summaryrefslogtreecommitdiff
path: root/kernel/watchdog.c
diff options
context:
space:
mode:
authorColin Cross <ccross@android.com>2013-01-11 13:51:48 -0800
committerColin Cross <ccross@android.com>2014-03-19 13:09:45 -0700
commite43009fd646bb519fe5d5f0988c7e8c952dd658d (patch)
treec331f00c2692b4e404abf884b72abe311e15dbfd /kernel/watchdog.c
parentde091367ead15b6e95dd1d0743a18f0da5a07ee5 (diff)
hardlockup: detect hard lockups without NMIs using secondary cpus
Emulate NMIs on systems where they are not available by using timer interrupts on other cpus. Each cpu will use its softlockup hrtimer to check that the next cpu is processing hrtimer interrupts by verifying that a counter is increasing. This patch is useful on systems where the hardlockup detector is not available due to a lack of NMIs, for example most ARM SoCs. Without this patch any cpu stuck with interrupts disabled can cause a hardware watchdog reset with no debugging information, but with this patch the kernel can detect the lockup and panic, which can result in useful debugging info. Signed-off-by: Colin Cross <ccross@android.com>
Diffstat (limited to 'kernel/watchdog.c')
-rw-r--r--kernel/watchdog.c123
1 files changed, 118 insertions, 5 deletions
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 4431610f049a..68fbd3f169f1 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -45,6 +45,11 @@ static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt);
static DEFINE_PER_CPU(bool, hard_watchdog_warn);
static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
+#endif
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU
+static cpumask_t __read_mostly watchdog_cpus;
+#endif
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
#endif
@@ -178,7 +183,7 @@ void touch_softlockup_watchdog_sync(void)
__raw_get_cpu_var(watchdog_touch_ts) = 0;
}
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
/* watchdog detector functions */
static int is_hardlockup(void)
{
@@ -192,6 +197,76 @@ static int is_hardlockup(void)
}
#endif
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU
+static unsigned int watchdog_next_cpu(unsigned int cpu)
+{
+ cpumask_t cpus = watchdog_cpus;
+ unsigned int next_cpu;
+
+ next_cpu = cpumask_next(cpu, &cpus);
+ if (next_cpu >= nr_cpu_ids)
+ next_cpu = cpumask_first(&cpus);
+
+ if (next_cpu == cpu)
+ return nr_cpu_ids;
+
+ return next_cpu;
+}
+
+static int is_hardlockup_other_cpu(unsigned 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;
+}
+
+static void watchdog_check_hardlockup_other_cpu(void)
+{
+ unsigned int next_cpu;
+
+ /*
+ * Test for hardlockups every 3 samples. The sample period is
+ * watchdog_thresh * 2 / 5, so 3 samples gets us back to slightly over
+ * watchdog_thresh (over by 20%).
+ */
+ if (__this_cpu_read(hrtimer_interrupts) % 3 != 0)
+ return;
+
+ /* check for a hardlockup on the next cpu */
+ next_cpu = watchdog_next_cpu(smp_processor_id());
+ if (next_cpu >= nr_cpu_ids)
+ return;
+
+ smp_rmb();
+
+ if (per_cpu(watchdog_nmi_touch, next_cpu) == true) {
+ per_cpu(watchdog_nmi_touch, next_cpu) = false;
+ return;
+ }
+
+ if (is_hardlockup_other_cpu(next_cpu)) {
+ /* only warn once */
+ if (per_cpu(hard_watchdog_warn, next_cpu) == true)
+ return;
+
+ if (hardlockup_panic)
+ panic("Watchdog detected hard LOCKUP on cpu %u", next_cpu);
+ else
+ WARN(1, "Watchdog detected hard LOCKUP on cpu %u", next_cpu);
+
+ per_cpu(hard_watchdog_warn, next_cpu) = true;
+ } else {
+ per_cpu(hard_watchdog_warn, next_cpu) = false;
+ }
+}
+#else
+static inline void watchdog_check_hardlockup_other_cpu(void) { return; }
+#endif
+
static int is_softlockup(unsigned long touch_ts)
{
unsigned long now = get_timestamp();
@@ -203,7 +278,7 @@ static int is_softlockup(unsigned long touch_ts)
return 0;
}
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
static struct perf_event_attr wd_hw_attr = {
.type = PERF_TYPE_HARDWARE,
@@ -251,7 +326,7 @@ static void watchdog_overflow_callback(struct perf_event *event,
__this_cpu_write(hard_watchdog_warn, false);
return;
}
-#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR_NMI */
static void watchdog_interrupt_count(void)
{
@@ -271,6 +346,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
/* kick the hardlockup detector */
watchdog_interrupt_count();
+ /* test for hardlockups on the next cpu */
+ watchdog_check_hardlockup_other_cpu();
+
/* kick the softlockup detector */
wake_up_process(__this_cpu_read(softlockup_watchdog));
@@ -395,7 +473,7 @@ static void watchdog(unsigned int cpu)
__touch_watchdog();
}
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
/*
* People like the simple clean cpu node info on boot.
* Reduce the watchdog noise by only printing messages
@@ -471,9 +549,44 @@ static void watchdog_nmi_disable(unsigned int cpu)
return;
}
#else
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU
+static int watchdog_nmi_enable(unsigned int cpu)
+{
+ /*
+ * The new cpu will be marked online before the first hrtimer interrupt
+ * runs on it. If another cpu tests for a hardlockup on the new cpu
+ * before it has run its first hrtimer, it will get a false positive.
+ * Touch the watchdog on the new cpu to delay the first check for at
+ * least 3 sampling periods to guarantee one hrtimer has run on the new
+ * cpu.
+ */
+ per_cpu(watchdog_nmi_touch, cpu) = true;
+ smp_wmb();
+ cpumask_set_cpu(cpu, &watchdog_cpus);
+ return 0;
+}
+
+static void watchdog_nmi_disable(unsigned int cpu)
+{
+ unsigned int next_cpu = watchdog_next_cpu(cpu);
+
+ /*
+ * Offlining this cpu will cause the cpu before this one to start
+ * checking the one after this one. If this cpu just finished checking
+ * the next cpu and updating hrtimer_interrupts_saved, and then the
+ * previous cpu checks it within one sample period, it will trigger a
+ * false positive. Touch the watchdog on the next cpu to prevent it.
+ */
+ if (next_cpu < nr_cpu_ids)
+ per_cpu(watchdog_nmi_touch, next_cpu) = true;
+ smp_wmb();
+ cpumask_clear_cpu(cpu, &watchdog_cpus);
+}
+#else
static int watchdog_nmi_enable(unsigned int cpu) { return 0; }
static void watchdog_nmi_disable(unsigned int cpu) { return; }
-#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR_NMI */
static struct smp_hotplug_thread watchdog_threads = {
.store = &softlockup_watchdog,