Merge branch 'mptcp-next'

Mat Martineau says:

====================
mptcp: Add SOL_MPTCP getsockopt support

Here's the first new MPTCP feature for the v5.16 cycle, and I'll defer
to Florian's helpful description of the series implementing some new
MPTCP socket options:

========

This adds the MPTCP_INFO, MPTCP_TCPINFO and MPTCP_SUBFLOW_ADDRS
mptcp getsockopt optnames.

MPTCP_INFO exposes the mptcp_info struct as an alternative to the
existing netlink diag interface.

MPTCP_TCPINFO exposes the tcp_info struct.
Unlike SOL_TCP/TCP_INFO, this returns one struct for each active
subflow.

MPTCP_SUBFLOW_ADDRS allows userspace to discover the ip addresses/ports
used by the local and remote endpoints, one for each active tcp subflow.

MPTCP_TCPINFO and MPTCP_SUBFLOW_ADDRS share the same meta-header that
needs to be pre-filled by userspace with the size of the data structures
it expects.  This is done to allow extension of the involved structs
later on, without breaking backwards compatibility.

The meta-structure can also be used to discover the required space
to obtain all information, as kernel will fill in the number of
active subflows even if there is not enough room for the requested info
itself.

More information is available in the individual patches.
Last patch adds test cases for the three optnames.

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

include/linux/socket.h

@@ -364,6 +364,7 @@ struct ucred {
 #define SOL_KCM		281
 #define SOL_TLS		282
 #define SOL_XDP		283
+#define SOL_MPTCP	284
 
 /* IPX options */
 #define IPX_TYPE	1

include/net/mptcp.h

@@ -12,6 +12,8 @@
 #include <linux/tcp.h>
 #include <linux/types.h>
 
+struct mptcp_info;
+struct mptcp_sock;
 struct seq_file;
 
 /* MPTCP sk_buff extension data */
@@ -121,6 +123,8 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb);
 void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 			 struct mptcp_out_options *opts);
 
+void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info);
+
 /* move the skb extension owership, with the assumption that 'to' is
  * newly allocated
  */

include/uapi/linux/mptcp.h

@@ -4,6 +4,13 @@
 
 #include <linux/const.h>
 #include <linux/types.h>
+#include <linux/in.h>		/* for sockaddr_in			*/
+#include <linux/in6.h>		/* for sockaddr_in6			*/
+#include <linux/socket.h>	/* for sockaddr_storage and sa_family	*/
+
+#ifndef __KERNEL__
+#include <sys/socket.h>		/* for struct sockaddr			*/
+#endif
 
 #define MPTCP_SUBFLOW_FLAG_MCAP_REM		_BITUL(0)
 #define MPTCP_SUBFLOW_FLAG_MCAP_LOC		_BITUL(1)
@@ -193,4 +200,32 @@ enum mptcp_event_attr {
 #define MPTCP_RST_EBADPERF	5
 #define MPTCP_RST_EMIDDLEBOX	6
 
+struct mptcp_subflow_data {
+	__u32		size_subflow_data;		/* size of this structure in userspace */
+	__u32		num_subflows;			/* must be 0, set by kernel */
+	__u32		size_kernel;			/* must be 0, set by kernel */
+	__u32		size_user;			/* size of one element in data[] */
+} __attribute__((aligned(8)));
+
+struct mptcp_subflow_addrs {
+	union {
+		__kernel_sa_family_t sa_family;
+		struct sockaddr sa_local;
+		struct sockaddr_in sin_local;
+		struct sockaddr_in6 sin6_local;
+		struct __kernel_sockaddr_storage ss_local;
+	};
+	union {
+		struct sockaddr sa_remote;
+		struct sockaddr_in sin_remote;
+		struct sockaddr_in6 sin6_remote;
+		struct __kernel_sockaddr_storage ss_remote;
+	};
+};
+
+/* MPTCP socket options */
+#define MPTCP_INFO		1
+#define MPTCP_TCPINFO		2
+#define MPTCP_SUBFLOW_ADDRS	3
+
 #endif /* _UAPI_MPTCP_H */

net/mptcp/mptcp_diag.c

@@ -113,37 +113,13 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_info *info = _info;
-	u32 flags = 0;
-	bool slow;
-	u8 val;
 
 	r->idiag_rqueue = sk_rmem_alloc_get(sk);
 	r->idiag_wqueue = sk_wmem_alloc_get(sk);
 	if (!info)
 		return;
 
-	slow = lock_sock_fast(sk);
-	info->mptcpi_subflows = READ_ONCE(msk->pm.subflows);
-	info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled);
-	info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted);
-	info->mptcpi_local_addr_used = READ_ONCE(msk->pm.local_addr_used);
-	info->mptcpi_subflows_max = mptcp_pm_get_subflows_max(msk);
-	val = mptcp_pm_get_add_addr_signal_max(msk);
-	info->mptcpi_add_addr_signal_max = val;
-	val = mptcp_pm_get_add_addr_accept_max(msk);
-	info->mptcpi_add_addr_accepted_max = val;
-	info->mptcpi_local_addr_max = mptcp_pm_get_local_addr_max(msk);
-	if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags))
-		flags |= MPTCP_INFO_FLAG_FALLBACK;
-	if (READ_ONCE(msk->can_ack))
-		flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED;
-	info->mptcpi_flags = flags;
-	info->mptcpi_token = READ_ONCE(msk->token);
-	info->mptcpi_write_seq = READ_ONCE(msk->write_seq);
-	info->mptcpi_snd_una = READ_ONCE(msk->snd_una);
-	info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq);
-	info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled);
-	unlock_sock_fast(sk, slow);
+	mptcp_diag_fill_info(msk, info);
 }
 
 static const struct inet_diag_handler mptcp_diag_handler = {

net/mptcp/sockopt.c

@@ -14,6 +14,8 @@
 #include <net/mptcp.h>
 #include "protocol.h"
 
+#define MIN_INFO_OPTLEN_SIZE	16
+
 static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk)
 {
 	sock_owned_by_me((const struct sock *)msk);
@@ -670,6 +672,263 @@ static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int
 	return ret;
 }
 
+void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
+{
+	struct sock *sk = &msk->sk.icsk_inet.sk;
+	u32 flags = 0;
+	bool slow;
+	u8 val;
+
+	memset(info, 0, sizeof(*info));
+
+	slow = lock_sock_fast(sk);
+
+	info->mptcpi_subflows = READ_ONCE(msk->pm.subflows);
+	info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled);
+	info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted);
+	info->mptcpi_local_addr_used = READ_ONCE(msk->pm.local_addr_used);
+	info->mptcpi_subflows_max = mptcp_pm_get_subflows_max(msk);
+	val = mptcp_pm_get_add_addr_signal_max(msk);
+	info->mptcpi_add_addr_signal_max = val;
+	val = mptcp_pm_get_add_addr_accept_max(msk);
+	info->mptcpi_add_addr_accepted_max = val;
+	info->mptcpi_local_addr_max = mptcp_pm_get_local_addr_max(msk);
+	if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags))
+		flags |= MPTCP_INFO_FLAG_FALLBACK;
+	if (READ_ONCE(msk->can_ack))
+		flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED;
+	info->mptcpi_flags = flags;
+	info->mptcpi_token = READ_ONCE(msk->token);
+	info->mptcpi_write_seq = READ_ONCE(msk->write_seq);
+	info->mptcpi_snd_una = READ_ONCE(msk->snd_una);
+	info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq);
+	info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled);
+
+	unlock_sock_fast(sk, slow);
+}
+EXPORT_SYMBOL_GPL(mptcp_diag_fill_info);
+
+static int mptcp_getsockopt_info(struct mptcp_sock *msk, char __user *optval, int __user *optlen)
+{
+	struct mptcp_info m_info;
+	int len;
+
+	if (get_user(len, optlen))
+		return -EFAULT;
+
+	len = min_t(unsigned int, len, sizeof(struct mptcp_info));
+
+	mptcp_diag_fill_info(msk, &m_info);
+
+	if (put_user(len, optlen))
+		return -EFAULT;
+
+	if (copy_to_user(optval, &m_info, len))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int mptcp_put_subflow_data(struct mptcp_subflow_data *sfd,
+				  char __user *optval,
+				  u32 copied,
+				  int __user *optlen)
+{
+	u32 copylen = min_t(u32, sfd->size_subflow_data, sizeof(*sfd));
+
+	if (copied)
+		copied += sfd->size_subflow_data;
+	else
+		copied = copylen;
+
+	if (put_user(copied, optlen))
+		return -EFAULT;
+
+	if (copy_to_user(optval, sfd, copylen))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int mptcp_get_subflow_data(struct mptcp_subflow_data *sfd,
+				  char __user *optval, int __user *optlen)
+{
+	int len, copylen;
+
+	if (get_user(len, optlen))
+		return -EFAULT;
+
+	/* if mptcp_subflow_data size is changed, need to adjust
+	 * this function to deal with programs using old version.
+	 */
+	BUILD_BUG_ON(sizeof(*sfd) != MIN_INFO_OPTLEN_SIZE);
+
+	if (len < MIN_INFO_OPTLEN_SIZE)
+		return -EINVAL;
+
+	memset(sfd, 0, sizeof(*sfd));
+
+	copylen = min_t(unsigned int, len, sizeof(*sfd));
+	if (copy_from_user(sfd, optval, copylen))
+		return -EFAULT;
+
+	/* size_subflow_data is u32, but len is signed */
+	if (sfd->size_subflow_data > INT_MAX ||
+	    sfd->size_user > INT_MAX)
+		return -EINVAL;
+
+	if (sfd->size_subflow_data < MIN_INFO_OPTLEN_SIZE ||
+	    sfd->size_subflow_data > len)
+		return -EINVAL;
+
+	if (sfd->num_subflows || sfd->size_kernel)
+		return -EINVAL;
+
+	return len - sfd->size_subflow_data;
+}
+
+static int mptcp_getsockopt_tcpinfo(struct mptcp_sock *msk, char __user *optval,
+				    int __user *optlen)
+{
+	struct mptcp_subflow_context *subflow;
+	struct sock *sk = &msk->sk.icsk_inet.sk;
+	unsigned int sfcount = 0, copied = 0;
+	struct mptcp_subflow_data sfd;
+	char __user *infoptr;
+	int len;
+
+	len = mptcp_get_subflow_data(&sfd, optval, optlen);
+	if (len < 0)
+		return len;
+
+	sfd.size_kernel = sizeof(struct tcp_info);
+	sfd.size_user = min_t(unsigned int, sfd.size_user,
+			      sizeof(struct tcp_info));
+
+	infoptr = optval + sfd.size_subflow_data;
+
+	lock_sock(sk);
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+		++sfcount;
+
+		if (len && len >= sfd.size_user) {
+			struct tcp_info info;
+
+			tcp_get_info(ssk, &info);
+
+			if (copy_to_user(infoptr, &info, sfd.size_user)) {
+				release_sock(sk);
+				return -EFAULT;
+			}
+
+			infoptr += sfd.size_user;
+			copied += sfd.size_user;
+			len -= sfd.size_user;
+		}
+	}
+
+	release_sock(sk);
+
+	sfd.num_subflows = sfcount;
+
+	if (mptcp_put_subflow_data(&sfd, optval, copied, optlen))
+		return -EFAULT;
+
+	return 0;
+}
+
+static void mptcp_get_sub_addrs(const struct sock *sk, struct mptcp_subflow_addrs *a)
+{
+	struct inet_sock *inet = inet_sk(sk);
+
+	memset(a, 0, sizeof(*a));
+
+	if (sk->sk_family == AF_INET) {
+		a->sin_local.sin_family = AF_INET;
+		a->sin_local.sin_port = inet->inet_sport;
+		a->sin_local.sin_addr.s_addr = inet->inet_rcv_saddr;
+
+		if (!a->sin_local.sin_addr.s_addr)
+			a->sin_local.sin_addr.s_addr = inet->inet_saddr;
+
+		a->sin_remote.sin_family = AF_INET;
+		a->sin_remote.sin_port = inet->inet_dport;
+		a->sin_remote.sin_addr.s_addr = inet->inet_daddr;
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (sk->sk_family == AF_INET6) {
+		const struct ipv6_pinfo *np = inet6_sk(sk);
+
+		a->sin6_local.sin6_family = AF_INET6;
+		a->sin6_local.sin6_port = inet->inet_sport;
+
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+			a->sin6_local.sin6_addr = np->saddr;
+		else
+			a->sin6_local.sin6_addr = sk->sk_v6_rcv_saddr;
+
+		a->sin6_remote.sin6_family = AF_INET6;
+		a->sin6_remote.sin6_port = inet->inet_dport;
+		a->sin6_remote.sin6_addr = sk->sk_v6_daddr;
+#endif
+	}
+}
+
+static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *optval,
+					  int __user *optlen)
+{
+	struct sock *sk = &msk->sk.icsk_inet.sk;
+	struct mptcp_subflow_context *subflow;
+	unsigned int sfcount = 0, copied = 0;
+	struct mptcp_subflow_data sfd;
+	char __user *addrptr;
+	int len;
+
+	len = mptcp_get_subflow_data(&sfd, optval, optlen);
+	if (len < 0)
+		return len;
+
+	sfd.size_kernel = sizeof(struct mptcp_subflow_addrs);
+	sfd.size_user = min_t(unsigned int, sfd.size_user,
+			      sizeof(struct mptcp_subflow_addrs));
+
+	addrptr = optval + sfd.size_subflow_data;
+
+	lock_sock(sk);
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+		++sfcount;
+
+		if (len && len >= sfd.size_user) {
+			struct mptcp_subflow_addrs a;
+
+			mptcp_get_sub_addrs(ssk, &a);
+
+			if (copy_to_user(addrptr, &a, sfd.size_user)) {
+				release_sock(sk);
+				return -EFAULT;
+			}
+
+			addrptr += sfd.size_user;
+			copied += sfd.size_user;
+			len -= sfd.size_user;
+		}
+	}
+
+	release_sock(sk);
+
+	sfd.num_subflows = sfcount;
+
+	if (mptcp_put_subflow_data(&sfd, optval, copied, optlen))
+		return -EFAULT;
+
+	return 0;
+}
+
 static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 				    char __user *optval, int __user *optlen)
 {
@@ -684,6 +943,21 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 	return -EOPNOTSUPP;
 }
 
+static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname,
+				      char __user *optval, int __user *optlen)
+{
+	switch (optname) {
+	case MPTCP_INFO:
+		return mptcp_getsockopt_info(msk, optval, optlen);
+	case MPTCP_TCPINFO:
+		return mptcp_getsockopt_tcpinfo(msk, optval, optlen);
+	case MPTCP_SUBFLOW_ADDRS:
+		return mptcp_getsockopt_subflow_addrs(msk, optval, optlen);
+	}
+
+	return -EOPNOTSUPP;
+}
+
 int mptcp_getsockopt(struct sock *sk, int level, int optname,
 		     char __user *optval, int __user *option)
 {
@@ -706,6 +980,8 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname,
 
 	if (level == SOL_TCP)
 		return mptcp_getsockopt_sol_tcp(msk, optname, optval, option);
+	if (level == SOL_MPTCP)
+		return mptcp_getsockopt_sol_mptcp(msk, optname, optval, option);
 	return -EOPNOTSUPP;
 }
 

tools/testing/selftests/net/mptcp/.gitignore

 # SPDX-License-Identifier: GPL-2.0-only
 mptcp_connect
+mptcp_sockopt
 pm_nl_ctl
 *.pcap

tools/testing/selftests/net/mptcp/Makefile

@@ -8,7 +8,7 @@ CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g  -I$(top_srcdir)/usr/include
 TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \
 	      simult_flows.sh mptcp_sockopt.sh
 
-TEST_GEN_FILES = mptcp_connect pm_nl_ctl
+TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt
 
 TEST_FILES := settings
 

tools/testing/selftests/net/mptcp/mptcp_sockopt.c

+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <assert.h>
+#include <errno.h>
+#include <limits.h>
+#include <string.h>
+#include <stdarg.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <strings.h>
+#include <unistd.h>
+
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+
+#include <netdb.h>
+#include <netinet/in.h>
+
+#include <linux/tcp.h>
+
+static int pf = AF_INET;
+
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+#ifndef SOL_MPTCP
+#define SOL_MPTCP 284
+#endif
+
+#ifndef MPTCP_INFO
+struct mptcp_info {
+	__u8	mptcpi_subflows;
+	__u8	mptcpi_add_addr_signal;
+	__u8	mptcpi_add_addr_accepted;
+	__u8	mptcpi_subflows_max;
+	__u8	mptcpi_add_addr_signal_max;
+	__u8	mptcpi_add_addr_accepted_max;
+	__u32	mptcpi_flags;
+	__u32	mptcpi_token;
+	__u64	mptcpi_write_seq;
+	__u64	mptcpi_snd_una;
+	__u64	mptcpi_rcv_nxt;
+	__u8	mptcpi_local_addr_used;
+	__u8	mptcpi_local_addr_max;
+	__u8	mptcpi_csum_enabled;
+};
+
+struct mptcp_subflow_data {
+	__u32		size_subflow_data;		/* size of this structure in userspace */
+	__u32		num_subflows;			/* must be 0, set by kernel */
+	__u32		size_kernel;			/* must be 0, set by kernel */
+	__u32		size_user;			/* size of one element in data[] */
+} __attribute__((aligned(8)));
+
+struct mptcp_subflow_addrs {
+	union {
+		__kernel_sa_family_t sa_family;
+		struct sockaddr sa_local;
+		struct sockaddr_in sin_local;
+		struct sockaddr_in6 sin6_local;
+		struct __kernel_sockaddr_storage ss_local;
+	};
+	union {
+		struct sockaddr sa_remote;
+		struct sockaddr_in sin_remote;
+		struct sockaddr_in6 sin6_remote;
+		struct __kernel_sockaddr_storage ss_remote;
+	};
+};
+
+#define MPTCP_INFO		1
+#define MPTCP_TCPINFO		2
+#define MPTCP_SUBFLOW_ADDRS	3
+#endif
+
+struct so_state {
+	struct mptcp_info mi;
+	uint64_t mptcpi_rcv_delta;
+	uint64_t tcpi_rcv_delta;
+};
+
+static void die_perror(const char *msg)
+{
+	perror(msg);
+	exit(1);
+}
+
+static void die_usage(int r)
+{
+	fprintf(stderr, "Usage: mptcp_sockopt [-6]\n");
+	exit(r);
+}
+
+static void xerror(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	fputc('\n', stderr);
+	exit(1);
+}
+
+static const char *getxinfo_strerr(int err)
+{
+	if (err == EAI_SYSTEM)
+		return strerror(errno);
+
+	return gai_strerror(err);
+}
+
+static void xgetaddrinfo(const char *node, const char *service,
+			 const struct addrinfo *hints,
+			 struct addrinfo **res)
+{
+	int err = getaddrinfo(node, service, hints, res);
+
+	if (err) {
+		const char *errstr = getxinfo_strerr(err);
+
+		fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
+			node ? node : "", service ? service : "", errstr);
+		exit(1);
+	}
+}
+
+static int sock_listen_mptcp(const char * const listenaddr,
+			     const char * const port)
+{
+	int sock;
+	struct addrinfo hints = {
+		.ai_protocol = IPPROTO_TCP,
+		.ai_socktype = SOCK_STREAM,
+		.ai_flags = AI_PASSIVE | AI_NUMERICHOST
+	};
+
+	hints.ai_family = pf;
+
+	struct addrinfo *a, *addr;
+	int one = 1;
+
+	xgetaddrinfo(listenaddr, port, &hints, &addr);
+	hints.ai_family = pf;
+
+	for (a = addr; a; a = a->ai_next) {
+		sock = socket(a->ai_family, a->ai_socktype, IPPROTO_MPTCP);
+		if (sock < 0)
+			continue;
+
+		if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one,
+				     sizeof(one)))
+			perror("setsockopt");
+
+		if (bind(sock, a->ai_addr, a->ai_addrlen) == 0)
+			break; /* success */
+
+		perror("bind");
+		close(sock);
+		sock = -1;
+	}
+
+	freeaddrinfo(addr);
+
+	if (sock < 0)
+		xerror("could not create listen socket");
+
+	if (listen(sock, 20))
+		die_perror("listen");
+
+	return sock;
+}
+
+static int sock_connect_mptcp(const char * const remoteaddr,
+			      const char * const port, int proto)
+{
+	struct addrinfo hints = {
+		.ai_protocol = IPPROTO_TCP,
+		.ai_socktype = SOCK_STREAM,
+	};
+	struct addrinfo *a, *addr;
+	int sock = -1;
+
+	hints.ai_family = pf;
+
+	xgetaddrinfo(remoteaddr, port, &hints, &addr);
+	for (a = addr; a; a = a->ai_next) {
+		sock = socket(a->ai_family, a->ai_socktype, proto);
+		if (sock < 0)
+			continue;
+
+		if (connect(sock, a->ai_addr, a->ai_addrlen) == 0)
+			break; /* success */
+
+		die_perror("connect");
+	}
+
+	if (sock < 0)
+		xerror("could not create connect socket");
+
+	freeaddrinfo(addr);
+	return sock;
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "h6")) != -1) {
+		switch (c) {
+		case 'h':
+			die_usage(0);
+			break;
+		case '6':
+			pf = AF_INET6;
+			break;
+		default:
+			die_usage(1);
+			break;
+		}
+	}
+}
+
+static void do_getsockopt_bogus_sf_data(int fd, int optname)
+{
+	struct mptcp_subflow_data good_data;
+	struct bogus_data {
+		struct mptcp_subflow_data d;
+		char buf[2];
+	} bd;
+	socklen_t olen, _olen;
+	int ret;
+
+	memset(&bd, 0, sizeof(bd));
+	memset(&good_data, 0, sizeof(good_data));
+
+	olen = sizeof(good_data);
+	good_data.size_subflow_data = olen;
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0); /* 0 size_subflow_data */
+	assert(olen == sizeof(good_data));
+
+	bd.d = good_data;
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret == 0);
+	assert(olen == sizeof(good_data));
+	assert(bd.d.num_subflows == 1);
+	assert(bd.d.size_kernel > 0);
+	assert(bd.d.size_user == 0);
+
+	bd.d = good_data;
+	_olen = rand() % olen;
+	olen = _olen;
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0);	/* bogus olen */
+	assert(olen == _olen);	/* must be unchanged */
+
+	bd.d = good_data;
+	olen = sizeof(good_data);
+	bd.d.size_kernel = 1;
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0); /* size_kernel not 0 */
+
+	bd.d = good_data;
+	olen = sizeof(good_data);
+	bd.d.num_subflows = 1;
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0); /* num_subflows not 0 */
+
+	/* forward compat check: larger struct mptcp_subflow_data on 'old' kernel */
+	bd.d = good_data;
+	olen = sizeof(bd);
+	bd.d.size_subflow_data = sizeof(bd);
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret == 0);
+
+	/* olen must be truncated to real data size filled by kernel: */
+	assert(olen == sizeof(good_data));
+
+	assert(bd.d.size_subflow_data == sizeof(bd));
+
+	bd.d = good_data;
+	bd.d.size_subflow_data += 1;
+	bd.d.size_user = 1;
+	olen = bd.d.size_subflow_data + 1;
+	_olen = olen;
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &_olen);
+	assert(ret == 0);
+
+	/* no truncation, kernel should have filled 1 byte of optname payload in buf[1]: */
+	assert(olen == _olen);
+
+	assert(bd.d.size_subflow_data == sizeof(good_data) + 1);
+	assert(bd.buf[0] == 0);
+}
+
+static void do_getsockopt_mptcp_info(struct so_state *s, int fd, size_t w)
+{
+	struct mptcp_info i;
+	socklen_t olen;
+	int ret;
+
+	olen = sizeof(i);
+	ret = getsockopt(fd, SOL_MPTCP, MPTCP_INFO, &i, &olen);
+
+	if (ret < 0)
+		die_perror("getsockopt MPTCP_INFO");
+
+	assert(olen == sizeof(i));
+
+	if (s->mi.mptcpi_write_seq == 0)
+		s->mi = i;
+
+	assert(s->mi.mptcpi_write_seq + w == i.mptcpi_write_seq);
+
+	s->mptcpi_rcv_delta = i.mptcpi_rcv_nxt - s->mi.mptcpi_rcv_nxt;
+}
+
+static void do_getsockopt_tcp_info(struct so_state *s, int fd, size_t r, size_t w)
+{
+	struct my_tcp_info {
+		struct mptcp_subflow_data d;
+		struct tcp_info ti[2];
+	} ti;
+	int ret, tries = 5;
+	socklen_t olen;
+
+	do {
+		memset(&ti, 0, sizeof(ti));
+
+		ti.d.size_subflow_data = sizeof(struct mptcp_subflow_data);
+		ti.d.size_user = sizeof(struct tcp_info);
+		olen = sizeof(ti);
+
+		ret = getsockopt(fd, SOL_MPTCP, MPTCP_TCPINFO, &ti, &olen);
+		if (ret < 0)
+			xerror("getsockopt MPTCP_TCPINFO (tries %d, %m)");
+
+		assert(olen <= sizeof(ti));
+		assert(ti.d.size_user == ti.d.size_kernel);
+		assert(ti.d.size_user == sizeof(struct tcp_info));
+		assert(ti.d.num_subflows == 1);
+
+		assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data));
+		olen -= sizeof(struct mptcp_subflow_data);
+		assert(olen == sizeof(struct tcp_info));
+
+		if (ti.ti[0].tcpi_bytes_sent == w &&
+		    ti.ti[0].tcpi_bytes_received == r)
+			goto done;
+
+		if (r == 0 && ti.ti[0].tcpi_bytes_sent == w &&
+		    ti.ti[0].tcpi_bytes_received) {
+			s->tcpi_rcv_delta = ti.ti[0].tcpi_bytes_received;
+			goto done;
+		}
+
+		/* wait and repeat, might be that tx is still ongoing */
+		sleep(1);
+	} while (tries-- > 0);
+
+	xerror("tcpi_bytes_sent %" PRIu64 ", want %zu. tcpi_bytes_received %" PRIu64 ", want %zu",
+		ti.ti[0].tcpi_bytes_sent, w, ti.ti[0].tcpi_bytes_received, r);
+
+done:
+	do_getsockopt_bogus_sf_data(fd, MPTCP_TCPINFO);
+}
+
+static void do_getsockopt_subflow_addrs(int fd)
+{
+	struct sockaddr_storage remote, local;
+	socklen_t olen, rlen, llen;
+	int ret;
+	struct my_addrs {
+		struct mptcp_subflow_data d;
+		struct mptcp_subflow_addrs addr[2];
+	} addrs;
+
+	memset(&addrs, 0, sizeof(addrs));
+	memset(&local, 0, sizeof(local));
+	memset(&remote, 0, sizeof(remote));
+
+	addrs.d.size_subflow_data = sizeof(struct mptcp_subflow_data);
+	addrs.d.size_user = sizeof(struct mptcp_subflow_addrs);
+	olen = sizeof(addrs);
+
+	ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, &addrs, &olen);
+	if (ret < 0)
+		die_perror("getsockopt MPTCP_SUBFLOW_ADDRS");
+
+	assert(olen <= sizeof(addrs));
+	assert(addrs.d.size_user == addrs.d.size_kernel);
+	assert(addrs.d.size_user == sizeof(struct mptcp_subflow_addrs));
+	assert(addrs.d.num_subflows == 1);
+
+	assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data));
+	olen -= sizeof(struct mptcp_subflow_data);
+	assert(olen == sizeof(struct mptcp_subflow_addrs));
+
+	llen = sizeof(local);
+	ret = getsockname(fd, (struct sockaddr *)&local, &llen);
+	if (ret < 0)
+		die_perror("getsockname");
+	rlen = sizeof(remote);
+	ret = getpeername(fd, (struct sockaddr *)&remote, &rlen);
+	if (ret < 0)
+		die_perror("getpeername");
+
+	assert(rlen > 0);
+	assert(rlen == llen);
+
+	assert(remote.ss_family == local.ss_family);
+
+	assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) == 0);
+	assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) == 0);
+
+	memset(&addrs, 0, sizeof(addrs));
+
+	addrs.d.size_subflow_data = sizeof(struct mptcp_subflow_data);
+	addrs.d.size_user = sizeof(sa_family_t);
+	olen = sizeof(addrs.d) + sizeof(sa_family_t);
+
+	ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, &addrs, &olen);
+	assert(ret == 0);
+	assert(olen == sizeof(addrs.d) + sizeof(sa_family_t));
+
+	assert(addrs.addr[0].sa_family == pf);
+	assert(addrs.addr[0].sa_family == local.ss_family);
+
+	assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) != 0);
+	assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) != 0);
+
+	do_getsockopt_bogus_sf_data(fd, MPTCP_SUBFLOW_ADDRS);
+}
+
+static void do_getsockopts(struct so_state *s, int fd, size_t r, size_t w)
+{
+	do_getsockopt_mptcp_info(s, fd, w);
+
+	do_getsockopt_tcp_info(s, fd, r, w);
+
+	do_getsockopt_subflow_addrs(fd);
+}
+
+static void connect_one_server(int fd, int pipefd)
+{
+	char buf[4096], buf2[4096];
+	size_t len, i, total;
+	struct so_state s;
+	bool eof = false;
+	ssize_t ret;
+
+	memset(&s, 0, sizeof(s));
+
+	len = rand() % (sizeof(buf) - 1);
+
+	if (len < 128)
+		len = 128;
+
+	for (i = 0; i < len ; i++) {
+		buf[i] = rand() % 26;
+		buf[i] += 'A';
+	}
+
+	buf[i] = '\n';
+
+	do_getsockopts(&s, fd, 0, 0);
+
+	/* un-block server */
+	ret = read(pipefd, buf2, 4);
+	assert(ret == 4);
+	close(pipefd);
+
+	assert(strncmp(buf2, "xmit", 4) == 0);
+
+	ret = write(fd, buf, len);
+	if (ret < 0)
+		die_perror("write");
+
+	if (ret != (ssize_t)len)
+		xerror("short write");
+
+	total = 0;
+	do {
+		ret = read(fd, buf2 + total, sizeof(buf2) - total);
+		if (ret < 0)
+			die_perror("read");
+		if (ret == 0) {
+			eof = true;
+			break;
+		}
+
+		total += ret;
+	} while (total < len);
+
+	if (total != len)
+		xerror("total %lu, len %lu eof %d\n", total, len, eof);
+
+	if (memcmp(buf, buf2, len))
+		xerror("data corruption");
+
+	if (s.tcpi_rcv_delta)
+		assert(s.tcpi_rcv_delta <= total);
+
+	do_getsockopts(&s, fd, ret, ret);
+
+	if (eof)
+		total += 1; /* sequence advances due to FIN */
+
+	assert(s.mptcpi_rcv_delta == (uint64_t)total);
+	close(fd);
+}
+
+static void process_one_client(int fd, int pipefd)
+{
+	ssize_t ret, ret2, ret3;
+	struct so_state s;
+	char buf[4096];
+
+	memset(&s, 0, sizeof(s));
+	do_getsockopts(&s, fd, 0, 0);
+
+	ret = write(pipefd, "xmit", 4);
+	assert(ret == 4);
+
+	ret = read(fd, buf, sizeof(buf));
+	if (ret < 0)
+		die_perror("read");
+
+	assert(s.mptcpi_rcv_delta <= (uint64_t)ret);
+
+	if (s.tcpi_rcv_delta)
+		assert(s.tcpi_rcv_delta == (uint64_t)ret);
+
+	ret2 = write(fd, buf, ret);
+	if (ret2 < 0)
+		die_perror("write");
+
+	/* wait for hangup */
+	ret3 = read(fd, buf, 1);
+	if (ret3 != 0)
+		xerror("expected EOF, got %lu", ret3);
+
+	do_getsockopts(&s, fd, ret, ret2);
+	if (s.mptcpi_rcv_delta != (uint64_t)ret + 1)
+		xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64, s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - ret);
+	close(fd);
+}
+
+static int xaccept(int s)
+{
+	int fd = accept(s, NULL, 0);
+
+	if (fd < 0)
+		die_perror("accept");
+
+	return fd;
+}
+
+static int server(int pipefd)
+{
+	int fd = -1, r;
+
+	switch (pf) {
+	case AF_INET:
+		fd = sock_listen_mptcp("127.0.0.1", "15432");
+		break;
+	case AF_INET6:
+		fd = sock_listen_mptcp("::1", "15432");
+		break;
+	default:
+		xerror("Unknown pf %d\n", pf);
+		break;
+	}
+
+	r = write(pipefd, "conn", 4);
+	assert(r == 4);
+
+	alarm(15);
+	r = xaccept(fd);
+
+	process_one_client(r, pipefd);
+
+	return 0;
+}
+
+static int client(int pipefd)
+{
+	int fd = -1;
+
+	alarm(15);
+
+	switch (pf) {
+	case AF_INET:
+		fd = sock_connect_mptcp("127.0.0.1", "15432", IPPROTO_MPTCP);
+		break;
+	case AF_INET6:
+		fd = sock_connect_mptcp("::1", "15432", IPPROTO_MPTCP);
+		break;
+	default:
+		xerror("Unknown pf %d\n", pf);
+	}
+
+	connect_one_server(fd, pipefd);
+
+	return 0;
+}
+
+static pid_t xfork(void)
+{
+	pid_t p = fork();
+
+	if (p < 0)
+		die_perror("fork");
+
+	return p;
+}
+
+static int rcheck(int wstatus, const char *what)
+{
+	if (WIFEXITED(wstatus)) {
+		if (WEXITSTATUS(wstatus) == 0)
+			return 0;
+		fprintf(stderr, "%s exited, status=%d\n", what, WEXITSTATUS(wstatus));
+		return WEXITSTATUS(wstatus);
+	} else if (WIFSIGNALED(wstatus)) {
+		xerror("%s killed by signal %d\n", what, WTERMSIG(wstatus));
+	} else if (WIFSTOPPED(wstatus)) {
+		xerror("%s stopped by signal %d\n", what, WSTOPSIG(wstatus));
+	}
+
+	return 111;
+}
+
+int main(int argc, char *argv[])
+{
+	int e1, e2, wstatus;
+	pid_t s, c, ret;
+	int pipefds[2];
+
+	parse_opts(argc, argv);
+
+	e1 = pipe(pipefds);
+	if (e1 < 0)
+		die_perror("pipe");
+
+	s = xfork();
+	if (s == 0)
+		return server(pipefds[1]);
+
+	close(pipefds[1]);
+
+	/* wait until server bound a socket */
+	e1 = read(pipefds[0], &e1, 4);
+	assert(e1 == 4);
+
+	c = xfork();
+	if (c == 0)
+		return client(pipefds[0]);
+
+	close(pipefds[0]);
+
+	ret = waitpid(s, &wstatus, 0);
+	if (ret == -1)
+		die_perror("waitpid");
+	e1 = rcheck(wstatus, "server");
+	ret = waitpid(c, &wstatus, 0);
+	if (ret == -1)
+		die_perror("waitpid");
+	e2 = rcheck(wstatus, "client");
+
+	return e1 ? e1 : e2;
+}

tools/testing/selftests/net/mptcp/mptcp_sockopt.sh

@@ -239,12 +239,35 @@ make_file()
 	echo "Created $name (size $size KB) containing data sent by $who"
 }
 
+do_mptcp_sockopt_tests()
+{
+	local lret=0
+
+	./mptcp_sockopt
+	lret=$?
+
+	if [ $lret -ne 0 ]; then
+		echo "FAIL: SOL_MPTCP getsockopt" 1>&2
+		ret=$lret
+		return
+	fi
+
+	./mptcp_sockopt -6
+	lret=$?
+
+	if [ $lret -ne 0 ]; then
+		echo "FAIL: SOL_MPTCP getsockopt (ipv6)" 1>&2
+		ret=$lret
+		return
+	fi
+}
+
 run_tests()
 {
 	listener_ns="$1"
 	connector_ns="$2"
 	connect_addr="$3"
-	lret=0
+	local lret=0
 
 	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr}
 
@@ -268,9 +291,13 @@ trap cleanup EXIT
 run_tests $ns1 $ns2 10.0.1.1
 run_tests $ns1 $ns2 dead:beef:1::1
 
-
 if [ $ret -eq 0 ];then
 	echo "PASS: all packets had packet mark set"
 fi
 
+do_mptcp_sockopt_tests
+if [ $ret -eq 0 ];then
+	echo "PASS: SOL_MPTCP getsockopt has expected information"
+fi
+
 exit $ret