> > 	if_faith.c
> > 	if_gif.c
> > 	if_stf.c
> > 
> > Note that the last three is the files from KAME and should be fixed in
> > the KAME tree.
> 
> So will you or someone else fix those up in KAME or should we just fix it
> in NetBSD anyway ?

I'll take care of these once we reach consensus how to fix.  But
now I come to think we should nuke fake mbuf here, and instead, we
should introduce some bpf dependent code, such as bpf_mtap2 I posted.
The main reason is a faked mbuf still cannot be handled as normal mbuf
(cannot be freed, referenced...) so that we hard to define the concrete
behavior for it.  And someday, we will face bugs as a result of mixup
a faked mbuf to normal mbuf.

So I object to introduce MBUFINIT.

Regards,

Atsushi Onoe