Re: [RFC PATCH v2 00/22] Introduce QC USB SND audio offloading support

[Pierre-Louis Bossart]

This version has lots of improvements, but I am concerned
about hard-coded ops/callbacks that look racy and assume dependencies
between driver probes. How does this work if the probe is delayed on one
side for some reason? What happens is a driver is 'blacklisted' and
manually added later? The code has to deal with this sort of known unknowns.

I also still have a bit of heartburn with the notion that there would be
a completely separate card with all the control for volume/mute/etc
having to be duplicated.

It's still a lot of good work so thanks for sharing and pushing for this
capability.