From f695cf94837de53864180400cbac42cfa370426f Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 14 Mar 2012 16:38:15 -0700 Subject: time: Fix change_clocksource locking change_clocksource() fails to grab locks or call timekeeping_update(), which leaves a race window for time inconsistencies. This adds proper locking and a call to timekeeping_update() to fix this. CC: Andy Lutomirski CC: Thomas Gleixner Signed-off-by: John Stultz --- kernel/time/timekeeping.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel/time') diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 403c2a092830..b53da5ecbea2 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -448,9 +448,12 @@ EXPORT_SYMBOL(timekeeping_inject_offset); static int change_clocksource(void *data) { struct clocksource *new, *old; + unsigned long flags; new = (struct clocksource *) data; + write_seqlock_irqsave(&timekeeper.lock, flags); + timekeeping_forward_now(); if (!new->enable || new->enable(new) == 0) { old = timekeeper.clock; @@ -458,6 +461,10 @@ static int change_clocksource(void *data) if (old->disable) old->disable(old); } + timekeeping_update(true); + + write_sequnlock_irqrestore(&timekeeper.lock, flags); + return 0; } -- cgit v1.2.3 From 6b43ae8a619d17c4935c3320d2ef9e92bdeed05d Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 15 Mar 2012 13:04:03 -0700 Subject: ntp: Fix leap-second hrtimer livelock Since commit 7dffa3c673fbcf835cd7be80bb4aec8ad3f51168 the ntp subsystem has used an hrtimer for triggering the leapsecond adjustment. However, this can cause a potential livelock. Thomas diagnosed this as the following pattern: CPU 0 CPU 1 do_adjtimex() spin_lock_irq(&ntp_lock); process_adjtimex_modes(); timer_interrupt() process_adj_status(); do_timer() ntp_start_leap_timer(); write_lock(&xtime_lock); hrtimer_start(); update_wall_time(); hrtimer_reprogram(); ntp_tick_length() tick_program_event() spin_lock(&ntp_lock); clockevents_program_event() ktime_get() seq = req_seqbegin(xtime_lock); This patch tries to avoid the problem by reverting back to not using an hrtimer to inject leapseconds, and instead we handle the leapsecond processing in the second_overflow() function. The downside to this change is that on systems that support highres timers, the leap second processing will occur on a HZ tick boundary, (ie: ~1-10ms, depending on HZ) after the leap second instead of possibly sooner (~34us in my tests w/ x86_64 lapic). This patch applies on top of tip/timers/core. CC: Sasha Levin CC: Thomas Gleixner Reported-by: Sasha Levin Diagnoised-by: Thomas Gleixner Tested-by: Sasha Levin Signed-off-by: John Stultz --- include/linux/timex.h | 2 +- kernel/time/ntp.c | 128 +++++++++++++++------------------------------- kernel/time/timekeeping.c | 20 +++----- 3 files changed, 48 insertions(+), 102 deletions(-) (limited to 'kernel/time') diff --git a/include/linux/timex.h b/include/linux/timex.h index b75e1864ed19..99bc88b1fc02 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -252,7 +252,7 @@ extern void ntp_clear(void); /* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */ extern u64 ntp_tick_length(void); -extern void second_overflow(void); +extern int second_overflow(unsigned long secs); extern int do_adjtimex(struct timex *); extern void hardpps(const struct timespec *, const struct timespec *); diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 6e039b144daf..3d17ebd47fa2 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -34,8 +34,6 @@ unsigned long tick_nsec; static u64 tick_length; static u64 tick_length_base; -static struct hrtimer leap_timer; - #define MAX_TICKADJ 500LL /* usecs */ #define MAX_TICKADJ_SCALED \ (((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ) @@ -381,70 +379,63 @@ u64 ntp_tick_length(void) /* - * Leap second processing. If in leap-insert state at the end of the - * day, the system clock is set back one second; if in leap-delete - * state, the system clock is set ahead one second. + * this routine handles the overflow of the microsecond field + * + * The tricky bits of code to handle the accurate clock support + * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame. + * They were originally developed for SUN and DEC kernels. + * All the kudos should go to Dave for this stuff. + * + * Also handles leap second processing, and returns leap offset */ -static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) +int second_overflow(unsigned long secs) { - enum hrtimer_restart res = HRTIMER_NORESTART; - unsigned long flags; + s64 delta; int leap = 0; + unsigned long flags; spin_lock_irqsave(&ntp_lock, flags); + + /* + * Leap second processing. If in leap-insert state at the end of the + * day, the system clock is set back one second; if in leap-delete + * state, the system clock is set ahead one second. + */ switch (time_state) { case TIME_OK: + if (time_status & STA_INS) + time_state = TIME_INS; + else if (time_status & STA_DEL) + time_state = TIME_DEL; break; case TIME_INS: - leap = -1; - time_state = TIME_OOP; - printk(KERN_NOTICE - "Clock: inserting leap second 23:59:60 UTC\n"); - hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC); - res = HRTIMER_RESTART; + if (secs % 86400 == 0) { + leap = -1; + time_state = TIME_OOP; + printk(KERN_NOTICE + "Clock: inserting leap second 23:59:60 UTC\n"); + } break; case TIME_DEL: - leap = 1; - time_tai--; - time_state = TIME_WAIT; - printk(KERN_NOTICE - "Clock: deleting leap second 23:59:59 UTC\n"); + if ((secs + 1) % 86400 == 0) { + leap = 1; + time_tai--; + time_state = TIME_WAIT; + printk(KERN_NOTICE + "Clock: deleting leap second 23:59:59 UTC\n"); + } break; case TIME_OOP: time_tai++; time_state = TIME_WAIT; - /* fall through */ + break; + case TIME_WAIT: if (!(time_status & (STA_INS | STA_DEL))) time_state = TIME_OK; break; } - spin_unlock_irqrestore(&ntp_lock, flags); - - /* - * We have to call this outside of the ntp_lock to keep - * the proper locking hierarchy - */ - if (leap) - timekeeping_leap_insert(leap); - - return res; -} - -/* - * this routine handles the overflow of the microsecond field - * - * The tricky bits of code to handle the accurate clock support - * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame. - * They were originally developed for SUN and DEC kernels. - * All the kudos should go to Dave for this stuff. - */ -void second_overflow(void) -{ - s64 delta; - unsigned long flags; - spin_lock_irqsave(&ntp_lock, flags); /* Bump the maxerror field */ time_maxerror += MAXFREQ / NSEC_PER_USEC; @@ -481,8 +472,13 @@ void second_overflow(void) tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ) << NTP_SCALE_SHIFT; time_adjust = 0; + + + out: spin_unlock_irqrestore(&ntp_lock, flags); + + return leap; } #ifdef CONFIG_GENERIC_CMOS_UPDATE @@ -544,27 +540,6 @@ static void notify_cmos_timer(void) static inline void notify_cmos_timer(void) { } #endif -/* - * Start the leap seconds timer: - */ -static inline void ntp_start_leap_timer(struct timespec *ts) -{ - long now = ts->tv_sec; - - if (time_status & STA_INS) { - time_state = TIME_INS; - now += 86400 - now % 86400; - hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS); - - return; - } - - if (time_status & STA_DEL) { - time_state = TIME_DEL; - now += 86400 - (now + 1) % 86400; - hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS); - } -} /* * Propagate a new txc->status value into the NTP state: @@ -589,22 +564,6 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts) time_status &= STA_RONLY; time_status |= txc->status & ~STA_RONLY; - switch (time_state) { - case TIME_OK: - ntp_start_leap_timer(ts); - break; - case TIME_INS: - case TIME_DEL: - time_state = TIME_OK; - ntp_start_leap_timer(ts); - case TIME_WAIT: - if (!(time_status & (STA_INS | STA_DEL))) - time_state = TIME_OK; - break; - case TIME_OOP: - hrtimer_restart(&leap_timer); - break; - } } /* * Called with the xtime lock held, so we can access and modify @@ -686,9 +645,6 @@ int do_adjtimex(struct timex *txc) (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) return -EINVAL; - - if (txc->modes & ADJ_STATUS && time_state != TIME_OK) - hrtimer_cancel(&leap_timer); } if (txc->modes & ADJ_SETOFFSET) { @@ -1010,6 +966,4 @@ __setup("ntp_tick_adj=", ntp_tick_adj_setup); void __init ntp_init(void) { ntp_clear(); - hrtimer_init(&leap_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); - leap_timer.function = ntp_leap_second; } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index b53da5ecbea2..5d76e09ddd3d 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -184,18 +184,6 @@ static void timekeeping_update(bool clearntp) } -void timekeeping_leap_insert(int leapsecond) -{ - unsigned long flags; - - write_seqlock_irqsave(&timekeeper.lock, flags); - timekeeper.xtime.tv_sec += leapsecond; - timekeeper.wall_to_monotonic.tv_sec -= leapsecond; - timekeeping_update(false); - write_sequnlock_irqrestore(&timekeeper.lock, flags); - -} - /** * timekeeping_forward_now - update clock to the current time * @@ -969,9 +957,11 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift) timekeeper.xtime_nsec += timekeeper.xtime_interval << shift; while (timekeeper.xtime_nsec >= nsecps) { + int leap; timekeeper.xtime_nsec -= nsecps; timekeeper.xtime.tv_sec++; - second_overflow(); + leap = second_overflow(timekeeper.xtime.tv_sec); + timekeeper.xtime.tv_sec += leap; } /* Accumulate raw time */ @@ -1082,9 +1072,11 @@ static void update_wall_time(void) * xtime.tv_nsec isn't larger then NSEC_PER_SEC */ if (unlikely(timekeeper.xtime.tv_nsec >= NSEC_PER_SEC)) { + int leap; timekeeper.xtime.tv_nsec -= NSEC_PER_SEC; timekeeper.xtime.tv_sec++; - second_overflow(); + leap = second_overflow(timekeeper.xtime.tv_sec); + timekeeper.xtime.tv_sec += leap; } timekeeping_update(false); -- cgit v1.2.3 From ad30dfa94c5cc23931c822922a50bd163ab293a5 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Fri, 23 Mar 2012 15:52:25 -0700 Subject: alarmtimer: Make sure we initialize the rtctimer jonghwan Choi reported seeing warnings with the alarmtimer code at suspend/resume time, and pointed out that the rtctimer isn't being properly initialized. This patch corrects this issue. Reported-by: jonghwan Choi Signed-off-by: John Stultz --- kernel/time/alarmtimer.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel/time') diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 8a46f5d64504..c16548807f1e 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -46,9 +46,10 @@ static struct alarm_base { static ktime_t freezer_delta; static DEFINE_SPINLOCK(freezer_delta_lock); +static struct rtc_timer rtctimer; + #ifdef CONFIG_RTC_CLASS /* rtc timer and device for setting alarm wakeups at suspend */ -static struct rtc_timer rtctimer; static struct rtc_device *rtcdev; static DEFINE_SPINLOCK(rtcdev_lock); @@ -783,6 +784,8 @@ static int __init alarmtimer_init(void) .nsleep = alarm_timer_nsleep, }; + rtc_timer_init(&rtctimer, NULL, NULL); + posix_timers_register_clock(CLOCK_REALTIME_ALARM, &alarm_clock); posix_timers_register_clock(CLOCK_BOOTTIME_ALARM, &alarm_clock); -- cgit v1.2.3 From e919cfd42da54d400e7e0385f22cae3672dcf874 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 22 Mar 2012 19:14:46 -0700 Subject: time: Avoid scary backtraces when warning of > 11% adj Folks have been getting a number of warnings about time adjustments > 11%. The WARN_ON leaves a big useless backtrace so this patch removes it for a printk_once(). I'm still working to narrow down the cause of the > 11% adjustment. Signed-off-by: John Stultz --- kernel/time/timekeeping.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 5d76e09ddd3d..16a175bed355 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -869,13 +869,15 @@ static void timekeeping_adjust(s64 offset) } else /* No adjustment needed */ return; - WARN_ONCE(timekeeper.clock->maxadj && - (timekeeper.mult + adj > timekeeper.clock->mult + - timekeeper.clock->maxadj), - "Adjusting %s more then 11%% (%ld vs %ld)\n", + if (unlikely(timekeeper.clock->maxadj && + (timekeeper.mult + adj > + timekeeper.clock->mult + timekeeper.clock->maxadj))) { + printk_once(KERN_WARNING + "Adjusting %s more than 11%% (%ld vs %ld)\n", timekeeper.clock->name, (long)timekeeper.mult + adj, (long)timekeeper.clock->mult + timekeeper.clock->maxadj); + } /* * So the following can be confusing. * -- cgit v1.2.3 From 335dd85895abeca1957d5eaa3013dfe8dc60c7d7 Mon Sep 17 00:00:00 2001 From: Cesar Eduardo Barros Date: Sat, 11 Feb 2012 17:54:59 -0200 Subject: time: remove no_sync_cmos_clock Commit 9863c90f682fba34cdc26c3437e8c00da6c83fa4 (x86, vmware: Remove deprecated VMI kernel support) removed the only place which set no_sync_cmos_clock. Since that commit, this variable is never set. Signed-off-by: Cesar Eduardo Barros Signed-off-by: John Stultz --- include/linux/time.h | 1 - kernel/time/ntp.c | 6 +----- 2 files changed, 1 insertion(+), 6 deletions(-) (limited to 'kernel/time') diff --git a/include/linux/time.h b/include/linux/time.h index b3061782dec3..97734e9409c6 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -116,7 +116,6 @@ static inline struct timespec timespec_sub(struct timespec lhs, extern void read_persistent_clock(struct timespec *ts); extern void read_boot_clock(struct timespec *ts); extern int update_persistent_clock(struct timespec now); -extern int no_sync_cmos_clock __read_mostly; void timekeeping_init(void); extern int timekeeping_suspended; diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 3d17ebd47fa2..f03fd83b170b 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -483,9 +483,6 @@ out: #ifdef CONFIG_GENERIC_CMOS_UPDATE -/* Disable the cmos update - used by virtualization and embedded */ -int no_sync_cmos_clock __read_mostly; - static void sync_cmos_clock(struct work_struct *work); static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock); @@ -532,8 +529,7 @@ static void sync_cmos_clock(struct work_struct *work) static void notify_cmos_timer(void) { - if (!no_sync_cmos_clock) - schedule_delayed_work(&sync_cmos_work, 0); + schedule_delayed_work(&sync_cmos_work, 0); } #else -- cgit v1.2.3 From 88b28adf6fcdd6d10a1cfc7765bb200d7366a265 Mon Sep 17 00:00:00 2001 From: Jim Cromie Date: Wed, 14 Mar 2012 21:28:56 -0600 Subject: kernel-time: fix s/then/than/ spelling errors Use than for comparisons, like more than. CC: John Stultz Signed-off-by: Jim Cromie Signed-off-by: John Stultz --- kernel/time/clocksource.c | 2 +- kernel/time/timekeeping.c | 14 +++++++------- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index a45ca167ab24..c9583382141a 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -500,7 +500,7 @@ static u32 clocksource_max_adjustment(struct clocksource *cs) { u64 ret; /* - * We won't try to correct for more then 11% adjustments (110,000 ppm), + * We won't try to correct for more than 11% adjustments (110,000 ppm), */ ret = (u64)cs->mult * 11; do_div(ret,100); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 16a175bed355..51b98568ba4d 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -822,7 +822,7 @@ static void timekeeping_adjust(s64 offset) int adj; /* - * The point of this is to check if the error is greater then half + * The point of this is to check if the error is greater than half * an interval. * * First we shift it down from NTP_SHIFT to clocksource->shifted nsecs. @@ -830,7 +830,7 @@ static void timekeeping_adjust(s64 offset) * Note we subtract one in the shift, so that error is really error*2. * This "saves" dividing(shifting) interval twice, but keeps the * (error > interval) comparison as still measuring if error is - * larger then half an interval. + * larger than half an interval. * * Note: It does not "save" on aggravation when reading the code. */ @@ -838,7 +838,7 @@ static void timekeeping_adjust(s64 offset) if (error > interval) { /* * We now divide error by 4(via shift), which checks if - * the error is greater then twice the interval. + * the error is greater than twice the interval. * If it is greater, we need a bigadjust, if its smaller, * we can adjust by 1. */ @@ -949,7 +949,7 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift) u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift; u64 raw_nsecs; - /* If the offset is smaller then a shifted interval, do nothing */ + /* If the offset is smaller than a shifted interval, do nothing */ if (offset < timekeeper.cycle_interval<= timekeeper.cycle_interval) { @@ -1071,7 +1071,7 @@ static void update_wall_time(void) /* * Finally, make sure that after the rounding - * xtime.tv_nsec isn't larger then NSEC_PER_SEC + * xtime.tv_nsec isn't larger than NSEC_PER_SEC */ if (unlikely(timekeeper.xtime.tv_nsec >= NSEC_PER_SEC)) { int leap; -- cgit v1.2.3 From c5e14e763046b11dd8bf57b5dc9f3ab444af8e60 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 24 Mar 2012 12:46:23 +0100 Subject: alarmtimer: Don't call rtc_timer_init() when CONFIG_RTC_CLASS=n rtc_timer_init() is not available when CONFIG_RTC_CLASS=n. Provide a proper wrapper in the RTC section of alarmtimer.c Reported-by: Ingo Molnar Signed-off-by: Thomas Gleixner Cc: John Stultz --- kernel/time/alarmtimer.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index c16548807f1e..8a538c55fc7b 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -46,10 +46,9 @@ static struct alarm_base { static ktime_t freezer_delta; static DEFINE_SPINLOCK(freezer_delta_lock); -static struct rtc_timer rtctimer; - #ifdef CONFIG_RTC_CLASS /* rtc timer and device for setting alarm wakeups at suspend */ +static struct rtc_timer rtctimer; static struct rtc_device *rtcdev; static DEFINE_SPINLOCK(rtcdev_lock); @@ -97,6 +96,11 @@ static int alarmtimer_rtc_add_device(struct device *dev, return 0; } +static inline void alarmtimer_rtc_timer_init(void) +{ + rtc_timer_init(&rtctimer, NULL, NULL); +} + static struct class_interface alarmtimer_rtc_interface = { .add_dev = &alarmtimer_rtc_add_device, }; @@ -118,6 +122,7 @@ static inline struct rtc_device *alarmtimer_get_rtcdev(void) #define rtcdev (NULL) static inline int alarmtimer_rtc_interface_setup(void) { return 0; } static inline void alarmtimer_rtc_interface_remove(void) { } +static inline void alarmtimer_rtc_timer_init(void) { } #endif /** @@ -784,7 +789,7 @@ static int __init alarmtimer_init(void) .nsleep = alarm_timer_nsleep, }; - rtc_timer_init(&rtctimer, NULL, NULL); + alarmtimer_rtc_timer_init(); posix_timers_register_clock(CLOCK_REALTIME_ALARM, &alarm_clock); posix_timers_register_clock(CLOCK_BOOTTIME_ALARM, &alarm_clock); -- cgit v1.2.3