From: David Miller
Date: Wed, 19 Dec 2018 11:02:22 -0800 (PST)
> I have no major issues with the approach, but I just want to understand all
> of the details before I apply this.
>
> And honestly, if this turns out to be the wrong direction we can
> revert and try doing this another way.
Ok, I
From: Florian Westphal
Date: Tue, 18 Dec 2018 17:15:14 +0100
> TL;DR:
> - objdiff shows no change if CONFIG_XFRM=n && BR_NETFILTER=n
> - small size reduction when one or both options are set
> - no changes in ipsec performance
>
> Changes since v1:
> - Allocate entire extension space from a
TL;DR:
- objdiff shows no change if CONFIG_XFRM=n && BR_NETFILTER=n
- small size reduction when one or both options are set
- no changes in ipsec performance
Changes since v1:
- Allocate entire extension space from a kmem_cache.
- Avoid atomic_dec_and_test operation on skb_ext_put() for refc
On Mon, Dec 10, 2018 at 8:21 AM Florian Westphal wrote:
>
> The (out-of-tree) Multipath-TCP implementation needs to map logical mptcp
> sequence numbers to the tcp sequence numbers used by individual subflows.
> This DSS mapping is read/written from tcp option space on receive and
> written to tcp
The (out-of-tree) Multipath-TCP implementation needs to map logical mptcp
sequence numbers to the tcp sequence numbers used by individual subflows.
This DSS mapping is read/written from tcp option space on receive and
written to tcp option space on transmitted tcp packets that are part of
and MPTCP
