sched: Fix hrtimer_cancel()/rq->lock deadlock
__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>
This commit is contained in:
parent
db06e78cc1
commit
927b54fccb
1 changed files with 11 additions and 4 deletions
|
@ -3225,6 +3225,13 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
|
||||||
if (idle)
|
if (idle)
|
||||||
goto out_unlock;
|
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);
|
__refill_cfs_bandwidth_runtime(cfs_b);
|
||||||
|
|
||||||
if (!throttled) {
|
if (!throttled) {
|
||||||
|
@ -3493,11 +3500,11 @@ void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
|
||||||
* (timer_active==0 becomes visible before the hrtimer call-back
|
* (timer_active==0 becomes visible before the hrtimer call-back
|
||||||
* terminates). In either case we ensure that it's re-programmed
|
* 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);
|
raw_spin_unlock(&cfs_b->lock);
|
||||||
/* ensure cfs_b->lock is available while we wait */
|
cpu_relax();
|
||||||
hrtimer_cancel(&cfs_b->period_timer);
|
|
||||||
|
|
||||||
raw_spin_lock(&cfs_b->lock);
|
raw_spin_lock(&cfs_b->lock);
|
||||||
/* if someone else restarted the timer then we're done */
|
/* if someone else restarted the timer then we're done */
|
||||||
if (cfs_b->timer_active)
|
if (cfs_b->timer_active)
|
||||||
|
|
Loading…
Reference in a new issue