powerpc: Convert global "BAD" interrupt to per cpu spurious

I often get asked if BAD interrupts are really bad. On some boxes (eg
IBM machines running a hypervisor) there are valid cases where are
presented with an interrupt that is not for us. These cases are common
enough to show up as thousands of BAD interrupts a day.

Tone them down by calling them spurious. Since they can be a significant cause
of OS jitter, we may as well log them per cpu so we know where they are
occurring.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h
index cd2d4be..3147a29 100644 (file)
--- a/arch/powerpc/include/asm/hardirq.h
+++ b/arch/powerpc/include/asm/hardirq.h
@@ -9,6 +9,7 @@ typedef struct {
        unsigned int timer_irqs;
        unsigned int pmu_irqs;
        unsigned int mce_exceptions;
+       unsigned int spurious_irqs;
 } ____cacheline_aligned irq_cpustat_t;
 
 DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
@@ -25,7 +26,4 @@ static inline void ack_bad_irq(unsigned int irq)
 extern u64 arch_irq_stat_cpu(unsigned int cpu);
 #define arch_irq_stat_cpu      arch_irq_stat_cpu
 
-extern u64 arch_irq_stat(void);
-#define arch_irq_stat          arch_irq_stat
-
 #endif /* _ASM_POWERPC_HARDIRQ_H */

diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 7105052..9ae77e5 100644 (file)
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -77,7 +77,6 @@ DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 EXPORT_PER_CPU_SYMBOL(irq_stat);
 
 int __irq_offset_value;
-static int ppc_spurious_interrupts;
 
 #ifdef CONFIG_PPC32
 EXPORT_SYMBOL(__irq_offset_value);
@@ -201,6 +200,11 @@ static int show_other_interrupts(struct seq_file *p, int prec)
                seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs);
         seq_printf(p, "  Local timer interrupts\n");
 
+       seq_printf(p, "%*s: ", prec, "SPU");
+       for_each_online_cpu(j)
+               seq_printf(p, "%10u ", per_cpu(irq_stat, j).spurious_irqs);
+       seq_printf(p, "  Spurious interrupts\n");
+
        seq_printf(p, "%*s: ", prec, "CNT");
        for_each_online_cpu(j)
                seq_printf(p, "%10u ", per_cpu(irq_stat, j).pmu_irqs);
@@ -211,8 +215,6 @@ static int show_other_interrupts(struct seq_file *p, int prec)
                seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions);
        seq_printf(p, "  Machine check exceptions\n");
 
-       seq_printf(p, "%*s: %10u\n", prec, "BAD", ppc_spurious_interrupts);
-
        return 0;
 }
 
@@ -282,13 +284,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 
        sum += per_cpu(irq_stat, cpu).pmu_irqs;
        sum += per_cpu(irq_stat, cpu).mce_exceptions;
-
-       return sum;
-}
-
-u64 arch_irq_stat(void)
-{
-       u64 sum = ppc_spurious_interrupts;
+       sum += per_cpu(irq_stat, cpu).spurious_irqs;
 
        return sum;
 }
@@ -404,8 +400,7 @@ void do_IRQ(struct pt_regs *regs)
        if (irq != NO_IRQ && irq != NO_IRQ_IGNORE)
                handle_one_irq(irq);
        else if (irq != NO_IRQ_IGNORE)
-               /* That's not SMP safe ... but who cares ? */
-               ppc_spurious_interrupts++;
+               __get_cpu_var(irq_stat).spurious_irqs++;
 
        irq_exit();
        set_irq_regs(old_regs);