1 files changed, 101 insertions, 103 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index bc81ea53a049..8ef2927ebca2 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -55,28 +55,14 @@ static u64 mptcp_wnd_end(const struct mptcp_sock *msk)
 	return READ_ONCE(msk->wnd_end);
 }
 
-static bool mptcp_is_tcpsk(struct sock *sk)
+static const struct proto_ops *mptcp_fallback_tcp_ops(const struct sock *sk)
 {
-	struct socket *sock = sk->sk_socket;
-
-	if (unlikely(sk->sk_prot == &tcp_prot)) {
-		/* we are being invoked after mptcp_accept() has
-		 * accepted a non-mp-capable flow: sk is a tcp_sk,
-		 * not an mptcp one.
-		 *
-		 * Hand the socket over to tcp so all further socket ops
-		 * bypass mptcp.
-		 */
-		WRITE_ONCE(sock->ops, &inet_stream_ops);
-		return true;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	} else if (unlikely(sk->sk_prot == &tcpv6_prot)) {
-		WRITE_ONCE(sock->ops, &inet6_stream_ops);
-		return true;
+	if (sk->sk_prot == &tcpv6_prot)
+		return &inet6_stream_ops;
 #endif
-	}
-
-	return false;
+	WARN_ON_ONCE(sk->sk_prot != &tcp_prot);
+	return &inet_stream_ops;
 }
 
 static int __mptcp_socket_create(struct mptcp_sock *msk)
@@ -443,11 +429,11 @@ static void mptcp_check_data_fin_ack(struct sock *sk)
 
 		switch (sk->sk_state) {
 		case TCP_FIN_WAIT1:
-			inet_sk_state_store(sk, TCP_FIN_WAIT2);
+			mptcp_set_state(sk, TCP_FIN_WAIT2);
 			break;
 		case TCP_CLOSING:
 		case TCP_LAST_ACK:
-			inet_sk_state_store(sk, TCP_CLOSE);
+			mptcp_set_state(sk, TCP_CLOSE);
 			break;
 		}
 
@@ -608,13 +594,13 @@ static bool mptcp_check_data_fin(struct sock *sk)
 
 		switch (sk->sk_state) {
 		case TCP_ESTABLISHED:
-			inet_sk_state_store(sk, TCP_CLOSE_WAIT);
+			mptcp_set_state(sk, TCP_CLOSE_WAIT);
 			break;
 		case TCP_FIN_WAIT1:
-			inet_sk_state_store(sk, TCP_CLOSING);
+			mptcp_set_state(sk, TCP_CLOSING);
 			break;
 		case TCP_FIN_WAIT2:
-			inet_sk_state_store(sk, TCP_CLOSE);
+			mptcp_set_state(sk, TCP_CLOSE);
 			break;
 		default:
 			/* Other states not expected */
@@ -789,7 +775,7 @@ static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk)
 	 */
 	ssk_state = inet_sk_state_load(ssk);
 	if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD))
-		inet_sk_state_store(sk, ssk_state);
+		mptcp_set_state(sk, ssk_state);
 	WRITE_ONCE(sk->sk_err, -err);
 
 	/* This barrier is coupled with smp_rmb() in mptcp_poll() */
@@ -1519,8 +1505,11 @@ static void mptcp_update_post_push(struct mptcp_sock *msk,
 
 void mptcp_check_and_set_pending(struct sock *sk)
 {
-	if (mptcp_send_head(sk))
-		mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING);
+	if (mptcp_send_head(sk)) {
+		mptcp_data_lock(sk);
+		mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING);
+		mptcp_data_unlock(sk);
+	}
 }
 
 static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
@@ -1974,6 +1963,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 	if (copied <= 0)
 		return;
 
+	if (!msk->rcvspace_init)
+		mptcp_rcv_space_init(msk, msk->first);
+
 	msk->rcvq_space.copied += copied;
 
 	mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC);
@@ -2328,9 +2320,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
 	if (__mptcp_check_fallback(msk))
 		return false;
 
-	if (tcp_rtx_and_write_queues_empty(sk))
-		return false;
-
 	/* the closing socket has some data untransmitted and/or unacked:
 	 * some data in the mptcp rtx queue has not really xmitted yet.
 	 * keep it simple and re-inject the whole mptcp level rtx queue
@@ -2477,7 +2466,7 @@ out:
 	    inet_sk_state_load(msk->first) == TCP_CLOSE) {
 		if (sk->sk_state != TCP_ESTABLISHED ||
 		    msk->in_accept_queue || sock_flag(sk, SOCK_DEAD)) {
-			inet_sk_state_store(sk, TCP_CLOSE);
+			mptcp_set_state(sk, TCP_CLOSE);
 			mptcp_close_wake_up(sk);
 		} else {
 			mptcp_start_tout_timer(sk);
@@ -2572,7 +2561,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 		WRITE_ONCE(sk->sk_err, ECONNRESET);
 	}
 
-	inet_sk_state_store(sk, TCP_CLOSE);
+	mptcp_set_state(sk, TCP_CLOSE);
 	WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 	smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
 	set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags);
@@ -2707,7 +2696,7 @@ static void mptcp_do_fastclose(struct sock *sk)
 	struct mptcp_subflow_context *subflow, *tmp;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	inet_sk_state_store(sk, TCP_CLOSE);
+	mptcp_set_state(sk, TCP_CLOSE);
 	mptcp_for_each_subflow_safe(msk, subflow, tmp)
 		__mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow),
 				  subflow, MPTCP_CF_FASTCLOSE);
@@ -2885,6 +2874,24 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
 	release_sock(ssk);
 }
 
+void mptcp_set_state(struct sock *sk, int state)
+{
+	int oldstate = sk->sk_state;
+
+	switch (state) {
+	case TCP_ESTABLISHED:
+		if (oldstate != TCP_ESTABLISHED)
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB);
+		break;
+
+	default:
+		if (oldstate == TCP_ESTABLISHED)
+			MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB);
+	}
+
+	inet_sk_state_store(sk, state);
+}
+
 static const unsigned char new_state[16] = {
 	/* current state:     new state:      action:	*/
 	[0 /* (Invalid) */] = TCP_CLOSE,
@@ -2907,7 +2914,7 @@ static int mptcp_close_state(struct sock *sk)
 	int next = (int)new_state[sk->sk_state];
 	int ns = next & TCP_STATE_MASK;
 
-	inet_sk_state_store(sk, ns);
+	mptcp_set_state(sk, ns);
 
 	return next & TCP_ACTION_FIN;
 }
@@ -3018,7 +3025,7 @@ bool __mptcp_close(struct sock *sk, long timeout)
 
 	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
 		mptcp_check_listen_stop(sk);
-		inet_sk_state_store(sk, TCP_CLOSE);
+		mptcp_set_state(sk, TCP_CLOSE);
 		goto cleanup;
 	}
 
@@ -3061,7 +3068,7 @@ cleanup:
 	 * state, let's not keep resources busy for no reasons
 	 */
 	if (subflows_alive == 0)
-		inet_sk_state_store(sk, TCP_CLOSE);
+		mptcp_set_state(sk, TCP_CLOSE);
 
 	sock_hold(sk);
 	pr_debug("msk=%p state=%d", sk, sk->sk_state);
@@ -3127,7 +3134,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 		return -EBUSY;
 
 	mptcp_check_listen_stop(sk);
-	inet_sk_state_store(sk, TCP_CLOSE);
+	mptcp_set_state(sk, TCP_CLOSE);
 
 	mptcp_stop_rtx_timer(sk);
 	mptcp_stop_tout_timer(sk);
@@ -3141,7 +3148,6 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE);
 	WRITE_ONCE(msk->flags, 0);
 	msk->cb_flags = 0;
-	msk->push_pending = 0;
 	msk->recovery = false;
 	msk->can_ack = false;
 	msk->fully_established = false;
@@ -3157,6 +3163,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	msk->bytes_received = 0;
 	msk->bytes_sent = 0;
 	msk->bytes_retrans = 0;
+	msk->rcvspace_init = 0;
 
 	WRITE_ONCE(sk->sk_shutdown, 0);
 	sk_error_report(sk);
@@ -3179,6 +3186,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 {
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
 	struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC);
+	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk;
 
 	if (!nsk)
@@ -3215,11 +3223,12 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 	/* this can't race with mptcp_close(), as the msk is
 	 * not yet exposted to user-space
 	 */
-	inet_sk_state_store(nsk, TCP_ESTABLISHED);
+	mptcp_set_state(nsk, TCP_ESTABLISHED);
 
 	/* The msk maintain a ref to each subflow in the connections list */
 	WRITE_ONCE(msk->first, ssk);
-	list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list);
+	subflow = mptcp_subflow_ctx(ssk);
+	list_add(&subflow->node, &msk->conn_list);
 	sock_hold(ssk);
 
 	/* new mpc subflow takes ownership of the newly
@@ -3234,6 +3243,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 	__mptcp_propagate_sndbuf(nsk, ssk);
 
 	mptcp_rcv_space_init(msk, ssk);
+
+	if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK)
+		__mptcp_subflow_fully_established(msk, subflow, mp_opt);
 	bh_unlock_sock(nsk);
 
 	/* note: the newly allocated socket refcount is 2 now */
@@ -3244,6 +3256,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
 {
 	const struct tcp_sock *tp = tcp_sk(ssk);
 
+	msk->rcvspace_init = 1;
 	msk->rcvq_space.copied = 0;
 	msk->rcvq_space.rtt_us = 0;
 
@@ -3254,46 +3267,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
 				      TCP_INIT_CWND * tp->advmss);
 	if (msk->rcvq_space.space == 0)
 		msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;
-
-	WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
-}
-
-static struct sock *mptcp_accept(struct sock *ssk, int flags, int *err,
-				 bool kern)
-{
-	struct sock *newsk;
-
-	pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk));
-	newsk = inet_csk_accept(ssk, flags, err, kern);
-	if (!newsk)
-		return NULL;
-
-	pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk));
-	if (sk_is_mptcp(newsk)) {
-		struct mptcp_subflow_context *subflow;
-		struct sock *new_mptcp_sock;
-
-		subflow = mptcp_subflow_ctx(newsk);
-		new_mptcp_sock = subflow->conn;
-
-		/* is_mptcp should be false if subflow->conn is missing, see
-		 * subflow_syn_recv_sock()
-		 */
-		if (WARN_ON_ONCE(!new_mptcp_sock)) {
-			tcp_sk(newsk)->is_mptcp = 0;
-			goto out;
-		}
-
-		newsk = new_mptcp_sock;
-		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
-	} else {
-		MPTCP_INC_STATS(sock_net(ssk),
-				MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
-	}
-
-out:
-	newsk->sk_kern_sock = kern;
-	return newsk;
 }
 
 void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
@@ -3367,8 +3340,7 @@ static void mptcp_release_cb(struct sock *sk)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	for (;;) {
-		unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) |
-				      msk->push_pending;
+		unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED);
 		struct list_head join_list;
 
 		if (!flags)
@@ -3384,7 +3356,6 @@ static void mptcp_release_cb(struct sock *sk)
 		 *    datapath acquires the msk socket spinlock while helding
 		 *    the subflow socket lock
 		 */
-		msk->push_pending = 0;
 		msk->cb_flags &= ~flags;
 		spin_unlock_bh(&sk->sk_lock.slock);
 
@@ -3402,12 +3373,12 @@ static void mptcp_release_cb(struct sock *sk)
 	if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags))
 		__mptcp_clean_una_wakeup(sk);
 	if (unlikely(msk->cb_flags)) {
-		/* be sure to set the current sk state before taking actions
+		/* be sure to sync the msk state before taking actions
 		 * depending on sk_state (MPTCP_ERROR_REPORT)
 		 * On sk release avoid actions depending on the first subflow
 		 */
-		if (__test_and_clear_bit(MPTCP_CONNECTED, &msk->cb_flags) && msk->first)
-			__mptcp_set_connected(sk);
+		if (__test_and_clear_bit(MPTCP_SYNC_STATE, &msk->cb_flags) && msk->first)
+			__mptcp_sync_state(sk, msk->pending_state);
 		if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags))
 			__mptcp_error_report(sk);
 		if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags))
@@ -3512,13 +3483,8 @@ void mptcp_finish_connect(struct sock *ssk)
 	 * accessing the field below
 	 */
 	WRITE_ONCE(msk->local_key, subflow->local_key);
-	WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
-	WRITE_ONCE(msk->snd_nxt, msk->write_seq);
-	WRITE_ONCE(msk->snd_una, msk->write_seq);
 
 	mptcp_pm_new_connection(msk, ssk, 0);
-
-	mptcp_rcv_space_init(msk, ssk);
 }
 
 void mptcp_sock_graft(struct sock *sk, struct socket *parent)
@@ -3674,7 +3640,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (IS_ERR(ssk))
 		return PTR_ERR(ssk);
 
-	inet_sk_state_store(sk, TCP_SYN_SENT);
+	mptcp_set_state(sk, TCP_SYN_SENT);
 	subflow = mptcp_subflow_ctx(ssk);
 #ifdef CONFIG_TCP_MD5SIG
 	/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
@@ -3724,7 +3690,7 @@ out:
 	if (unlikely(err)) {
 		/* avoid leaving a dangling token in an unconnected socket */
 		mptcp_token_destroy(msk);
-		inet_sk_state_store(sk, TCP_CLOSE);
+		mptcp_set_state(sk, TCP_CLOSE);
 		return err;
 	}
 
@@ -3739,7 +3705,6 @@ static struct proto mptcp_prot = {
 	.connect	= mptcp_connect,
 	.disconnect	= mptcp_disconnect,
 	.close		= mptcp_close,
-	.accept		= mptcp_accept,
 	.setsockopt	= mptcp_setsockopt,
 	.getsockopt	= mptcp_getsockopt,
 	.shutdown	= mptcp_shutdown,
@@ -3814,13 +3779,13 @@ static int mptcp_listen(struct socket *sock, int backlog)
 		goto unlock;
 	}
 
-	inet_sk_state_store(sk, TCP_LISTEN);
+	mptcp_set_state(sk, TCP_LISTEN);
 	sock_set_flag(sk, SOCK_RCU_FREE);
 
 	lock_sock(ssk);
 	err = __inet_listen_sk(ssk, backlog);
 	release_sock(ssk);
-	inet_sk_state_store(sk, inet_sk_state_load(ssk));
+	mptcp_set_state(sk, inet_sk_state_load(ssk));
 
 	if (!err) {
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -3849,18 +3814,36 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 	if (!ssk)
 		return -EINVAL;
 
-	newsk = mptcp_accept(ssk, flags, &err, kern);
+	pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk));
+	newsk = inet_csk_accept(ssk, flags, &err, kern);
 	if (!newsk)
 		return err;
 
-	lock_sock(newsk);
-
-	__inet_accept(sock, newsock, newsk);
-	if (!mptcp_is_tcpsk(newsock->sk)) {
-		struct mptcp_sock *msk = mptcp_sk(newsk);
+	pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk));
+	if (sk_is_mptcp(newsk)) {
 		struct mptcp_subflow_context *subflow;
+		struct sock *new_mptcp_sock;
+
+		subflow = mptcp_subflow_ctx(newsk);
+		new_mptcp_sock = subflow->conn;
+
+		/* is_mptcp should be false if subflow->conn is missing, see
+		 * subflow_syn_recv_sock()
+		 */
+		if (WARN_ON_ONCE(!new_mptcp_sock)) {
+			tcp_sk(newsk)->is_mptcp = 0;
+			goto tcpfallback;
+		}
+
+		newsk = new_mptcp_sock;
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
+
+		newsk->sk_kern_sock = kern;
+		lock_sock(newsk);
+		__inet_accept(sock, newsock, newsk);
 
 		set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags);
+		msk = mptcp_sk(newsk);
 		msk->in_accept_queue = 0;
 
 		/* set ssk->sk_socket of accept()ed flows to mptcp socket.
@@ -3880,8 +3863,23 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 			__mptcp_close_ssk(newsk, msk->first,
 					  mptcp_subflow_ctx(msk->first), 0);
 			if (unlikely(list_is_singular(&msk->conn_list)))
-				inet_sk_state_store(newsk, TCP_CLOSE);
+				mptcp_set_state(newsk, TCP_CLOSE);
 		}
+	} else {
+		MPTCP_INC_STATS(sock_net(ssk),
+				MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
+tcpfallback:
+		newsk->sk_kern_sock = kern;
+		lock_sock(newsk);
+		__inet_accept(sock, newsock, newsk);
+		/* we are being invoked after accepting a non-mp-capable
+		 * flow: sk is a tcp_sk, not an mptcp one.
+		 *
+		 * Hand the socket over to tcp so all further socket ops
+		 * bypass mptcp.
+		 */
+		WRITE_ONCE(newsock->sk->sk_socket->ops,
+			   mptcp_fallback_tcp_ops(newsock->sk));
 	}
 	release_sock(newsk);