[MODERATED] Re: [patch V3 5/9] MDS basics 5

On 21/02/2019 23:44, speck for Thomas Gleixner wrote:
> +   There is one non maskable exception which returns through paranoid exit
> +   and is not mitigated: #DF. If user space is able to trigger a double
> +   fault the possible MDS leakage is the least problem to worry about.

What about espfix64?  An IRET fault from that ends up at #DF, and
purposefully recovers.  It is trigger-able from at least modify_ldt().

The #DF path is normally fatal, but in the cases that it's not, an extra
VERW isn't going to be the slow part.

~Andrew