nohz: Prevent clocksource wrapping during idle

The dynamic tick allows the kernel to sleep for periods longer than a
single tick, but it does not limit the sleep time currently. In the
worst case the kernel could sleep longer than the wrap around time of
the time keeping clock source which would result in losing track of
time.

Prevent this by limiting it to the safe maximum sleep time of the
current time keeping clock source. The value is calculated when the
clock source is registered.

[ tglx: simplified the code a bit and massaged the commit msg ]

Signed-off-by: Jon Hunter <jon-hunter@ti.com>
Cc: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <1250617512-23567-2-git-send-email-jon-hunter@ti.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 38 insertions, 14 deletions

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index c65ba0faa98..a80b4644fe6 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -208,6 +208,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 	struct tick_sched *ts;
 	ktime_t last_update, expires, now;
 	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+	u64 time_delta;
 	int cpu;
 
 	local_irq_save(flags);
@@ -262,6 +263,17 @@ void tick_nohz_stop_sched_tick(int inidle)
 		seq = read_seqbegin(&xtime_lock);
 		last_update = last_jiffies_update;
 		last_jiffies = jiffies;
+
+		/*
+		 * On SMP we really should only care for the CPU which
+		 * has the do_timer duty assigned. All other CPUs can
+		 * sleep as long as they want.
+		 */
+		if (cpu == tick_do_timer_cpu ||
+		    tick_do_timer_cpu == TICK_DO_TIMER_NONE)
+			time_delta = timekeeping_max_deferment();
+		else
+			time_delta = KTIME_MAX;
 	} while (read_seqretry(&xtime_lock, seq));
 
 	if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
@@ -284,11 +296,26 @@ void tick_nohz_stop_sched_tick(int inidle)
 	if ((long)delta_jiffies >= 1) {
 
 		/*
-		* calculate the expiry time for the next timer wheel
-		* timer
-		*/
-		expires = ktime_add_ns(last_update, tick_period.tv64 *
-				   delta_jiffies);
+		 * calculate the expiry time for the next timer wheel
+		 * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals
+		 * that there is no timer pending or at least extremely
+		 * far into the future (12 days for HZ=1000). In this
+		 * case we set the expiry to the end of time.
+		 */
+		if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
+			/*
+			 * Calculate the time delta for the next timer event.
+			 * If the time delta exceeds the maximum time delta
+			 * permitted by the current clocksource then adjust
+			 * the time delta accordingly to ensure the
+			 * clocksource does not wrap.
+			 */
+			time_delta = min_t(u64, time_delta,
+					   tick_period.tv64 * delta_jiffies);
+			expires = ktime_add_ns(last_update, time_delta);
+		} else {
+			expires.tv64 = KTIME_MAX;
+		}
 
 		/*
 		 * If this cpu is the one which updates jiffies, then
@@ -332,22 +359,19 @@ void tick_nohz_stop_sched_tick(int inidle)
 
 		ts->idle_sleeps++;
 
+		/* Mark expires */
+		ts->idle_expires = expires;
+
 		/*
-		 * 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 the expiration time == KTIME_MAX, then
+		 * in this case we simply stop the tick timer.
 		 */
-		if (unlikely(delta_jiffies >= NEXT_TIMER_MAX_DELTA)) {
-			ts->idle_expires.tv64 = KTIME_MAX;
+		 if (unlikely(expires.tv64 == KTIME_MAX)) {
 			if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
 				hrtimer_cancel(&ts->sched_timer);
 			goto out;
 		}
 
-		/* Mark expiries */
-		ts->idle_expires = expires;
-
 		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
 			hrtimer_start(&ts->sched_timer, expires,
 				      HRTIMER_MODE_ABS_PINNED);