[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: [Xen-devel] We still have to disable vtd for old chipset?



Aha, looks like a BIOS issue.  Upgrading from BIOS A02 to A03 to A04 seems to 
have fixed it.  I now see the "Intel VT-d has been enabled" in the xm dmesg.  
The support.dell.com webpage shows BIOS A03 included a fix to the ACPI table.

Now to see if device passthru works...  :)

Ed

-----Original Message-----
From: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx 
[mailto:xen-devel-bounces@xxxxxxxxxxxxxxxxxxx] On Behalf Of Nadolski, Ed
Sent: Tuesday, September 23, 2008 4:39 PM
To: Espen Skoglund; Neo Jia; Kumar, Venkat
Cc: Keir@xxxxxxxxxxxxxx; xen-devel@xxxxxxxxxxxxxxxxxxx; Fraser
Subject: RE: [Xen-devel] We still have to disable vtd for old chipset?

May I ask: on the Dell T7400, what kernel parameters do you use in grub.conf to 
enable VT-D?

On my DQ35 mobo with Xen 3.3.0 and CentOS 5.2, I used "kernel /xen-3.3.0.gz 
vtd=1 iommu=1 acpi=force apic=on", and it comes up & NIC passthru works. But 
the same line on my T7400 just crashes very early in the boot with a big hex 
dump.

If I set "acpi=off" it boots on the T7400, but I get a VT-D error: 
"intel_iommu_add_device: context mapping failed".


Is this addressed in xen-unstable?  Is there a way to tell if I have the old 
Seaburg chipset?  (This T7400 is pretty new tho.)

Thanks,
Ed Nadolski

-----Original Message-----
From: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx 
[mailto:xen-devel-bounces@xxxxxxxxxxxxxxxxxxx] On Behalf Of Espen Skoglund
Sent: Tuesday, June 03, 2008 4:50 AM
To: Neo Jia
Cc: xen-devel@xxxxxxxxxxxxxxxxxxx; Keir Fraser
Subject: Re: [Xen-devel] We still have to disable vtd for old chipset?

I've been using VT-d with a Dell T7400 myself without seeing this
particular problem.  As Keir suggests, I guess you have a pre-retail
version of the machine.  That said, I've had to patch up Xen to get my
version of the chipset working.  There were some bogus values in the
ACPI tables that determined the scope of the IOMMUs.  I'm not sure how
to reliably detect that this problem exists, or whether it's even
worth trying to fix.  I've been waiting for updates that solves the
problem, but there hasn't been anything so far.  I've attached the
patch in case someone else have similar problems.

        eSk



_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.