Commit 55537871 authored by Jiri Kosina's avatar Jiri Kosina Committed by Linus Torvalds

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: default avatarJiri Kosina <>
Reviewed-by: default avatarAaron Tomlin <>
Cc: Ulrich Obergfell <>
Acked-by: default avatarDon Zickus <>
Signed-off-by: default avatarAndrew Morton <>
Signed-off-by: default avatarLinus Torvalds <>
parent ee7fed54
......@@ -1269,6 +1269,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0.
Default: 1024
[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.
......@@ -33,6 +33,7 @@ show up in /proc/sys/kernel:
- domainname
- hostname
- hotplug
- hardlockup_all_cpu_backtrace
- hung_task_panic
- hung_task_check_count
- hung_task_timeout_secs
......@@ -292,6 +293,17 @@ Information Service) or YP (Yellow Pages) domainname. These two
domain names are in general different. For a detailed discussion
see the hostname(1) man page.
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.
......@@ -73,6 +73,7 @@ extern int watchdog_user_enabled;
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 *);
......@@ -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 */
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
......@@ -57,8 +57,10 @@ int __read_mostly watchdog_thresh = 10;
int __read_mostly sysctl_softlockup_all_cpu_backtrace;
int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
#define sysctl_softlockup_all_cpu_backtrace 0
#define sysctl_hardlockup_all_cpu_backtrace 0
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;
static int hardlockup_panic =
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);
......@@ -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)
if (hardlockup_panic)
panic("Watchdog detected hard LOCKUP on cpu %d",
pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
if (regs)
WARN(1, "Watchdog detected hard LOCKUP on cpu %d",
* 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))
if (hardlockup_panic)
panic("Hard LOCKUP");
__this_cpu_write(hard_watchdog_warn, true);
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment