Re: [PATCH] expand /proc/interrupts to include missing vectors, v3

[Andi Kleen <andi@firstfloor.org>]

Joe Korty <joe.korty@ccur.com> writes:
> 	spurious interrupts
> 
> A threshold interrupt occurs when ECC memory correction
> is occuring at too high a frequency. 

It's configurable and the default is off. Also 
it's only on AMD hardware.

Your description is a little misleading.

> Thresholds are used
> by the ECC hardware as occasional ECC failures are part
> of normal operation,

Not really.


> ===================================================================
> --- 2.6.23-rc1-git7.orig/arch/i386/kernel/apic.c	2007-07-30 19:08:05.000000000 -0400
> +++ 2.6.23-rc1-git7/arch/i386/kernel/apic.c	2007-07-30 19:08:07.000000000 -0400
> @@ -1280,6 +1280,7 @@
>  	printk(KERN_INFO "spurious APIC interrupt on CPU#%d, "
>  	       "should never happen.\n", smp_processor_id());
>  	irq_exit();
> +	__get_cpu_var(irq_stat).irq_spur_counts++;

Wouldn't it be safer on preemptible kernels to have that inside
the irq_exit? 

>  }
>  
>  /*
> Index: 2.6.23-rc1-git7/arch/i386/kernel/cpu/mcheck/p4.c
> ===================================================================
> --- 2.6.23-rc1-git7.orig/arch/i386/kernel/cpu/mcheck/p4.c	2007-07-30 19:08:05.000000000 -0400
> +++ 2.6.23-rc1-git7/arch/i386/kernel/cpu/mcheck/p4.c	2007-07-30 19:08:07.000000000 -0400
> @@ -62,6 +62,7 @@
>  	irq_enter();
>  	vendor_thermal_interrupt(regs);
>  	irq_exit();
> +	__get_cpu_var(irq_stat).irq_thermal_counts++;
>  }
>  
>  /* P4/Xeon Thermal regulation detect and init */
> Index: 2.6.23-rc1-git7/arch/i386/kernel/irq.c
> ===================================================================
> --- 2.6.23-rc1-git7.orig/arch/i386/kernel/irq.c	2007-07-30 19:08:05.000000000 -0400
> +++ 2.6.23-rc1-git7/arch/i386/kernel/irq.c	2007-07-31 09:40:58.000000000 -0400
> @@ -284,14 +284,41 @@
>  		seq_printf(p, "NMI: ");
>  		for_each_online_cpu(j)
>  			seq_printf(p, "%10u ", nmi_count(j));
> -		seq_putc(p, '\n');
> +		seq_printf(p, "  Non-maskable interrupts\n");
>  #ifdef CONFIG_X86_LOCAL_APIC
>  		seq_printf(p, "LOC: ");
>  		for_each_online_cpu(j)
>  			seq_printf(p, "%10u ",
>  				per_cpu(irq_stat,j).apic_timer_irqs);
> -		seq_putc(p, '\n');
> +		seq_printf(p, "  Local interrupts\n");
>  #endif
> +#ifdef CONFIG_SMP
> +		seq_printf(p, "RES: ");

I think it would be better to use 5-6 char identifiers even
when it whacks the columns a bit; otherwise
nobody will know what it means. e.g. SCHED here. 

Also there you should update proc(5) and send a patch
to the manpage maintainer.

> Index: 2.6.23-rc1-git7/arch/x86_64/kernel/apic.c
> ===================================================================
> --- 2.6.23-rc1-git7.orig/arch/x86_64/kernel/apic.c	2007-07-30 19:08:05.000000000 -0400
> +++ 2.6.23-rc1-git7/arch/x86_64/kernel/apic.c	2007-07-30 19:08:07.000000000 -0400
> @@ -1118,6 +1118,7 @@
>  asmlinkage void smp_spurious_interrupt(void)
>  {
>  	unsigned int v;
> +

Don't add white space.


-Andi