NOHZ: prevent multiplication overflow - stop timer for huge timeouts

get_next_timer_interrupt() returns a delta of (LONG_MAX > 1) in case
there is no timer pending. On 64 bit machines this results in a
multiplication overflow in tick_nohz_stop_sched_tick().

Reported by: Dave Miller <davem@davemloft.net>

Make the return value a constant and limit the return value to a 32 bit
value.

When the max timeout value is returned, we can safely stop the tick
timer device. The max jiffies delta results in a 12 days timeout for
HZ=1000.

In the long term the get_next_timer_interrupt() code needs to be
reworked to return ktime instead of jiffies, but we have to wait until
the last users of the original NO_IDLE_HZ code are converted.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 30 insertions, 2 deletions

diff --git a/include/linux/timer.h b/include/linux/timer.h
index e0c5c16..c661710 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -69,6 +69,12 @@ extern int __mod_timer(struct timer_list *timer, unsigned long expires);
 extern int mod_timer(struct timer_list *timer, unsigned long expires);
 
 /*
+ * The jiffies value which is added to now, when there is no timer
+ * in the timer wheel:
+ */
+#define NEXT_TIMER_MAX_DELTA	((1UL << 30) - 1)
+
+/*
  * Return when the next timer-wheel timeout occurs (in absolute jiffies),
  * locks the timer base:
  */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3e7ebc4..52db9e3 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -247,6 +247,21 @@ void tick_nohz_stop_sched_tick(void)
 		if (cpu == tick_do_timer_cpu)
 			tick_do_timer_cpu = -1;
 
+		ts->idle_sleeps++;
+
+		/*
+		 * delta_jiffies >= NEXT_TIMER_MAX_DELTA signals that
+		 * there is no timer pending or at least extremly far
+		 * into the future (12 days for HZ=1000). In this case
+		 * we simply stop the tick timer:
+		 */
+		if (unlikely(delta_jiffies >= NEXT_TIMER_MAX_DELTA)) {
+			ts->idle_expires.tv64 = KTIME_MAX;
+			if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
+				hrtimer_cancel(&ts->sched_timer);
+			goto out;
+		}
+
 		/*
 		 * calculate the expiry time for the next timer wheel
 		 * timer
@@ -254,7 +269,6 @@ void tick_nohz_stop_sched_tick(void)
 		expires = ktime_add_ns(last_update, tick_period.tv64 *
 				       delta_jiffies);
 		ts->idle_expires = expires;
-		ts->idle_sleeps++;
 
 		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
 			hrtimer_start(&ts->sched_timer, expires,
diff --git a/kernel/timer.c b/kernel/timer.c
index 5ec5490..1a69705 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -666,7 +666,7 @@ static inline void __run_timers(tvec_base_t *base)
 static unsigned long __next_timer_interrupt(tvec_base_t *base)
 {
 	unsigned long timer_jiffies = base->timer_jiffies;
-	unsigned long expires = timer_jiffies + (LONG_MAX >> 1);
+	unsigned long expires = timer_jiffies + NEXT_TIMER_MAX_DELTA;
 	int index, slot, array, found = 0;
 	struct timer_list *nte;
 	tvec_t *varray[4];
@@ -752,6 +752,14 @@ static unsigned long cmp_next_hrtimer_event(unsigned long now,
 
 	tsdelta = ktime_to_timespec(hr_delta);
 	delta = timespec_to_jiffies(&tsdelta);
+
+	/*
+	 * Limit the delta to the max value, which is checked in
+	 * tick_nohz_stop_sched_tick():
+	 */
+	if (delta > NEXT_TIMER_MAX_DELTA)
+		delta = NEXT_TIMER_MAX_DELTA;
+
 	/*
 	 * Take rounding errors in to account and make sure, that it
 	 * expires in the next tick. Otherwise we go into an endless