Re: [PATCH v2.1] x86/retpoline: Fill return stack buffer on vmexit

[Brian Gerst]

On Thu, Jan 11, 2018 at 10:23 AM, David Woodhouse <dwmw2@xxxxxxxxxxxxx> wrote:
> On Thu, 2018-01-11 at 10:22 -0500, Brian Gerst wrote:
>> On Thu, Jan 11, 2018 at 9:32 AM, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
>> > On Thu, Jan 11, 2018 at 02:28:32PM +0000, David Woodhouse wrote:
>> >> On Thu, 2018-01-11 at 08:20 -0600, Josh Poimboeuf wrote:
>> >> >
>> >> > This seems weird.  I liked v1 a lot better.  What's the problem with
>> >> > patching in the whole thing?
>> >> >
>> >> > Also, if you go back to v1, it should be an easy objtool fix, just add
>> >> > ANNOTATE_NOSPEC_ALTERNATIVE in front of it.
>> >>
>> >> The objection was that I was patching in a fairly long set of
>> >> instructions. I confess I don't actually know why that's a problem,
>> >
>> > You get a giant string of NOPs, a single jmp should be faster.
>>
>> That could be handled in add_nops(), where if over a certain threshold
>> it changes to a JMP.
>
> Currently that only processes the *altinstr* doesn't it? Not the
> oldinstr?

It does both.

--
Brian Gerst