Re: [2.6] Problem with PDC20265 on system with I865 chipset and PIVHT

[Zwane Mwaikambo]

On Fri, 13 Jan 2006, Andrew Morton wrote:

> This decode from eip onwards should be reliable
> 
> Code;  c0110471 No symbols available
> 00000000 <_EIP>:
> Code;  c0110471 No symbols available   <=====
>    0:   c7 05 b0 d0 ff ff 00      movl   $0x0,0xffffd0b0   <=====
> Code;  c0110478 No symbols available
>    7:   00 00 00 
> Code;  c011047b No symbols available
>    a:   f0 0f b3 15 38 d6 57      lock btr %edx,0xc057d638
> Code;  c0110482 No symbols available
>   11:   c0 
> Code;  c0110483 No symbols available
>   12:   c3                        ret    
> Code;  c0110484 No symbols available
>   13:   83                        .byte 0x83
> Code;  c0110485 No symbols available
>   14:   78                        .byte 0x78
> 
> 
> That's oopsing when trying to write to the APIC:
> 
> 	apic_write_around(APIC_EOI, 0);
> 
> <cc's x86 people>
> 
> Is there any sane way in which APIC accesses can fault, or does this
> indicate bad hardware?

Without pagetable corruption no they shouldn't fault, interestingly this 
looks like;

http://bugzilla.kernel.org/show_bug.cgi?id=5565

Albeit with a pdc20262. Miroslaw, are there any other similarities in 
hardware with that bugzilla entry?

Thanks,
	Zwane

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/