Merge branch 'mptcp-Improve-DATA_FIN-transmission'

Mat Martineau says:

====================
mptcp: Improve DATA_FIN transmission

MPTCP's DATA_FIN flag is sent in a DSS option when closing the
MPTCP-level connection. This patch series prepares for correct DATA_FIN
handling across multiple subflows (where individual subflows may
disconnect without closing the entire MPTCP connection) by changing the
way the MPTCP-level socket requests a DATA_FIN on a subflow and
propagates the necessary data for the TCP option.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

net/mptcp/options.c

@@ -304,21 +304,22 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
 static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow,
 				 struct mptcp_ext *ext)
 {
-	ext->data_fin = 1;
-
 	if (!ext->use_map) {
 		/* RFC6824 requires a DSS mapping with specific values
 		 * if DATA_FIN is set but no data payload is mapped
 		 */
+		ext->data_fin = 1;
 		ext->use_map = 1;
 		ext->dsn64 = 1;
-		ext->data_seq = mptcp_sk(subflow->conn)->write_seq;
+		ext->data_seq = subflow->data_fin_tx_seq;
 		ext->subflow_seq = 0;
 		ext->data_len = 1;
-	} else {
-		/* If there's an existing DSS mapping, DATA_FIN consumes
-		 * 1 additional byte of mapping space.
+	} else if (ext->data_seq + ext->data_len == subflow->data_fin_tx_seq) {
+		/* If there's an existing DSS mapping and it is the
+		 * final mapping, DATA_FIN consumes 1 additional byte of
+		 * mapping space.
 		 */
+		ext->data_fin = 1;
 		ext->data_len++;
 	}
 }
@@ -354,8 +355,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 		if (mpext)
 			opts->ext_copy = *mpext;
 
-		if (skb && tcp_fin &&
-		    subflow->conn->sk_state != TCP_ESTABLISHED)
+		if (skb && tcp_fin && subflow->data_fin_tx_enable)
 			mptcp_write_data_fin(subflow, &opts->ext_copy);
 		ret = true;
 	}

net/mptcp/protocol.c

@@ -419,6 +419,15 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		return -EOPNOTSUPP;
 
 	lock_sock(sk);
+
+	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+
+	if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
+		ret = sk_stream_wait_connect(sk, &timeo);
+		if (ret)
+			goto out;
+	}
+
 	ssock = __mptcp_tcp_fallback(msk);
 	if (unlikely(ssock)) {
 fallback:
@@ -427,8 +436,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		return ret >= 0 ? ret + copied : (copied ? copied : ret);
 	}
 
-	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
-
 	ssk = mptcp_subflow_get(msk);
 	if (!ssk) {
 		release_sock(sk);
@@ -460,6 +467,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	ssk_check_wmem(msk, ssk);
 	release_sock(ssk);
+out:
 	release_sock(sk);
 	return ret;
 }
@@ -712,7 +720,8 @@ static void mptcp_cancel_work(struct sock *sk)
 		sock_put(sk);
 }
 
-static void mptcp_subflow_shutdown(struct sock *ssk, int how)
+static void mptcp_subflow_shutdown(struct sock *ssk, int how,
+				   bool data_fin_tx_enable, u64 data_fin_tx_seq)
 {
 	lock_sock(ssk);
 
@@ -725,6 +734,14 @@ static void mptcp_subflow_shutdown(struct sock *ssk, int how)
 		tcp_disconnect(ssk, O_NONBLOCK);
 		break;
 	default:
+		if (data_fin_tx_enable) {
+			struct mptcp_subflow_context *subflow;
+
+			subflow = mptcp_subflow_ctx(ssk);
+			subflow->data_fin_tx_seq = data_fin_tx_seq;
+			subflow->data_fin_tx_enable = 1;
+		}
+
 		ssk->sk_shutdown |= how;
 		tcp_shutdown(ssk, how);
 		break;
@@ -741,6 +758,7 @@ static void mptcp_close(struct sock *sk, long timeout)
 	struct mptcp_subflow_context *subflow, *tmp;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	LIST_HEAD(conn_list);
+	u64 data_fin_tx_seq;
 
 	lock_sock(sk);
 
@@ -749,11 +767,15 @@ static void mptcp_close(struct sock *sk, long timeout)
 
 	list_splice_init(&msk->conn_list, &conn_list);
 
+	data_fin_tx_seq = msk->write_seq;
+
 	release_sock(sk);
 
 	list_for_each_entry_safe(subflow, tmp, &conn_list, node) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
+		subflow->data_fin_tx_seq = data_fin_tx_seq;
+		subflow->data_fin_tx_enable = 1;
 		__mptcp_close_ssk(sk, ssk, subflow, timeout);
 	}
 
@@ -846,7 +868,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 			*err = -ENOBUFS;
 			local_bh_enable();
 			release_sock(sk);
-			mptcp_subflow_shutdown(newsk, SHUT_RDWR + 1);
+			mptcp_subflow_shutdown(newsk, SHUT_RDWR + 1, 0, 0);
 			tcp_close(newsk, 0);
 			return NULL;
 		}
@@ -1301,7 +1323,7 @@ static int mptcp_shutdown(struct socket *sock, int how)
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
 
-		mptcp_subflow_shutdown(tcp_sk, how);
+		mptcp_subflow_shutdown(tcp_sk, how, 1, msk->write_seq);
 	}
 
 out_unlock:

net/mptcp/protocol.h

@@ -125,7 +125,9 @@ struct mptcp_subflow_context {
 		mpc_map : 1,
 		data_avail : 1,
 		rx_eof : 1,
+		data_fin_tx_enable : 1,
 		can_ack : 1;	    /* only after processing the remote a key */
+	u64	data_fin_tx_seq;
 
 	struct	sock *tcp_sock;	    /* tcp sk backpointer */
 	struct	sock *conn;	    /* parent mptcp_sock */