netdev - Re: [PATCH net-next v3 07/11] tcp: Prevent coalesce/collapse when skb has MPTCP extensions

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <518dc6a3c77f51a9d56b66ac80ffb883d80ceedf.camel@redhat.com>
Date:   Wed, 18 Dec 2019 22:52:24 +0100
From:   Paolo Abeni <pabeni@...hat.com>
To:     subashab@...eaurora.org,
        Mat Martineau <mathew.j.martineau@...ux.intel.com>
Cc:     David Miller <davem@...emloft.net>, eric.dumazet@...il.com,
        netdev@...r.kernel.org, mptcp@...ts.01.org,
        netdev-owner@...r.kernel.org
Subject: Re: [PATCH net-next v3 07/11] tcp: Prevent coalesce/collapse when
 skb has MPTCP extensions

On Wed, 2019-12-18 at 14:36 -0700, subashab@...eaurora.org wrote:
> > Ok, understood. Not every packet has this MPTCP extension data so
> > coalescing was not always turned off, but given the importance of
> > avoiding
> > 
> > this memory waste I'll confirm GRO behavior and work on maintaining
> > coalesce/collapse with identical MPTCP extension data.
> > 
> 
> Hi Mat
> 
> Are identical MPTCP extensions a common case?

Yes, they are.

> AFAIK the data sequence number and the subflow sequence number change
> per packet even in a single stream scenario.

What actually change on per packet basis is the TCP sequence number.
The DSS mapping can spawn on multiple packets, and will have constand
(base) sequence number and length.

Cheers,

Paolo