Merge branch 'mptcp-fixes-for-5-13'

Mat Martineau says:

====================
mptcp: Fixes for 5.13

These patches address two issues in MPTCP.

Patch 1 fixes a locking issue affecting MPTCP-level retransmissions.

Patches 2-4 improve handling of out-of-order packet arrival early
in a connection, so it falls back to TCP rather than forcing a
reset. Includes a selftest.
====================

Link: https://lore.kernel.org/r/20210527233140.182728-1-mathew.j.martineau@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 64 insertions, 44 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 2bc199549a88..5edc686faff1 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -947,6 +947,10 @@ static void __mptcp_update_wmem(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
+#ifdef CONFIG_LOCKDEP
+	WARN_ON_ONCE(!lockdep_is_held(&sk->sk_lock.slock));
+#endif
+
 	if (!msk->wmem_reserved)
 		return;
 
@@ -1085,10 +1089,20 @@ out:
 
 static void __mptcp_clean_una_wakeup(struct sock *sk)
 {
+#ifdef CONFIG_LOCKDEP
+	WARN_ON_ONCE(!lockdep_is_held(&sk->sk_lock.slock));
+#endif
 	__mptcp_clean_una(sk);
 	mptcp_write_space(sk);
 }
 
+static void mptcp_clean_una_wakeup(struct sock *sk)
+{
+	mptcp_data_lock(sk);
+	__mptcp_clean_una_wakeup(sk);
+	mptcp_data_unlock(sk);
+}
+
 static void mptcp_enter_memory_pressure(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow;
@@ -2299,7 +2313,7 @@ static void __mptcp_retrans(struct sock *sk)
 	struct sock *ssk;
 	int ret;
 
-	__mptcp_clean_una_wakeup(sk);
+	mptcp_clean_una_wakeup(sk);
 	dfrag = mptcp_rtx_head(sk);
 	if (!dfrag) {
 		if (mptcp_data_fin_enabled(msk)) {
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index bde6be77ea73..ef3d037f984a 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -630,21 +630,20 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 
 	/* if the sk is MP_CAPABLE, we try to fetch the client key */
 	if (subflow_req->mp_capable) {
-		if (TCP_SKB_CB(skb)->seq != subflow_req->ssn_offset + 1) {
-			/* here we can receive and accept an in-window,
-			 * out-of-order pkt, which will not carry the MP_CAPABLE
-			 * opt even on mptcp enabled paths
-			 */
-			goto create_msk;
-		}
-
+		/* we can receive and accept an in-window, out-of-order pkt,
+		 * which may not carry the MP_CAPABLE opt even on mptcp enabled
+		 * paths: always try to extract the peer key, and fallback
+		 * for packets missing it.
+		 * Even OoO DSS packets coming legitly after dropped or
+		 * reordered MPC will cause fallback, but we don't have other
+		 * options.
+		 */
 		mptcp_get_options(skb, &mp_opt);
 		if (!mp_opt.mp_capable) {
 			fallback = true;
 			goto create_child;
 		}
 
-create_msk:
 		new_msk = mptcp_sk_clone(listener->conn, &mp_opt, req);
 		if (!new_msk)
 			fallback = true;
@@ -1012,21 +1011,11 @@ static bool subflow_check_data_avail(struct sock *ssk)
 
 		status = get_mapping_status(ssk, msk);
 		trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue));
-		if (status == MAPPING_INVALID) {
-			ssk->sk_err = EBADMSG;
-			goto fatal;
-		}
-		if (status == MAPPING_DUMMY) {
-			__mptcp_do_fallback(msk);
-			skb = skb_peek(&ssk->sk_receive_queue);
-			subflow->map_valid = 1;
-			subflow->map_seq = READ_ONCE(msk->ack_seq);
-			subflow->map_data_len = skb->len;
-			subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq -
-						   subflow->ssn_offset;
-			subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL;
-			return true;
-		}
+		if (unlikely(status == MAPPING_INVALID))
+			goto fallback;
+
+		if (unlikely(status == MAPPING_DUMMY))
+			goto fallback;
 
 		if (status != MAPPING_OK)
 			goto no_data;
@@ -1039,10 +1028,8 @@ static bool subflow_check_data_avail(struct sock *ssk)
 		 * MP_CAPABLE-based mapping
 		 */
 		if (unlikely(!READ_ONCE(msk->can_ack))) {
-			if (!subflow->mpc_map) {
-				ssk->sk_err = EBADMSG;
-				goto fatal;
-			}
+			if (!subflow->mpc_map)
+				goto fallback;
 			WRITE_ONCE(msk->remote_key, subflow->remote_key);
 			WRITE_ONCE(msk->ack_seq, subflow->map_seq);
 			WRITE_ONCE(msk->can_ack, true);
@@ -1070,17 +1057,31 @@ static bool subflow_check_data_avail(struct sock *ssk)
 no_data:
 	subflow_sched_work_if_closed(msk, ssk);
 	return false;
-fatal:
-	/* fatal protocol error, close the socket */
-	/* This barrier is coupled with smp_rmb() in tcp_poll() */
-	smp_wmb();
-	ssk->sk_error_report(ssk);
-	tcp_set_state(ssk, TCP_CLOSE);
-	subflow->reset_transient = 0;
-	subflow->reset_reason = MPTCP_RST_EMPTCP;
-	tcp_send_active_reset(ssk, GFP_ATOMIC);
-	subflow->data_avail = 0;
-	return false;
+
+fallback:
+	/* RFC 8684 section 3.7. */
+	if (subflow->mp_join || subflow->fully_established) {
+		/* fatal protocol error, close the socket.
+		 * subflow_error_report() will introduce the appropriate barriers
+		 */
+		ssk->sk_err = EBADMSG;
+		ssk->sk_error_report(ssk);
+		tcp_set_state(ssk, TCP_CLOSE);
+		subflow->reset_transient = 0;
+		subflow->reset_reason = MPTCP_RST_EMPTCP;
+		tcp_send_active_reset(ssk, GFP_ATOMIC);
+		subflow->data_avail = 0;
+		return false;
+	}
+
+	__mptcp_do_fallback(msk);
+	skb = skb_peek(&ssk->sk_receive_queue);
+	subflow->map_valid = 1;
+	subflow->map_seq = READ_ONCE(msk->ack_seq);
+	subflow->map_data_len = skb->len;
+	subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset;
+	subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL;
+	return true;
 }
 
 bool mptcp_subflow_data_available(struct sock *sk)
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 3c4cb72ed8a4..9ca5f1ba461e 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -501,6 +501,7 @@ do_transfer()
 	local stat_ackrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
 	local stat_cookietx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent")
 	local stat_cookierx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv")
+	local stat_ooo_now=$(get_mib_counter "${listener_ns}" "TcpExtTCPOFOQueue")
 
 	expect_synrx=$((stat_synrx_last_l))
 	expect_ackrx=$((stat_ackrx_last_l))
@@ -518,10 +519,14 @@ do_transfer()
 			"${stat_synrx_now_l}" "${expect_synrx}" 1>&2
 		retc=1
 	fi
-	if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ]; then
-		printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \
-			"${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2
-		rets=1
+	if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} -a ${stat_ooo_now} -eq 0 ]; then
+		if [ ${stat_ooo_now} -eq 0 ]; then
+			printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \
+				"${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2
+			rets=1
+		else
+			printf "[ Note ] fallback due to TCP OoO"
+		fi
 	fi
 
 	if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then