News for hackers. Stuff that matters.

A comment on A survey of attacks against Intel x86 over last 10 years (2015) [pdf]. Parent comment

Re:A survey of attacks against Intel x86 over last 10 years ... by pgeorgi on Monday July 23, 2018 @05:49AM (#17591625)
Extensions are fair game, of course. As is not buying chips with closed extensions.

But designing the hooks for anti-user binary blobs into the ISA just encourages misbehavior as soon as they can get away with it.

RISC-V code in privileged and protected pockets of the systems is so much easier to design, maintain and update than ISA extensions that I consider that the bigger problem due to its future ubiquity.

[ Parent | on HN ]
Re:A survey of attacks against Intel x86 over last 10 years ... by rwmj on Monday July 23, 2018 @06:10AM (#17591691)
The machine mode is there for a very good reasons of microarchitecture design scalability, allowing the same machine model to be presented to the operating system with everything from tiny designs to everything-in-hardware. In all existing designs it is open source. It's quite reasonable to have this explicit layer, since in many other cases it has been hidden away (think: Transmeta, or many x86 emulators).
[ Parent | on HN ]