);
+ update_wall_time();
+}
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
new file mode 100644
index 00000000000..4d54f97558d
--- /dev/null
+++ b/kernel/time/timekeeping_debug.c
@@ -0,0 +1,74 @@
+/*
+ * debugfs file to track time spent in suspend
+ *
+ * Copyright (c) 2011, Google, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/seq_file.h>
+#include <linux/time.h>
+
+#include "timekeeping_internal.h"
+
+static unsigned int sleep_time_bin[32] = {0};
+
+static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
+{
+ unsigned int bin;
+ seq_puts(s, " time (secs) count\n");
+ seq_puts(s, "------------------------------\n");
+ for (bin = 0; bin < 32; bin++) {
+ if (sleep_time_bin[bin] == 0)
+ continue;
+ seq_printf(s, "%10u - %-10u %4u\n",
+ bin ? 1 << (bin - 1) : 0, 1 << bin,
+ sleep_time_bin[bin]);
+ }
+ return 0;
+}
+
+static int tk_debug_sleep_time_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, tk_debug_show_sleep_time, NULL);
+}
+
+static const struct file_operations tk_debug_sleep_time_fops = {
+ .open = tk_debug_sleep_time_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int __init tk_debug_sleep_time_init(void)
+{
+ struct dentry *d;
+
+ d = debugfs_create_file("sleep_time", 0444, NULL, NULL,
+ &tk_debug_sleep_time_fops);
+ if (!d) {
+ pr_err("Failed to create sleep_time debug file\n");
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+late_initcall(tk_debug_sleep_time_init);
+
+void tk_debug_account_sleep_time(struct timespec *t)
+{
+ sleep_time_bin[fls(t->tv_sec)]++;
+}
+
diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h
new file mode 100644
index 00000000000..13323ea08ff
--- /dev/null
+++ b/kernel/time/timekeeping_internal.h
@@ -0,0 +1,14 @@
+#ifndef _TIMEKEEPING_INTERNAL_H
+#define _TIMEKEEPING_INTERNAL_H
+/*
+ * timekeeping debug functions
+ */
+#include <linux/time.h>
+
+#ifdef CONFIG_DEBUG_FS
+extern void tk_debug_account_sleep_time(struct timespec *t);
+#else
+#define tk_debug_account_sleep_time(x)
+#endif
+
+#endif /* _TIMEKEEPING_INTERNAL_H */
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index ab8f5e33fa9..61ed862cdd3 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -20,6 +20,13 @@
#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);
@@ -41,7 +48,7 @@ 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, "<%p>", sym);
+ SEQ_printf(m, "<%pK>", sym);
else
SEQ_printf(m, "%s", symname);
}
@@ -79,26 +86,26 @@ print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base,
{
struct hrtimer *timer, tmp;
unsigned long next = 0, i;
- struct rb_node *curr;
+ struct timerqueue_node *curr;
unsigned long flags;
next_one:
i = 0;
raw_spin_lock_irqsave(&base->cpu_base->lock, flags);
- curr = base->first;
+ 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 = rb_next(curr);
+ curr = timerqueue_iterate_next(curr);
i++;
}
if (curr) {
- timer = rb_entry(curr, struct hrtimer, node);
+ timer = container_of(curr, struct hrtimer, node);
tmp = *timer;
raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags);
@@ -112,7 +119,7 @@ next_one:
static void
print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
{
- SEQ_printf(m, " .base: %p\n", base);
+ SEQ_printf(m, " .base: %pK\n", base);
SEQ_printf(m, " .index: %d\n",
base->index);
SEQ_printf(m, " .resolution: %Lu nsecs\n",
@@ -133,7 +140,6 @@ 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, "\n");
SEQ_printf(m, "cpu: %d\n", cpu);
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
SEQ_printf(m, " clock %d:\n", i);
@@ -167,7 +173,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
{
struct tick_sched *ts = tick_get_tick_sched(cpu);
P(nohz_mode);
- P_ns(idle_tick);
+ P_ns(last_tick);
P(tick_stopped);
P(idle_jiffies);
P(idle_calls);
@@ -187,6 +193,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
#undef P
#undef P_ns
+ SEQ_printf(m, "\n");
}
#ifdef CONFIG_GENERIC_CLOCKEVENTS
@@ -195,7 +202,6 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
{
struct clock_event_device *dev = td->evtdev;
- SEQ_printf(m, "\n");
SEQ_printf(m, "Tick Device: mode: %d\n", td->mode);
if (cpu < 0)
SEQ_printf(m, "Broadcast device\n");
@@ -230,12 +236,11 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
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(struct seq_file *m)
+static void timer_list_show_tickdevices_header(struct seq_file *m)
{
- int cpu;
-
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
print_tickdevice(m, tick_get_broadcast_device(), -1);
SEQ_printf(m, "tick_broadcast_mask: %08lx\n",
@@ -246,47 +251,111 @@ static void timer_list_show_tickdevices(struct seq_file *m)
#endif
SEQ_printf(m, "\n");
#endif
- for_each_online_cpu(cpu)
- print_tickdevice(m, tick_get_device(cpu), cpu);
- SEQ_printf(m, "\n");
}
-#else
-static void timer_list_show_tickdevices(struct seq_file *m) { }
#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;
- SEQ_printf(m, "Timer List Version: v0.6\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);
+ timer_list_header(NULL, now);
for_each_online_cpu(cpu)
- print_cpu(m, cpu, now);
+ print_cpu(NULL, cpu, now);
- SEQ_printf(m, "\n");
- timer_list_show_tickdevices(m);
+#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;
+}
- return 0;
+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;
}
-void sysrq_timer_list_show(void)
+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)
{
- timer_list_show(NULL, NULL);
}
+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 single_open(filp, timer_list_show, NULL);
+ 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 = single_release,
+ .release = seq_release_private,
};
static int __init init_timer_list_procfs(void)
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index 2f3b585b8d7..1fb08f21302 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -81,7 +81,7 @@ struct entry {
/*
* Spinlock protecting the tables - not taken during lookup:
*/
-static DEFINE_SPINLOCK(table_lock);
+static DEFINE_RAW_SPINLOCK(table_lock);
/*
* Per-CPU lookup locks for fast hash lookup:
@@ -188,7 +188,7 @@ static struct entry *tstat_lookup(struct entry *entry, char *comm)
prev = NULL;
curr = *head;
- spin_lock(&table_lock);
+ raw_spin_lock(&table_lock);
/*
* Make sure we have not raced with another CPU:
*/
@@ -215,7 +215,7 @@ static struct entry *tstat_lookup(struct entry *entry, char *comm)
*head = curr;
}
out_unlock:
- spin_unlock(&table_lock);
+ raw_spin_unlock(&table_lock);
return curr;
}
@@ -236,7 +236,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
unsigned int timer_flag)
{
/*
- * It doesnt matter which lock we take:
+ * It doesn't matter which lock we take:
*/
raw_spinlock_t *lock;
struct entry *entry, input;
@@ -298,15 +298,15 @@ static int tstats_show(struct seq_file *m, void *v)
period = ktime_to_timespec(time);
ms = period.tv_nsec / 1000000;
- seq_puts(m, "Timer Stats Version: v0.2\n");
+ seq_puts(m, "Timer Stats Version: v0.3\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));
+ seq_printf(m, "Overflow: %d entries\n", atomic_read(&overflow_count));
+ seq_printf(m, "Collection: %s\n", timer_stats_active ? "active" : "inactive");
for (i = 0; i < nr_entries; i++) {
entry = entries + i;
- if (entry->timer_flag & TIMER_STATS_FLAG_DEFERRABLE) {
+ if (entry->timer_flag & TIMER_STATS_FLAG_DEFERRABLE) {
seq_printf(m, "%4luD, %5d %-16s ",
entry->count, entry->pid, entry->comm);
} else {
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-04 01:48:28 +0000