From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Hemminger Subject: Re: [PATCH net-next V4 00/13] Add basic VLAN support to bridges Date: Thu, 20 Dec 2012 09:07:12 -0800 Message-ID: <20121220090712.736dff45@nehalam.linuxnetplumber.net> References: <1355939304-21804-1-git-send-email-vyasevic@redhat.com> <201212201208.14204.vitas@nppfactor.kiev.ua> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: Andrew Collins , Vlad Yasevich , netdev@vger.kernel.org, davem@davemloft.net, or.gerlitz@gmail.com, jhs@mojatatu.com, mst@redhat.com, erdnetdev@gmail.com, jiri@resnulli.us To: Vitalii Demianets Return-path: Received: from mail.vyatta.com ([76.74.103.46]:42766 "EHLO mail.vyatta.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751324Ab2LTRI3 (ORCPT ); Thu, 20 Dec 2012 12:08:29 -0500 In-Reply-To: <201212201208.14204.vitas@nppfactor.kiev.ua> Sender: netdev-owner@vger.kernel.org List-ID: On Thu, 20 Dec 2012 12:08:13 +0200 Vitalii Demianets wrote: > On Thursday 20 December 2012 00:54:27 Andrew Collins wrote: > > On Wed, Dec 19, 2012 at 10:48 AM, Vlad Yasevich wrote: > > > This series of patches provides an ability to add VLANs to the bridge > > > ports. This is similar to what can be found in most switches. The > > > bridge port may have any number of VLANs added to it including vlan 0 > > > priority tagged traffic. When vlans are added to the port, only traffic > > > tagged with particular vlan will forwarded over this port. Additionally, > > > vlan ids are added to FDB entries and become part of the lookup. This > > > way we correctly identify the FDB entry. > > > > This is likely well beyond the scope of this change, but I figured I'd > > throw out the question anyway. This changeset looks to bring the > > Linux bridging code closer to the 802.1Q-2005 definition of a bridge, > > which is nice to see, I'm curious if this changeset also opens up the > > possibility of supporting MSTP in the future? The big thing I see > > missing is per-VLAN port state, although I'm not very familiar with > > the current STP/bridge interactions. Has anyone put any thought into > > what other necessary bridge pieces might be missing for MSTP support? > > I think, to be compatible with 802.1Q-2005 we need the following pieces: > 1) Multiple FIDs (it is 802.1Q term for FDB) support. It means that kernel > should support several independent FDBs on a single bridge. The 802.1Q-2005 > standard requires the number of supported FDBs to be no less than the number > of different MSTIs the implementation supports; > 2) VLAN-to-FDB mapping should be introduced; > 3) Support of Multiple Spanning Tree Instances (MSTIs); > 4) FDB-to-MSTI mapping should be introduced; > 5) And finally, per-MST port states should be implemented. > > > obviously something to handle the MSTP protocol itself would need to exist > as well > > Please look here: http://sourceforge.net/projects/mstpd/ A couple of points: * How does this compare with features/functionality of commercial hardware bridges? * Is this as simple as possible? It looks like there is creeping-featurism here. I am all for a simple extension to allow bridge vlan filtering, but not the added complexity of "let's teach bridges all about all possible things any user might want to do with vlan.s"