mptcp: Add handling of outgoing MP_JOIN requests

Subflow creation may be initiated by the path manager when
the primary connection is fully established and a remote
address has been received via ADD_ADDR.

Create an in-kernel sock and use kernel_connect() to
initiate connection.

Passive sockets can't acquire the mptcp socket lock at
subflow creation time, so an additional list protected by
a new spinlock is used to track the MPJ subflows.

Such list is spliced into conn_list tail every time the msk
socket lock is acquired, so that it will not interfere
with data flow on the original connection.

Data flow and connection failover not addressed by this commit.

Co-developed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Florian Westphal <fw@strlen.de>
Co-developed-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Co-developed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Peter Krystad <peter.krystad@linux.intel.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 30 insertions, 1 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index f2dac715a17e..3d84e0b83c99 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -241,6 +241,16 @@ wake:
 	sk->sk_data_ready(sk);
 }
 
+static void __mptcp_flush_join_list(struct mptcp_sock *msk)
+{
+	if (likely(list_empty(&msk->join_list)))
+		return;
+
+	spin_lock_bh(&msk->join_list_lock);
+	list_splice_tail_init(&msk->join_list, &msk->conn_list);
+	spin_unlock_bh(&msk->join_list_lock);
+}
+
 static bool mptcp_ext_cache_refill(struct mptcp_sock *msk)
 {
 	if (!msk->cached_ext)
@@ -462,6 +472,7 @@ fallback:
 		return ret >= 0 ? ret + copied : (copied ? copied : ret);
 	}
 
+	__mptcp_flush_join_list(msk);
 	ssk = mptcp_subflow_get_send(msk);
 	while (!sk_stream_memory_free(sk) || !ssk) {
 		ret = sk_stream_wait_memory(sk, &timeo);
@@ -603,6 +614,7 @@ fallback:
 
 	len = min_t(size_t, len, INT_MAX);
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
+	__mptcp_flush_join_list(msk);
 
 	while (len > (size_t)copied) {
 		int bytes_read;
@@ -718,6 +730,7 @@ static void mptcp_worker(struct work_struct *work)
 	struct sock *sk = &msk->sk.icsk_inet.sk;
 
 	lock_sock(sk);
+	__mptcp_flush_join_list(msk);
 	__mptcp_move_skbs(msk);
 	release_sock(sk);
 	sock_put(sk);
@@ -727,7 +740,10 @@ static int __mptcp_init_sock(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
+	spin_lock_init(&msk->join_list_lock);
+
 	INIT_LIST_HEAD(&msk->conn_list);
+	INIT_LIST_HEAD(&msk->join_list);
 	__set_bit(MPTCP_SEND_SPACE, &msk->flags);
 	INIT_WORK(&msk->work, mptcp_worker);
 
@@ -800,6 +816,8 @@ static void mptcp_close(struct sock *sk, long timeout)
 	mptcp_token_destroy(msk->token);
 	inet_sk_state_store(sk, TCP_CLOSE);
 
+	__mptcp_flush_join_list(msk);
+
 	list_splice_init(&msk->conn_list, &conn_list);
 
 	data_fin_tx_seq = msk->write_seq;
@@ -1107,6 +1125,7 @@ bool mptcp_finish_join(struct sock *sk)
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
 	struct sock *parent = (void *)msk;
 	struct socket *parent_sock;
+	bool ret;
 
 	pr_debug("msk=%p, subflow=%p", msk, subflow);
 
@@ -1122,7 +1141,15 @@ bool mptcp_finish_join(struct sock *sk)
 	if (parent_sock && !sk->sk_socket)
 		mptcp_sock_graft(sk, parent_sock);
 
-	return mptcp_pm_allow_new_subflow(msk);
+	ret = mptcp_pm_allow_new_subflow(msk);
+	if (ret) {
+		/* active connections are already on conn_list */
+		spin_lock_bh(&msk->join_list_lock);
+		if (!WARN_ON_ONCE(!list_empty(&subflow->node)))
+			list_add_tail(&subflow->node, &msk->join_list);
+		spin_unlock_bh(&msk->join_list_lock);
+	}
+	return ret;
 }
 
 bool mptcp_sk_is_subflow(const struct sock *sk)
@@ -1311,6 +1338,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 		/* set ssk->sk_socket of accept()ed flows to mptcp socket.
 		 * This is needed so NOSPACE flag can be set from tcp stack.
 		 */
+		__mptcp_flush_join_list(msk);
 		list_for_each_entry(subflow, &msk->conn_list, node) {
 			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
@@ -1392,6 +1420,7 @@ static int mptcp_shutdown(struct socket *sock, int how)
 			sock->state = SS_CONNECTED;
 	}
 
+	__mptcp_flush_join_list(msk);
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);