Date: Tue, 4 Sep 2018 20:18:29 +0200 From: Vincenzo Maffione <v.maffione@gmail.com> To: Marko Zec <zec@fer.hr>, Luigi Rizzo <rizzo@iet.unipi.it>, "freebsd-net@freebsd.org" <net@freebsd.org> Subject: Re: vale and netmap module questions Message-ID: <CA%2B_eA9jp2rB0GjojNrbWuQJ3fChpF6U5KPOX-DvEzJDVzOSP4w@mail.gmail.com> In-Reply-To: <20180904162815.GA75530@funkthat.com> References: <20180901014953.GV45503@funkthat.com> <CA%2B_eA9gH_uzxV_YLBH1XdM-ygPUxXzD_W9_b45jTmeY-t0bQKg@mail.gmail.com> <20180901211123.GZ45503@funkthat.com> <20180904164303.68c43b6e@x23> <20180904162815.GA75530@funkthat.com>
next in thread | previous in thread | raw e-mail | index | archive | help
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. Cheers, Vincenzo Il giorno mar 4 set 2018 alle ore 18:28 John-Mark Gurney <jmg@funkthat.com> ha scritto: > Marko Zec wrote this message on Tue, Sep 04, 2018 at 16:43 +0200: > > On Sat, 1 Sep 2018 14:11:23 -0700 > > John-Mark Gurney <jmg@funkthat.com> wrote: > > > Vincenzo Maffione wrote this message on Sat, Sep 01, 2018 at 22:25 > > > +0200: > > ... > > > > 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... > > > > Hi John-Mark, > > > > out of curiosity I tested all four kernel config combinations with > > "device netmap" and "options VIMAGE" being on and off (both are on by > > default now in GENERIC) on amd64 @r338446, and found that kldloading > > netmap.ko can't provoke a panic. Was there a particular sequence of > > commands issued after kldloading netmap which led to the crash you > > reported earlier? > > Nope. I would kldload netmap, and then run the tcpdump command listed > in the original report, and it would just panic... > > Also note that my panic was on arm64, NOT amd64.. so it could be > something platform specific... > > > Nevertheless, note that building the kernel without "device netmap" is > > borderline pointless even if netmap core built as a kld module works, as > > this will result in all the drivers being built without the required > > netmap bits, which means they will only work in the painfully slow > > "emulation" mode with netmap. > > I was only doing it to test something out quickly.. > > > Perhaps the panic you stepped into was related to the emulation mode > > being used with netmap, instead of using the native netmap hooks in > > device drivers? Or maybe was it vale + VNET related? > > All I know was that it was the arm64 GENERIC kernel + module netmap > + running tcpdump w/ that command... Nothing special configured, just > a single ethernet interface configured w/ DHCP. No firewall configured, > just sshd and ntpd enabled.. > > -- > John-Mark Gurney Voice: +1 415 225 5579 > > "All that I will do, has been done, All that I have, has not." > -- Vincenzo
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CA%2B_eA9jp2rB0GjojNrbWuQJ3fChpF6U5KPOX-DvEzJDVzOSP4w>