mptcp: Implement MPTCP receive path

Parses incoming DSS options and populates outgoing MPTCP ACK
fields. MPTCP fields are parsed from the TCP option header and placed in
an skb extension, allowing the upper MPTCP layer to access MPTCP
options after the skb has gone through the TCP stack.

The subflow implements its own data_ready() ops, which ensures that the
pending data is in sequence - according to MPTCP seq number - dropping
out-of-seq skbs. The DATA_READY bit flag is set if this is the case.
This allows the MPTCP socket layer to determine if more data is
available without having to consult the individual subflows.

It additionally validates the current mapping and propagates EoF events
to the connection socket.

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

include/linux/tcp.h

@@ -82,9 +82,19 @@ struct tcp_sack_block {
 struct mptcp_options_received {
 	u64	sndr_key;
 	u64	rcvr_key;
+	u64	data_ack;
+	u64	data_seq;
+	u32	subflow_seq;
+	u16	data_len;
 	u8	mp_capable : 1,
 		mp_join : 1,
 		dss : 1;
+	u8	use_map:1,
+		dsn64:1,
+		data_fin:1,
+		use_ack:1,
+		ack64:1,
+		__unused:3;
 };
 #endif
 

include/net/mptcp.h

@@ -60,6 +60,8 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
 bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 			       unsigned int *size, unsigned int remaining,
 			       struct mptcp_out_options *opts);
+void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
+			    struct tcp_options_received *opt_rx);
 
 void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts);
 
@@ -150,6 +152,12 @@ static inline bool mptcp_established_options(struct sock *sk,
 	return false;
 }
 
+static inline void mptcp_incoming_options(struct sock *sk,
+					  struct sk_buff *skb,
+					  struct tcp_options_received *opt_rx)
+{
+}
+
 static inline void mptcp_skb_ext_move(struct sk_buff *to,
 				      const struct sk_buff *from)
 {

net/ipv4/tcp_input.c

@@ -4770,6 +4770,9 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	bool fragstolen;
 	int eaten;
 
+	if (sk_is_mptcp(sk))
+		mptcp_incoming_options(sk, skb, &tp->rx_opt);
+
 	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
 		__kfree_skb(skb);
 		return;
@@ -6346,8 +6349,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	case TCP_CLOSE_WAIT:
 	case TCP_CLOSING:
 	case TCP_LAST_ACK:
-		if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
+		if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
+			if (sk_is_mptcp(sk))
+				mptcp_incoming_options(sk, skb, &tp->rx_opt);
 			break;
+		}
 		/* fall through */
 	case TCP_FIN_WAIT1:
 	case TCP_FIN_WAIT2:

net/mptcp/options.c

@@ -14,6 +14,7 @@ void mptcp_parse_option(const unsigned char *ptr, int opsize,
 {
 	struct mptcp_options_received *mp_opt = &opt_rx->mptcp;
 	u8 subtype = *ptr >> 4;
+	int expected_opsize;
 	u8 version;
 	u8 flags;
 
@@ -64,7 +65,79 @@ void mptcp_parse_option(const unsigned char *ptr, int opsize,
 
 	case MPTCPOPT_DSS:
 		pr_debug("DSS");
+		ptr++;
+
+		flags = (*ptr++) & MPTCP_DSS_FLAG_MASK;
+		mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0;
+		mp_opt->dsn64 = (flags & MPTCP_DSS_DSN64) != 0;
+		mp_opt->use_map = (flags & MPTCP_DSS_HAS_MAP) != 0;
+		mp_opt->ack64 = (flags & MPTCP_DSS_ACK64) != 0;
+		mp_opt->use_ack = (flags & MPTCP_DSS_HAS_ACK);
+
+		pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d",
+			 mp_opt->data_fin, mp_opt->dsn64,
+			 mp_opt->use_map, mp_opt->ack64,
+			 mp_opt->use_ack);
+
+		expected_opsize = TCPOLEN_MPTCP_DSS_BASE;
+
+		if (mp_opt->use_ack) {
+			if (mp_opt->ack64)
+				expected_opsize += TCPOLEN_MPTCP_DSS_ACK64;
+			else
+				expected_opsize += TCPOLEN_MPTCP_DSS_ACK32;
+		}
+
+		if (mp_opt->use_map) {
+			if (mp_opt->dsn64)
+				expected_opsize += TCPOLEN_MPTCP_DSS_MAP64;
+			else
+				expected_opsize += TCPOLEN_MPTCP_DSS_MAP32;
+		}
+
+		/* RFC 6824, Section 3.3:
+		 * If a checksum is present, but its use had
+		 * not been negotiated in the MP_CAPABLE handshake,
+		 * the checksum field MUST be ignored.
+		 */
+		if (opsize != expected_opsize &&
+		    opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM)
+			break;
+
 		mp_opt->dss = 1;
+
+		if (mp_opt->use_ack) {
+			if (mp_opt->ack64) {
+				mp_opt->data_ack = get_unaligned_be64(ptr);
+				ptr += 8;
+			} else {
+				mp_opt->data_ack = get_unaligned_be32(ptr);
+				ptr += 4;
+			}
+
+			pr_debug("data_ack=%llu", mp_opt->data_ack);
+		}
+
+		if (mp_opt->use_map) {
+			if (mp_opt->dsn64) {
+				mp_opt->data_seq = get_unaligned_be64(ptr);
+				ptr += 8;
+			} else {
+				mp_opt->data_seq = get_unaligned_be32(ptr);
+				ptr += 4;
+			}
+
+			mp_opt->subflow_seq = get_unaligned_be32(ptr);
+			ptr += 4;
+
+			mp_opt->data_len = get_unaligned_be16(ptr);
+			ptr += 2;
+
+			pr_debug("data_seq=%llu subflow_seq=%u data_len=%u",
+				 mp_opt->data_seq, mp_opt->subflow_seq,
+				 mp_opt->data_len);
+		}
+
 		break;
 
 	default:
@@ -275,6 +348,40 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
 	return false;
 }
 
+void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
+			    struct tcp_options_received *opt_rx)
+{
+	struct mptcp_options_received *mp_opt;
+	struct mptcp_ext *mpext;
+
+	mp_opt = &opt_rx->mptcp;
+
+	if (!mp_opt->dss)
+		return;
+
+	mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
+	if (!mpext)
+		return;
+
+	memset(mpext, 0, sizeof(*mpext));
+
+	if (mp_opt->use_map) {
+		mpext->data_seq = mp_opt->data_seq;
+		mpext->subflow_seq = mp_opt->subflow_seq;
+		mpext->data_len = mp_opt->data_len;
+		mpext->use_map = 1;
+		mpext->dsn64 = mp_opt->dsn64;
+	}
+
+	if (mp_opt->use_ack) {
+		mpext->data_ack = mp_opt->data_ack;
+		mpext->use_ack = 1;
+		mpext->ack64 = mp_opt->ack64;
+	}
+
+	mpext->data_fin = mp_opt->data_fin;
+}
+
 void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
 {
 	if ((OPTION_MPTCP_MPC_SYN |

net/mptcp/protocol.c

@@ -224,6 +224,33 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	return ret;
 }
 
+int mptcp_read_actor(read_descriptor_t *desc, struct sk_buff *skb,
+		     unsigned int offset, size_t len)
+{
+	struct mptcp_read_arg *arg = desc->arg.data;
+	size_t copy_len;
+
+	copy_len = min(desc->count, len);
+
+	if (likely(arg->msg)) {
+		int err;
+
+		err = skb_copy_datagram_msg(skb, offset, arg->msg, copy_len);
+		if (err) {
+			pr_debug("error path");
+			desc->error = err;
+			return err;
+		}
+	} else {
+		pr_debug("Flushing skb payload");
+	}
+
+	desc->count -= copy_len;
+
+	pr_debug("consumed %zu bytes, %zu left", copy_len, desc->count);
+	return copy_len;
+}
+
 static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			 int nonblock, int flags, int *addr_len)
 {
@@ -414,7 +441,10 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 		msk->write_seq = subflow->idsn + 1;
 		ack_seq++;
 		msk->ack_seq = ack_seq;
+		subflow->map_seq = ack_seq;
+		subflow->map_subflow_seq = 1;
 		subflow->rel_write_seq = 1;
+		subflow->tcp_sock = ssk;
 		newsk = new_mptcp_sock;
 		mptcp_copy_inaddrs(newsk, ssk);
 		list_add(&subflow->node, &msk->conn_list);
@@ -519,8 +549,12 @@ void mptcp_finish_connect(struct sock *ssk)
 	sk = subflow->conn;
 	msk = mptcp_sk(sk);
 
+	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_subflow_seq = 1;
 	subflow->rel_write_seq = 1;
 
 	/* the socket is not connected yet, no msk/subflow ops can access/race

net/mptcp/protocol.h

@@ -33,7 +33,9 @@
 #define TCPOLEN_MPTCP_MPC_SYNACK	12
 #define TCPOLEN_MPTCP_MPC_ACK		20
 #define TCPOLEN_MPTCP_DSS_BASE		4
+#define TCPOLEN_MPTCP_DSS_ACK32		4
 #define TCPOLEN_MPTCP_DSS_ACK64		8
+#define TCPOLEN_MPTCP_DSS_MAP32		10
 #define TCPOLEN_MPTCP_DSS_MAP64		14
 #define TCPOLEN_MPTCP_DSS_CHECKSUM	2
 
@@ -50,6 +52,10 @@
 #define MPTCP_DSS_HAS_MAP	BIT(2)
 #define MPTCP_DSS_ACK64		BIT(1)
 #define MPTCP_DSS_HAS_ACK	BIT(0)
+#define MPTCP_DSS_FLAG_MASK	(0x1F)
+
+/* MPTCP socket flags */
+#define MPTCP_DATA_READY	BIT(0)
 
 /* MPTCP connection sock */
 struct mptcp_sock {
@@ -60,6 +66,7 @@ struct mptcp_sock {
 	u64		write_seq;
 	u64		ack_seq;
 	u32		token;
+	unsigned long	flags;
 	struct list_head conn_list;
 	struct skb_ext	*cached_ext;	/* for the next sendmsg */
 	struct socket	*subflow; /* outgoing connect/listener/!mp_capable */
@@ -82,6 +89,7 @@ struct mptcp_subflow_request_sock {
 	u64	remote_key;
 	u64	idsn;
 	u32	token;
+	u32	ssn_offset;
 };
 
 static inline struct mptcp_subflow_request_sock *
@@ -96,15 +104,27 @@ struct mptcp_subflow_context {
 	u64	local_key;
 	u64	remote_key;
 	u64	idsn;
+	u64	map_seq;
 	u32	token;
 	u32	rel_write_seq;
+	u32	map_subflow_seq;
+	u32	ssn_offset;
+	u32	map_data_len;
 	u32	request_mptcp : 1,  /* send MP_CAPABLE */
 		mp_capable : 1,	    /* remote is MPTCP capable */
 		fourth_ack : 1,	    /* send initial DSS */
-		conn_finished : 1;
+		conn_finished : 1,
+		map_valid : 1,
+		data_avail : 1,
+		rx_eof : 1;
+
 	struct	sock *tcp_sock;	    /* tcp sk backpointer */
 	struct	sock *conn;	    /* parent mptcp_sock */
 	const	struct inet_connection_sock_af_ops *icsk_af_ops;
+	void	(*tcp_data_ready)(struct sock *sk);
+	void	(*tcp_state_change)(struct sock *sk);
+	void	(*tcp_write_space)(struct sock *sk);
+
 	struct	rcu_head rcu;
 };
 
@@ -123,14 +143,49 @@ mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow)
 	return subflow->tcp_sock;
 }
 
+static inline u64
+mptcp_subflow_get_map_offset(const struct mptcp_subflow_context *subflow)
+{
+	return tcp_sk(mptcp_subflow_tcp_sock(subflow))->copied_seq -
+		      subflow->ssn_offset -
+		      subflow->map_subflow_seq;
+}
+
+static inline u64
+mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow)
+{
+	return subflow->map_seq + mptcp_subflow_get_map_offset(subflow);
+}
+
+int mptcp_is_enabled(struct net *net);
+bool mptcp_subflow_data_available(struct sock *sk);
 void mptcp_subflow_init(void);
 int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock);
 
+static inline void mptcp_subflow_tcp_fallback(struct sock *sk,
+					      struct mptcp_subflow_context *ctx)
+{
+	sk->sk_data_ready = ctx->tcp_data_ready;
+	sk->sk_state_change = ctx->tcp_state_change;
+	sk->sk_write_space = ctx->tcp_write_space;
+
+	inet_csk(sk)->icsk_af_ops = ctx->icsk_af_ops;
+}
+
 extern const struct inet_connection_sock_af_ops ipv4_specific;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 extern const struct inet_connection_sock_af_ops ipv6_specific;
 #endif
 
+void mptcp_proto_init(void);
+
+struct mptcp_read_arg {
+	struct msghdr *msg;
+};
+
+int mptcp_read_actor(read_descriptor_t *desc, struct sk_buff *skb,
+		     unsigned int offset, size_t len);
+
 void mptcp_get_options(const struct sk_buff *skb,
 		       struct tcp_options_received *opt_rx);
 
@@ -164,4 +219,11 @@ static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb)
 	return (struct mptcp_ext *)skb_ext_find(skb, SKB_EXT_MPTCP);
 }
 
+static inline bool before64(__u64 seq1, __u64 seq2)
+{
+	return (__s64)(seq1 - seq2) < 0;
+}
+
+#define after64(seq2, seq1)	before64(seq1, seq2)
+
 #endif /* __MPTCP_PROTOCOL_H */