Merge branch 'mptcp-multiple-subflows-path-management'

Mat Martineau says:

====================
Multipath TCP part 3: Multiple subflows and path management

v2 -> v3: Remove 'inline' in .c files, fix uapi bit macros, and rebase.

v1 -> v2: Rebase on current net-next, fix for netlink limit setting,
and update .gitignore for selftest.

This patch set allows more than one TCP subflow to be established and
used for a multipath TCP connection. Subflows are added to an existing
connection using the MP_JOIN option during the 3-way handshake. With
multiple TCP subflows available, sent data is now stored in the MPTCP
socket so it may be retransmitted on any TCP subflow if there is no
DATA_ACK before a timeout. If an MPTCP-level timeout occurs, data is
retransmitted using an available subflow. Storing this sent data
requires the addition of memory accounting at the MPTCP level, which was
previously delegated to the single subflow. Incoming DATA_ACKs now free
data from the MPTCP-level retransmit buffer.

IP addresses available for new subflow connections can now be advertised
and received with the ADD_ADDR option, and the corresponding REMOVE_ADDR
option likewise advertises that an address is no longer available.

The MPTCP path manager netlink interface has commands to set in-kernel
limits for the number of concurrent subflows and control the
advertisement of IP addresses between peers.

To track and debug MPTCP connections there are new MPTCP MIB counters,
and subflow context can be requested using inet_diag. The MPTCP
self-tests now validate multiple-subflow operation and the netlink path
manager interface.
====================

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

Author: davem330

MAINTAINERS

@@ -11727,6 +11727,7 @@ 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:	include/uapi/linux/mptcp.h
 F:	net/mptcp/
 F:	tools/testing/selftests/net/mptcp/
 

include/linux/tcp.h

@@ -86,16 +86,36 @@ struct mptcp_options_received {
 	u64	data_seq;
 	u32	subflow_seq;
 	u16	data_len;
-	u8	mp_capable : 1,
+	u16	mp_capable : 1,
 		mp_join : 1,
-		dss : 1;
+		dss : 1,
+		add_addr : 1,
+		rm_addr : 1,
+		family : 4,
+		echo : 1,
+		backup : 1;
+	u32	token;
+	u32	nonce;
+	u64	thmac;
+	u8	hmac[20];
+	u8	join_id;
 	u8	use_map:1,
 		dsn64:1,
 		data_fin:1,
 		use_ack:1,
 		ack64:1,
 		mpc_map:1,
 		__unused:2;
+	u8	addr_id;
+	u8	rm_id;
+	union {
+		struct in_addr	addr;
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+		struct in6_addr	addr6;
+#endif
+	};
+	u64	ahmac;
+	u16	port;
 };
 #endif
 
@@ -131,6 +151,8 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
 #if IS_ENABLED(CONFIG_MPTCP)
 	rx_opt->mptcp.mp_capable = 0;
 	rx_opt->mptcp.mp_join = 0;
+	rx_opt->mptcp.add_addr = 0;
+	rx_opt->mptcp.rm_addr = 0;
 	rx_opt->mptcp.dss = 0;
 #endif
 }

include/net/mptcp.h

@@ -12,6 +12,8 @@
 #include <linux/tcp.h>
 #include <linux/types.h>
 
+struct seq_file;
+
 /* MPTCP sk_buff extension data */
 struct mptcp_ext {
 	u64		data_ack;
@@ -33,6 +35,21 @@ struct mptcp_out_options {
 	u16 suboptions;
 	u64 sndr_key;
 	u64 rcvr_key;
+	union {
+		struct in_addr addr;
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+		struct in6_addr addr6;
+#endif
+	};
+	u8 addr_id;
+	u64 ahmac;
+	u8 rm_id;
+	u8 join_id;
+	u8 backup;
+	u32 nonce;
+	u64 thmac;
+	u32 token;
+	u8 hmac[20];
 	struct mptcp_ext ext_copy;
 #endif
 };
@@ -106,6 +123,9 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
 				 skb_ext_find(from, SKB_EXT_MPTCP));
 }
 
+bool mptcp_sk_is_subflow(const struct sock *sk);
+
+void mptcp_seq_show(struct seq_file *seq);
 #else
 
 static inline void mptcp_init(void)
@@ -172,6 +192,12 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
 	return true;
 }
 
+static inline bool mptcp_sk_is_subflow(const struct sock *sk)
+{
+	return false;
+}
+
+static inline void mptcp_seq_show(struct seq_file *seq) { }
 #endif /* CONFIG_MPTCP */
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)

include/net/netns/mib.h

@@ -27,6 +27,9 @@ struct netns_mib {
 #if IS_ENABLED(CONFIG_TLS)
 	DEFINE_SNMP_STAT(struct linux_tls_mib, tls_statistics);
 #endif
+#ifdef CONFIG_MPTCP
+	DEFINE_SNMP_STAT(struct mptcp_mib, mptcp_statistics);
+#endif
 };
 
 #endif

include/uapi/linux/inet_diag.h

@@ -166,6 +166,7 @@ enum {
 	INET_ULP_INFO_UNSPEC,
 	INET_ULP_INFO_NAME,
 	INET_ULP_INFO_TLS,
+	INET_ULP_INFO_MPTCP,
 	__INET_ULP_INFO_MAX,
 };
 #define INET_ULP_INFO_MAX (__INET_ULP_INFO_MAX - 1)

include/uapi/linux/mptcp.h

@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _UAPI_MPTCP_H
+#define _UAPI_MPTCP_H
+
+#include <linux/const.h>
+#include <linux/types.h>
+
+#define MPTCP_SUBFLOW_FLAG_MCAP_REM		_BITUL(0)
+#define MPTCP_SUBFLOW_FLAG_MCAP_LOC		_BITUL(1)
+#define MPTCP_SUBFLOW_FLAG_JOIN_REM		_BITUL(2)
+#define MPTCP_SUBFLOW_FLAG_JOIN_LOC		_BITUL(3)
+#define MPTCP_SUBFLOW_FLAG_BKUP_REM		_BITUL(4)
+#define MPTCP_SUBFLOW_FLAG_BKUP_LOC		_BITUL(5)
+#define MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED	_BITUL(6)
+#define MPTCP_SUBFLOW_FLAG_CONNECTED		_BITUL(7)
+#define MPTCP_SUBFLOW_FLAG_MAPVALID		_BITUL(8)
+
+enum {
+	MPTCP_SUBFLOW_ATTR_UNSPEC,
+	MPTCP_SUBFLOW_ATTR_TOKEN_REM,
+	MPTCP_SUBFLOW_ATTR_TOKEN_LOC,
+	MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ,
+	MPTCP_SUBFLOW_ATTR_MAP_SEQ,
+	MPTCP_SUBFLOW_ATTR_MAP_SFSEQ,
+	MPTCP_SUBFLOW_ATTR_SSN_OFFSET,
+	MPTCP_SUBFLOW_ATTR_MAP_DATALEN,
+	MPTCP_SUBFLOW_ATTR_FLAGS,
+	MPTCP_SUBFLOW_ATTR_ID_REM,
+	MPTCP_SUBFLOW_ATTR_ID_LOC,
+	MPTCP_SUBFLOW_ATTR_PAD,
+	__MPTCP_SUBFLOW_ATTR_MAX
+};
+
+#define MPTCP_SUBFLOW_ATTR_MAX (__MPTCP_SUBFLOW_ATTR_MAX - 1)
+
+/* netlink interface */
+#define MPTCP_PM_NAME		"mptcp_pm"
+#define MPTCP_PM_CMD_GRP_NAME	"mptcp_pm_cmds"
+#define MPTCP_PM_VER		0x1
+
+/*
+ * ATTR types defined for MPTCP
+ */
+enum {
+	MPTCP_PM_ATTR_UNSPEC,
+
+	MPTCP_PM_ATTR_ADDR,				/* nested address */
+	MPTCP_PM_ATTR_RCV_ADD_ADDRS,			/* u32 */
+	MPTCP_PM_ATTR_SUBFLOWS,				/* u32 */
+
+	__MPTCP_PM_ATTR_MAX
+};
+
+#define MPTCP_PM_ATTR_MAX (__MPTCP_PM_ATTR_MAX - 1)
+
+enum {
+	MPTCP_PM_ADDR_ATTR_UNSPEC,
+
+	MPTCP_PM_ADDR_ATTR_FAMILY,			/* u16 */
+	MPTCP_PM_ADDR_ATTR_ID,				/* u8 */
+	MPTCP_PM_ADDR_ATTR_ADDR4,			/* struct in_addr */
+	MPTCP_PM_ADDR_ATTR_ADDR6,			/* struct in6_addr */
+	MPTCP_PM_ADDR_ATTR_PORT,			/* u16 */
+	MPTCP_PM_ADDR_ATTR_FLAGS,			/* u32 */
+	MPTCP_PM_ADDR_ATTR_IF_IDX,			/* s32 */
+
+	__MPTCP_PM_ADDR_ATTR_MAX
+};
+
+#define MPTCP_PM_ADDR_ATTR_MAX (__MPTCP_PM_ADDR_ATTR_MAX - 1)
+
+#define MPTCP_PM_ADDR_FLAG_SIGNAL			(1 << 0)
+#define MPTCP_PM_ADDR_FLAG_SUBFLOW			(1 << 1)
+#define MPTCP_PM_ADDR_FLAG_BACKUP			(1 << 2)
+
+enum {
+	MPTCP_PM_CMD_UNSPEC,
+
+	MPTCP_PM_CMD_ADD_ADDR,
+	MPTCP_PM_CMD_DEL_ADDR,
+	MPTCP_PM_CMD_GET_ADDR,
+	MPTCP_PM_CMD_FLUSH_ADDRS,
+	MPTCP_PM_CMD_SET_LIMITS,
+	MPTCP_PM_CMD_GET_LIMITS,
+
+	__MPTCP_PM_CMD_AFTER_LAST
+};
+
+#endif /* _UAPI_MPTCP_H */

net/ipv4/af_inet.c

@@ -1793,6 +1793,10 @@ static __net_exit void ipv4_mib_exit_net(struct net *net)
 	free_percpu(net->mib.net_statistics);
 	free_percpu(net->mib.ip_statistics);
 	free_percpu(net->mib.tcp_statistics);
+#ifdef CONFIG_MPTCP
+	/* allocated on demand, see mptcp_init_sock() */
+	free_percpu(net->mib.mptcp_statistics);
+#endif
 }
 
 static __net_initdata struct pernet_operations ipv4_mib_ops = {

net/ipv4/proc.c

@@ -32,6 +32,7 @@
 #include <net/icmp.h>
 #include <net/protocol.h>
 #include <net/tcp.h>
+#include <net/mptcp.h>
 #include <net/udp.h>
 #include <net/udplite.h>
 #include <linux/bottom_half.h>
@@ -485,6 +486,7 @@ static int netstat_seq_show(struct seq_file *seq, void *v)
 					     offsetof(struct ipstats_mib, syncp)));
 
 	seq_putc(seq, '\n');
+	mptcp_seq_show(seq);
 	return 0;
 }
 

net/ipv4/tcp_minisocks.c

@@ -774,6 +774,12 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	if (!child)
 		goto listen_overflow;
 
+	if (own_req && sk_is_mptcp(child) && mptcp_sk_is_subflow(child)) {
+		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
+		inet_csk_reqsk_queue_drop_and_put(sk, req);
+		return child;
+	}
+
 	sock_rps_save_rxhash(child, skb);
 	tcp_synack_rtt_meas(child, req);
 	*req_stolen = !own_req;

net/mptcp/Makefile

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_MPTCP) += mptcp.o
 
-mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o
+mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \
+	   mib.o pm_netlink.o