Marko Zec wrote this message on Wed, Sep 05, 2018 at 12:47 +0200:
> On Wed, 5 Sep 2018 12:36:38 +0200
> Vincenzo Maffione <v.maffi...@gmail.com> wrote:
>
> > Hi Marko,
> > Thanks a lot for identifying the problem.
> > If I understand correctly, simply adding -D VIMAGE here
> > https://github.com/luigirizzo/netmap/blob/master/sys/modules/netmap/Makefile#L11
> > would at least mitigate the issue.
> > If you think I'm right I'll just add it.
>
> Right, go for it...
Why not just hook up netmap to the build?
Because if you add -DVIMAGE to the Makefile, you'll now break people
who have kernels w/o VIMAGE.. And the only reason to build netmap
module manually is because it's not hooked up.
> > Il giorno mer 5 set 2018 alle ore 10:44 Marko Zec <z...@fer.hr> ha
> > scritto:
> >
> > > On Tue, 4 Sep 2018 20:18:29 +0200
> > > Vincenzo Maffione <v.maffi...@gmail.com> wrote:
> > >
> > > > Hi,
> > > > I don't think the panic depends on the architecture. Also, it
> > > > does not depend on using emulated mode or not.
> > > > We have seen this happening on x86_64 on FreeBSD 12 head.
> > > >
> > > > As John-Mark says, kdloading netmap.ko is not enough. You need to
> > > > open a netmap port corresponding
> > > > to any network interface, e.g.
> > > > # pkt-gen -i eth0
> > > > because this will trigger ifunit_ref() in the kernel (netmap
> > > > tries to grab the interface called "eth0").
> > > > The ifunit_ref() panics and we still need to figure out why.
> > >
> > > After more carefully rereading jmg's original report, on amd64 I
> > > reproduced exactly the same panic he reported on arm64, the summary
> > > follows:
> > >
> > > - the problem can be observed as VNET related, and can be triggered
> > > only on kernels built with "options VIMAGE" but without "device
> > > netmap".
> > >
> > > - netmap.ko built using make buildkernel works fine.
> > >
> > > - netmap.ko built separately (cd sys/modules/netmap; make) panics
> > > on a first reference to vale interface, such as "tcpdump -ni
> > > vale1:a"
> > >
> > > - the problem is that the separately built module is compiled
> > > without "options VIMAGE", and as such does not set curvnet prior to
> > > calling into network stack functions, therefore we have a null
> > > pointer dereference in ifunit_ref() and voila...
> > >
> > > - hence, there's nothing to fix in the netmap code, and there's
> > > nothing to fix in the network stack either related to this
> > > particular problem, but rather we need a general mechanism which
> > > would prevent kldloading non-VNETized .ko modules into a VNETized
> > > kernel. I have no idea how to approach this, besides adding bz@ to
> > > the cc: list, perhaps he could chime in with some thoughts?
--
John-Mark Gurney Voice: +1 415 225 5579
"All that I will do, has been done, All that I have, has not."
_______________________________________________
freebsd-net@freebsd.org mailing list
https://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to "freebsd-net-unsubscr...@freebsd.org"
