diff options
Diffstat (limited to 'kernel/time')
| -rw-r--r-- | kernel/time/Kconfig | 55 | ||||
| -rw-r--r-- | kernel/time/Makefile | 7 | ||||
| -rw-r--r-- | kernel/time/alarmtimer.c | 71 | ||||
| -rw-r--r-- | kernel/time/clockevents.c | 384 | ||||
| -rw-r--r-- | kernel/time/clocksource.c | 312 | ||||
| -rw-r--r-- | kernel/time/jiffies.c | 6 | ||||
| -rw-r--r-- | kernel/time/ntp.c | 46 | ||||
| -rw-r--r-- | kernel/time/sched_clock.c | 217 | ||||
| -rw-r--r-- | kernel/time/tick-broadcast-hrtimer.c | 106 | ||||
| -rw-r--r-- | kernel/time/tick-broadcast.c | 233 | ||||
| -rw-r--r-- | kernel/time/tick-common.c | 229 | ||||
| -rw-r--r-- | kernel/time/tick-internal.h | 33 | ||||
| -rw-r--r-- | kernel/time/tick-sched.c | 173 | ||||
| -rw-r--r-- | kernel/time/timekeeping.c | 124 | ||||
| -rw-r--r-- | kernel/time/timekeeping_debug.c | 74 | ||||
| -rw-r--r-- | kernel/time/timekeeping_internal.h | 14 | ||||
| -rw-r--r-- | kernel/time/timer_list.c | 41 | ||||
| -rw-r--r-- | kernel/time/timer_stats.c | 8 |
18 files changed, 1623 insertions, 510 deletions
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 70f27e89012..f448513a45e 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -100,12 +100,11 @@ config NO_HZ_FULL # RCU_USER_QS dependency depends on HAVE_CONTEXT_TRACKING # VIRT_CPU_ACCOUNTING_GEN dependency - depends on 64BIT + 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 CONTEXT_TRACKING_FORCE select IRQ_WORK help Adaptively try to shutdown the tick whenever possible, even when @@ -125,7 +124,7 @@ config NO_HZ_FULL endchoice config NO_HZ_FULL_ALL - bool "Full dynticks system on all CPUs by default" + 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 @@ -134,6 +133,56 @@ config NO_HZ_FULL_ALL 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 + 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 diff --git a/kernel/time/Makefile b/kernel/time/Makefile index ff7d9d2ab50..57a413fd0eb 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -3,7 +3,12 @@ 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 index f11d83b1294..fe75444ae7e 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -199,6 +199,13 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) } +ktime_t alarm_expires_remaining(const struct alarm *alarm) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + return ktime_sub(alarm->node.expires, base->gettime()); +} +EXPORT_SYMBOL_GPL(alarm_expires_remaining); + #ifdef CONFIG_RTC_CLASS /** * alarmtimer_suspend - Suspend time callback @@ -303,9 +310,10 @@ void alarm_init(struct alarm *alarm, enum alarmtimer_type type, alarm->type = type; alarm->state = ALARMTIMER_STATE_INACTIVE; } +EXPORT_SYMBOL_GPL(alarm_init); /** - * alarm_start - Sets an alarm to fire + * alarm_start - Sets an absolute alarm to fire * @alarm: ptr to alarm to set * @start: time to run the alarm */ @@ -323,6 +331,34 @@ int alarm_start(struct alarm *alarm, ktime_t start) spin_unlock_irqrestore(&base->lock, flags); return ret; } +EXPORT_SYMBOL_GPL(alarm_start); + +/** + * alarm_start_relative - Sets a relative alarm to fire + * @alarm: ptr to alarm to set + * @start: time relative to now to run the alarm + */ +int alarm_start_relative(struct alarm *alarm, ktime_t start) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + + start = ktime_add(start, base->gettime()); + return alarm_start(alarm, start); +} +EXPORT_SYMBOL_GPL(alarm_start_relative); + +void alarm_restart(struct alarm *alarm) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + unsigned long flags; + + spin_lock_irqsave(&base->lock, flags); + hrtimer_set_expires(&alarm->timer, alarm->node.expires); + hrtimer_restart(&alarm->timer); + alarmtimer_enqueue(base, alarm); + spin_unlock_irqrestore(&base->lock, flags); +} +EXPORT_SYMBOL_GPL(alarm_restart); /** * alarm_try_to_cancel - Tries to cancel an alarm timer @@ -344,6 +380,7 @@ int alarm_try_to_cancel(struct alarm *alarm) spin_unlock_irqrestore(&base->lock, flags); return ret; } +EXPORT_SYMBOL_GPL(alarm_try_to_cancel); /** @@ -361,6 +398,7 @@ int alarm_cancel(struct alarm *alarm) cpu_relax(); } } +EXPORT_SYMBOL_GPL(alarm_cancel); u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) @@ -393,8 +431,15 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) alarm->node.expires = ktime_add(alarm->node.expires, interval); return overrun; } +EXPORT_SYMBOL_GPL(alarm_forward); +u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + return alarm_forward(alarm, base->gettime(), interval); +} +EXPORT_SYMBOL_GPL(alarm_forward_now); /** @@ -445,7 +490,7 @@ static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp) clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid; if (!alarmtimer_get_rtcdev()) - return -ENOTSUPP; + return -EINVAL; return hrtimer_get_res(baseid, tp); } @@ -462,7 +507,7 @@ static int alarm_clock_get(clockid_t which_clock, struct timespec *tp) struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)]; if (!alarmtimer_get_rtcdev()) - return -ENOTSUPP; + return -EINVAL; *tp = ktime_to_timespec(base->gettime()); return 0; @@ -540,9 +585,14 @@ 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); @@ -552,8 +602,16 @@ static int alarm_timer_set(struct k_itimer *timr, int flags, /* start the timer */ timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval); - alarm_start(&timr->it.alarm.alarmtimer, - timespec_to_ktime(new_setting->it_value)); + 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; } @@ -685,6 +743,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, if (!alarmtimer_get_rtcdev()) return -ENOTSUPP; + if (flags & ~TIMER_ABSTIME) + return -EINVAL; + if (!capable(CAP_WAKE_ALARM)) return -EPERM; diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index c6d6400ee13..9c94c19f130 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -15,44 +15,82 @@ #include <linux/hrtimer.h> #include <linux/init.h> #include <linux/module.h> -#include <linux/notifier.h> #include <linux/smp.h> +#include <linux/device.h> #include "tick-internal.h" /* The registered clock event devices */ static LIST_HEAD(clockevent_devices); static LIST_HEAD(clockevents_released); - -/* Notification for clock events */ -static RAW_NOTIFIER_HEAD(clockevents_chain); - /* Protection for the above */ static DEFINE_RAW_SPINLOCK(clockevents_lock); +/* Protection for unbind operations */ +static DEFINE_MUTEX(clockevents_mutex); -/** - * 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); @@ -108,7 +146,8 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev) { /* Nothing to do if we already reached the limit */ if (dev->min_delta_ns >= MIN_DELTA_LIMIT) { - printk(KERN_WARNING "CE: Reprogramming failure. Giving up\n"); + printk_deferred(KERN_WARNING + "CE: Reprogramming failure. Giving up\n"); dev->next_event.tv64 = KTIME_MAX; return -ETIME; } @@ -121,9 +160,10 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev) 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); + 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; } @@ -232,46 +272,106 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, return (rc && force) ? clockevents_program_min_delta(dev) : rc; } -/** - * clockevents_register_notifier - register a clock events change listener +/* + * Called after a notify add to make devices available which were + * released from the notifier call. */ -int clockevents_register_notifier(struct notifier_block *nb) +static void clockevents_notify_released(void) { - unsigned long flags; - int ret; + struct clock_event_device *dev; - raw_spin_lock_irqsave(&clockevents_lock, flags); - ret = raw_notifier_chain_register(&clockevents_chain, nb); - raw_spin_unlock_irqrestore(&clockevents_lock, flags); + while (!list_empty(&clockevents_released)) { + dev = list_entry(clockevents_released.next, + struct clock_event_device, list); + list_del(&dev->list); + list_add(&dev->list, &clockevent_devices); + tick_check_new_device(dev); + } +} - return ret; +/* + * Try to install a replacement clock event device + */ +static int clockevents_replace(struct clock_event_device *ced) +{ + struct clock_event_device *dev, *newdev = NULL; + + list_for_each_entry(dev, &clockevent_devices, list) { + if (dev == ced || dev->mode != CLOCK_EVT_MODE_UNUSED) + continue; + + if (!tick_check_replacement(newdev, dev)) + continue; + + if (!try_module_get(dev->owner)) + continue; + + if (newdev) + module_put(newdev->owner); + newdev = dev; + } + if (newdev) { + tick_install_replacement(newdev); + list_del_init(&ced->list); + } + return newdev ? 0 : -EBUSY; } /* - * Notify about a clock event change. Called with clockevents_lock - * held. + * Called with clockevents_mutex and clockevents_lock held */ -static void clockevents_do_notify(unsigned long reason, void *dev) +static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu) { - raw_notifier_call_chain(&clockevents_chain, reason, dev); + /* Fast track. Device is unused */ + if (ced->mode == CLOCK_EVT_MODE_UNUSED) { + list_del_init(&ced->list); + return 0; + } + + return ced == per_cpu(tick_cpu_device, cpu).evtdev ? -EAGAIN : -EBUSY; } /* - * Called after a notify add to make devices available which were - * released from the notifier call. + * SMP function call to unbind a device */ -static void clockevents_notify_released(void) +static void __clockevents_unbind(void *arg) { - struct clock_event_device *dev; + struct ce_unbind *cu = arg; + int res; + + raw_spin_lock(&clockevents_lock); + res = __clockevents_try_unbind(cu->ce, smp_processor_id()); + if (res == -EAGAIN) + res = clockevents_replace(cu->ce); + cu->res = res; + raw_spin_unlock(&clockevents_lock); +} - while (!list_empty(&clockevents_released)) { - dev = list_entry(clockevents_released.next, - struct clock_event_device, list); - list_del(&dev->list); - list_add(&dev->list, &clockevent_devices); - clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev); - } +/* + * Issues smp function call to unbind a per cpu device. Called with + * clockevents_mutex held. + */ +static int clockevents_unbind(struct clock_event_device *ced, int cpu) +{ + struct ce_unbind cu = { .ce = ced, .res = -ENODEV }; + + smp_call_function_single(cpu, __clockevents_unbind, &cu, 1); + return cu.res; +} + +/* + * Unbind a clockevents device. + */ +int clockevents_unbind_device(struct clock_event_device *ced, int cpu) +{ + int ret; + + mutex_lock(&clockevents_mutex); + ret = clockevents_unbind(ced, cpu); + mutex_unlock(&clockevents_mutex); + return ret; } +EXPORT_SYMBOL_GPL(clockevents_unbind); /** * clockevents_register_device - register a clock event device @@ -290,7 +390,7 @@ void clockevents_register_device(struct clock_event_device *dev) raw_spin_lock_irqsave(&clockevents_lock, flags); list_add(&dev->list, &clockevent_devices); - clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev); + tick_check_new_device(dev); clockevents_notify_released(); raw_spin_unlock_irqrestore(&clockevents_lock, flags); @@ -317,8 +417,8 @@ void clockevents_config(struct clock_event_device *dev, u32 freq) sec = 600; clockevents_calc_mult_shift(dev, freq, sec); - dev->min_delta_ns = clockevent_delta2ns(dev->min_delta_ticks, dev); - dev->max_delta_ns = clockevent_delta2ns(dev->max_delta_ticks, dev); + dev->min_delta_ns = cev_delta2ns(dev->min_delta_ticks, dev, false); + dev->max_delta_ns = cev_delta2ns(dev->max_delta_ticks, dev, true); } /** @@ -341,6 +441,19 @@ void clockevents_config_and_register(struct clock_event_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 @@ -348,17 +461,22 @@ EXPORT_SYMBOL_GPL(clockevents_config_and_register); * * Reconfigure and reprogram a clock event device in oneshot * mode. Must be called on the cpu for which the device delivers per - * cpu timer events with interrupts disabled! Returns 0 on success, - * -ETIME when the event is in the past. + * 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) { - clockevents_config(dev, freq); - - if (dev->mode != CLOCK_EVT_MODE_ONESHOT) - return 0; + unsigned long flags; + int ret; - return clockevents_program_event(dev, dev->next_event, false); + 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; } /* @@ -386,6 +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); @@ -425,18 +544,45 @@ void clockevents_resume(void) #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. @@ -460,6 +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 c9583382141..ba3e502c955 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -31,6 +31,8 @@ #include <linux/tick.h> #include <linux/kthread.h> +#include "tick-internal.h" + void timecounter_init(struct timecounter *tc, const struct cyclecounter *cc, u64 start_tstamp) @@ -174,11 +176,12 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 maxsec) static struct clocksource *curr_clocksource; static LIST_HEAD(clocksource_list); static DEFINE_MUTEX(clocksource_mutex); -static char override_name[32]; +static char override_name[CS_NAME_LEN]; static int finished_booting; #ifdef CONFIG_CLOCKSOURCE_WATCHDOG static void clocksource_watchdog_work(struct work_struct *work); +static void clocksource_select(void); static LIST_HEAD(watchdog_list); static struct clocksource *watchdog; @@ -299,13 +302,30 @@ static void clocksource_watchdog(unsigned long data) if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) && (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) { + /* Mark it valid for high-res. */ cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; + /* - * We just marked the clocksource as highres-capable, - * notify the rest of the system as well so that we - * transition into high-res mode: + * clocksource_done_booting() will sort it if + * finished_booting is not set yet. */ - tick_clock_notify(); + if (!finished_booting) + continue; + + /* + * 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. + */ + if (cs != curr_clocksource) { + cs->flags |= CLOCK_SOURCE_RESELECT; + schedule_work(&watchdog_work); + } else { + tick_clock_notify(); + } } } @@ -388,44 +408,39 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) static void clocksource_dequeue_watchdog(struct clocksource *cs) { - struct clocksource *tmp; unsigned long flags; spin_lock_irqsave(&watchdog_lock, flags); - if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { - /* cs is a watched clocksource. */ - list_del_init(&cs->wd_list); - } else if (cs == watchdog) { - /* Reset watchdog cycles */ - clocksource_reset_watchdog(); - /* Current watchdog is removed. Find an alternative. */ - watchdog = NULL; - list_for_each_entry(tmp, &clocksource_list, list) { - if (tmp == cs || tmp->flags & CLOCK_SOURCE_MUST_VERIFY) - continue; - if (!watchdog || tmp->rating > watchdog->rating) - watchdog = tmp; + if (cs != watchdog) { + if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { + /* cs is a watched clocksource. */ + list_del_init(&cs->wd_list); + /* Check if the watchdog timer needs to be stopped. */ + clocksource_stop_watchdog(); } } - cs->flags &= ~CLOCK_SOURCE_WATCHDOG; - /* Check if the watchdog timer needs to be stopped. */ - clocksource_stop_watchdog(); spin_unlock_irqrestore(&watchdog_lock, flags); } -static int clocksource_watchdog_kthread(void *data) +static int __clocksource_watchdog_kthread(void) { struct clocksource *cs, *tmp; unsigned long flags; LIST_HEAD(unstable); + int select = 0; - mutex_lock(&clocksource_mutex); spin_lock_irqsave(&watchdog_lock, flags); - list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) + list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) { if (cs->flags & CLOCK_SOURCE_UNSTABLE) { list_del_init(&cs->wd_list); list_add(&cs->wd_list, &unstable); + select = 1; } + if (cs->flags & CLOCK_SOURCE_RESELECT) { + cs->flags &= ~CLOCK_SOURCE_RESELECT; + select = 1; + } + } /* Check if the watchdog timer needs to be stopped. */ clocksource_stop_watchdog(); spin_unlock_irqrestore(&watchdog_lock, flags); @@ -435,10 +450,23 @@ static int clocksource_watchdog_kthread(void *data) list_del_init(&cs->wd_list); __clocksource_change_rating(cs, 0); } + return select; +} + +static int clocksource_watchdog_kthread(void *data) +{ + mutex_lock(&clocksource_mutex); + if (__clocksource_watchdog_kthread()) + clocksource_select(); mutex_unlock(&clocksource_mutex); return 0; } +static bool clocksource_is_watchdog(struct clocksource *cs) +{ + return cs == watchdog; +} + #else /* CONFIG_CLOCKSOURCE_WATCHDOG */ static void clocksource_enqueue_watchdog(struct clocksource *cs) @@ -449,7 +477,9 @@ 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 */ @@ -508,40 +538,55 @@ static u32 clocksource_max_adjustment(struct clocksource *cs) } /** - * clocksource_max_deferment - Returns max time the clocksource can be deferred - * @cs: Pointer to clocksource - * + * 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 */ -static u64 clocksource_max_deferment(struct clocksource *cs) +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+cs->maxadj) + * maximum number of cycles is equal to ULLONG_MAX/(mult+maxadj) * which is equivalent to the below. - * max_cycles < (2^63)/(cs->mult + cs->maxadj) - * max_cycles < 2^(log2((2^63)/(cs->mult + cs->maxadj))) - * max_cycles < 2^(log2(2^63) - log2(cs->mult + cs->maxadj)) - * max_cycles < 2^(63 - log2(cs->mult + cs->maxadj)) - * max_cycles < 1 << (63 - log2(cs->mult + cs->maxadj)) + * 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 + cs->maxadj) + 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->maxadj, - 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 @@ -553,24 +598,42 @@ static u64 clocksource_max_deferment(struct clocksource *cs) #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET -/** - * clocksource_select - Select the best clocksource available - * - * Private function. Must hold clocksource_mutex when called. - * - * Select the clocksource with the best rating, or the clocksource, - * which is selected by userspace override. - */ -static void clocksource_select(void) +static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur) { - struct clocksource *best, *cs; + struct clocksource *cs; if (!finished_booting || list_empty(&clocksource_list)) + return NULL; + + /* + * We pick the clocksource with the highest rating. If oneshot + * mode is active, we pick the highres valid clocksource with + * the best rating. + */ + list_for_each_entry(cs, &clocksource_list, list) { + if (skipcur && cs == curr_clocksource) + continue; + if (oneshot && !(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES)) + continue; + return cs; + } + return NULL; +} + +static void __clocksource_select(bool skipcur) +{ + bool oneshot = tick_oneshot_mode_active(); + struct clocksource *best, *cs; + + /* Find the best suitable clocksource */ + best = clocksource_find_best(oneshot, skipcur); + if (!best) return; - /* First clocksource on the list has the best rating. */ - best = list_first_entry(&clocksource_list, struct clocksource, list); + /* Check for the override clocksource. */ list_for_each_entry(cs, &clocksource_list, list) { + if (skipcur && cs == curr_clocksource) + continue; if (strcmp(cs->name, override_name) != 0) continue; /* @@ -578,8 +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 " @@ -590,16 +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 @@ -614,16 +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; @@ -756,7 +832,6 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating) list_del(&cs->list); cs->rating = rating; clocksource_enqueue(cs); - clocksource_select(); } /** @@ -768,21 +843,47 @@ void clocksource_change_rating(struct clocksource *cs, int rating) { mutex_lock(&clocksource_mutex); __clocksource_change_rating(cs, rating); + clocksource_select(); mutex_unlock(&clocksource_mutex); } EXPORT_SYMBOL(clocksource_change_rating); +/* + * Unbind clocksource @cs. Called with clocksource_mutex held + */ +static int clocksource_unbind(struct clocksource *cs) +{ + /* + * I really can't convince myself to support this on hardware + * designed by lobotomized monkeys. + */ + if (clocksource_is_watchdog(cs)) + return -EBUSY; + + if (cs == curr_clocksource) { + /* Select and try to install a replacement clock source */ + clocksource_select_fallback(); + if (curr_clocksource == cs) + return -EBUSY; + } + clocksource_dequeue_watchdog(cs); + list_del_init(&cs->list); + return 0; +} + /** * clocksource_unregister - remove a registered clocksource * @cs: clocksource to be unregistered */ -void clocksource_unregister(struct clocksource *cs) +int clocksource_unregister(struct clocksource *cs) { + int ret = 0; + mutex_lock(&clocksource_mutex); - clocksource_dequeue_watchdog(cs); - list_del(&cs->list); - clocksource_select(); + if (!list_empty(&cs->list)) + ret = clocksource_unbind(cs); mutex_unlock(&clocksource_mutex); + return ret; } EXPORT_SYMBOL(clocksource_unregister); @@ -808,6 +909,23 @@ sysfs_show_current_clocksources(struct 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 @@ -822,22 +940,13 @@ static ssize_t sysfs_override_clocksource(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - size_t ret = count; - - /* strings from sysfs write are not 0 terminated! */ - if (count >= sizeof(override_name)) - return -EINVAL; - - /* strip of \n: */ - if (buf[count-1] == '\n') - count--; + 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); @@ -845,6 +954,40 @@ static ssize_t sysfs_override_clocksource(struct device *dev, } /** + * sysfs_unbind_current_clocksource - interface for manually unbinding clocksource + * @dev: unused + * @attr: unused + * @buf: unused + * @count: length of buffer + * + * Takes input from sysfs interface for manually unbinding a clocksource. + */ +static ssize_t sysfs_unbind_clocksource(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct clocksource *cs; + char name[CS_NAME_LEN]; + 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 @@ -886,6 +1029,8 @@ sysfs_show_available_clocksources(struct device *dev, static DEVICE_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources, sysfs_override_clocksource); +static DEVICE_ATTR(unbind_clocksource, 0200, NULL, sysfs_unbind_clocksource); + static DEVICE_ATTR(available_clocksource, 0444, sysfs_show_available_clocksources, NULL); @@ -910,6 +1055,9 @@ static int __init init_clocksource_sysfs(void) &device_clocksource, &dev_attr_current_clocksource); if (!error) + error = device_create_file(&device_clocksource, + &dev_attr_unbind_clocksource); + if (!error) error = device_create_file( &device_clocksource, &dev_attr_available_clocksource); diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 7a925ba456f..a6a5bf53e86 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -51,7 +51,13 @@ * 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) { diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 8f5b3b98577..33db43a3951 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -165,21 +165,21 @@ static inline void pps_set_freq(s64 freq) static inline int is_error_status(int status) { - return (time_status & (STA_UNSYNC|STA_CLOCKERR)) + return (status & (STA_UNSYNC|STA_CLOCKERR)) /* PPS signal lost when either PPS time or * PPS frequency synchronization requested */ - || ((time_status & (STA_PPSFREQ|STA_PPSTIME)) - && !(time_status & STA_PPSSIGNAL)) + || ((status & (STA_PPSFREQ|STA_PPSTIME)) + && !(status & STA_PPSSIGNAL)) /* PPS jitter exceeded when * PPS time synchronization requested */ - || ((time_status & (STA_PPSTIME|STA_PPSJITTER)) + || ((status & (STA_PPSTIME|STA_PPSJITTER)) == (STA_PPSTIME|STA_PPSJITTER)) /* PPS wander exceeded or calibration error when * PPS frequency synchronization requested */ - || ((time_status & STA_PPSFREQ) - && (time_status & (STA_PPSWANDER|STA_PPSERROR))); + || ((status & STA_PPSFREQ) + && (status & (STA_PPSWANDER|STA_PPSERROR))); } static inline void pps_fill_timex(struct timex *txc) @@ -475,6 +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()) { /* @@ -485,7 +486,7 @@ static void sync_cmos_clock(struct work_struct *work) } getnstimeofday(&now); - if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2) { + if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) { struct timespec adjust = now; fail = -ENODEV; @@ -513,16 +514,17 @@ 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) { - 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 @@ -687,8 +689,6 @@ int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai) if (!(time_status & STA_NANO)) txc->time.tv_usec /= NSEC_PER_USEC; - notify_cmos_timer(); - return result; } @@ -786,8 +786,9 @@ static long hardpps_update_freq(struct pps_normtime freq_norm) time_status |= STA_PPSERROR; pps_errcnt++; pps_dec_freq_interval(); - pr_err("hardpps: PPSERROR: interval too long - %ld s\n", - freq_norm.sec); + printk_deferred(KERN_ERR + "hardpps: PPSERROR: interval too long - %ld s\n", + freq_norm.sec); return 0; } @@ -800,7 +801,8 @@ static long hardpps_update_freq(struct pps_normtime freq_norm) delta = shift_right(ftemp - pps_freq, NTP_SCALE_SHIFT); pps_freq = ftemp; if (delta > PPS_MAXWANDER || delta < -PPS_MAXWANDER) { - pr_warning("hardpps: PPSWANDER: change=%ld\n", delta); + printk_deferred(KERN_WARNING + "hardpps: PPSWANDER: change=%ld\n", delta); time_status |= STA_PPSWANDER; pps_stbcnt++; pps_dec_freq_interval(); @@ -844,8 +846,9 @@ static void hardpps_update_phase(long error) * the time offset is updated. */ if (jitter > (pps_jitter << PPS_POPCORN)) { - pr_warning("hardpps: PPSJITTER: jitter=%ld, limit=%ld\n", - jitter, (pps_jitter << PPS_POPCORN)); + 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) { @@ -902,7 +905,7 @@ void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) time_status |= STA_PPSJITTER; /* restart the frequency calibration interval */ pps_fbase = *raw_ts; - pr_err("hardpps: PPSJITTER: bad pulse\n"); + printk_deferred(KERN_ERR "hardpps: PPSJITTER: bad pulse\n"); return; } @@ -923,7 +926,10 @@ void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) 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; 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 0c739423b0f..64c5990fd50 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -19,6 +19,7 @@ #include <linux/profile.h> #include <linux/sched.h> #include <linux/smp.h> +#include <linux/module.h> #include "tick-internal.h" @@ -29,6 +30,7 @@ static struct tick_device tick_broadcast_device; static cpumask_var_t tick_broadcast_mask; +static cpumask_var_t tick_broadcast_on; static cpumask_var_t tmpmask; static DEFINE_RAW_SPINLOCK(tick_broadcast_lock); static int tick_broadcast_force; @@ -64,17 +66,35 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc) /* * Check, if the device can be utilized as broadcast device: */ -int tick_check_broadcast_device(struct clock_event_device *dev) +static bool tick_check_broadcast_device(struct clock_event_device *curdev, + struct clock_event_device *newdev) +{ + if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) || + (newdev->features & CLOCK_EVT_FEAT_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 ((dev->features & CLOCK_EVT_FEAT_DUMMY) || - (tick_broadcast_device.evtdev && - tick_broadcast_device.evtdev->rating >= dev->rating) || - (dev->features & CLOCK_EVT_FEAT_C3STOP)) - return 0; + if (!tick_check_broadcast_device(cur, dev)) + return; + + if (!try_module_get(dev->owner)) + return; - clockevents_exchange_device(tick_broadcast_device.evtdev, dev); + clockevents_exchange_device(cur, dev); if (cur) cur->event_handler = clockevents_handle_noop; tick_broadcast_device.evtdev = dev; @@ -90,7 +110,6 @@ int tick_check_broadcast_device(struct clock_event_device *dev) */ if (dev->features & CLOCK_EVT_FEAT_ONESHOT) tick_clock_notify(); - return 1; } /* @@ -101,6 +120,19 @@ 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"); @@ -123,8 +155,9 @@ static void tick_device_setup_broadcast_func(struct clock_event_device *dev) */ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { + struct clock_event_device *bc = tick_broadcast_device.evtdev; unsigned long flags; - int ret = 0; + int ret; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); @@ -138,20 +171,62 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) dev->event_handler = tick_handle_periodic; tick_device_setup_broadcast_func(dev); cpumask_set_cpu(cpu, tick_broadcast_mask); - tick_broadcast_start_periodic(tick_broadcast_device.evtdev); + 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); - tick_broadcast_clear_oneshot(cpu); - } else { + else tick_device_setup_broadcast_func(dev); + + /* + * Clear the broadcast bit if the CPU is not in + * periodic broadcast on state. + */ + if (!cpumask_test_cpu(cpu, tick_broadcast_on)) + cpumask_clear_cpu(cpu, tick_broadcast_mask); + + switch (tick_broadcast_device.mode) { + case TICKDEV_MODE_ONESHOT: + /* + * If the system is in oneshot mode we can + * unconditionally clear the oneshot mask bit, + * because the CPU is running and therefore + * not in an idle state which causes the power + * state affected device to stop. Let the + * caller initialize the device. + */ + tick_broadcast_clear_oneshot(cpu); + ret = 0; + break; + + case TICKDEV_MODE_PERIODIC: + /* + * If the system is in periodic mode, check + * whether the broadcast device can be + * switched off now. + */ + if (cpumask_empty(tick_broadcast_mask) && bc) + clockevents_shutdown(bc); + /* + * If we kept the cpu in the broadcast mask, + * tell the caller to leave the per cpu device + * in shutdown state. The periodic interrupt + * is delivered by the broadcast device. + */ + ret = cpumask_test_cpu(cpu, tick_broadcast_mask); + break; + default: + /* Nothing to do */ + ret = 0; + break; } } raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); @@ -210,12 +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(tmpmask, cpu_online_mask, tick_broadcast_mask); tick_do_broadcast(tmpmask); - - raw_spin_unlock(&tick_broadcast_lock); } /* @@ -225,13 +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 @@ -244,9 +317,11 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) next = ktime_add(next, tick_period); if (!clockevents_program_event(dev, next, false)) - return; + goto unlock; tick_do_periodic_broadcast(); } +unlock: + raw_spin_unlock(&tick_broadcast_lock); } /* @@ -281,6 +356,7 @@ static void tick_do_broadcast_on_off(unsigned long *reason) switch (*reason) { case CLOCK_EVT_NOTIFY_BROADCAST_ON: case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: + cpumask_set_cpu(cpu, tick_broadcast_on); if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) { if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) @@ -290,8 +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_and_clear_cpu(cpu, tick_broadcast_mask)) { + if (tick_broadcast_force) + break; + cpumask_clear_cpu(cpu, tick_broadcast_on); + if (!tick_device_is_functional(dev)) + break; + if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) { if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) tick_setup_periodic(dev, 0); @@ -349,6 +429,7 @@ void tick_shutdown_broadcast(unsigned int *cpup) bc = tick_broadcast_device.evtdev; cpumask_clear_cpu(cpu, tick_broadcast_mask); + cpumask_clear_cpu(cpu, tick_broadcast_on); if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) { if (bc && cpumask_empty(tick_broadcast_mask)) @@ -470,12 +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, 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); + } } } @@ -522,6 +611,13 @@ again: cpumask_clear(tick_broadcast_force_mask); /* + * Sanity check. Catch the case where we try to broadcast to + * offline cpus. + */ + if (WARN_ON_ONCE(!cpumask_subset(tmpmask, cpu_online_mask))) + cpumask_and(tmpmask, tmpmask, cpu_online_mask); + + /* * Wakeup the cpus which have an expired event. */ tick_do_broadcast(tmpmask); @@ -547,24 +643,61 @@ 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; ktime_t now; - int cpu; + int cpu, ret = 0; /* * Periodic mode does not care about the enter/exit of power * states */ if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) - return; + return 0; /* * We are called with preemtion disabled from the depth of the @@ -575,7 +708,7 @@ void tick_broadcast_oneshot_control(unsigned long reason) dev = td->evtdev; if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) - return; + return 0; bc = tick_broadcast_device.evtdev; @@ -583,7 +716,7 @@ void tick_broadcast_oneshot_control(unsigned long reason) if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) { if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) { WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask)); - clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN); + broadcast_shutdown_local(bc, dev); /* * We only reprogram the broadcast timer if we * did not mark ourself in the force mask and @@ -596,11 +729,19 @@ void tick_broadcast_oneshot_control(unsigned long reason) 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_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) { clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); - if (dev->next_event.tv64 == KTIME_MAX) - goto out; /* * The cpu which was handling the broadcast * timer marked this cpu in the broadcast @@ -615,6 +756,11 @@ void tick_broadcast_oneshot_control(unsigned long reason) 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. @@ -660,6 +806,7 @@ void tick_broadcast_oneshot_control(unsigned long reason) } out: raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); + return ret; } /* @@ -670,6 +817,7 @@ out: static void tick_broadcast_clear_oneshot(int cpu) { 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, @@ -698,10 +846,6 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) bc->event_handler = tick_handle_oneshot_broadcast; - /* Take the do_timer update */ - if (!tick_nohz_full_cpu(cpu)) - tick_do_timer_cpu = cpu; - /* * We must be careful here. There might be other CPUs * waiting for periodic broadcast. We need to set the @@ -762,10 +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_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); } @@ -793,6 +941,7 @@ bool tick_broadcast_oneshot_available(void) void __init tick_broadcast_init(void) { zalloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT); + zalloc_cpumask_var(&tick_broadcast_on, GFP_NOWAIT); zalloc_cpumask_var(&tmpmask, GFP_NOWAIT); #ifdef CONFIG_TICK_ONESHOT zalloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT); diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 5d3fb100bc0..0a0608edeb2 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -18,6 +18,7 @@ #include <linux/percpu.h> #include <linux/profile.h> #include <linux/sched.h> +#include <linux/module.h> #include <asm/irq_regs.h> @@ -32,8 +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 @@ -70,6 +85,7 @@ static void tick_periodic(int cpu) do_timer(1); write_sequnlock(&jiffies_lock); + update_wall_time(); } update_process_times(user_mode(get_irq_regs())); @@ -82,18 +98,19 @@ 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 (;;) { + /* + * 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; /* @@ -102,12 +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); } } @@ -194,7 +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; @@ -205,17 +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)) @@ -225,40 +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 @@ -273,20 +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); } /* @@ -294,7 +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); @@ -311,13 +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) { /* @@ -329,26 +370,20 @@ static void tick_shutdown(unsigned int *cpup) dev->event_handler = clockevents_handle_noop; td->evtdev = NULL; } - raw_spin_unlock_irqrestore(&tick_device_lock, flags); } -static void tick_suspend(void) +void tick_suspend(void) { struct tick_device *td = &__get_cpu_var(tick_cpu_device); - unsigned long flags; - raw_spin_lock_irqsave(&tick_device_lock, flags); clockevents_shutdown(td->evtdev); - raw_spin_unlock_irqrestore(&tick_device_lock, flags); } -static void tick_resume(void) +void tick_resume(void) { struct tick_device *td = &__get_cpu_var(tick_cpu_device); - unsigned long flags; int broadcast = tick_resume_broadcast(); - raw_spin_lock_irqsave(&tick_device_lock, flags); clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME); if (!broadcast) { @@ -357,68 +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 f0299eae460..7ab92b19965 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -6,6 +6,8 @@ extern seqlock_t jiffies_lock; +#define CS_NAME_LEN 32 + #ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD #define TICK_DO_TIMER_NONE -1 @@ -18,9 +20,19 @@ extern int tick_do_timer_cpu __read_mostly; extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast); extern void tick_handle_periodic(struct clock_event_device *dev); +extern void tick_check_new_device(struct clock_event_device *dev); +extern void tick_handover_do_timer(int *cpup); +extern void tick_shutdown(unsigned int *cpup); +extern void tick_suspend(void); +extern void tick_resume(void); +extern bool tick_check_replacement(struct clock_event_device *curdev, + struct clock_event_device *newdev); +extern void tick_install_replacement(struct clock_event_device *dev); extern void clockevents_shutdown(struct clock_event_device *dev); +extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); + /* * NO_HZ / high resolution timer shared code */ @@ -34,23 +46,23 @@ 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 */ @@ -75,7 +87,7 @@ 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) { @@ -90,7 +102,7 @@ static inline bool tick_broadcast_oneshot_available(void) { return false; } */ #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); -extern int tick_check_broadcast_device(struct clock_event_device *dev); +extern void tick_install_broadcast_device(struct clock_event_device *dev); extern int tick_is_broadcast_device(struct clock_event_device *dev); extern void tick_broadcast_on_off(unsigned long reason, int *oncpu); extern void tick_shutdown_broadcast(unsigned int *cpup); @@ -99,12 +111,12 @@ 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) @@ -122,6 +134,8 @@ 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 @@ -141,6 +155,9 @@ 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-sched.c b/kernel/time/tick-sched.c index f4208138fbf..6558b7ac112 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -23,6 +23,7 @@ #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> @@ -83,8 +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(&jiffies_lock); + update_wall_time(); } /* @@ -148,8 +153,8 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) } #ifdef CONFIG_NO_HZ_FULL -static cpumask_var_t nohz_full_mask; -bool have_nohz_full_mask; +cpumask_var_t tick_nohz_full_mask; +bool tick_nohz_full_running; static bool can_stop_full_tick(void) { @@ -176,8 +181,14 @@ static bool can_stop_full_tick(void) * TODO: kick full dynticks CPUs when * sched_clock_stable is set. */ - if (!sched_clock_stable) { + 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 @@ -191,7 +202,7 @@ 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) +void __tick_nohz_full_check(void) { struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); @@ -205,7 +216,7 @@ void tick_nohz_full_check(void) static void nohz_full_kick_work_func(struct irq_work *work) { - tick_nohz_full_check(); + __tick_nohz_full_check(); } static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { @@ -224,7 +235,7 @@ void tick_nohz_full_kick(void) static void nohz_full_kick_ipi(void *info) { - tick_nohz_full_check(); + __tick_nohz_full_check(); } /* @@ -233,12 +244,13 @@ static void nohz_full_kick_ipi(void *info) */ void tick_nohz_full_kick_all(void) { - if (!have_nohz_full_mask) + if (!tick_nohz_full_running) return; preempt_disable(); - smp_call_function_many(nohz_full_mask, + smp_call_function_many(tick_nohz_full_mask, nohz_full_kick_ipi, NULL, false); + tick_nohz_full_kick(); preempt_enable(); } @@ -247,7 +259,7 @@ void tick_nohz_full_kick_all(void) * 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) +void __tick_nohz_task_switch(struct task_struct *tsk) { unsigned long flags; @@ -263,37 +275,29 @@ out: local_irq_restore(flags); } -int tick_nohz_full_cpu(int cpu) -{ - if (!have_nohz_full_mask) - return 0; - - return cpumask_test_cpu(cpu, nohz_full_mask); -} - /* 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(&nohz_full_mask); - if (cpulist_parse(str, nohz_full_mask) < 0) { + 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, nohz_full_mask)) { + 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, nohz_full_mask); + cpumask_clear_cpu(cpu, tick_nohz_full_mask); } - have_nohz_full_mask = true; + tick_nohz_full_running = true; return 1; } __setup("nohz_full=", tick_nohz_full_setup); -static int __cpuinit tick_nohz_cpu_down_callback(struct notifier_block *nfb, +static int tick_nohz_cpu_down_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -305,8 +309,8 @@ static int __cpuinit tick_nohz_cpu_down_callback(struct notifier_block *nfb, * If we handle the timekeeping duty for full dynticks CPUs, * we can't safely shutdown that CPU. */ - if (have_nohz_full_mask && tick_do_timer_cpu == cpu) - return -EINVAL; + if (tick_nohz_full_running && tick_do_timer_cpu == cpu) + return NOTIFY_BAD; break; } return NOTIFY_OK; @@ -324,14 +328,14 @@ static int tick_nohz_init_all(void) int err = -1; #ifdef CONFIG_NO_HZ_FULL_ALL - if (!alloc_cpumask_var(&nohz_full_mask, GFP_KERNEL)) { + 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(nohz_full_mask); - cpumask_clear_cpu(smp_processor_id(), nohz_full_mask); - have_nohz_full_mask = true; + cpumask_setall(tick_nohz_full_mask); + cpumask_clear_cpu(smp_processor_id(), tick_nohz_full_mask); + tick_nohz_full_running = true; #endif return err; } @@ -340,27 +344,18 @@ void __init tick_nohz_init(void) { int cpu; - if (!have_nohz_full_mask) { + if (!tick_nohz_full_running) { if (tick_nohz_init_all() < 0) return; } - cpu_notifier(tick_nohz_cpu_down_callback, 0); + for_each_cpu(cpu, tick_nohz_full_mask) + context_tracking_cpu_set(cpu); - /* Make sure full dynticks CPU are also RCU nocbs */ - for_each_cpu(cpu, nohz_full_mask) { - if (!rcu_is_nocb_cpu(cpu)) { - pr_warning("NO_HZ: CPU %d is not RCU nocb: " - "cleared from nohz_full range", cpu); - cpumask_clear_cpu(cpu, nohz_full_mask); - } - } - - cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), nohz_full_mask); + 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); } -#else -#define have_nohz_full_mask (0) #endif /* @@ -370,8 +365,8 @@ void __init tick_nohz_init(void) /* * NO HZ enabled ? */ -int tick_nohz_enabled __read_mostly = 1; - +static int tick_nohz_enabled __read_mostly = 1; +int tick_nohz_active __read_mostly; /* * Enable / Disable tickless mode */ @@ -400,11 +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; - ts->idle_waketime = now; + __this_cpu_write(tick_cpu_sched.idle_waketime, now); local_irq_save(flags); tick_do_update_jiffies64(now); @@ -435,17 +428,15 @@ 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 = ktime_get(); @@ -474,7 +465,7 @@ 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; now = ktime_get(); @@ -515,7 +506,7 @@ 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; now = ktime_get(); @@ -545,12 +536,13 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev; u64 time_delta; + time_delta = timekeeping_max_deferment(); + /* Read jiffies and the time when jiffies were updated last */ do { seq = read_seqbegin(&jiffies_lock); last_update = last_jiffies_update; last_jiffies = jiffies; - time_delta = timekeeping_max_deferment(); } while (read_seqretry(&jiffies_lock, seq)); if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || @@ -690,18 +682,18 @@ out: static void tick_nohz_full_stop_tick(struct tick_sched *ts) { #ifdef CONFIG_NO_HZ_FULL - int cpu = smp_processor_id(); + int cpu = smp_processor_id(); - if (!tick_nohz_full_cpu(cpu) || is_idle_task(current)) - return; + if (!tick_nohz_full_cpu(cpu) || is_idle_task(current)) + return; - if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE) - return; + if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE) + return; - if (!can_stop_full_tick()) - return; + if (!can_stop_full_tick()) + return; - tick_nohz_stop_sched_tick(ts, ktime_get(), cpu); + tick_nohz_stop_sched_tick(ts, ktime_get(), cpu); #endif } @@ -720,8 +712,10 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; } - if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) + 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; @@ -738,7 +732,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; } - if (have_nohz_full_mask) { + if (tick_nohz_full_enabled()) { /* * Keep the tick alive to guarantee timekeeping progression * if there are full dynticks CPUs around @@ -761,7 +755,7 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts) ktime_t now, expires; int cpu = smp_processor_id(); - now = tick_nohz_start_idle(cpu, ts); + now = tick_nohz_start_idle(ts); if (can_stop_idle_tick(cpu, ts)) { int was_stopped = ts->tick_stopped; @@ -808,11 +802,6 @@ void tick_nohz_idle_enter(void) local_irq_disable(); ts = &__get_cpu_var(tick_cpu_sched); - /* - * 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; __tick_nohz_idle_enter(ts); @@ -832,13 +821,10 @@ void tick_nohz_irq_exit(void) { struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); - if (ts->inidle) { - /* Cancel the timer because CPU already waken up from the C-states*/ - menu_hrtimer_cancel(); + if (ts->inidle) __tick_nohz_idle_enter(ts); - } else { + else tick_nohz_full_stop_tick(ts); - } } /** @@ -926,8 +912,7 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts) */ void tick_nohz_idle_exit(void) { - int cpu = smp_processor_id(); - struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); ktime_t now; local_irq_disable(); @@ -936,13 +921,11 @@ void tick_nohz_idle_exit(void) ts->inidle = 0; - /* Cancel the timer because CPU already waken up from the C-states*/ - menu_hrtimer_cancel(); if (ts->idle_active || ts->tick_stopped) 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_restart_sched_tick(ts, now); @@ -995,7 +978,7 @@ static void tick_nohz_switch_to_nohz(void) local_irq_enable(); return; } - + tick_nohz_active = 1; ts->nohz_mode = NOHZ_MODE_LOWRES; /* @@ -1026,12 +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; /* @@ -1046,36 +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 /* 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(); } /* @@ -1153,8 +1134,10 @@ void tick_setup_sched_timer(void) } #ifdef CONFIG_NO_HZ_COMMON - if (tick_nohz_enabled) + if (tick_nohz_enabled) { ts->nohz_mode = NOHZ_MODE_HIGHRES; + tick_nohz_active = 1; + } #endif } #endif /* HIGH_RES_TIMERS */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index baeeb5c87cf..32d8d6aaedb 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -22,9 +22,15 @@ #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> +#include <linux/compiler.h> #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); @@ -72,7 +78,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm) 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_sub(tk->offs_real, ktime_set(tk->tai_offset, 0)); + 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) @@ -85,8 +91,9 @@ static void tk_set_sleep_time(struct timekeeper *tk, struct timespec 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 @@ -200,9 +207,9 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); -static void update_pvclock_gtod(struct timekeeper *tk) +static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) { - raw_notifier_call_chain(&pvclock_gtod_chain, 0, tk); + raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); } /** @@ -216,7 +223,7 @@ int pvclock_gtod_register_notifier(struct notifier_block *nb) raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); - update_pvclock_gtod(tk); + update_pvclock_gtod(tk, true); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; @@ -241,16 +248,16 @@ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* must hold timekeeper_lock */ -static void timekeeping_update(struct timekeeper *tk, bool clearntp, bool mirror) +static void timekeeping_update(struct timekeeper *tk, unsigned int action) { - if (clearntp) { + if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(); } update_vsyscall(tk); - update_pvclock_gtod(tk); + update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); - if (mirror) + if (action & TK_MIRROR) memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper)); } @@ -508,7 +515,7 @@ int do_settimeofday(const struct timespec *tv) tk_set_xtime(tk, tv); - timekeeping_update(tk, true, true); + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -552,7 +559,7 @@ int timekeeping_inject_offset(struct timespec *ts) tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *ts)); error: /* even if we error out, we forwarded the time, so call update */ - timekeeping_update(tk, true, true); + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -590,7 +597,7 @@ s32 timekeeping_get_tai_offset(void) static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) { tk->tai_offset = tai_offset; - tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tai_offset, 0)); + tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); } /** @@ -605,6 +612,7 @@ void timekeeping_set_tai_offset(s32 tai_offset) 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(); @@ -627,13 +635,22 @@ static int change_clocksource(void *data) write_seqcount_begin(&timekeeper_seq); timekeeping_forward_now(tk); - if (!new->enable || new->enable(new) == 0) { - old = tk->clock; - tk_setup_internals(tk, new); - if (old->disable) - old->disable(old); + /* + * If the cs is in module, get a module reference. Succeeds + * for built-in code (owner == NULL) as well. + */ + if (try_module_get(new->owner)) { + if (!new->enable || new->enable(new) == 0) { + old = tk->clock; + tk_setup_internals(tk, new); + if (old->disable) + old->disable(old); + module_put(old->owner); + } else { + module_put(new->owner); + } } - timekeeping_update(tk, true, true); + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -648,14 +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) { struct timekeeper *tk = &timekeeper; if (tk->clock == clock) - return; + return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); + return tk->clock == clock ? 0 : -1; } /** @@ -743,7 +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; @@ -758,7 +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; @@ -834,13 +852,15 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, struct timespec *delta) { if (!timespec_valid_strict(delta)) { - printk(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " - "sleep delta value!\n"); + 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); } /** @@ -872,7 +892,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta) __timekeeping_inject_sleeptime(tk, delta); - timekeeping_update(tk, true, true); + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -954,7 +974,7 @@ static void timekeeping_resume(void) tk->cycle_last = clock->cycle_last = cycle_now; tk->ntp_error = 0; timekeeping_suspended = 0; - timekeeping_update(tk, false, true); + timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -1007,6 +1027,8 @@ static int timekeeping_suspend(void) 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); @@ -1114,16 +1136,6 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) * we can adjust by 1. */ error >>= 2; - /* - * XXX - In update_wall_time, we round up to the next - * nanosecond, and store the amount rounded up into - * the error. This causes the likely below to be unlikely. - * - * The proper fix is to avoid rounding up by using - * the high precision tk->xtime_nsec instead of - * xtime.tv_nsec everywhere. Fixing this will take some - * time. - */ if (likely(error <= interval)) adj = 1; else @@ -1146,7 +1158,7 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) if (unlikely(tk->clock->maxadj && (tk->mult + adj > tk->clock->mult + tk->clock->maxadj))) { - printk_once(KERN_WARNING + 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); @@ -1236,9 +1248,10 @@ out_adjust: * It also calls into the NTP code to handle leapsecond processing. * */ -static inline void accumulate_nsecs_to_secs(struct timekeeper *tk) +static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { u64 nsecps = (u64)NSEC_PER_SEC << tk->shift; + unsigned int clock_set = 0; while (tk->xtime_nsec >= nsecps) { int leap; @@ -1260,9 +1273,10 @@ static inline void accumulate_nsecs_to_secs(struct timekeeper *tk) __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); - clock_was_set_delayed(); + clock_set = TK_CLOCK_WAS_SET; } } + return clock_set; } /** @@ -1275,7 +1289,8 @@ static inline void accumulate_nsecs_to_secs(struct timekeeper *tk) * Returns the unconsumed cycles. */ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, - u32 shift) + u32 shift, + unsigned int *clock_set) { cycle_t interval = tk->cycle_interval << shift; u64 raw_nsecs; @@ -1289,7 +1304,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, tk->cycle_last += interval; tk->xtime_nsec += tk->xtime_interval << shift; - accumulate_nsecs_to_secs(tk); + *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ raw_nsecs = (u64)tk->raw_interval << shift; @@ -1328,7 +1343,7 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk) 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) @@ -1340,13 +1355,14 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk) * update_wall_time - Uses the current clocksource to increment the wall time * */ -static void update_wall_time(void) +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); @@ -1381,7 +1397,8 @@ static void update_wall_time(void) maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); while (offset >= tk->cycle_interval) { - offset = logarithmic_accumulation(tk, offset, shift); + offset = logarithmic_accumulation(tk, offset, shift, + &clock_set); if (offset < tk->cycle_interval<<shift) shift--; } @@ -1399,7 +1416,7 @@ static void update_wall_time(void) * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ - accumulate_nsecs_to_secs(tk); + clock_set |= accumulate_nsecs_to_secs(tk); write_seqcount_begin(&timekeeper_seq); /* Update clock->cycle_last with the new value */ @@ -1415,10 +1432,13 @@ static void update_wall_time(void) * updating. */ memcpy(real_tk, tk, sizeof(*tk)); - timekeeping_update(real_tk, false, false); + 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(); } /** @@ -1563,7 +1583,6 @@ struct timespec get_monotonic_coarse(void) void do_timer(unsigned long ticks) { jiffies_64 += ticks; - update_wall_time(); calc_global_load(ticks); } @@ -1593,9 +1612,10 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, * 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_interupt() or retrigger_next_event() + * 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) @@ -1677,11 +1697,16 @@ int do_adjtimex(struct timex *txc) if (tai != orig_tai) { __timekeeping_set_tai_offset(tk, tai); - clock_was_set_delayed(); + 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; } @@ -1715,4 +1740,5 @@ 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 3bdf2832301..61ed862cdd3 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -265,10 +265,9 @@ static inline void timer_list_header(struct seq_file *m, u64 now) static int timer_list_show(struct seq_file *m, void *v) { struct timer_list_iter *iter = v; - u64 now = ktime_to_ns(ktime_get()); if (iter->cpu == -1 && !iter->second_pass) - timer_list_header(m, now); + timer_list_header(m, iter->now); else if (!iter->second_pass) print_cpu(m, iter->cpu, iter->now); #ifdef CONFIG_GENERIC_CLOCKEVENTS @@ -298,33 +297,41 @@ void sysrq_timer_list_show(void) return; } -static void *timer_list_start(struct seq_file *file, loff_t *offset) +static void *move_iter(struct timer_list_iter *iter, loff_t offset) { - struct timer_list_iter *iter = file->private; - - if (!*offset) { - iter->cpu = -1; - iter->now = ktime_to_ns(ktime_get()); - } else if (iter->cpu >= nr_cpu_ids) { + 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; + if (!iter->second_pass) { + iter->cpu = -1; + iter->second_pass = true; + } else + return NULL; #else - return NULL; + return NULL; #endif + } } return iter; } +static void *timer_list_start(struct seq_file *file, loff_t *offset) +{ + struct timer_list_iter *iter = file->private; + + if (!*offset) + iter->now = ktime_to_ns(ktime_get()); + iter->cpu = -1; + iter->second_pass = false; + return move_iter(iter, *offset); +} + static void *timer_list_next(struct seq_file *file, void *v, loff_t *offset) { struct timer_list_iter *iter = file->private; - iter->cpu = cpumask_next(iter->cpu, cpu_online_mask); ++*offset; - return timer_list_start(file, offset); + return move_iter(iter, 1); } static void timer_list_stop(struct seq_file *seq, void *v) diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c index 0b537f27b55..1fb08f21302 100644 --- a/kernel/time/timer_stats.c +++ b/kernel/time/timer_stats.c @@ -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 { |