kernel/watchdog.c: perform all-CPU backtrace in case of hard lockup

In many cases of hardlockup reports, it's actually not possible to know
why it triggered, because the CPU that got stuck is usually waiting on a
resource (with IRQs disabled) in posession of some other CPU is holding.

IOW, we are often looking at the stacktrace of the victim and not the
actual offender.

Introduce sysctl / cmdline parameter that makes it possible to have
hardlockup detector perform all-CPU backtrace.

Signed-off-by: Jiri Kosina <[e-mail]>
Reviewed-by: Aaron Tomlin <[e-mail]>
Cc: Ulrich Obergfell <[e-mail]>
Acked-by: Don Zickus <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

Documentation/kernel-parameters.txt

···
 			Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0.
 			Default: 1024
 
+	hardlockup_all_cpu_backtrace=
+			[KNL] Should the hard-lockup detector generate
+			backtraces on all cpus.
+			Format: <integer>
+
 	hashdist=	[KNL,NUMA] Large hashes allocated during boot
 			are distributed across NUMA nodes.  Defaults on
 			for 64-bit NUMA, off otherwise.

Documentation/sysctl/kernel.txt

···
 - domainname
 - hostname
 - hotplug
+- hardlockup_all_cpu_backtrace
 - hung_task_panic
 - hung_task_check_count
 - hung_task_timeout_secs
···
 domain names are in general different. For a detailed discussion
 see the hostname(1) man page.
 
+==============================================================
+hardlockup_all_cpu_backtrace:
+
+This value controls the hard lockup detector behavior when a hard
+lockup condition is detected as to whether or not to gather further
+debug information. If enabled, arch-specific all-CPU stack dumping
+will be initiated.
+
+0: do nothing. This is the default behavior.
+
+1: on detection capture more debug information.
 ==============================================================
 
 hotplug:

include/linux/nmi.h

···
 extern int watchdog_thresh;
 extern unsigned long *watchdog_cpumask_bits;
 extern int sysctl_softlockup_all_cpu_backtrace;
+extern int sysctl_hardlockup_all_cpu_backtrace;
 struct ctl_table;
 extern int proc_watchdog(struct ctl_table *, int ,
 			 void __user *, size_t *, loff_t *);

kernel/sysctl.c

···
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+	{
+		.procname	= "hardlockup_all_cpu_backtrace",
+		.data		= &sysctl_hardlockup_all_cpu_backtrace,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 #endif /* CONFIG_SMP */
 #endif
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)

kernel/watchdog.c

···
 
 #ifdef CONFIG_SMP
 int __read_mostly sysctl_softlockup_all_cpu_backtrace;
+int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
 #else
 #define sysctl_softlockup_all_cpu_backtrace 0
+#define sysctl_hardlockup_all_cpu_backtrace 0
 #endif
 static struct cpumask watchdog_cpumask __read_mostly;
 unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
···
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 static int hardlockup_panic =
 			CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
+static unsigned long hardlockup_allcpu_dumped;
 /*
  * We may not want to enable hard lockup detection by default in all cases,
  * for example when running the kernel as a guest on a hypervisor. In these
···
 	return 1;
 }
 __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup);
+static int __init hardlockup_all_cpu_backtrace_setup(char *str)
+{
+	sysctl_hardlockup_all_cpu_backtrace =
+		!!simple_strtol(str, NULL, 0);
+	return 1;
+}
+__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
 #endif
 
 /*
···
 	 */
 	if (is_hardlockup()) {
 		int this_cpu = smp_processor_id();
+		struct pt_regs *regs = get_irq_regs();
 
 		/* only print hardlockups once */
 		if (__this_cpu_read(hard_watchdog_warn) == true)
 			return;
 
-		if (hardlockup_panic)
-			panic("Watchdog detected hard LOCKUP on cpu %d",
-			      this_cpu);
+		pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
+		print_modules();
+		print_irqtrace_events(current);
+		if (regs)
+			show_regs(regs);
 		else
-			WARN(1, "Watchdog detected hard LOCKUP on cpu %d",
-			     this_cpu);
+			dump_stack();
+
+		/*
+		 * Perform all-CPU dump only once to avoid multiple hardlockups
+		 * generating interleaving traces
+		 */
+		if (sysctl_hardlockup_all_cpu_backtrace &&
+				!test_and_set_bit(0, &hardlockup_allcpu_dumped))
+			trigger_allbutself_cpu_backtrace();
+
+		if (hardlockup_panic)
+			panic("Hard LOCKUP");
 
 		__this_cpu_write(hard_watchdog_warn, true);
 		return;