nmi_watchdog: Config option to enable new nmi_watchdog

These are the bits that enable the new nmi_watchdog and safely
isolate the old nmi_watchdog.  Only one or the other can run,
not both at the same time.

Signed-off-by: Don Zickus <dzickus@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: gorcunov@gmail.com
Cc: aris@redhat.com
Cc: peterz@infradead.org
LKML-Reference: <1265424425-31562-4-git-send-email-dzickus@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/kernel/apic/Makefile

@@ -2,7 +2,12 @@
 # Makefile for local APIC drivers and for the IO-APIC code
 #
 
-obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o apic_noop.o probe_$(BITS).o ipi.o nmi.o
+obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o apic_noop.o probe_$(BITS).o ipi.o
+ifneq ($(CONFIG_NMI_WATCHDOG),y)
+obj-$(CONFIG_X86_LOCAL_APIC)	+= nmi.o
+endif
+obj-$(CONFIG_NMI_WATCHDOG)	+= hw_nmi.o
+
 obj-$(CONFIG_X86_IO_APIC)	+= io_apic.o
 obj-$(CONFIG_SMP)		+= ipi.o
 

arch/x86/kernel/traps.c

@@ -406,6 +406,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
 	        			                == NOTIFY_STOP)
 	                return;
 
+#ifndef CONFIG_NMI_WATCHDOG
 		/*
 		 * Ok, so this is none of the documented NMI sources,
 		 * so it must be the NMI watchdog.
@@ -413,6 +414,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
 		if (nmi_watchdog_tick(regs, reason))
 			return;
 		if (!do_nmi_callback(regs, cpu))
+#endif /* !CONFIG_NMI_WATCHDOG */
 			unknown_nmi_error(reason, regs);
 #else
 		unknown_nmi_error(reason, regs);

include/linux/nmi.h

@@ -47,4 +47,8 @@ static inline bool trigger_all_cpu_backtrace(void)
 }
 #endif
 
+#ifdef CONFIG_NMI_WATCHDOG
+int hw_nmi_is_cpu_stuck(struct pt_regs *);
+#endif
+
 #endif

kernel/Makefile

@@ -76,6 +76,7 @@ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
 obj-$(CONFIG_KPROBES) += kprobes.o
 obj-$(CONFIG_KGDB) += kgdb.o
 obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o
+obj-$(CONFIG_NMI_WATCHDOG) += nmi_watchdog.o
 obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
 obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o

lib/Kconfig.debug

@@ -170,6 +170,19 @@ config DETECT_SOFTLOCKUP
 	   can be detected via the NMI-watchdog, on platforms that
 	   support it.)
 
+config NMI_WATCHDOG
+	bool "Detect Hard Lockups with an NMI Watchdog"
+	depends on DEBUG_KERNEL && PERF_EVENTS
+	default y
+	help
+	  Say Y here to enable the kernel to use the NMI as a watchdog
+	  to detect hard lockups.  This is useful when a cpu hangs for no
+	  reason but can still respond to NMIs.  A backtrace is displayed
+	  for reviewing and reporting.
+
+	  The overhead should be minimal, just an extra NMI every few
+	  seconds.
+
 config BOOTPARAM_SOFTLOCKUP_PANIC
 	bool "Panic (Reboot) On Soft Lockups"
 	depends on DETECT_SOFTLOCKUP