From 9ca715c462018a8631240088dafa567bec6fe721 Mon Sep 17 00:00:00 2001 From: Ben Segall Date: Wed, 16 Oct 2013 11:16:22 -0700 Subject: 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 Signed-off-by: Peter Zijlstra 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 Cc: Chris J Arges Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d0a7b93ce05e..516bc354212d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2410,6 +2410,13 @@ 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) { @@ -2682,11 +2689,11 @@ 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) -- cgit v1.2.3