I don't like where this is going.
I think the model of storing the polling cookie in the bio is useful,
but:
(1) I think having this in the iter is a mess. Can you measure if
just marking bvec_iter __packed will generate much worse code
at all anymore? If not we can just move this into the bio
If it really generates much worse code I think you need to pick
a different name as as that i really confusing vs the bio field
of the same name that is used entirely differenly. Similarly
the bio_get_private_data and bio_set_private_data helpers are
entirely misnamed, as the names suggest they deal with the
bi_private field in struct bio. I actually suspect not having
these helpers would be much preferable
(2) once we do have the cookie in the bio we need to take advantage
of that properly. That is stop returning the cookie up the stack
as we do right now but just rely on the bio, which will clean up
tons of crap.
--
dm-devel mailing list
dm-devel@xxxxxxxxxx
https://listman.redhat.com/mailman/listinfo/dm-devel
