Yes I suppose the branch can be executed "non speculatively" before the 
lwsync is completed. Wheras the larx/stcwx will have to complete before
the branch outcome can be known. I suppose probably not worthwhile
avoiding the full IO sync by adding yet more crap to make this work.

Thanks for putting my mind to rest though :)

I'd still be interested to know how expensive the full sync is when you
have a lot of IOs in flight.

Question, are you going to do the hint and isync->lwsync thing for
userspace as well? Too bad the kernel doesn't export synchronisation
primitives to userspace...

We'd love to.... the vdso inherits from all the dynamic patching
features of the kernel and more...

It's really a matter of getting glibc to grok it, and doing so
efficiently (ie, not just having a function point in glibc, might be a
good use of the IFUNC stuff).

Cheers,
Ben.