summaryrefslogtreecommitdiffstats
path: root/kernel/sched/fair.c
diff options
context:
space:
mode:
authorBen Segall <bsegall@google.com>2013-10-16 20:16:32 +0200
committerIngo Molnar <mingo@kernel.org>2013-10-29 12:02:32 +0100
commitf9f9ffc237dd924f048204e8799da74f9ecf40cf (patch)
tree81ed0c3435dfe54781d0f120d3a5938d571bacd1 /kernel/sched/fair.c
parentsched: Guarantee new group-entities always have weight (diff)
downloadlinux-f9f9ffc237dd924f048204e8799da74f9ecf40cf.tar.xz
linux-f9f9ffc237dd924f048204e8799da74f9ecf40cf.zip
sched: Avoid throttle_cfs_rq() racing with period_timer stopping
throttle_cfs_rq() doesn't check to make sure that period_timer is running, and while update_curr/assign_cfs_runtime does, a concurrently running period_timer on another cpu could cancel itself between this cpu's update_curr and throttle_cfs_rq(). If there are no other cfs_rqs running in the tg to restart the timer, this causes the cfs_rq to be stranded forever. Fix this by calling __start_cfs_bandwidth() in throttle if the timer is inactive. (Also add some sched_debug lines for cfs_bandwidth.) Tested: make a run/sleep task in a cgroup, loop switching the cgroup between 1ms/100ms quota and unlimited, checking for timer_active=0 and throttled=1 as a failure. With the throttle_cfs_rq() change commented out this fails, with the full patch it passes. Signed-off-by: Ben Segall <bsegall@google.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: pjt@google.com Link: http://lkml.kernel.org/r/20131016181632.22647.84174.stgit@sword-of-the-dawn.mtv.corp.google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to '')
-rw-r--r--kernel/sched/fair.c2
1 files changed, 2 insertions, 0 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0923ab2b7eb9..41c02b6b090e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3112,6 +3112,8 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
cfs_rq->throttled_clock = rq_clock(rq);
raw_spin_lock(&cfs_b->lock);
list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+ if (!cfs_b->timer_active)
+ __start_cfs_bandwidth(cfs_b);
raw_spin_unlock(&cfs_b->lock);
}