netdev - Re: [PATCH net-next 9/9] mptcp: refactor sndbuf auto-tuning

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]

Date: Thu, 2 Nov 2023 11:38:51 -0700 (PDT)
From: Mat Martineau <martineau@...nel.org>
To: Eric Dumazet <edumazet@...gle.com>, Paolo Abeni <pabeni@...hat.com>, 
    Matthieu Baerts <matttbe@...nel.org>
cc: "David S. Miller" <davem@...emloft.net>, Jakub Kicinski <kuba@...nel.org>, 
    netdev@...r.kernel.org, mptcp@...ts.linux.dev
Subject: Re: [PATCH net-next 9/9] mptcp: refactor sndbuf auto-tuning

On Thu, 2 Nov 2023, Eric Dumazet wrote:

> On Mon, Oct 23, 2023 at 10:45 PM Mat Martineau <martineau@...nel.org> wrote:
>>
>> From: Paolo Abeni <pabeni@...hat.com>
>>
>> The MPTCP protocol account for the data enqueued on all the subflows
>> to the main socket send buffer, while the send buffer auto-tuning
>> algorithm set the main socket send buffer size as the max size among
>> the subflows.
>>
>> That causes bad performances when at least one subflow is sndbuf
>> limited, e.g. due to very high latency, as the MPTCP scheduler can't
>> even fill such buffer.
>>
>> Change the send-buffer auto-tuning algorithm to compute the main socket
>> send buffer size as the sum of all the subflows buffer size.
>>
>> Reviewed-by: Mat Martineau <martineau@...nel.org>
>> Signed-off-by: Paolo Abeni <pabeni@...hat.com>
>> Signed-off-by: Mat Martineau <martineau@...nel.org
>
> ...
>
>> diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
>> index df208666fd19..2b43577f952e 100644
>> --- a/net/mptcp/subflow.c
>> +++ b/net/mptcp/subflow.c
>> @@ -421,6 +421,7 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc
>>
>>  void __mptcp_set_connected(struct sock *sk)
>>  {
>> +       __mptcp_propagate_sndbuf(sk, mptcp_sk(sk)->first);
>
> ->first can be NULL here, according to syzbot.
>

Thanks for reporting this, Eric. We will get a fix to the net tree.


Paolo & Matthieu, I created a github issue to track this:

https://github.com/multipath-tcp/mptcp_net-next/issues/454



- Mat