[tip:sched/core] watchdog/softlockup: Fix cpu_stop_queue_work() double-queue bug

[tip-bot for Peter Zijlstra]

Commit-ID:  be45bf5395e0886a93fc816bbe41a008ec2e42e2
Gitweb:     https://git.kernel.org/tip/be45bf5395e0886a93fc816bbe41a008ec2e42e2
Author:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate: Fri, 13 Jul 2018 12:42:08 +0200
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Sun, 15 Jul 2018 23:51:19 +0200

watchdog/softlockup: Fix cpu_stop_queue_work() double-queue bug

When scheduling is delayed for longer than the softlockup interrupt
period it is possible to double-queue the cpu_stop_work, causing list
corruption.

Cure this by adding a completion to track the cpu_stop_work's
progress.

Reported-by: kernel test robot <lkp@xxxxxxxxx>
Tested-by: Rong Chen <rong.a.chen@xxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Fixes: 9cf57731b63e ("watchdog/softlockup: Replace "watchdog/%u" threads with cpu_stop_work")
Link: http://lkml.kernel.org/r/20180713104208.GW2494@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 kernel/watchdog.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index b81f777838d5..5470dce212c0 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -330,6 +330,9 @@ static void watchdog_interrupt_count(void)
 	__this_cpu_inc(hrtimer_interrupts);
 }
 
+static DEFINE_PER_CPU(struct completion, softlockup_completion);
+static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
+
 /*
  * The watchdog thread function - touches the timestamp.
  *
@@ -343,12 +346,11 @@ static int softlockup_fn(void *data)
 	__this_cpu_write(soft_lockup_hrtimer_cnt,
 			 __this_cpu_read(hrtimer_interrupts));
 	__touch_watchdog();
+	complete(this_cpu_ptr(&softlockup_completion));
 
 	return 0;
 }
 
-static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
-
 /* watchdog kicker functions */
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
@@ -364,9 +366,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	watchdog_interrupt_count();
 
 	/* kick the softlockup detector */
-	stop_one_cpu_nowait(smp_processor_id(),
-			softlockup_fn, NULL,
-			this_cpu_ptr(&softlockup_stop_work));
+	if (completion_done(this_cpu_ptr(&softlockup_completion))) {
+		reinit_completion(this_cpu_ptr(&softlockup_completion));
+		stop_one_cpu_nowait(smp_processor_id(),
+				softlockup_fn, NULL,
+				this_cpu_ptr(&softlockup_stop_work));
+	}
 
 	/* .. and repeat */
 	hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
@@ -467,9 +472,13 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 static void watchdog_enable(unsigned int cpu)
 {
 	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
+	struct completion *done = this_cpu_ptr(&softlockup_completion);
 
 	WARN_ON_ONCE(cpu != smp_processor_id());
 
+	init_completion(done);
+	complete(done);
+
 	/*
 	 * Start the timer first to prevent the NMI watchdog triggering
 	 * before the timer has a chance to fire.
@@ -499,6 +508,7 @@ static void watchdog_disable(unsigned int cpu)
 	 */
 	watchdog_nmi_disable(cpu);
 	hrtimer_cancel(hrtimer);
+	wait_for_completion(this_cpu_ptr(&softlockup_completion));
 }
 
 static int softlockup_stop_fn(void *data)