From: Paolo Abeni <pabeni@redhat.com>
To: quanyeyang@proton.me, MPTCP Linux <mptcp@lists.linux.dev>
Cc: geliang@kernel.org, matttbe@kernel.org
Subject: Re: [PATCH mptcp-net v3 3/3] tcp: fix data-race in do_recvmmsg / mptcp_recvmsg
Date: Mon, 7 Sep 2026 15:46:45 +0200 [thread overview]
Message-ID: <14749060-d011-41e7-9a4b-754eb5bd9d5b@redhat.com> (raw)
In-Reply-To: <20260907-mptcp-snd-una-race-v3-3-65ba0d5f0221@proton.me>
On 9/7/26 12:15 PM, Quanye Yang via B4 Relay wrote:
> From: Quanye Yang <quanyeyang@proton.me>
>
> KCSAN reported a data race between do_recvmmsg() and
> mptcp_recvmsg() on sk->sk_err.
>
> do_recvmmsg() calls sock_error() without holding the socket lock.
> sock_error() atomically clears sk_err using xchg(), which can race
> with the plain read in tcp_recv_should_stop(), even when its caller
> holds the socket lock.
It looks like the same data-race is present for plain TCP betweem i.e.
multiple concurrent recvmmsg() reader? If so, I think this patch
could/should go separately directly into the net tree.
Also please include the full KCSAN splat.
/P
next prev parent reply other threads:[~2026-09-07 13:46 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-07 10:15 [PATCH mptcp-net v3 0/3] mptcp: fix reported data-races quanyeyang
2026-09-07 10:15 ` [PATCH mptcp-net v3 1/3] mptcp: fix data-race in __mptcp_retrans / mptcp_incoming_options quanyeyang
2026-09-07 13:38 ` Paolo Abeni
2026-09-07 13:55 ` Matthieu Baerts
2026-09-07 10:15 ` [PATCH mptcp-net v3 2/3] mptcp: fix data-race in mptcp_subflow_get_send / tcp_ack Quanye Yang via B4 Relay
2026-09-07 10:15 ` Quanye Yang
2026-09-07 10:15 ` [PATCH mptcp-net v3 3/3] tcp: fix data-race in do_recvmmsg / mptcp_recvmsg Quanye Yang via B4 Relay
2026-09-07 10:15 ` Quanye Yang
2026-09-07 10:24 ` sashiko-bot
2026-09-07 13:23 ` quanyeyang
2026-09-07 13:46 ` Paolo Abeni [this message]
2026-09-07 14:38 ` quanyeyang
2026-09-07 11:28 ` [PATCH mptcp-net v3 0/3] mptcp: fix reported data-races MPTCP CI
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=14749060-d011-41e7-9a4b-754eb5bd9d5b@redhat.com \
--to=pabeni@redhat.com \
--cc=geliang@kernel.org \
--cc=matttbe@kernel.org \
--cc=mptcp@lists.linux.dev \
--cc=quanyeyang@proton.me \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.