vale and netmap module questions

[Vincenzo Maffione]

Il giorno sab 1 set 2018 alle ore 23:11 John-Mark Gurney <jmg at funkthat.com>
ha scritto:

> Vincenzo Maffione wrote this message on Sat, Sep 01, 2018 at 22:25 +0200:
> > Il giorno sab 1 set 2018 alle ore 03:50 John-Mark Gurney <
> jmg at funkthat.com>
> > ha scritto:
> >
> > > First, does vale work for anyone?  At least one of the documented
> > > commands in vale(4) does not work.
> > >
> > > After manually building the netmap module and loading it:
> > > # tcpdump -ni vale-a:1
> > > 313.748851 nm_open [947] invalid bridge name vale-a:1
> > > tcpdump: netmap open: cannot access vale-a:1: Invalid argument
> >
> > That name is invalid. See netmap(4).
>
> Are there plans to update the documentation then?  It seems like
> vale(4) should be a more authoratative reference for vale's naming
> than netmap(4)...
>

You are right. I just updated the man page in the netmap github. I will
commit this to FreeBSD soon.


>
> > > If I run tcpdump with a more correct looking name of vale1:a, I get a
> > > null deref panic in ifunit_ref.  Full trace is at the end.
> >
> > Yes, this is a known bug, already posted to this mailing list. Don't
> build
> > netmap as a module, but link it in the kernel image and it will work.
> > (Add "dev netmap" to the kernel config).
> >
> > > Second, is there a good reason why the netmap module is still
> > > disconnected from being built as a module?  I guess not working
> > > would be one, but I figure the above might be an aarch64 specific
> > > problem, and not a general issue.
> >
> > On x86_64 netmap is not built as a module, so everything works fine. I
> > don't see any reason why it should be a module in aarch64.
>
> Well, sys/modules/netmap exists... If it isn't planned on ever being
> made to work, it should be removed so people don't get confused, or
> at least marked broken so it doesn't get built...
>
> I built it manually because it was quicker than recompiling an entire
> kernel and rebooting...
>

That's right. It used to work fine, then something must have changed in the
way ifunit_ref()
must be used from modules (CURVNET related?). I have not had the time to
dig into this,
so if anyone has any suggestion please tell me.
Is there a standard way to mark a module as broken so that it does not get
built as a module,
but it still gets built statically?


>
> --
>   John-Mark Gurney                              Voice: +1 415 225 5579
>
>      "All that I will do, has been done, All that I have, has not."
>


-- 
Vincenzo