GitLab

This change:
- Has a small code size reduction.
- Should slightly improve overall performance.  The old hook code
  seemed to use between 0.1% and 1.6% of the total CPU time doing no-op
  calls even when no USB work was required.
- USB performance is mostly the same, there is a small increase in
  latency for some workloads that seems to because sometimes the hook
  usbd_task() is called at the right time to line up with the next USB host
  request.  This only happened semi-randomly due to the timing of the hook.
  Improving the wakeup latency by switching rp2 to tickless WFE allows the
  usbd_task() to run in time for the next USB host request almost always,
  improving performance and more than offsetting this impact.

This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>