Commit 11e31f60 authored by Thomas Gleixner's avatar Thomas Gleixner
Browse files

watchdog/softlockup: Enforce that timestamp is valid on boot 



Robert reported that during boot the watchdog timestamp is set to 0 for one
second which is the indicator for a watchdog reset.

The reason for this is that the timestamp is in seconds and the time is
taken from sched clock and divided by ~1e9. sched clock starts at 0 which
means that for the first second during boot the watchdog timestamp is 0,
i.e. reset.

Use ULONG_MAX as the reset indicator value so the watchdog works correctly
right from the start. ULONG_MAX would only conflict with a real timestamp
if the system reaches an uptime of 136 years on 32bit and almost eternity
on 64bit.

Reported-by: default avatarRobert Richter <rrichter@marvell.com>
Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/87o8v3uuzl.fsf@nanos.tec.linutronix.de
parent 3a51449b

kernel/watchdog.c

+6 −4
Original line number Diff line number Diff line
@@ -161,6 +161,8 @@ static void lockup_detector_update_enable(void) 


#ifdef CONFIG_SOFTLOCKUP_DETECTOR



#define SOFTLOCKUP_RESET	ULONG_MAX



/* Global variables, exported for sysctl */

unsigned int __read_mostly softlockup_panic =

			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
@@ -272,7 +274,7 @@ notrace void touch_softlockup_watchdog_sched(void) 
	 * Preemption can be enabled.  It doesn't matter which CPU's timestamp

	 * gets zeroed here, so use the raw_ operation.

	 */

	raw_cpu_write(watchdog_touch_ts, 0);

	raw_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET);

}



notrace void touch_softlockup_watchdog(void)
@@ -296,14 +298,14 @@ void touch_all_softlockup_watchdogs(void) 
	 * the softlockup check.

	 */

	for_each_cpu(cpu, &watchdog_allowed_mask)

		per_cpu(watchdog_touch_ts, cpu) = 0;

		per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET;

	wq_watchdog_touch(-1);

}



void touch_softlockup_watchdog_sync(void)

{

	__this_cpu_write(softlockup_touch_sync, true);

	__this_cpu_write(watchdog_touch_ts, 0);

	__this_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET);

}



static int is_softlockup(unsigned long touch_ts)
@@ -379,7 +381,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) 
	/* .. and repeat */

	hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));



	if (touch_ts == 0) {

	if (touch_ts == SOFTLOCKUP_RESET) {

		if (unlikely(__this_cpu_read(softlockup_touch_sync))) {

			/*

			 * If the time stamp was touched atomically

CRA Git | Maintained and supported by SUSTech CRA and CCSE