If you think I should not add the udata parameter to the req_notify_cq()
provider verb, then I can rework the chelsio driver:

1) at cq creation time, pass the virtual address of the u32 used by the
library to track the current cq index.  That way the chelsio kernel
driver can save the address in its kernel cq context for later use.

2) change chelsio's req_notify_cq() to copy in the current cq index
value directly for rearming.

This puts all the burden on the chelsio driver, which is apparently the
only one that needs this functionality.  

Good thinking, I haven't thought of this approach.

This way there won't be any API/core changes and no changes to
other low level drivers, correct? And for chelsio, there's no overhead
as compared to code you posted.

Sounds good.

-- 
MST