Interesting, I haven't noticed the thread you mentioned. The thread I referenced to was more than a year ago.
So if I read through it quickly, this guy had succeeded in passing through his GTX980, but it went wrong on the driver installation (code 43). This is expected, as nVidia disables the card automatically when a virtualised environment is found. Solution is to hide the virtualisation extensions inside the VM, more info on this matter here: https://lime-technology.com/forum/index.php?topic=38664.0 Marcus, are you reading? On 2016-07-02 16:11, Andrew David Wong wrote: > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA512 > > On 2016-07-02 06:24, foss-gro...@isvanmij.nl wrote: > >> Hi All, >> >> Is there any update on GPU-passtrough support, since it is on the >> roadmap? >> >> I need to use Windows for some tasks heavily relying on GPU-power, >> but rebooting every time isn't ideal, to say the least. >> >> My system has a Intel Core i5 2400S-processor, a nVidia GTX680 GPU >> and a chipset/BIOS supporting VT-d. Now ideally, VT-d works just >> out of the box. But the VT-d version found on desktop processors >> is a bit different than the one found on server processors. >> Especially when it comes to the handling of IOMMU groups. AFAIK, >> Xeon E5 and E7 handles them properly out of the box. But with my >> processor, I needed a patched VFIO kernel (ACS Patch, Intel VGA >> Arbiter patch). I have successfully passed through my GPU to a >> QEMU-VM, but on XEN, it doesn't work. Some XEN devs said QEMU has a >> lot of device specific quirks, that is. >> >> However, working around this IOMMU grouping bug imposes a security >> risk. That needs to be addressed, off course. But for now I want >> to get things working and increase my productivity. >> >> I read some guys had success passing through an nVidia card using >> XEN 4.6.1, which is the default in the just released in Fedora 24. > > Is this the thread you're referring to? > > https://groups.google.com/d/topic/qubes-users/zHmaZ3dbus8/discussion > > If so, I'm not aware of more recent news on this topic than what's > contained in that thread (which, as you can see, is quite recent). > >> Qubes devs, will this version find it's way into 3.2? > > I don't think so, but I'll leave it to Marek to answer. > >> Anyway, the other option was to use a method called >> "qubes-qvm-traditional", but I didn't find any information about >> it, nor how to configure it. >> >> The information about GPU-passtrough on the XEN wiki is outdated. >> >> Any ideas or news on this? > > - -- > Andrew David Wong (Axon) > Community Manager, Qubes OS > https://www.qubes-os.org > -----BEGIN PGP SIGNATURE----- > > iQIcBAEBCgAGBQJXd8uRAAoJENtN07w5UDAwxN8P/isZVQ2RdwQB+cXnC55+Co8/ > Oi74oakWjLs8QLYjYHGebjyCRCK5J2s8W1FUroW5n3nFU9Moe7C8C5XA1B+SrbzF > a8snrRFbKyMS5u2LqvvDfInQQo9XodvQbx+E7SPbVyt7ms78R1mT9o66DixliiMI > 3ZCgKlh8nrc73yH429y0IpXVILKnzXkWbWd4An0TuWsA/m6RmD2y07WAey9Lkr/8 > weGx488Izyxyinawjpr1fqLneNSSPfylwdRpwvwYIRR6Qu0Y3T4G+a4I3XtOZrYf > mJu/nDxTUQrLGPggTlH6i1LlCfGYiFlGTgGLQafu4htpbgRHXjsyQHmOL0wi0xbQ > NLqSkJfWLkjY7nKTGKdQ8rhHEuJtDX/IxNdxzF00jwMpMmcWeQRi9qsn+Nm1DlmN > TFaJU240OINigPJ+eQpZR0Pb18XN+ppN9MTR6q4MvY4L8vuimThUboWKcMEs8GkV > 141YvnNvLpdpcuVnWDnElRrHGsZeU2fsxEosAUNffighhgatvZiTK6G7kN8YQ8Ha > kxavRwCbu7lrn3I3Z/26YHzOrxLHdVA49/CMijFp9HQvcgch8sPCVj1ZsLS5pA30 > 1X3hZj7vHbyEtpxGZg8AtWOREr4BuruWv0kT3ZTn5aBO8QbDEZuWWxRSz3qXsWsh > DJnC7Kk203MfqWHzCfVT > =xANk > -----END PGP SIGNATURE----- -- You received this message because you are subscribed to the Google Groups "qubes-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to qubes-users+unsubscr...@googlegroups.com. To post to this group, send email to qubes-users@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/qubes-users/9c58927d8d9921b6abeca6cc05001b33%40isvanmij.nl. For more options, visit https://groups.google.com/d/optout.
