[vfio-users] Failed to mmap 0000:01:00.0 BAR 3. Performance may be slow

Konrad Eisele eiselekd at gmail.com
Thu Aug 23 22:59:57 UTC 2018


Now I also got the Gt 710 working. I had to:

 - use the patched  nvidia_vbios_patcher.py (previouse post) to patch vbios
dumped by nvflash of the Gt710 while in secondary port.
 - Add x-vga=on in the vfio-pci device declaration
 - Add "hv_relaxed,hv_spinlocks=0x1fff,hv_vapic,hv_time,hv_vendor_id=amd"
to the -cpu definiton

That seem to have convinced the nvidia driver to not go into "Code 43"
state.








Am Do., 23. Aug. 2018 um 23:54 Uhr schrieb Alex Williamson <
alex.williamson at redhat.com>:

> On Thu, 23 Aug 2018 23:35:34 +0200
> Konrad Eisele <eiselekd at gmail.com> wrote:
>
> > I gave the Nvidia 710b card a try:
> > - booted with 2 cards, AMD primary, NVidia secondary
> > - unbind noveau driver
> > - use nvflash (see below) to dump nvidia vbios
> > - rom-parser parser on it:
> > Valid ROM signature found @600h, PCIR offset 190h
> >        PCIR: type 0 (x86 PC-AT), vendor: 10de, device: 128b, class:
> 030000
> >        PCIR: revision 0, vendor revision: 1
> > Valid ROM signature found @fc00h, PCIR offset 1ch
> >        PCIR: type 3 (EFI), vendor: 10de, device: 128b, class: 030000
> >        PCIR: revision 3, vendor revision: 0
> >                EFI: Signature Valid, Subsystem: Boot, Machine: X64
> >        Last image
> >
> >
> > However when I try to use nvidia_vbios_vfio_patcher.py I get an error:
> > ...
> > But actually I have no idea what the patcher actually does.
> > Is it patching x86 vbios code?
>
> I don't know what it's doing or supposed to do either, but it does say
> in the readme that it's for Pascal and your card is Kepler, which is two
> generations before Pascal.  I've never had any need for that script.
> Thanks,
>
> Alex
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listman.redhat.com/archives/vfio-users/attachments/20180824/0f240c3e/attachment.htm>


More information about the vfio-users mailing list