On Thu, Jun 19, 2025 at 12:51:32PM +0100, Mikołaj Lenczewski wrote:

On Thu, Jun 19, 2025 at 12:05:05PM +0100, Catalin Marinas wrote:

quoted

On Tue, Jun 17, 2025 at 09:51:02AM +0000, Mikołaj Lenczewski wrote:

quoted

+	 * whether the MIDR check passes. This is because we specifically
+	 * care only about a stricter form of BBML2 (one guaranteeing noabort),
+	 * and so the MMFR2 check is pointless (all implementations passing the
+	 * MIDR check should also pass the MMFR2 check).

I think there's at least one implementation that behaves as
BBML2-noabort but does not have the ID field advertising BBML2.

Yes, I put "should" instead of "will" because of the AmpereOne
situation, but I didn't want to "name and shame". Should I explicitly
call this out? Or would you like me to soften the vocabulary here to imply
that as long as the MIDR passes, the MMFR2 check is not important?

I missed the "should" part. Anyway, I would just drop the explanation
from "This is because...".

-- 
Catalin