4 files changed, 167 insertions, 127 deletions

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 2043c08..957869f 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -657,6 +657,14 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
 	return 0;
 }
 
+static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
+{
+	ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
+	ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
+
+	return ktime_get_update_offsets(offs_real, offs_boot);
+}
+
 /*
  * Retrigger next event is called after clock was set
  *
@@ -665,22 +673,12 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
 static void retrigger_next_event(void *arg)
 {
 	struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
-	struct timespec realtime_offset, xtim, wtm, sleep;
 
 	if (!hrtimer_hres_active())
 		return;
 
-	/* Optimized out for !HIGH_RES */
-	get_xtime_and_monotonic_and_sleep_offset(&xtim, &wtm, &sleep);
-	set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec);
-
-	/* Adjust CLOCK_REALTIME offset */
 	raw_spin_lock(&base->lock);
-	base->clock_base[HRTIMER_BASE_REALTIME].offset =
-		timespec_to_ktime(realtime_offset);
-	base->clock_base[HRTIMER_BASE_BOOTTIME].offset =
-		timespec_to_ktime(sleep);
-
+	hrtimer_update_base(base);
 	hrtimer_force_reprogram(base, 0);
 	raw_spin_unlock(&base->lock);
 }
@@ -710,13 +708,25 @@ static int hrtimer_switch_to_hres(void)
 		base->clock_base[i].resolution = KTIME_HIGH_RES;
 
 	tick_setup_sched_timer();
-
 	/* "Retrigger" the interrupt to get things going */
 	retrigger_next_event(NULL);
 	local_irq_restore(flags);
 	return 1;
 }
 
+/*
+ * Called from timekeeping code to reprogramm the hrtimer interrupt
+ * device. If called from the timer interrupt context we defer it to
+ * softirq context.
+ */
+void clock_was_set_delayed(void)
+{
+	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+
+	cpu_base->clock_was_set = 1;
+	__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+}
+
 #else
 
 static inline int hrtimer_hres_active(void) { return 0; }
@@ -1250,11 +1260,10 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	cpu_base->nr_events++;
 	dev->next_event.tv64 = KTIME_MAX;
 
-	entry_time = now = ktime_get();
+	raw_spin_lock(&cpu_base->lock);
+	entry_time = now = hrtimer_update_base(cpu_base);
 retry:
 	expires_next.tv64 = KTIME_MAX;
-
-	raw_spin_lock(&cpu_base->lock);
 	/*
 	 * We set expires_next to KTIME_MAX here with cpu_base->lock
 	 * held to prevent that a timer is enqueued in our queue via
@@ -1330,8 +1339,12 @@ retry:
 	 * We need to prevent that we loop forever in the hrtimer
 	 * interrupt routine. We give it 3 attempts to avoid
 	 * overreacting on some spurious event.
+	 *
+	 * Acquire base lock for updating the offsets and retrieving
+	 * the current time.
 	 */
-	now = ktime_get();
+	raw_spin_lock(&cpu_base->lock);
+	now = hrtimer_update_base(cpu_base);
 	cpu_base->nr_retries++;
 	if (++retries < 3)
 		goto retry;
@@ -1343,6 +1356,7 @@ retry:
 	 */
 	cpu_base->nr_hangs++;
 	cpu_base->hang_detected = 1;
+	raw_spin_unlock(&cpu_base->lock);
 	delta = ktime_sub(now, entry_time);
 	if (delta.tv64 > cpu_base->max_hang_time.tv64)
 		cpu_base->max_hang_time = delta;
@@ -1395,6 +1409,13 @@ void hrtimer_peek_ahead_timers(void)
 
 static void run_hrtimer_softirq(struct softirq_action *h)
 {
+	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+
+	if (cpu_base->clock_was_set) {
+		cpu_base->clock_was_set = 0;
+		clock_was_set();
+	}
+
 	hrtimer_peek_ahead_timers();
 }
 
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 4b85a7a..f1eb182 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -31,8 +31,6 @@ unsigned long			tick_nsec;
 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)
@@ -350,60 +348,60 @@ void ntp_clear(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;
-
-	write_seqlock(&xtime_lock);
+	int leap = 0;
+	s64 delta;
 
+	/*
+	 * 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;
+			time_tai++;
+			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;
@@ -423,23 +421,25 @@ 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:
+	return leap;
 }
 
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
@@ -501,27 +501,6 @@ static void notify_cmos_timer(void)
 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 +525,6 @@ 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 +606,6 @@ 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) {
@@ -967,6 +927,4 @@ __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 9b28d04..84d4f8b 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -161,23 +161,43 @@ static struct timespec xtime __attribute__ ((aligned (16)));
 static struct timespec wall_to_monotonic __attribute__ ((aligned (16)));
 static struct timespec total_sleep_time;
 
+/* Offset clock monotonic -> clock realtime */
+static ktime_t offs_real;
+
+/* Offset clock monotonic -> clock boottime */
+static ktime_t offs_boot;
+
 /*
  * 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 write on xtime_lock */
+static void update_rt_offset(void)
+{
+	struct timespec tmp, *wtm = &wall_to_monotonic;
 
-/* must hold xtime_lock */
-void timekeeping_leap_insert(int leapsecond)
+	set_normalized_timespec(&tmp, -wtm->tv_sec, -wtm->tv_nsec);
+	offs_real = timespec_to_ktime(tmp);
+}
+
+/* must hold write on xtime_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_rt_offset();
+	update_vsyscall(&xtime, &wall_to_monotonic,
+			 timekeeper.clock, timekeeper.mult);
 }
 
+
+
+/* flag for if timekeeping is suspended */
+int __read_mostly timekeeping_suspended;
+
 /**
  * timekeeping_forward_now - update clock to the current time
  *
@@ -375,11 +395,7 @@ int do_settimeofday(const struct timespec *tv)
 
 	xtime = *tv;
 
-	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);
 
@@ -412,11 +428,7 @@ int timekeeping_inject_offset(struct timespec *ts)
 	xtime = timespec_add(xtime, *ts);
 	wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts);
 
-	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);
 
@@ -591,6 +603,7 @@ void __init timekeeping_init(void)
 	}
 	set_normalized_timespec(&wall_to_monotonic,
 				-boot.tv_sec, -boot.tv_nsec);
+	update_rt_offset();
 	total_sleep_time.tv_sec = 0;
 	total_sleep_time.tv_nsec = 0;
 	write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -599,6 +612,12 @@ void __init timekeeping_init(void)
 /* time in seconds when suspend began */
 static struct timespec timekeeping_suspend_time;
 
+static void update_sleep_time(struct timespec t)
+{
+	total_sleep_time = t;
+	offs_boot = timespec_to_ktime(t);
+}
+
 /**
  * __timekeeping_inject_sleeptime - Internal function to add sleep interval
  * @delta: pointer to a timespec delta value
@@ -616,7 +635,7 @@ static void __timekeeping_inject_sleeptime(struct timespec *delta)
 
 	xtime = timespec_add(xtime, *delta);
 	wall_to_monotonic = timespec_sub(wall_to_monotonic, *delta);
-	total_sleep_time = timespec_add(total_sleep_time, *delta);
+	update_sleep_time(timespec_add(total_sleep_time, *delta));
 }
 
 
@@ -645,10 +664,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta)
 
 	__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);
 
@@ -683,6 +699,7 @@ static void timekeeping_resume(void)
 	timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
 	timekeeper.ntp_error = 0;
 	timekeeping_suspended = 0;
+	timekeeping_update(false);
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 
 	touch_softlockup_watchdog();
@@ -834,9 +851,14 @@ 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();
+		leap = second_overflow(xtime.tv_sec);
+		xtime.tv_sec += leap;
+		wall_to_monotonic.tv_sec -= leap;
+		if (leap)
+			clock_was_set_delayed();
 	}
 
 	/* Accumulate raw time */
@@ -942,14 +964,17 @@ static void update_wall_time(void)
 	 * xtime.tv_nsec isn't larger then NSEC_PER_SEC
 	 */
 	if (unlikely(xtime.tv_nsec >= NSEC_PER_SEC)) {
+		int leap;
 		xtime.tv_nsec -= NSEC_PER_SEC;
 		xtime.tv_sec++;
-		second_overflow();
+		leap = second_overflow(xtime.tv_sec);
+		xtime.tv_sec += leap;
+		wall_to_monotonic.tv_sec -= leap;
+		if (leap)
+			clock_was_set_delayed();
 	}
 
-	/* check to see if there is a new clocksource to use */
-	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
-				timekeeper.mult);
+	timekeeping_update(false);
 }
 
 /**
@@ -1108,6 +1133,40 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
 	} while (read_seqretry(&xtime_lock, seq));
 }
 
+#ifdef CONFIG_HIGH_RES_TIMERS
+/**
+ * ktime_get_update_offsets - hrtimer helper
+ * @real:	pointer to storage for monotonic -> realtime offset
+ * @_boot:	pointer to storage for monotonic -> boottime offset
+ *
+ * Returns current monotonic time and updates the offsets
+ * Called from hrtimer_interupt() or retrigger_next_event()
+ */
+ktime_t ktime_get_update_offsets(ktime_t *real, ktime_t *boot)
+{
+	ktime_t now;
+	unsigned int seq;
+	u64 secs, nsecs;
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+
+		secs = xtime.tv_sec;
+		nsecs = xtime.tv_nsec;
+		nsecs += timekeeping_get_ns();
+		/* If arch requires, add in gettimeoffset() */
+		nsecs += arch_gettimeoffset();
+
+		*real = offs_real;
+		*boot = offs_boot;
+	} while (read_seqretry(&xtime_lock, seq));
+
+	now = ktime_add_ns(ktime_set(secs, 0), nsecs);
+	now = ktime_sub(now, *real);
+	return now;
+}
+#endif
+
 /**
  * ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format
  */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0731e81a..672a749 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2432,10 +2432,12 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 		if (cpumask_test_cpu(cpu, tracing_cpumask) &&
 				!cpumask_test_cpu(cpu, tracing_cpumask_new)) {
 			atomic_inc(&global_trace.data[cpu]->disabled);
+			ring_buffer_record_disable_cpu(global_trace.buffer, cpu);
 		}
 		if (!cpumask_test_cpu(cpu, tracing_cpumask) &&
 				cpumask_test_cpu(cpu, tracing_cpumask_new)) {
 			atomic_dec(&global_trace.data[cpu]->disabled);
+			ring_buffer_record_enable_cpu(global_trace.buffer, cpu);
 		}
 	}
 	arch_spin_unlock(&ftrace_max_lock);