From 948befd65cac90703caef207bdb39e6ccee0bb8d Mon Sep 17 00:00:00 2001
From: Matt Fleming <mfleming@suse.de>
Date: Mon, 11 Jun 2018 14:06:02 +0100
Subject: [PATCH] sched/fair: Avoid divide by zero when rebalancing domains
Patch-mainline: Not yet, under discussion on LKML
References: bsc#1096254

It's possible that the CPU doing nohz idle balance hasn't had its own
load updated for many seconds. This can lead to huge deltas between
rq->avg_stamp and rq->clock when rebalancing, and has been seen to
cause the following crash:

 divide error: 0000 [#1] SMP
 Call Trace:
  [<ffffffff810bcba8>] update_sd_lb_stats+0xe8/0x560
  [<ffffffff810bd04d>] find_busiest_group+0x2d/0x4b0
  [<ffffffff810bd640>] load_balance+0x170/0x950
  [<ffffffff810be3ff>] rebalance_domains+0x13f/0x290
  [<ffffffff810852bc>] __do_softirq+0xec/0x300
  [<ffffffff8108578a>] irq_exit+0xfa/0x110
  [<ffffffff816167d9>] reschedule_interrupt+0xc9/0xd0

Signed-off-by: Matt Fleming <mfleming@suse.de>
---
 kernel/sched/fair.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 57a229857719..d5ffb20bfc31 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8395,6 +8395,16 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 	    !test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu)))
 		goto end;
 
+	/*
+	 * Ensure this_rq's clock and load are up-to-date before we
+	 * rebalance since it's possible that they haven't been
+	 * updated for multiple schedule periods, i.e. many seconds.
+	 */
+	raw_spin_lock_irq(&this_rq->lock);
+	update_rq_clock(this_rq);
+	cpu_load_update_idle(this_rq);
+	raw_spin_unlock_irq(&this_rq->lock);
+
 	for_each_cpu(balance_cpu, nohz.idle_cpus_mask) {
 		if (balance_cpu == this_cpu || !idle_cpu(balance_cpu))
 			continue;
-- 
2.13.6