From f9f9ffc237dd924f048204e8799da74f9ecf40cf Mon Sep 17 00:00:00 2001 From: Ben Segall Date: Wed, 16 Oct 2013 11:16:32 -0700 Subject: [PATCH] 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 Signed-off-by: Peter Zijlstra 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 --- kernel/sched/debug.c | 8 ++++++++ kernel/sched/fair.c | 2 ++ 2 files changed, 10 insertions(+) diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index e6ba5e31c7ca..5c34d1817e8f 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -229,6 +229,14 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) atomic_read(&cfs_rq->tg->runnable_avg)); #endif #endif +#ifdef CONFIG_CFS_BANDWIDTH + SEQ_printf(m, " .%-30s: %d\n", "tg->cfs_bandwidth.timer_active", + cfs_rq->tg->cfs_bandwidth.timer_active); + SEQ_printf(m, " .%-30s: %d\n", "throttled", + cfs_rq->throttled); + SEQ_printf(m, " .%-30s: %d\n", "throttle_count", + cfs_rq->throttle_count); +#endif #ifdef CONFIG_FAIR_GROUP_SCHED print_cfs_group_stats(m, cpu, cfs_rq->tg); 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); }