diff mbox

[trusty] sched: Avoid throttle_cfs_rq() racing with period_timer stopping

Message ID 1386782006-3169-1-git-send-email-chris.j.arges@canonical.com
State New
Headers show

Commit Message

Chris J Arges Dec. 11, 2013, 5:13 p.m. UTC 
From: Ben Segall <bsegall@google.com>

BugLink: http://bugs.launchpad.net/bugs/1259645

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>
(cherry picked from commit f9f9ffc237dd924f048204e8799da74f9ecf40cf)

Signed-off-by: Chris J Arges <chris.j.arges@canonical.com>
---
 kernel/sched/debug.c |    8 ++++++++
 kernel/sched/fair.c  |    2 ++
 2 files changed, 10 insertions(+)

Comments

Stefan Bader Dec. 12, 2013, 10:51 a.m. UTC | #1 
Understand this might be pressing matter and we would want it as quick as
possible. Which for T will be automatic as soon as we move to 3.13.
Generally this should be verified with the author/maintainer as of how far this
needs to go back (quickly looking 3.2 maybe?). And then have that requested
upstream.

-Stefan
Tim Gardner Dec. 12, 2013, 3:53 p.m. UTC | #2
diff mbox

Patch

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 1965599..fd9ca1d 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -225,6 +225,14 @@  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 7c70201..513fc2f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2335,6 +2335,8 @@  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);
 }