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.
