Re: "APIC error on CPUx" - what does this mean?

[Martin Eriksson]

----- Original Message -----
From: "Petr Vandrovec" <[e-mail]>
To: "Chris Wedgwood" <[e-mail]>
Cc: <[e-mail]>; "Linux Kernel Mailing List"
<[e-mail]>; <[e-mail]>
Sent: Monday, January 07, 2002 2:16 PM
Subject: Re: "APIC error on CPUx" - what does this mean?

> On  8 Jan 02 at 2:08, Chris Wedgwood wrote:
> > On Mon, Jan 07, 2002 at 01:29:42PM +0100, Petr Vandrovec wrote:
> >
> >     They are spurious IRQ 7, just message is printed only once during
> >     kernel lifetime... I have about three spurious IRQ 7 per each 1000
> >     interrupts delivered to CPU. It is on A7V (Via KT133).
> >
> > Any idea _why_ these occur though?  It seems some mainboards produce a
> > plethora of these whilst others never produce these...
>
> Nope. Probably when CPU is in local APIC mode, it acknowledges interrupts
> to chipset with different timming, and from time to time CPU still
> sees IRQ pending, so it asks for vector, but as chipset has no
> interrupt pending, it answers with IRQ7. I did no analysis to find
> whether IRQ7 happens directly when we send confirmation to 8259,
> or whether it happens due to some noise on IRQ line.
>
> AFAIK it happens only on VIA based boards, and only if (AMD) CPU is using
> APIC.

This (APIC errors) happened very often with my BP6 board too, but with
recent kernels I don't get many of these messages.

As for spurious interrupts, I had these coming every five minutes on my
Cyrix 6x86/SiS 5597 box. But this "settled" when I moved the box to another
corner in the room, and also did some interior adjustments of cables and
such (it is a server running in a very crammed slimline desktop box, with a
HUB taped to the floppy mount =)

_____________________________________________________
|  Martin Eriksson <[e-mail]>
|  MSc CSE student, department of Computing Science
|  Umeå University, Sweden