[PATCH] fix next_timer_interrupt() for hrtimer

Also from Thomas Gleixner <tglx@linutronix.de>

Function next_timer_interrupt() got broken with a recent patch
6ba1b912 as sys_nanosleep() was moved to
hrtimer.  This broke things as next_timer_interrupt() did not check hrtimer
tree for next event.

Function next_timer_interrupt() is needed with dyntick (CONFIG_NO_IDLE_HZ,
VST) implementations, as the system can be in idle when next hrtimer event
was supposed to happen.  At least ARM and S390 currently use
next_timer_interrupt().
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/arm/kernel/time.c

@@ -422,12 +422,14 @@ static int timer_dyn_tick_disable(void)
 void timer_dyn_reprogram(void)
 {
 	struct dyn_tick_timer *dyn_tick = system_timer->dyn_tick;
+	unsigned long next, seq;
 
-	if (dyn_tick) {
-		write_seqlock(&xtime_lock);
-		if (dyn_tick->state & DYN_TICK_ENABLED)
+	if (dyn_tick && (dyn_tick->state & DYN_TICK_ENABLED)) {
+		next = next_timer_interrupt();
+		do {
+			seq = read_seqbegin(&xtime_lock);
 			dyn_tick->reprogram(next_timer_interrupt() - jiffies);
-		write_sequnlock(&xtime_lock);
+		} while (read_seqretry(&xtime_lock, seq));
 	}
 }
 

include/linux/hrtimer.h

@@ -116,6 +116,10 @@ extern int hrtimer_try_to_cancel(struct hrtimer *timer);
 extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer);
 extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp);
 
+#ifdef CONFIG_NO_IDLE_HZ
+extern ktime_t hrtimer_get_next_event(void);
+#endif
+
 static inline int hrtimer_active(const struct hrtimer *timer)
 {
 	return timer->state == HRTIMER_PENDING;

kernel/hrtimer.c

@@ -505,6 +505,41 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
 	return rem;
 }
 
+#ifdef CONFIG_NO_IDLE_HZ
+/**
+ * hrtimer_get_next_event - get the time until next expiry event
+ *
+ * Returns the delta to the next expiry event or KTIME_MAX if no timer
+ * is pending.
+ */
+ktime_t hrtimer_get_next_event(void)
+{
+	struct hrtimer_base *base = __get_cpu_var(hrtimer_bases);
+	ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
+	unsigned long flags;
+	int i;
+
+	for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) {
+		struct hrtimer *timer;
+
+		spin_lock_irqsave(&base->lock, flags);
+		if (!base->first) {
+			spin_unlock_irqrestore(&base->lock, flags);
+			continue;
+		}
+		timer = rb_entry(base->first, struct hrtimer, node);
+		delta.tv64 = timer->expires.tv64;
+		spin_unlock_irqrestore(&base->lock, flags);
+		delta = ktime_sub(delta, base->get_time());
+		if (delta.tv64 < mindelta.tv64)
+			mindelta.tv64 = delta.tv64;
+	}
+	if (mindelta.tv64 < 0)
+		mindelta.tv64 = 0;
+	return mindelta;
+}
+#endif
+
 /**
  * hrtimer_init - initialize a timer to the given clock
  *

kernel/timer.c

@@ -489,9 +489,21 @@ unsigned long next_timer_interrupt(void)
 	struct list_head *list;
 	struct timer_list *nte;
 	unsigned long expires;
+	unsigned long hr_expires = MAX_JIFFY_OFFSET;
+	ktime_t hr_delta;
 	tvec_t *varray[4];
 	int i, j;
 
+	hr_delta = hrtimer_get_next_event();
+	if (hr_delta.tv64 != KTIME_MAX) {
+		struct timespec tsdelta;
+		tsdelta = ktime_to_timespec(hr_delta);
+		hr_expires = timespec_to_jiffies(&tsdelta);
+		if (hr_expires < 3)
+			return hr_expires + jiffies;
+	}
+	hr_expires += jiffies;
+
 	base = &__get_cpu_var(tvec_bases);
 	spin_lock(&base->t_base.lock);
 	expires = base->timer_jiffies + (LONG_MAX >> 1);
@@ -542,6 +554,10 @@ unsigned long next_timer_interrupt(void)
 		}
 	}
 	spin_unlock(&base->t_base.lock);
+
+	if (time_before(hr_expires, expires))
+		return hr_expires;
+
 	return expires;
 }
 #endif