6 files changed, 315 insertions, 280 deletions

diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 8a46f5d64504..8a538c55fc7b 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -96,6 +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,
 };
@@ -117,6 +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
 
 /**
@@ -783,6 +789,8 @@ static int __init alarmtimer_init(void)
                 .nsleep         = alarm_timer_nsleep,
         };
 
+        alarmtimer_rtc_timer_init();
+
         posix_timers_register_clock(CLOCK_REALTIME_ALARM, &alarm_clock);
         posix_timers_register_clock(CLOCK_BOOTTIME_ALARM, &alarm_clock);
 
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/ntp.c b/kernel/time/ntp.c
index f6117a4c7cb8..f03fd83b170b 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -22,17 +22,18 @@
  * NTP timekeeping variables:
  */
 
+DEFINE_SPINLOCK(ntp_lock);
+
+
 /* USER_HZ period (usecs): */
 unsigned long                   tick_usec = TICK_USEC;
 
 /* ACTHZ period (nsecs): */
 unsigned long                   tick_nsec;
 
-u64                             tick_length;
+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)
@@ -49,7 +50,7 @@ static struct hrtimer		leap_timer;
 static int                      time_state = TIME_OK;
 
 /* clock status bits:                                                   */
-int                             time_status = STA_UNSYNC;
+static int                      time_status = STA_UNSYNC;
 
 /* TAI offset (secs):                                                   */
 static long                     time_tai;
@@ -133,7 +134,7 @@ static inline void pps_reset_freq_interval(void)
 /**
  * pps_clear - Clears the PPS state variables
  *
- * Must be called while holding a write on the xtime_lock
+ * Must be called while holding a write on the ntp_lock
  */
 static inline void pps_clear(void)
 {
@@ -149,7 +150,7 @@ static inline void pps_clear(void)
  * the last PPS signal. When it reaches 0, indicate that PPS signal is
  * missing.
  *
- * Must be called while holding a write on the xtime_lock
+ * Must be called while holding a write on the ntp_lock
  */
 static inline void pps_dec_valid(void)
 {
@@ -233,6 +234,17 @@ static inline void pps_fill_timex(struct timex *txc)
 
 #endif /* CONFIG_NTP_PPS */
 
+
+/**
+ * ntp_synced - Returns 1 if the NTP status is not UNSYNC
+ *
+ */
+static inline int ntp_synced(void)
+{
+        return !(time_status & STA_UNSYNC);
+}
+
+
 /*
  * NTP methods:
  */
@@ -275,7 +287,7 @@ static inline s64 ntp_update_offset_fll(s64 offset64, long secs)
 
         time_status |= STA_MODE;
 
-        return div_s64(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs);
+        return div64_long(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs);
 }
 
 static void ntp_update_offset(long offset)
@@ -330,11 +342,13 @@ static void ntp_update_offset(long offset)
 
 /**
  * ntp_clear - Clears the NTP state variables
- *
- * Must be called while holding a write on the xtime_lock
  */
 void ntp_clear(void)
 {
+        unsigned long flags;
+
+        spin_lock_irqsave(&ntp_lock, flags);
+
         time_adjust     = 0;            /* stop active adjtime() */
         time_status     |= STA_UNSYNC;
         time_maxerror   = NTP_PHASE_LIMIT;
@@ -347,63 +361,81 @@ void ntp_clear(void)
 
         /* Clear PPS state variables */
         pps_clear();
+        spin_unlock_irqrestore(&ntp_lock, flags);
+
+}
+
+
+u64 ntp_tick_length(void)
+{
+        unsigned long flags;
+        s64 ret;
+
+        spin_lock_irqsave(&ntp_lock, flags);
+        ret = tick_length;
+        spin_unlock_irqrestore(&ntp_lock, flags);
+        return ret;
 }
 
+
 /*
- * 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;
+        s64 delta;
+        int leap = 0;
+        unsigned long flags;
 
-        write_seqlock(&xtime_lock);
+        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:
-                timekeeping_leap_insert(-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:
-                timekeeping_leap_insert(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;
         }
 
-        write_sequnlock(&xtime_lock);
-
-        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;
 
         /* Bump the maxerror field */
         time_maxerror += MAXFREQ / NSEC_PER_USEC;
@@ -423,30 +455,34 @@ void second_overflow(void)
         pps_dec_valid();
 
         if (!time_adjust)
-                return;
+                goto out;
 
         if (time_adjust > MAX_TICKADJ) {
                 time_adjust -= MAX_TICKADJ;
                 tick_length += MAX_TICKADJ_SCALED;
-                return;
+                goto out;
         }
 
         if (time_adjust < -MAX_TICKADJ) {
                 time_adjust += MAX_TICKADJ;
                 tick_length -= MAX_TICKADJ_SCALED;
-                return;
+                goto out;
         }
 
         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
 
-/* 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);
@@ -493,35 +529,13 @@ 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
 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:
@@ -546,22 +560,6 @@ 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
@@ -643,9 +641,6 @@ 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) {
@@ -663,7 +658,7 @@ int do_adjtimex(struct timex *txc)
 
         getnstimeofday(&ts);
 
-        write_seqlock_irq(&xtime_lock);
+        spin_lock_irq(&ntp_lock);
 
         if (txc->modes & ADJ_ADJTIME) {
                 long save_adjust = time_adjust;
@@ -705,7 +700,7 @@ int do_adjtimex(struct timex *txc)
         /* fill PPS status fields */
         pps_fill_timex(txc);
 
-        write_sequnlock_irq(&xtime_lock);
+        spin_unlock_irq(&ntp_lock);
 
         txc->time.tv_sec = ts.tv_sec;
         txc->time.tv_usec = ts.tv_nsec;
@@ -903,7 +898,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
 
         pts_norm = pps_normalize_ts(*phase_ts);
 
-        write_seqlock_irqsave(&xtime_lock, flags);
+        spin_lock_irqsave(&ntp_lock, flags);
 
         /* clear the error bits, they will be set again if needed */
         time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR);
@@ -916,7 +911,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
          * just start the frequency interval */
         if (unlikely(pps_fbase.tv_sec == 0)) {
                 pps_fbase = *raw_ts;
-                write_sequnlock_irqrestore(&xtime_lock, flags);
+                spin_unlock_irqrestore(&ntp_lock, flags);
                 return;
         }
 
@@ -931,7 +926,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
                 time_status |= STA_PPSJITTER;
                 /* restart the frequency calibration interval */
                 pps_fbase = *raw_ts;
-                write_sequnlock_irqrestore(&xtime_lock, flags);
+                spin_unlock_irqrestore(&ntp_lock, flags);
                 pr_err("hardpps: PPSJITTER: bad pulse\n");
                 return;
         }
@@ -948,7 +943,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
 
         hardpps_update_phase(pts_norm.nsec);
 
-        write_sequnlock_irqrestore(&xtime_lock, flags);
+        spin_unlock_irqrestore(&ntp_lock, flags);
 }
 EXPORT_SYMBOL(hardpps);
 
@@ -967,6 +962,4 @@ __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/tick-broadcast.c b/kernel/time/tick-broadcast.c
index fd4a7b1625a2..e883f57a3cd3 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -575,11 +575,15 @@ void tick_broadcast_switch_to_oneshot(void)
         unsigned long flags;
 
         raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+        if (cpumask_empty(tick_get_broadcast_mask()))
+                goto end;
 
         tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT;
         bc = tick_broadcast_device.evtdev;
         if (bc)
                 tick_broadcast_setup_oneshot(bc);
+
+end:
         raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 7656642e4b8e..3526038f2836 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -182,11 +182,7 @@ static void tick_nohz_stop_idle(int cpu, ktime_t now)
 
 static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
 {
-        ktime_t now;
-
-        now = ktime_get();
-
-        update_ts_time_stats(cpu, ts, now, NULL);
+        ktime_t now = ktime_get();
 
         ts->idle_entrytime = now;
         ts->idle_active = 1;
@@ -562,20 +558,21 @@ void tick_nohz_idle_exit(void)
 
         local_irq_disable();
 
-        if (ts->idle_active || (ts->inidle && ts->tick_stopped))
+        WARN_ON_ONCE(!ts->inidle);
+
+        ts->inidle = 0;
+
+        if (ts->idle_active || ts->tick_stopped)
                 now = ktime_get();
 
         if (ts->idle_active)
                 tick_nohz_stop_idle(cpu, now);
 
-        if (!ts->inidle || !ts->tick_stopped) {
-                ts->inidle = 0;
+        if (!ts->tick_stopped) {
                 local_irq_enable();
                 return;
         }
 
-        ts->inidle = 0;
-
         /* Update jiffies first */
         select_nohz_load_balancer(0);
         tick_do_update_jiffies64(now);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 0c6358186401..d66b21308f7c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -25,6 +25,8 @@
 struct timekeeper {
         /* Current clocksource used for timekeeping. */
         struct clocksource *clock;
+        /* NTP adjusted clock multiplier */
+        u32     mult;
         /* The shift value of the current clocksource. */
         int     shift;
 
@@ -45,12 +47,47 @@ struct timekeeper {
         /* Shift conversion between clock shifted nano seconds and
          * ntp shifted nano seconds. */
         int     ntp_error_shift;
-        /* NTP adjusted clock multiplier */
-        u32     mult;
+
+        /* The current time */
+        struct timespec xtime;
+        /*
+         * 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.
+         *
+         * wall_to_monotonic is moved after resume from suspend for the
+         * monotonic time not to jump. We need to add total_sleep_time to
+         * wall_to_monotonic to get the real boot based time offset.
+         *
+         * - wall_to_monotonic is no longer the boot time, getboottime must be
+         * used instead.
+         */
+        struct timespec wall_to_monotonic;
+        /* time spent in suspend */
+        struct timespec total_sleep_time;
+        /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */
+        struct timespec raw_time;
+
+        /* Seqlock for all timekeeper values */
+        seqlock_t lock;
 };
 
 static struct timekeeper timekeeper;
 
+/*
+ * This read-write spinlock protects us from races in SMP while
+ * playing with xtime.
+ */
+__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
+
+
+/* flag for if timekeeping is suspended */
+int __read_mostly timekeeping_suspended;
+
+
+
 /**
  * timekeeper_setup_internals - Set up internals to use clocksource clock.
  *
@@ -135,49 +172,18 @@ static inline s64 timekeeping_get_ns_raw(void)
         return clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
 }
 
-/*
- * This read-write spinlock protects us from races in SMP while
- * playing with xtime.
- */
-__cacheline_aligned_in_smp DEFINE_SEQLOCK(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.
- *
- * wall_to_monotonic is moved after resume from suspend for the monotonic
- * time not to jump. We need to add total_sleep_time to wall_to_monotonic
- * to get the real boot based time offset.
- *
- * - wall_to_monotonic is no longer the boot time, getboottime must be
- * used instead.
- */
-static struct timespec xtime __attribute__ ((aligned (16)));
-static struct timespec wall_to_monotonic __attribute__ ((aligned (16)));
-static struct timespec total_sleep_time;
-
-/*
- * The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock.
- */
-static struct timespec raw_time;
-
-/* flag for if timekeeping is suspended */
-int __read_mostly timekeeping_suspended;
-
-/* must hold xtime_lock */
-void timekeeping_leap_insert(int leapsecond)
+/* must hold write on timekeeper.lock */
+static void timekeeping_update(bool clearntp)
 {
-        xtime.tv_sec += leapsecond;
-        wall_to_monotonic.tv_sec -= leapsecond;
-        update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
-                        timekeeper.mult);
+        if (clearntp) {
+                timekeeper.ntp_error = 0;
+                ntp_clear();
+        }
+        update_vsyscall(&timekeeper.xtime, &timekeeper.wall_to_monotonic,
+                         timekeeper.clock, timekeeper.mult);
 }
 
+
 /**
  * timekeeping_forward_now - update clock to the current time
  *
@@ -202,10 +208,10 @@ static void timekeeping_forward_now(void)
         /* If arch requires, add in gettimeoffset() */
         nsec += arch_gettimeoffset();
 
-        timespec_add_ns(&xtime, nsec);
+        timespec_add_ns(&timekeeper.xtime, nsec);
 
         nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
-        timespec_add_ns(&raw_time, nsec);
+        timespec_add_ns(&timekeeper.raw_time, nsec);
 }
 
 /**
@@ -222,15 +228,15 @@ void getnstimeofday(struct timespec *ts)
         WARN_ON(timekeeping_suspended);
 
         do {
-                seq = read_seqbegin(&xtime_lock);
+                seq = read_seqbegin(&timekeeper.lock);
 
-                *ts = xtime;
+                *ts = timekeeper.xtime;
                 nsecs = timekeeping_get_ns();
 
                 /* If arch requires, add in gettimeoffset() */
                 nsecs += arch_gettimeoffset();
 
-        } while (read_seqretry(&xtime_lock, seq));
+        } while (read_seqretry(&timekeeper.lock, seq));
 
         timespec_add_ns(ts, nsecs);
 }
@@ -245,14 +251,16 @@ ktime_t ktime_get(void)
         WARN_ON(timekeeping_suspended);
 
         do {
-                seq = read_seqbegin(&xtime_lock);
-                secs = xtime.tv_sec + wall_to_monotonic.tv_sec;
-                nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec;
+                seq = read_seqbegin(&timekeeper.lock);
+                secs = timekeeper.xtime.tv_sec +
+                                timekeeper.wall_to_monotonic.tv_sec;
+                nsecs = timekeeper.xtime.tv_nsec +
+                                timekeeper.wall_to_monotonic.tv_nsec;
                 nsecs += timekeeping_get_ns();
                 /* If arch requires, add in gettimeoffset() */
                 nsecs += arch_gettimeoffset();
 
-        } while (read_seqretry(&xtime_lock, seq));
+        } while (read_seqretry(&timekeeper.lock, seq));
         /*
          * Use ktime_set/ktime_add_ns to create a proper ktime on
          * 32-bit architectures without CONFIG_KTIME_SCALAR.
@@ -278,14 +286,14 @@ void ktime_get_ts(struct timespec *ts)
         WARN_ON(timekeeping_suspended);
 
         do {
-                seq = read_seqbegin(&xtime_lock);
-                *ts = xtime;
-                tomono = wall_to_monotonic;
+                seq = read_seqbegin(&timekeeper.lock);
+                *ts = timekeeper.xtime;
+                tomono = timekeeper.wall_to_monotonic;
                 nsecs = timekeeping_get_ns();
                 /* If arch requires, add in gettimeoffset() */
                 nsecs += arch_gettimeoffset();
 
-        } while (read_seqretry(&xtime_lock, seq));
+        } while (read_seqretry(&timekeeper.lock, seq));
 
         set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec,
                                 ts->tv_nsec + tomono.tv_nsec + nsecs);
@@ -313,10 +321,10 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
         do {
                 u32 arch_offset;
 
-                seq = read_seqbegin(&xtime_lock);
+                seq = read_seqbegin(&timekeeper.lock);
 
-                *ts_raw = raw_time;
-                *ts_real = xtime;
+                *ts_raw = timekeeper.raw_time;
+                *ts_real = timekeeper.xtime;
 
                 nsecs_raw = timekeeping_get_ns_raw();
                 nsecs_real = timekeeping_get_ns();
@@ -326,7 +334,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
                 nsecs_raw += arch_offset;
                 nsecs_real += arch_offset;
 
-        } while (read_seqretry(&xtime_lock, seq));
+        } while (read_seqretry(&timekeeper.lock, seq));
 
         timespec_add_ns(ts_raw, nsecs_raw);
         timespec_add_ns(ts_real, nsecs_real);
@@ -365,23 +373,19 @@ int do_settimeofday(const struct timespec *tv)
         if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
                 return -EINVAL;
 
-        write_seqlock_irqsave(&xtime_lock, flags);
+        write_seqlock_irqsave(&timekeeper.lock, flags);
 
         timekeeping_forward_now();
 
-        ts_delta.tv_sec = tv->tv_sec - xtime.tv_sec;
-        ts_delta.tv_nsec = tv->tv_nsec - xtime.tv_nsec;
-        wall_to_monotonic = timespec_sub(wall_to_monotonic, ts_delta);
+        ts_delta.tv_sec = tv->tv_sec - timekeeper.xtime.tv_sec;
+        ts_delta.tv_nsec = tv->tv_nsec - timekeeper.xtime.tv_nsec;
+        timekeeper.wall_to_monotonic =
+                        timespec_sub(timekeeper.wall_to_monotonic, ts_delta);
 
-        xtime = *tv;
-
-        timekeeper.ntp_error = 0;
-        ntp_clear();
+        timekeeper.xtime = *tv;
+        timekeeping_update(true);
 
-        update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
-                                timekeeper.mult);
-
-        write_sequnlock_irqrestore(&xtime_lock, flags);
+        write_sequnlock_irqrestore(&timekeeper.lock, flags);
 
         /* signal hrtimers about time change */
         clock_was_set();
@@ -405,20 +409,17 @@ int timekeeping_inject_offset(struct timespec *ts)
         if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
                 return -EINVAL;
 
-        write_seqlock_irqsave(&xtime_lock, flags);
+        write_seqlock_irqsave(&timekeeper.lock, flags);
 
         timekeeping_forward_now();
 
-        xtime = timespec_add(xtime, *ts);
-        wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts);
-
-        timekeeper.ntp_error = 0;
-        ntp_clear();
+        timekeeper.xtime = timespec_add(timekeeper.xtime, *ts);
+        timekeeper.wall_to_monotonic =
+                                timespec_sub(timekeeper.wall_to_monotonic, *ts);
 
-        update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
-                                timekeeper.mult);
+        timekeeping_update(true);
 
-        write_sequnlock_irqrestore(&xtime_lock, flags);
+        write_sequnlock_irqrestore(&timekeeper.lock, flags);
 
         /* signal hrtimers about time change */
         clock_was_set();
@@ -435,9 +436,12 @@ 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;
@@ -445,6 +449,10 @@ static int change_clocksource(void *data)
                 if (old->disable)
                         old->disable(old);
         }
+        timekeeping_update(true);
+
+        write_sequnlock_irqrestore(&timekeeper.lock, flags);
+
         return 0;
 }
 
@@ -490,11 +498,11 @@ void getrawmonotonic(struct timespec *ts)
         s64 nsecs;
 
         do {
-                seq = read_seqbegin(&xtime_lock);
+                seq = read_seqbegin(&timekeeper.lock);
                 nsecs = timekeeping_get_ns_raw();
-                *ts = raw_time;
+                *ts = timekeeper.raw_time;
 
-        } while (read_seqretry(&xtime_lock, seq));
+        } while (read_seqretry(&timekeeper.lock, seq));
 
         timespec_add_ns(ts, nsecs);
 }
@@ -510,24 +518,30 @@ int timekeeping_valid_for_hres(void)
         int ret;
 
         do {
-                seq = read_seqbegin(&xtime_lock);
+                seq = read_seqbegin(&timekeeper.lock);
 
                 ret = timekeeper.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
 
-        } while (read_seqretry(&xtime_lock, seq));
+        } while (read_seqretry(&timekeeper.lock, seq));
 
         return ret;
 }
 
 /**
  * timekeeping_max_deferment - Returns max time the clocksource can be deferred
- *
- * Caller must observe xtime_lock via read_seqbegin/read_seqretry to
- * ensure that the clocksource does not change!
  */
 u64 timekeeping_max_deferment(void)
 {
-        return timekeeper.clock->max_idle_ns;
+        unsigned long seq;
+        u64 ret;
+        do {
+                seq = read_seqbegin(&timekeeper.lock);
+
+                ret = timekeeper.clock->max_idle_ns;
+
+        } while (read_seqretry(&timekeeper.lock, seq));
+
+        return ret;
 }
 
 /**
@@ -572,28 +586,29 @@ void __init timekeeping_init(void)
         read_persistent_clock(&now);
         read_boot_clock(&boot);
 
-        write_seqlock_irqsave(&xtime_lock, flags);
+        seqlock_init(&timekeeper.lock);
 
         ntp_init();
 
+        write_seqlock_irqsave(&timekeeper.lock, flags);
         clock = clocksource_default_clock();
         if (clock->enable)
                 clock->enable(clock);
         timekeeper_setup_internals(clock);
 
-        xtime.tv_sec = now.tv_sec;
-        xtime.tv_nsec = now.tv_nsec;
-        raw_time.tv_sec = 0;
-        raw_time.tv_nsec = 0;
+        timekeeper.xtime.tv_sec = now.tv_sec;
+        timekeeper.xtime.tv_nsec = now.tv_nsec;
+        timekeeper.raw_time.tv_sec = 0;
+        timekeeper.raw_time.tv_nsec = 0;
         if (boot.tv_sec == 0 && boot.tv_nsec == 0) {
-                boot.tv_sec = xtime.tv_sec;
-                boot.tv_nsec = xtime.tv_nsec;
+                boot.tv_sec = timekeeper.xtime.tv_sec;
+                boot.tv_nsec = timekeeper.xtime.tv_nsec;
         }
-        set_normalized_timespec(&wall_to_monotonic,
+        set_normalized_timespec(&timekeeper.wall_to_monotonic,
                                 -boot.tv_sec, -boot.tv_nsec);
-        total_sleep_time.tv_sec = 0;
-        total_sleep_time.tv_nsec = 0;
-        write_sequnlock_irqrestore(&xtime_lock, flags);
+        timekeeper.total_sleep_time.tv_sec = 0;
+        timekeeper.total_sleep_time.tv_nsec = 0;
+        write_sequnlock_irqrestore(&timekeeper.lock, flags);
 }
 
 /* time in seconds when suspend began */
@@ -614,9 +629,11 @@ static void __timekeeping_inject_sleeptime(struct timespec *delta)
                 return;
         }
 
-        xtime = timespec_add(xtime, *delta);
-        wall_to_monotonic = timespec_sub(wall_to_monotonic, *delta);
-        total_sleep_time = timespec_add(total_sleep_time, *delta);
+        timekeeper.xtime = timespec_add(timekeeper.xtime, *delta);
+        timekeeper.wall_to_monotonic =
+                        timespec_sub(timekeeper.wall_to_monotonic, *delta);
+        timekeeper.total_sleep_time = timespec_add(
+                                        timekeeper.total_sleep_time, *delta);
 }
 
 
@@ -640,17 +657,15 @@ void timekeeping_inject_sleeptime(struct timespec *delta)
         if (!(ts.tv_sec == 0 && ts.tv_nsec == 0))
                 return;
 
-        write_seqlock_irqsave(&xtime_lock, flags);
+        write_seqlock_irqsave(&timekeeper.lock, flags);
+
         timekeeping_forward_now();
 
         __timekeeping_inject_sleeptime(delta);
 
-        timekeeper.ntp_error = 0;
-        ntp_clear();
-        update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
-                                timekeeper.mult);
+        timekeeping_update(true);
 
-        write_sequnlock_irqrestore(&xtime_lock, flags);
+        write_sequnlock_irqrestore(&timekeeper.lock, flags);
 
         /* signal hrtimers about time change */
         clock_was_set();
@@ -673,7 +688,7 @@ static void timekeeping_resume(void)
 
         clocksource_resume();
 
-        write_seqlock_irqsave(&xtime_lock, flags);
+        write_seqlock_irqsave(&timekeeper.lock, flags);
 
         if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) {
                 ts = timespec_sub(ts, timekeeping_suspend_time);
@@ -683,7 +698,7 @@ static void timekeeping_resume(void)
         timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
         timekeeper.ntp_error = 0;
         timekeeping_suspended = 0;
-        write_sequnlock_irqrestore(&xtime_lock, flags);
+        write_sequnlock_irqrestore(&timekeeper.lock, flags);
 
         touch_softlockup_watchdog();
 
@@ -701,7 +716,7 @@ static int timekeeping_suspend(void)
 
         read_persistent_clock(&timekeeping_suspend_time);
 
-        write_seqlock_irqsave(&xtime_lock, flags);
+        write_seqlock_irqsave(&timekeeper.lock, flags);
         timekeeping_forward_now();
         timekeeping_suspended = 1;
 
@@ -711,7 +726,7 @@ static int timekeeping_suspend(void)
          * try to compensate so the difference in system time
          * and persistent_clock time stays close to constant.
          */
-        delta = timespec_sub(xtime, timekeeping_suspend_time);
+        delta = timespec_sub(timekeeper.xtime, timekeeping_suspend_time);
         delta_delta = timespec_sub(delta, old_delta);
         if (abs(delta_delta.tv_sec)  >= 2) {
                 /*
@@ -724,7 +739,7 @@ static int timekeeping_suspend(void)
                 timekeeping_suspend_time =
                         timespec_add(timekeeping_suspend_time, delta_delta);
         }
-        write_sequnlock_irqrestore(&xtime_lock, flags);
+        write_sequnlock_irqrestore(&timekeeper.lock, flags);
 
         clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
         clocksource_suspend();
@@ -775,7 +790,7 @@ static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval,
          * Now calculate the error in (1 << look_ahead) ticks, but first
          * remove the single look ahead already included in the error.
          */
-        tick_error = tick_length >> (timekeeper.ntp_error_shift + 1);
+        tick_error = ntp_tick_length() >> (timekeeper.ntp_error_shift + 1);
         tick_error -= timekeeper.xtime_interval >> 1;
         error = ((error - tick_error) >> look_ahead) + tick_error;
 
@@ -807,7 +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.
@@ -815,7 +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.
          */
@@ -823,7 +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.
                  */
@@ -854,13 +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.
          *
@@ -932,7 +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<<shift)
                 return offset;
 
@@ -942,23 +959,25 @@ 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;
-                xtime.tv_sec++;
-                second_overflow();
+                timekeeper.xtime.tv_sec++;
+                leap = second_overflow(timekeeper.xtime.tv_sec);
+                timekeeper.xtime.tv_sec += leap;
         }
 
         /* Accumulate raw time */
         raw_nsecs = timekeeper.raw_interval << shift;
-        raw_nsecs += raw_time.tv_nsec;
+        raw_nsecs += timekeeper.raw_time.tv_nsec;
         if (raw_nsecs >= NSEC_PER_SEC) {
                 u64 raw_secs = raw_nsecs;
                 raw_nsecs = do_div(raw_secs, NSEC_PER_SEC);
-                raw_time.tv_sec += raw_secs;
+                timekeeper.raw_time.tv_sec += raw_secs;
         }
-        raw_time.tv_nsec = raw_nsecs;
+        timekeeper.raw_time.tv_nsec = raw_nsecs;
 
         /* Accumulate error between NTP and clock interval */
-        timekeeper.ntp_error += tick_length << shift;
+        timekeeper.ntp_error += ntp_tick_length() << shift;
         timekeeper.ntp_error -=
             (timekeeper.xtime_interval + timekeeper.xtime_remainder) <<
                                 (timekeeper.ntp_error_shift + shift);
@@ -970,17 +989,19 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int 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.
  */
 static void update_wall_time(void)
 {
         struct clocksource *clock;
         cycle_t offset;
         int shift = 0, maxshift;
+        unsigned long flags;
+
+        write_seqlock_irqsave(&timekeeper.lock, flags);
 
         /* Make sure we're fully resumed: */
         if (unlikely(timekeeping_suspended))
-                return;
+                goto out;
 
         clock = timekeeper.clock;
 
@@ -989,20 +1010,21 @@ static void update_wall_time(void)
 #else
         offset = (clock->read(clock) - clock->cycle_last) & clock->mask;
 #endif
-        timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;
+        timekeeper.xtime_nsec = (s64)timekeeper.xtime.tv_nsec <<
+                                                timekeeper.shift;
 
         /*
          * With NO_HZ we may have to accumulate many cycle_intervals
          * (think "ticks") worth of time at once. To do this efficiently,
          * we calculate the largest doubling multiple of cycle_intervals
-         * that is smaller then the offset. We then accumulate that
+         * that is smaller than the offset.  We then accumulate that
          * chunk in one go, and then try to consume the next smaller
          * doubled multiple.
          */
         shift = ilog2(offset) - ilog2(timekeeper.cycle_interval);
         shift = max(0, shift);
-        /* Bound shift to one less then what overflows tick_length */
-        maxshift = (8*sizeof(tick_length) - (ilog2(tick_length)+1)) - 1;
+        /* Bound shift to one less than what overflows tick_length */
+        maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
         shift = min(shift, maxshift);
         while (offset >= timekeeper.cycle_interval) {
                 offset = logarithmic_accumulation(offset, shift);
@@ -1040,24 +1062,30 @@ static void update_wall_time(void)
          * Store full nanoseconds into xtime after rounding it up and
          * add the remainder to the error difference.
          */
-        xtime.tv_nsec = ((s64) timekeeper.xtime_nsec >> timekeeper.shift) + 1;
-        timekeeper.xtime_nsec -= (s64) xtime.tv_nsec << timekeeper.shift;
+        timekeeper.xtime.tv_nsec = ((s64)timekeeper.xtime_nsec >>
+                                                timekeeper.shift) + 1;
+        timekeeper.xtime_nsec -= (s64)timekeeper.xtime.tv_nsec <<
+                                                timekeeper.shift;
         timekeeper.ntp_error += timekeeper.xtime_nsec <<
                                 timekeeper.ntp_error_shift;
 
         /*
          * 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(xtime.tv_nsec >= NSEC_PER_SEC)) {
-                xtime.tv_nsec -= NSEC_PER_SEC;
-                xtime.tv_sec++;
-                second_overflow();
+        if (unlikely(timekeeper.xtime.tv_nsec >= NSEC_PER_SEC)) {
+                int leap;
+                timekeeper.xtime.tv_nsec -= NSEC_PER_SEC;
+                timekeeper.xtime.tv_sec++;
+                leap = second_overflow(timekeeper.xtime.tv_sec);
+                timekeeper.xtime.tv_sec += leap;
         }
 
-        /* check to see if there is a new clocksource to use */
-        update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
-                                timekeeper.mult);
+        timekeeping_update(false);
+
+out:
+        write_sequnlock_irqrestore(&timekeeper.lock, flags);
+
 }
 
 /**
@@ -1074,8 +1102,10 @@ static void update_wall_time(void)
 void getboottime(struct timespec *ts)
 {
         struct timespec boottime = {
-                .tv_sec = wall_to_monotonic.tv_sec + total_sleep_time.tv_sec,
-                .tv_nsec = wall_to_monotonic.tv_nsec + total_sleep_time.tv_nsec
+                .tv_sec = timekeeper.wall_to_monotonic.tv_sec +
+                                timekeeper.total_sleep_time.tv_sec,
+                .tv_nsec = timekeeper.wall_to_monotonic.tv_nsec +
+                                timekeeper.total_sleep_time.tv_nsec
         };
 
         set_normalized_timespec(ts, -boottime.tv_sec, -boottime.tv_nsec);
@@ -1101,13 +1131,13 @@ void get_monotonic_boottime(struct timespec *ts)
         WARN_ON(timekeeping_suspended);
 
         do {
-                seq = read_seqbegin(&xtime_lock);
-                *ts = xtime;
-                tomono = wall_to_monotonic;
-                sleep = total_sleep_time;
+                seq = read_seqbegin(&timekeeper.lock);
+                *ts = timekeeper.xtime;
+                tomono = timekeeper.wall_to_monotonic;
+                sleep = timekeeper.total_sleep_time;
                 nsecs = timekeeping_get_ns();
 
-        } while (read_seqretry(&xtime_lock, seq));
+        } while (read_seqretry(&timekeeper.lock, seq));
 
         set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec,
                         ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs);
@@ -1137,19 +1167,19 @@ EXPORT_SYMBOL_GPL(ktime_get_boottime);
  */
 void monotonic_to_bootbased(struct timespec *ts)
 {
-        *ts = timespec_add(*ts, total_sleep_time);
+        *ts = timespec_add(*ts, timekeeper.total_sleep_time);
 }
 EXPORT_SYMBOL_GPL(monotonic_to_bootbased);
 
 unsigned long get_seconds(void)
 {
-        return xtime.tv_sec;
+        return timekeeper.xtime.tv_sec;
 }
 EXPORT_SYMBOL(get_seconds);
 
 struct timespec __current_kernel_time(void)
 {
-        return xtime;
+        return timekeeper.xtime;
 }
 
 struct timespec current_kernel_time(void)
@@ -1158,10 +1188,10 @@ struct timespec current_kernel_time(void)
         unsigned long seq;
 
         do {
-                seq = read_seqbegin(&xtime_lock);
+                seq = read_seqbegin(&timekeeper.lock);
 
-                now = xtime;
-        } while (read_seqretry(&xtime_lock, seq));
+                now = timekeeper.xtime;
+        } while (read_seqretry(&timekeeper.lock, seq));
 
         return now;
 }
@@ -1173,11 +1203,11 @@ struct timespec get_monotonic_coarse(void)
         unsigned long seq;
 
         do {
-                seq = read_seqbegin(&xtime_lock);
+                seq = read_seqbegin(&timekeeper.lock);
 
-                now = xtime;
-                mono = wall_to_monotonic;
-        } while (read_seqretry(&xtime_lock, seq));
+                now = timekeeper.xtime;
+                mono = timekeeper.wall_to_monotonic;
+        } while (read_seqretry(&timekeeper.lock, seq));
 
         set_normalized_timespec(&now, now.tv_sec + mono.tv_sec,
                                 now.tv_nsec + mono.tv_nsec);
@@ -1209,11 +1239,11 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
         unsigned long seq;
 
         do {
-                seq = read_seqbegin(&xtime_lock);
-                *xtim = xtime;
-                *wtom = wall_to_monotonic;
-                *sleep = total_sleep_time;
-        } while (read_seqretry(&xtime_lock, seq));
+                seq = read_seqbegin(&timekeeper.lock);
+                *xtim = timekeeper.xtime;
+                *wtom = timekeeper.wall_to_monotonic;
+                *sleep = timekeeper.total_sleep_time;
+        } while (read_seqretry(&timekeeper.lock, seq));
 }
 
 /**
@@ -1225,11 +1255,14 @@ ktime_t ktime_get_monotonic_offset(void)
         struct timespec wtom;
 
         do {
-                seq = read_seqbegin(&xtime_lock);
-                wtom = wall_to_monotonic;
-        } while (read_seqretry(&xtime_lock, seq));
+                seq = read_seqbegin(&timekeeper.lock);
+                wtom = timekeeper.wall_to_monotonic;
+        } while (read_seqretry(&timekeeper.lock, seq));
+
         return timespec_to_ktime(wtom);
 }
+EXPORT_SYMBOL_GPL(ktime_get_monotonic_offset);
+
 
 /**
  * xtime_update() - advances the timekeeping infrastructure