Merge branch 'perf/nmi' into perf/core

Conflicts:
	kernel/Makefile

Merge reason: Add the now complete topic, fix the conflict.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

Documentation/kernel-parameters.txt

@@ -1812,6 +1812,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	nousb		[USB] Disable the USB subsystem
 
+	nowatchdog	[KNL] Disable the lockup detector.
+
 	nowb		[ARM]
 
 	nox2apic	[X86-64,APIC] Do not enable x2APIC mode.

arch/Kconfig

@@ -151,4 +151,11 @@ config HAVE_MIXED_BREAKPOINTS_REGS
 config HAVE_USER_RETURN_NOTIFIER
 	bool
 
+config HAVE_PERF_EVENTS_NMI
+	bool
+	help
+	  System hardware can generate an NMI using the perf event
+	  subsystem.  Also has support for calculating CPU cycle events
+	  to determine how many clock cycles in a given period.
+
 source "kernel/gcov/Kconfig"

arch/x86/Kconfig

@@ -55,6 +55,7 @@ config X86
 	select HAVE_HW_BREAKPOINT
 	select HAVE_MIXED_BREAKPOINTS_REGS
 	select PERF_EVENTS
+	select HAVE_PERF_EVENTS_NMI
 	select ANON_INODES
 	select HAVE_ARCH_KMEMCHECK
 	select HAVE_USER_RETURN_NOTIFIER

arch/x86/include/asm/nmi.h

@@ -17,7 +17,9 @@ int do_nmi_callback(struct pt_regs *regs, int cpu);
 
 extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
 extern int check_nmi_watchdog(void);
+#if !defined(CONFIG_LOCKUP_DETECTOR)
 extern int nmi_watchdog_enabled;
+#endif
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
 extern int reserve_perfctr_nmi(unsigned int);
 extern void release_perfctr_nmi(unsigned int);

arch/x86/kernel/apic/Makefile

@@ -2,7 +2,12 @@
 # Makefile for local APIC drivers and for the IO-APIC code
 #
 
-obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o apic_noop.o probe_$(BITS).o ipi.o nmi.o
+obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o apic_noop.o probe_$(BITS).o ipi.o
+ifneq ($(CONFIG_HARDLOCKUP_DETECTOR),y)
+obj-$(CONFIG_X86_LOCAL_APIC)	+= nmi.o
+endif
+obj-$(CONFIG_HARDLOCKUP_DETECTOR)	+= hw_nmi.o
+
 obj-$(CONFIG_X86_IO_APIC)	+= io_apic.o
 obj-$(CONFIG_SMP)		+= ipi.o
 

arch/x86/kernel/apic/hw_nmi.c

+/*
+ *  HW NMI watchdog support
+ *
+ *  started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
+ *
+ *  Arch specific calls to support NMI watchdog
+ *
+ *  Bits copied from original nmi.c file
+ *
+ */
+#include <asm/apic.h>
+
+#include <linux/cpumask.h>
+#include <linux/kdebug.h>
+#include <linux/notifier.h>
+#include <linux/kprobes.h>
+#include <linux/nmi.h>
+#include <linux/module.h>
+
+/* For reliability, we're prepared to waste bits here. */
+static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
+
+u64 hw_nmi_get_sample_period(void)
+{
+	return (u64)(cpu_khz) * 1000 * 60;
+}
+
+#ifdef ARCH_HAS_NMI_WATCHDOG
+void arch_trigger_all_cpu_backtrace(void)
+{
+	int i;
+
+	cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
+
+	printk(KERN_INFO "sending NMI to all CPUs:\n");
+	apic->send_IPI_all(NMI_VECTOR);
+
+	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
+	for (i = 0; i < 10 * 1000; i++) {
+		if (cpumask_empty(to_cpumask(backtrace_mask)))
+			break;
+		mdelay(1);
+	}
+}
+
+static int __kprobes
+arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
+			 unsigned long cmd, void *__args)
+{
+	struct die_args *args = __args;
+	struct pt_regs *regs;
+	int cpu = smp_processor_id();
+
+	switch (cmd) {
+	case DIE_NMI:
+	case DIE_NMI_IPI:
+		break;
+
+	default:
+		return NOTIFY_DONE;
+	}
+
+	regs = args->regs;
+
+	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
+		static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+		arch_spin_lock(&lock);
+		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
+		show_regs(regs);
+		dump_stack();
+		arch_spin_unlock(&lock);
+		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
+		return NOTIFY_STOP;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static __read_mostly struct notifier_block backtrace_notifier = {
+	.notifier_call          = arch_trigger_all_cpu_backtrace_handler,
+	.next                   = NULL,
+	.priority               = 1
+};
+
+static int __init register_trigger_all_cpu_backtrace(void)
+{
+	register_die_notifier(&backtrace_notifier);
+	return 0;
+}
+early_initcall(register_trigger_all_cpu_backtrace);
+#endif
+
+/* STUB calls to mimic old nmi_watchdog behaviour */
+#if defined(CONFIG_X86_LOCAL_APIC)
+unsigned int nmi_watchdog = NMI_NONE;
+EXPORT_SYMBOL(nmi_watchdog);
+void acpi_nmi_enable(void) { return; }
+void acpi_nmi_disable(void) { return; }
+#endif
+atomic_t nmi_active = ATOMIC_INIT(0);           /* oprofile uses this */
+EXPORT_SYMBOL(nmi_active);
+int unknown_nmi_panic;
+void cpu_nmi_set_wd_enabled(void) { return; }
+void stop_apic_nmi_watchdog(void *unused) { return; }
+void setup_apic_nmi_watchdog(void *unused) { return; }
+int __init check_nmi_watchdog(void) { return 0; }

arch/x86/kernel/apic/nmi.c

@@ -401,13 +401,6 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 	int cpu = smp_processor_id();
 	int rc = 0;
 
-	/* check for other users first */
-	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
-			== NOTIFY_STOP) {
-		rc = 1;
-		touched = 1;
-	}
-
 	sum = get_timer_irqs(cpu);
 
 	if (__get_cpu_var(nmi_touch)) {

arch/x86/kernel/traps.c

@@ -392,7 +392,13 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
 		if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT)
 								== NOTIFY_STOP)
 			return;
+
 #ifdef CONFIG_X86_LOCAL_APIC
+		if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
+							== NOTIFY_STOP)
+			return;
+
+#ifndef CONFIG_LOCKUP_DETECTOR
 		/*
 		 * Ok, so this is none of the documented NMI sources,
 		 * so it must be the NMI watchdog.
@@ -400,6 +406,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
 		if (nmi_watchdog_tick(regs, reason))
 			return;
 		if (!do_nmi_callback(regs, cpu))
+#endif /* !CONFIG_LOCKUP_DETECTOR */
 			unknown_nmi_error(reason, regs);
 #else
 		unknown_nmi_error(reason, regs);

include/linux/nmi.h

@@ -20,10 +20,14 @@ extern void touch_nmi_watchdog(void);
 extern void acpi_nmi_disable(void);
 extern void acpi_nmi_enable(void);
 #else
+#ifndef CONFIG_HARDLOCKUP_DETECTOR
 static inline void touch_nmi_watchdog(void)
 {
 	touch_softlockup_watchdog();
 }
+#else
+extern void touch_nmi_watchdog(void);
+#endif
 static inline void acpi_nmi_disable(void) { }
 static inline void acpi_nmi_enable(void) { }
 #endif
@@ -47,4 +51,13 @@ static inline bool trigger_all_cpu_backtrace(void)
 }
 #endif
 
+#ifdef CONFIG_LOCKUP_DETECTOR
+int hw_nmi_is_cpu_stuck(struct pt_regs *);
+u64 hw_nmi_get_sample_period(void);
+extern int watchdog_enabled;
+struct ctl_table;
+extern int proc_dowatchdog_enabled(struct ctl_table *, int ,
+			void __user *, size_t *, loff_t *);
+#endif
+
 #endif

include/linux/sched.h

@@ -316,20 +316,16 @@ extern void scheduler_tick(void);
 
 extern void sched_show_task(struct task_struct *p);
 
-#ifdef CONFIG_DETECT_SOFTLOCKUP
-extern void softlockup_tick(void);
+#ifdef CONFIG_LOCKUP_DETECTOR
 extern void touch_softlockup_watchdog(void);
 extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
-extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
-				    void __user *buffer,
-				    size_t *lenp, loff_t *ppos);
+extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
+				  void __user *buffer,
+				  size_t *lenp, loff_t *ppos);
 extern unsigned int  softlockup_panic;
 extern int softlockup_thresh;
 #else
-static inline void softlockup_tick(void)
-{
-}
 static inline void touch_softlockup_watchdog(void)
 {
 }

kernel/Makefile

@@ -76,8 +76,8 @@ obj-$(CONFIG_GCOV_KERNEL) += gcov/
 obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
 obj-$(CONFIG_KPROBES) += kprobes.o
 obj-$(CONFIG_KGDB) += debug/
-obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o
 obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
+obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
 obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o

kernel/softlockup.c

-/*
- * Detect Soft Lockups
- *
- * started by Ingo Molnar, Copyright (C) 2005, 2006 Red Hat, Inc.
- *
- * this code detects soft lockups: incidents in where on a CPU
- * the kernel does not reschedule for 10 seconds or more.
- */
-#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>
-
-static DEFINE_SPINLOCK(print_lock);
-
-static DEFINE_PER_CPU(unsigned long, softlockup_touch_ts); /* touch timestamp */
-static DEFINE_PER_CPU(unsigned long, softlockup_print_ts); /* print timestamp */
-static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
-static DEFINE_PER_CPU(bool, softlock_touch_sync);
-
-static int __read_mostly did_panic;
-int __read_mostly softlockup_thresh = 60;
-
-/*
- * Should we panic (and reboot, if panic_timeout= is set) when a
- * soft-lockup occurs:
- */
-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
-softlock_panic(struct notifier_block *this, unsigned long event, void *ptr)
-{
-	did_panic = 1;
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block panic_block = {
-	.notifier_call = softlock_panic,
-};
-
-/*
- * 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 void __touch_softlockup_watchdog(void)
-{
-	int this_cpu = raw_smp_processor_id();
-
-	__raw_get_cpu_var(softlockup_touch_ts) = get_timestamp(this_cpu);
-}
-
-void touch_softlockup_watchdog(void)
-{
-	__raw_get_cpu_var(softlockup_touch_ts) = 0;
-}
-EXPORT_SYMBOL(touch_softlockup_watchdog);
-
-void touch_softlockup_watchdog_sync(void)
-{
-	__raw_get_cpu_var(softlock_touch_sync) = true;
-	__raw_get_cpu_var(softlockup_touch_ts) = 0;
-}
-
-void touch_all_softlockup_watchdogs(void)
-{
-	int cpu;
-
-	/* Cause each CPU to re-update its timestamp rather than complain */
-	for_each_online_cpu(cpu)
-		per_cpu(softlockup_touch_ts, cpu) = 0;
-}
-EXPORT_SYMBOL(touch_all_softlockup_watchdogs);
-
-int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
-			     void __user *buffer,
-			     size_t *lenp, loff_t *ppos)
-{
-	touch_all_softlockup_watchdogs();
-	return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-}
-
-/*
- * This callback runs from the timer interrupt, and checks
- * whether the watchdog thread has hung or not:
- */
-void softlockup_tick(void)
-{
-	int this_cpu = smp_processor_id();
-	unsigned long touch_ts = per_cpu(softlockup_touch_ts, this_cpu);
-	unsigned long print_ts;
-	struct pt_regs *regs = get_irq_regs();
-	unsigned long now;
-
-	/* Is detection switched off? */
-	if (!per_cpu(softlockup_watchdog, this_cpu) || softlockup_thresh <= 0) {
-		/* Be sure we don't false trigger if switched back on */
-		if (touch_ts)
-			per_cpu(softlockup_touch_ts, this_cpu) = 0;
-		return;
-	}
-
-	if (touch_ts == 0) {
-		if (unlikely(per_cpu(softlock_touch_sync, this_cpu))) {
-			/*
-			 * If the time stamp was touched atomically
-			 * make sure the scheduler tick is up to date.
-			 */
-			per_cpu(softlock_touch_sync, this_cpu) = false;
-			sched_clock_tick();
-		}
-		__touch_softlockup_watchdog();
-		return;
-	}
-
-	print_ts = per_cpu(softlockup_print_ts, this_cpu);
-
-	/* report at most once a second */
-	if (print_ts == touch_ts || did_panic)
-		return;
-
-	/* do not print during early bootup: */
-	if (unlikely(system_state != SYSTEM_RUNNING)) {
-		__touch_softlockup_watchdog();
-		return;
-	}
-
-	now = get_timestamp(this_cpu);
-
-	/*
-	 * Wake up the high-prio watchdog task twice per
-	 * threshold timespan.
-	 */
-	if (time_after(now - softlockup_thresh/2, touch_ts))
-		wake_up_process(per_cpu(softlockup_watchdog, this_cpu));
-
-	/* Warn about unreasonable delays: */
-	if (time_before_eq(now - softlockup_thresh, touch_ts))
-		return;
-
-	per_cpu(softlockup_print_ts, this_cpu) = touch_ts;
-
-	spin_lock(&print_lock);
-	printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %lus! [%s:%d]\n",
-			this_cpu, now - touch_ts,
-			current->comm, task_pid_nr(current));
-	print_modules();
-	print_irqtrace_events(current);
-	if (regs)
-		show_regs(regs);
-	else
-		dump_stack();
-	spin_unlock(&print_lock);
-
-	if (softlockup_panic)
-		panic("softlockup: hung tasks");
-}
-
-/*
- * The watchdog thread - runs every second and touches the timestamp.
- */
-static int watchdog(void *__bind_cpu)
-{
-	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
-
-	sched_setscheduler(current, SCHED_FIFO, &param);
-
-	/* initialize timestamp */
-	__touch_softlockup_watchdog();
-
-	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_softlockup_watchdog();
-		schedule();
-
-		if (kthread_should_stop())
-			break;
-
-		set_current_state(TASK_INTERRUPTIBLE);
-	}
-	__set_current_state(TASK_RUNNING);
-
-	return 0;
-}
-
-/*
- * 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;
-	struct task_struct *p;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		BUG_ON(per_cpu(softlockup_watchdog, hotcpu));
-		p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu);
-		if (IS_ERR(p)) {
-			printk(KERN_ERR "watchdog for %i failed\n", hotcpu);
-			return NOTIFY_BAD;
-		}
-		per_cpu(softlockup_touch_ts, hotcpu) = 0;
-		per_cpu(softlockup_watchdog, hotcpu) = p;
-		kthread_bind(p, hotcpu);
-		break;
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		wake_up_process(per_cpu(softlockup_watchdog, hotcpu));
-		break;
-#ifdef CONFIG_HOTPLUG_CPU
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		if (!per_cpu(softlockup_watchdog, hotcpu))
-			break;
-		/* Unbind so it can run.  Fall thru. */
-		kthread_bind(per_cpu(softlockup_watchdog, hotcpu),
-			     cpumask_any(cpu_online_mask));
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		p = per_cpu(softlockup_watchdog, hotcpu);
-		per_cpu(softlockup_watchdog, hotcpu) = NULL;
-		kthread_stop(p);
-		break;
-#endif /* CONFIG_HOTPLUG_CPU */
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block __cpuinitdata cpu_nfb = {
-	.notifier_call = cpu_callback
-};
-
-static int __initdata nosoftlockup;
-
-static int __init nosoftlockup_setup(char *str)
-{
-	nosoftlockup = 1;
-	return 1;
-}
-__setup("nosoftlockup", nosoftlockup_setup);
-
-static int __init spawn_softlockup_task(void)
-{
-	void *cpu = (void *)(long)smp_processor_id();
-	int err;
-
-	if (nosoftlockup)
-		return 0;
-
-	err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
-	if (err == NOTIFY_BAD) {
-		BUG();
-		return 1;
-	}
-	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_softlockup_task);

kernel/sysctl.c

@@ -76,6 +76,10 @@
 #include <scsi/sg.h>
 #endif
 
+#ifdef CONFIG_LOCKUP_DETECTOR
+#include <linux/nmi.h>
+#endif
+
 
 #if defined(CONFIG_SYSCTL)
 
@@ -106,7 +110,7 @@ extern int blk_iopoll_enabled;
 #endif
 
 /* Constants used for minimum and  maximum */
-#ifdef CONFIG_DETECT_SOFTLOCKUP
+#ifdef CONFIG_LOCKUP_DETECTOR
 static int sixty = 60;
 static int neg_one = -1;
 #endif
@@ -710,7 +714,34 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0444,
 		.proc_handler	= proc_dointvec,
 	},
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
+#if defined(CONFIG_LOCKUP_DETECTOR)
+	{
+		.procname       = "watchdog",
+		.data           = &watchdog_enabled,
+		.maxlen         = sizeof (int),
+		.mode           = 0644,
+		.proc_handler   = proc_dowatchdog_enabled,
+	},
+	{
+		.procname	= "watchdog_thresh",
+		.data		= &softlockup_thresh,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dowatchdog_thresh,
+		.extra1		= &neg_one,
+		.extra2		= &sixty,
+	},
+	{
+		.procname	= "softlockup_panic",
+		.data		= &softlockup_panic,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+#endif
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) && !defined(CONFIG_LOCKUP_DETECTOR)
 	{
 		.procname       = "unknown_nmi_panic",
 		.data           = &unknown_nmi_panic,
@@ -813,26 +844,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#ifdef CONFIG_DETECT_SOFTLOCKUP
-	{
-		.procname	= "softlockup_panic",
-		.data		= &softlockup_panic,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
-	},
-	{
-		.procname	= "softlockup_thresh",
-		.data		= &softlockup_thresh,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dosoftlockup_thresh,
-		.extra1		= &neg_one,
-		.extra2		= &sixty,
-	},
-#endif
 #ifdef CONFIG_DETECT_HUNG_TASK
 	{
 		.procname	= "hung_task_panic",

kernel/timer.c

@@ -1289,7 +1289,6 @@ void run_local_timers(void)
 {
 	hrtimer_run_queues();
 	raise_softirq(TIMER_SOFTIRQ);
-	softlockup_tick();
 }
 
 /*

kernel/watchdog.c

+/*
+ * 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, soft_watchdog_warn);
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+static DEFINE_PER_CPU(bool, hard_watchdog_warn);
+static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
+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_HARDLOCKUP_DETECTOR
+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 = smp_processor_id();
+
+	__get_cpu_var(watchdog_touch_ts) = get_timestamp(this_cpu);
+}
+
+void touch_softlockup_watchdog(void)
+{
+	__get_cpu_var(watchdog_touch_ts) = 0;
+}
+EXPORT_SYMBOL(touch_softlockup_watchdog);
+
+void touch_all_softlockup_watchdogs(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;
+}
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+void touch_nmi_watchdog(void)
+{
+	__get_cpu_var(watchdog_nmi_touch) = true;
+	touch_softlockup_watchdog();
+}
+EXPORT_SYMBOL(touch_nmi_watchdog);
+
+#endif
+
+void touch_softlockup_watchdog_sync(void)
+{
+	__raw_get_cpu_var(softlockup_touch_sync) = true;
+	__raw_get_cpu_var(watchdog_touch_ts) = 0;
+}
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+/* watchdog detector functions */
+static int is_hardlockup(void)
+{
+	unsigned long hrint = __get_cpu_var(hrtimer_interrupts);
+
+	if (__get_cpu_var(hrtimer_interrupts_saved) == hrint)
+		return 1;
+
+	__get_cpu_var(hrtimer_interrupts_saved) = hrint;
+	return 0;
+}
+#endif
+
+static int is_softlockup(unsigned long touch_ts)
+{
+	unsigned long now = get_timestamp(smp_processor_id());
+
+	/* 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_HARDLOCKUP_DETECTOR
+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)
+{
+	if (__get_cpu_var(watchdog_nmi_touch) == true) {
+		__get_cpu_var(watchdog_nmi_touch) = false;
+		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()) {
+		int this_cpu = smp_processor_id();
+
+		/* 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_HARDLOCKUP_DETECTOR */
+
+/* watchdog kicker functions */
+static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
+{
+	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(__get_cpu_var(softlockup_touch_sync))) {
+			/*
+			 * If the time stamp was touched atomically
+			 * make sure the scheduler tick is up to date.
+			 */
+			__get_cpu_var(softlockup_touch_sync) = 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);
+	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",
+			smp_processor_id(), 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 *unused)
+{
+	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+	struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
+
+	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 watchdog_timer_fn().
+	 */
+	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_HARDLOCKUP_DETECTOR
+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_HARDLOCKUP_DETECTOR */
+
+/* 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 = 0;
+
+	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);
+}
+#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);

lib/Kconfig.debug

@@ -152,28 +152,33 @@ config DEBUG_SHIRQ
 	  Drivers ought to be able to handle interrupts coming in at those
 	  points; some don't and need to be caught.
 
-config DETECT_SOFTLOCKUP
-	bool "Detect Soft Lockups"
+config LOCKUP_DETECTOR
+	bool "Detect Hard and Soft Lockups"
 	depends on DEBUG_KERNEL && !S390
-	default y
 	help
-	  Say Y here to enable the kernel to detect "soft lockups",
-	  which are bugs that cause the kernel to loop in kernel
+	  Say Y here to enable the kernel to act as a watchdog to detect
+	  hard and soft lockups.
+
+	  Softlockups are bugs that cause the kernel to loop in kernel
 	  mode for more than 60 seconds, without giving other tasks a
-	  chance to run.
+	  chance to run.  The current stack trace is displayed upon
+	  detection and the system will stay locked up.
 
-	  When a soft-lockup is detected, the kernel will print the
-	  current stack trace (which you should report), but the
-	  system will stay locked up. This feature has negligible
-	  overhead.
+	  Hardlockups are bugs that cause the CPU to loop in kernel mode
+	  for more than 60 seconds, without letting other interrupts have a
+	  chance to run.  The current stack trace is displayed upon detection
+	  and the system will stay locked up.
+
+	  The overhead should be minimal.  A periodic hrtimer runs to
+	  generate interrupts and kick the watchdog task every 10-12 seconds.
+	  An NMI is generated every 60 seconds or so to check for hardlockups.
 
-	  (Note that "hard lockups" are separate type of bugs that
-	   can be detected via the NMI-watchdog, on platforms that
-	   support it.)
+config HARDLOCKUP_DETECTOR
+	def_bool LOCKUP_DETECTOR && PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 
 config BOOTPARAM_SOFTLOCKUP_PANIC
 	bool "Panic (Reboot) On Soft Lockups"
-	depends on DETECT_SOFTLOCKUP
+	depends on LOCKUP_DETECTOR
 	help
 	  Say Y here to enable the kernel to panic on "soft lockups",
 	  which are bugs that cause the kernel to loop in kernel
@@ -190,7 +195,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC
 
 config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
 	int
-	depends on DETECT_SOFTLOCKUP
+	depends on LOCKUP_DETECTOR
 	range 0 1
 	default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
 	default 1 if BOOTPARAM_SOFTLOCKUP_PANIC