From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dominique Martinet Subject: Re: bnx2 vlan issue Date: Fri, 17 Jun 2011 06:10:24 +0000 (UTC) Message-ID: References: Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit To: netdev@vger.kernel.org Return-path: Received: from lo.gmane.org ([80.91.229.12]:39961 "EHLO lo.gmane.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751603Ab1FQGPK (ORCPT ); Fri, 17 Jun 2011 02:15:10 -0400 Received: from list by lo.gmane.org with local (Exim 4.69) (envelope-from ) id 1QXSKh-0000Ks-PU for netdev@vger.kernel.org; Fri, 17 Jun 2011 08:15:09 +0200 Received: from nobunaga.t.u-tokyo.ac.jp ([157.82.13.93]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Fri, 17 Jun 2011 08:15:07 +0200 Received: from rnfhrznznaq.tf by nobunaga.t.u-tokyo.ac.jp with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Fri, 17 Jun 2011 08:15:07 +0200 Sender: netdev-owner@vger.kernel.org List-ID: Hi, Jesse Gross nicira.com> writes: > On Thu, Mar 24, 2011 at 5:26 PM, Seblu seblu.net> wrote: > > Maybe i was not enough clear. It seems to me that new behaviour, with > > vlan on top of bridge rather than above interface in bridge is not > > functional. > > In other words, i cannot use vlan and bridge together in 2.6.38 (with > > e1000e). > > Sorry, I misunderstood what you were saying before. Can you try and > see where the packets are getting lost or improperly handled by > running tcpdump on the various interfaces? For example, check that > packets are coming in with tags on the physical interfaces, have tags > on the bridge interface, no tag on the vlan interface, etc. I think I ran into the same problem, and my workaround for this was to add a vlan do the bridge and then add the vlan'ed bridge to another bridge, i.e. (since I can't draw, commands will be better :P) brctl addbr br0 brctl addif br0 eth0 ip link add link br0 name br0.42 type vlan id 42 ip link set br0.42 up brctl addbr br_42 brctl addif br_42 br0.42 and then I could put VMs in br_42 which got network "as expected" before, I used to have br_42 with eth0.42 in it, so it is just one more step.. What bothers me is that I also want to put VMs in br0, and it does work, but this bridge also sees all the tagged data - isn't there a way to just "pick" the untagged network? My other question is that I'm not certain if that's the expected way to use the new behaviour, if not I wouldn't mind light shining from above :) This is enough for me, though I can't say I like the change I can't argue that having everything behave the same way is better, but I'm still curious... Regards, Dominique Martinet | Asmadeus