OpenBSD chief de Raadt says no easy fix for new Intel CPU bug

Re:OpenBSD chief de Raadt says no easy fix for new Intel CPU... by zik on Monday June 25, 2018 @04:42AM (#17390864)

No, as he points out in the article even a kernel call can change the virtual address space so even two threads of the same program may leak data. There's basically no known fix except to disable hyperthreading entirely.

[ Parent | on HN ]

Re:OpenBSD chief de Raadt says no easy fix for new Intel CPU... by alkonaut on Monday June 25, 2018 @04:46AM (#17390873)

Yes I meant more generally - effectively: at what point do we trust that there are no side channels in a modern cpu?

It seems they are complex enough that the answer may be "never", at least for some high risk scenarios.

[ Parent | on HN ]

Re:OpenBSD chief de Raadt says no easy fix for new Intel CPU... by DyslexicAtheist on Monday June 25, 2018 @05:49AM (#17391090)

> There's basically no known fix except to disable hyperthreading entirely.

on kabylake & skylake this has been the recommendation anyway https://lists.debian.org/debian-devel/2017/06/msg00308.html

[ Parent | on HN ]

Re:OpenBSD chief de Raadt says no easy fix for new Intel CPU... by tambre on Monday June 25, 2018 @06:41AM (#17391291)

That was the recommendation before the microcode fixes for the issue became widely available.

[ Parent | on HN ]

Re:OpenBSD chief de Raadt says no easy fix for new Intel CPU... by JdeBP on Monday June 25, 2018 @06:50AM (#17391329)

For more on which, see the news from a few days ago:

* https://www.mail-archive.com/[email protected]/msg9... (https://news.ycombinator.com/item?id=17350278)

[ Parent | on HN ]

Re:OpenBSD chief de Raadt says no easy fix for new Intel CPU... by pas on Monday June 25, 2018 @05:51AM (#17391100)

If you pin VMs to different cores, never sharing hyperthreads, then the risk is contained per VM (or per core).

[ Parent | on HN ]

Re:OpenBSD chief de Raadt says no easy fix for new Intel CPU... by pabloski on Monday June 25, 2018 @06:26AM (#17391233)

Let's hope there's no inter-core side-channel lurking in the shadows :(

It is time to rethinking the engineering methodologies we use in the electronics/informatics field.

[ Parent | on HN ]

Re:OpenBSD chief de Raadt says no easy fix for new Intel CPU... by cm2187 on Monday June 25, 2018 @06:32AM (#17391259)

Breaking x86 backward compatibility? That would be fun.

[ Parent | on HN ]

Re:OpenBSD chief de Raadt says no easy fix for new Intel CPU... by pabloski on Monday June 25, 2018 @10:27AM (#17392664)

So we are between a rock and a hard place.

[ Parent | on HN ]

Re:OpenBSD chief de Raadt says no easy fix for new Intel CPU... by pocak on Monday June 25, 2018 @09:12AM (#17392101)

If you give two threads on one core to one VM, the VM could attack the hypervisor. It could have one thread run the TLB probe loop while the other does something that's handled by the hypervisor.

[ Parent | on HN ]

Re:OpenBSD chief de Raadt says no easy fix for new Intel CPU... by AlphaSite on Monday June 25, 2018 @10:48AM (#17392811)

Isn’t there typically a VMM per VM? So the risk is then lower?

http://3.bp.blogspot.com/-OyjQUpLowmg/Udz1_NxqNLI/AAAAAAAABV...

[ Parent | on HN ]