1 files changed, 257 insertions, 99 deletions

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 8e61f21e7e33..be38276a365f 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -29,20 +29,18 @@
 
 static DEFINE_MUTEX(watchdog_mutex);
 
-#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG)
-# define WATCHDOG_DEFAULT	(SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED)
-# define NMI_WATCHDOG_DEFAULT	1
+#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HARDLOCKUP_DETECTOR_SPARC64)
+# define WATCHDOG_HARDLOCKUP_DEFAULT	1
 #else
-# define WATCHDOG_DEFAULT	(SOFT_WATCHDOG_ENABLED)
-# define NMI_WATCHDOG_DEFAULT	0
+# define WATCHDOG_HARDLOCKUP_DEFAULT	0
 #endif
 
 unsigned long __read_mostly watchdog_enabled;
 int __read_mostly watchdog_user_enabled = 1;
-int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT;
-int __read_mostly soft_watchdog_user_enabled = 1;
+static int __read_mostly watchdog_hardlockup_user_enabled = WATCHDOG_HARDLOCKUP_DEFAULT;
+static int __read_mostly watchdog_softlockup_user_enabled = 1;
 int __read_mostly watchdog_thresh = 10;
-static int __read_mostly nmi_watchdog_available;
+static int __read_mostly watchdog_hardlockup_available;
 
 struct cpumask watchdog_cpumask __read_mostly;
 unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
@@ -68,7 +66,7 @@ unsigned int __read_mostly hardlockup_panic =
  */
 void __init hardlockup_detector_disable(void)
 {
-	nmi_watchdog_user_enabled = 0;
+	watchdog_hardlockup_user_enabled = 0;
 }
 
 static int __init hardlockup_panic_setup(char *str)
@@ -78,54 +76,163 @@ static int __init hardlockup_panic_setup(char *str)
 	else if (!strncmp(str, "nopanic", 7))
 		hardlockup_panic = 0;
 	else if (!strncmp(str, "0", 1))
-		nmi_watchdog_user_enabled = 0;
+		watchdog_hardlockup_user_enabled = 0;
 	else if (!strncmp(str, "1", 1))
-		nmi_watchdog_user_enabled = 1;
+		watchdog_hardlockup_user_enabled = 1;
 	return 1;
 }
 __setup("nmi_watchdog=", hardlockup_panic_setup);
 
 #endif /* CONFIG_HARDLOCKUP_DETECTOR */
 
-/*
- * These functions can be overridden if an architecture implements its
- * own hardlockup detector.
- *
- * watchdog_nmi_enable/disable can be implemented to start and stop when
- * softlockup watchdog start and stop. The arch must select the
- * SOFTLOCKUP_DETECTOR Kconfig.
- */
-int __weak watchdog_nmi_enable(unsigned int cpu)
+#if defined(CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER)
+
+static DEFINE_PER_CPU(atomic_t, hrtimer_interrupts);
+static DEFINE_PER_CPU(int, hrtimer_interrupts_saved);
+static DEFINE_PER_CPU(bool, watchdog_hardlockup_warned);
+static DEFINE_PER_CPU(bool, watchdog_hardlockup_touched);
+static unsigned long watchdog_hardlockup_all_cpu_dumped;
+
+notrace void arch_touch_nmi_watchdog(void)
 {
-	hardlockup_detector_perf_enable();
-	return 0;
+	/*
+	 * Using __raw here because some code paths have
+	 * preemption enabled.  If preemption is enabled
+	 * then interrupts should be enabled too, in which
+	 * case we shouldn't have to worry about the watchdog
+	 * going off.
+	 */
+	raw_cpu_write(watchdog_hardlockup_touched, true);
+}
+EXPORT_SYMBOL(arch_touch_nmi_watchdog);
+
+void watchdog_hardlockup_touch_cpu(unsigned int cpu)
+{
+	per_cpu(watchdog_hardlockup_touched, cpu) = true;
 }
 
-void __weak watchdog_nmi_disable(unsigned int cpu)
+static bool is_hardlockup(unsigned int cpu)
 {
-	hardlockup_detector_perf_disable();
+	int hrint = atomic_read(&per_cpu(hrtimer_interrupts, cpu));
+
+	if (per_cpu(hrtimer_interrupts_saved, cpu) == hrint)
+		return true;
+
+	/*
+	 * NOTE: we don't need any fancy atomic_t or READ_ONCE/WRITE_ONCE
+	 * for hrtimer_interrupts_saved. hrtimer_interrupts_saved is
+	 * written/read by a single CPU.
+	 */
+	per_cpu(hrtimer_interrupts_saved, cpu) = hrint;
+
+	return false;
 }
 
-/* Return 0, if a NMI watchdog is available. Error code otherwise */
-int __weak __init watchdog_nmi_probe(void)
+static void watchdog_hardlockup_kick(void)
 {
-	return hardlockup_detector_perf_init();
+	int new_interrupts;
+
+	new_interrupts = atomic_inc_return(this_cpu_ptr(&hrtimer_interrupts));
+	watchdog_buddy_check_hardlockup(new_interrupts);
+}
+
+void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
+{
+	if (per_cpu(watchdog_hardlockup_touched, cpu)) {
+		per_cpu(watchdog_hardlockup_touched, cpu) = false;
+		return;
+	}
+
+	/*
+	 * Check for a hardlockup by making sure the CPU's 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(cpu)) {
+		unsigned int this_cpu = smp_processor_id();
+		struct cpumask backtrace_mask;
+
+		cpumask_copy(&backtrace_mask, cpu_online_mask);
+
+		/* Only print hardlockups once. */
+		if (per_cpu(watchdog_hardlockup_warned, cpu))
+			return;
+
+		pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", cpu);
+		print_modules();
+		print_irqtrace_events(current);
+		if (cpu == this_cpu) {
+			if (regs)
+				show_regs(regs);
+			else
+				dump_stack();
+			cpumask_clear_cpu(cpu, &backtrace_mask);
+		} else {
+			if (trigger_single_cpu_backtrace(cpu))
+				cpumask_clear_cpu(cpu, &backtrace_mask);
+		}
+
+		/*
+		 * Perform multi-CPU dump only once to avoid multiple
+		 * hardlockups generating interleaving traces
+		 */
+		if (sysctl_hardlockup_all_cpu_backtrace &&
+		    !test_and_set_bit(0, &watchdog_hardlockup_all_cpu_dumped))
+			trigger_cpumask_backtrace(&backtrace_mask);
+
+		if (hardlockup_panic)
+			nmi_panic(regs, "Hard LOCKUP");
+
+		per_cpu(watchdog_hardlockup_warned, cpu) = true;
+	} else {
+		per_cpu(watchdog_hardlockup_warned, cpu) = false;
+	}
+}
+
+#else /* CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER */
+
+static inline void watchdog_hardlockup_kick(void) { }
+
+#endif /* !CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER */
+
+/*
+ * These functions can be overridden based on the configured hardlockdup detector.
+ *
+ * watchdog_hardlockup_enable/disable can be implemented to start and stop when
+ * softlockup watchdog start and stop. The detector must select the
+ * SOFTLOCKUP_DETECTOR Kconfig.
+ */
+void __weak watchdog_hardlockup_enable(unsigned int cpu) { }
+
+void __weak watchdog_hardlockup_disable(unsigned int cpu) { }
+
+/*
+ * Watchdog-detector specific API.
+ *
+ * Return 0 when hardlockup watchdog is available, negative value otherwise.
+ * Note that the negative value means that a delayed probe might
+ * succeed later.
+ */
+int __weak __init watchdog_hardlockup_probe(void)
+{
+	return -ENODEV;
 }
 
 /**
- * watchdog_nmi_stop - Stop the watchdog for reconfiguration
+ * watchdog_hardlockup_stop - Stop the watchdog for reconfiguration
  *
  * The reconfiguration steps are:
- * watchdog_nmi_stop();
+ * watchdog_hardlockup_stop();
  * update_variables();
- * watchdog_nmi_start();
+ * watchdog_hardlockup_start();
  */
-void __weak watchdog_nmi_stop(void) { }
+void __weak watchdog_hardlockup_stop(void) { }
 
 /**
- * watchdog_nmi_start - Start the watchdog after reconfiguration
+ * watchdog_hardlockup_start - Start the watchdog after reconfiguration
  *
- * Counterpart to watchdog_nmi_stop().
+ * Counterpart to watchdog_hardlockup_stop().
  *
  * The following variables have been updated in update_variables() and
  * contain the currently valid configuration:
@@ -133,23 +240,23 @@ void __weak watchdog_nmi_stop(void) { }
  * - watchdog_thresh
  * - watchdog_cpumask
  */
-void __weak watchdog_nmi_start(void) { }
+void __weak watchdog_hardlockup_start(void) { }
 
 /**
  * lockup_detector_update_enable - Update the sysctl enable bit
  *
- * Caller needs to make sure that the NMI/perf watchdogs are off, so this
- * can't race with watchdog_nmi_disable().
+ * Caller needs to make sure that the hard watchdogs are off, so this
+ * can't race with watchdog_hardlockup_disable().
  */
 static void lockup_detector_update_enable(void)
 {
 	watchdog_enabled = 0;
 	if (!watchdog_user_enabled)
 		return;
-	if (nmi_watchdog_available && nmi_watchdog_user_enabled)
-		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
-	if (soft_watchdog_user_enabled)
-		watchdog_enabled |= SOFT_WATCHDOG_ENABLED;
+	if (watchdog_hardlockup_available && watchdog_hardlockup_user_enabled)
+		watchdog_enabled |= WATCHDOG_HARDLOCKUP_ENABLED;
+	if (watchdog_softlockup_user_enabled)
+		watchdog_enabled |= WATCHDOG_SOFTOCKUP_ENABLED;
 }
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
@@ -179,8 +286,6 @@ static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
 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(unsigned long, hrtimer_interrupts);
-static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static unsigned long soft_lockup_nmi_warn;
 
 static int __init nowatchdog_setup(char *str)
@@ -192,7 +297,7 @@ __setup("nowatchdog", nowatchdog_setup);
 
 static int __init nosoftlockup_setup(char *str)
 {
-	soft_watchdog_user_enabled = 0;
+	watchdog_softlockup_user_enabled = 0;
 	return 1;
 }
 __setup("nosoftlockup", nosoftlockup_setup);
@@ -306,7 +411,7 @@ static int is_softlockup(unsigned long touch_ts,
 			 unsigned long period_ts,
 			 unsigned long now)
 {
-	if ((watchdog_enabled & SOFT_WATCHDOG_ENABLED) && watchdog_thresh){
+	if ((watchdog_enabled & WATCHDOG_SOFTOCKUP_ENABLED) && watchdog_thresh) {
 		/* Warn about unreasonable delays. */
 		if (time_after(now, period_ts + get_softlockup_thresh()))
 			return now - touch_ts;
@@ -315,22 +420,6 @@ static int is_softlockup(unsigned long touch_ts,
 }
 
 /* watchdog detector functions */
-bool is_hardlockup(void)
-{
-	unsigned long hrint = __this_cpu_read(hrtimer_interrupts);
-
-	if (__this_cpu_read(hrtimer_interrupts_saved) == hrint)
-		return true;
-
-	__this_cpu_write(hrtimer_interrupts_saved, hrint);
-	return false;
-}
-
-static void watchdog_interrupt_count(void)
-{
-	__this_cpu_inc(hrtimer_interrupts);
-}
-
 static DEFINE_PER_CPU(struct completion, softlockup_completion);
 static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
 
@@ -361,8 +450,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	if (!watchdog_enabled)
 		return HRTIMER_NORESTART;
 
-	/* kick the hardlockup detector */
-	watchdog_interrupt_count();
+	watchdog_hardlockup_kick();
 
 	/* kick the softlockup detector */
 	if (completion_done(this_cpu_ptr(&softlockup_completion))) {
@@ -458,7 +546,7 @@ static void watchdog_enable(unsigned int cpu)
 	complete(done);
 
 	/*
-	 * Start the timer first to prevent the NMI watchdog triggering
+	 * Start the timer first to prevent the hardlockup watchdog triggering
 	 * before the timer has a chance to fire.
 	 */
 	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
@@ -468,9 +556,9 @@ static void watchdog_enable(unsigned int cpu)
 
 	/* Initialize timestamp */
 	update_touch_ts();
-	/* Enable the perf event */
-	if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
-		watchdog_nmi_enable(cpu);
+	/* Enable the hardlockup detector */
+	if (watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED)
+		watchdog_hardlockup_enable(cpu);
 }
 
 static void watchdog_disable(unsigned int cpu)
@@ -480,11 +568,11 @@ static void watchdog_disable(unsigned int cpu)
 	WARN_ON_ONCE(cpu != smp_processor_id());
 
 	/*
-	 * Disable the perf event first. That prevents that a large delay
-	 * between disabling the timer and disabling the perf event causes
-	 * the perf NMI to detect a false positive.
+	 * Disable the hardlockup detector first. That prevents that a large
+	 * delay between disabling the timer and disabling the hardlockup
+	 * detector causes a false positive.
 	 */
-	watchdog_nmi_disable(cpu);
+	watchdog_hardlockup_disable(cpu);
 	hrtimer_cancel(hrtimer);
 	wait_for_completion(this_cpu_ptr(&softlockup_completion));
 }
@@ -540,7 +628,7 @@ int lockup_detector_offline_cpu(unsigned int cpu)
 static void __lockup_detector_reconfigure(void)
 {
 	cpus_read_lock();
-	watchdog_nmi_stop();
+	watchdog_hardlockup_stop();
 
 	softlockup_stop_all();
 	set_sample_period();
@@ -548,7 +636,7 @@ static void __lockup_detector_reconfigure(void)
 	if (watchdog_enabled && watchdog_thresh)
 		softlockup_start_all();
 
-	watchdog_nmi_start();
+	watchdog_hardlockup_start();
 	cpus_read_unlock();
 	/*
 	 * Must be called outside the cpus locked section to prevent
@@ -589,9 +677,9 @@ static __init void lockup_detector_setup(void)
 static void __lockup_detector_reconfigure(void)
 {
 	cpus_read_lock();
-	watchdog_nmi_stop();
+	watchdog_hardlockup_stop();
 	lockup_detector_update_enable();
-	watchdog_nmi_start();
+	watchdog_hardlockup_start();
 	cpus_read_unlock();
 }
 void lockup_detector_reconfigure(void)
@@ -646,14 +734,14 @@ static void proc_watchdog_update(void)
 /*
  * common function for watchdog, nmi_watchdog and soft_watchdog parameter
  *
- * caller             | table->data points to      | 'which'
- * -------------------|----------------------------|--------------------------
- * proc_watchdog      | watchdog_user_enabled      | NMI_WATCHDOG_ENABLED |
- *                    |                            | SOFT_WATCHDOG_ENABLED
- * -------------------|----------------------------|--------------------------
- * proc_nmi_watchdog  | nmi_watchdog_user_enabled  | NMI_WATCHDOG_ENABLED
- * -------------------|----------------------------|--------------------------
- * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED
+ * caller             | table->data points to            | 'which'
+ * -------------------|----------------------------------|-------------------------------
+ * proc_watchdog      | watchdog_user_enabled            | WATCHDOG_HARDLOCKUP_ENABLED |
+ *                    |                                  | WATCHDOG_SOFTOCKUP_ENABLED
+ * -------------------|----------------------------------|-------------------------------
+ * proc_nmi_watchdog  | watchdog_hardlockup_user_enabled | WATCHDOG_HARDLOCKUP_ENABLED
+ * -------------------|----------------------------------|-------------------------------
+ * proc_soft_watchdog | watchdog_softlockup_user_enabled | WATCHDOG_SOFTOCKUP_ENABLED
  */
 static int proc_watchdog_common(int which, struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
@@ -685,7 +773,8 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write,
 int proc_watchdog(struct ctl_table *table, int write,
 		  void *buffer, size_t *lenp, loff_t *ppos)
 {
-	return proc_watchdog_common(NMI_WATCHDOG_ENABLED|SOFT_WATCHDOG_ENABLED,
+	return proc_watchdog_common(WATCHDOG_HARDLOCKUP_ENABLED |
+				    WATCHDOG_SOFTOCKUP_ENABLED,
 				    table, write, buffer, lenp, ppos);
 }
 
@@ -695,9 +784,9 @@ int proc_watchdog(struct ctl_table *table, int write,
 int proc_nmi_watchdog(struct ctl_table *table, int write,
 		      void *buffer, size_t *lenp, loff_t *ppos)
 {
-	if (!nmi_watchdog_available && write)
+	if (!watchdog_hardlockup_available && write)
 		return -ENOTSUPP;
-	return proc_watchdog_common(NMI_WATCHDOG_ENABLED,
+	return proc_watchdog_common(WATCHDOG_HARDLOCKUP_ENABLED,
 				    table, write, buffer, lenp, ppos);
 }
 
@@ -707,7 +796,7 @@ int proc_nmi_watchdog(struct ctl_table *table, int write,
 int proc_soft_watchdog(struct ctl_table *table, int write,
 			void *buffer, size_t *lenp, loff_t *ppos)
 {
-	return proc_watchdog_common(SOFT_WATCHDOG_ENABLED,
+	return proc_watchdog_common(WATCHDOG_SOFTOCKUP_ENABLED,
 				    table, write, buffer, lenp, ppos);
 }
 
@@ -774,15 +863,6 @@ static struct ctl_table watchdog_sysctls[] = {
 		.extra2		= (void *)&sixty,
 	},
 	{
-		.procname       = "nmi_watchdog",
-		.data		= &nmi_watchdog_user_enabled,
-		.maxlen		= sizeof(int),
-		.mode		= NMI_WATCHDOG_SYSCTL_PERM,
-		.proc_handler   = proc_nmi_watchdog,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
-	{
 		.procname	= "watchdog_cpumask",
 		.data		= &watchdog_cpumask_bits,
 		.maxlen		= NR_CPUS,
@@ -792,7 +872,7 @@ static struct ctl_table watchdog_sysctls[] = {
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
 	{
 		.procname       = "soft_watchdog",
-		.data		= &soft_watchdog_user_enabled,
+		.data		= &watchdog_softlockup_user_enabled,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler   = proc_soft_watchdog,
@@ -845,14 +925,90 @@ static struct ctl_table watchdog_sysctls[] = {
 	{}
 };
 
+static struct ctl_table watchdog_hardlockup_sysctl[] = {
+	{
+		.procname       = "nmi_watchdog",
+		.data		= &watchdog_hardlockup_user_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.proc_handler   = proc_nmi_watchdog,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{}
+};
+
 static void __init watchdog_sysctl_init(void)
 {
 	register_sysctl_init("kernel", watchdog_sysctls);
+
+	if (watchdog_hardlockup_available)
+		watchdog_hardlockup_sysctl[0].mode = 0644;
+	register_sysctl_init("kernel", watchdog_hardlockup_sysctl);
 }
+
 #else
 #define watchdog_sysctl_init() do { } while (0)
 #endif /* CONFIG_SYSCTL */
 
+static void __init lockup_detector_delay_init(struct work_struct *work);
+static bool allow_lockup_detector_init_retry __initdata;
+
+static struct work_struct detector_work __initdata =
+		__WORK_INITIALIZER(detector_work, lockup_detector_delay_init);
+
+static void __init lockup_detector_delay_init(struct work_struct *work)
+{
+	int ret;
+
+	ret = watchdog_hardlockup_probe();
+	if (ret) {
+		pr_info("Delayed init of the lockup detector failed: %d\n", ret);
+		pr_info("Hard watchdog permanently disabled\n");
+		return;
+	}
+
+	allow_lockup_detector_init_retry = false;
+
+	watchdog_hardlockup_available = true;
+	lockup_detector_setup();
+}
+
+/*
+ * lockup_detector_retry_init - retry init lockup detector if possible.
+ *
+ * Retry hardlockup detector init. It is useful when it requires some
+ * functionality that has to be initialized later on a particular
+ * platform.
+ */
+void __init lockup_detector_retry_init(void)
+{
+	/* Must be called before late init calls */
+	if (!allow_lockup_detector_init_retry)
+		return;
+
+	schedule_work(&detector_work);
+}
+
+/*
+ * Ensure that optional delayed hardlockup init is proceed before
+ * the init code and memory is freed.
+ */
+static int __init lockup_detector_check(void)
+{
+	/* Prevent any later retry. */
+	allow_lockup_detector_init_retry = false;
+
+	/* Make sure no work is pending. */
+	flush_work(&detector_work);
+
+	watchdog_sysctl_init();
+
+	return 0;
+
+}
+late_initcall_sync(lockup_detector_check);
+
 void __init lockup_detector_init(void)
 {
 	if (tick_nohz_full_enabled())
@@ -861,8 +1017,10 @@ void __init lockup_detector_init(void)
 	cpumask_copy(&watchdog_cpumask,
 		     housekeeping_cpumask(HK_TYPE_TIMER));
 
-	if (!watchdog_nmi_probe())
-		nmi_watchdog_available = true;
+	if (!watchdog_hardlockup_probe())
+		watchdog_hardlockup_available = true;
+	else
+		allow_lockup_detector_init_retry = true;
+
 	lockup_detector_setup();
-	watchdog_sysctl_init();
 }