x86: only check for two watchdog NMIs

Since the NMI handler can now recognize watchdog NMIs, make
check_nmi_watchdog() only check for at least two watchdog NMIs.  This
prevents false negatives caused by other processors (which may be
being power managed by the BIOS) running at reduced clock frequencies.

We check for more than one NMI since there are apparently systems
where the NMI works only once.

This will also slightly speed up boot times since we only wait the
full 10 ticks if the NMI watchdog on one or more CPUs is not working.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>

diff --git a/xen/arch/x86/nmi.c b/xen/arch/x86/nmi.c
index b1195a1ef0fd4cd82fd6538fc5c5f5e9512ea443..426c24ed9b27edf1cfc408c2bf5cab92fce4dfd5 100644 (file)
--- a/xen/arch/x86/nmi.c
+++ b/xen/arch/x86/nmi.c
@@ -139,7 +139,18 @@ int nmi_active;
 
 static void __init wait_for_nmis(void *p)
 {
-    mdelay((10*1000)/nmi_hz); /* wait 10 ticks */
+    unsigned int cpu = smp_processor_id();
+    unsigned int start_count = nmi_count(cpu);
+    unsigned long ticks = 10 * 1000 * cpu_khz / nmi_hz;
+    unsigned long s, e;
+
+    s = rdtsc();
+    do {
+        cpu_relax();
+        if ( nmi_count(cpu) >= start_count + 2 )
+            break;
+        e = rdtsc();
+    } while( e - s < ticks );
 }
 
 int __init check_nmi_watchdog (void)
@@ -156,15 +167,16 @@ int __init check_nmi_watchdog (void)
     for_each_online_cpu ( cpu )
         prev_nmi_count[cpu] = nmi_count(cpu);
 
-    /* Wait for 10 ticks.  Busy-wait on all CPUs: the LAPIC counter that
-     * the NMI watchdog uses only runs while the core's not halted */
-    if ( nmi_watchdog == NMI_LOCAL_APIC )
-        smp_call_function(wait_for_nmis, NULL, 0);
-    wait_for_nmis(NULL);
+    /*
+     * Wait at most 10 ticks for 2 watchdog NMIs on each CPU.
+     * Busy-wait on all CPUs: the LAPIC counter that the NMI watchdog
+     * uses only runs while the core's not halted
+     */
+    on_selected_cpus(&cpu_online_map, wait_for_nmis, NULL, 1);
 
     for_each_online_cpu ( cpu )
     {
-        if ( nmi_count(cpu) - prev_nmi_count[cpu] <= 5 )
+        if ( nmi_count(cpu) - prev_nmi_count[cpu] < 2 )
         {
             printk(" %d", cpu);
             ok = 0;