1 files changed, 42 insertions, 67 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 1dbc62537259..8cd6cc67c2c5 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -36,15 +36,6 @@ struct mptcp6_sock {
 };
 #endif
 
-struct mptcp_skb_cb {
-	u64 map_seq;
-	u64 end_seq;
-	u32 offset;
-	u8  has_rxtstamp:1;
-};
-
-#define MPTCP_SKB_CB(__skb)	((struct mptcp_skb_cb *)&((__skb)->cb[0]))
-
 enum {
 	MPTCP_CMSG_TS = BIT(0),
 	MPTCP_CMSG_INQ = BIT(1),
@@ -107,7 +98,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	struct socket *ssock;
 	int err;
 
-	err = mptcp_subflow_create_socket(sk, &ssock);
+	err = mptcp_subflow_create_socket(sk, sk->sk_family, &ssock);
 	if (err)
 		return err;
 
@@ -200,7 +191,7 @@ static void mptcp_rfree(struct sk_buff *skb)
 	mptcp_rmem_uncharge(sk, len);
 }
 
-static void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk)
+void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk)
 {
 	skb_orphan(skb);
 	skb->sk = sk;
@@ -1602,7 +1593,7 @@ out:
 		__mptcp_check_send_data_fin(sk);
 }
 
-static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
+static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_sendmsg_info info = {
@@ -1611,7 +1602,6 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
 	struct mptcp_data_frag *dfrag;
 	struct sock *xmit_ssk;
 	int len, copied = 0;
-	bool first = true;
 
 	info.flags = 0;
 	while ((dfrag = mptcp_send_head(sk))) {
@@ -1621,11 +1611,10 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
 		while (len > 0) {
 			int ret = 0;
 
-			/* the caller already invoked the packet scheduler,
-			 * check for a different subflow usage only after
+			/* check for a different subflow usage only after
 			 * spooling the first chunk of data
 			 */
-			xmit_ssk = first ? ssk : mptcp_subflow_get_send(mptcp_sk(sk));
+			xmit_ssk = first ? ssk : mptcp_subflow_get_send(msk);
 			if (!xmit_ssk)
 				goto out;
 			if (xmit_ssk != ssk) {
@@ -1673,6 +1662,8 @@ static void mptcp_set_nospace(struct sock *sk)
 	set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags);
 }
 
+static int mptcp_disconnect(struct sock *sk, int flags);
+
 static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msghdr *msg,
 				  size_t len, int *copied_syn)
 {
@@ -1683,9 +1674,9 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msgh
 	lock_sock(ssk);
 	msg->msg_flags |= MSG_DONTWAIT;
 	msk->connect_flags = O_NONBLOCK;
-	msk->is_sendmsg = 1;
+	msk->fastopening = 1;
 	ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL);
-	msk->is_sendmsg = 0;
+	msk->fastopening = 0;
 	msg->msg_flags = saved_flags;
 	release_sock(ssk);
 
@@ -1699,6 +1690,8 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msgh
 		 */
 		if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR)
 			*copied_syn = 0;
+	} else if (ret && ret != -EINPROGRESS) {
+		mptcp_disconnect(sk, 0);
 	}
 
 	return ret;
@@ -1713,17 +1706,14 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	int ret = 0;
 	long timeo;
 
-	/* we don't support FASTOPEN yet */
-	if (msg->msg_flags & MSG_FASTOPEN)
-		return -EOPNOTSUPP;
-
 	/* silently ignore everything else */
-	msg->msg_flags &= MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL;
+	msg->msg_flags &= MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_FASTOPEN;
 
 	lock_sock(sk);
 
 	ssock = __mptcp_nmpc_socket(msk);
-	if (unlikely(ssock && inet_sk(ssock->sk)->defer_connect)) {
+	if (unlikely(ssock && (inet_sk(ssock->sk)->defer_connect ||
+			       msg->msg_flags & MSG_FASTOPEN))) {
 		int copied_syn = 0;
 
 		ret = mptcp_sendmsg_fastopen(sk, ssock->sk, msg, len, &copied_syn);
@@ -2275,7 +2265,7 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
 	struct mptcp_data_frag *cur, *rtx_head;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	if (__mptcp_check_fallback(mptcp_sk(sk)))
+	if (__mptcp_check_fallback(msk))
 		return false;
 
 	if (tcp_rtx_and_write_queues_empty(sk))
@@ -2367,8 +2357,9 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 		/* otherwise tcp will dispose of the ssk and subflow ctx */
 		if (ssk->sk_state == TCP_LISTEN) {
 			tcp_set_state(ssk, TCP_CLOSE);
-			mptcp_subflow_queue_clean(ssk);
+			mptcp_subflow_queue_clean(sk, ssk);
 			inet_csk_listen_stop(ssk);
+			mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
 		}
 		__tcp_close(ssk, 0);
 
@@ -2451,7 +2442,7 @@ static bool mptcp_check_close_timeout(const struct sock *sk)
 static void mptcp_check_fastclose(struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow, *tmp;
-	struct sock *sk = &msk->sk.icsk_inet.sk;
+	struct sock *sk = (struct sock *)msk;
 
 	if (likely(!READ_ONCE(msk->rcv_fastclose)))
 		return;
@@ -2613,7 +2604,7 @@ static void mptcp_do_fastclose(struct sock *sk)
 static void mptcp_worker(struct work_struct *work)
 {
 	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
-	struct sock *sk = &msk->sk.icsk_inet.sk;
+	struct sock *sk = (struct sock *)msk;
 	unsigned long fail_tout;
 	int state;
 
@@ -2725,6 +2716,8 @@ static int mptcp_init_sock(struct sock *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
 	 * propagate the correct value
 	 */
@@ -2946,7 +2939,7 @@ cleanup:
 
 	sock_hold(sk);
 	pr_debug("msk=%p state=%d", sk, sk->sk_state);
-	if (mptcp_sk(sk)->token)
+	if (msk->token)
 		mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
 
 	if (sk->sk_state == TCP_CLOSE) {
@@ -3000,13 +2993,21 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
+	/* We are on the fastopen error path. We can't call straight into the
+	 * subflows cleanup code due to lock nesting (we are already under
+	 * msk->firstsocket lock). Do nothing and leave the cleanup to the
+	 * caller.
+	 */
+	if (msk->fastopening)
+		return 0;
+
 	inet_sk_state_store(sk, TCP_CLOSE);
 
 	mptcp_stop_timer(sk);
 	sk_stop_timer(sk, &sk->sk_timer);
 
-	if (mptcp_sk(sk)->token)
-		mptcp_event(MPTCP_EVENT_CLOSED, mptcp_sk(sk), NULL, GFP_KERNEL);
+	if (msk->token)
+		mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
 
 	/* msk->subflow is still intact, the following will not free the first
 	 * subflow
@@ -3048,7 +3049,6 @@ struct sock *mptcp_sk_clone(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_sock *msk;
-	u64 ack_seq;
 
 	if (!nsk)
 		return NULL;
@@ -3074,15 +3074,6 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 	msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
 	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
 
-	if (mp_opt->suboptions & OPTIONS_MPTCP_MPC) {
-		msk->can_ack = true;
-		msk->remote_key = mp_opt->sndr_key;
-		mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq);
-		ack_seq++;
-		WRITE_ONCE(msk->ack_seq, ack_seq);
-		atomic64_set(&msk->rcv_wnd_sent, ack_seq);
-	}
-
 	sock_reset_flag(nsk, SOCK_RCU_FREE);
 	/* will be fully established after successful MPC subflow creation */
 	inet_sk_state_store(nsk, TCP_SYN_RECV);
@@ -3217,16 +3208,10 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk)
 	if (!mptcp_send_head(sk))
 		return;
 
-	if (!sock_owned_by_user(sk)) {
-		struct sock *xmit_ssk = mptcp_subflow_get_send(mptcp_sk(sk));
-
-		if (xmit_ssk == ssk)
-			__mptcp_subflow_push_pending(sk, ssk);
-		else if (xmit_ssk)
-			mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk), MPTCP_DELEGATE_SEND);
-	} else {
+	if (!sock_owned_by_user(sk))
+		__mptcp_subflow_push_pending(sk, ssk, false);
+	else
 		__set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags);
-	}
 }
 
 #define MPTCP_FLAGS_PROCESS_CTX_NEED (BIT(MPTCP_PUSH_PENDING) | \
@@ -3317,7 +3302,7 @@ void mptcp_subflow_process_delegated(struct sock *ssk)
 	if (test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) {
 		mptcp_data_lock(sk);
 		if (!sock_owned_by_user(sk))
-			__mptcp_subflow_push_pending(sk, ssk);
+			__mptcp_subflow_push_pending(sk, ssk, true);
 		else
 			__set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags);
 		mptcp_data_unlock(sk);
@@ -3361,7 +3346,6 @@ void mptcp_finish_connect(struct sock *ssk)
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk;
 	struct sock *sk;
-	u64 ack_seq;
 
 	subflow = mptcp_subflow_ctx(ssk);
 	sk = subflow->conn;
@@ -3369,22 +3353,16 @@ void mptcp_finish_connect(struct sock *ssk)
 
 	pr_debug("msk=%p, token=%u", sk, subflow->token);
 
-	mptcp_crypto_key_sha(subflow->remote_key, NULL, &ack_seq);
-	ack_seq++;
-	subflow->map_seq = ack_seq;
+	subflow->map_seq = subflow->iasn;
 	subflow->map_subflow_seq = 1;
 
 	/* the socket is not connected yet, no msk/subflow ops can access/race
 	 * accessing the field below
 	 */
-	WRITE_ONCE(msk->remote_key, subflow->remote_key);
 	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->ack_seq, ack_seq);
-	WRITE_ONCE(msk->can_ack, 1);
 	WRITE_ONCE(msk->snd_una, msk->write_seq);
-	atomic64_set(&msk->rcv_wnd_sent, ack_seq);
 
 	mptcp_pm_new_connection(msk, ssk, 0);
 
@@ -3566,7 +3544,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	/* if reaching here via the fastopen/sendmsg path, the caller already
 	 * acquired the subflow socket lock, too.
 	 */
-	if (msk->is_sendmsg)
+	if (msk->fastopening)
 		err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1);
 	else
 		err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags);
@@ -3682,6 +3660,8 @@ static int mptcp_listen(struct socket *sock, int backlog)
 	if (!err)
 		mptcp_copy_inaddrs(sock->sk, ssock->sk);
 
+	mptcp_event_pm_listener(ssock->sk, MPTCP_EVENT_LISTENER_CREATED);
+
 unlock:
 	release_sock(sock->sk);
 	return err;
@@ -3706,6 +3686,8 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 		struct mptcp_subflow_context *subflow;
 		struct sock *newsk = newsock->sk;
 
+		set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags);
+
 		lock_sock(newsk);
 
 		/* PM/worker can now acquire the first subflow socket
@@ -3919,12 +3901,6 @@ static const struct proto_ops mptcp_v6_stream_ops = {
 
 static struct proto mptcp_v6_prot;
 
-static void mptcp_v6_destroy(struct sock *sk)
-{
-	mptcp_destroy(sk);
-	inet6_destroy_sock(sk);
-}
-
 static struct inet_protosw mptcp_v6_protosw = {
 	.type		= SOCK_STREAM,
 	.protocol	= IPPROTO_MPTCP,
@@ -3940,7 +3916,6 @@ int __init mptcp_proto_v6_init(void)
 	mptcp_v6_prot = mptcp_prot;
 	strcpy(mptcp_v6_prot.name, "MPTCPv6");
 	mptcp_v6_prot.slab = NULL;
-	mptcp_v6_prot.destroy = mptcp_v6_destroy;
 	mptcp_v6_prot.obj_size = sizeof(struct mptcp6_sock);
 
 	err = proto_register(&mptcp_v6_prot, 1);