Merge tag 'timers-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timers and timekeeping updates from Thomas Gleixner:
 "Core:

   - Robustness improvements for the NOHZ tick management

   - Fixes and consolidation of the NTP/RTC synchronization code

   - Small fixes and improvements in various places

   - A set of function documentation udpates and fixes

   Drivers:

   - Cleanups and improvements in various clocksoure/event drivers

   - Removal of the EZChip NPS clocksource driver as the platfrom
     support was removed from ARC

   - The usual set of new device tree binding and json conversions

   - The RTC driver which have been acked by the RTC maintainer:

       * fix a long standing bug in the MC146818 library code which can
         cause reading garbage during the RTC internal update.

       * changes related to the NTP/RTC consolidation work"

* tag 'timers-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (46 commits)
  ntp: Fix prototype in the !CONFIG_GENERIC_CMOS_UPDATE case
  tick/sched: Make jiffies update quick check more robust
  ntp: Consolidate the RTC update implementation
  ntp: Make the RTC sync offset less obscure
  ntp, rtc: Move rtc_set_ntp_time() to ntp code
  ntp: Make the RTC synchronization more reliable
  rtc: core: Make the sync offset default more realistic
  rtc: cmos: Make rtc_cmos sync offset correct
  rtc: mc146818: Reduce spinlock section in mc146818_set_time()
  rtc: mc146818: Prevent reading garbage
  clocksource/drivers/sh_cmt: Fix potential deadlock when calling runtime PM
  clocksource/drivers/arm_arch_timer: Correct fault programming of CNTKCTL_EL1.EVNTI
  clocksource/drivers/arm_arch_timer: Use stable count reader in erratum sne
  clocksource/drivers/dw_apb_timer_of: Add error handling if no clock available
  clocksource/drivers/riscv: Make RISCV_TIMER depends on RISCV_SBI
  clocksource/drivers/ingenic: Fix section mismatch
  clocksource/drivers/cadence_ttc: Fix memory leak in ttc_setup_clockevent()
  dt-bindings: timer: renesas: tmu: Convert to json-schema
  dt-bindings: timer: renesas: tmu: Document r8a774e1 bindings
  clocksource/drivers/orion: Add missing clk_disable_unprepare() on error path
  ...

1 files changed, 139 insertions, 90 deletions

diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 069ca78fb0bf..7404d3831527 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -494,65 +494,74 @@ 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;
-
-	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;
-	}
-
-	/* 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;
-	}
+	queue_work(system_power_efficient_wq, &sync_work);
 
-	queue_delayed_work(system_power_efficient_wq, &sync_work,
-			   timespec64_to_jiffies(&next));
+	return HRTIMER_NORESTART;
 }
 
-static void sync_rtc_clock(void)
+static void sched_sync_hw_clock(unsigned long offset_nsec, bool retry)
 {
-	unsigned long target_nsec;
-	struct timespec64 adjust, now;
-	int rc;
+	ktime_t exp = ktime_set(ktime_get_real_seconds(), 0);
 
-	if (!IS_ENABLED(CONFIG_RTC_SYSTOHC))
-		return;
+	if (retry)
+		exp = ktime_add_ns(exp, 2 * NSEC_PER_SEC - offset_nsec);
+	else
+		exp = ktime_add_ns(exp, SYNC_PERIOD_NS - offset_nsec);
 
-	ktime_get_real_ts64(&now);
+	hrtimer_start(&sync_hrtimer, exp, HRTIMER_MODE_ABS);
+}
 
-	adjust = now;
-	if (persistent_clock_is_local)
-		adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
+/*
+ * 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.
+ *
+ * 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(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 = -1,
+				   .tv_nsec = set_offset_nsec};
 
-	/*
-	 * The current RTC in use will provide the target_nsec it wants to be
-	 * called at, and does rtc_tv_nsec_ok internally.
-	 */
-	rc = rtc_set_ntp_time(adjust, &target_nsec);
-	if (rc == -ENODEV)
-		return;
+	*to_set = timespec64_add(*now, delay);
+
+	if (to_set->tv_nsec < TIME_SET_NSEC_FUZZ) {
+		to_set->tv_nsec = 0;
+		return true;
+	}
 
-	sched_sync_hw_clock(now, target_nsec, rc);
+	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_GENERIC_CMOS_UPDATE
@@ -560,48 +569,47 @@ int __weak update_persistent_clock64(struct timespec64 now64)
 {
 	return -ENODEV;
 }
+#else
+static inline int update_persistent_clock64(struct timespec64 now64)
+{
+	return -ENODEV;
+}
 #endif
 
-static bool sync_cmos_clock(void)
+#ifdef CONFIG_RTC_SYSTOHC
+/* Save NTP synchronized time to the RTC */
+static int update_rtc(struct timespec64 *to_set, unsigned long *offset_nsec)
 {
-	static bool no_cmos;
-	struct timespec64 now;
-	struct timespec64 adjust;
-	int rc = -EPROTO;
-	long target_nsec = NSEC_PER_SEC / 2;
+	struct rtc_device *rtc;
+	struct rtc_time tm;
+	int err = -ENODEV;
 
-	if (!IS_ENABLED(CONFIG_GENERIC_CMOS_UPDATE))
-		return false;
+	rtc = rtc_class_open(CONFIG_RTC_SYSTOHC_DEVICE);
+	if (!rtc)
+		return -ENODEV;
 
-	if (no_cmos)
-		return false;
+	if (!rtc->ops || !rtc->ops->set_time)
+		goto out_close;
 
-	/*
-	 * Historically update_persistent_clock64() has followed x86
-	 * semantics, which match the MC146818A/etc RTC. This RTC will store
-	 * 'adjust' and then in .5s it will advance once second.
-	 *
-	 * Architectures are strongly encouraged to use rtclib and not
-	 * implement this legacy API.
-	 */
-	ktime_get_real_ts64(&now);
-	if (rtc_tv_nsec_ok(-1 * target_nsec, &adjust, &now)) {
-		if (persistent_clock_is_local)
-			adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
-		rc = update_persistent_clock64(adjust);
-		/*
-		 * The machine does not support update_persistent_clock64 even
-		 * though it defines CONFIG_GENERIC_CMOS_UPDATE.
-		 */
-		if (rc == -ENODEV) {
-			no_cmos = true;
-			return false;
-		}
+	/* First call might not have the correct offset */
+	if (*offset_nsec == rtc->set_offset_nsec) {
+		rtc_time64_to_tm(to_set->tv_sec, &tm);
+		err = rtc_set_time(rtc, &tm);
+	} else {
+		/* Store the update offset and let the caller try again */
+		*offset_nsec = rtc->set_offset_nsec;
+		err = -EAGAIN;
 	}
-
-	sched_sync_hw_clock(now, target_nsec, rc);
-	return true;
+out_close:
+	rtc_class_close(rtc);
+	return err;
+}
+#else
+static inline int update_rtc(struct timespec64 *to_set, unsigned long *offset_nsec)
+{
+	return -ENODEV;
 }
+#endif
 
 /*
  * If we have an externally synchronized Linux clock, then update RTC clock
@@ -613,24 +621,64 @@ static bool sync_cmos_clock(void)
  */
 static void sync_hw_clock(struct work_struct *work)
 {
-	if (!ntp_synced())
-		return;
+	/*
+	 * The default synchronization offset is 500ms for the deprecated
+	 * update_persistent_clock64() under the assumption that it uses
+	 * the infamous CMOS clock (MC146818).
+	 */
+	static unsigned long offset_nsec = NSEC_PER_SEC / 2;
+	struct timespec64 now, to_set;
+	int res = -EAGAIN;
 
-	if (sync_cmos_clock())
+	/*
+	 * 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;
 
-	sync_rtc_clock();
+	ktime_get_real_ts64(&now);
+	/* If @now is not in the allowed window, try again */
+	if (!rtc_tv_nsec_ok(offset_nsec, &to_set, &now))
+		goto rearm;
+
+	/* Take timezone adjusted RTCs into account */
+	if (persistent_clock_is_local)
+		to_set.tv_sec -= (sys_tz.tz_minuteswest * 60);
+
+	/* Try the legacy RTC first. */
+	res = update_persistent_clock64(to_set);
+	if (res != -ENODEV)
+		goto rearm;
+
+	/* Try the RTC class */
+	res = update_rtc(&to_set, &offset_nsec);
+	if (res == -ENODEV)
+		return;
+rearm:
+	sched_sync_hw_clock(offset_nsec, res != 0);
 }
 
 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 +1092,5 @@ __setup("ntp_tick_adj=", ntp_tick_adj_setup);
 void __init ntp_init(void)
 {
 	ntp_clear();
+	ntp_init_cmos_sync();
 }