VT-d HowTo Update

VT-d HowTo Update

[Simon Horman]

Hi,

in preparation for 3.4.0 I have made a number of updates to the VT-d Howto.
I have tried to retain the original information while reorganising things a
bit. I have also added information on recent work I have done in this area.

Apologies in advance for any errors, accidental deletions, etc...

http://wiki.xensource.com/xenwiki/VTdHowTo

-- 
Simon Horman
  VA Linux Systems Japan K.K. Satellite Lab in Sydney, Australia
  H: www.vergenet.net/~horms/            W: www.valinux.co.jp/en

RE: VT-d HowTo Update

[Han, Weidong]

Simon Horman wrote:
> Hi,
> 
> in preparation for 3.4.0 I have made a number of updates to the VT-d
> Howto. I have tried to retain the original information while
> reorganising things a bit. I have also added information on recent
> work I have done in this area. 
> 
> Apologies in advance for any errors, accidental deletions, etc...
> 
> http://wiki.xensource.com/xenwiki/VTdHowTo

Simon,

It looks fine for me. It's good to update VT-d Howto according to upstream status. Thanks.

Regards,
Weidong

RE: VT-d HowTo Update

[Cui, Dexuan]

Simon Horman wrote:
> Hi,
> 
> in preparation for 3.4.0 I have made a number of updates to the VT-d
> Howto. I have tried to retain the original information while
> reorganising things a bit. I have also added information on recent
> work I have done in this area. 
> 
> Apologies in advance for any errors, accidental deletions, etc...
> 
> http://wiki.xensource.com/xenwiki/VTdHowTo

Hi Simon,
There is a bug: we can't pci-detach a statically-assigned (I mean: use the pci string in hvm config file) devices for hvm guest.
Accordong my limited experience, after a device is assigned to hvm guest, ioemu does write the correct vslots value into xenstore, but looks xend can't get the correct value somwhow.
Could you help to have a look? Thanks!

-- Dexuan

Re: VT-d HowTo Update

[Espen Skoglund]

You may also want to mention the various boot time parameters (or at
least some of them).  The following comment is snipped from
xen/drivers/passthrough/iommu.c.

	eSk

/*
 * The 'iommu' parameter enables the IOMMU.  Optional comma separated
 * value may contain:
 *
 *   off|no|false|disable       Disable IOMMU (default)
 *   pv                         Enable IOMMU for PV domains
 *   no-pv                      Disable IOMMU for PV domains (default)
 *   force|required             Don't boot unless IOMMU is enabled
 *   passthrough                Enable VT-d DMA passthrough (no DMA
 *                              translation for Dom0)
 *   no-snoop                   Disable VT-d Snoop Control
 *   no-qinval                  Disable VT-d Queued Invalidation
 *   no-intremap                Disable VT-d Interrupt Remapping
 */


[Simon Horman]
> Hi,
> in preparation for 3.4.0 I have made a number of updates to the VT-d Howto.
> I have tried to retain the original information while reorganising things a
> bit. I have also added information on recent work I have done in this area.

> Apologies in advance for any errors, accidental deletions, etc...

> http://wiki.xensource.com/xenwiki/VTdHowTo

> -- 
> Simon Horman
>   VA Linux Systems Japan K.K. Satellite Lab in Sydney, Australia
>   H: www.vergenet.net/~horms/            W: www.valinux.co.jp/en


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

Re: VT-d HowTo Update

[Leonard Michelet]

Hi, Simon
I've read it, and it's much more complete than before. Thanks a lot.
Beside, you don't write about the library PCI devel that you need when you
compile Xen to enable PCI passtrought, and so, the use of VT-d. Debian
package is libpci_dev.
Is this library still necessary to use VT-d? If yes, shouldn't you write
about it in this wiki page?
>From my experience, I lost some times before finding that I had to compil
with this lib.
Hope this will help someone.

Bye

Léonard

Simon Horman wrote:
> 
> Hi,
> 
> in preparation for 3.4.0 I have made a number of updates to the VT-d
> Howto.
> I have tried to retain the original information while reorganising things
> a
> bit. I have also added information on recent work I have done in this
> area.
> 
> Apologies in advance for any errors, accidental deletions, etc...
> 
> http://wiki.xensource.com/xenwiki/VTdHowTo
> 
> -- 
> Simon Horman
>   VA Linux Systems Japan K.K. Satellite Lab in Sydney, Australia
>   H: www.vergenet.net/~horms/            W: www.valinux.co.jp/en
> 
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xensource.com
> http://lists.xensource.com/xen-devel
> 
> 

-- 
View this message in context: http://www.nabble.com/VT-d-HowTo-Update-tp23150620p23156969.html
Sent from the Xen - Dev mailing list archive at Nabble.com.

Re: VT-d HowTo Update

[Simon Horman]

On Tue, Apr 21, 2009 at 05:16:14PM +0800, Cui, Dexuan wrote:
> Simon Horman wrote:
> > Hi,
> > 
> > in preparation for 3.4.0 I have made a number of updates to the VT-d
> > Howto. I have tried to retain the original information while
> > reorganising things a bit. I have also added information on recent
> > work I have done in this area. 
> > 
> > Apologies in advance for any errors, accidental deletions, etc...
> > 
> > http://wiki.xensource.com/xenwiki/VTdHowTo
> 
> Hi Simon,
> There is a bug: we can't pci-detach a statically-assigned (I mean: use the pci string in hvm config file) devices for hvm guest.
> Accordong my limited experience, after a device is assigned to hvm guest, ioemu does write the correct vslots value into xenstore, but looks xend can't get the correct value somwhow.
> Could you help to have a look? Thanks!

Sure, I can look into that. Do you have a version that you are worried
about? It did seem to work the last time that I checked.

-- 
Simon Horman
  VA Linux Systems Japan K.K. Satellite Lab in Sydney, Australia
  H: www.vergenet.net/~horms/            W: www.valinux.co.jp/en

Re: VT-d HowTo Update

[Simon Horman]

On Tue, Apr 21, 2009 at 07:11:00AM -0700, Leonard Michelet wrote:
> 
> Hi, Simon
> I've read it, and it's much more complete than before. Thanks a lot.
> Beside, you don't write about the library PCI devel that you need when you
> compile Xen to enable PCI passtrought, and so, the use of VT-d. Debian
> package is libpci_dev.
> Is this library still necessary to use VT-d? If yes, shouldn't you write
> about it in this wiki page?
> >From my experience, I lost some times before finding that I had to compil
> with this lib.

Yes, I lost some time due to that too, and it is neccessary.

I tried to avoid discussing compilation issues as its a bit of a can of
worms because they are usually very dependant on the system in use.
But this probably is worth a mention.

-- 
Simon Horman
  VA Linux Systems Japan K.K. Satellite Lab in Sydney, Australia
  H: www.vergenet.net/~horms/            W: www.valinux.co.jp/en

Re: VT-d HowTo Update

[Simon Horman]

On Tue, Apr 21, 2009 at 11:08:39AM +0100, Espen Skoglund wrote:
> You may also want to mention the various boot time parameters (or at
> least some of them).  The following comment is snipped from
> xen/drivers/passthrough/iommu.c.
> 
> 	eSk
> 
> /*
>  * The 'iommu' parameter enables the IOMMU.  Optional comma separated
>  * value may contain:
>  *
>  *   off|no|false|disable       Disable IOMMU (default)
>  *   pv                         Enable IOMMU for PV domains
>  *   no-pv                      Disable IOMMU for PV domains (default)
>  *   force|required             Don't boot unless IOMMU is enabled
>  *   passthrough                Enable VT-d DMA passthrough (no DMA
>  *                              translation for Dom0)
>  *   no-snoop                   Disable VT-d Snoop Control
>  *   no-qinval                  Disable VT-d Queued Invalidation
>  *   no-intremap                Disable VT-d Interrupt Remapping
>  */

Thanks, that is a good point. Though to be honest I'm not
entirely sure what the last 3 options do.

-- 
Simon Horman
  VA Linux Systems Japan K.K. Satellite Lab in Sydney, Australia
  H: www.vergenet.net/~horms/            W: www.valinux.co.jp/en

Re: VT-d HowTo Update

[Simon Horman]

On Wed, Apr 22, 2009 at 09:13:33AM +1000, Simon Horman wrote:
> On Tue, Apr 21, 2009 at 07:11:00AM -0700, Leonard Michelet wrote:
> > 
> > Hi, Simon
> > I've read it, and it's much more complete than before. Thanks a lot.
> > Beside, you don't write about the library PCI devel that you need when you
> > compile Xen to enable PCI passtrought, and so, the use of VT-d. Debian
> > package is libpci_dev.
> > Is this library still necessary to use VT-d? If yes, shouldn't you write
> > about it in this wiki page?
> > >From my experience, I lost some times before finding that I had to compil
> > with this lib.
> 
> Yes, I lost some time due to that too, and it is neccessary.
> 
> I tried to avoid discussing compilation issues as its a bit of a can of
> worms because they are usually very dependant on the system in use.
> But this probably is worth a mention.

I have updated the HowTo with some information on this.

http://wiki.xensource.com/xenwiki/VTdHowTo

-- 
Simon Horman
  VA Linux Systems Japan K.K. Satellite Lab in Sydney, Australia
  H: www.vergenet.net/~horms/            W: www.valinux.co.jp/en

Re: VT-d HowTo Update

[Tej]

On Wed, Apr 22, 2009 at 6:33 AM, Simon Horman <horms@verge.net.au> wrote:
> On Wed, Apr 22, 2009 at 09:13:33AM +1000, Simon Horman wrote:
>> On Tue, Apr 21, 2009 at 07:11:00AM -0700, Leonard Michelet wrote:
>> >
>> > Hi, Simon
>> > I've read it, and it's much more complete than before. Thanks a lot.
>> > Beside, you don't write about the library PCI devel that you need when you
>> > compile Xen to enable PCI passtrought, and so, the use of VT-d. Debian
>> > package is libpci_dev.
>> > Is this library still necessary to use VT-d? If yes, shouldn't you write
>> > about it in this wiki page?
>> > >From my experience, I lost some times before finding that I had to compil
>> > with this lib.
>>
>> Yes, I lost some time due to that too, and it is neccessary.
>>
>> I tried to avoid discussing compilation issues as its a bit of a can of
>> worms because they are usually very dependant on the system in use.
>> But this probably is worth a mention.
>
> I have updated the HowTo with some information on this.
>
> http://wiki.xensource.com/xenwiki/VTdHowTo
>

Some typo i guess.

>From VTdHowTo:
"VT-d Device Hot-Unplug

VT-d hot-unplug refers to detaching a pass-through device from a
running HVM domain. The device may have been attached using boot-time
VT-d device pass-through or VT-d device hot-plug.

xm's pci-attach command is used to perform hot-unplug."
              ^^^^^
should be detach right?

> --
> Simon Horman
>  VA Linux Systems Japan K.K. Satellite Lab in Sydney, Australia
>  H: www.vergenet.net/~horms/            W: www.valinux.co.jp/en
>
>
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xensource.com
> http://lists.xensource.com/xen-devel
>

Re: VT-d HowTo Update

[Simon Horman]

On Wed, Apr 22, 2009 at 02:58:23PM +0530, Tej wrote:
> On Wed, Apr 22, 2009 at 6:33 AM, Simon Horman <horms@verge.net.au> wrote:
> > On Wed, Apr 22, 2009 at 09:13:33AM +1000, Simon Horman wrote:
> >> On Tue, Apr 21, 2009 at 07:11:00AM -0700, Leonard Michelet wrote:
> >> >
> >> > Hi, Simon
> >> > I've read it, and it's much more complete than before. Thanks a lot.
> >> > Beside, you don't write about the library PCI devel that you need when you
> >> > compile Xen to enable PCI passtrought, and so, the use of VT-d. Debian
> >> > package is libpci_dev.
> >> > Is this library still necessary to use VT-d? If yes, shouldn't you write
> >> > about it in this wiki page?
> >> > >From my experience, I lost some times before finding that I had to compil
> >> > with this lib.
> >>
> >> Yes, I lost some time due to that too, and it is neccessary.
> >>
> >> I tried to avoid discussing compilation issues as its a bit of a can of
> >> worms because they are usually very dependant on the system in use.
> >> But this probably is worth a mention.
> >
> > I have updated the HowTo with some information on this.
> >
> > http://wiki.xensource.com/xenwiki/VTdHowTo
> >
> 
> Some typo i guess.
> 
> >From VTdHowTo:
> "VT-d Device Hot-Unplug
> 
> VT-d hot-unplug refers to detaching a pass-through device from a
> running HVM domain. The device may have been attached using boot-time
> VT-d device pass-through or VT-d device hot-plug.
> 
> xm's pci-attach command is used to perform hot-unplug."
>               ^^^^^
> should be detach right?

Thanks, I have now fixed that.

-- 
Simon Horman
  VA Linux Systems Japan K.K. Satellite Lab in Sydney, Australia
  H: www.vergenet.net/~horms/            W: www.valinux.co.jp/en