From 9a68fa0ebb288370be3f74819e1d8c8f401c4e71 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Mon, 8 Feb 2021 08:35:53 +0100 Subject: [PATCH] sched/features: Fix hrtick reprogramming [ Upstream commit 156ec6f42b8d300dbbf382738ff35c8bad8f4c3a ] Hung tasks and RCU stall cases were reported on systems which were not 100% busy. Investigation of such unexpected cases (no sign of potential starvation caused by tasks hogging the system) pointed out that the periodic sched tick timer wasn't serviced anymore after a certain point and that caused all machinery that depends on it (timers, RCU, etc.) to stop working as well. This issues was however only reproducible if HRTICK was enabled. Looking at core dumps it was found that the rbtree of the hrtimer base used also for the hrtick was corrupted (i.e. next as seen from the base root and actual leftmost obtained by traversing the tree are different). Same base is also used for periodic tick hrtimer, which might get "lost" if the rbtree gets corrupted. Much alike what described in commit 1f71addd34f4c ("tick/sched: Do not mess with an enqueued hrtimer") there is a race window between hrtimer_set_expires() in hrtick_start and hrtimer_start_expires() in __hrtick_restart() in which the former might be operating on an already queued hrtick hrtimer, which might lead to corruption of the base. Use hrtick_start() (which removes the timer before enqueuing it back) to ensure hrtick hrtimer reprogramming is entirely guarded by the base lock, so that no race conditions can occur. Signed-off-by: Juri Lelli Signed-off-by: Luis Claudio R. Goncalves Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20210208073554.14629-2-juri.lelli@redhat.com Signed-off-by: Sasha Levin --- kernel/sched/core.c | 8 +++----- kernel/sched/sched.h | 1 + 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 269165bf440a..3a150445e0cb 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -363,8 +363,9 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer) static void __hrtick_restart(struct rq *rq) { struct hrtimer *timer = &rq->hrtick_timer; + ktime_t time = rq->hrtick_time; - hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED_HARD); + hrtimer_start(timer, time, HRTIMER_MODE_ABS_PINNED_HARD); } /* @@ -388,7 +389,6 @@ static void __hrtick_start(void *arg) void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; - ktime_t time; s64 delta; /* @@ -396,9 +396,7 @@ void hrtick_start(struct rq *rq, u64 delay) * doesn't make sense and can cause timer DoS. */ delta = max_t(s64, delay, 10000LL); - time = ktime_add_ns(timer->base->get_time(), delta); - - hrtimer_set_expires(timer, time); + rq->hrtick_time = ktime_add_ns(timer->base->get_time(), delta); if (rq == this_rq()) __hrtick_restart(rq); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c122176c627e..fac1b121d113 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1018,6 +1018,7 @@ struct rq { call_single_data_t hrtick_csd; #endif struct hrtimer hrtick_timer; + ktime_t hrtick_time; #endif #ifdef CONFIG_SCHEDSTATS