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

Pull timer core updates from Thomas Gleixner.

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  ia64: vsyscall: Add missing paranthesis
  alarmtimer: Don't call rtc_timer_init() when CONFIG_RTC_CLASS=n
  x86: vdso: Put declaration before code
  x86-64: Inline vdso clock_gettime helpers
  x86-64: Simplify and optimize vdso clock_gettime monotonic variants
  kernel-time: fix s/then/than/ spelling errors
  time: remove no_sync_cmos_clock
  time: Avoid scary backtraces when warning of > 11% adj
  alarmtimer: Make sure we initialize the rtctimer
  ntp: Fix leap-second hrtimer livelock
  x86, tsc: Skip refined tsc calibration on systems with reliable TSC
  rtc: Provide flag for rtc devices that don't support UIE
  ia64: vsyscall: Use seqcount instead of seqlock
  x86: vdso: Use seqcount instead of seqlock
  x86: vdso: Remove bogus locking in update_vsyscall_tz()
  time: Remove bogus comments
  time: Fix change_clocksource locking
  time: x86: Fix race switching from vsyscall to non-vsyscall clock

5 files changed, 77 insertions, 124 deletions

diff --git a/kernel/time.c b/kernel/time.c
index 73e416db0a1..ba744cf8069 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -163,7 +163,6 @@ int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz)
 		return error;
 
 	if (tz) {
-		/* SMP safe, global irq locking makes it work. */
 		sys_tz = *tz;
 		update_vsyscall_tz();
 		if (firsttime) {
@@ -173,12 +172,7 @@ int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz)
 		}
 	}
 	if (tv)
-	{
-		/* SMP safe, again the code in arch/foo/time.c should
-		 * globally block out interrupts when it runs.
-		 */
 		return do_settimeofday(tv);
-	}
 	return 0;
 }
 
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 8a46f5d6450..8a538c55fc7 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 a45ca167ab2..c9583382141 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 6e039b144da..f03fd83b170 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -34,8 +34,6 @@ unsigned long			tick_nsec;
 static u64			tick_length;
 static u64			tick_length_base;
 
-static struct hrtimer		leap_timer;
-
 #define MAX_TICKADJ		500LL		/* usecs */
 #define MAX_TICKADJ_SCALED \
 	(((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
@@ -381,70 +379,63 @@ u64 ntp_tick_length(void)
 
 
 /*
- * Leap second processing. If in leap-insert state at the end of the
- * day, the system clock is set back one second; if in leap-delete
- * state, the system clock is set ahead one second.
+ * this routine handles the overflow of the microsecond field
+ *
+ * The tricky bits of code to handle the accurate clock support
+ * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
+ * They were originally developed for SUN and DEC kernels.
+ * All the kudos should go to Dave for this stuff.
+ *
+ * Also handles leap second processing, and returns leap offset
  */
-static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
+int second_overflow(unsigned long secs)
 {
-	enum hrtimer_restart res = HRTIMER_NORESTART;
-	unsigned long flags;
+	s64 delta;
 	int leap = 0;
+	unsigned long flags;
 
 	spin_lock_irqsave(&ntp_lock, flags);
+
+	/*
+	 * Leap second processing. If in leap-insert state at the end of the
+	 * day, the system clock is set back one second; if in leap-delete
+	 * state, the system clock is set ahead one second.
+	 */
 	switch (time_state) {
 	case TIME_OK:
+		if (time_status & STA_INS)
+			time_state = TIME_INS;
+		else if (time_status & STA_DEL)
+			time_state = TIME_DEL;
 		break;
 	case TIME_INS:
-		leap = -1;
-		time_state = TIME_OOP;
-		printk(KERN_NOTICE
-			"Clock: inserting leap second 23:59:60 UTC\n");
-		hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC);
-		res = HRTIMER_RESTART;
+		if (secs % 86400 == 0) {
+			leap = -1;
+			time_state = TIME_OOP;
+			printk(KERN_NOTICE
+				"Clock: inserting leap second 23:59:60 UTC\n");
+		}
 		break;
 	case TIME_DEL:
-		leap = 1;
-		time_tai--;
-		time_state = TIME_WAIT;
-		printk(KERN_NOTICE
-			"Clock: deleting leap second 23:59:59 UTC\n");
+		if ((secs + 1) % 86400 == 0) {
+			leap = 1;
+			time_tai--;
+			time_state = TIME_WAIT;
+			printk(KERN_NOTICE
+				"Clock: deleting leap second 23:59:59 UTC\n");
+		}
 		break;
 	case TIME_OOP:
 		time_tai++;
 		time_state = TIME_WAIT;
-		/* fall through */
+		break;
+
 	case TIME_WAIT:
 		if (!(time_status & (STA_INS | STA_DEL)))
 			time_state = TIME_OK;
 		break;
 	}
-	spin_unlock_irqrestore(&ntp_lock, flags);
 
-	/*
-	 * We have to call this outside of the ntp_lock to keep
-	 * the proper locking hierarchy
-	 */
-	if (leap)
-		timekeeping_leap_insert(leap);
-
-	return res;
-}
-
-/*
- * this routine handles the overflow of the microsecond field
- *
- * The tricky bits of code to handle the accurate clock support
- * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
- * They were originally developed for SUN and DEC kernels.
- * All the kudos should go to Dave for this stuff.
- */
-void second_overflow(void)
-{
-	s64 delta;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ntp_lock, flags);
 
 	/* Bump the maxerror field */
 	time_maxerror += MAXFREQ / NSEC_PER_USEC;
@@ -481,15 +472,17 @@ void second_overflow(void)
 	tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ)
 							 << NTP_SCALE_SHIFT;
 	time_adjust = 0;
+
+
+
 out:
 	spin_unlock_irqrestore(&ntp_lock, flags);
+
+	return leap;
 }
 
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
 
-/* 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);
@@ -536,35 +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:
@@ -589,22 +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
@@ -686,9 +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) {
@@ -1010,6 +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/timekeeping.c b/kernel/time/timekeeping.c
index 15be32e19c6..d66b21308f7 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -184,18 +184,6 @@ static void timekeeping_update(bool clearntp)
 }
 
 
-void timekeeping_leap_insert(int leapsecond)
-{
-	unsigned long flags;
-
-	write_seqlock_irqsave(&timekeeper.lock, flags);
-	timekeeper.xtime.tv_sec += leapsecond;
-	timekeeper.wall_to_monotonic.tv_sec -= leapsecond;
-	timekeeping_update(false);
-	write_sequnlock_irqrestore(&timekeeper.lock, flags);
-
-}
-
 /**
  * timekeeping_forward_now - update clock to the current time
  *
@@ -448,9 +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;
@@ -458,6 +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;
 }
 
@@ -827,7 +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.
@@ -835,7 +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.
 	 */
@@ -843,7 +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.
 		 */
@@ -874,13 +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.
 	 *
@@ -952,7 +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;
 
@@ -962,9 +959,11 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
 
 	timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
 	while (timekeeper.xtime_nsec >= nsecps) {
+		int leap;
 		timekeeper.xtime_nsec -= nsecps;
 		timekeeper.xtime.tv_sec++;
-		second_overflow();
+		leap = second_overflow(timekeeper.xtime.tv_sec);
+		timekeeper.xtime.tv_sec += leap;
 	}
 
 	/* Accumulate raw time */
@@ -1018,13 +1017,13 @@ static void update_wall_time(void)
 	 * 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 */
+	/* 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) {
@@ -1072,12 +1071,14 @@ static void update_wall_time(void)
 
 	/*
 	 * Finally, make sure that after the rounding
-	 * xtime.tv_nsec isn't larger then NSEC_PER_SEC
+	 * xtime.tv_nsec isn't larger than NSEC_PER_SEC
 	 */
 	if (unlikely(timekeeper.xtime.tv_nsec >= NSEC_PER_SEC)) {
+		int leap;
 		timekeeper.xtime.tv_nsec -= NSEC_PER_SEC;
 		timekeeper.xtime.tv_sec++;
-		second_overflow();
+		leap = second_overflow(timekeeper.xtime.tv_sec);
+		timekeeper.xtime.tv_sec += leap;
 	}
 
 	timekeeping_update(false);