1 files changed, 120 insertions, 63 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 60b23b2716c4..08dc53f56bc2 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -49,18 +49,6 @@ static void __mptcp_check_send_data_fin(struct sock *sk);
 DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
 static struct net_device mptcp_napi_dev;
 
-/* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not
- * completed yet or has failed, return the subflow socket.
- * Otherwise return NULL.
- */
-struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk)
-{
-	if (!msk->subflow || READ_ONCE(msk->can_ack))
-		return NULL;
-
-	return msk->subflow;
-}
-
 /* Returns end sequence number of the receiver's advertised window */
 static u64 mptcp_wnd_end(const struct mptcp_sock *msk)
 {
@@ -116,6 +104,31 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	return 0;
 }
 
+/* If the MPC handshake is not started, returns the first subflow,
+ * eventually allocating it.
+ */
+struct socket *__mptcp_nmpc_socket(struct mptcp_sock *msk)
+{
+	struct sock *sk = (struct sock *)msk;
+	int ret;
+
+	if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
+		return ERR_PTR(-EINVAL);
+
+	if (!msk->subflow) {
+		if (msk->first)
+			return ERR_PTR(-EINVAL);
+
+		ret = __mptcp_socket_create(msk);
+		if (ret)
+			return ERR_PTR(ret);
+
+		mptcp_sockopt_sync(msk, msk->first);
+	}
+
+	return msk->subflow;
+}
+
 static void mptcp_drop(struct sock *sk, struct sk_buff *skb)
 {
 	sk_drops_add(sk, skb);
@@ -459,7 +472,7 @@ static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq)
 	return false;
 }
 
-static void mptcp_set_datafin_timeout(const struct sock *sk)
+static void mptcp_set_datafin_timeout(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 retransmits;
@@ -1662,13 +1675,31 @@ static void mptcp_set_nospace(struct sock *sk)
 
 static int mptcp_disconnect(struct sock *sk, int flags);
 
-static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msghdr *msg,
+static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 				  size_t len, int *copied_syn)
 {
 	unsigned int saved_flags = msg->msg_flags;
 	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct socket *ssock;
+	struct sock *ssk;
 	int ret;
 
+	/* on flags based fastopen the mptcp is supposed to create the
+	 * first subflow right now. Otherwise we are in the defer_connect
+	 * path, and the first subflow must be already present.
+	 * Since the defer_connect flag is cleared after the first succsful
+	 * fastopen attempt, no need to check for additional subflow status.
+	 */
+	if (msg->msg_flags & MSG_FASTOPEN) {
+		ssock = __mptcp_nmpc_socket(msk);
+		if (IS_ERR(ssock))
+			return PTR_ERR(ssock);
+	}
+	if (!msk->first)
+		return -EINVAL;
+
+	ssk = msk->first;
+
 	lock_sock(ssk);
 	msg->msg_flags |= MSG_DONTWAIT;
 	msk->connect_flags = O_NONBLOCK;
@@ -1691,6 +1722,7 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msgh
 	} else if (ret && ret != -EINPROGRESS) {
 		mptcp_disconnect(sk, 0);
 	}
+	inet_sk(sk)->defer_connect = 0;
 
 	return ret;
 }
@@ -1699,7 +1731,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct page_frag *pfrag;
-	struct socket *ssock;
 	size_t copied = 0;
 	int ret = 0;
 	long timeo;
@@ -1709,12 +1740,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	lock_sock(sk);
 
-	ssock = __mptcp_nmpc_socket(msk);
-	if (unlikely(ssock && (inet_sk(ssock->sk)->defer_connect ||
-			       msg->msg_flags & MSG_FASTOPEN))) {
+	if (unlikely(inet_sk(sk)->defer_connect || msg->msg_flags & MSG_FASTOPEN)) {
 		int copied_syn = 0;
 
-		ret = mptcp_sendmsg_fastopen(sk, ssock->sk, msg, len, &copied_syn);
+		ret = mptcp_sendmsg_fastopen(sk, msg, len, &copied_syn);
 		copied += copied_syn;
 		if (ret == -EINPROGRESS && copied_syn > 0)
 			goto out;
@@ -2315,7 +2344,26 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 			      unsigned int flags)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	bool need_push, dispose_it;
+	bool dispose_it, need_push = false;
+
+	/* If the first subflow moved to a close state before accept, e.g. due
+	 * to an incoming reset, mptcp either:
+	 * - if either the subflow or the msk are dead, destroy the context
+	 *   (the subflow socket is deleted by inet_child_forget) and the msk
+	 * - otherwise do nothing at the moment and take action at accept and/or
+	 *   listener shutdown - user-space must be able to accept() the closed
+	 *   socket.
+	 */
+	if (msk->in_accept_queue && msk->first == ssk) {
+		if (!sock_flag(sk, SOCK_DEAD) && !sock_flag(ssk, SOCK_DEAD))
+			return;
+
+		/* ensure later check in mptcp_worker() will dispose the msk */
+		sock_set_flag(sk, SOCK_DEAD);
+		lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
+		mptcp_subflow_drop_ctx(ssk);
+		goto out_release;
+	}
 
 	dispose_it = !msk->subflow || ssk != msk->subflow->sk;
 	if (dispose_it)
@@ -2351,28 +2399,22 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 	if (!inet_csk(ssk)->icsk_ulp_ops) {
 		WARN_ON_ONCE(!sock_flag(ssk, SOCK_DEAD));
 		kfree_rcu(subflow, rcu);
-	} else if (msk->in_accept_queue && msk->first == ssk) {
-		/* if the first subflow moved to a close state, e.g. due to
-		 * incoming reset and we reach here before inet_child_forget()
-		 * the TCP stack could later try to close it via
-		 * inet_csk_listen_stop(), or deliver it to the user space via
-		 * accept().
-		 * We can't delete the subflow - or risk a double free - nor let
-		 * the msk survive - or will be leaked in the non accept scenario:
-		 * fallback and let TCP cope with the subflow cleanup.
-		 */
-		WARN_ON_ONCE(sock_flag(ssk, SOCK_DEAD));
-		mptcp_subflow_drop_ctx(ssk);
 	} else {
 		/* otherwise tcp will dispose of the ssk and subflow ctx */
-		if (ssk->sk_state == TCP_LISTEN)
+		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 */
 		__sock_put(ssk);
 	}
+
+out_release:
 	release_sock(ssk);
 
 	sock_put(ssk);
@@ -2427,21 +2469,14 @@ static void __mptcp_close_subflow(struct sock *sk)
 		mptcp_close_ssk(sk, ssk, subflow);
 	}
 
-	/* if the MPC subflow has been closed before the msk is accepted,
-	 * msk will never be accept-ed, close it now
-	 */
-	if (!msk->first && msk->in_accept_queue) {
-		sock_set_flag(sk, SOCK_DEAD);
-		inet_sk_state_store(sk, TCP_CLOSE);
-	}
 }
 
-static bool mptcp_check_close_timeout(const struct sock *sk)
+static bool mptcp_should_close(const struct sock *sk)
 {
 	s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp;
 	struct mptcp_subflow_context *subflow;
 
-	if (delta >= TCP_TIMEWAIT_LEN)
+	if (delta >= TCP_TIMEWAIT_LEN || mptcp_sk(sk)->in_accept_queue)
 		return true;
 
 	/* if all subflows are in closed status don't bother with additional
@@ -2480,15 +2515,15 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 	/* Mirror the tcp_reset() error propagation */
 	switch (sk->sk_state) {
 	case TCP_SYN_SENT:
-		sk->sk_err = ECONNREFUSED;
+		WRITE_ONCE(sk->sk_err, ECONNREFUSED);
 		break;
 	case TCP_CLOSE_WAIT:
-		sk->sk_err = EPIPE;
+		WRITE_ONCE(sk->sk_err, EPIPE);
 		break;
 	case TCP_CLOSE:
 		return;
 	default:
-		sk->sk_err = ECONNRESET;
+		WRITE_ONCE(sk->sk_err, ECONNRESET);
 	}
 
 	inet_sk_state_store(sk, TCP_CLOSE);
@@ -2626,7 +2661,7 @@ static void mptcp_worker(struct work_struct *work)
 
 	lock_sock(sk);
 	state = sk->sk_state;
-	if (unlikely(state == TCP_CLOSE))
+	if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN)))
 		goto unlock;
 
 	mptcp_check_data_fin_ack(sk);
@@ -2649,7 +2684,7 @@ static void mptcp_worker(struct work_struct *work)
 	 * even if it is orphaned and in FIN_WAIT2 state
 	 */
 	if (sock_flag(sk, SOCK_DEAD)) {
-		if (mptcp_check_close_timeout(sk)) {
+		if (mptcp_should_close(sk)) {
 			inet_sk_state_store(sk, TCP_CLOSE);
 			mptcp_do_fastclose(sk);
 		}
@@ -2728,10 +2763,6 @@ static int mptcp_init_sock(struct sock *sk)
 	if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net))
 		return -ENOMEM;
 
-	ret = __mptcp_socket_create(mptcp_sk(sk));
-	if (ret)
-		return ret;
-
 	set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags);
 
 	/* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will
@@ -2895,6 +2926,14 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	sock_put(sk);
 }
 
+void __mptcp_unaccepted_force_close(struct sock *sk)
+{
+	sock_set_flag(sk, SOCK_DEAD);
+	inet_sk_state_store(sk, TCP_CLOSE);
+	mptcp_do_fastclose(sk);
+	__mptcp_destroy_sock(sk);
+}
+
 static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
 {
 	/* Concurrent splices from sk_receive_queue into receive_queue will
@@ -2928,10 +2967,13 @@ bool __mptcp_close(struct sock *sk, long timeout)
 		goto cleanup;
 	}
 
-	if (mptcp_check_readable(msk)) {
-		/* the msk has read data, do the MPTCP equivalent of TCP reset */
+	if (mptcp_check_readable(msk) || timeout < 0) {
+		/* If the msk has read data, or the caller explicitly ask it,
+		 * do the MPTCP equivalent of TCP reset, aka MPTCP fastclose
+		 */
 		inet_sk_state_store(sk, TCP_CLOSE);
 		mptcp_do_fastclose(sk);
+		timeout = 0;
 	} else if (mptcp_close_state(sk)) {
 		__mptcp_wr_shutdown(sk);
 	}
@@ -3143,7 +3185,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 	struct socket *listener;
 	struct sock *newsk;
 
-	listener = __mptcp_nmpc_socket(msk);
+	listener = msk->subflow;
 	if (WARN_ON_ONCE(!listener)) {
 		*err = -EINVAL;
 		return NULL;
@@ -3363,7 +3405,7 @@ static int mptcp_get_port(struct sock *sk, unsigned short snum)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct socket *ssock;
 
-	ssock = __mptcp_nmpc_socket(msk);
+	ssock = msk->subflow;
 	pr_debug("msk=%p, subflow=%p", msk, ssock);
 	if (WARN_ON_ONCE(!ssock))
 		return -EINVAL;
@@ -3551,8 +3593,8 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	int err = -EINVAL;
 
 	ssock = __mptcp_nmpc_socket(msk);
-	if (!ssock)
-		return -EINVAL;
+	if (IS_ERR(ssock))
+		return PTR_ERR(ssock);
 
 	mptcp_token_destroy(msk);
 	inet_sk_state_store(sk, TCP_SYN_SENT);
@@ -3640,8 +3682,8 @@ static int mptcp_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 
 	lock_sock(sock->sk);
 	ssock = __mptcp_nmpc_socket(msk);
-	if (!ssock) {
-		err = -EINVAL;
+	if (IS_ERR(ssock)) {
+		err = PTR_ERR(ssock);
 		goto unlock;
 	}
 
@@ -3677,8 +3719,8 @@ static int mptcp_listen(struct socket *sock, int backlog)
 
 	lock_sock(sk);
 	ssock = __mptcp_nmpc_socket(msk);
-	if (!ssock) {
-		err = -EINVAL;
+	if (IS_ERR(ssock)) {
+		err = PTR_ERR(ssock);
 		goto unlock;
 	}
 
@@ -3709,7 +3751,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 
 	pr_debug("msk=%p", msk);
 
-	ssock = __mptcp_nmpc_socket(msk);
+	/* buggy applications can call accept on socket states other then LISTEN
+	 * but no need to allocate the first subflow just to error out.
+	 */
+	ssock = msk->subflow;
 	if (!ssock)
 		return -EINVAL;
 
@@ -3733,6 +3778,18 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 			if (!ssk->sk_socket)
 				mptcp_sock_graft(ssk, newsock);
 		}
+
+		/* Do late cleanup for the first subflow as necessary. Also
+		 * deal with bad peers not doing a complete shutdown.
+		 */
+		if (msk->first &&
+		    unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) {
+			__mptcp_close_ssk(newsk, msk->first,
+					  mptcp_subflow_ctx(msk->first), 0);
+			if (unlikely(list_empty(&msk->conn_list)))
+				inet_sk_state_store(newsk, TCP_CLOSE);
+		}
+
 		release_sock(newsk);
 	}
 
@@ -3791,7 +3848,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 
 	/* This barrier is coupled with smp_wmb() in __mptcp_error_report() */
 	smp_rmb();
-	if (sk->sk_err)
+	if (READ_ONCE(sk->sk_err))
 		mask |= EPOLLERR;
 
 	return mask;