From b94f51183b0617e7b9b4fb4137d4cf1cab7547c2 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Tue, 24 Jan 2017 15:17:53 -0800 Subject: [PATCH] kernel/watchdog: prevent false hardlockup on overloaded system On an overloaded system, it is possible that a change in the watchdog threshold can be delayed long enough to trigger a false positive. This can easily be achieved by having a cpu spinning indefinitely on a task, while another cpu updates watchdog threshold. What happens is while trying to park the watchdog threads, the hrtimers on the other cpus trigger and reprogram themselves with the new slower watchdog threshold. Meanwhile, the nmi watchdog is still programmed with the old faster threshold. Because the one cpu is blocked, it prevents the thread parking on the other cpus from completing, which is needed to shutdown the nmi watchdog and reprogram it correctly. As a result, a false positive from the nmi watchdog is reported. Fix this by setting a park_in_progress flag to block all lockups until the parking is complete. Fix provided by Ulrich Obergfell. [akpm@linux-foundation.org: s/park_in_progress/watchdog_park_in_progress/] Link: http://lkml.kernel.org/r/1481041033-192236-1-git-send-email-dzickus@redhat.com Signed-off-by: Don Zickus Reviewed-by: Aaron Tomlin Cc: Ulrich Obergfell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nmi.h | 1 + kernel/watchdog.c | 9 +++++++++ kernel/watchdog_hld.c | 3 +++ 3 files changed, 13 insertions(+) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index aacca824a6ae..0a3fadc32693 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -110,6 +110,7 @@ extern int watchdog_user_enabled; extern int watchdog_thresh; extern unsigned long watchdog_enabled; extern unsigned long *watchdog_cpumask_bits; +extern atomic_t watchdog_park_in_progress; #ifdef CONFIG_SMP extern int sysctl_softlockup_all_cpu_backtrace; extern int sysctl_hardlockup_all_cpu_backtrace; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index d4b0fa01cae3..63177be0159e 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -49,6 +49,8 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); #define for_each_watchdog_cpu(cpu) \ for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) +atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); + /* * The 'watchdog_running' variable is set to 1 when the watchdog threads * are registered/started and is set to 0 when the watchdog threads are @@ -260,6 +262,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; + if (atomic_read(&watchdog_park_in_progress) != 0) + return HRTIMER_NORESTART; + /* kick the hardlockup detector */ watchdog_interrupt_count(); @@ -467,12 +472,16 @@ static int watchdog_park_threads(void) { int cpu, ret = 0; + atomic_set(&watchdog_park_in_progress, 1); + for_each_watchdog_cpu(cpu) { ret = kthread_park(per_cpu(softlockup_watchdog, cpu)); if (ret) break; } + atomic_set(&watchdog_park_in_progress, 0); + return ret; } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 84016c8aee6b..12b8dd640786 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -84,6 +84,9 @@ static void watchdog_overflow_callback(struct perf_event *event, /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; + if (atomic_read(&watchdog_park_in_progress) != 0) + return; + if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; -- 2.39.5