On Fri, May 15, 2020 at 09:52:32AM -0700, Zach Lym wrote:
> The only truly effective mitigation for ROWHAMMER that I am aware of is 
> encrypted memory, which is only available on some AMD processors.  

do you have any reference/paper/link for this?

aiui pure "destructive" rowhammer will not be changed by "memory
encryption" at all.

a "privilege escalation / limited targeted write" rowhammer will 
only be a little harder and easier to detect. (depending on 
implementation details)

and a memory encrpytion implementation that was designed with this
problem in mind might make "rambleed / reading through reverse 
rowhammer" somewhat hard.



-- 
You received this message because you are subscribed to the Google Groups 
"qubes-devel" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
To view this discussion on the web visit 
https://groups.google.com/d/msgid/qubes-devel/20200515174007.GJ1079%40priv-mua.

Reply via email to