Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Ingo Molnar:
 "The main changes in this cycle were:

   - rework hrtimer expiry calculation in hrtimer_interrupt(): the
     previous code had a subtle bug where expiry caching would miss an
     expiry, resulting in occasional bogus (late) expiry of hrtimers.

   - continuing Y2038 fixes

   - ktime division optimization

   - misc smaller fixes and cleanups"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  hrtimer: Make __hrtimer_get_next_event() static
  rtc: Convert rtc_set_ntp_time() to use timespec64
  rtc: Remove redundant rtc_valid_tm() from rtc_hctosys()
  rtc: Modify rtc_hctosys() to address y2038 issues
  rtc: Update rtc-dev to use y2038-safe time interfaces
  rtc: Update interface.c to use y2038-safe time interfaces
  time: Expose get_monotonic_boottime64 for in-kernel use
  time: Expose getboottime64 for in-kernel uses
  ktime: Optimize ktime_divns for constant divisors
  hrtimer: Prevent stale expiry time in hrtimer_interrupt()
  ktime.h: Introduce ktime_ms_delta

11 files changed, 120 insertions, 104 deletions

diff --git a/drivers/rtc/hctosys.c b/drivers/rtc/hctosys.c
index 4aa60d74004e..6c719f23520a 100644
--- a/drivers/rtc/hctosys.c
+++ b/drivers/rtc/hctosys.c
@@ -26,7 +26,7 @@ static int __init rtc_hctosys(void)
 {
         int err = -ENODEV;
         struct rtc_time tm;
-        struct timespec tv = {
+        struct timespec64 tv64 = {
                 .tv_nsec = NSEC_PER_SEC >> 1,
         };
         struct rtc_device *rtc = rtc_class_open(CONFIG_RTC_HCTOSYS_DEVICE);
@@ -45,25 +45,17 @@ static int __init rtc_hctosys(void)
 
         }
 
-        err = rtc_valid_tm(&tm);
-        if (err) {
-                dev_err(rtc->dev.parent,
-                        "hctosys: invalid date/time\n");
-                goto err_invalid;
-        }
-
-        rtc_tm_to_time(&tm, &tv.tv_sec);
+        tv64.tv_sec = rtc_tm_to_time64(&tm);
 
-        err = do_settimeofday(&tv);
+        err = do_settimeofday64(&tv64);
 
         dev_info(rtc->dev.parent,
                 "setting system clock to "
-                "%d-%02d-%02d %02d:%02d:%02d UTC (%u)\n",
+                "%d-%02d-%02d %02d:%02d:%02d UTC (%lld)\n",
                 tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
                 tm.tm_hour, tm.tm_min, tm.tm_sec,
-                (unsigned int) tv.tv_sec);
+                (long long) tv64.tv_sec);
 
-err_invalid:
 err_read:
         rtc_class_close(rtc);
 
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 45bfc28ee3aa..37215cf983e9 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -73,10 +73,8 @@ int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm)
         else if (rtc->ops->set_time)
                 err = rtc->ops->set_time(rtc->dev.parent, tm);
         else if (rtc->ops->set_mmss) {
-                unsigned long secs;
-                err = rtc_tm_to_time(tm, &secs);
-                if (err == 0)
-                        err = rtc->ops->set_mmss(rtc->dev.parent, secs);
+                time64_t secs64 = rtc_tm_to_time64(tm);
+                err = rtc->ops->set_mmss(rtc->dev.parent, secs64);
         } else
                 err = -EINVAL;
 
@@ -105,7 +103,7 @@ int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs)
 
                 err = rtc->ops->read_time(rtc->dev.parent, &old);
                 if (err == 0) {
-                        rtc_time_to_tm(secs, &new);
+                        rtc_time64_to_tm(secs, &new);
 
                         /*
                          * avoid writing when we're going to change the day of
@@ -157,7 +155,7 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
         int err;
         struct rtc_time before, now;
         int first_time = 1;
-        unsigned long t_now, t_alm;
+        time64_t t_now, t_alm;
         enum { none, day, month, year } missing = none;
         unsigned days;
 
@@ -258,8 +256,8 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
         }
 
         /* with luck, no rollover is needed */
-        rtc_tm_to_time(&now, &t_now);
-        rtc_tm_to_time(&alarm->time, &t_alm);
+        t_now = rtc_tm_to_time64(&now);
+        t_alm = rtc_tm_to_time64(&alarm->time);
         if (t_now < t_alm)
                 goto done;
 
@@ -273,7 +271,7 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
         case day:
                 dev_dbg(&rtc->dev, "alarm rollover: %s\n", "day");
                 t_alm += 24 * 60 * 60;
-                rtc_time_to_tm(t_alm, &alarm->time);
+                rtc_time64_to_tm(t_alm, &alarm->time);
                 break;
 
         /* Month rollover ... if it's the 31th, an alarm on the 3rd will
@@ -346,19 +344,19 @@ EXPORT_SYMBOL_GPL(rtc_read_alarm);
 static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 {
         struct rtc_time tm;
-        long now, scheduled;
+        time64_t now, scheduled;
         int err;
 
         err = rtc_valid_tm(&alarm->time);
         if (err)
                 return err;
-        rtc_tm_to_time(&alarm->time, &scheduled);
+        scheduled = rtc_tm_to_time64(&alarm->time);
 
         /* Make sure we're not setting alarms in the past */
         err = __rtc_read_time(rtc, &tm);
         if (err)
                 return err;
-        rtc_tm_to_time(&tm, &now);
+        now = rtc_tm_to_time64(&tm);
         if (scheduled <= now)
                 return -ETIME;
         /*
diff --git a/drivers/rtc/rtc-dev.c b/drivers/rtc/rtc-dev.c
index d04939369251..799c34bcb26f 100644
--- a/drivers/rtc/rtc-dev.c
+++ b/drivers/rtc/rtc-dev.c
@@ -304,12 +304,12 @@ static long rtc_dev_ioctl(struct file *file,
                  * Not supported here.
                  */
                 {
-                        unsigned long now, then;
+                        time64_t now, then;
 
                         err = rtc_read_time(rtc, &tm);
                         if (err < 0)
                                 return err;
-                        rtc_tm_to_time(&tm, &now);
+                        now = rtc_tm_to_time64(&tm);
 
                         alarm.time.tm_mday = tm.tm_mday;
                         alarm.time.tm_mon = tm.tm_mon;
@@ -317,11 +317,11 @@ static long rtc_dev_ioctl(struct file *file,
                         err  = rtc_valid_tm(&alarm.time);
                         if (err < 0)
                                 return err;
-                        rtc_tm_to_time(&alarm.time, &then);
+                        then = rtc_tm_to_time64(&alarm.time);
 
                         /* alarm may need to wrap into tomorrow */
                         if (then < now) {
-                                rtc_time_to_tm(now + 24 * 60 * 60, &tm);
+                                rtc_time64_to_tm(now + 24 * 60 * 60, &tm);
                                 alarm.time.tm_mday = tm.tm_mday;
                                 alarm.time.tm_mon = tm.tm_mon;
                                 alarm.time.tm_year = tm.tm_year;
diff --git a/drivers/rtc/systohc.c b/drivers/rtc/systohc.c
index bf3e242ccc5c..eb71872d0361 100644
--- a/drivers/rtc/systohc.c
+++ b/drivers/rtc/systohc.c
@@ -20,16 +20,16 @@
  *
  * If temporary failure is indicated the caller should try again 'soon'
  */
-int rtc_set_ntp_time(struct timespec now)
+int rtc_set_ntp_time(struct timespec64 now)
 {
         struct rtc_device *rtc;
         struct rtc_time tm;
         int err = -ENODEV;
 
         if (now.tv_nsec < (NSEC_PER_SEC >> 1))
-                rtc_time_to_tm(now.tv_sec, &tm);
+                rtc_time64_to_tm(now.tv_sec, &tm);
         else
-                rtc_time_to_tm(now.tv_sec + 1, &tm);
+                rtc_time64_to_tm(now.tv_sec + 1, &tm);
 
         rtc = rtc_class_open(CONFIG_RTC_HCTOSYS_DEVICE);
         if (rtc) {
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index a036d058a249..05f6df1fdf5b 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -170,6 +170,7 @@ enum  hrtimer_base_type {
  * @clock_was_set:      Indicates that clock was set from irq context.
  * @expires_next:       absolute time of the next event which was scheduled
  *                      via clock_set_next_event()
+ * @in_hrtirq:          hrtimer_interrupt() is currently executing
  * @hres_active:        State of high resolution mode
  * @hang_detected:      The last hrtimer interrupt detected a hang
  * @nr_events:          Total number of hrtimer interrupt events
@@ -185,6 +186,7 @@ struct hrtimer_cpu_base {
         unsigned int                    clock_was_set;
 #ifdef CONFIG_HIGH_RES_TIMERS
         ktime_t                         expires_next;
+        int                             in_hrtirq;
         int                             hres_active;
         int                             hang_detected;
         unsigned long                   nr_events;
diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index c9d645ad98ff..5fc3d1083071 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -166,7 +166,17 @@ static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2)
 }
 
 #if BITS_PER_LONG < 64
-extern u64 ktime_divns(const ktime_t kt, s64 div);
+extern u64 __ktime_divns(const ktime_t kt, s64 div);
+static inline u64 ktime_divns(const ktime_t kt, s64 div)
+{
+        if (__builtin_constant_p(div) && !(div >> 32)) {
+                u64 ns = kt.tv64;
+                do_div(ns, div);
+                return ns;
+        } else {
+                return __ktime_divns(kt, div);
+        }
+}
 #else /* BITS_PER_LONG < 64 */
 # define ktime_divns(kt, div)           (u64)((kt).tv64 / (div))
 #endif
@@ -186,6 +196,11 @@ static inline s64 ktime_us_delta(const ktime_t later, const ktime_t earlier)
        return ktime_to_us(ktime_sub(later, earlier));
 }
 
+static inline s64 ktime_ms_delta(const ktime_t later, const ktime_t earlier)
+{
+        return ktime_to_ms(ktime_sub(later, earlier));
+}
+
 static inline ktime_t ktime_add_us(const ktime_t kt, const u64 usec)
 {
         return ktime_add_ns(kt, usec * NSEC_PER_USEC);
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 6d6be09a2fe5..dcad7ee0d746 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -161,7 +161,7 @@ extern void devm_rtc_device_unregister(struct device *dev,
 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_mmss(struct rtc_device *rtc, unsigned long secs);
-extern int rtc_set_ntp_time(struct timespec now);
+extern int rtc_set_ntp_time(struct timespec64 now);
 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);
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 9b63d13ba82b..3eaae4754275 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -33,6 +33,7 @@ extern time64_t ktime_get_real_seconds(void);
 
 extern int __getnstimeofday64(struct timespec64 *tv);
 extern void getnstimeofday64(struct timespec64 *tv);
+extern void getboottime64(struct timespec64 *ts);
 
 #if BITS_PER_LONG == 64
 /**
@@ -72,6 +73,11 @@ static inline struct timespec get_monotonic_coarse(void)
 {
         return get_monotonic_coarse64();
 }
+
+static inline void getboottime(struct timespec *ts)
+{
+        return getboottime64(ts);
+}
 #else
 /**
  * Deprecated. Use do_settimeofday64().
@@ -129,9 +135,15 @@ static inline struct timespec get_monotonic_coarse(void)
 {
         return timespec64_to_timespec(get_monotonic_coarse64());
 }
-#endif
 
-extern void getboottime(struct timespec *ts);
+static inline void getboottime(struct timespec *ts)
+{
+        struct timespec64 ts64;
+
+        getboottime64(&ts64);
+        *ts = timespec64_to_timespec(ts64);
+}
+#endif
 
 #define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts)
 #define ktime_get_real_ts64(ts) getnstimeofday64(ts)
@@ -217,6 +229,11 @@ static inline void get_monotonic_boottime(struct timespec *ts)
         *ts = ktime_to_timespec(ktime_get_boottime());
 }
 
+static inline void get_monotonic_boottime64(struct timespec64 *ts)
+{
+        *ts = ktime_to_timespec64(ktime_get_boottime());
+}
+
 static inline void timekeeping_clocktai(struct timespec *ts)
 {
         *ts = ktime_to_timespec(ktime_get_clocktai());
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index d8c724cda37b..3f5e183c3d97 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -266,7 +266,7 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
 /*
  * Divide a ktime value by a nanosecond value
  */
-u64 ktime_divns(const ktime_t kt, s64 div)
+u64 __ktime_divns(const ktime_t kt, s64 div)
 {
         u64 dclc;
         int sft = 0;
@@ -282,7 +282,7 @@ u64 ktime_divns(const ktime_t kt, s64 div)
 
         return dclc;
 }
-EXPORT_SYMBOL_GPL(ktime_divns);
+EXPORT_SYMBOL_GPL(__ktime_divns);
 #endif /* BITS_PER_LONG >= 64 */
 
 /*
@@ -440,6 +440,37 @@ static inline void debug_deactivate(struct hrtimer *timer)
         trace_hrtimer_cancel(timer);
 }
 
+#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
+static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
+{
+        struct hrtimer_clock_base *base = cpu_base->clock_base;
+        ktime_t expires, expires_next = { .tv64 = KTIME_MAX };
+        int i;
+
+        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
+                struct timerqueue_node *next;
+                struct hrtimer *timer;
+
+                next = timerqueue_getnext(&base->active);
+                if (!next)
+                        continue;
+
+                timer = container_of(next, struct hrtimer, node);
+                expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
+                if (expires.tv64 < expires_next.tv64)
+                        expires_next = expires;
+        }
+        /*
+         * clock_was_set() might have changed base->offset of any of
+         * the clock bases so the result might be negative. Fix it up
+         * to prevent a false positive in clockevents_program_event().
+         */
+        if (expires_next.tv64 < 0)
+                expires_next.tv64 = 0;
+        return expires_next;
+}
+#endif
+
 /* High resolution timer related functions */
 #ifdef CONFIG_HIGH_RES_TIMERS
 
@@ -488,32 +519,7 @@ static inline int hrtimer_hres_active(void)
 static void
 hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 {
-        int i;
-        struct hrtimer_clock_base *base = cpu_base->clock_base;
-        ktime_t expires, expires_next;
-
-        expires_next.tv64 = KTIME_MAX;
-
-        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
-                struct hrtimer *timer;
-                struct timerqueue_node *next;
-
-                next = timerqueue_getnext(&base->active);
-                if (!next)
-                        continue;
-                timer = container_of(next, struct hrtimer, node);
-
-                expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
-                /*
-                 * clock_was_set() has changed base->offset so the
-                 * result might be negative. Fix it up to prevent a
-                 * false positive in clockevents_program_event()
-                 */
-                if (expires.tv64 < 0)
-                        expires.tv64 = 0;
-                if (expires.tv64 < expires_next.tv64)
-                        expires_next = expires;
-        }
+        ktime_t expires_next = __hrtimer_get_next_event(cpu_base);
 
         if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
                 return;
@@ -587,6 +593,15 @@ static int hrtimer_reprogram(struct hrtimer *timer,
                 return 0;
 
         /*
+         * When the target cpu of the timer is currently executing
+         * hrtimer_interrupt(), then we do not touch the clock event
+         * device. hrtimer_interrupt() will reevaluate all clock bases
+         * before reprogramming the device.
+         */
+        if (cpu_base->in_hrtirq)
+                return 0;
+
+        /*
          * If a hang was detected in the last timer interrupt then we
          * do not schedule a timer which is earlier than the expiry
          * which we enforced in the hang detection. We want the system
@@ -1104,29 +1119,14 @@ EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
 ktime_t hrtimer_get_next_event(void)
 {
         struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-        struct hrtimer_clock_base *base = cpu_base->clock_base;
-        ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
+        ktime_t mindelta = { .tv64 = KTIME_MAX };
         unsigned long flags;
-        int i;
 
         raw_spin_lock_irqsave(&cpu_base->lock, flags);
 
-        if (!hrtimer_hres_active()) {
-                for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
-                        struct hrtimer *timer;
-                        struct timerqueue_node *next;
-
-                        next = timerqueue_getnext(&base->active);
-                        if (!next)
-                                continue;
-
-                        timer = container_of(next, struct hrtimer, node);
-                        delta.tv64 = hrtimer_get_expires_tv64(timer);
-                        delta = ktime_sub(delta, base->get_time());
-                        if (delta.tv64 < mindelta.tv64)
-                                mindelta.tv64 = delta.tv64;
-                }
-        }
+        if (!hrtimer_hres_active())
+                mindelta = ktime_sub(__hrtimer_get_next_event(cpu_base),
+                                     ktime_get());
 
         raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 
@@ -1253,7 +1253,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
         raw_spin_lock(&cpu_base->lock);
         entry_time = now = hrtimer_update_base(cpu_base);
 retry:
-        expires_next.tv64 = KTIME_MAX;
+        cpu_base->in_hrtirq = 1;
         /*
          * We set expires_next to KTIME_MAX here with cpu_base->lock
          * held to prevent that a timer is enqueued in our queue via
@@ -1291,28 +1291,20 @@ retry:
                          * are right-of a not yet expired timer, because that
                          * timer will have to trigger a wakeup anyway.
                          */
-
-                        if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
-                                ktime_t expires;
-
-                                expires = ktime_sub(hrtimer_get_expires(timer),
-                                                    base->offset);
-                                if (expires.tv64 < 0)
-                                        expires.tv64 = KTIME_MAX;
-                                if (expires.tv64 < expires_next.tv64)
-                                        expires_next = expires;
+                        if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer))
                                 break;
-                        }
 
                         __run_hrtimer(timer, &basenow);
                 }
         }
-
+        /* Reevaluate the clock bases for the next expiry */
+        expires_next = __hrtimer_get_next_event(cpu_base);
         /*
          * Store the new expiry value so the migration code can verify
          * against it.
          */
         cpu_base->expires_next = expires_next;
+        cpu_base->in_hrtirq = 0;
         raw_spin_unlock(&cpu_base->lock);
 
         /* Reprogramming necessary ? */
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 28bf91c60a0b..4b585e0fdd22 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -488,13 +488,13 @@ static void sync_cmos_clock(struct work_struct *work)
 
         getnstimeofday64(&now);
         if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) {
-                struct timespec adjust = timespec64_to_timespec(now);
+                struct timespec64 adjust = now;
 
                 fail = -ENODEV;
                 if (persistent_clock_is_local)
                         adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
-                fail = update_persistent_clock(adjust);
+                fail = update_persistent_clock(timespec64_to_timespec(adjust));
 #endif
 #ifdef CONFIG_RTC_SYSTOHC
                 if (fail == -ENODEV)
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 6a931852082f..b124af259800 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1659,24 +1659,24 @@ out:
 }
 
 /**
- * getboottime - Return the real time of system boot.
- * @ts:         pointer to the timespec to be set
+ * getboottime64 - Return the real time of system boot.
+ * @ts:         pointer to the timespec64 to be set
  *
- * Returns the wall-time of boot in a timespec.
+ * Returns the wall-time of boot in a timespec64.
  *
  * This is based on the wall_to_monotonic offset and the total suspend
  * time. Calls to settimeofday will affect the value returned (which
  * basically means that however wrong your real time clock is at boot time,
  * you get the right time here).
  */
-void getboottime(struct timespec *ts)
+void getboottime64(struct timespec64 *ts)
 {
         struct timekeeper *tk = &tk_core.timekeeper;
         ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot);
 
-        *ts = ktime_to_timespec(t);
+        *ts = ktime_to_timespec64(t);
 }
-EXPORT_SYMBOL_GPL(getboottime);
+EXPORT_SYMBOL_GPL(getboottime64);
 
 unsigned long get_seconds(void)
 {