summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorBen Segall <bsegall@google.com>2013-10-16 11:16:22 -0700
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2014-01-15 15:27:11 -0800
commit03d35a39f4de9f2e9d7fbc5c2d03dbcc5b882df7 (patch)
treebe90a817103d24c521ba427819374fd0600cef40
parent9b318052acd24780f4dba1349ef3a30a7aef52ad (diff)
downloadlwn-03d35a39f4de9f2e9d7fbc5c2d03dbcc5b882df7.tar.gz
lwn-03d35a39f4de9f2e9d7fbc5c2d03dbcc5b882df7.zip
sched: Fix hrtimer_cancel()/rq->lock deadlock
commit 927b54fccbf04207ec92f669dce6806848cbec7d upstream. __start_cfs_bandwidth calls hrtimer_cancel while holding rq->lock, waiting for the hrtimer to finish. However, if sched_cfs_period_timer runs for another loop iteration, the hrtimer can attempt to take rq->lock, resulting in deadlock. Fix this by ensuring that cfs_b->timer_active is cleared only if the _latest_ call to do_sched_cfs_period_timer is returning as idle. Then __start_cfs_bandwidth can just call hrtimer_try_to_cancel and wait for that to succeed or timer_active == 1. 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/20131016181622.22647.16643.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>
-rw-r--r--kernel/sched/fair.c15
1 files changed, 11 insertions, 4 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8609fa84210a..3ce6561109b7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1771,6 +1771,13 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
if (idle)
goto out_unlock;
+ /*
+ * if we have relooped after returning idle once, we need to update our
+ * status as actually running, so that other cpus doing
+ * __start_cfs_bandwidth will stop trying to cancel us.
+ */
+ cfs_b->timer_active = 1;
+
__refill_cfs_bandwidth_runtime(cfs_b);
if (!throttled) {
@@ -2043,11 +2050,11 @@ void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
* (timer_active==0 becomes visible before the hrtimer call-back
* terminates). In either case we ensure that it's re-programmed
*/
- while (unlikely(hrtimer_active(&cfs_b->period_timer))) {
+ while (unlikely(hrtimer_active(&cfs_b->period_timer)) &&
+ hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) {
+ /* bounce the lock to allow do_sched_cfs_period_timer to run */
raw_spin_unlock(&cfs_b->lock);
- /* ensure cfs_b->lock is available while we wait */
- hrtimer_cancel(&cfs_b->period_timer);
-
+ cpu_relax();
raw_spin_lock(&cfs_b->lock);
/* if someone else restarted the timer then we're done */
if (cfs_b->timer_active)