Re: [PATCH v2] x86/cpu: Use SERIALIZE in sync_core() when available

[Andy Lutomirski]

> On Aug 5, 2020, at 12:11 PM, Ricardo Neri <ricardo.neri-calderon@xxxxxxxxxxxxxxx> wrote:
> 
> On Wed, Aug 05, 2020 at 11:28:31AM -0700, Andy Lutomirski wrote:
>>> On Wed, Aug 5, 2020 at 10:07 AM Ricardo Neri
>>> <ricardo.neri-calderon@xxxxxxxxxxxxxxx> wrote:
>>> 
>>> On Wed, Aug 05, 2020 at 07:08:08AM +0200, Borislav Petkov wrote:
>>>> On Tue, Aug 04, 2020 at 09:58:25PM -0700, hpa@xxxxxxxxx wrote:
>>>>> Because why use an alternative to jump over one instruction?
>>>>> 
>>>>> I personally would prefer to have the IRET put out of line
>>>> 
>>>> Can't yet - SERIALIZE CPUs are a minority at the moment.
>>>> 
>>>>> and have the call/jmp replaced by SERIALIZE inline.
>>>> 
>>>> Well, we could do:
>>>> 
>>>>      alternative_io("... IRET bunch", __ASM_SERIALIZE, X86_FEATURE_SERIALIZE, ...);
>>>> 
>>>> and avoid all kinds of jumping. Alternatives get padded so there
>>>> would be a couple of NOPs following when SERIALIZE gets patched in
>>>> but it shouldn't be a problem. I guess one needs to look at what gcc
>>>> generates...
>>> 
>>> But the IRET-TO-SELF code has instruction which modify the stack. This
>>> would violate stack invariance in alternatives as enforced in commit
>>> 7117f16bf460 ("objtool: Fix ORC vs alternatives"). As a result, objtool
>>> gives warnings as follows:
>>> 
>>> arch/x86/kernel/alternative.o: warning: objtool: do_sync_core()+0xe:
>>> alternative modifies stack
>>> 
>>> Perhaps in this specific case it does not matter as the changes in the
>>> stack will be undone by IRET. However, using alternative_io would require
>>> adding the macro STACK_FRAME_NON_STANDARD to functions using sync_core().
>>> IMHO, it wouldn't look good.
>>> 
>>> So maybe the best approach is to implement as you suggested using
>>> static_cpu_has()?
>> 
>> I agree.  Let's keep it simple.
>> 
>> Honestly, I think the right solution is to have iret_to_self() in
>> actual asm and invoke it from C as needed. 
> 
> Do you mean anything different from what we have already [1]? If I
> understand your comment correctly, we have exactly that: an
> iret_to_self() asm implementation invoked from C.

I meant asm as in a .S file. But the code we have is fine for this purpose, at least for now.

> 
> Thanks and BR,
> Ricardo
> 
> [1]. https://lore.kernel.org/lkml/20200727043132.15082-4-ricardo.neri-calderon@xxxxxxxxxxxxxxx/
> 
> Thanks and BR,
> Ricardo