Linux Ethernet Bridging - Oct 2018 - [Bridge] [PATCH 1/1] bridge: remove BR_GROUPFWD_RESTRICTED for arbitrary forwarding of reserved addresses

On Mon, Oct 01, 2018 at 08:54:08PM +0200, Richard Weinberger
wrote:
> So the only option is having a bridge and transport STP via tc-mirred
> or patching the bridge code (what we do right now).
And I vote for the first option. I understand it involves more typing,
but I see no reason to push more complexity into the kernel - and break
standards - when you can relatively easily accomplish the same thing in
other ways.

Adding Nik and Roopa who now maintain the bridge code and should
eventually decide about this.

Am Montag, 1. Oktober 2018, 21:04:33 CEST schrieb Ido
Schimmel:
> On Mon, Oct 01, 2018 at 08:54:08PM +0200, Richard Weinberger wrote:
> > So the only option is having a bridge and transport STP via tc-mirred
> > or patching the bridge code (what we do right now).
> 
> And I vote for the first option. I understand it involves more typing,
hehe, it is not about typing. The setup is done by a script.
And we both know that getting a patch upstream is much more work than
typing a few lines of hacky bash scripts.
Since I want a decent solution and feedback I'm bringing this up here.

I could also just go with my in-house patch and don't tell anyone...
> but I see no reason to push more complexity into the kernel - and break
> standards - when you can relatively easily accomplish the same thing in
> other ways.
If having a bridge plus u32+mirred for STP bypass is the preferred solution,
I'm fine with it.
So far we use the kernel patch and didn't test the mirred-bypass a lot.
My fear was that mirred rules from eth0 to eth1 and back might cause a
loop or confuse the bridge...
> Adding Nik and Roopa who now maintain the bridge code and should
> eventually decide about this.
Thanks,
//richard