Linux Will End Up Disabling x86 PTI For AMD Processors - Update: Now Disabled

[oiaohm]

That is interesting Apple is usually slow with these fixes. It would be interesting to see if they have a work around that resolves the performance hit.

Apple case is they respond to the KASLR bug in 2016 they were still fairly slow. It remembering that the KPTI fix for the Linux kernel also started development in 2016 not being merged due to performance hit and without some other bug in software/hardware the exploit ability was limited.

So without the extra hardware fault turning up KPTI might not have been merged in Apple yet either. Due to the style of problem this is no operating system development should be starting from a standing start. Everyone should have been working on the issue.

[MartinN]

Nope. All he has to do is not spill the secret that he knew of this problem beforehand. Remember, innocent until proven guilty.

Have the Equifax execs that sold stock before the recent breach been charged with insider trading? I know DOJ said they'd investigate, but is anyone aware of any charges? (Even if Equifax ex-execs are charged, lots of other people in the past have been let off for lack of proof of something obvious - obviousness isn't legal proof)

That said, I hope he does get held legally responsible. Oh so bad.

...they could make him an offer he can't refuse ...and fuggedaboutit!

[MrApophis]

Has anyone seen any benchmarks comparing Intel CPU's with the KPTI patch against kernels prior to PCID implementation (<=4.13)? It would be interesting to know just how much PCID offsets the performance hit introduced by KPTI.

[Michael]

Has anyone seen any benchmarks comparing Intel CPU's with the KPTI patch against kernels prior to PCID implementation (<=4.13)? It would be interesting to know just how much PCID offsets the performance hit introduced by KPTI.

I will be soon. So far just the 4.14 kernel update but have seen patches for 4.1 LTS... Once any pre-4.13 kernel gets released with the support will run some benchmarks.

[MrApophis]

I will be soon. So far just the 4.14 kernel update but have seen patches for 4.1 LTS... Once any pre-4.13 kernel gets released with the support will run some benchmarks.

Thanks Michael, very much appreciated. I've just read over your new article, and am glad to see negligible performance deficit even without PCID.

[drSeehas]

... the most recent Intel cpu which is guaranteed not to have this bug (as it lacks speculative execution) is the original Pentium

Nope, the first Atom processor models (e.g. Diamondville 2008, Pineview 2009/2010, Cedarview 2011)!