On Mon, Jan 30, 2023 at 09:30:38AM -0800, H. Peter Anvin wrote:
> It's somewhat odd to me that reading %dr7 is volatile, but %dr6 is
> not... %dr6 is the status register!
Yeah, as a precaution I think we should make all those volatile. Just in
case.
> I believe they should all be volatile (the compiler semantics is that
> volatile operations are always executed exactly once, in strict
> program order with respect to any other volatile operations); the real
> question is if there should also be memory clobbers on %dr6 reads and
> any %dr write.
Yes, I think so too. From gcc docs:
"6.47.2.1 Volatile
.................
...
Note that the compiler can move even 'volatile asm' instructions
relative to other code, including across jump instructions."
We already have __FORCE_ORDER for exactly things like that.
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
