[PATCH v2] sched/fair: Limit sched_cfs_period_timer loop to avoid hard lockup

[Phil Auld]

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.

[  217.264946] NMI watchdog: Watchdog detected hard LOCKUP on cpu 24
[  217.264948] Modules linked in: sunrpc iTCO_wdt gpio_ich iTCO_vendor_support intel_powerclamp coretemp kvm_intel
+kvm ipmi_ssif irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ipmi_si intel_cstate joydev
+ipmi_devintf pcspkr hpilo intel_uncore sg hpwdt ipmi_msghandler acpi_power_meter i7core_edac lpc_ich acpi_cpufreq
+ip_tables xfs libcrc32c sr_mod sd_mod cdrom ata_generic radeon i2c_algo_bit drm_kms_helper syscopyarea
+sysfillrect sysimgblt fb_sys_fops ttm ata_piix drm serio_raw crc32c_intel hpsa myri10ge libata dca
+scsi_transport_sas netxen_nic dm_mirror dm_region_hash dm_log dm_mod
[  217.264964] CPU: 24 PID: 46684 Comm: myapp Not tainted 5.0.0-rc7+ #25
[  217.264965] Hardware name: HP ProLiant DL580 G7, BIOS P65 08/16/2015
[  217.264965] RIP: 0010:tg_nop+0x0/0x10
[  217.264966] Code: 83 c9 08 f0 48 0f b1 0f 48 39 c2 74 0e 48 89 c2 f7 c2 00 00 20 00 75 dc 31 c0 c3 b8 01 00 00
+00 c3 66 0f 1f 84 00 00 00 00 00 <66> 66 66 66 90 31 c0 c3 0f 1f 84 00 00 00 00 00 66 66 66 66 90 8b
[  217.264967] RSP: 0000:ffff976a7f703e48 EFLAGS: 00000087
[  217.264967] RAX: ffff976a7c7c8f00 RBX: ffff976a6f4fad00 RCX: ffff976a7c7c90f0
[  217.264968] RDX: ffff976a6f4faee0 RSI: ffff976a7f961f00 RDI: ffff976a6f4fad00
[  217.264968] RBP: ffff976a7f961f00 R08: 0000000000000002 R09: ffffffad2c9b3331
[  217.264969] R10: 0000000000000000 R11: 0000000000000000 R12: ffff976a7c7c8f00
[  217.264969] R13: ffffffffb2305c00 R14: 0000000000000000 R15: ffffffffb22f8510
[  217.264970] FS:  00007f6240678740(0000) GS:ffff976a7f700000(0000) knlGS:0000000000000000
[  217.264970] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  217.264971] CR2: 00000000006dee20 CR3: 000000bf2bffc005 CR4: 00000000000206e0
[  217.264971] Call Trace:
[  217.264971]  <IRQ>
[  217.264972]  walk_tg_tree_from+0x29/0xb0
[  217.264972]  unthrottle_cfs_rq+0xe0/0x1a0
[  217.264972]  distribute_cfs_runtime+0xd3/0xf0
[  217.264973]  sched_cfs_period_timer+0xcb/0x160
[  217.264973]  ? sched_cfs_slack_timer+0xd0/0xd0
[  217.264973]  __hrtimer_run_queues+0xfb/0x270
[  217.264974]  hrtimer_interrupt+0x122/0x270
[  217.264974]  smp_apic_timer_interrupt+0x6a/0x140
[  217.264975]  apic_timer_interrupt+0xf/0x20
[  217.264975]  </IRQ>
[  217.264975] RIP: 0033:0x7f6240125fe5
[  217.264976] Code: 44 17 d0 f3 44 0f 7f 47 30 f3 44 0f 7f 44 17 c0 48 01 fa 48 83 e2 c0 48 39 d1 74 a3 66 0f 1f
+84 00 00 00 00 00 66 44 0f 7f 01 <66> 44 0f 7f 41 10 66 44 0f 7f 41 20 66 44 0f 7f 41 30 48 83 c1 40
...

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.

v2: Math reworked/simplified by Peter Zijlstra.

Signed-off-by: Phil Auld <pauld@xxxxxxxxxx>
Cc: Ben Segall <bsegall@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Anton Blanchard <anton@xxxxxxxxxx>
---
 kernel/sched/fair.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ea74d43924b2..4e43a40ec13c 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 /= 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(),
+				new/NSEC_PER_USEC,
+				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)
-- 
2.18.0