mptcp: plug races between subflow fail and subflow creation

We have races similar to the one addressed by the previous patch between
subflow failing and additional subflow creation. They are just harder to
trigger.

The solution is similar. Use a separate flag to track the condition
'socket state prevent any additional subflow creation' protected by the
fallback lock.

The socket fallback makes such flag true, and also receiving or sending
an MP_FAIL option.

The field 'allow_infinite_fallback' is now always touched under the
relevant lock, we can drop the ONCE annotation on write.

Fixes: 478d770008b0 ("mptcp: send out MP_FAIL when data checksum fails")
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250714-net-mptcp-fallback-races-v1-2-391aff963322@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 14 insertions, 5 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index a6a35985e551..1802bc5435a1 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1302,20 +1302,29 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss
 		mptcp_schedule_work(sk);
 }
 
-static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
+static bool mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	unsigned long fail_tout;
 
+	/* we are really failing, prevent any later subflow join */
+	spin_lock_bh(&msk->fallback_lock);
+	if (!msk->allow_infinite_fallback) {
+		spin_unlock_bh(&msk->fallback_lock);
+		return false;
+	}
+	msk->allow_subflows = false;
+	spin_unlock_bh(&msk->fallback_lock);
+
 	/* graceful failure can happen only on the MPC subflow */
 	if (WARN_ON_ONCE(ssk != READ_ONCE(msk->first)))
-		return;
+		return false;
 
 	/* since the close timeout take precedence on the fail one,
 	 * no need to start the latter when the first is already set
 	 */
 	if (sock_flag((struct sock *)msk, SOCK_DEAD))
-		return;
+		return true;
 
 	/* we don't need extreme accuracy here, use a zero fail_tout as special
 	 * value meaning no fail timeout at all;
@@ -1327,6 +1336,7 @@ static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
 	tcp_send_ack(ssk);
 
 	mptcp_reset_tout_timer(msk, subflow->fail_tout);
+	return true;
 }
 
 static bool subflow_check_data_avail(struct sock *ssk)
@@ -1387,12 +1397,11 @@ fallback:
 		    (subflow->mp_join || subflow->valid_csum_seen)) {
 			subflow->send_mp_fail = 1;
 
-			if (!READ_ONCE(msk->allow_infinite_fallback)) {
+			if (!mptcp_subflow_fail(msk, ssk)) {
 				subflow->reset_transient = 0;
 				subflow->reset_reason = MPTCP_RST_EMIDDLEBOX;
 				goto reset;
 			}
-			mptcp_subflow_fail(msk, ssk);
 			WRITE_ONCE(subflow->data_avail, true);
 			return true;
 		}