hi,

> I'm still not aware of any real-world case where lo0 throughput is a
> significant bottleneck?  Speed up something that's well under 10% of
> your application, by some 10%[*]? Not a big win.

how about something like pkgsrc/security/sfs?
anyway, a small win is good enough for this small change, IMO.

> [*] assuming all the data-touching for checksums hits in L1 CPU cache,
> after the original copyin(). Not a bad bet, given packet sizes and
> today's CPU cache sizes.

- no copyin when pages are loaned.
- not everyone runs on cpus with such "big" cache. :-)

YAMAMOTO Takashi