summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPhil Auld <pauld@redhat.com>2019-03-19 09:00:05 -0400
committerIngo Molnar <mingo@kernel.org>2019-04-16 16:50:05 +0200
commit2e8e19226398db8265a8e675fcc0118b9e80c9e8 (patch)
tree7985a28d4e3d231defec044435c9b59b04e0f38a
parent618d919cae2fcaadc752f27ddac8b939da8b441a (diff)
sched/fair: Limit sched_cfs_period_timer() loop to avoid hard lockup
With extremely short cfs_period_us setting on a parent task group with a large number of children the for loop in sched_cfs_period_timer() can run until the watchdog fires. There is no guarantee that the call to hrtimer_forward_now() will ever return 0. The large number of children can make do_sched_cfs_period_timer() take longer than the period. NMI watchdog: Watchdog detected hard LOCKUP on cpu 24 RIP: 0010:tg_nop+0x0/0x10 <IRQ> walk_tg_tree_from+0x29/0xb0 unthrottle_cfs_rq+0xe0/0x1a0 distribute_cfs_runtime+0xd3/0xf0 sched_cfs_period_timer+0xcb/0x160 ? sched_cfs_slack_timer+0xd0/0xd0 __hrtimer_run_queues+0xfb/0x270 hrtimer_interrupt+0x122/0x270 smp_apic_timer_interrupt+0x6a/0x140 apic_timer_interrupt+0xf/0x20 </IRQ> To prevent this we add protection to the loop that detects when the loop has run too many times and scales the period and quota up, proportionally, so that the timer can complete before then next period expires. This preserves the relative runtime quota while preventing the hard lockup. A warning is issued reporting this state and the new values. Signed-off-by: Phil Auld <pauld@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <stable@vger.kernel.org> Cc: Anton Blanchard <anton@ozlabs.org> Cc: Ben Segall <bsegall@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20190319130005.25492-1-pauld@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
-rw-r--r--kernel/sched/fair.c25
1 files changed, 25 insertions, 0 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 40bd1e27b1b7..a4d9e14bf138 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4885,6 +4885,8 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
return HRTIMER_NORESTART;
}
+extern const u64 max_cfs_quota_period;
+
static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
{
struct cfs_bandwidth *cfs_b =
@@ -4892,6 +4894,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
unsigned long flags;
int overrun;
int idle = 0;
+ int count = 0;
raw_spin_lock_irqsave(&cfs_b->lock, flags);
for (;;) {
@@ -4899,6 +4902,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
if (!overrun)
break;
+ if (++count > 3) {
+ u64 new, old = ktime_to_ns(cfs_b->period);
+
+ new = (old * 147) / 128; /* ~115% */
+ new = min(new, max_cfs_quota_period);
+
+ cfs_b->period = ns_to_ktime(new);
+
+ /* since max is 1s, this is limited to 1e9^2, which fits in u64 */
+ cfs_b->quota *= new;
+ cfs_b->quota = div64_u64(cfs_b->quota, old);
+
+ pr_warn_ratelimited(
+ "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n",
+ smp_processor_id(),
+ div_u64(new, NSEC_PER_USEC),
+ div_u64(cfs_b->quota, NSEC_PER_USEC));
+
+ /* reset count so we don't come right back in here */
+ count = 0;
+ }
+
idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
}
if (idle)