Re:Nvidia releases open-source GPU kernel modules
by RussianCow on Thursday May 12, 2022 @07:17PM
(#31361249)
I'm not sure why you were downvoted; this is 100% correct. Open source makes adding backdoors much more difficult, but I imagine GPU driver code is so complex that there are likely security flaws that even the entire open source community wouldn't catch. Yes, an open source driver is an improvement in many ways, but it certainly doesn't solve these problems because the attack surface is so gigantic.
Re:Nvidia releases open-source GPU kernel modules
by mjan22640 on Friday May 13, 2022 @06:34AM
(#31365575)
> has access to all of the memory in your computer
You can use IOMMU to restrict the access to the appropriate memory sections.
Re:Nvidia releases open-source GPU kernel modules
by hoistbypetard on Sunday May 15, 2022 @02:17PM
(#31389639)
I don't think, for accelerating a desktop graphics card used across your entire desktop environment, IOMMU changes my argument at all.
I believe it *does* help if, say your desktop's integrated video works natively and you have a second card you want to pass through to a gaming VM. Or if you have a server with no card shared between users and a one-card-per-user scenario.
In theory this may be true. But the particular opaque user-space program is talking to a driver authored by the same team. That driver is talking to hardware that has access to all of the memory in your computer.
The odds are high that a userspace program talking to this kind of driver could make your computer do something you don't want it to do in a way that is very difficult to suss out just by reviewing the driver source code.
(I agree that an open driver is a great improvement over a closed one. But I don't think you can make any strong guarantees about the safety of the closed userspace portions of this one, yet.)