[PATCH] check nmi watchdog is broken

A bug against an xSeries system showed up recently noting that the
check_nmi_watchdog() test was failing.

I have been investigating it and discovered in both i386 and x86_64 the
recent change to the routine to use the cpu_callin_map has uncovered a
problem.  Prior to that change, on an SMP box, the test was trivally
passing because all cpu's were found to not yet be online, but now with the
callin_map they are discovered, it goes on to test the counter and they
have not yet begun to increment, so it announces a CPU is stuck and bails
out.

On all the systems I have access to test, the announcement of failure is
also bougs...  by the time you can login and check /proc/interrupts, the
NMI count is happily incrementing on all CPUs.  Its just that the test is
being done too early.

I have tried moving the call to the test around a bit, and it was always
too early.  I finally hit on this proposed solution, it delays the routine
via a late_initcall(), seems like the right solution to me.

Signed-off-by: Adrian Bunk <bunk@stusta.de>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

4 files changed, 7 insertions, 11 deletions

diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c
index e3879f7625c2..d509836b70c3 100644
--- a/arch/i386/kernel/apic.c
+++ b/arch/i386/kernel/apic.c
@@ -1265,8 +1265,6 @@ int __init APIC_init_uniprocessor (void)
 
         setup_local_APIC();
 
-        if (nmi_watchdog == NMI_LOCAL_APIC)
-                check_nmi_watchdog();
 #ifdef CONFIG_X86_IO_APIC
         if (smp_found_config)
                 if (!skip_ioapic_setup && nr_ioapics)
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index 5e0d55be5435..7a324e8b86f9 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -2175,7 +2175,6 @@ static inline void check_timer(void)
                                 disable_8259A_irq(0);
                                 setup_nmi();
                                 enable_8259A_irq(0);
-                                check_nmi_watchdog();
                         }
                         return;
                 }
@@ -2198,7 +2197,6 @@ static inline void check_timer(void)
                                 add_pin_to_irq(0, 0, pin2);
                         if (nmi_watchdog == NMI_IO_APIC) {
                                 setup_nmi();
-                                check_nmi_watchdog();
                         }
                         return;
                 }
diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index 2f89d000f954..2c0ee9c2d020 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -102,20 +102,21 @@ int nmi_active;
         (P4_CCCR_OVF_PMI0|P4_CCCR_THRESHOLD(15)|P4_CCCR_COMPLEMENT|     \
          P4_CCCR_COMPARE|P4_CCCR_REQUIRED|P4_CCCR_ESCR_SELECT(4)|P4_CCCR_ENABLE)
 
-int __init check_nmi_watchdog (void)
+static int __init check_nmi_watchdog(void)
 {
         unsigned int prev_nmi_count[NR_CPUS];
         int cpu;
 
-        printk(KERN_INFO "testing NMI watchdog ... ");
+        if (nmi_watchdog == NMI_NONE)
+                return 0;
+
+        printk(KERN_INFO "Testing NMI watchdog ... ");
 
         for (cpu = 0; cpu < NR_CPUS; cpu++)
                 prev_nmi_count[cpu] = per_cpu(irq_stat, cpu).__nmi_count;
         local_irq_enable();
         mdelay((10*1000)/nmi_hz); // wait 10 ticks
 
-        /* FIXME: Only boot CPU is online at this stage.  Check CPUs
-           as they come up. */
         for (cpu = 0; cpu < NR_CPUS; cpu++) {
 #ifdef CONFIG_SMP
                 /* Check cpu_callin_map here because that is set
@@ -139,6 +140,8 @@ int __init check_nmi_watchdog (void)
 
         return 0;
 }
+/* This needs to happen later in boot so counters are working */
+late_initcall(check_nmi_watchdog);
 
 static int __init setup_nmi_watchdog(char *str)
 {
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index fd36d2f65f88..cbea7ac582e5 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -1089,9 +1089,6 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
                 }
         }
 
-        if (nmi_watchdog == NMI_LOCAL_APIC)
-                check_nmi_watchdog();
-
         smpboot_setup_io_apic();
 
         setup_boot_APIC_clock();