summaryrefslogtreecommitdiffstats
path: root/kernel/time
diff options
context:
space:
mode:
authorThomas Gleixner <tglx@linutronix.de>2018-04-24 21:22:18 +0200
committerThomas Gleixner <tglx@linutronix.de>2018-04-26 14:53:32 +0200
commit1f71addd34f4c442bec7d7c749acc1beb58126f2 (patch)
tree4c8e9b49bbe2d850137ba2a6e4c6b4adcbc22e33 /kernel/time
parent6d08b06e67cd117f6992c46611dfb4ce267cd71e (diff)
downloadlinux-1f71addd34f4c442bec7d7c749acc1beb58126f2.tar.bz2
tick/sched: Do not mess with an enqueued hrtimer
Kaike reported that in tests rdma hrtimers occasionaly stopped working. He did great debugging, which provided enough context to decode the problem. CPU 3 CPU 2 idle start sched_timer expires = 712171000000 queue->next = sched_timer start rdmavt timer. expires = 712172915662 lock(baseof(CPU3)) tick_nohz_stop_tick() tick = 716767000000 timerqueue_add(tmr) hrtimer_set_expires(sched_timer, tick); sched_timer->expires = 716767000000 <---- FAIL if (tmr->expires < queue->next->expires) hrtimer_start(sched_timer) queue->next = tmr; lock(baseof(CPU3)) unlock(baseof(CPU3)) timerqueue_remove() timerqueue_add() ts->sched_timer is queued and queue->next is pointing to it, but then ts->sched_timer.expires is modified. This not only corrupts the ordering of the timerqueue RB tree, it also makes CPU2 see the new expiry time of timerqueue->next->expires when checking whether timerqueue->next needs to be updated. So CPU2 sees that the rdma timer is earlier than timerqueue->next and sets the rdma timer as new next. Depending on whether it had also seen the new time at RB tree enqueue, it might have queued the rdma timer at the wrong place and then after removing the sched_timer the RB tree is completely hosed. The problem was introduced with a commit which tried to solve inconsistency between the hrtimer in the tick_sched data and the underlying hardware clockevent. It split out hrtimer_set_expires() to store the new tick time in both the NOHZ and the NOHZ + HIGHRES case, but missed the fact that in the NOHZ + HIGHRES case the hrtimer might still be queued. Use hrtimer_start(timer, tick...) for the NOHZ + HIGHRES case which sets timer->expires after canceling the timer and move the hrtimer_set_expires() invocation into the NOHZ only code path which is not affected as it merily uses the hrtimer as next event storage so code pathes can be shared with the NOHZ + HIGHRES case. Fixes: d4af6d933ccf ("nohz: Fix spurious warning when hrtimer and clockevent get out of sync") Reported-by: "Wan Kaike" <kaike.wan@intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Frederic Weisbecker <frederic@kernel.org> Cc: "Marciniszyn Mike" <mike.marciniszyn@intel.com> Cc: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: linux-rdma@vger.kernel.org Cc: "Dalessandro Dennis" <dennis.dalessandro@intel.com> Cc: "Fleck John" <john.fleck@intel.com> Cc: stable@vger.kernel.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: "Weiny Ira" <ira.weiny@intel.com> Cc: "linux-rdma@vger.kernel.org" Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1804241637390.1679@nanos.tec.linutronix.de Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1804242119210.1597@nanos.tec.linutronix.de
Diffstat (limited to 'kernel/time')
-rw-r--r--kernel/time/tick-sched.c10
1 files changed, 5 insertions, 5 deletions
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 646645e981f9..d31bec177fa5 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -804,12 +804,12 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
return;
}
- hrtimer_set_expires(&ts->sched_timer, tick);
-
- if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
- hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
- else
+ if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
+ hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED);
+ } else {
+ hrtimer_set_expires(&ts->sched_timer, tick);
tick_program_event(tick, 1);
+ }
}
static void tick_nohz_retain_tick(struct tick_sched *ts)