diff options
Diffstat (limited to 'kernel/watchdog.c')
| -rw-r--r-- | kernel/watchdog.c | 54 |
1 files changed, 51 insertions, 3 deletions
diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 1f1b05f5a94b..f2813e137b23 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -13,6 +13,7 @@ #include <linux/mm.h> #include <linux/cpu.h> +#include <linux/device.h> #include <linux/nmi.h> #include <linux/init.h> #include <linux/module.h> @@ -20,6 +21,7 @@ #include <linux/smpboot.h> #include <linux/sched/rt.h> #include <linux/tick.h> +#include <linux/workqueue.h> #include <asm/irq_regs.h> #include <linux/kvm_para.h> @@ -94,6 +96,7 @@ static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); +static DEFINE_PER_CPU(unsigned int, watchdog_en); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static DEFINE_PER_CPU(bool, soft_watchdog_warn); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); @@ -119,7 +122,9 @@ static unsigned long soft_lockup_nmi_warn; #ifdef CONFIG_HARDLOCKUP_DETECTOR unsigned int __read_mostly hardlockup_panic = CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; +#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI static unsigned long __maybe_unused hardlockup_allcpu_dumped; +#endif /* * We may not want to enable hard lockup detection by default in all cases, * for example when running the kernel as a guest on a hypervisor. In these @@ -230,7 +235,15 @@ static void __touch_watchdog(void) __this_cpu_write(watchdog_touch_ts, get_timestamp()); } -void touch_softlockup_watchdog(void) +/** + * touch_softlockup_watchdog_sched - touch watchdog on scheduler stalls + * + * Call when the scheduler may have stalled for legitimate reasons + * preventing the watchdog task from executing - e.g. the scheduler + * entering idle state. This should only be used for scheduler events. + * Use touch_softlockup_watchdog() for everything else. + */ +void touch_softlockup_watchdog_sched(void) { /* * Preemption can be enabled. It doesn't matter which CPU's timestamp @@ -238,6 +251,12 @@ void touch_softlockup_watchdog(void) */ raw_cpu_write(watchdog_touch_ts, 0); } + +void touch_softlockup_watchdog(void) +{ + touch_softlockup_watchdog_sched(); + wq_watchdog_touch(raw_smp_processor_id()); +} EXPORT_SYMBOL(touch_softlockup_watchdog); void touch_all_softlockup_watchdogs(void) @@ -251,6 +270,7 @@ void touch_all_softlockup_watchdogs(void) */ for_each_watchdog_cpu(cpu) per_cpu(watchdog_touch_ts, cpu) = 0; + wq_watchdog_touch(-1); } #ifdef CONFIG_HARDLOCKUP_DETECTOR @@ -568,9 +588,13 @@ static void watchdog_set_prio(unsigned int policy, unsigned int prio) sched_setscheduler(current, policy, ¶m); } -static void watchdog_enable(unsigned int cpu) +void watchdog_enable(unsigned int cpu) { struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + unsigned int *enabled = raw_cpu_ptr(&watchdog_en); + + if (*enabled) + return; /* kick off the timer for the hardlockup detector */ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); @@ -586,16 +610,40 @@ static void watchdog_enable(unsigned int cpu) /* initialize timestamp */ watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); __touch_watchdog(); + + /* + * Need to ensure above operations are observed by other CPUs before + * indicating that timer is enabled. This is to synchronize core + * isolation and hotplug. Core isolation will wait for this flag to be + * set. + */ + mb(); + *enabled = 1; } -static void watchdog_disable(unsigned int cpu) +void watchdog_disable(unsigned int cpu) { struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + unsigned int *enabled = raw_cpu_ptr(&watchdog_en); + + if (!*enabled) + return; watchdog_set_prio(SCHED_NORMAL, 0); hrtimer_cancel(hrtimer); /* disable the perf event */ watchdog_nmi_disable(cpu); + + /* + * No need for barrier here since disabling the watchdog is + * synchronized with hotplug lock + */ + *enabled = 0; +} + +bool watchdog_configured(unsigned int cpu) +{ + return *per_cpu_ptr(&watchdog_en, cpu); } static void watchdog_cleanup(unsigned int cpu, bool online) |