Re: x86-64 Uncorrected machine check panic on boot

From: Andi Kleen
Date: Thu Apr 21 2005 - 06:58:00 EST


On Tue, Apr 19, 2005 at 10:12:43PM +0900, Akinobu Mita wrote:
> Hello,
>
> I got the following Machine Check Exception on 4-way Opteron Server.
> I've tried 2.6.11.7 and 2.6.12-rc2.
> The kernel parameter "nomce" could help to boot it up.

Sounds like a bogus BIOS. It should disable these machine checks
for timeout on pci config access imho.

What 4way board did you use? Can you check if there is a BIOS
update?

-Andi

>
> I wrote this panic messages by hand.
> This panic seems to happen around "arch/x86_64/pci/../../i386/pci/direct.c:28"
>
> ==========================================================
> Calling initcall 0xffffffff........: netlink_proto_init...
> NET: Registered protocol family 16
>
> Calling initcall 0xffffffff........: pcibus_class_init...
> Calling initcall 0xffffffff........: pci_driver_init
> Calling initcall 0xffffffff........: tty_class_init
> Calling initcall 0xffffffff........: mtrr_if_init
> Calling initcall 0xffffffff........: pci_direct_init
>
> CPU3: Machine Check Exception: 7 Bank 3: b40000000000083b
> RIP 10: <ffffffff802cfefe> {pci_conf1_read+0xce/0x110}
> TSC 85ece4f ADDR fdfc000cfe
>
> kernel panic - not syncing: Uncorrected machine check
> ==========================================================
>
>
> $ addr2line -e vmlinux ffffffff802cfee0
> arch/x86_64/pci/../../i386/pci/direct.c:28
>
> $ addr2line -e vmlinux ffffffff802cfee2
> include/asm/io.h:81
>
> $ addr2line -e vmlinux ffffffff802cfefe
> include/asm/io.h:84
>
>
-
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/