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 <jkosina@suse.cz>
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Acked-by: Don Zickus <dzickus@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 37 insertions, 5 deletions

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 96c856b04081..1a5faa3e1521 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -898,6 +898,15 @@ static struct ctl_table kern_table[] = {
 		.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)
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 452e4ed507e5..f6b32b8cbffe 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -57,8 +57,10 @@ int __read_mostly watchdog_thresh = 10;
 
 #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);
@@ -112,6 +114,7 @@ static unsigned long soft_lockup_nmi_warn;
 #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
@@ -173,6 +176,13 @@ static int __init softlockup_all_cpu_backtrace_setup(char *str)
 	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
 
 /*
@@ -318,17 +328,30 @@ static void watchdog_overflow_callback(struct perf_event *event,
 	 */
 	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;