Re: [Xen-devel] [xen-unstable bisection] complete test-amd64-amd64-xl-xsm

["Jan Beulich" <JBeulich@xxxxxxxx>]

>>> On 14.06.15 at 22:54, <osstest@xxxxxxxxxxxxxxx> wrote:
> branch xen-unstable
> xen branch xen-unstable
> job test-amd64-amd64-xl-xsm
> test xen-boot
> 
> Tree: linux git://xenbits.xen.org/linux-pvops.git
> Tree: linuxfirmware git://xenbits.xen.org/osstest/linux-firmware.git
> Tree: qemu git://xenbits.xen.org/staging/qemu-xen-unstable.git
> Tree: qemuu git://xenbits.xen.org/staging/qemu-upstream-unstable.git
> Tree: xen git://xenbits.xen.org/xen.git
> 
> *** Found and reproduced problem changeset ***
> 
>   Bug is in tree:  xen git://xenbits.xen.org/xen.git
>   Bug introduced:  73cb5d43a8f48930e4594ef7b15b974487651ffe
>   Bug not present: 284ffb4f9b0d5c3a33c4c5bd87645d0cc342ca96
> 
> 
>   commit 73cb5d43a8f48930e4594ef7b15b974487651ffe
>   Author: Jan Beulich <jbeulich@xxxxxxxx>
>   Date:   Thu Jun 11 11:53:20 2015 +0200
>   
>       x86/MSI-X: use qword MMIO access for address writes
>       
>       Now that we support it for our guests, let's do so ourselves too.
>       
>       Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
>       Reviewed-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>

The only thing I can see us doing here is revert. Three machine
pairs are affected, yet each exhibits the problem in different ways:
- elbling[01] see tg3 transmit timeouts
- merlot[01] see SERR NMIs
- godello[01] appear to suffer from silent reboots
Other than assuming that the NICs of these systems (all using the
tg3 driver) don't properly support what the standard mandates I
have no explanation so far. Maybe once I run the code on a few
more systems here I can find one also showing such bad behavior.

Jan


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel