On Wed, Jul 28, 2021 at 02:17:27PM +0100, Christoph Hellwig wrote:

So common checks obviously make sense, but I really hate the stupid multiplexer. Having one well-documented helper per feature is much easier to follow.

We had that in x86 - it was called cpu_has_<xxx> where xxx is the feature bit. It didn't scale with the sheer amount of feature bits that kept getting added so we do cpu_feature_enabled(X86_FEATURE_XXX) now.

The idea behind this is very similar - those protected guest flags will only grow in the couple of tens range - at least - so having a multiplexer is a lot simpler, I'd say, than having a couple of tens of helpers. And those PATTR flags should have good, readable names, btw.

Thx.