x86: Fix irq0 / local apic timer accounting

The clock events merge introduced a change to the nmi watchdog code to
handle the not longer increasing local apic timer count in the
broadcast mode. This is fine for UP, but on SMP it pampers over a
stuck CPU which is not handling the broadcast interrupt due to the
unconditional sum up of local apic timer count and irq0 count.

To cover all cases we need to keep track on which CPU irq0 is
handled. In theory this is CPU#0 due to the explicit disabling of irq
balancing for irq0, but there are systems which ignore this on the
hardware level. The per cpu irq0 accounting allows us to remove the
irq0 to CPU0 binding as well.

Add a per cpu counter for irq0 and evaluate this instead of the global
irq0 count in the nmi watchdog code.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>

diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c
index c7227e2..95d3fc2 100644 (file)
--- a/arch/x86/kernel/nmi_32.c
+++ b/arch/x86/kernel/nmi_32.c
@@ -353,7 +353,8 @@ __kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
         * Take the local apic timer and PIT/HPET into account. We don't
         * know which one is active, when we have highres/dyntick on
         */
-       sum = per_cpu(irq_stat, cpu).apic_timer_irqs + kstat_cpu(cpu).irqs[0];
+       sum = per_cpu(irq_stat, cpu).apic_timer_irqs +
+               per_cpu(irq_stat, cpu).irq0_irqs;
 
        /* if the none of the timers isn't firing, this cpu isn't doing much */
        if (!touched && last_irq_sums[cpu] == sum) {

diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c
index 19a6c67..56dadfc 100644 (file)
--- a/arch/x86/kernel/time_32.c
+++ b/arch/x86/kernel/time_32.c
@@ -157,6 +157,9 @@ EXPORT_SYMBOL(profile_pc);
  */
 irqreturn_t timer_interrupt(int irq, void *dev_id)
 {
+       /* Keep nmi watchdog up to date */
+       per_cpu(irq_stat, smp_processor_id()).irq0_irqs++;
+
 #ifdef CONFIG_X86_IO_APIC
        if (timer_ack) {
                /*

diff --git a/include/asm-x86/hardirq_32.h b/include/asm-x86/hardirq_32.h
index 0e358dc..3464958 100644 (file)
--- a/include/asm-x86/hardirq_32.h
+++ b/include/asm-x86/hardirq_32.h
@@ -9,6 +9,7 @@ typedef struct {
        unsigned long idle_timestamp;
        unsigned int __nmi_count;       /* arch dependent */
        unsigned int apic_timer_irqs;   /* arch dependent */
+       unsigned int irq0_irqs;
 } ____cacheline_aligned irq_cpustat_t;
 
 DECLARE_PER_CPU(irq_cpustat_t, irq_stat);