[Info-vax] Intel x86-64 Processor Design Security Vulnerability?

[Neil Rieck]

On Tuesday, January 2, 2018 at 11:20:30 AM UTC-5, Stephen Hoffman wrote:
> There's speculation around a potential security vulnerability and 
> related information embargo, involving various Intel x86-64 processors, 
> in the implementations of memory management and speculative execution.
> 
> http://pythonsweetness.tumblr.com/post/169166980422/the-mysterious-case-of-the-linux-page-table 
> 
> https://lkml.org/lkml/2017/12/27/2
> https://www.tugraz.at/en/tu-graz/services/news-stories/planet-research/singleview/article/wenn-rowhammer-nur-noch-einmal-klopft/ 
> 
> Etc.
> 
> The issue appears specific to Intel x86-64 designs, and does not arise 
> in the AMD x86-64 designs.
> 
> Looks like might know a more by later this week based on other reports; 
> the apparent embargo may be nearing its end.
> 
> Expect to see some vendor software updates, and probably by next 
> Tuesday for the Microsoft Windows folks.  Once the patches for an 
> exploit or a design vulnerability start rolling out to folks. the 
> associated knowledge of the exploit becomes available to anybody that's 
> interested in reversing the patches.
> 
> 
> 
> 
> 
> -- 
> Pure Personal Opinion | HoffmanLabs LLC

I noticed that the security exploit only exists in some products from Intel and ARM but no products from AMD.

"Critical flaws revealed to affect most Intel chips since 1995"
http://www.zdnet.com/article/security-flaws-affect-every-intel-chip-since-1995-arm-processors-vulnerable/

https://www.extremetech.com/computing/261364-massive-intel-cpu-bug-leaves-kernel-vulnerable-reduce-performance
 
Now anyone who has installed Linux recently already knows that there are processor-specific variants available for x86-64 technology (which is labelled AMD since that company developed 64-bit extensions first) so I wonder if this problem will be as difficult to fix as some doom-and-gloom types are already inferring.
 
(p.s. don't get me wrong; the flaws need to be fixed in order to prevent future developers from accidentally re-implementing a problem and/or someone infecting a system with flaw-specific malware) 
 
Neil Rieck
Waterloo, Ontario, Canada.
http://neilrieck.net