@@ -293,8 +293,15 @@ static void clocksource_watchdog(struct timer_list *unused)
next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
if (next_cpu >= nr_cpu_ids)
next_cpu = cpumask_first(cpu_online_mask);
- watchdog_timer.expires += WATCHDOG_INTERVAL;
- add_timer_on(&watchdog_timer, next_cpu);
+
+ /*
+ * Arm timer if not already pending: could race with concurrent
+ * pair clocksource_stop_watchdog() clocksource_start_watchdog().
+ */
+ if (!timer_pending(&watchdog_timer)) {
+ watchdog_timer.expires += WATCHDOG_INTERVAL;
+ add_timer_on(&watchdog_timer, next_cpu);
+ }
out:
spin_unlock(&watchdog_lock);
}
The following commit has been merged into the timers/urgent branch of tip: Commit-ID: febac332a819f0e764aa4da62757ba21d18c182b Gitweb: https://git.kernel.org/tip/febac332a819f0e764aa4da62757ba21d18c182b Author: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> AuthorDate: Fri, 31 Jan 2020 19:08:59 +03:00 Committer: Thomas Gleixner <tglx@linutronix.de> CommitterDate: Sat, 01 Feb 2020 11:07:56 +01:00 clocksource: Prevent double add_timer_on() for watchdog_timer Kernel crashes inside QEMU/KVM are observed: kernel BUG at kernel/time/timer.c:1154! BUG_ON(timer_pending(timer) || !timer->function) in add_timer_on(). At the same time another cpu got: general protection fault: 0000 [#1] SMP PTI of poinson pointer 0xdead000000000200 in: __hlist_del at include/linux/list.h:681 (inlined by) detach_timer at kernel/time/timer.c:818 (inlined by) expire_timers at kernel/time/timer.c:1355 (inlined by) __run_timers at kernel/time/timer.c:1686 (inlined by) run_timer_softirq at kernel/time/timer.c:1699 Unfortunately kernel logs are badly scrambled, stacktraces are lost. Printing the timer->function before the BUG_ON() pointed to clocksource_watchdog(). The execution of clocksource_watchdog() can race with a sequence of clocksource_stop_watchdog() .. clocksource_start_watchdog(): expire_timers() detach_timer(timer, true); timer->entry.pprev = NULL; raw_spin_unlock_irq(&base->lock); call_timer_fn clocksource_watchdog() clocksource_watchdog_kthread() or clocksource_unbind() spin_lock_irqsave(&watchdog_lock, flags); clocksource_stop_watchdog(); del_timer(&watchdog_timer); watchdog_running = 0; spin_unlock_irqrestore(&watchdog_lock, flags); spin_lock_irqsave(&watchdog_lock, flags); clocksource_start_watchdog(); add_timer_on(&watchdog_timer, ...); watchdog_running = 1; spin_unlock_irqrestore(&watchdog_lock, flags); spin_lock(&watchdog_lock); add_timer_on(&watchdog_timer, ...); BUG_ON(timer_pending(timer) || !timer->function); timer_pending() -> true BUG() I.e. inside clocksource_watchdog() watchdog_timer could be already armed. Check timer_pending() before calling add_timer_on(). This is sufficient as all operations are synchronized by watchdog_lock. Fixes: 75c5158f70c0 ("timekeeping: Update clocksource with stop_machine") Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/158048693917.4378.13823603769948933793.stgit@buzz --- kernel/time/clocksource.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)