[PATCH] x86_64: make touch_nmi_watchdog() not touch impossible cpus' private data

Along with that, also suppress the memory touching altogether when the
watchdog is not running, to eliminate needless crosstalk. Plus ad a call
to it to make things consistent (one could also consider removing the call
in enable_timer_nmi_watchdog()).

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index 8be407a..5bf17e4 100644 (file)
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -236,6 +236,7 @@ static void enable_lapic_nmi_watchdog(void)
 {
        if (nmi_active < 0) {
                nmi_watchdog = NMI_LOCAL_APIC;
+               touch_nmi_watchdog();
                setup_apic_nmi_watchdog();
        }
 }
@@ -456,15 +457,17 @@ static DEFINE_PER_CPU(int, nmi_touch);
 
 void touch_nmi_watchdog (void)
 {
-       int i;
+       if (nmi_watchdog > 0) {
+               unsigned cpu;
 
-       /*
-        * Tell other CPUs to reset their alert counters. We cannot
-        * do it ourselves because the alert count increase is not
-        * atomic.
-        */
-       for (i = 0; i < NR_CPUS; i++)
-               per_cpu(nmi_touch, i) = 1;
+               /*
+                * Tell other CPUs to reset their alert counters. We cannot
+                * do it ourselves because the alert count increase is not
+                * atomic.
+                */
+               for_each_present_cpu (cpu)
+                       per_cpu(nmi_touch, cpu) = 1;
+       }
 
        touch_softlockup_watchdog();
 }