kernel/watchdog.c: print traces for all cpus on lockup detection
A 'softlockup' is defined as a bug that causes the kernel to loop in
kernel mode for more than a predefined period to time, without giving
other tasks a chance to run.
Currently, upon detection of this condition by the per-cpu watchdog
task, debug information (including a stack trace) is sent to the system
log.
On some occasions, we have observed that the "victim" rather than the
actual "culprit" (i.e. the owner/holder of the contended resource) is
reported to the user. Often this information has proven to be
insufficient to assist debugging efforts.
To avoid loss of useful debug information, for architectures which
support NMI, this patch makes it possible to improve soft lockup
reporting. This is accomplished by issuing an NMI to each cpu to obtain
a stack trace.
If NMI is not supported we just revert back to the old method. A sysctl
and boot-time parameter is available to toggle this feature.
[dzickus@redhat.com: add CONFIG_SMP in certain areas]
[akpm@linux-foundation.org: additional CONFIG_SMP=n optimisations]
[mq@suse.cz: fix warning]
Signed-off-by: Aaron Tomlin <atomlin@redhat.com>
Signed-off-by: Don Zickus <dzickus@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Mateusz Guzik <mguzik@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Jan Moskyto Matejka <mq@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 30e4822..c3319bd 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -31,6 +31,12 @@
int watchdog_user_enabled = 1;
int __read_mostly watchdog_thresh = 10;
+#ifdef CONFIG_SMP
+int __read_mostly sysctl_softlockup_all_cpu_backtrace;
+#else
+#define sysctl_softlockup_all_cpu_backtrace 0
+#endif
+
static int __read_mostly watchdog_running;
static u64 __read_mostly sample_period;
@@ -47,6 +53,7 @@
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
#endif
+static unsigned long soft_lockup_nmi_warn;
/* boot commands */
/*
@@ -95,6 +102,15 @@
}
__setup("nosoftlockup", nosoftlockup_setup);
/* */
+#ifdef CONFIG_SMP
+static int __init softlockup_all_cpu_backtrace_setup(char *str)
+{
+ sysctl_softlockup_all_cpu_backtrace =
+ !!simple_strtol(str, NULL, 0);
+ return 1;
+}
+__setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup);
+#endif
/*
* Hard-lockup warnings should be triggered after just a few seconds. Soft-
@@ -271,6 +287,7 @@
unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts);
struct pt_regs *regs = get_irq_regs();
int duration;
+ int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
/* kick the hardlockup detector */
watchdog_interrupt_count();
@@ -317,6 +334,17 @@
if (__this_cpu_read(soft_watchdog_warn) == true)
return HRTIMER_RESTART;
+ if (softlockup_all_cpu_backtrace) {
+ /* Prevent multiple soft-lockup reports if one cpu is already
+ * engaged in dumping cpu back traces
+ */
+ if (test_and_set_bit(0, &soft_lockup_nmi_warn)) {
+ /* Someone else will report us. Let's give up */
+ __this_cpu_write(soft_watchdog_warn, true);
+ return HRTIMER_RESTART;
+ }
+ }
+
printk(KERN_EMERG "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
smp_processor_id(), duration,
current->comm, task_pid_nr(current));
@@ -327,6 +355,17 @@
else
dump_stack();
+ if (softlockup_all_cpu_backtrace) {
+ /* Avoid generating two back traces for current
+ * given that one is already made above
+ */
+ trigger_allbutself_cpu_backtrace();
+
+ clear_bit(0, &soft_lockup_nmi_warn);
+ /* Barrier to sync with other cpus */
+ smp_mb__after_atomic();
+ }
+
if (softlockup_panic)
panic("softlockup: hung tasks");
__this_cpu_write(soft_watchdog_warn, true);