nohz: Fix collision between tick and other hrtimers

When the tick is stopped and an interrupt occurs afterward, we check on
that interrupt exit if the next tick needs to be rescheduled. If it doesn't need any update, we don't want to do anything.

In order to check if the tick needs an update, we compare it against the
clockevent device deadline. Now that's a problem because the clockevent
device is at a lower level than the tick itself if it is implemented on top of hrtimer.

Quoted 5 lines · Frederic Weisbecker

When the tick is stopped and an interrupt occurs afterward, we check on
that interrupt exit if the next tick needs to be rescheduled. If it doesn't need any update, we don't want to do anything.

Quoted 6 lines

In order to check if the tick needs an update, we compare it against the
clockevent device deadline. Now that's a problem because the clockevent
device is at a lower level than the tick itself if it is implemented on top of hrtimer.

Ohhhhh, good find. That is one subtle bug.

Acked-by Rik van Riel <[email protected]>

Signature · 2 lines

-- 
All Rights Reversed.

When the tick is stopped and an interrupt occurs afterward, we check on that interrupt exit if the next tick needs to be rescheduled. If it doesn't need any update, we don't want to do anything.

In order to check if the tick needs an update, we compare it against the clockevent device deadline. Now that's a problem because the clockevent device is at a lower level than the tick itself if it is implemented on top of hrtimer.

Every hrtimer share this clockevent device. So comparing the next tick deadline against the clockevent device deadline is wrong because the device may be programmed for another hrtimer whose deadline collides with the tick. As a result we may end up not reprogramming the tick accidentally.

In a worst case scenario under full dynticks mode, the tick stops firing as it is supposed to every 1hz, leaving /proc/stat stalled:

Task in a full dynticks CPU
----------------------------

* hrtimer A is queued 2 seconds ahead
* the tick is stopped, scheduled 1 second ahead
* tick fires 1 second later
* on tick exit, nohz schedules the tick 1 second ahead but sees the clockevent device is already programmed to that deadline, fooled by hrtimer A, the tick isn't rescheduled.
* hrtimer A is cancelled before its deadline
* tick never fires again until an interrupt happens...

In order to fix this, store the next tick deadline to the tick_sched local structure and reuse that value later to check whether we need to reprogram the clock after an interrupt.

Reported-by James Hartsock <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc Rik van Riel <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Thomas Gleixner <[email protected]>

Cc James Hartsock <[email protected]>

Signed-off-by Frederic Weisbecker <[email protected]>

---
 kernel/time/tick-sched.c | 7 ++++---
 kernel/time/tick-sched.h | 2 ++
 2 files changed, 6 insertions(+), 3 deletions(-)

kernel/time/tick-sched.c +4 -3

index 71496a2..85d0688 100644
@@ -661,7 +661,6 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
                                         ktime_t now, int cpu)
 {
-       struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
        u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
        unsigned long seq, basejiff;
        ktime_t tick;

@@ -767,7 +766,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
        tick.tv64 = expires;
 
        /* Skip reprogram of event if its not changed */
-       if (ts->tick_stopped && (expires == dev->next_event.tv64))
+       if (ts->tick_stopped && (expires == ts->next_tick.tv64))
                goto out;
 
        /*

@@ -787,6 +786,8 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
                trace_tick_stop(1, TICK_DEP_MASK_NONE);
        }
 
+       ts->next_tick = tick;
+
        /*
         * If the expiration time == KTIME_MAX, then we simply stop
         * the tick timer.

@@ -803,7 +804,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
                tick_program_event(tick, 1);
 out:
        /* Update the estimated sleep length */
-       ts->sleep_length = ktime_sub(dev->next_event, now);
+       ts->sleep_length = ktime_sub(ts->next_tick, now);
        return tick;
 }
 

kernel/time/tick-sched.h +2 -1

index bf38226..075444e 100644
@@ -27,6 +27,7 @@ enum tick_nohz_mode {
  *                     timer is modified for nohz sleeps. This is necessary
  *                     to resume the tick timer operation in the timeline
  *                     when the CPU returns from nohz sleep.
+ * @next_tick:         Next tick to be fired when in dynticks mode.
  * @tick_stopped:      Indicator that the idle tick has been stopped
  * @idle_jiffies:      jiffies at the entry to idle for idle time accounting
  * @idle_calls:                Total number of idle calls

@@ -44,6 +45,7 @@ struct tick_sched {
        unsigned long                   check_clocks;
        enum tick_nohz_mode             nohz_mode;
        ktime_t                         last_tick;
+       ktime_t                         next_tick;
        int                             inidle;
        int                             tick_stopped;
        unsigned long                   idle_jiffies;
--

2.7.4

static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,

kernel/time/tick-sched.c +0 -1

 					 ktime_t now, int cpu)
 {
-	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 	u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
 	unsigned long seq, basejiff;
 	ktime_t	tick;

kernel/time/tick-sched.c +2 -0

 	/*

@@ -787,6 +786,8 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 		trace_tick_stop(1, TICK_DEP_MASK_NONE);
 	}
 
+	ts->next_tick = tick;
+
 	/*
 	 * If the expiration time == KTIME_MAX, then we simply stop
 	 * the tick timer.

Quoted 8 lines · Frederic Weisbecker

static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,

kernel/time/tick-sched.c +0 -1

 					 ktime_t now, int cpu)
 {
-	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 	u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
 	unsigned long seq, basejiff;
 	ktime_t	tick;

kernel/time/tick-sched.c static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, · line 770

Quoted 6 lines

kernel/time/tick-sched.c +1 -1

@@ -767,7 +766,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	tick.tv64 = expires;
 
 	/* Skip reprogram of event if its not changed */
-	if (ts->tick_stopped && (expires == dev->next_event.tv64))
+	if (ts->tick_stopped && (expires == ts->next_tick.tv64))
 		goto out;

Good catch!

Quoted 6 lines

kernel/time/tick-sched.c +0 -0

 	/*

@@ -787,6 +786,8 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 		trace_tick_stop(1, TICK_DEP_MASK_NONE);
 	}
 

kernel/time/tick-sched.c static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, · line 807

Quoted 11 lines

kernel/time/tick-sched.c +3 -1

+	ts->next_tick = tick;
+
 	/*
 	 * If the expiration time == KTIME_MAX, then we simply stop
 	 * the tick timer.

@@ -803,7 +804,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 		tick_program_event(tick, 1);
 out:
 	/* Update the estimated sleep length */
-	ts->sleep_length = ktime_sub(dev->next_event, now);
+	ts->sleep_length = ktime_sub(ts->next_tick, now);

This is wrong. If the next event is earlier than the next estimated tick then tick_nohz_get_sleep_length() will return crap and the idle governor will go into a deeper C-state than sensible.