diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 8efd2a8d9f10..6bc5113d3d74 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -154,7 +154,11 @@ static void lockup_detector_update_enable(void) #ifdef CONFIG_SOFTLOCKUP_DETECTOR -#define SOFTLOCKUP_RESET ULONG_MAX +/* + * Delay the soflockup report when running a known slow code. + * It does _not_ affect the timestamp of the last successdul reschedule. + */ +#define SOFTLOCKUP_DELAY_REPORT ULONG_MAX #ifdef CONFIG_SMP int __read_mostly sysctl_softlockup_all_cpu_backtrace; @@ -169,7 +173,10 @@ unsigned int __read_mostly softlockup_panic = static bool softlockup_initialized __read_mostly; static u64 __read_mostly sample_period; +/* Timestamp taken after the last successful reschedule. */ static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); +/* Timestamp of the last softlockup report. */ +static DEFINE_PER_CPU(unsigned long, watchdog_report_ts); static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static DEFINE_PER_CPU(bool, soft_watchdog_warn); @@ -235,10 +242,16 @@ static void set_sample_period(void) watchdog_update_hrtimer_threshold(sample_period); } +static void update_report_ts(void) +{ + __this_cpu_write(watchdog_report_ts, get_timestamp()); +} + /* Commands for resetting the watchdog */ static void update_touch_ts(void) { __this_cpu_write(watchdog_touch_ts, get_timestamp()); + update_report_ts(); } /** @@ -252,10 +265,10 @@ static void update_touch_ts(void) 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. + * Preemption can be enabled. It doesn't matter which CPU's watchdog + * report period gets restarted here, so use the raw_ operation. */ - raw_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET); + raw_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT); } notrace void touch_softlockup_watchdog(void) @@ -279,7 +292,7 @@ void touch_all_softlockup_watchdogs(void) * the softlockup check. */ for_each_cpu(cpu, &watchdog_allowed_mask) { - per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET; + per_cpu(watchdog_report_ts, cpu) = SOFTLOCKUP_DELAY_REPORT; wq_watchdog_touch(cpu); } } @@ -287,16 +300,16 @@ void touch_all_softlockup_watchdogs(void) void touch_softlockup_watchdog_sync(void) { __this_cpu_write(softlockup_touch_sync, true); - __this_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET); + __this_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT); } -static int is_softlockup(unsigned long touch_ts) +static int is_softlockup(unsigned long touch_ts, unsigned long period_ts) { unsigned long now = get_timestamp(); if ((watchdog_enabled & SOFT_WATCHDOG_ENABLED) && watchdog_thresh){ /* Warn about unreasonable delays. */ - if (time_after(now, touch_ts + get_softlockup_thresh())) + if (time_after(now, period_ts + get_softlockup_thresh())) return now - touch_ts; } return 0; @@ -342,6 +355,7 @@ static int softlockup_fn(void *data) static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts); + unsigned long period_ts = __this_cpu_read(watchdog_report_ts); struct pt_regs *regs = get_irq_regs(); int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; @@ -363,7 +377,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); - if (touch_ts == SOFTLOCKUP_RESET) { + /* Reset the interval when touched externally by a known slow code. */ + if (period_ts == SOFTLOCKUP_DELAY_REPORT) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { /* * If the time stamp was touched atomically @@ -375,7 +390,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) /* Clear the guest paused flag on watchdog reset */ kvm_check_and_clear_guest_paused(); - update_touch_ts(); + update_report_ts(); + return HRTIMER_RESTART; } @@ -385,7 +401,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) * indicate it is getting cpu time. If it hasn't then * this is a good indication some task is hogging the cpu */ - duration = is_softlockup(touch_ts); + duration = is_softlockup(touch_ts, period_ts); if (unlikely(duration)) { /* * If a virtual machine is stopped by the host it can look to @@ -411,7 +427,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) } /* Start period for the next softlockup warning. */ - update_touch_ts(); + update_report_ts(); pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration,