diff options
Diffstat (limited to 'kernel/time')
| -rw-r--r-- | kernel/time/Makefile | 2 | ||||
| -rw-r--r-- | kernel/time/tick-common.c | 8 | ||||
| -rw-r--r-- | kernel/time/tick-internal.h | 1 | ||||
| -rw-r--r-- | kernel/time/tick-sched.c | 51 | ||||
| -rw-r--r-- | kernel/time/timekeeping.c | 476 | ||||
| -rw-r--r-- | kernel/time/timer_list.c | 15 | ||||
| -rw-r--r-- | kernel/time/timer_stats.c | 14 |
7 files changed, 544 insertions, 23 deletions
diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 93bccba1f26..99b6034fc86 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -1,4 +1,4 @@ -obj-y += ntp.o clocksource.o jiffies.o timer_list.o +obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o obj-$(CONFIG_GENERIC_CLOCKEVENTS) += clockevents.o obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index bfda3f7f071..a96ec9ab345 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -31,7 +31,7 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device); */ ktime_t tick_next_period; ktime_t tick_period; -static int tick_do_timer_cpu = -1; +int tick_do_timer_cpu __read_mostly = -1; DEFINE_SPINLOCK(tick_device_lock); /* @@ -295,6 +295,12 @@ static void tick_shutdown(unsigned int *cpup) clockevents_exchange_device(dev, NULL); td->evtdev = NULL; } + /* Transfer the do_timer job away from this cpu */ + if (*cpup == tick_do_timer_cpu) { + int cpu = first_cpu(cpu_online_map); + + tick_do_timer_cpu = (cpu != NR_CPUS) ? cpu : -1; + } spin_unlock_irqrestore(&tick_device_lock, flags); } diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index c9d203bde51..bb13f272490 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -5,6 +5,7 @@ DECLARE_PER_CPU(struct tick_device, tick_cpu_device); extern spinlock_t tick_device_lock; extern ktime_t tick_next_period; extern ktime_t tick_period; +extern int tick_do_timer_cpu __read_mostly; extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast); extern void tick_handle_periodic(struct clock_event_device *dev); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 51556b95f60..3483e6cb954 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -217,10 +217,30 @@ void tick_nohz_stop_sched_tick(void) * the scheduler tick in nohz_restart_sched_tick. */ if (!ts->tick_stopped) { + if (select_nohz_load_balancer(1)) { + /* + * sched tick not stopped! + */ + cpu_clear(cpu, nohz_cpu_mask); + goto out; + } + ts->idle_tick = ts->sched_timer.expires; ts->tick_stopped = 1; ts->idle_jiffies = last_jiffies; } + + /* + * If this cpu is the one which updates jiffies, then + * give up the assignment and let it be taken by the + * cpu which runs the tick timer next, which might be + * this cpu as well. If we don't drop this here the + * jiffies might be stale and do_timer() never + * invoked. + */ + if (cpu == tick_do_timer_cpu) + tick_do_timer_cpu = -1; + /* * calculate the expiry time for the next timer wheel * timer @@ -273,6 +293,7 @@ void tick_nohz_restart_sched_tick(void) now = ktime_get(); local_irq_disable(); + select_nohz_load_balancer(0); tick_do_update_jiffies64(now); cpu_clear(cpu, nohz_cpu_mask); @@ -338,12 +359,24 @@ static void tick_nohz_handler(struct clock_event_device *dev) { struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); struct pt_regs *regs = get_irq_regs(); + int cpu = smp_processor_id(); ktime_t now = ktime_get(); dev->next_event.tv64 = KTIME_MAX; + /* + * Check if the do_timer duty was dropped. We don't care about + * concurrency: This happens only when the cpu in charge went + * into a long sleep. If two cpus happen to assign themself to + * this duty, then the jiffies update is still serialized by + * xtime_lock. + */ + if (unlikely(tick_do_timer_cpu == -1)) + tick_do_timer_cpu = cpu; + /* Check, if the jiffies need an update */ - tick_do_update_jiffies64(now); + if (tick_do_timer_cpu == cpu) + tick_do_update_jiffies64(now); /* * When we are idle and the tick is stopped, we have to touch @@ -431,9 +464,23 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) struct hrtimer_cpu_base *base = timer->base->cpu_base; struct pt_regs *regs = get_irq_regs(); ktime_t now = ktime_get(); + int cpu = smp_processor_id(); + +#ifdef CONFIG_NO_HZ + /* + * Check if the do_timer duty was dropped. We don't care about + * concurrency: This happens only when the cpu in charge went + * into a long sleep. If two cpus happen to assign themself to + * this duty, then the jiffies update is still serialized by + * xtime_lock. + */ + if (unlikely(tick_do_timer_cpu == -1)) + tick_do_timer_cpu = cpu; +#endif /* Check, if the jiffies need an update */ - tick_do_update_jiffies64(now); + if (tick_do_timer_cpu == cpu) + tick_do_update_jiffies64(now); /* * Do not call, when we are not in irq context and have diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c new file mode 100644 index 00000000000..f9217bf644f --- /dev/null +++ b/kernel/time/timekeeping.c @@ -0,0 +1,476 @@ +/* + * linux/kernel/time/timekeeping.c + * + * Kernel timekeeping code and accessor functions + * + * This code was moved from linux/kernel/timer.c. + * Please see that file for copyright and history logs. + * + */ + +#include <linux/module.h> +#include <linux/interrupt.h> +#include <linux/percpu.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/sysdev.h> +#include <linux/clocksource.h> +#include <linux/jiffies.h> +#include <linux/time.h> +#include <linux/tick.h> + + +/* + * This read-write spinlock protects us from races in SMP while + * playing with xtime and avenrun. + */ +__attribute__((weak)) __cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); + +EXPORT_SYMBOL(xtime_lock); + + +/* + * The current time + * wall_to_monotonic is what we need to add to xtime (or xtime corrected + * for sub jiffie times) to get to monotonic time. Monotonic is pegged + * at zero at system boot time, so wall_to_monotonic will be negative, + * however, we will ALWAYS keep the tv_nsec part positive so we can use + * the usual normalization. + */ +struct timespec xtime __attribute__ ((aligned (16))); +struct timespec wall_to_monotonic __attribute__ ((aligned (16))); + +EXPORT_SYMBOL(xtime); + + +static struct clocksource *clock; /* pointer to current clocksource */ + + +#ifdef CONFIG_GENERIC_TIME +/** + * __get_nsec_offset - Returns nanoseconds since last call to periodic_hook + * + * private function, must hold xtime_lock lock when being + * called. Returns the number of nanoseconds since the + * last call to update_wall_time() (adjusted by NTP scaling) + */ +static inline s64 __get_nsec_offset(void) +{ + cycle_t cycle_now, cycle_delta; + s64 ns_offset; + + /* read clocksource: */ + cycle_now = clocksource_read(clock); + + /* calculate the delta since the last update_wall_time: */ + cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + + /* convert to nanoseconds: */ + ns_offset = cyc2ns(clock, cycle_delta); + + return ns_offset; +} + +/** + * __get_realtime_clock_ts - Returns the time of day in a timespec + * @ts: pointer to the timespec to be set + * + * Returns the time of day in a timespec. Used by + * do_gettimeofday() and get_realtime_clock_ts(). + */ +static inline void __get_realtime_clock_ts(struct timespec *ts) +{ + unsigned long seq; + s64 nsecs; + + do { + seq = read_seqbegin(&xtime_lock); + + *ts = xtime; + nsecs = __get_nsec_offset(); + + } while (read_seqretry(&xtime_lock, seq)); + + timespec_add_ns(ts, nsecs); +} + +/** + * getnstimeofday - Returns the time of day in a timespec + * @ts: pointer to the timespec to be set + * + * Returns the time of day in a timespec. + */ +void getnstimeofday(struct timespec *ts) +{ + __get_realtime_clock_ts(ts); +} + +EXPORT_SYMBOL(getnstimeofday); + +/** + * do_gettimeofday - Returns the time of day in a timeval + * @tv: pointer to the timeval to be set + * + * NOTE: Users should be converted to using get_realtime_clock_ts() + */ +void do_gettimeofday(struct timeval *tv) +{ + struct timespec now; + + __get_realtime_clock_ts(&now); + tv->tv_sec = now.tv_sec; + tv->tv_usec = now.tv_nsec/1000; +} + +EXPORT_SYMBOL(do_gettimeofday); +/** + * do_settimeofday - Sets the time of day + * @tv: pointer to the timespec variable containing the new time + * + * Sets the time of day to the new time and update NTP and notify hrtimers + */ +int do_settimeofday(struct timespec *tv) +{ + unsigned long flags; + time_t wtm_sec, sec = tv->tv_sec; + long wtm_nsec, nsec = tv->tv_nsec; + + if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) + return -EINVAL; + + write_seqlock_irqsave(&xtime_lock, flags); + + nsec -= __get_nsec_offset(); + + wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); + wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); + + set_normalized_timespec(&xtime, sec, nsec); + set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); + + clock->error = 0; + ntp_clear(); + + update_vsyscall(&xtime, clock); + + write_sequnlock_irqrestore(&xtime_lock, flags); + + /* signal hrtimers about time change */ + clock_was_set(); + + return 0; +} + +EXPORT_SYMBOL(do_settimeofday); + +/** + * change_clocksource - Swaps clocksources if a new one is available + * + * Accumulates current time interval and initializes new clocksource + */ +static void change_clocksource(void) +{ + struct clocksource *new; + cycle_t now; + u64 nsec; + + new = clocksource_get_next(); + + if (clock == new) + return; + + now = clocksource_read(new); + nsec = __get_nsec_offset(); + timespec_add_ns(&xtime, nsec); + + clock = new; + clock->cycle_last = now; + + clock->error = 0; + clock->xtime_nsec = 0; + clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH); + + tick_clock_notify(); + + printk(KERN_INFO "Time: %s clocksource has been installed.\n", + clock->name); +} +#else +static inline void change_clocksource(void) { } +#endif + +/** + * timekeeping_is_continuous - check to see if timekeeping is free running + */ +int timekeeping_is_continuous(void) +{ + unsigned long seq; + int ret; + + do { + seq = read_seqbegin(&xtime_lock); + + ret = clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; + + } while (read_seqretry(&xtime_lock, seq)); + + return ret; +} + +/** + * read_persistent_clock - Return time in seconds from the persistent clock. + * + * Weak dummy function for arches that do not yet support it. + * Returns seconds from epoch using the battery backed persistent clock. + * Returns zero if unsupported. + * + * XXX - Do be sure to remove it once all arches implement it. + */ +unsigned long __attribute__((weak)) read_persistent_clock(void) +{ + return 0; +} + +/* + * timekeeping_init - Initializes the clocksource and common timekeeping values + */ +void __init timekeeping_init(void) +{ + unsigned long flags; + unsigned long sec = read_persistent_clock(); + + write_seqlock_irqsave(&xtime_lock, flags); + + ntp_clear(); + + clock = clocksource_get_next(); + clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH); + clock->cycle_last = clocksource_read(clock); + + xtime.tv_sec = sec; + xtime.tv_nsec = 0; + set_normalized_timespec(&wall_to_monotonic, + -xtime.tv_sec, -xtime.tv_nsec); + + write_sequnlock_irqrestore(&xtime_lock, flags); +} + +/* flag for if timekeeping is suspended */ +static int timekeeping_suspended; +/* time in seconds when suspend began */ +static unsigned long timekeeping_suspend_time; + +/** + * timekeeping_resume - Resumes the generic timekeeping subsystem. + * @dev: unused + * + * This is for the generic clocksource timekeeping. + * xtime/wall_to_monotonic/jiffies/etc are + * still managed by arch specific suspend/resume code. + */ +static int timekeeping_resume(struct sys_device *dev) +{ + unsigned long flags; + unsigned long now = read_persistent_clock(); + + write_seqlock_irqsave(&xtime_lock, flags); + + if (now && (now > timekeeping_suspend_time)) { + unsigned long sleep_length = now - timekeeping_suspend_time; + + xtime.tv_sec += sleep_length; + wall_to_monotonic.tv_sec -= sleep_length; + } + /* re-base the last cycle value */ + clock->cycle_last = clocksource_read(clock); + clock->error = 0; + timekeeping_suspended = 0; + write_sequnlock_irqrestore(&xtime_lock, flags); + + touch_softlockup_watchdog(); + + clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL); + + /* Resume hrtimers */ + hres_timers_resume(); + + return 0; +} + +static int timekeeping_suspend(struct sys_device *dev, pm_message_t state) +{ + unsigned long flags; + + write_seqlock_irqsave(&xtime_lock, flags); + timekeeping_suspended = 1; + timekeeping_suspend_time = read_persistent_clock(); + write_sequnlock_irqrestore(&xtime_lock, flags); + + clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); + + return 0; +} + +/* sysfs resume/suspend bits for timekeeping */ +static struct sysdev_class timekeeping_sysclass = { + .resume = timekeeping_resume, + .suspend = timekeeping_suspend, + set_kset_name("timekeeping"), +}; + +static struct sys_device device_timer = { + .id = 0, + .cls = &timekeeping_sysclass, +}; + +static int __init timekeeping_init_device(void) +{ + int error = sysdev_class_register(&timekeeping_sysclass); + if (!error) + error = sysdev_register(&device_timer); + return error; +} + +device_initcall(timekeeping_init_device); + +/* + * If the error is already larger, we look ahead even further + * to compensate for late or lost adjustments. + */ +static __always_inline int clocksource_bigadjust(s64 error, s64 *interval, + s64 *offset) +{ + s64 tick_error, i; + u32 look_ahead, adj; + s32 error2, mult; + + /* + * Use the current error value to determine how much to look ahead. + * The larger the error the slower we adjust for it to avoid problems + * with losing too many ticks, otherwise we would overadjust and + * produce an even larger error. The smaller the adjustment the + * faster we try to adjust for it, as lost ticks can do less harm + * here. This is tuned so that an error of about 1 msec is adusted + * within about 1 sec (or 2^20 nsec in 2^SHIFT_HZ ticks). + */ + error2 = clock->error >> (TICK_LENGTH_SHIFT + 22 - 2 * SHIFT_HZ); + error2 = abs(error2); + for (look_ahead = 0; error2 > 0; look_ahead++) + error2 >>= 2; + + /* + * Now calculate the error in (1 << look_ahead) ticks, but first + * remove the single look ahead already included in the error. + */ + tick_error = current_tick_length() >> + (TICK_LENGTH_SHIFT - clock->shift + 1); + tick_error -= clock->xtime_interval >> 1; + error = ((error - tick_error) >> look_ahead) + tick_error; + + /* Finally calculate the adjustment shift value. */ + i = *interval; + mult = 1; + if (error < 0) { + error = -error; + *interval = -*interval; + *offset = -*offset; + mult = -1; + } + for (adj = 0; error > i; adj++) + error >>= 1; + + *interval <<= adj; + *offset <<= adj; + return mult << adj; +} + +/* + * Adjust the multiplier to reduce the error value, + * this is optimized for the most common adjustments of -1,0,1, + * for other values we can do a bit more work. + */ +static void clocksource_adjust(struct clocksource *clock, s64 offset) +{ + s64 error, interval = clock->cycle_interval; + int adj; + + error = clock->error >> (TICK_LENGTH_SHIFT - clock->shift - 1); + if (error > interval) { + error >>= 2; + if (likely(error <= interval)) + adj = 1; + else + adj = clocksource_bigadjust(error, &interval, &offset); + } else if (error < -interval) { + error >>= 2; + if (likely(error >= -interval)) { + adj = -1; + interval = -interval; + offset = -offset; + } else + adj = clocksource_bigadjust(error, &interval, &offset); + } else + return; + + clock->mult += adj; + clock->xtime_interval += interval; + clock->xtime_nsec -= offset; + clock->error -= (interval - offset) << + (TICK_LENGTH_SHIFT - clock->shift); +} + +/** + * update_wall_time - Uses the current clocksource to increment the wall time + * + * Called from the timer interrupt, must hold a write on xtime_lock. + */ +void update_wall_time(void) +{ + cycle_t offset; + + /* Make sure we're fully resumed: */ + if (unlikely(timekeeping_suspended)) + return; + +#ifdef CONFIG_GENERIC_TIME + offset = (clocksource_read(clock) - clock->cycle_last) & clock->mask; +#else + offset = clock->cycle_interval; +#endif + clock->xtime_nsec += (s64)xtime.tv_nsec << clock->shift; + + /* normally this loop will run just once, however in the + * case of lost or late ticks, it will accumulate correctly. + */ + while (offset >= clock->cycle_interval) { + /* accumulate one interval */ + clock->xtime_nsec += clock->xtime_interval; + clock->cycle_last += clock->cycle_interval; + offset -= clock->cycle_interval; + + if (clock->xtime_nsec >= (u64)NSEC_PER_SEC << clock->shift) { + clock->xtime_nsec -= (u64)NSEC_PER_SEC << clock->shift; + xtime.tv_sec++; + second_overflow(); + } + + /* interpolator bits */ + time_interpolator_update(clock->xtime_interval + >> clock->shift); + + /* accumulate error between NTP and clock interval */ + clock->error += current_tick_length(); + clock->error -= clock->xtime_interval << (TICK_LENGTH_SHIFT - clock->shift); + } + + /* correct the clock when NTP error is too big */ + clocksource_adjust(clock, offset); + + /* store full nanoseconds into xtime */ + xtime.tv_nsec = (s64)clock->xtime_nsec >> clock->shift; + clock->xtime_nsec -= (s64)xtime.tv_nsec << clock->shift; + + /* check to see if there is a new clocksource to use */ + change_clocksource(); + update_vsyscall(&xtime, clock); +} diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 59df5e8555a..b734ca4bc75 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -38,17 +38,12 @@ DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases); static void print_name_offset(struct seq_file *m, void *sym) { - unsigned long addr = (unsigned long)sym; - char namebuf[KSYM_NAME_LEN+1]; - unsigned long size, offset; - const char *sym_name; - char *modname; - - sym_name = kallsyms_lookup(addr, &size, &offset, &modname, namebuf); - if (sym_name) - SEQ_printf(m, "%s", sym_name); - else + char symname[KSYM_NAME_LEN+1]; + + if (lookup_symbol_name((unsigned long)sym, symname) < 0) SEQ_printf(m, "<%p>", sym); + else + SEQ_printf(m, "%s", symname); } static void diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c index 1bc4882e28e..868f1bceb07 100644 --- a/kernel/time/timer_stats.c +++ b/kernel/time/timer_stats.c @@ -257,16 +257,12 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf, static void print_name_offset(struct seq_file *m, unsigned long addr) { - char namebuf[KSYM_NAME_LEN+1]; - unsigned long size, offset; - const char *sym_name; - char *modname; - - sym_name = kallsyms_lookup(addr, &size, &offset, &modname, namebuf); - if (sym_name) - seq_printf(m, "%s", sym_name); - else + char symname[KSYM_NAME_LEN+1]; + + if (lookup_symbol_name(addr, symname) < 0) seq_printf(m, "<%p>", (void *)addr); + else + seq_printf(m, "%s", symname); } static int tstats_show(struct seq_file *m, void *v) |