lockup_detector: Combine nmi_watchdog and softlockup detector

The new nmi_watchdog (which uses the perf event subsystem) is very
similar in structure to the softlockup detector.  Using Ingo's
suggestion, I combined the two functionalities into one file:
kernel/watchdog.c.

Now both the nmi_watchdog (or hardlockup detector) and softlockup
detector sit on top of the perf event subsystem, which is run every
60 seconds or so to see if there are any lockups.

To detect hardlockups, cpus not responding to interrupts, I
implemented an hrtimer that runs 5 times for every perf event
overflow event.  If that stops counting on a cpu, then the cpu is
most likely in trouble.

To detect softlockups, tasks not yielding to the scheduler, I used the
previous kthread idea that now gets kicked every time the hrtimer fires.
If the kthread isn't being scheduled neither is anyone else and the
warning is printed to the console.

I tested this on x86_64 and both the softlockup and hardlockup paths
work.

V2:
- cleaned up the Kconfig and softlockup combination
- surrounded hardlockup cases with #ifdef CONFIG_PERF_EVENTS_NMI
- seperated out the softlockup case from perf event subsystem
- re-arranged the enabling/disabling nmi watchdog from proc space
- added cpumasks for hardlockup failure cases
- removed fallback to soft events if no PMU exists for hard events

V3:
- comment cleanups
- drop support for older softlockup code
- per_cpu cleanups
- completely remove software clock base hardlockup detector
- use per_cpu masking on hard/soft lockup detection
- #ifdef cleanups
- rename config option NMI_WATCHDOG to LOCKUP_DETECTOR
- documentation additions

V4:
- documentation fixes
- convert per_cpu to __get_cpu_var
- powerpc compile fixes

V5:
- split apart warn flags for hard and soft lockups

TODO:
- figure out how to make an arch-agnostic clock2cycles call
  (if possible) to feed into perf events as a sample period

[fweisbec: merged conflict patch]

Signed-off-by: Don Zickus <dzickus@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Eric Paris <eparis@redhat.com>
Cc: Randy Dunlap <randy.dunlap@oracle.com>
LKML-Reference: <1273266711-18706-2-git-send-email-dzickus@redhat.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>

1 files changed, 592 insertions, 0 deletions

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
new file mode 100644
index 000000000000..6b7fad8497af
--- /dev/null
+++ b/kernel/watchdog.c
@@ -0,0 +1,592 @@
+/*
+ * Detect hard and soft lockups on a system
+ *
+ * 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
+ * to those contributors as well.
+ */
+
+#include <linux/mm.h>
+#include <linux/cpu.h>
+#include <linux/nmi.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/freezer.h>
+#include <linux/kthread.h>
+#include <linux/lockdep.h>
+#include <linux/notifier.h>
+#include <linux/module.h>
+#include <linux/sysctl.h>
+
+#include <asm/irq_regs.h>
+#include <linux/perf_event.h>
+
+int watchdog_enabled;
+int __read_mostly softlockup_thresh = 60;
+
+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(bool, softlockup_touch_sync);
+static DEFINE_PER_CPU(bool, hard_watchdog_warn);
+static DEFINE_PER_CPU(bool, soft_watchdog_warn);
+#ifdef CONFIG_PERF_EVENTS_NMI
+static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
+static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
+static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
+#endif
+
+static int __read_mostly did_panic;
+static int __initdata no_watchdog;
+
+
+/* boot commands */
+/*
+ * Should we panic when a soft-lockup or hard-lockup occurs:
+ */
+#ifdef CONFIG_PERF_EVENTS_NMI
+static int hardlockup_panic;
+
+static int __init hardlockup_panic_setup(char *str)
+{
+        if (!strncmp(str, "panic", 5))
+                hardlockup_panic = 1;
+        return 1;
+}
+__setup("nmi_watchdog=", hardlockup_panic_setup);
+#endif
+
+unsigned int __read_mostly softlockup_panic =
+                        CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
+
+static int __init softlockup_panic_setup(char *str)
+{
+        softlockup_panic = simple_strtoul(str, NULL, 0);
+
+        return 1;
+}
+__setup("softlockup_panic=", softlockup_panic_setup);
+
+static int __init nowatchdog_setup(char *str)
+{
+        no_watchdog = 1;
+        return 1;
+}
+__setup("nowatchdog", nowatchdog_setup);
+
+/* deprecated */
+static int __init nosoftlockup_setup(char *str)
+{
+        no_watchdog = 1;
+        return 1;
+}
+__setup("nosoftlockup", nosoftlockup_setup);
+/*  */
+
+
+/*
+ * Returns seconds, approximately.  We don't need nanosecond
+ * resolution, and we don't need to waste time with a big divide when
+ * 2^30ns == 1.074s.
+ */
+static unsigned long get_timestamp(int this_cpu)
+{
+        return cpu_clock(this_cpu) >> 30LL;  /* 2^30 ~= 10^9 */
+}
+
+static unsigned long get_sample_period(void)
+{
+        /*
+         * convert softlockup_thresh from seconds to ns
+         * the divide by 5 is to give hrtimer 5 chances to
+         * increment before the hardlockup detector generates
+         * a warning
+         */
+        return softlockup_thresh / 5 * NSEC_PER_SEC;
+}
+
+/* Commands for resetting the watchdog */
+static void __touch_watchdog(void)
+{
+        int this_cpu = raw_smp_processor_id();
+
+        __get_cpu_var(watchdog_touch_ts) = get_timestamp(this_cpu);
+}
+
+void touch_watchdog(void)
+{
+        __get_cpu_var(watchdog_touch_ts) = 0;
+}
+EXPORT_SYMBOL(touch_watchdog);
+
+void touch_all_watchdog(void)
+{
+        int cpu;
+
+        /*
+         * this is done lockless
+         * do we care if a 0 races with a timestamp?
+         * all it means is the softlock check starts one cycle later
+         */
+        for_each_online_cpu(cpu)
+                per_cpu(watchdog_touch_ts, cpu) = 0;
+}
+
+void touch_nmi_watchdog(void)
+{
+        touch_watchdog();
+}
+EXPORT_SYMBOL(touch_nmi_watchdog);
+
+void touch_all_nmi_watchdog(void)
+{
+        touch_all_watchdog();
+}
+
+void touch_softlockup_watchdog(void)
+{
+        touch_watchdog();
+}
+
+void touch_all_softlockup_watchdogs(void)
+{
+        touch_all_watchdog();
+}
+
+void touch_softlockup_watchdog_sync(void)
+{
+        __raw_get_cpu_var(softlockup_touch_sync) = true;
+        __raw_get_cpu_var(watchdog_touch_ts) = 0;
+}
+
+void softlockup_tick(void)
+{
+}
+
+#ifdef CONFIG_PERF_EVENTS_NMI
+/* watchdog detector functions */
+static int is_hardlockup(int cpu)
+{
+        unsigned long hrint = per_cpu(hrtimer_interrupts, cpu);
+
+        if (per_cpu(hrtimer_interrupts_saved, cpu) == hrint)
+                return 1;
+
+        per_cpu(hrtimer_interrupts_saved, cpu) = hrint;
+        return 0;
+}
+#endif
+
+static int is_softlockup(unsigned long touch_ts, int cpu)
+{
+        unsigned long now = get_timestamp(cpu);
+
+        /* Warn about unreasonable delays: */
+        if (time_after(now, touch_ts + softlockup_thresh))
+                return now - touch_ts;
+
+        return 0;
+}
+
+static int
+watchdog_panic(struct notifier_block *this, unsigned long event, void *ptr)
+{
+        did_panic = 1;
+
+        return NOTIFY_DONE;
+}
+
+static struct notifier_block panic_block = {
+        .notifier_call = watchdog_panic,
+};
+
+#ifdef CONFIG_PERF_EVENTS_NMI
+static struct perf_event_attr wd_hw_attr = {
+        .type           = PERF_TYPE_HARDWARE,
+        .config         = PERF_COUNT_HW_CPU_CYCLES,
+        .size           = sizeof(struct perf_event_attr),
+        .pinned         = 1,
+        .disabled       = 1,
+};
+
+/* Callback function for perf event subsystem */
+void watchdog_overflow_callback(struct perf_event *event, int nmi,
+                 struct perf_sample_data *data,
+                 struct pt_regs *regs)
+{
+        int this_cpu = smp_processor_id();
+        unsigned long touch_ts = per_cpu(watchdog_touch_ts, this_cpu);
+
+        if (touch_ts == 0) {
+                __touch_watchdog();
+                return;
+        }
+
+        /* check for a hardlockup
+         * This is done by making sure our timer interrupt
+         * is incrementing.  The timer interrupt should have
+         * fired multiple times before we overflow'd.  If it hasn't
+         * then this is a good indication the cpu is stuck
+         */
+        if (is_hardlockup(this_cpu)) {
+                /* only print hardlockups once */
+                if (__get_cpu_var(hard_watchdog_warn) == true)
+                        return;
+
+                if (hardlockup_panic)
+                        panic("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
+                else
+                        WARN(1, "Watchdog detected hard LOCKUP on cpu %d", this_cpu);
+
+                __get_cpu_var(hard_watchdog_warn) = true;
+                return;
+        }
+
+        __get_cpu_var(hard_watchdog_warn) = false;
+        return;
+}
+static void watchdog_interrupt_count(void)
+{
+        __get_cpu_var(hrtimer_interrupts)++;
+}
+#else
+static inline void watchdog_interrupt_count(void) { return; }
+#endif /* CONFIG_PERF_EVENTS_NMI */
+
+/* watchdog kicker functions */
+static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
+{
+        int this_cpu = smp_processor_id();
+        unsigned long touch_ts = __get_cpu_var(watchdog_touch_ts);
+        struct pt_regs *regs = get_irq_regs();
+        int duration;
+
+        /* kick the hardlockup detector */
+        watchdog_interrupt_count();
+
+        /* kick the softlockup detector */
+        wake_up_process(__get_cpu_var(softlockup_watchdog));
+
+        /* .. and repeat */
+        hrtimer_forward_now(hrtimer, ns_to_ktime(get_sample_period()));
+
+        if (touch_ts == 0) {
+                if (unlikely(per_cpu(softlockup_touch_sync, this_cpu))) {
+                        /*
+                         * If the time stamp was touched atomically
+                         * make sure the scheduler tick is up to date.
+                         */
+                        per_cpu(softlockup_touch_sync, this_cpu) = false;
+                        sched_clock_tick();
+                }
+                __touch_watchdog();
+                return HRTIMER_RESTART;
+        }
+
+        /* check for a softlockup
+         * This is done by making sure a high priority task is
+         * being scheduled.  The task touches the watchdog to
+         * 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, this_cpu);
+        if (unlikely(duration)) {
+                /* only warn once */
+                if (__get_cpu_var(soft_watchdog_warn) == true)
+                        return HRTIMER_RESTART;
+
+                printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
+                        this_cpu, duration,
+                        current->comm, task_pid_nr(current));
+                print_modules();
+                print_irqtrace_events(current);
+                if (regs)
+                        show_regs(regs);
+                else
+                        dump_stack();
+
+                if (softlockup_panic)
+                        panic("softlockup: hung tasks");
+                __get_cpu_var(soft_watchdog_warn) = true;
+        } else
+                __get_cpu_var(soft_watchdog_warn) = false;
+
+        return HRTIMER_RESTART;
+}
+
+
+/*
+ * The watchdog thread - touches the timestamp.
+ */
+static int watchdog(void *__bind_cpu)
+{
+        struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+        struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, (unsigned long)__bind_cpu);
+
+        sched_setscheduler(current, SCHED_FIFO, &param);
+
+        /* initialize timestamp */
+        __touch_watchdog();
+
+        /* kick off the timer for the hardlockup detector */
+        /* done here because hrtimer_start can only pin to smp_processor_id() */
+        hrtimer_start(hrtimer, ns_to_ktime(get_sample_period()),
+                      HRTIMER_MODE_REL_PINNED);
+
+        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 softlockup_tick().
+         */
+        while (!kthread_should_stop()) {
+                __touch_watchdog();
+                schedule();
+
+                if (kthread_should_stop())
+                        break;
+
+                set_current_state(TASK_INTERRUPTIBLE);
+        }
+        __set_current_state(TASK_RUNNING);
+
+        return 0;
+}
+
+
+#ifdef CONFIG_PERF_EVENTS_NMI
+static int watchdog_nmi_enable(int cpu)
+{
+        struct perf_event_attr *wd_attr;
+        struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+        /* is it already setup and enabled? */
+        if (event && event->state > PERF_EVENT_STATE_OFF)
+                goto out;
+
+        /* it is setup but not enabled */
+        if (event != NULL)
+                goto out_enable;
+
+        /* Try to register using hardware perf events */
+        wd_attr = &wd_hw_attr;
+        wd_attr->sample_period = hw_nmi_get_sample_period();
+        event = perf_event_create_kernel_counter(wd_attr, cpu, -1, watchdog_overflow_callback);
+        if (!IS_ERR(event)) {
+                printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n");
+                goto out_save;
+        }
+
+        printk(KERN_ERR "NMI watchdog failed to create perf event on cpu%i: %p\n", cpu, event);
+        return -1;
+
+        /* success path */
+out_save:
+        per_cpu(watchdog_ev, cpu) = event;
+out_enable:
+        perf_event_enable(per_cpu(watchdog_ev, cpu));
+out:
+        return 0;
+}
+
+static void watchdog_nmi_disable(int cpu)
+{
+        struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+        if (event) {
+                perf_event_disable(event);
+                per_cpu(watchdog_ev, cpu) = NULL;
+
+                /* should be in cleanup, but blocks oprofile */
+                perf_event_release_kernel(event);
+        }
+        return;
+}
+#else
+static int watchdog_nmi_enable(int cpu) { return 0; }
+static void watchdog_nmi_disable(int cpu) { return; }
+#endif /* CONFIG_PERF_EVENTS_NMI */
+
+/* prepare/enable/disable routines */
+static int watchdog_prepare_cpu(int cpu)
+{
+        struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu);
+
+        WARN_ON(per_cpu(softlockup_watchdog, cpu));
+        hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+        hrtimer->function = watchdog_timer_fn;
+
+        return 0;
+}
+
+static int watchdog_enable(int cpu)
+{
+        struct task_struct *p = per_cpu(softlockup_watchdog, cpu);
+
+        /* enable the perf event */
+        if (watchdog_nmi_enable(cpu) != 0)
+                return -1;
+
+        /* create the watchdog thread */
+        if (!p) {
+                p = kthread_create(watchdog, (void *)(unsigned long)cpu, "watchdog/%d", cpu);
+                if (IS_ERR(p)) {
+                        printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu);
+                        return -1;
+                }
+                kthread_bind(p, cpu);
+                per_cpu(watchdog_touch_ts, cpu) = 0;
+                per_cpu(softlockup_watchdog, cpu) = p;
+                wake_up_process(p);
+        }
+
+        return 0;
+}
+
+static void watchdog_disable(int cpu)
+{
+        struct task_struct *p = per_cpu(softlockup_watchdog, cpu);
+        struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu);
+
+        /*
+         * cancel the timer first to stop incrementing the stats
+         * and waking up the kthread
+         */
+        hrtimer_cancel(hrtimer);
+
+        /* disable the perf event */
+        watchdog_nmi_disable(cpu);
+
+        /* stop the watchdog thread */
+        if (p) {
+                per_cpu(softlockup_watchdog, cpu) = NULL;
+                kthread_stop(p);
+        }
+
+        /* if any cpu succeeds, watchdog is considered enabled for the system */
+        watchdog_enabled = 1;
+}
+
+static void watchdog_enable_all_cpus(void)
+{
+        int cpu;
+        int result;
+
+        for_each_online_cpu(cpu)
+                result += watchdog_enable(cpu);
+
+        if (result)
+                printk(KERN_ERR "watchdog: failed to be enabled on some cpus\n");
+
+}
+
+static void watchdog_disable_all_cpus(void)
+{
+        int cpu;
+
+        for_each_online_cpu(cpu)
+                watchdog_disable(cpu);
+
+        /* if all watchdogs are disabled, then they are disabled for the system */
+        watchdog_enabled = 0;
+}
+
+
+/* sysctl functions */
+#ifdef CONFIG_SYSCTL
+/*
+ * proc handler for /proc/sys/kernel/nmi_watchdog
+ */
+
+int proc_dowatchdog_enabled(struct ctl_table *table, int write,
+                     void __user *buffer, size_t *length, loff_t *ppos)
+{
+        proc_dointvec(table, write, buffer, length, ppos);
+
+        if (watchdog_enabled)
+                watchdog_enable_all_cpus();
+        else
+                watchdog_disable_all_cpus();
+        return 0;
+}
+
+int proc_dowatchdog_thresh(struct ctl_table *table, int write,
+                             void __user *buffer,
+                             size_t *lenp, loff_t *ppos)
+{
+        return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+}
+
+/* stub functions */
+int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
+                             void __user *buffer,
+                             size_t *lenp, loff_t *ppos)
+{
+        return proc_dowatchdog_thresh(table, write, buffer, lenp, ppos);
+}
+/* end of stub functions */
+#endif /* CONFIG_SYSCTL */
+
+
+/*
+ * Create/destroy watchdog threads as CPUs come and go:
+ */
+static int __cpuinit
+cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
+{
+        int hotcpu = (unsigned long)hcpu;
+
+        switch (action) {
+        case CPU_UP_PREPARE:
+        case CPU_UP_PREPARE_FROZEN:
+                if (watchdog_prepare_cpu(hotcpu))
+                        return NOTIFY_BAD;
+                break;
+        case CPU_ONLINE:
+        case CPU_ONLINE_FROZEN:
+                if (watchdog_enable(hotcpu))
+                        return NOTIFY_BAD;
+                break;
+#ifdef CONFIG_HOTPLUG_CPU
+        case CPU_UP_CANCELED:
+        case CPU_UP_CANCELED_FROZEN:
+                watchdog_disable(hotcpu);
+                break;
+        case CPU_DEAD:
+        case CPU_DEAD_FROZEN:
+                watchdog_disable(hotcpu);
+                break;
+#endif /* CONFIG_HOTPLUG_CPU */
+        }
+        return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata cpu_nfb = {
+        .notifier_call = cpu_callback
+};
+
+static int __init spawn_watchdog_task(void)
+{
+        void *cpu = (void *)(long)smp_processor_id();
+        int err;
+
+        if (no_watchdog)
+                return 0;
+
+        err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+        WARN_ON(err == NOTIFY_BAD);
+
+        cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
+        register_cpu_notifier(&cpu_nfb);
+
+        atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
+
+        return 0;
+}
+early_initcall(spawn_watchdog_task);