[TUHS] OT: critical Intel design flaw

Random832 random832 at fastmail.com
Thu Jan 4 00:22:23 AEST 2018


On Wed, Jan 3, 2018, at 06:57, Ron Natalie wrote:
> I think it’s much ado about nothing.   In fact, nearly the same bug 
> cropped up in the 386 and we had to hack around it in UNIX then (in the 
> 32 bit pentiums you can use one of the segment registers to provide a 
> second layer of security over paging.   Alas, this doesn’t work on the 
> 64 bit addressing mode).

To my understanding, what's leaking is the addresses (and possibly physical addresses), which are in turn usable in a "rowhammer"-style attack - something that didn't exist (or wasn't known, anyway) in the 386 era.


More information about the TUHS mailing list