<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<p><br>
<font size="-1">Did you check if the 1060 has a rom with EFI
support? See here:
<a class="moz-txt-link-freetext" href="https://vfio.blogspot.com/2014/08/does-my-graphics-card-rom-support-efi.html">https://vfio.blogspot.com/2014/08/does-my-graphics-card-rom-support-efi.html</a></font></p>
<p><font size="-1">If you have successfully downloaded the rom from
the 1060 you could also specify that rom file in your qemu xml:
<a class="moz-txt-link-freetext" href="https://libvirt.org/formatdomain.html#elementsHostDevSubsys">https://libvirt.org/formatdomain.html#elementsHostDevSubsys</a></font><br>
</p>
<br>
<div class="moz-cite-prefix">On 31/12/17 13:31, Sascha Fröhlich
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:CALU2qqotAf6hhfG6ThtdP0X2YY6-OHVhJNK8oS6A13xAmvsmrw@mail.gmail.com">
<div dir="ltr">I am loading the appropiate vfio modules at boot
time before the nvidia module and I use efifb=off as kernel
parameter. lspci -nnk states that the 2 cards are correctly
claimed by vfio-pci.
<div><br>
</div>
<div>Additionally, I tried to use the driver_override approach
mentioned in the blog post, but to no avail.</div>
</div>
<div class="gmail_extra"><br>
<div class="gmail_quote">2017-12-31 13:21 GMT+01:00 Torbjorn
Jansson <span dir="ltr"><<a
href="mailto:torbjorn.jansson@mbox200.swipnet.se"
target="_blank" moz-do-not-send="true">torbjorn.jansson@mbox200.swipnet.se</a>></span>:<br>
<blockquote class="gmail_quote" style="margin:0 0 0
.8ex;border-left:1px #ccc solid;padding-left:1ex"><span
class="">On 2017-12-31 12:25, Sascha Fröhlich wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0
.8ex;border-left:1px #ccc solid;padding-left:1ex">
Hi,<br>
<br>
I am trying to get the following setup with a Xeon
E5/ASUS X99-A II to work:<br>
<br>
First slot: GTX 1060 -> VM 1<br>
Second slot: GTX 1070 -> VM 2<br>
Third slot: GT 710 -> Host<br>
<br>
This is the latest ArchLinux. I had to use the
propietary NVIDIA drivers<br>
and an additional Xorg configuration for the host GPU,
because nouveau<br>
would flicker and crash. No need to blacklist anything.<br>
<br>
IOMMU and VFIO works fine though, lspci -nn -k reports
the two GTX GPUs<br>
using vfio-pci:<br>
<a
href="https://gist.github.com/anonymous/89ebd0e18464cef3c5dde6897c39eb5f"
rel="noreferrer" target="_blank"
moz-do-not-send="true">https://gist.github.com/anonym<wbr>ous/89ebd0e18464cef3c5dde6897c<wbr>39eb5f</a><br>
<br>
</blockquote>
<br>
</span>
did you make sure that the proprietary nvidia driver is
never attached/loaded for the 2 cards you intend to forward
to a vm?<br>
see: <a
href="http://vfio.blogspot.se/2015/05/vfio-gpu-how-to-series-part-3-host.html"
rel="noreferrer" target="_blank" moz-do-not-send="true">http://vfio.blogspot.se/2015/0<wbr>5/vfio-gpu-how-to-series-part-<wbr>3-host.html</a><br>
<br>
</blockquote>
</div>
<br>
</div>
<br>
<fieldset class="mimeAttachmentHeader"></fieldset>
<br>
<pre wrap="">_______________________________________________
vfio-users mailing list
<a class="moz-txt-link-abbreviated" href="mailto:vfio-users@redhat.com">vfio-users@redhat.com</a>
<a class="moz-txt-link-freetext" href="https://www.redhat.com/mailman/listinfo/vfio-users">https://www.redhat.com/mailman/listinfo/vfio-users</a>
</pre>
</blockquote>
<br>
</body>
</html>