From: Florian Westphal
Date: Mon, 18 May 2015 23:33:29 +0200
> Thanks for spending time on this.
Ok, I've heard what you have to say.
Of the fixes you've proposed already, I prefer the device MTU one
because it doesn't penalize the ip_fragment.c optimizations just
because a netfilter module is
From: Florian Westphal
Date: Mon, 18 May 2015 22:40:49 +0200
> But, to the best of my understanding, what you ask will push a lot of
> non-trivial code into the kernel for no functional gain over
> what has been proposed.
The functional gain is that we stop linearizing the packet, which
involves
From: Florian Westphal
Date: Mon, 18 May 2015 22:06:37 +0200
> So, please please re-evaluate your stance on any of the previous
> attempts or tell me how you would provide bridge netfilter with
> the means to transparently forward (refrag) reassembled skbs, without
> breaking PMTUD, in ipv4 and i
From: Florian Westphal
Date: Thu, 7 May 2015 23:04:24 +0200
> There was interest in keeping geometry of original fragments on forward.
>
> This (re)enables this feature.
>
> on router with mtu 1500 on all interfaces and netfilter conntrack enabled:
...
> Caveat:
> This disables the optimizati
