as we can have multiple threads in the event library if there are multiple
MPI threads. Well, we could, once I fix the need for the lock in
opal_progress(), which should happen shortly. Anyway, we need to use the
same locking scheme throughout the code, and the device support was
already using the OPAL_THREAD__{lock,unlock} macros, which only go
active when we think there are multiple threads we care about.
Also, stop duplicating the OPAL_THREAD_SCOPED_LOCK macro's functionality
and use it in a bunch of places in the code.
This commit was SVN r11383.
a9c2b38877