On Mon, Sep 5, 2011 at 1:15 PM, Jan Beulich <JBeulich@xxxxxxxx> wrote:
>>>> On 01.09.11 at 16:20, George Dunlap <george.dunlap@xxxxxxxxxxxxx> wrote:
>> On some systems, requests devices behind a PCIe-to-PCI bridge all
>> appear to the IOMMU as though they come from from slot 0, function
>> 0 on that device; so the mapping code much punch a hole for X:0.0
>> in the IOMMU for such devices.  When punching the hole, if that device
>> has already been mapped once, we simply need to check ownership to
>> make sure it's legal.  To do so, domain_context_mapping_one() will look
>> up the device for the mapping with pci_get_pdev() and look for the owner.
>>
>> However, if there is no device in X:0.0, this look up will fail.
>
> Was it really that there was no device at all at X:0.0, or rather that
> Xen just didn't know about the device (because Dom0 failed to notify
> Xen, as could happen in the 2.6.18-derived trees up to pretty
> recently)?
Don't know for sure; this was a partner that turned this up through
our beta-test program. But IIRC, running "lspci" in dom0 reported
nothing under X:0.0 (although I may well be remembering incorrectly).
This was for XenServer 6.0 which is using Novell's Xen-ified 2.6.32 kernel.
> Also, didn't we sort of agree that creating a phantom device would
> be more elegant (or at least much smaller a change)?
I don't remember talking about that, but perhaps. :-)
In reality, I don't know the code well enough to whip up a patch
(like, where / how would I make such a device), and this is not that
much of a priority for me. If this patch isn't accepted, it will
probably fall to you or Keir (or some other sufficiently motivated
party) to fix it.
 -George
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel