summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorFrederic Weisbecker <fweisbec@gmail.com>2017-01-04 15:12:04 +0100
committerThomas Gleixner <tglx@linutronix.de>2017-01-11 10:41:33 +0100
commit24b91e360ef521a2808771633d76ebc68bd5604b (patch)
treebca05efec060a4efaf79c0260bebdb22fa3a0635 /kernel
parenta121103c922847ba5010819a3f250f1f7fc84ab8 (diff)
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. 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. On the other hand, ts->sleep_length still wants to know about the next clock event and not just the tick, so we want to improve the related comment to avoid confusion. Reported-by: James Hartsock <hartsjc@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Reviewed-by: Wanpeng Li <wanpeng.li@hotmail.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Rik van Riel <riel@redhat.com> Link: http://lkml.kernel.org/r/1483539124-5693-1-git-send-email-fweisbec@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/time/tick-sched.c9
-rw-r--r--kernel/time/tick-sched.h2
2 files changed, 9 insertions, 2 deletions
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 2c115fdab397..74e0388cc88d 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -767,7 +767,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
tick = expires;
/* Skip reprogram of event if its not changed */
- if (ts->tick_stopped && (expires == dev->next_event))
+ if (ts->tick_stopped && (expires == ts->next_tick))
goto out;
/*
@@ -787,6 +787,8 @@ 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.
@@ -802,7 +804,10 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
else
tick_program_event(tick, 1);
out:
- /* Update the estimated sleep length */
+ /*
+ * Update the estimated sleep length until the next timer
+ * (not only the tick).
+ */
ts->sleep_length = ktime_sub(dev->next_event, now);
return tick;
}
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index bf38226e5c17..075444e3d48e 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -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;