The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable@xxxxxxxxxxxxxxx>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 57fc0f1ceaa4016354cf6f88533e20b56190e41a # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable@xxxxxxxxxxxxxxx>' --in-reply-to '2023062330-scrawny-capture-257c@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 57fc0f1ceaa4016354cf6f88533e20b56190e41a Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni@xxxxxxxxxx> Date: Tue, 20 Jun 2023 18:24:23 +0200 Subject: [PATCH] mptcp: ensure listener is unhashed before updating the sk status The MPTCP protocol access the listener subflow in a lockless manner in a couple of places (poll, diag). That works only if the msk itself leaves the listener status only after that the subflow itself has been closed/disconnected. Otherwise we risk deadlock in diag, as reported by Christoph. Address the issue ensuring that the first subflow (the listener one) is always disconnected before updating the msk socket status. Reported-by: Christoph Paasch <cpaasch@xxxxxxxxx> Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/407 Fixes: b29fcfb54cd7 ("mptcp: full disconnect implementation") Cc: stable@xxxxxxxxxxxxxxx Signed-off-by: Paolo Abeni <pabeni@xxxxxxxxxx> Reviewed-by: Matthieu Baerts <matthieu.baerts@xxxxxxxxxxxx> Signed-off-by: Matthieu Baerts <matthieu.baerts@xxxxxxxxxxxx> Signed-off-by: Jakub Kicinski <kuba@xxxxxxxxxx> diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 59f8f3124855..1224dfca5bf3 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1047,6 +1047,7 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, if (err) return err; + inet_sk_state_store(newsk, TCP_LISTEN); err = kernel_listen(ssock, backlog); if (err) return err; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a66ec341485e..a6c7f2d24909 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2368,13 +2368,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, kfree_rcu(subflow, rcu); } else { /* otherwise tcp will dispose of the ssk and subflow ctx */ - if (ssk->sk_state == TCP_LISTEN) { - tcp_set_state(ssk, TCP_CLOSE); - mptcp_subflow_queue_clean(sk, ssk); - inet_csk_listen_stop(ssk); - mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); - } - __tcp_close(ssk, 0); /* close acquired an extra ref */ @@ -2902,10 +2895,24 @@ static __poll_t mptcp_check_readable(struct mptcp_sock *msk) return EPOLLIN | EPOLLRDNORM; } -static void mptcp_listen_inuse_dec(struct sock *sk) +static void mptcp_check_listen_stop(struct sock *sk) { - if (inet_sk_state_load(sk) == TCP_LISTEN) - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + struct sock *ssk; + + if (inet_sk_state_load(sk) != TCP_LISTEN) + return; + + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + ssk = mptcp_sk(sk)->first; + if (WARN_ON_ONCE(!ssk || inet_sk_state_load(ssk) != TCP_LISTEN)) + return; + + lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); + mptcp_subflow_queue_clean(sk, ssk); + inet_csk_listen_stop(ssk); + mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); + tcp_set_state(ssk, TCP_CLOSE); + release_sock(ssk); } bool __mptcp_close(struct sock *sk, long timeout) @@ -2918,7 +2925,7 @@ bool __mptcp_close(struct sock *sk, long timeout) WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { - mptcp_listen_inuse_dec(sk); + mptcp_check_listen_stop(sk); inet_sk_state_store(sk, TCP_CLOSE); goto cleanup; } @@ -3035,7 +3042,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) if (msk->fastopening) return -EBUSY; - mptcp_listen_inuse_dec(sk); + mptcp_check_listen_stop(sk); inet_sk_state_store(sk, TCP_CLOSE); mptcp_stop_timer(sk);
