From cc947f2b9c04113d84eeef67cc7c6326e1982019 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 16 Nov 2020 10:53:38 +0100 Subject: timers: Make run_local_timers() static No users outside of the timer code. Move the caller below this function to avoid a pointless forward declaration. Signed-off-by: Thomas Gleixner --- include/linux/timer.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index d10bc7e73b41..fda13c9d1256 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -193,7 +193,6 @@ extern int try_to_del_timer_sync(struct timer_list *timer); #define del_singleshot_timer_sync(t) del_timer_sync(t) extern void init_timers(void); -extern void run_local_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); -- cgit v1.2.3-71-gd317 From 66981c37b3199d293c58f84cf2366e86a06e1a3d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 16 Nov 2020 11:18:14 +0100 Subject: hrtimer: Fix kernel-doc markups The hrtimer_get_remaining() markup is documenting, instead, __hrtimer_get_remaining(), as it is placed at the C file. In order to properly document it, a kernel-doc markup is needed together with the function prototype. So, add a new one, while preserving the existing one, just fixing the function name. The hrtimer_is_queued prototype has a typo: it is using '=' instead of '-' to split: identifier - description as required by kernel-doc markup. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/9dc87808c2fd07b7e050bafcd033c5ef05808fea.1605521731.git.mchehab+huawei@kernel.org --- include/linux/hrtimer.h | 6 +++++- kernel/time/hrtimer.c | 2 +- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 107cedd7019a..bb5e7b0a4274 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -447,6 +447,10 @@ static inline void hrtimer_restart(struct hrtimer *timer) /* Query timers: */ extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); +/** + * hrtimer_get_remaining - get remaining time for the timer + * @timer: the timer to read + */ static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer) { return __hrtimer_get_remaining(timer, false); @@ -458,7 +462,7 @@ extern u64 hrtimer_next_event_without(const struct hrtimer *exclude); extern bool hrtimer_active(const struct hrtimer *timer); /** - * hrtimer_is_queued = check, whether the timer is on one of the queues + * hrtimer_is_queued - check, whether the timer is on one of the queues * @timer: Timer to check * * Returns: True if the timer is queued, false otherwise diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 3624b9b5835d..61c39ff68439 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1289,7 +1289,7 @@ int hrtimer_cancel(struct hrtimer *timer) EXPORT_SYMBOL_GPL(hrtimer_cancel); /** - * hrtimer_get_remaining - get remaining time for the timer + * __hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y */ -- cgit v1.2.3-71-gd317 From c9e6189fb03123a7dfb93589280347b46f30b161 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 6 Dec 2020 22:46:18 +0100 Subject: ntp: Make the RTC synchronization more reliable Miroslav reported that the periodic RTC synchronization in the NTP code fails more often than not to hit the specified update window. The reason is that the code uses delayed_work to schedule the update which needs to be in thread context as the underlying RTC might be connected via a slow bus, e.g. I2C. In the update function it verifies whether the current time is correct vs. the requirements of the underlying RTC. But delayed_work is using the timer wheel for scheduling which is inaccurate by design. Depending on the distance to the expiry the wheel gets less granular to allow batching and to avoid the cascading of the original timer wheel. See 500462a9de65 ("timers: Switch to a non-cascading wheel") and the code for further details. The code already deals with this by splitting the 660 seconds period into a long 659 seconds timer and then retrying with a smaller delta. But looking at the actual granularities of the timer wheel (which depend on the HZ configuration) the 659 seconds timer ends up in an outer wheel level and is affected by a worst case granularity of: HZ Granularity 1000 32s 250 16s 100 40s So the initial timer can be already off by max 12.5% which is not a big issue as the period of the sync is defined as ~11 minutes. The fine grained second attempt schedules to the desired update point with a timer expiring less than a second from now. Depending on the actual delta and the HZ setting even the second attempt can end up in outer wheel levels which have a large enough granularity to make the correctness check fail. As this is a fundamental property of the timer wheel there is no way to make this more accurate short of iterating in one jiffies steps towards the update point. Switch it to an hrtimer instead which schedules the actual update work. The hrtimer will expire precisely (max 1 jiffie delay when high resolution timers are not available). The actual scheduling delay of the work is the same as before. The update is triggered from do_adjtimex() which is a bit racy but not much more racy than it was before: if (ntp_synced()) queue_delayed_work(system_power_efficient_wq, &sync_work, 0); which is racy when the work is currently executed and has not managed to reschedule itself. This becomes now: if (ntp_synced() && !hrtimer_is_queued(&sync_hrtimer)) queue_work(system_power_efficient_wq, &sync_work, 0); which is racy when the hrtimer has expired and the work is currently executed and has not yet managed to rearm the hrtimer. Not a big problem as it just schedules work for nothing. The new implementation has a safe guard in place to catch the case where the hrtimer is queued on entry to the work function and avoids an extra update attempt of the RTC that way. Reported-by: Miroslav Lichvar Signed-off-by: Thomas Gleixner Tested-by: Miroslav Lichvar Reviewed-by: Jason Gunthorpe Acked-by: Alexandre Belloni Link: https://lore.kernel.org/r/20201206220542.062910520@linutronix.de --- include/linux/timex.h | 1 - kernel/time/ntp.c | 90 ++++++++++++++++++++++++---------------------- kernel/time/ntp_internal.h | 7 ++++ 3 files changed, 55 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index ce0859763670..9c2e54faf9b7 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -157,7 +157,6 @@ extern int do_clock_adjtime(const clockid_t which_clock, struct __kernel_timex * extern void hardpps(const struct timespec64 *, const struct timespec64 *); int read_current_timer(unsigned long *timer_val); -void ntp_notify_cmos_timer(void); /* The clock frequency of the i8253/i8254 PIT */ #define PIT_TICK_RATE 1193182ul diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 069ca78fb0bf..ff1a7b8ec4ef 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -494,65 +494,55 @@ out: return leap; } +#if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) static void sync_hw_clock(struct work_struct *work); -static DECLARE_DELAYED_WORK(sync_work, sync_hw_clock); - -static void sched_sync_hw_clock(struct timespec64 now, - unsigned long target_nsec, bool fail) +static DECLARE_WORK(sync_work, sync_hw_clock); +static struct hrtimer sync_hrtimer; +#define SYNC_PERIOD_NS (11UL * 60 * NSEC_PER_SEC) +static enum hrtimer_restart sync_timer_callback(struct hrtimer *timer) { - struct timespec64 next; + queue_work(system_power_efficient_wq, &sync_work); - ktime_get_real_ts64(&next); - if (!fail) - next.tv_sec = 659; - else { - /* - * Try again as soon as possible. Delaying long periods - * decreases the accuracy of the work queue timer. Due to this - * the algorithm is very likely to require a short-sleep retry - * after the above long sleep to synchronize ts_nsec. - */ - next.tv_sec = 0; - } + return HRTIMER_NORESTART; +} - /* Compute the needed delay that will get to tv_nsec == target_nsec */ - next.tv_nsec = target_nsec - next.tv_nsec; - if (next.tv_nsec <= 0) - next.tv_nsec += NSEC_PER_SEC; - if (next.tv_nsec >= NSEC_PER_SEC) { - next.tv_sec++; - next.tv_nsec -= NSEC_PER_SEC; - } +static void sched_sync_hw_clock(unsigned long offset_nsec, bool retry) +{ + ktime_t exp = ktime_set(ktime_get_real_seconds(), 0); + + if (retry) + exp = ktime_add_ns(exp, 2 * NSEC_PER_SEC - offset_nsec); + else + exp = ktime_add_ns(exp, SYNC_PERIOD_NS - offset_nsec); - queue_delayed_work(system_power_efficient_wq, &sync_work, - timespec64_to_jiffies(&next)); + hrtimer_start(&sync_hrtimer, exp, HRTIMER_MODE_ABS); } static void sync_rtc_clock(void) { - unsigned long target_nsec; - struct timespec64 adjust, now; + unsigned long offset_nsec; + struct timespec64 adjust; int rc; if (!IS_ENABLED(CONFIG_RTC_SYSTOHC)) return; - ktime_get_real_ts64(&now); + ktime_get_real_ts64(&adjust); - adjust = now; if (persistent_clock_is_local) adjust.tv_sec -= (sys_tz.tz_minuteswest * 60); /* - * The current RTC in use will provide the target_nsec it wants to be - * called at, and does rtc_tv_nsec_ok internally. + * The current RTC in use will provide the nanoseconds offset prior + * to a full second it wants to be called at, and invokes + * rtc_tv_nsec_ok() internally. */ - rc = rtc_set_ntp_time(adjust, &target_nsec); + rc = rtc_set_ntp_time(adjust, &offset_nsec); if (rc == -ENODEV) return; - sched_sync_hw_clock(now, target_nsec, rc); + sched_sync_hw_clock(offset_nsec, rc != 0); } #ifdef CONFIG_GENERIC_CMOS_UPDATE @@ -599,7 +589,7 @@ static bool sync_cmos_clock(void) } } - sched_sync_hw_clock(now, target_nsec, rc); + sched_sync_hw_clock(target_nsec, rc != 0); return true; } @@ -613,7 +603,12 @@ static bool sync_cmos_clock(void) */ static void sync_hw_clock(struct work_struct *work) { - if (!ntp_synced()) + /* + * Don't update if STA_UNSYNC is set and if ntp_notify_cmos_timer() + * managed to schedule the work between the timer firing and the + * work being able to rearm the timer. Wait for the timer to expire. + */ + if (!ntp_synced() || hrtimer_is_queued(&sync_hrtimer)) return; if (sync_cmos_clock()) @@ -624,13 +619,23 @@ static void sync_hw_clock(struct work_struct *work) void ntp_notify_cmos_timer(void) { - if (!ntp_synced()) - return; + /* + * When the work is currently executed but has not yet the timer + * rearmed this queues the work immediately again. No big issue, + * just a pointless work scheduled. + */ + if (ntp_synced() && !hrtimer_is_queued(&sync_hrtimer)) + queue_work(system_power_efficient_wq, &sync_work); +} - if (IS_ENABLED(CONFIG_GENERIC_CMOS_UPDATE) || - IS_ENABLED(CONFIG_RTC_SYSTOHC)) - queue_delayed_work(system_power_efficient_wq, &sync_work, 0); +static void __init ntp_init_cmos_sync(void) +{ + hrtimer_init(&sync_hrtimer, CLOCK_REALTIME, HRTIMER_MODE_ABS); + sync_hrtimer.function = sync_timer_callback; } +#else /* CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) */ +static inline void __init ntp_init_cmos_sync(void) { } +#endif /* !CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) */ /* * Propagate a new txc->status value into the NTP state: @@ -1044,4 +1049,5 @@ __setup("ntp_tick_adj=", ntp_tick_adj_setup); void __init ntp_init(void) { ntp_clear(); + ntp_init_cmos_sync(); } diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index 908ecaa65fc3..23d1b74c3065 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -12,4 +12,11 @@ extern int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts, s32 *time_tai, struct audit_ntp_data *ad); extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts); + +#if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) +extern void ntp_notify_cmos_timer(void); +#else +static inline void ntp_notify_cmos_timer(void) { } +#endif + #endif /* _LINUX_NTP_INTERNAL_H */ -- cgit v1.2.3-71-gd317 From 33e62e832384c8cb523044e0e9d99d7133f98e93 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 6 Dec 2020 22:46:19 +0100 Subject: ntp, rtc: Move rtc_set_ntp_time() to ntp code rtc_set_ntp_time() is not really RTC functionality as the code is just a user of RTC. Move it into the NTP code which allows further cleanups. Requested-by: Alexandre Belloni Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Acked-by: Alexandre Belloni Link: https://lore.kernel.org/r/20201206220542.166871172@linutronix.de --- drivers/rtc/Makefile | 1 - drivers/rtc/systohc.c | 61 ----------------------------------- include/linux/rtc.h | 34 -------------------- kernel/time/ntp.c | 88 +++++++++++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 85 insertions(+), 99 deletions(-) delete mode 100644 drivers/rtc/systohc.c (limited to 'include/linux') diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index bfb57464118d..bb8f319b09fb 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -6,7 +6,6 @@ ccflags-$(CONFIG_RTC_DEBUG) := -DDEBUG obj-$(CONFIG_RTC_LIB) += lib.o -obj-$(CONFIG_RTC_SYSTOHC) += systohc.o obj-$(CONFIG_RTC_CLASS) += rtc-core.o obj-$(CONFIG_RTC_MC146818_LIB) += rtc-mc146818-lib.o rtc-core-y := class.o interface.o diff --git a/drivers/rtc/systohc.c b/drivers/rtc/systohc.c deleted file mode 100644 index 8b70f0520e13..000000000000 --- a/drivers/rtc/systohc.c +++ /dev/null @@ -1,61 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include - -/** - * rtc_set_ntp_time - Save NTP synchronized time to the RTC - * @now: Current time of day - * @target_nsec: pointer for desired now->tv_nsec value - * - * Replacement for the NTP platform function update_persistent_clock64 - * that stores time for later retrieval by rtc_hctosys. - * - * Returns 0 on successful RTC update, -ENODEV if a RTC update is not - * possible at all, and various other -errno for specific temporary failure - * cases. - * - * -EPROTO is returned if now.tv_nsec is not close enough to *target_nsec. - * - * If temporary failure is indicated the caller should try again 'soon' - */ -int rtc_set_ntp_time(struct timespec64 now, unsigned long *target_nsec) -{ - struct rtc_device *rtc; - struct rtc_time tm; - struct timespec64 to_set; - int err = -ENODEV; - bool ok; - - rtc = rtc_class_open(CONFIG_RTC_SYSTOHC_DEVICE); - if (!rtc) - goto out_err; - - if (!rtc->ops || !rtc->ops->set_time) - goto out_close; - - /* Compute the value of tv_nsec we require the caller to supply in - * now.tv_nsec. This is the value such that (now + - * set_offset_nsec).tv_nsec == 0. - */ - set_normalized_timespec64(&to_set, 0, -rtc->set_offset_nsec); - *target_nsec = to_set.tv_nsec; - - /* The ntp code must call this with the correct value in tv_nsec, if - * it does not we update target_nsec and return EPROTO to make the ntp - * code try again later. - */ - ok = rtc_tv_nsec_ok(rtc->set_offset_nsec, &to_set, &now); - if (!ok) { - err = -EPROTO; - goto out_close; - } - - rtc_time64_to_tm(to_set.tv_sec, &tm); - - err = rtc_set_time(rtc, &tm); - -out_close: - rtc_class_close(rtc); -out_err: - return err; -} diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 22d1575e4991..ff62680b48ca 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -165,7 +165,6 @@ int __rtc_register_device(struct module *owner, struct rtc_device *rtc); extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm); -extern int rtc_set_ntp_time(struct timespec64 now, unsigned long *target_nsec); int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm); extern int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); @@ -205,39 +204,6 @@ static inline bool is_leap_year(unsigned int year) return (!(year % 4) && (year % 100)) || !(year % 400); } -/* Determine if we can call to driver to set the time. Drivers can only be - * called to set a second aligned time value, and the field set_offset_nsec - * specifies how far away from the second aligned time to call the driver. - * - * This also computes 'to_set' which is the time we are trying to set, and has - * a zero in tv_nsecs, such that: - * to_set - set_delay_nsec == now +/- FUZZ - * - */ -static inline bool rtc_tv_nsec_ok(s64 set_offset_nsec, - struct timespec64 *to_set, - const struct timespec64 *now) -{ - /* Allowed error in tv_nsec, arbitarily set to 5 jiffies in ns. */ - const unsigned long TIME_SET_NSEC_FUZZ = TICK_NSEC * 5; - struct timespec64 delay = {.tv_sec = 0, - .tv_nsec = set_offset_nsec}; - - *to_set = timespec64_add(*now, delay); - - if (to_set->tv_nsec < TIME_SET_NSEC_FUZZ) { - to_set->tv_nsec = 0; - return true; - } - - if (to_set->tv_nsec > NSEC_PER_SEC - TIME_SET_NSEC_FUZZ) { - to_set->tv_sec++; - to_set->tv_nsec = 0; - return true; - } - return false; -} - #define rtc_register_device(device) \ __rtc_register_device(THIS_MODULE, device) diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index ff1a7b8ec4ef..84a554622cee 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -519,15 +519,94 @@ static void sched_sync_hw_clock(unsigned long offset_nsec, bool retry) hrtimer_start(&sync_hrtimer, exp, HRTIMER_MODE_ABS); } +/* + * Determine if we can call to driver to set the time. Drivers can only be + * called to set a second aligned time value, and the field set_offset_nsec + * specifies how far away from the second aligned time to call the driver. + * + * This also computes 'to_set' which is the time we are trying to set, and has + * a zero in tv_nsecs, such that: + * to_set - set_delay_nsec == now +/- FUZZ + * + */ +static inline bool rtc_tv_nsec_ok(long set_offset_nsec, + struct timespec64 *to_set, + const struct timespec64 *now) +{ + /* Allowed error in tv_nsec, arbitarily set to 5 jiffies in ns. */ + const unsigned long TIME_SET_NSEC_FUZZ = TICK_NSEC * 5; + struct timespec64 delay = {.tv_sec = 0, + .tv_nsec = set_offset_nsec}; + + *to_set = timespec64_add(*now, delay); + + if (to_set->tv_nsec < TIME_SET_NSEC_FUZZ) { + to_set->tv_nsec = 0; + return true; + } + + if (to_set->tv_nsec > NSEC_PER_SEC - TIME_SET_NSEC_FUZZ) { + to_set->tv_sec++; + to_set->tv_nsec = 0; + return true; + } + return false; +} + +#ifdef CONFIG_RTC_SYSTOHC +/* + * rtc_set_ntp_time - Save NTP synchronized time to the RTC + */ +static int rtc_set_ntp_time(struct timespec64 now, unsigned long *target_nsec) +{ + struct rtc_device *rtc; + struct rtc_time tm; + struct timespec64 to_set; + int err = -ENODEV; + bool ok; + + rtc = rtc_class_open(CONFIG_RTC_SYSTOHC_DEVICE); + if (!rtc) + goto out_err; + + if (!rtc->ops || !rtc->ops->set_time) + goto out_close; + + /* + * Compute the value of tv_nsec we require the caller to supply in + * now.tv_nsec. This is the value such that (now + + * set_offset_nsec).tv_nsec == 0. + */ + set_normalized_timespec64(&to_set, 0, -rtc->set_offset_nsec); + *target_nsec = to_set.tv_nsec; + + /* + * The ntp code must call this with the correct value in tv_nsec, if + * it does not we update target_nsec and return EPROTO to make the ntp + * code try again later. + */ + ok = rtc_tv_nsec_ok(rtc->set_offset_nsec, &to_set, &now); + if (!ok) { + err = -EPROTO; + goto out_close; + } + + rtc_time64_to_tm(to_set.tv_sec, &tm); + + err = rtc_set_time(rtc, &tm); + +out_close: + rtc_class_close(rtc); +out_err: + return err; +} + static void sync_rtc_clock(void) { unsigned long offset_nsec; struct timespec64 adjust; int rc; - if (!IS_ENABLED(CONFIG_RTC_SYSTOHC)) - return; - ktime_get_real_ts64(&adjust); if (persistent_clock_is_local) @@ -544,6 +623,9 @@ static void sync_rtc_clock(void) sched_sync_hw_clock(offset_nsec, rc != 0); } +#else +static inline void sync_rtc_clock(void) { } +#endif #ifdef CONFIG_GENERIC_CMOS_UPDATE int __weak update_persistent_clock64(struct timespec64 now64) -- cgit v1.2.3-71-gd317 From 69eca258c85000564577642ba28335eb4e1df8f0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 6 Dec 2020 22:46:20 +0100 Subject: ntp: Make the RTC sync offset less obscure The current RTC set_offset_nsec value is not really intuitive to understand. tsched twrite(t2.tv_sec - 1) t2 (seconds increment) The offset is calculated from twrite based on the assumption that t2 - twrite == 1s. That means for the MC146818 RTC the offset needs to be negative so that the write happens 500ms before t2. It's easier to understand when the whole calculation is based on t2. That avoids negative offsets and the meaning is obvious: t2 - twrite: The time defined by the chip when seconds increment after the write. twrite - tsched: The time for the transport to the point where the chip is updated. ==> set_offset_nsec = t2 - tsched ttransport = twrite - tsched tRTCinc = t2 - twrite ==> set_offset_nsec = ttransport + tRTCinc tRTCinc is a chip property and can be obtained from the data sheet. ttransport depends on how the RTC is connected. It is close to 0 for directly accessible RTCs. For RTCs behind a slow bus, e.g. i2c, it's the time required to send the update over the bus. This can be estimated or even calibrated, but that's a different problem. Adjust the implementation and update comments accordingly. Signed-off-by: Thomas Gleixner Acked-by: Alexandre Belloni Link: https://lore.kernel.org/r/20201206220542.263204937@linutronix.de --- drivers/rtc/class.c | 9 +++++++-- drivers/rtc/rtc-cmos.c | 2 +- include/linux/rtc.h | 35 +++++++++++++++++++++++++++++------ kernel/time/ntp.c | 47 ++++++++++++++++++++++++----------------------- 4 files changed, 61 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index d7957376eb96..5855aa2eef62 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -200,8 +200,13 @@ static struct rtc_device *rtc_allocate_device(void) device_initialize(&rtc->dev); - /* Drivers can revise this default after allocating the device. */ - rtc->set_offset_nsec = 5 * NSEC_PER_MSEC; + /* + * Drivers can revise this default after allocating the device. + * The default is what most RTCs do: Increment seconds exactly one + * second after the write happened. This adds a default transport + * time of 5ms which is at least halfways close to reality. + */ + rtc->set_offset_nsec = NSEC_PER_SEC + 5 * NSEC_PER_MSEC; rtc->irq_freq = 1; rtc->max_user_freq = 64; diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 7728faca01b4..c5bcd2adc9fe 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -869,7 +869,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq) goto cleanup2; /* Set the sync offset for the periodic 11min update correct */ - cmos_rtc.rtc->set_offset_nsec = -(NSEC_PER_SEC / 2); + cmos_rtc.rtc->set_offset_nsec = NSEC_PER_SEC / 2; /* export at least the first block of NVRAM */ nvmem_cfg.size = address_space - NVRAM_OFFSET; diff --git a/include/linux/rtc.h b/include/linux/rtc.h index ff62680b48ca..b829382de6c3 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -110,13 +110,36 @@ struct rtc_device { /* Some hardware can't support UIE mode */ int uie_unsupported; - /* Number of nsec it takes to set the RTC clock. This influences when - * the set ops are called. An offset: - * - of 0.5 s will call RTC set for wall clock time 10.0 s at 9.5 s - * - of 1.5 s will call RTC set for wall clock time 10.0 s at 8.5 s - * - of -0.5 s will call RTC set for wall clock time 10.0 s at 10.5 s + /* + * This offset specifies the update timing of the RTC. + * + * tsched t1 write(t2.tv_sec - 1sec)) t2 RTC increments seconds + * + * The offset defines how tsched is computed so that the write to + * the RTC (t2.tv_sec - 1sec) is correct versus the time required + * for the transport of the write and the time which the RTC needs + * to increment seconds the first time after the write (t2). + * + * For direct accessible RTCs tsched ~= t1 because the write time + * is negligible. For RTCs behind slow busses the transport time is + * significant and has to be taken into account. + * + * The time between the write (t1) and the first increment after + * the write (t2) is RTC specific. For a MC146818 RTC it's 500ms, + * for many others it's exactly 1 second. Consult the datasheet. + * + * The value of this offset is also used to calculate the to be + * written value (t2.tv_sec - 1sec) at tsched. + * + * The default value for this is NSEC_PER_SEC + 10 msec default + * transport time. The offset can be adjusted by drivers so the + * calculation for the to be written value at tsched becomes + * correct: + * + * newval = tsched + set_offset_nsec - NSEC_PER_SEC + * and (tsched + set_offset_nsec) % NSEC_PER_SEC == 0 */ - long set_offset_nsec; + unsigned long set_offset_nsec; bool registered; diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 84a554622cee..a34ac069335f 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -520,22 +520,33 @@ static void sched_sync_hw_clock(unsigned long offset_nsec, bool retry) } /* - * Determine if we can call to driver to set the time. Drivers can only be - * called to set a second aligned time value, and the field set_offset_nsec - * specifies how far away from the second aligned time to call the driver. + * Check whether @now is correct versus the required time to update the RTC + * and calculate the value which needs to be written to the RTC so that the + * next seconds increment of the RTC after the write is aligned with the next + * seconds increment of clock REALTIME. * - * This also computes 'to_set' which is the time we are trying to set, and has - * a zero in tv_nsecs, such that: - * to_set - set_delay_nsec == now +/- FUZZ + * tsched t1 write(t2.tv_sec - 1sec)) t2 RTC increments seconds * + * t2.tv_nsec == 0 + * tsched = t2 - set_offset_nsec + * newval = t2 - NSEC_PER_SEC + * + * ==> neval = tsched + set_offset_nsec - NSEC_PER_SEC + * + * As the execution of this code is not guaranteed to happen exactly at + * tsched this allows it to happen within a fuzzy region: + * + * abs(now - tsched) < FUZZ + * + * If @now is not inside the allowed window the function returns false. */ -static inline bool rtc_tv_nsec_ok(long set_offset_nsec, +static inline bool rtc_tv_nsec_ok(unsigned long set_offset_nsec, struct timespec64 *to_set, const struct timespec64 *now) { /* Allowed error in tv_nsec, arbitarily set to 5 jiffies in ns. */ const unsigned long TIME_SET_NSEC_FUZZ = TICK_NSEC * 5; - struct timespec64 delay = {.tv_sec = 0, + struct timespec64 delay = {.tv_sec = -1, .tv_nsec = set_offset_nsec}; *to_set = timespec64_add(*now, delay); @@ -557,11 +568,11 @@ static inline bool rtc_tv_nsec_ok(long set_offset_nsec, /* * rtc_set_ntp_time - Save NTP synchronized time to the RTC */ -static int rtc_set_ntp_time(struct timespec64 now, unsigned long *target_nsec) +static int rtc_set_ntp_time(struct timespec64 now, unsigned long *offset_nsec) { + struct timespec64 to_set; struct rtc_device *rtc; struct rtc_time tm; - struct timespec64 to_set; int err = -ENODEV; bool ok; @@ -572,19 +583,9 @@ static int rtc_set_ntp_time(struct timespec64 now, unsigned long *target_nsec) if (!rtc->ops || !rtc->ops->set_time) goto out_close; - /* - * Compute the value of tv_nsec we require the caller to supply in - * now.tv_nsec. This is the value such that (now + - * set_offset_nsec).tv_nsec == 0. - */ - set_normalized_timespec64(&to_set, 0, -rtc->set_offset_nsec); - *target_nsec = to_set.tv_nsec; + /* Store the update offset for this RTC */ + *offset_nsec = rtc->set_offset_nsec; - /* - * The ntp code must call this with the correct value in tv_nsec, if - * it does not we update target_nsec and return EPROTO to make the ntp - * code try again later. - */ ok = rtc_tv_nsec_ok(rtc->set_offset_nsec, &to_set, &now); if (!ok) { err = -EPROTO; @@ -657,7 +658,7 @@ static bool sync_cmos_clock(void) * implement this legacy API. */ ktime_get_real_ts64(&now); - if (rtc_tv_nsec_ok(-1 * target_nsec, &adjust, &now)) { + if (rtc_tv_nsec_ok(target_nsec, &adjust, &now)) { if (persistent_clock_is_local) adjust.tv_sec -= (sys_tz.tz_minuteswest * 60); rc = update_persistent_clock64(adjust); -- cgit v1.2.3-71-gd317 From 3cabca87b329cbcbdf295be0094adbd72c7b1f67 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 12 Dec 2020 18:29:20 +0100 Subject: ntp: Fix prototype in the !CONFIG_GENERIC_CMOS_UPDATE case In the !CONFIG_GENERIC_CMOS_UPDATE case the update_persistent_clock64() function gets defined as a stub in ntp.c - make the prototype in conditional on CONFIG_GENERIC_CMOS_UPDATE as well. Fixes: 76e87d96b30b5 ("ntp: Consolidate the RTC update implementation") Signed-off-by: Ingo Molnar Acked-by: Thomas Gleixner --- include/linux/timekeeping.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 7f7e4a3f4394..929d3f3937c0 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -303,6 +303,8 @@ extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, struct timespec64 *boot_offset); +#ifdef CONFIG_GENERIC_CMOS_UPDATE extern int update_persistent_clock64(struct timespec64 now); +#endif #endif -- cgit v1.2.3-71-gd317