sched: Avoid throttle_cfs_rq() racing with period_timer stopping

commit f9f9ffc237dd924f048204e8799da74f9ecf40cf upstream.

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>
Cc: Chris J Arges <chris.j.arges@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 75024a673520b9c5e0e506b1e0963d782cc84c5d..e745a154836703bc3bd3980ba5adb1651ebf50f7 100644 (file)
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -224,6 +224,14 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
        SEQ_printf(m, "  .%-30s: %d\n", "tg->runnable_avg",
                        atomic_read(&cfs_rq->tg->runnable_avg));
 #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
 
        print_cfs_group_stats(m, cpu, cfs_rq->tg);
 #endif

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 009a62bb859d756348cddc9ba55a6e753f401323..da7eebb22b06db15bc791591918f086ae54b4614 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2288,6 +2288,8 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
        cfs_rq->throttled_clock = rq->clock;
        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);
 }