diff options
Diffstat (limited to 'kernel/watchdog.c')
| -rw-r--r-- | kernel/watchdog.c | 53 |
1 files changed, 30 insertions, 23 deletions
diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 1d7bca7f4f5..df30ee08bdd 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -3,15 +3,14 @@ * * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. * - * this code detects hard lockups: incidents in where on a CPU - * the kernel does not respond to anything except NMI. - * - * Note: Most of this code is borrowed heavily from softlockup.c, - * so thanks to Ingo for the initial implementation. - * Some chunks also taken from arch/x86/kernel/apic/nmi.c, thanks + * Note: Most of this code is borrowed heavily from the original softlockup + * detector, so thanks to Ingo for the initial implementation. + * Some chunks also taken from the old x86-specific nmi watchdog code, thanks * to those contributors as well. */ +#define pr_fmt(fmt) "NMI watchdog: " fmt + #include <linux/mm.h> #include <linux/cpu.h> #include <linux/nmi.h> @@ -117,9 +116,10 @@ static unsigned long get_sample_period(void) { /* * convert watchdog_thresh from seconds to ns - * the divide by 5 is to give hrtimer 5 chances to - * increment before the hardlockup detector generates - * a warning + * the divide by 5 is to give hrtimer several chances (two + * or three with the current relation between the soft + * and hard thresholds) to increment before the + * hardlockup detector generates a warning */ return get_softlockup_thresh() * (NSEC_PER_SEC / 5); } @@ -296,7 +296,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) if (__this_cpu_read(soft_watchdog_warn) == true) return HRTIMER_RESTART; - printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", + printk(KERN_EMERG "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); print_modules(); @@ -321,11 +321,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) */ static int watchdog(void *unused) { - struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; + struct sched_param param = { .sched_priority = 0 }; struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); - sched_setscheduler(current, SCHED_FIFO, ¶m); - /* initialize timestamp */ __touch_watchdog(); @@ -336,9 +334,11 @@ static int watchdog(void *unused) set_current_state(TASK_INTERRUPTIBLE); /* - * Run briefly once per second to reset the softlockup timestamp. - * If this gets delayed for more than 60 seconds then the - * debug-printout triggers in watchdog_timer_fn(). + * Run briefly (kicked by the hrtimer callback function) once every + * get_sample_period() seconds (4 seconds by default) to reset the + * softlockup timestamp. If this gets delayed for more than + * 2*watchdog_thresh seconds then the debug-printout triggers in + * watchdog_timer_fn(). */ while (!kthread_should_stop()) { __touch_watchdog(); @@ -349,8 +349,11 @@ static int watchdog(void *unused) set_current_state(TASK_INTERRUPTIBLE); } + /* + * Drop the policy/priority elevation during thread exit to avoid a + * scheduling latency spike. + */ __set_current_state(TASK_RUNNING); - param.sched_priority = 0; sched_setscheduler(current, SCHED_NORMAL, ¶m); return 0; } @@ -376,18 +379,20 @@ static int watchdog_nmi_enable(int cpu) /* Try to register using hardware perf events */ event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); if (!IS_ERR(event)) { - printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n"); + pr_info("enabled, takes one hw-pmu counter.\n"); goto out_save; } /* vary the KERN level based on the returned errno */ if (PTR_ERR(event) == -EOPNOTSUPP) - printk(KERN_INFO "NMI watchdog disabled (cpu%i): not supported (no LAPIC?)\n", cpu); + pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu); else if (PTR_ERR(event) == -ENOENT) - printk(KERN_WARNING "NMI watchdog disabled (cpu%i): hardware events not enabled\n", cpu); + pr_warning("disabled (cpu%i): hardware events not enabled\n", + cpu); else - printk(KERN_ERR "NMI watchdog disabled (cpu%i): unable to create perf event: %ld\n", cpu, PTR_ERR(event)); + pr_err("disabled (cpu%i): unable to create perf event: %ld\n", + cpu, PTR_ERR(event)); return PTR_ERR(event); /* success path */ @@ -439,9 +444,10 @@ static int watchdog_enable(int cpu) /* create the watchdog thread */ if (!p) { + struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; p = kthread_create_on_node(watchdog, NULL, cpu_to_node(cpu), "watchdog/%d", cpu); if (IS_ERR(p)) { - printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu); + pr_err("softlockup watchdog for %i failed\n", cpu); if (!err) { /* if hardlockup hasn't already set this */ err = PTR_ERR(p); @@ -450,6 +456,7 @@ static int watchdog_enable(int cpu) } goto out; } + sched_setscheduler(p, SCHED_FIFO, ¶m); kthread_bind(p, cpu); per_cpu(watchdog_touch_ts, cpu) = 0; per_cpu(softlockup_watchdog, cpu) = p; @@ -496,7 +503,7 @@ static void watchdog_enable_all_cpus(void) watchdog_enabled = 1; if (!watchdog_enabled) - printk(KERN_ERR "watchdog: failed to be enabled on some cpus\n"); + pr_err("failed to be enabled on some cpus\n"); } |