kernel/watchdog.c: allow hardlockup to panic by default

When a cpu is considered stuck, instead of limping along and just printing
a warning, it is sometimes preferred to just panic, let kdump capture the
vmcore and reboot.  This gets the machine back into a stable state quickly
while saving the info that got it into a stuck state to begin with.

Add a Kconfig option to allow users to set the hardlockup to panic
by default.  Also add in a 'nmi_watchdog=nopanic' to override this.

[[email protected]: fix strncmp length]
Signed-off-by: Don Zickus <[email protected]>
Acked-by: Peter Zijlstra <[email protected]>
Reviewed-by: WANG Cong <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: dzickusrh

Documentation/kernel-parameters.txt

@@ -1597,11 +1597,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Format: [state][,regs][,debounce][,die]
 
 	nmi_watchdog=	[KNL,BUGS=X86] Debugging features for SMP kernels
-			Format: [panic,][num]
+			Format: [panic,][nopanic,][num]
 			Valid num: 0
 			0 - turn nmi_watchdog off
 			When panic is specified, panic when an NMI watchdog
-			timeout occurs.
+			timeout occurs (or 'nopanic' to override the opposite
+			default).
 			This is useful when you use a panic=... timeout and
 			need the box quickly up again.
 

kernel/watchdog.c

@@ -48,12 +48,15 @@ static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
  * Should we panic when a soft-lockup or hard-lockup occurs:
  */
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
-static int hardlockup_panic;
+static int hardlockup_panic =
+			CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
 
 static int __init hardlockup_panic_setup(char *str)
 {
 	if (!strncmp(str, "panic", 5))
 		hardlockup_panic = 1;
+	else if (!strncmp(str, "nopanic", 7))
+		hardlockup_panic = 0;
 	else if (!strncmp(str, "0", 1))
 		watchdog_enabled = 0;
 	return 1;

lib/Kconfig.debug

@@ -171,6 +171,23 @@ config HARDLOCKUP_DETECTOR
 	def_bool LOCKUP_DETECTOR && PERF_EVENTS && HAVE_PERF_EVENTS_NMI && \
 		 !ARCH_HAS_NMI_WATCHDOG
 
+config BOOTPARAM_HARDLOCKUP_PANIC
+	bool "Panic (Reboot) On Hard Lockups"
+	depends on LOCKUP_DETECTOR
+	help
+	  Say Y here to enable the kernel to panic on "hard lockups",
+	  which are bugs that cause the kernel to loop in kernel
+	  mode with interrupts disabled for more than 60 seconds.
+
+	  Say N if unsure.
+
+config BOOTPARAM_HARDLOCKUP_PANIC_VALUE
+	int
+	depends on LOCKUP_DETECTOR
+	range 0 1
+	default 0 if !BOOTPARAM_HARDLOCKUP_PANIC
+	default 1 if BOOTPARAM_HARDLOCKUP_PANIC
+
 config BOOTPARAM_SOFTLOCKUP_PANIC
 	bool "Panic (Reboot) On Soft Lockups"
 	depends on LOCKUP_DETECTOR