From 2e8e19226398db8265a8e675fcc0118b9e80c9e8 Mon Sep 17 00:00:00 2001
From: Phil Auld
Date: Tue, 19 Mar 2019 09:00:05 -0400
Subject: 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
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
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
Signed-off-by: Peter Zijlstra (Intel)
Cc:
Cc: Anton Blanchard
Cc: Ben Segall
Cc: Linus Torvalds
Cc: Peter Zijlstra
Cc: Thomas Gleixner
Link: https://lkml.kernel.org/r/20190319130005.25492-1-pauld@redhat.com
Signed-off-by: Ingo Molnar
---
kernel/sched/fair.c | 25 +++++++++++++++++++++++++
1 file changed, 25 insertions(+)
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)
--
cgit v1.2.3
From 1b02cd6a2d7f3e2a6a5262887d2cb2912083e42f Mon Sep 17 00:00:00 2001
From: luca abeni
Date: Mon, 25 Mar 2019 14:15:30 +0100
Subject: sched/deadline: Correctly handle active 0-lag timers
syzbot reported the following warning:
[ ] WARNING: CPU: 4 PID: 17089 at kernel/sched/deadline.c:255 task_non_contending+0xae0/0x1950
line 255 of deadline.c is:
WARN_ON(hrtimer_active(&dl_se->inactive_timer));
in task_non_contending().
Unfortunately, in some cases (for example, a deadline task
continuosly blocking and waking immediately) it can happen that
a task blocks (and task_non_contending() is called) while the
0-lag timer is still active.
In this case, the safest thing to do is to immediately decrease
the running bandwidth of the task, without trying to re-arm the 0-lag timer.
Signed-off-by: luca abeni
Signed-off-by: Peter Zijlstra (Intel)
Acked-by: Juri Lelli
Cc: Linus Torvalds
Cc: Peter Zijlstra
Cc: Thomas Gleixner
Cc: chengjian (D)
Link: https://lkml.kernel.org/r/20190325131530.34706-1-luca.abeni@santannapisa.it
Signed-off-by: Ingo Molnar
---
kernel/sched/deadline.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 6a73e41a2016..43901fa3f269 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -252,7 +252,6 @@ static void task_non_contending(struct task_struct *p)
if (dl_entity_is_special(dl_se))
return;
- WARN_ON(hrtimer_active(&dl_se->inactive_timer));
WARN_ON(dl_se->dl_non_contending);
zerolag_time = dl_se->deadline -
@@ -269,7 +268,7 @@ static void task_non_contending(struct task_struct *p)
* If the "0-lag time" already passed, decrease the active
* utilization now, instead of starting a timer
*/
- if (zerolag_time < 0) {
+ if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) {
if (dl_task(p))
sub_running_bw(dl_se, dl_rq);
if (!dl_task(p) || p->state == TASK_DEAD) {
--
cgit v1.2.3