Merge branch 'mptcp-part-two'

Christoph Paasch says:

====================
Multipath TCP part 2: Single subflow & RFC8684 support

v2 -> v3: Added RFC8684-style handshake (see below fore more details) and some minor fixes
v1 -> v2: Rebased on latest "Multipath TCP: Prerequisites" v3 series

This set adds MPTCP connection establishment, writing & reading MPTCP
options on data packets, a sysctl to allow MPTCP per-namespace, and self
tests. This is sufficient to establish and maintain a connection with a
MPTCP peer, but will not yet allow or initiate establishment of
additional MPTCP subflows.

We also add the necessary code for the RFC8684-style handshake.
RFC8684 obsoletes the experimental RFC6824 and makes MPTCP move-on to
version 1.

Originally our plan was to submit single-subflow and RFC8684 support in
two patchsets, but to simplify the merging-process and ensure that a coherent
MPTCP-version lands in Linux we decided to merge the two sets into a single
one.

The MPTCP patchset exclusively supports RFC 8684. Although all MPTCP
deployments are currently based on RFC 6824, future deployments will be
migrating to MPTCP version 1. 3GPP's 5G standardization also solely supports
RFC 8684. In addition, we believe that this initial submission of MPTCP will be
cleaner by solely supporting RFC 8684. If later on support for the old
MPTCP-version is required it can always be added in the future.

The major difference between RFC 8684 and RFC 6824 is that it has a better
support for servers using TCP SYN-cookies by reliably retransmitting the
MP_CAPABLE option.

Before ending this cover letter with some refs, it is worth mentioning
that we promise David Miller that merging this series will be rewarded by
Twitter dopamine hits :-D

Clone/fetch:
https://github.com/multipath-tcp/mptcp_net-next.git (tag: netdev-v3-part2)

Browse:
https://github.com/multipath-tcp/mptcp_net-next/tree/netdev-v3-part2

Thank you for your review. You can find us at [email protected] and
https://is.gd/mptcp_upstream
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

MAINTAINERS

@@ -11583,6 +11583,8 @@ W:	https://github.com/multipath-tcp/mptcp_net-next/wiki
 B:	https://github.com/multipath-tcp/mptcp_net-next/issues
 S:	Maintained
 F:	include/net/mptcp.h
+F:	net/mptcp/
+F:	tools/testing/selftests/net/mptcp/
 
 NETWORKING [TCP]
 M:	Eric Dumazet <[email protected]>

include/linux/tcp.h

@@ -78,6 +78,27 @@ struct tcp_sack_block {
 #define TCP_SACK_SEEN     (1 << 0)   /*1 = peer is SACK capable, */
 #define TCP_DSACK_SEEN    (1 << 2)   /*1 = DSACK was received from peer*/
 
+#if IS_ENABLED(CONFIG_MPTCP)
+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,
+		mpc_map:1,
+		__unused:2;
+};
+#endif
+
 struct tcp_options_received {
 /*	PAWS/RTTM data	*/
 	int	ts_recent_stamp;/* Time we stored ts_recent (for aging) */
@@ -95,6 +116,9 @@ struct tcp_options_received {
 	u8	num_sacks;	/* Number of SACK blocks		*/
 	u16	user_mss;	/* mss requested by user in ioctl	*/
 	u16	mss_clamp;	/* Maximal mss, negotiated at connection setup */
+#if IS_ENABLED(CONFIG_MPTCP)
+	struct mptcp_options_received	mptcp;
+#endif
 };
 
 static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
@@ -104,6 +128,11 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
 #if IS_ENABLED(CONFIG_SMC)
 	rx_opt->smc_ok = 0;
 #endif
+#if IS_ENABLED(CONFIG_MPTCP)
+	rx_opt->mptcp.mp_capable = 0;
+	rx_opt->mptcp.mp_join = 0;
+	rx_opt->mptcp.dss = 0;
+#endif
 }
 
 /* This is the max number of SACKS that we'll generate and process. It's safe
@@ -119,6 +148,9 @@ struct tcp_request_sock {
 	const struct tcp_request_sock_ops *af_specific;
 	u64				snt_synack; /* first SYNACK sent time */
 	bool				tfo_listener;
+#if IS_ENABLED(CONFIG_MPTCP)
+	bool				is_mptcp;
+#endif
 	u32				txhash;
 	u32				rcv_isn;
 	u32				snt_isn;
@@ -379,6 +411,9 @@ struct tcp_sock {
 	u32	mtu_info; /* We received an ICMP_FRAG_NEEDED / ICMPV6_PKT_TOOBIG
 			   * while socket was owned by user.
 			   */
+#if IS_ENABLED(CONFIG_MPTCP)
+	bool	is_mptcp;
+#endif
 
 #ifdef CONFIG_TCP_MD5SIG
 /* TCP AF-Specific parts; only used by MD5 Signature support so far */

include/net/mptcp.h

@@ -9,6 +9,7 @@
 #define __NET_MPTCP_H
 
 #include <linux/skbuff.h>
+#include <linux/tcp.h>
 #include <linux/types.h>
 
 /* MPTCP sk_buff extension data */
@@ -22,12 +23,49 @@ struct mptcp_ext {
 			data_fin:1,
 			use_ack:1,
 			ack64:1,
-			__unused:3;
+			mpc_map:1,
+			__unused:2;
 	/* one byte hole */
 };
 
+struct mptcp_out_options {
+#if IS_ENABLED(CONFIG_MPTCP)
+	u16 suboptions;
+	u64 sndr_key;
+	u64 rcvr_key;
+	struct mptcp_ext ext_copy;
+#endif
+};
+
 #ifdef CONFIG_MPTCP
 
+void mptcp_init(void);
+
+static inline bool sk_is_mptcp(const struct sock *sk)
+{
+	return tcp_sk(sk)->is_mptcp;
+}
+
+static inline bool rsk_is_mptcp(const struct request_sock *req)
+{
+	return tcp_rsk(req)->is_mptcp;
+}
+
+void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr,
+			int opsize, struct tcp_options_received *opt_rx);
+bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
+		       unsigned int *size, struct mptcp_out_options *opts);
+void mptcp_rcv_synsent(struct sock *sk);
+bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
+			  struct mptcp_out_options *opts);
+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);
+
 /* move the skb extension owership, with the assumption that 'to' is
  * newly allocated
  */
@@ -70,6 +108,59 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
 
 #else
 
+static inline void mptcp_init(void)
+{
+}
+
+static inline bool sk_is_mptcp(const struct sock *sk)
+{
+	return false;
+}
+
+static inline bool rsk_is_mptcp(const struct request_sock *req)
+{
+	return false;
+}
+
+static inline void mptcp_parse_option(const struct sk_buff *skb,
+				      const unsigned char *ptr, int opsize,
+				      struct tcp_options_received *opt_rx)
+{
+}
+
+static inline bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
+				     unsigned int *size,
+				     struct mptcp_out_options *opts)
+{
+	return false;
+}
+
+static inline void mptcp_rcv_synsent(struct sock *sk)
+{
+}
+
+static inline bool mptcp_synack_options(const struct request_sock *req,
+					unsigned int *size,
+					struct mptcp_out_options *opts)
+{
+	return false;
+}
+
+static inline bool mptcp_established_options(struct sock *sk,
+					     struct sk_buff *skb,
+					     unsigned int *size,
+					     unsigned int remaining,
+					     struct mptcp_out_options *opts)
+{
+	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)
 {
@@ -82,4 +173,16 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
 }
 
 #endif /* CONFIG_MPTCP */
+
+void mptcp_handle_ipv6_mapped(struct sock *sk, bool mapped);
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+int mptcpv6_init(void);
+#elif IS_ENABLED(CONFIG_IPV6)
+static inline int mptcpv6_init(void)
+{
+	return 0;
+}
+#endif
+
 #endif /* __NET_MPTCP_H */

net/Kconfig

@@ -91,6 +91,7 @@ if INET
 source "net/ipv4/Kconfig"
 source "net/ipv6/Kconfig"
 source "net/netlabel/Kconfig"
+source "net/mptcp/Kconfig"
 
 endif # if INET
 

net/Makefile

@@ -87,3 +87,4 @@ endif
 obj-$(CONFIG_QRTR)		+= qrtr/
 obj-$(CONFIG_NET_NCSI)		+= ncsi/
 obj-$(CONFIG_XDP_SOCKETS)	+= xdp/
+obj-$(CONFIG_MPTCP)		+= mptcp/

net/ipv4/tcp.c

@@ -271,6 +271,7 @@
 #include <net/icmp.h>
 #include <net/inet_common.h>
 #include <net/tcp.h>
+#include <net/mptcp.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
 #include <net/sock.h>
@@ -4021,4 +4022,5 @@ void __init tcp_init(void)
 	tcp_metrics_init();
 	BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0);
 	tcp_tasklet_init();
+	mptcp_init();
 }

net/ipv4/tcp_input.c

@@ -79,6 +79,7 @@
 #include <trace/events/tcp.h>
 #include <linux/jump_label_ratelimit.h>
 #include <net/busy_poll.h>
+#include <net/mptcp.h>
 
 int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
 
@@ -3924,6 +3925,10 @@ void tcp_parse_options(const struct net *net,
 				 */
 				break;
 #endif
+			case TCPOPT_MPTCP:
+				mptcp_parse_option(skb, ptr, opsize, opt_rx);
+				break;
+
 			case TCPOPT_FASTOPEN:
 				tcp_parse_fastopen_option(
 					opsize - TCPOLEN_FASTOPEN_BASE,
@@ -4765,6 +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;
@@ -5973,6 +5981,9 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		tcp_initialize_rcv_mss(sk);
 
+		if (sk_is_mptcp(sk))
+			mptcp_rcv_synsent(sk);
+
 		/* Remember, tcp_poll() does not lock socket!
 		 * Change state from SYN-SENT only after copied_seq
 		 * is initialized. */
@@ -6338,8 +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:
@@ -6595,6 +6609,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 
 	tcp_rsk(req)->af_specific = af_ops;
 	tcp_rsk(req)->ts_off = 0;
+#if IS_ENABLED(CONFIG_MPTCP)
+	tcp_rsk(req)->is_mptcp = 0;
+#endif
 
 	tcp_clear_options(&tmp_opt);
 	tmp_opt.mss_clamp = af_ops->mss_clamp;