I am seeing the following error message in xm dmesg. (XEN) [VT-D]utils.c:59: *** VT-d disabled - pre C0-step Seaburg found (XEN) [VT-D]utils.c:62: *** vendor = 8086 device = 4000 revision = 10 This is on Dell T7400. And the change is http://lists.xensource.com/archives/html/xen-changelog/2007-09/msg00284.html. So, I am wondering if there is any fix for this? Thanks, Neo -- I would remember that if researchers were not ambitious probably today we haven''t the technology we are using! _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Keir Fraser
2008-Jun-03 07:15 UTC
Re: [Xen-devel] We still have to disable vtd for old chipset?
I believe the hardware interface was different in older chipsets, so there''s really no chance we''ll support them. -- Keir On 3/6/08 02:00, "Neo Jia" <neojia@gmail.com> wrote:> I am seeing the following error message in xm dmesg. > > (XEN) [VT-D]utils.c:59: *** VT-d disabled - pre C0-step Seaburg found > (XEN) [VT-D]utils.c:62: *** vendor = 8086 device = 4000 revision = 10 > > This is on Dell T7400. And the change is > http://lists.xensource.com/archives/html/xen-changelog/2007-09/msg00284.html. > > So, I am wondering if there is any fix for this? > > Thanks, > Neo_______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Neo Jia
2008-Jun-03 07:17 UTC
Re: [Xen-devel] We still have to disable vtd for old chipset?
> sudo /sbin/lspciPassword: 00:00.0 Host bridge: Intel Corporation 5400 Chipset Memory Controller Hub (rev 10) 00:01.0 PCI bridge: Intel Corporation 5400 Chipset PCI Express Port 1 (rev 10) 00:05.0 PCI bridge: Intel Corporation 5400 Chipset PCI Express Port 5 (rev 10) 00:09.0 PCI bridge: Intel Corporation 5400 Chipset PCI Express Port 9 (rev 10) 00:10.0 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) 00:10.1 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) 00:10.2 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) 00:10.3 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) 00:10.4 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) 00:11.0 Host bridge: Intel Corporation 5400 Chipset CE/SF Registers (rev 10) 00:15.0 Host bridge: Intel Corporation 5400 Chipset FBD Registers (rev 10) In the user mailing list, I saw somebody is using VT-D on this chipset? Thanks, Neo On Tue, Jun 3, 2008 at 12:15 AM, Keir Fraser <keir.fraser@eu.citrix.com> wrote:> I believe the hardware interface was different in older chipsets, so there''s > really no chance we''ll support them. > > -- Keir > > On 3/6/08 02:00, "Neo Jia" <neojia@gmail.com> wrote: > >> I am seeing the following error message in xm dmesg. >> >> (XEN) [VT-D]utils.c:59: *** VT-d disabled - pre C0-step Seaburg found >> (XEN) [VT-D]utils.c:62: *** vendor = 8086 device = 4000 revision = 10 >> >> This is on Dell T7400. And the change is >> http://lists.xensource.com/archives/html/xen-changelog/2007-09/msg00284.html. >> >> So, I am wondering if there is any fix for this? >> >> Thanks, >> Neo > > >-- I would remember that if researchers were not ambitious probably today we haven''t the technology we are using! _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Keir Fraser
2008-Jun-03 07:23 UTC
Re: [Xen-devel] We still have to disable vtd for old chipset?
The interface changed in a pre-release stepping of that chipset model. I assume you must have a development (not retail) machine? -- Keir On 3/6/08 08:17, "Neo Jia" <neojia@gmail.com> wrote:>> sudo /sbin/lspci > Password: > 00:00.0 Host bridge: Intel Corporation 5400 Chipset Memory Controller > Hub (rev 10) > 00:01.0 PCI bridge: Intel Corporation 5400 Chipset PCI Express Port 1 (rev 10) > 00:05.0 PCI bridge: Intel Corporation 5400 Chipset PCI Express Port 5 (rev 10) > 00:09.0 PCI bridge: Intel Corporation 5400 Chipset PCI Express Port 9 (rev 10) > 00:10.0 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) > 00:10.1 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) > 00:10.2 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) > 00:10.3 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) > 00:10.4 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) > 00:11.0 Host bridge: Intel Corporation 5400 Chipset CE/SF Registers (rev 10) > 00:15.0 Host bridge: Intel Corporation 5400 Chipset FBD Registers (rev 10) > > In the user mailing list, I saw somebody is using VT-D on this chipset? > > Thanks, > Neo > > On Tue, Jun 3, 2008 at 12:15 AM, Keir Fraser <keir.fraser@eu.citrix.com> > wrote: >> I believe the hardware interface was different in older chipsets, so there''s >> really no chance we''ll support them. >> >> -- Keir >> >> On 3/6/08 02:00, "Neo Jia" <neojia@gmail.com> wrote: >> >>> I am seeing the following error message in xm dmesg. >>> >>> (XEN) [VT-D]utils.c:59: *** VT-d disabled - pre C0-step Seaburg found >>> (XEN) [VT-D]utils.c:62: *** vendor = 8086 device = 4000 revision = 10 >>> >>> This is on Dell T7400. And the change is >>>http://lists.xensource.com/archives/html/xen-changelog/2007-09/msg00284.html>>> .>>> >>> So, I am wondering if there is any fix for this? >>> >>> Thanks, >>> Neo >> >> >> > >_______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Espen Skoglund
2008-Jun-03 10:50 UTC
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 [Neo Jia]>> sudo /sbin/lspci > Password: > 00:00.0 Host bridge: Intel Corporation 5400 Chipset Memory Controller > Hub (rev 10) > 00:01.0 PCI bridge: Intel Corporation 5400 Chipset PCI Express Port 1 (rev 10) > 00:05.0 PCI bridge: Intel Corporation 5400 Chipset PCI Express Port 5 (rev 10) > 00:09.0 PCI bridge: Intel Corporation 5400 Chipset PCI Express Port 9 (rev 10) > 00:10.0 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) > 00:10.1 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) > 00:10.2 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) > 00:10.3 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) > 00:10.4 Host bridge: Intel Corporation 5400 Chipset FSB Registers (rev 10) > 00:11.0 Host bridge: Intel Corporation 5400 Chipset CE/SF Registers (rev 10) > 00:15.0 Host bridge: Intel Corporation 5400 Chipset FBD Registers (rev 10)> In the user mailing list, I saw somebody is using VT-D on this chipset?> Thanks, > Neo> On Tue, Jun 3, 2008 at 12:15 AM, Keir Fraser <keir.fraser@eu.citrix.com> wrote: >> I believe the hardware interface was different in older chipsets, so there''s >> really no chance we''ll support them. >> >> -- Keir >> >> On 3/6/08 02:00, "Neo Jia" <neojia@gmail.com> wrote: >> >>> I am seeing the following error message in xm dmesg. >>> >>> (XEN) [VT-D]utils.c:59: *** VT-d disabled - pre C0-step Seaburg found >>> (XEN) [VT-D]utils.c:62: *** vendor = 8086 device = 4000 revision = 10 >>> >>> This is on Dell T7400. And the change is >>> http://lists.xensource.com/archives/html/xen-changelog/2007-09/msg00284.html. >>> >>> So, I am wondering if there is any fix for this?_______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Kay, Allen M
2008-Jun-03 15:19 UTC
RE: [Xen-devel] We still have to disable vtd for old chipset?
This check was needed as some earlier versions of server platform does not support p2m/vt-d page table sharing. Since now we have separate page tables, we don''t need that check anymore. You can just remove the check locally to get it to work on your system. We will submit a patch to remove it in the upstream. Allen>-----Original Message----- >From: xen-devel-bounces@lists.xensource.com >[mailto:xen-devel-bounces@lists.xensource.com] On Behalf Of Neo Jia >Sent: Monday, June 02, 2008 6:01 PM >To: xen-devel@lists.xensource.com >Subject: [Xen-devel] We still have to disable vtd for old chipset? > >I am seeing the following error message in xm dmesg. > >(XEN) [VT-D]utils.c:59: *** VT-d disabled - pre C0-step Seaburg found >(XEN) [VT-D]utils.c:62: *** vendor = 8086 device = 4000 revision = 10 > >This is on Dell T7400. And the change is >http://lists.xensource.com/archives/html/xen-changelog/2007-09/ >msg00284.html. > >So, I am wondering if there is any fix for this? > >Thanks, >Neo >-- >I would remember that if researchers were not ambitious >probably today we haven''t the technology we are using! > >_______________________________________________ >Xen-devel mailing list >Xen-devel@lists.xensource.com >http://lists.xensource.com/xen-devel >_______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Neo Jia
2008-Jun-03 15:22 UTC
Re: [Xen-devel] We still have to disable vtd for old chipset?
So, Xen VT-d should work on my system (pre-retail)? Thanks, Neo On Tue, Jun 3, 2008 at 8:19 AM, Kay, Allen M <allen.m.kay@intel.com> wrote:> This check was needed as some earlier versions of server platform does > not support p2m/vt-d page table sharing. > > Since now we have separate page tables, we don''t need that check > anymore. You can just remove the check locally to get it to work on > your system. > > We will submit a patch to remove it in the upstream. > > Allen > >>-----Original Message----- >>From: xen-devel-bounces@lists.xensource.com >>[mailto:xen-devel-bounces@lists.xensource.com] On Behalf Of Neo Jia >>Sent: Monday, June 02, 2008 6:01 PM >>To: xen-devel@lists.xensource.com >>Subject: [Xen-devel] We still have to disable vtd for old chipset? >> >>I am seeing the following error message in xm dmesg. >> >>(XEN) [VT-D]utils.c:59: *** VT-d disabled - pre C0-step Seaburg found >>(XEN) [VT-D]utils.c:62: *** vendor = 8086 device = 4000 revision = 10 >> >>This is on Dell T7400. And the change is >>http://lists.xensource.com/archives/html/xen-changelog/2007-09/ >>msg00284.html. >> >>So, I am wondering if there is any fix for this? >> >>Thanks, >>Neo >>-- >>I would remember that if researchers were not ambitious >>probably today we haven''t the technology we are using! >> >>_______________________________________________ >>Xen-devel mailing list >>Xen-devel@lists.xensource.com >>http://lists.xensource.com/xen-devel >> >-- I would remember that if researchers were not ambitious probably today we haven''t the technology we are using! _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Kay, Allen M
2008-Jun-03 15:26 UTC
RE: [Xen-devel] We still have to disable vtd for old chipset?
It should work assuming your BIOS is reporting VT-d correctly. At least the page table sharing should no longer be the issue. Allen>-----Original Message----- >From: Neo Jia [mailto:neojia@gmail.com] >Sent: Tuesday, June 03, 2008 8:23 AM >To: Kay, Allen M >Cc: xen-devel@lists.xensource.com >Subject: Re: [Xen-devel] We still have to disable vtd for old chipset? > >So, Xen VT-d should work on my system (pre-retail)? > >Thanks, >Neo > >On Tue, Jun 3, 2008 at 8:19 AM, Kay, Allen M ><allen.m.kay@intel.com> wrote: >> This check was needed as some earlier versions of server >platform does >> not support p2m/vt-d page table sharing. >> >> Since now we have separate page tables, we don''t need that check >> anymore. You can just remove the check locally to get it to work on >> your system. >> >> We will submit a patch to remove it in the upstream. >> >> Allen >> >>>-----Original Message----- >>>From: xen-devel-bounces@lists.xensource.com >>>[mailto:xen-devel-bounces@lists.xensource.com] On Behalf Of Neo Jia >>>Sent: Monday, June 02, 2008 6:01 PM >>>To: xen-devel@lists.xensource.com >>>Subject: [Xen-devel] We still have to disable vtd for old chipset? >>> >>>I am seeing the following error message in xm dmesg. >>> >>>(XEN) [VT-D]utils.c:59: *** VT-d disabled - pre C0-step Seaburg found >>>(XEN) [VT-D]utils.c:62: *** vendor = 8086 device = 4000 >revision = 10 >>> >>>This is on Dell T7400. And the change is >>>http://lists.xensource.com/archives/html/xen-changelog/2007-09/ >>>msg00284.html. >>> >>>So, I am wondering if there is any fix for this? >>> >>>Thanks, >>>Neo >>>-- >>>I would remember that if researchers were not ambitious >>>probably today we haven''t the technology we are using! >>> >>>_______________________________________________ >>>Xen-devel mailing list >>>Xen-devel@lists.xensource.com >>>http://lists.xensource.com/xen-devel >>> >> > > > >-- >I would remember that if researchers were not ambitious >probably today we haven''t the technology we are using! >_______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Ian Jackson
2008-Jun-03 15:36 UTC
RE: [Xen-devel] We still have to disable vtd for old chipset?
Kay, Allen M writes ("RE: [Xen-devel] We still have to disable vtd for old
chipset?"):> It should work assuming your BIOS is reporting VT-d correctly. At least
> the page table sharing should no longer be the issue.
Are you sure ? My understanding (admittedly half-remembered from some
technical note that came with the motherboard replacement to bring our
pre-C0 pre-production VT-d system up to date) was that the iommu page
table format is different in the pre-C0 chipsets.
That would explain why pagetable sharing between iommu and normal mmu
is not possible with those chipsets. But it also makes those pre-C0
chipsets completely incompatible with all of the code in Xen, because
Xen doesn''t know anything about those pre-C0 pagetables ? (And
isn''t
going to be taught.)
Ian.
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xensource.com
http://lists.xensource.com/xen-devel
Neo Jia
2008-Jun-03 18:38 UTC
Re: [Xen-devel] We still have to disable vtd for old chipset?
I just tried it by removing the checking. The following is from my xm dmesg. Does those warning matter? (XEN) [VT-D]iommu.c:1722: Queued Invalidation hardware not found (XEN) [VT-D]iommu.c:1722: Queued Invalidation hardware not found (XEN) [VT-D]iommu.c:1722: Queued Invalidation hardware not found (XEN) [VT-D]iommu.c:1722: Queued Invalidation hardware not found (XEN) [VT-D]iommu.c:1730: Interrupt Remapping hardware not found (XEN) [VT-D]iommu.c:1730: Interrupt Remapping hardware not found (XEN) [VT-D]iommu.c:1730: Interrupt Remapping hardware not found (XEN) [VT-D]iommu.c:1730: Interrupt Remapping hardware not found (XEN) I/O virtualisation enabled (XEN) [VT-D]iommu.c:1241:d32767 context_context_mapping: nested PCI bridge not supported: bdf = 0:9:0 sec_bus = 3 sub_bus = 7 (XEN) [VT-D]iommu.c:1241:d32767 context_context_mapping: nested PCI bridge not supported: bdf = 3:0:0 sec_bus = 4 sub_bus = 6 (XEN) *** LOADING DOMAIN 0 *** Thanks, Neo On Tue, Jun 3, 2008 at 8:36 AM, Ian Jackson <Ian.Jackson@eu.citrix.com> wrote:> Kay, Allen M writes ("RE: [Xen-devel] We still have to disable vtd for old chipset?"): >> It should work assuming your BIOS is reporting VT-d correctly. At least >> the page table sharing should no longer be the issue. > > Are you sure ? My understanding (admittedly half-remembered from some > technical note that came with the motherboard replacement to bring our > pre-C0 pre-production VT-d system up to date) was that the iommu page > table format is different in the pre-C0 chipsets. > > That would explain why pagetable sharing between iommu and normal mmu > is not possible with those chipsets. But it also makes those pre-C0 > chipsets completely incompatible with all of the code in Xen, because > Xen doesn''t know anything about those pre-C0 pagetables ? (And isn''t > going to be taught.) > > Ian. >-- I would remember that if researchers were not ambitious probably today we haven''t the technology we are using! _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Kay, Allen M
2008-Jun-03 19:07 UTC
RE: [Xen-devel] We still have to disable vtd for old chipset?
Queued invalidation and Interrupt Remapping are for Nahalem generation of HW. The messages are probably too verbose. Nested PCI bridge means you the devices behind more than 1 level of pci bridges are found. As we don''t support this in our code yet, these devices most likely don''t work. Try PCI-e device passthrough first. They should work for you. We are thinking of implementing a new "xm" tool to list the devices that are available for passthrough to make this stuff easier. Allen>-----Original Message----- >From: Neo Jia [mailto:neojia@gmail.com] >Sent: Tuesday, June 03, 2008 11:39 AM >To: Ian Jackson >Cc: Kay, Allen M; xen-devel@lists.xensource.com >Subject: Re: [Xen-devel] We still have to disable vtd for old chipset? > >I just tried it by removing the checking. The following is from my xm >dmesg. Does those warning matter? > > >(XEN) [VT-D]iommu.c:1722: Queued Invalidation hardware not found >(XEN) [VT-D]iommu.c:1722: Queued Invalidation hardware not found >(XEN) [VT-D]iommu.c:1722: Queued Invalidation hardware not found >(XEN) [VT-D]iommu.c:1722: Queued Invalidation hardware not found >(XEN) [VT-D]iommu.c:1730: Interrupt Remapping hardware not found >(XEN) [VT-D]iommu.c:1730: Interrupt Remapping hardware not found >(XEN) [VT-D]iommu.c:1730: Interrupt Remapping hardware not found >(XEN) [VT-D]iommu.c:1730: Interrupt Remapping hardware not found >(XEN) I/O virtualisation enabled >(XEN) [VT-D]iommu.c:1241:d32767 context_context_mapping: nested PCI >bridge not supported: bdf = 0:9:0 sec_bus = 3 sub_bus = 7 >(XEN) [VT-D]iommu.c:1241:d32767 context_context_mapping: nested PCI >bridge not supported: bdf = 3:0:0 sec_bus = 4 sub_bus = 6 >(XEN) *** LOADING DOMAIN 0 *** > > >Thanks, >Neo > >On Tue, Jun 3, 2008 at 8:36 AM, Ian Jackson ><Ian.Jackson@eu.citrix.com> wrote: >> Kay, Allen M writes ("RE: [Xen-devel] We still have to >disable vtd for old chipset?"): >>> It should work assuming your BIOS is reporting VT-d >correctly. At least >>> the page table sharing should no longer be the issue. >> >> Are you sure ? My understanding (admittedly half-remembered >from some >> technical note that came with the motherboard replacement to >bring our >> pre-C0 pre-production VT-d system up to date) was that the iommu page >> table format is different in the pre-C0 chipsets. >> >> That would explain why pagetable sharing between iommu and normal mmu >> is not possible with those chipsets. But it also makes those pre-C0 >> chipsets completely incompatible with all of the code in Xen, because >> Xen doesn''t know anything about those pre-C0 pagetables ? (And isn''t >> going to be taught.) >> >> Ian. >> > > > >-- >I would remember that if researchers were not ambitious >probably today we haven''t the technology we are using! >_______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Kay, Allen M
2008-Jun-03 19:20 UTC
RE: [Xen-devel] We still have to disable vtd for old chipset?
> >Are you sure ? My understanding (admittedly half-remembered from some >technical note that came with the motherboard replacement to bring our >pre-C0 pre-production VT-d system up to date) was that the iommu page >table format is different in the pre-C0 chipsets. > >That would explain why pagetable sharing between iommu and normal mmu >is not possible with those chipsets. But it also makes those pre-C0 >chipsets completely incompatible with all of the code in Xen, because >Xen doesn''t know anything about those pre-C0 pagetables ? (And isn''t >going to be taught.) >I think the issues was the pre-c0 seaburg was force checking 0 for some bits by the cpu. It''s just something for a quick try. I don''t have access to pre-c0 HW anymore. allen _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Nadolski, Ed
2008-Sep-23 22:38 UTC
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@lists.xensource.com
[mailto:xen-devel-bounces@lists.xensource.com] On Behalf Of Espen Skoglund
Sent: Tuesday, June 03, 2008 4:50 AM
To: Neo Jia
Cc: xen-devel@lists.xensource.com; 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@lists.xensource.com
http://lists.xensource.com/xen-devel
Nadolski, Ed
2008-Sep-23 23:08 UTC
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@lists.xensource.com
[mailto:xen-devel-bounces@lists.xensource.com] On Behalf Of Nadolski, Ed
Sent: Tuesday, September 23, 2008 4:39 PM
To: Espen Skoglund; Neo Jia; Kumar, Venkat
Cc: Keir@mail2.lsil.com; xen-devel@lists.xensource.com; 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@lists.xensource.com
[mailto:xen-devel-bounces@lists.xensource.com] On Behalf Of Espen Skoglund
Sent: Tuesday, June 03, 2008 4:50 AM
To: Neo Jia
Cc: xen-devel@lists.xensource.com; 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@lists.xensource.com
http://lists.xensource.com/xen-devel
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xensource.com
http://lists.xensource.com/xen-devel