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 mptcp@lists.01.org and
https://is.gd/mptcp_upstream
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 57 insertions, 0 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 786978cb2db7..fec4b3a4b22d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -38,6 +38,7 @@
 #define pr_fmt(fmt) "TCP: " fmt
 
 #include <net/tcp.h>
+#include <net/mptcp.h>
 
 #include <linux/compiler.h>
 #include <linux/gfp.h>
@@ -414,6 +415,7 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
 #define OPTION_WSCALE		(1 << 3)
 #define OPTION_FAST_OPEN_COOKIE	(1 << 8)
 #define OPTION_SMC		(1 << 9)
+#define OPTION_MPTCP		(1 << 10)
 
 static void smc_options_write(__be32 *ptr, u16 *options)
 {
@@ -439,8 +441,17 @@ struct tcp_out_options {
 	__u8 *hash_location;	/* temporary pointer, overloaded */
 	__u32 tsval, tsecr;	/* need to include OPTION_TS */
 	struct tcp_fastopen_cookie *fastopen_cookie;	/* Fast open cookie */
+	struct mptcp_out_options mptcp;
 };
 
+static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts)
+{
+#if IS_ENABLED(CONFIG_MPTCP)
+	if (unlikely(OPTION_MPTCP & opts->options))
+		mptcp_write_options(ptr, &opts->mptcp);
+#endif
+}
+
 /* Write previously computed TCP options to the packet.
  *
  * Beware: Something in the Internet is very sensitive to the ordering of
@@ -549,6 +560,8 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 	}
 
 	smc_options_write(ptr, &options);
+
+	mptcp_options_write(ptr, opts);
 }
 
 static void smc_set_option(const struct tcp_sock *tp,
@@ -584,6 +597,22 @@ static void smc_set_option_cond(const struct tcp_sock *tp,
 #endif
 }
 
+static void mptcp_set_option_cond(const struct request_sock *req,
+				  struct tcp_out_options *opts,
+				  unsigned int *remaining)
+{
+	if (rsk_is_mptcp(req)) {
+		unsigned int size;
+
+		if (mptcp_synack_options(req, &size, &opts->mptcp)) {
+			if (*remaining >= size) {
+				opts->options |= OPTION_MPTCP;
+				*remaining -= size;
+			}
+		}
+	}
+}
+
 /* Compute TCP options for SYN packets. This is not the final
  * network wire format yet.
  */
@@ -653,6 +682,15 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 
 	smc_set_option(tp, opts, &remaining);
 
+	if (sk_is_mptcp(sk)) {
+		unsigned int size;
+
+		if (mptcp_syn_options(sk, skb, &size, &opts->mptcp)) {
+			opts->options |= OPTION_MPTCP;
+			remaining -= size;
+		}
+	}
+
 	return MAX_TCP_OPTION_SPACE - remaining;
 }
 
@@ -714,6 +752,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 		}
 	}
 
+	mptcp_set_option_cond(req, opts, &remaining);
+
 	smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining);
 
 	return MAX_TCP_OPTION_SPACE - remaining;
@@ -751,6 +791,23 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 		size += TCPOLEN_TSTAMP_ALIGNED;
 	}
 
+	/* MPTCP options have precedence over SACK for the limited TCP
+	 * option space because a MPTCP connection would be forced to
+	 * fall back to regular TCP if a required multipath option is
+	 * missing. SACK still gets a chance to use whatever space is
+	 * left.
+	 */
+	if (sk_is_mptcp(sk)) {
+		unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
+		unsigned int opt_size = 0;
+
+		if (mptcp_established_options(sk, skb, &opt_size, remaining,
+					      &opts->mptcp)) {
+			opts->options |= OPTION_MPTCP;
+			size += opt_size;
+		}
+	}
+
 	eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack;
 	if (unlikely(eff_sacks)) {
 		const unsigned int remaining = MAX_TCP_OPTION_SPACE - size;