Re: Meltdown-US / Meltdown 3a Remaining Leakage

[Solar Designer <solar () openwall com>]

Hello Daniel et al.,

Thank you very much for your research and for posting about it in here!

On Fri, Oct 06, 2023 at 12:07:17PM +0200, Daniel Weber wrote:
> we analyzed the remaining leakage of the "original" Meltdown attack 
> (Meltdown-US) (1) and the variant Meltdown 3a (2). We discovered that 
> the "original" Meltdown attack can be abused to infer the cache state of 
> memory pages that remain mapped despite KPTI. This allows an attacker to 
> monitor interrupt activity.

I assume you're talking specifically about Linux's KPTI.  Let's be
naming Linux explicitly, as this list isn't only about Linux.

In Linux, /proc/interrupts is generally world-readable.  So perhaps
that's something to fix first, since yes it's known to allow for
keystroke timing attacks.  Should be fixed in the kernel or/and chmod'ed
by the userland.  And then:

> 1) Preventing the Meltdown attack from leaking information about the 
> cache state can be achieved by marking the remaining memory pages, e.g., 
> the IDT, as uncacheable. This can be achieved by using a memory-type 
> range register (MTRR) or by modifying the corresponding page-table entries.

Alexander