linux-kernel - Re: linux 5.17.1 disregarding ACK values resulting in stalled TCP connections

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: <CADVnQy=pOfT+OmXdibc6y6uWMk2i_5ZBC1_1JZyt=vOjWhyQAw@mail.gmail.com>
Date:   Fri, 1 Apr 2022 11:48:29 -0400
From:   Neal Cardwell <ncardwell@...gle.com>
To:     Jaco Kroon <jaco@....co.za>
Cc:     Eric Dumazet <edumazet@...gle.com>,
        LKML <linux-kernel@...r.kernel.org>,
        Netdev <netdev@...r.kernel.org>,
        Yuchung Cheng <ycheng@...gle.com>, Wei Wang <weiwan@...gle.com>
Subject: Re: linux 5.17.1 disregarding ACK values resulting in stalled TCP connections

On Fri, Apr 1, 2022 at 11:39 AM Neal Cardwell <ncardwell@...gle.com> wrote:
...
> Jaco, to provide some evidence for this hypothesis, can you please
> re-enable fastopen but also enable the TFO blackhole detection that
> was disabled in v5.14 (213ad73d0607), with something like:
>
>   sysctl -w net.ipv4.tcp_fastopen=1
>   sysctl -w tcp_fastopen_blackhole_timeout=3600

I would also suggest using Florian's suggestion to log invalid
packets, so perhaps we can get a clue as to why netfilter thinks these
packets are invalid:

    sysctl net.netfilter.nf_conntrack_log_invalid=6

> And then after a few hours, check to see if this blackholing behavior
> has been detected:
>   nstat -az | grep -i blackhole
> And see if TFO FastOpenActive attempts have been cut to a super-low rate:
>   nstat -az | grep -i fastopenactive

Then I would correspondingly echo Florian's suggestion to check
dmesg/syslog/nflog to learn more about the drops.

neal