Merge branch 'mptcp-socket-options'

Mat Martineau says:

====================
mptcp: Improve socket option handling

MPTCP sockets have previously had limited socket option support. The
architecture of MPTCP sockets (one userspace-facing MPTCP socket that
manages one or more in-kernel TCP subflow sockets) adds complexity for
passing options through to lower levels. This patch set adds MPTCP
support for socket options commonly used with TCP.

Patch 1 reverts an interim socket option fix (a socket option blocklist)
that was merged in the net tree for v5.12.

Patch 2 moves the socket option code to a separate file, with no
functional changes.

Patch 3 adds an allowlist for socket options that are known to function
with MPTCP. Later patches in this set add more allowed options.

Patches 4 and 5 add infrastructure for syncing MPTCP-level options with
the TCP subflows.

Patches 6-12 add support for specific socket options.

Patch 13 adds a socket option self test.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

net/mptcp/Makefile

@@ -2,7 +2,7 @@
 obj-$(CONFIG_MPTCP) += mptcp.o
 
 mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \
-	   mib.o pm_netlink.o
+	   mib.o pm_netlink.o sockopt.o
 
 obj-$(CONFIG_SYN_COOKIES) += syncookies.o
 obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o

net/mptcp/protocol.c

@@ -90,16 +90,6 @@ static bool mptcp_is_tcpsk(struct sock *sk)
 	return false;
 }
 
-static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk)
-{
-	sock_owned_by_me((const struct sock *)msk);
-
-	if (likely(!__mptcp_check_fallback(msk)))
-		return NULL;
-
-	return msk->first;
-}
-
 static int __mptcp_socket_create(struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow;
@@ -740,18 +730,47 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 		sk->sk_data_ready(sk);
 }
 
-void __mptcp_flush_join_list(struct mptcp_sock *msk)
+static bool mptcp_do_flush_join_list(struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow;
+	bool ret = false;
 
 	if (likely(list_empty(&msk->join_list)))
-		return;
+		return false;
 
 	spin_lock_bh(&msk->join_list_lock);
-	list_for_each_entry(subflow, &msk->join_list, node)
+	list_for_each_entry(subflow, &msk->join_list, node) {
+		u32 sseq = READ_ONCE(subflow->setsockopt_seq);
+
 		mptcp_propagate_sndbuf((struct sock *)msk, mptcp_subflow_tcp_sock(subflow));
+		if (READ_ONCE(msk->setsockopt_seq) != sseq)
+			ret = true;
+	}
 	list_splice_tail_init(&msk->join_list, &msk->conn_list);
 	spin_unlock_bh(&msk->join_list_lock);
+
+	return ret;
+}
+
+void __mptcp_flush_join_list(struct mptcp_sock *msk)
+{
+	if (likely(!mptcp_do_flush_join_list(msk)))
+		return;
+
+	if (!test_and_set_bit(MPTCP_WORK_SYNC_SETSOCKOPT, &msk->flags))
+		mptcp_schedule_work((struct sock *)msk);
+}
+
+static void mptcp_flush_join_list(struct mptcp_sock *msk)
+{
+	bool sync_needed = test_and_clear_bit(MPTCP_WORK_SYNC_SETSOCKOPT, &msk->flags);
+
+	might_sleep();
+
+	if (!mptcp_do_flush_join_list(msk) && !sync_needed)
+		return;
+
+	mptcp_sockopt_sync_all(msk);
 }
 
 static bool mptcp_timer_pending(struct sock *sk)
@@ -1467,7 +1486,7 @@ static void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 			int ret = 0;
 
 			prev_ssk = ssk;
-			__mptcp_flush_join_list(msk);
+			mptcp_flush_join_list(msk);
 			ssk = mptcp_subflow_get_send(msk);
 
 			/* try to keep the subflow socket lock across
@@ -1893,7 +1912,7 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)
 	unsigned int moved = 0;
 	bool ret, done;
 
-	__mptcp_flush_join_list(msk);
+	mptcp_flush_join_list(msk);
 	do {
 		struct sock *ssk = mptcp_subflow_recv_lookup(msk);
 		bool slowpath;
@@ -2317,7 +2336,7 @@ static void mptcp_worker(struct work_struct *work)
 		goto unlock;
 
 	mptcp_check_data_fin_ack(sk);
-	__mptcp_flush_join_list(msk);
+	mptcp_flush_join_list(msk);
 
 	mptcp_check_fastclose(msk);
 
@@ -2380,6 +2399,9 @@ static int __mptcp_init_sock(struct sock *sk)
 	/* re-use the csk retrans timer for MPTCP-level retrans */
 	timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
 	timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);
+
+	tcp_assign_congestion_control(sk);
+
 	return 0;
 }
 
@@ -2517,7 +2539,7 @@ static void __mptcp_check_send_data_fin(struct sock *sk)
 		}
 	}
 
-	__mptcp_flush_join_list(msk);
+	mptcp_flush_join_list(msk);
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
 
@@ -2573,6 +2595,8 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	WARN_ON_ONCE(msk->rmem_released);
 	sk_stream_kill_queues(sk);
 	xfrm_sk_free_policy(sk);
+
+	tcp_cleanup_congestion_control(sk);
 	sk_refcnt_debug_release(sk);
 	mptcp_dispose_initial_subflow(msk);
 	sock_put(sk);
@@ -2654,7 +2678,8 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	__mptcp_flush_join_list(msk);
+	mptcp_do_flush_join_list(msk);
+
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
@@ -2703,6 +2728,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 	msk->snd_nxt = msk->write_seq;
 	msk->snd_una = msk->write_seq;
 	msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
+	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
 
 	if (mp_opt->mp_capable) {
 		msk->can_ack = true;
@@ -2811,161 +2837,6 @@ static void mptcp_destroy(struct sock *sk)
 	sk_sockets_allocated_dec(sk);
 }
 
-static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
-				       sockptr_t optval, unsigned int optlen)
-{
-	struct sock *sk = (struct sock *)msk;
-	struct socket *ssock;
-	int ret;
-
-	switch (optname) {
-	case SO_REUSEPORT:
-	case SO_REUSEADDR:
-		lock_sock(sk);
-		ssock = __mptcp_nmpc_socket(msk);
-		if (!ssock) {
-			release_sock(sk);
-			return -EINVAL;
-		}
-
-		ret = sock_setsockopt(ssock, SOL_SOCKET, optname, optval, optlen);
-		if (ret == 0) {
-			if (optname == SO_REUSEPORT)
-				sk->sk_reuseport = ssock->sk->sk_reuseport;
-			else if (optname == SO_REUSEADDR)
-				sk->sk_reuse = ssock->sk->sk_reuse;
-		}
-		release_sock(sk);
-		return ret;
-	}
-
-	return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen);
-}
-
-static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
-			       sockptr_t optval, unsigned int optlen)
-{
-	struct sock *sk = (struct sock *)msk;
-	int ret = -EOPNOTSUPP;
-	struct socket *ssock;
-
-	switch (optname) {
-	case IPV6_V6ONLY:
-		lock_sock(sk);
-		ssock = __mptcp_nmpc_socket(msk);
-		if (!ssock) {
-			release_sock(sk);
-			return -EINVAL;
-		}
-
-		ret = tcp_setsockopt(ssock->sk, SOL_IPV6, optname, optval, optlen);
-		if (ret == 0)
-			sk->sk_ipv6only = ssock->sk->sk_ipv6only;
-
-		release_sock(sk);
-		break;
-	}
-
-	return ret;
-}
-
-static bool mptcp_unsupported(int level, int optname)
-{
-	if (level == SOL_IP) {
-		switch (optname) {
-		case IP_ADD_MEMBERSHIP:
-		case IP_ADD_SOURCE_MEMBERSHIP:
-		case IP_DROP_MEMBERSHIP:
-		case IP_DROP_SOURCE_MEMBERSHIP:
-		case IP_BLOCK_SOURCE:
-		case IP_UNBLOCK_SOURCE:
-		case MCAST_JOIN_GROUP:
-		case MCAST_LEAVE_GROUP:
-		case MCAST_JOIN_SOURCE_GROUP:
-		case MCAST_LEAVE_SOURCE_GROUP:
-		case MCAST_BLOCK_SOURCE:
-		case MCAST_UNBLOCK_SOURCE:
-		case MCAST_MSFILTER:
-			return true;
-		}
-		return false;
-	}
-	if (level == SOL_IPV6) {
-		switch (optname) {
-		case IPV6_ADDRFORM:
-		case IPV6_ADD_MEMBERSHIP:
-		case IPV6_DROP_MEMBERSHIP:
-		case IPV6_JOIN_ANYCAST:
-		case IPV6_LEAVE_ANYCAST:
-		case MCAST_JOIN_GROUP:
-		case MCAST_LEAVE_GROUP:
-		case MCAST_JOIN_SOURCE_GROUP:
-		case MCAST_LEAVE_SOURCE_GROUP:
-		case MCAST_BLOCK_SOURCE:
-		case MCAST_UNBLOCK_SOURCE:
-		case MCAST_MSFILTER:
-			return true;
-		}
-		return false;
-	}
-	return false;
-}
-
-static int mptcp_setsockopt(struct sock *sk, int level, int optname,
-			    sockptr_t optval, unsigned int optlen)
-{
-	struct mptcp_sock *msk = mptcp_sk(sk);
-	struct sock *ssk;
-
-	pr_debug("msk=%p", msk);
-
-	if (mptcp_unsupported(level, optname))
-		return -ENOPROTOOPT;
-
-	if (level == SOL_SOCKET)
-		return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen);
-
-	/* @@ the meaning of setsockopt() when the socket is connected and
-	 * there are multiple subflows is not yet defined. It is up to the
-	 * MPTCP-level socket to configure the subflows until the subflow
-	 * is in TCP fallback, when TCP socket options are passed through
-	 * to the one remaining subflow.
-	 */
-	lock_sock(sk);
-	ssk = __mptcp_tcp_fallback(msk);
-	release_sock(sk);
-	if (ssk)
-		return tcp_setsockopt(ssk, level, optname, optval, optlen);
-
-	if (level == SOL_IPV6)
-		return mptcp_setsockopt_v6(msk, optname, optval, optlen);
-
-	return -EOPNOTSUPP;
-}
-
-static int mptcp_getsockopt(struct sock *sk, int level, int optname,
-			    char __user *optval, int __user *option)
-{
-	struct mptcp_sock *msk = mptcp_sk(sk);
-	struct sock *ssk;
-
-	pr_debug("msk=%p", msk);
-
-	/* @@ the meaning of setsockopt() when the socket is connected and
-	 * there are multiple subflows is not yet defined. It is up to the
-	 * MPTCP-level socket to configure the subflows until the subflow
-	 * is in TCP fallback, when socket options are passed through
-	 * to the one remaining subflow.
-	 */
-	lock_sock(sk);
-	ssk = __mptcp_tcp_fallback(msk);
-	release_sock(sk);
-	if (ssk)
-		return tcp_getsockopt(ssk, level, optname, optval, option);
-
-	return -EOPNOTSUPP;
-}
-
 void __mptcp_data_acked(struct sock *sk)
 {
 	if (!sock_owned_by_user(sk))
@@ -3375,7 +3246,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 		/* set ssk->sk_socket of accept()ed flows to mptcp socket.
 		 * This is needed so NOSPACE flag can be set from tcp stack.
 		 */
-		__mptcp_flush_join_list(msk);
+		mptcp_flush_join_list(msk);
 		mptcp_for_each_subflow(msk, subflow) {
 			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 

net/mptcp/protocol.h

@@ -108,6 +108,7 @@
 #define MPTCP_CLEAN_UNA		7
 #define MPTCP_ERROR_REPORT	8
 #define MPTCP_RETRANSMIT	9
+#define MPTCP_WORK_SYNC_SETSOCKOPT 10
 
 static inline bool before64(__u64 seq1, __u64 seq2)
 {
@@ -255,6 +256,8 @@ struct mptcp_sock {
 		u64	time;	/* start time of measurement window */
 		u64	rtt_us; /* last maximum rtt of subflows */
 	} rcvq_space;
+
+	u32 setsockopt_seq;
 };
 
 #define mptcp_lock_sock(___sk, cb) do {					\
@@ -413,6 +416,8 @@ struct mptcp_subflow_context {
 	long	delegated_status;
 	struct	list_head delegated_node;   /* link into delegated_action, protected by local BH */
 
+	u32 setsockopt_seq;
+
 	struct	sock *tcp_sock;	    /* tcp sk backpointer */
 	struct	sock *conn;	    /* parent mptcp_sock */
 	const	struct inet_connection_sock_af_ops *icsk_af_ops;
@@ -571,6 +576,11 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk);
 void mptcp_data_ready(struct sock *sk, struct sock *ssk);
 bool mptcp_finish_join(struct sock *sk);
 bool mptcp_schedule_work(struct sock *sk);
+int mptcp_setsockopt(struct sock *sk, int level, int optname,
+		     sockptr_t optval, unsigned int optlen);
+int mptcp_getsockopt(struct sock *sk, int level, int optname,
+		     char __user *optval, int __user *option);
+
 void __mptcp_check_push(struct sock *sk, struct sock *ssk);
 void __mptcp_data_acked(struct sock *sk);
 void __mptcp_error_report(struct sock *sk);
@@ -730,6 +740,12 @@ unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk);
 
+int mptcp_setsockopt(struct sock *sk, int level, int optname,
+		     sockptr_t optval, unsigned int optlen);
+
+void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk);
+void mptcp_sockopt_sync_all(struct mptcp_sock *msk);
+
 static inline struct mptcp_ext *mptcp_get_ext(const struct sk_buff *skb)
 {
 	return (struct mptcp_ext *)skb_ext_find(skb, SKB_EXT_MPTCP);

net/mptcp/sockopt.c

+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2021, Red Hat.
+ */
+
+#define pr_fmt(fmt) "MPTCP: " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <net/sock.h>
+#include <net/protocol.h>
+#include <net/tcp.h>
+#include <net/mptcp.h>
+#include "protocol.h"
+
+static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk)
+{
+	sock_owned_by_me((const struct sock *)msk);
+
+	if (likely(!__mptcp_check_fallback(msk)))
+		return NULL;
+
+	return msk->first;
+}
+
+static u32 sockopt_seq_reset(const struct sock *sk)
+{
+	sock_owned_by_me(sk);
+
+	/* Highbits contain state.  Allows to distinguish sockopt_seq
+	 * of listener and established:
+	 * s0 = new_listener()
+	 * sockopt(s0) - seq is 1
+	 * s1 = accept(s0) - s1 inherits seq 1 if listener sk (s0)
+	 * sockopt(s0) - seq increments to 2 on s0
+	 * sockopt(s1) // seq increments to 2 on s1 (different option)
+	 * new ssk completes join, inherits options from s0 // seq 2
+	 * Needs sync from mptcp join logic, but ssk->seq == msk->seq
+	 *
+	 * Set High order bits to sk_state so ssk->seq == msk->seq test
+	 * will fail.
+	 */
+
+	return (u32)sk->sk_state << 24u;
+}
+
+static void sockopt_seq_inc(struct mptcp_sock *msk)
+{
+	u32 seq = (msk->setsockopt_seq + 1) & 0x00ffffff;
+
+	msk->setsockopt_seq = sockopt_seq_reset((struct sock *)msk) + seq;
+}
+
+static int mptcp_get_int_option(struct mptcp_sock *msk, sockptr_t optval,
+				unsigned int optlen, int *val)
+{
+	if (optlen < sizeof(int))
+		return -EINVAL;
+
+	if (copy_from_sockptr(val, optval, sizeof(*val)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, int val)
+{
+	struct mptcp_subflow_context *subflow;
+	struct sock *sk = (struct sock *)msk;
+
+	lock_sock(sk);
+	sockopt_seq_inc(msk);
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		bool slow = lock_sock_fast(ssk);
+
+		switch (optname) {
+		case SO_DEBUG:
+			sock_valbool_flag(ssk, SOCK_DBG, !!val);
+			break;
+		case SO_KEEPALIVE:
+			if (ssk->sk_prot->keepalive)
+				ssk->sk_prot->keepalive(ssk, !!val);
+			sock_valbool_flag(ssk, SOCK_KEEPOPEN, !!val);
+			break;
+		case SO_PRIORITY:
+			ssk->sk_priority = val;
+			break;
+		case SO_SNDBUF:
+		case SO_SNDBUFFORCE:
+			ssk->sk_userlocks |= SOCK_SNDBUF_LOCK;
+			WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf);
+			break;
+		case SO_RCVBUF:
+		case SO_RCVBUFFORCE:
+			ssk->sk_userlocks |= SOCK_RCVBUF_LOCK;
+			WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf);
+			break;
+		case SO_MARK:
+			if (READ_ONCE(ssk->sk_mark) != sk->sk_mark) {
+				ssk->sk_mark = sk->sk_mark;
+				sk_dst_reset(ssk);
+			}
+			break;
+		case SO_INCOMING_CPU:
+			WRITE_ONCE(ssk->sk_incoming_cpu, val);
+			break;
+		}
+
+		subflow->setsockopt_seq = msk->setsockopt_seq;
+		unlock_sock_fast(ssk, slow);
+	}
+
+	release_sock(sk);
+}
+
+static int mptcp_sol_socket_intval(struct mptcp_sock *msk, int optname, int val)
+{
+	sockptr_t optval = KERNEL_SOCKPTR(&val);
+	struct sock *sk = (struct sock *)msk;
+	int ret;
+
+	ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname,
+			      optval, sizeof(val));
+	if (ret)
+		return ret;
+
+	mptcp_sol_socket_sync_intval(msk, optname, val);
+	return 0;
+}
+
+static void mptcp_so_incoming_cpu(struct mptcp_sock *msk, int val)
+{
+	struct sock *sk = (struct sock *)msk;
+
+	WRITE_ONCE(sk->sk_incoming_cpu, val);
+
+	mptcp_sol_socket_sync_intval(msk, SO_INCOMING_CPU, val);
+}
+
+static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
+					   sockptr_t optval, unsigned int optlen)
+{
+	int val, ret;
+
+	ret = mptcp_get_int_option(msk, optval, optlen, &val);
+	if (ret)
+		return ret;
+
+	switch (optname) {
+	case SO_KEEPALIVE:
+		mptcp_sol_socket_sync_intval(msk, optname, val);
+		return 0;
+	case SO_DEBUG:
+	case SO_MARK:
+	case SO_PRIORITY:
+	case SO_SNDBUF:
+	case SO_SNDBUFFORCE:
+	case SO_RCVBUF:
+	case SO_RCVBUFFORCE:
+		return mptcp_sol_socket_intval(msk, optname, val);
+	case SO_INCOMING_CPU:
+		mptcp_so_incoming_cpu(msk, val);
+		return 0;
+	}
+
+	return -ENOPROTOOPT;
+}
+
+static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_t optval,
+					      unsigned int optlen)
+{
+	struct mptcp_subflow_context *subflow;
+	struct sock *sk = (struct sock *)msk;
+	struct linger ling;
+	sockptr_t kopt;
+	int ret;
+
+	if (optlen < sizeof(ling))
+		return -EINVAL;
+
+	if (copy_from_sockptr(&ling, optval, sizeof(ling)))
+		return -EFAULT;
+
+	kopt = KERNEL_SOCKPTR(&ling);
+	ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, SO_LINGER, kopt, sizeof(ling));
+	if (ret)
+		return ret;
+
+	lock_sock(sk);
+	sockopt_seq_inc(msk);
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		bool slow = lock_sock_fast(ssk);
+
+		if (!ling.l_onoff) {
+			sock_reset_flag(ssk, SOCK_LINGER);
+		} else {
+			ssk->sk_lingertime = sk->sk_lingertime;
+			sock_set_flag(ssk, SOCK_LINGER);
+		}
+
+		subflow->setsockopt_seq = msk->setsockopt_seq;
+		unlock_sock_fast(ssk, slow);
+	}
+
+	release_sock(sk);
+	return 0;
+}
+
+static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
+				       sockptr_t optval, unsigned int optlen)
+{
+	struct sock *sk = (struct sock *)msk;
+	struct socket *ssock;
+	int ret;
+
+	switch (optname) {
+	case SO_REUSEPORT:
+	case SO_REUSEADDR:
+	case SO_BINDTODEVICE:
+	case SO_BINDTOIFINDEX:
+		lock_sock(sk);
+		ssock = __mptcp_nmpc_socket(msk);
+		if (!ssock) {
+			release_sock(sk);
+			return -EINVAL;
+		}
+
+		ret = sock_setsockopt(ssock, SOL_SOCKET, optname, optval, optlen);
+		if (ret == 0) {
+			if (optname == SO_REUSEPORT)
+				sk->sk_reuseport = ssock->sk->sk_reuseport;
+			else if (optname == SO_REUSEADDR)
+				sk->sk_reuse = ssock->sk->sk_reuse;
+			else if (optname == SO_BINDTODEVICE)
+				sk->sk_bound_dev_if = ssock->sk->sk_bound_dev_if;
+			else if (optname == SO_BINDTOIFINDEX)
+				sk->sk_bound_dev_if = ssock->sk->sk_bound_dev_if;
+		}
+		release_sock(sk);
+		return ret;
+	case SO_KEEPALIVE:
+	case SO_PRIORITY:
+	case SO_SNDBUF:
+	case SO_SNDBUFFORCE:
+	case SO_RCVBUF:
+	case SO_RCVBUFFORCE:
+	case SO_MARK:
+	case SO_INCOMING_CPU:
+	case SO_DEBUG:
+		return mptcp_setsockopt_sol_socket_int(msk, optname, optval, optlen);
+	case SO_LINGER:
+		return mptcp_setsockopt_sol_socket_linger(msk, optval, optlen);
+	case SO_NO_CHECK:
+	case SO_DONTROUTE:
+	case SO_BROADCAST:
+	case SO_BSDCOMPAT:
+	case SO_PASSCRED:
+	case SO_PASSSEC:
+	case SO_RXQ_OVFL:
+	case SO_WIFI_STATUS:
+	case SO_NOFCS:
+	case SO_SELECT_ERR_QUEUE:
+		return 0;
+	}
+
+	return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen);
+}
+
+static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
+			       sockptr_t optval, unsigned int optlen)
+{
+	struct sock *sk = (struct sock *)msk;
+	int ret = -EOPNOTSUPP;
+	struct socket *ssock;
+
+	switch (optname) {
+	case IPV6_V6ONLY:
+		lock_sock(sk);
+		ssock = __mptcp_nmpc_socket(msk);
+		if (!ssock) {
+			release_sock(sk);
+			return -EINVAL;
+		}
+
+		ret = tcp_setsockopt(ssock->sk, SOL_IPV6, optname, optval, optlen);
+		if (ret == 0)
+			sk->sk_ipv6only = ssock->sk->sk_ipv6only;
+
+		release_sock(sk);
+		break;
+	}
+
+	return ret;
+}
+
+static bool mptcp_supported_sockopt(int level, int optname)
+{
+	if (level == SOL_SOCKET) {
+		switch (optname) {
+		case SO_DEBUG:
+		case SO_REUSEPORT:
+		case SO_REUSEADDR:
+
+		/* the following ones need a better implementation,
+		 * but are quite common we want to preserve them
+		 */
+		case SO_BINDTODEVICE:
+		case SO_SNDBUF:
+		case SO_SNDBUFFORCE:
+		case SO_RCVBUF:
+		case SO_RCVBUFFORCE:
+		case SO_KEEPALIVE:
+		case SO_PRIORITY:
+		case SO_LINGER:
+		case SO_TIMESTAMP_OLD:
+		case SO_TIMESTAMP_NEW:
+		case SO_TIMESTAMPNS_OLD:
+		case SO_TIMESTAMPNS_NEW:
+		case SO_TIMESTAMPING_OLD:
+		case SO_TIMESTAMPING_NEW:
+		case SO_RCVLOWAT:
+		case SO_RCVTIMEO_OLD:
+		case SO_RCVTIMEO_NEW:
+		case SO_SNDTIMEO_OLD:
+		case SO_SNDTIMEO_NEW:
+		case SO_MARK:
+		case SO_INCOMING_CPU:
+		case SO_BINDTOIFINDEX:
+		case SO_BUSY_POLL:
+		case SO_PREFER_BUSY_POLL:
+		case SO_BUSY_POLL_BUDGET:
+
+		/* next ones are no-op for plain TCP */
+		case SO_NO_CHECK:
+		case SO_DONTROUTE:
+		case SO_BROADCAST:
+		case SO_BSDCOMPAT:
+		case SO_PASSCRED:
+		case SO_PASSSEC:
+		case SO_RXQ_OVFL:
+		case SO_WIFI_STATUS:
+		case SO_NOFCS:
+		case SO_SELECT_ERR_QUEUE:
+			return true;
+		}
+
+		/* SO_OOBINLINE is not supported, let's avoid the related mess */
+		/* SO_ATTACH_FILTER, SO_ATTACH_BPF, SO_ATTACH_REUSEPORT_CBPF,
+		 * SO_DETACH_REUSEPORT_BPF, SO_DETACH_FILTER, SO_LOCK_FILTER,
+		 * we must be careful with subflows
+		 */
+		/* SO_ATTACH_REUSEPORT_EBPF is not supported, at it checks
+		 * explicitly the sk_protocol field
+		 */
+		/* SO_PEEK_OFF is unsupported, as it is for plain TCP */
+		/* SO_MAX_PACING_RATE is unsupported, we must be careful with subflows */
+		/* SO_CNX_ADVICE is currently unsupported, could possibly be relevant,
+		 * but likely needs careful design
+		 */
+		/* SO_ZEROCOPY is currently unsupported, TODO in sndmsg */
+		/* SO_TXTIME is currently unsupported */
+		return false;
+	}
+	if (level == SOL_IP) {
+		switch (optname) {
+		/* should work fine */
+		case IP_FREEBIND:
+		case IP_TRANSPARENT:
+
+		/* the following are control cmsg related */
+		case IP_PKTINFO:
+		case IP_RECVTTL:
+		case IP_RECVTOS:
+		case IP_RECVOPTS:
+		case IP_RETOPTS:
+		case IP_PASSSEC:
+		case IP_RECVORIGDSTADDR:
+		case IP_CHECKSUM:
+		case IP_RECVFRAGSIZE:
+
+		/* common stuff that need some love */
+		case IP_TOS:
+		case IP_TTL:
+		case IP_BIND_ADDRESS_NO_PORT:
+		case IP_MTU_DISCOVER:
+		case IP_RECVERR:
+
+		/* possibly less common may deserve some love */
+		case IP_MINTTL:
+
+		/* the following is apparently a no-op for plain TCP */
+		case IP_RECVERR_RFC4884:
+			return true;
+		}
+
+		/* IP_OPTIONS is not supported, needs subflow care */
+		/* IP_HDRINCL, IP_NODEFRAG are not supported, RAW specific */
+		/* IP_MULTICAST_TTL, IP_MULTICAST_LOOP, IP_UNICAST_IF,
+		 * IP_ADD_MEMBERSHIP, IP_ADD_SOURCE_MEMBERSHIP, IP_DROP_MEMBERSHIP,
+		 * IP_DROP_SOURCE_MEMBERSHIP, IP_BLOCK_SOURCE, IP_UNBLOCK_SOURCE,
+		 * MCAST_JOIN_GROUP, MCAST_LEAVE_GROUP MCAST_JOIN_SOURCE_GROUP,
+		 * MCAST_LEAVE_SOURCE_GROUP, MCAST_BLOCK_SOURCE, MCAST_UNBLOCK_SOURCE,
+		 * MCAST_MSFILTER, IP_MULTICAST_ALL are not supported, better not deal
+		 * with mcast stuff
+		 */
+		/* IP_IPSEC_POLICY, IP_XFRM_POLICY are nut supported, unrelated here */
+		return false;
+	}
+	if (level == SOL_IPV6) {
+		switch (optname) {
+		case IPV6_V6ONLY:
+
+		/* the following are control cmsg related */
+		case IPV6_RECVPKTINFO:
+		case IPV6_2292PKTINFO:
+		case IPV6_RECVHOPLIMIT:
+		case IPV6_2292HOPLIMIT:
+		case IPV6_RECVRTHDR:
+		case IPV6_2292RTHDR:
+		case IPV6_RECVHOPOPTS:
+		case IPV6_2292HOPOPTS:
+		case IPV6_RECVDSTOPTS:
+		case IPV6_2292DSTOPTS:
+		case IPV6_RECVTCLASS:
+		case IPV6_FLOWINFO:
+		case IPV6_RECVPATHMTU:
+		case IPV6_RECVORIGDSTADDR:
+		case IPV6_RECVFRAGSIZE:
+
+		/* the following ones need some love but are quite common */
+		case IPV6_TCLASS:
+		case IPV6_TRANSPARENT:
+		case IPV6_FREEBIND:
+		case IPV6_PKTINFO:
+		case IPV6_2292PKTOPTIONS:
+		case IPV6_UNICAST_HOPS:
+		case IPV6_MTU_DISCOVER:
+		case IPV6_MTU:
+		case IPV6_RECVERR:
+		case IPV6_FLOWINFO_SEND:
+		case IPV6_FLOWLABEL_MGR:
+		case IPV6_MINHOPCOUNT:
+		case IPV6_DONTFRAG:
+		case IPV6_AUTOFLOWLABEL:
+
+		/* the following one is a no-op for plain TCP */
+		case IPV6_RECVERR_RFC4884:
+			return true;
+		}
+
+		/* IPV6_HOPOPTS, IPV6_RTHDRDSTOPTS, IPV6_RTHDR, IPV6_DSTOPTS are
+		 * not supported
+		 */
+		/* IPV6_MULTICAST_HOPS, IPV6_MULTICAST_LOOP, IPV6_UNICAST_IF,
+		 * IPV6_MULTICAST_IF, IPV6_ADDRFORM,
+		 * IPV6_ADD_MEMBERSHIP, IPV6_DROP_MEMBERSHIP, IPV6_JOIN_ANYCAST,
+		 * IPV6_LEAVE_ANYCAST, IPV6_MULTICAST_ALL, MCAST_JOIN_GROUP, MCAST_LEAVE_GROUP,
+		 * MCAST_JOIN_SOURCE_GROUP, MCAST_LEAVE_SOURCE_GROUP,
+		 * MCAST_BLOCK_SOURCE, MCAST_UNBLOCK_SOURCE, MCAST_MSFILTER
+		 * are not supported better not deal with mcast
+		 */
+		/* IPV6_ROUTER_ALERT, IPV6_ROUTER_ALERT_ISOLATE are not supported, since are evil */
+
+		/* IPV6_IPSEC_POLICY, IPV6_XFRM_POLICY are not supported */
+		/* IPV6_ADDR_PREFERENCES is not supported, we must be careful with subflows */
+		return false;
+	}
+	if (level == SOL_TCP) {
+		switch (optname) {
+		/* the following are no-op or should work just fine */
+		case TCP_THIN_DUPACK:
+		case TCP_DEFER_ACCEPT:
+
+		/* the following need some love */
+		case TCP_MAXSEG:
+		case TCP_NODELAY:
+		case TCP_THIN_LINEAR_TIMEOUTS:
+		case TCP_CONGESTION:
+		case TCP_ULP:
+		case TCP_CORK:
+		case TCP_KEEPIDLE:
+		case TCP_KEEPINTVL:
+		case TCP_KEEPCNT:
+		case TCP_SYNCNT:
+		case TCP_SAVE_SYN:
+		case TCP_LINGER2:
+		case TCP_WINDOW_CLAMP:
+		case TCP_QUICKACK:
+		case TCP_USER_TIMEOUT:
+		case TCP_TIMESTAMP:
+		case TCP_NOTSENT_LOWAT:
+		case TCP_TX_DELAY:
+			return true;
+		}
+
+		/* TCP_MD5SIG, TCP_MD5SIG_EXT are not supported, MD5 is not compatible with MPTCP */
+
+		/* TCP_REPAIR, TCP_REPAIR_QUEUE, TCP_QUEUE_SEQ, TCP_REPAIR_OPTIONS,
+		 * TCP_REPAIR_WINDOW are not supported, better avoid this mess
+		 */
+		/* TCP_FASTOPEN_KEY, TCP_FASTOPEN TCP_FASTOPEN_CONNECT, TCP_FASTOPEN_NO_COOKIE,
+		 * are not supported fastopen is currently unsupported
+		 */
+		/* TCP_INQ is currently unsupported, needs some recvmsg work */
+	}
+	return false;
+}
+
+static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t optval,
+					       unsigned int optlen)
+{
+	struct mptcp_subflow_context *subflow;
+	struct sock *sk = (struct sock *)msk;
+	char name[TCP_CA_NAME_MAX];
+	bool cap_net_admin;
+	int ret;
+
+	if (optlen < 1)
+		return -EINVAL;
+
+	ret = strncpy_from_sockptr(name, optval,
+				   min_t(long, TCP_CA_NAME_MAX - 1, optlen));
+	if (ret < 0)
+		return -EFAULT;
+
+	name[ret] = 0;
+
+	cap_net_admin = ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN);
+
+	ret = 0;
+	lock_sock(sk);
+	sockopt_seq_inc(msk);
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		int err;
+
+		lock_sock(ssk);
+		err = tcp_set_congestion_control(ssk, name, true, cap_net_admin);
+		if (err < 0 && ret == 0)
+			ret = err;
+		subflow->setsockopt_seq = msk->setsockopt_seq;
+		release_sock(ssk);
+	}
+
+	if (ret == 0)
+		tcp_set_congestion_control(sk, name, false, cap_net_admin);
+
+	release_sock(sk);
+	return ret;
+}
+
+static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
+				    sockptr_t optval, unsigned int optlen)
+{
+	switch (optname) {
+	case TCP_ULP:
+		return -EOPNOTSUPP;
+	case TCP_CONGESTION:
+		return mptcp_setsockopt_sol_tcp_congestion(msk, optval, optlen);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+int mptcp_setsockopt(struct sock *sk, int level, int optname,
+		     sockptr_t optval, unsigned int optlen)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct sock *ssk;
+
+	pr_debug("msk=%p", msk);
+
+	if (!mptcp_supported_sockopt(level, optname))
+		return -ENOPROTOOPT;
+
+	if (level == SOL_SOCKET)
+		return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen);
+
+	/* @@ the meaning of setsockopt() when the socket is connected and
+	 * there are multiple subflows is not yet defined. It is up to the
+	 * MPTCP-level socket to configure the subflows until the subflow
+	 * is in TCP fallback, when TCP socket options are passed through
+	 * to the one remaining subflow.
+	 */
+	lock_sock(sk);
+	ssk = __mptcp_tcp_fallback(msk);
+	release_sock(sk);
+	if (ssk)
+		return tcp_setsockopt(ssk, level, optname, optval, optlen);
+
+	if (level == SOL_IPV6)
+		return mptcp_setsockopt_v6(msk, optname, optval, optlen);
+
+	if (level == SOL_TCP)
+		return mptcp_setsockopt_sol_tcp(msk, optname, optval, optlen);
+
+	return -EOPNOTSUPP;
+}
+
+static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname,
+					  char __user *optval, int __user *optlen)
+{
+	struct sock *sk = (struct sock *)msk;
+	struct socket *ssock;
+	int ret = -EINVAL;
+	struct sock *ssk;
+
+	lock_sock(sk);
+	ssk = msk->first;
+	if (ssk) {
+		ret = tcp_getsockopt(ssk, level, optname, optval, optlen);
+		goto out;
+	}
+
+	ssock = __mptcp_nmpc_socket(msk);
+	if (!ssock)
+		goto out;
+
+	ret = tcp_getsockopt(ssock->sk, level, optname, optval, optlen);
+
+out:
+	release_sock(sk);
+	return ret;
+}
+
+static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
+				    char __user *optval, int __user *optlen)
+{
+	switch (optname) {
+	case TCP_ULP:
+	case TCP_CONGESTION:
+	case TCP_INFO:
+	case TCP_CC_INFO:
+		return mptcp_getsockopt_first_sf_only(msk, SOL_TCP, optname,
+						      optval, optlen);
+	}
+	return -EOPNOTSUPP;
+}
+
+int mptcp_getsockopt(struct sock *sk, int level, int optname,
+		     char __user *optval, int __user *option)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct sock *ssk;
+
+	pr_debug("msk=%p", msk);
+
+	/* @@ the meaning of setsockopt() when the socket is connected and
+	 * there are multiple subflows is not yet defined. It is up to the
+	 * MPTCP-level socket to configure the subflows until the subflow
+	 * is in TCP fallback, when socket options are passed through
+	 * to the one remaining subflow.
+	 */
+	lock_sock(sk);
+	ssk = __mptcp_tcp_fallback(msk);
+	release_sock(sk);
+	if (ssk)
+		return tcp_getsockopt(ssk, level, optname, optval, option);
+
+	if (level == SOL_TCP)
+		return mptcp_getsockopt_sol_tcp(msk, optname, optval, option);
+	return -EOPNOTSUPP;
+}
+
+static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
+{
+	static const unsigned int tx_rx_locks = SOCK_RCVBUF_LOCK | SOCK_SNDBUF_LOCK;
+	struct sock *sk = (struct sock *)msk;
+
+	if (ssk->sk_prot->keepalive) {
+		if (sock_flag(sk, SOCK_KEEPOPEN))
+			ssk->sk_prot->keepalive(ssk, 1);
+		else
+			ssk->sk_prot->keepalive(ssk, 0);
+	}
+
+	ssk->sk_priority = sk->sk_priority;
+	ssk->sk_bound_dev_if = sk->sk_bound_dev_if;
+	ssk->sk_incoming_cpu = sk->sk_incoming_cpu;
+
+	if (sk->sk_userlocks & tx_rx_locks) {
+		ssk->sk_userlocks |= sk->sk_userlocks & tx_rx_locks;
+		if (sk->sk_userlocks & SOCK_SNDBUF_LOCK)
+			WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf);
+		if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
+			WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf);
+	}
+
+	if (sock_flag(sk, SOCK_LINGER)) {
+		ssk->sk_lingertime = sk->sk_lingertime;
+		sock_set_flag(ssk, SOCK_LINGER);
+	} else {
+		sock_reset_flag(ssk, SOCK_LINGER);
+	}
+
+	if (sk->sk_mark != ssk->sk_mark) {
+		ssk->sk_mark = sk->sk_mark;
+		sk_dst_reset(ssk);
+	}
+
+	sock_valbool_flag(ssk, SOCK_DBG, sock_flag(sk, SOCK_DBG));
+
+	if (inet_csk(sk)->icsk_ca_ops != inet_csk(ssk)->icsk_ca_ops)
+		tcp_set_congestion_control(ssk, inet_csk(sk)->icsk_ca_ops->name, false, true);
+}
+
+static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk)
+{
+	bool slow = lock_sock_fast(ssk);
+
+	sync_socket_options(msk, ssk);
+
+	unlock_sock_fast(ssk, slow);
+}
+
+void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+
+	msk_owned_by_me(msk);
+
+	if (READ_ONCE(subflow->setsockopt_seq) != msk->setsockopt_seq) {
+		__mptcp_sockopt_sync(msk, ssk);
+
+		subflow->setsockopt_seq = msk->setsockopt_seq;
+	}
+}
+
+void mptcp_sockopt_sync_all(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+	struct sock *sk = (struct sock *)msk;
+	u32 seq;
+
+	seq = sockopt_seq_reset(sk);
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		u32 sseq = READ_ONCE(subflow->setsockopt_seq);
+
+		if (sseq != msk->setsockopt_seq) {
+			__mptcp_sockopt_sync(msk, ssk);
+			WRITE_ONCE(subflow->setsockopt_seq, seq);
+		} else if (sseq != seq) {
+			WRITE_ONCE(subflow->setsockopt_seq, seq);
+		}
+
+		cond_resched();
+	}
+
+	msk->setsockopt_seq = seq;
+}

net/mptcp/subflow.c

@@ -679,6 +679,9 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 			goto out;
 		}
 
+		/* ssk inherits options of listener sk */
+		ctx->setsockopt_seq = listener->setsockopt_seq;
+
 		if (ctx->mp_capable) {
 			/* this can't race with mptcp_close(), as the msk is
 			 * not yet exposted to user-space
@@ -694,6 +697,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 			 * created mptcp socket
 			 */
 			new_msk->sk_destruct = mptcp_sock_destruct;
+			mptcp_sk(new_msk)->setsockopt_seq = ctx->setsockopt_seq;
 			mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1);
 			mptcp_token_accept(subflow_req, mptcp_sk(new_msk));
 			ctx->conn = new_msk;
@@ -1317,6 +1321,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	mptcp_info2sockaddr(remote, &addr, ssk->sk_family);
 
 	mptcp_add_pending_subflow(msk, subflow);
+	mptcp_sockopt_sync(msk, ssk);
 	err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK);
 	if (err && err != -EINPROGRESS)
 		goto failed_unlink;

tools/testing/selftests/net/mptcp/Makefile

@@ -6,7 +6,7 @@ KSFT_KHDR_INSTALL := 1
 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
+	      simult_flows.sh mptcp_sockopt.sh
 
 TEST_GEN_FILES = mptcp_connect pm_nl_ctl
 

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

@@ -57,6 +57,7 @@ static bool cfg_join;
 static bool cfg_remove;
 static unsigned int cfg_do_w;
 static int cfg_wait;
+static uint32_t cfg_mark;
 
 static void die_usage(void)
 {
@@ -69,6 +70,7 @@ static void die_usage(void)
 	fprintf(stderr, "\t-p num -- use port num\n");
 	fprintf(stderr, "\t-s [MPTCP|TCP] -- use mptcp(default) or tcp sockets\n");
 	fprintf(stderr, "\t-m [poll|mmap|sendfile] -- use poll(default)/mmap+write/sendfile\n");
+	fprintf(stderr, "\t-M mark -- set socket packet mark\n");
 	fprintf(stderr, "\t-u -- check mptcp ulp\n");
 	fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n");
 	exit(1);
@@ -140,6 +142,17 @@ static void set_sndbuf(int fd, unsigned int size)
 	}
 }
 
+static void set_mark(int fd, uint32_t mark)
+{
+	int err;
+
+	err = setsockopt(fd, SOL_SOCKET, SO_MARK, &mark, sizeof(mark));
+	if (err) {
+		perror("set SO_MARK");
+		exit(1);
+	}
+}
+
 static int sock_listen_mptcp(const char * const listenaddr,
 			     const char * const port)
 {
@@ -248,6 +261,9 @@ static int sock_connect_mptcp(const char * const remoteaddr,
 			continue;
 		}
 
+		if (cfg_mark)
+			set_mark(sock, cfg_mark);
+
 		if (connect(sock, a->ai_addr, a->ai_addrlen) == 0)
 			break; /* success */
 
@@ -830,7 +846,7 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:")) != -1) {
+	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:M:")) != -1) {
 		switch (c) {
 		case 'j':
 			cfg_join = true;
@@ -880,6 +896,9 @@ static void parse_opts(int argc, char **argv)
 		case 'w':
 			cfg_wait = atoi(optarg)*1000000;
 			break;
+		case 'M':
+			cfg_mark = strtol(optarg, NULL, 0);
+			break;
 		}
 	}
 
@@ -911,6 +930,8 @@ int main(int argc, char *argv[])
 			set_rcvbuf(fd, cfg_rcvbuf);
 		if (cfg_sndbuf)
 			set_sndbuf(fd, cfg_sndbuf);
+		if (cfg_mark)
+			set_mark(fd, cfg_mark);
 
 		return main_loop_s(fd);
 	}

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

+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ret=0
+sin=""
+sout=""
+cin=""
+cout=""
+ksft_skip=4
+timeout_poll=30
+timeout_test=$((timeout_poll * 2 + 1))
+mptcp_connect=""
+do_all_tests=1
+
+add_mark_rules()
+{
+	local ns=$1
+	local m=$2
+
+	for t in iptables ip6tables; do
+		# just to debug: check we have multiple subflows connection requests
+		ip netns exec $ns $t -A OUTPUT -p tcp --syn -m mark --mark $m -j ACCEPT
+
+		# RST packets might be handled by a internal dummy socket
+		ip netns exec $ns $t -A OUTPUT -p tcp --tcp-flags RST RST -m mark --mark 0 -j ACCEPT
+
+		ip netns exec $ns $t -A OUTPUT -p tcp -m mark --mark $m -j ACCEPT
+		ip netns exec $ns $t -A OUTPUT -p tcp -m mark --mark 0 -j DROP
+	done
+}
+
+init()
+{
+	rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
+
+	ns1="ns1-$rndh"
+	ns2="ns2-$rndh"
+
+	for netns in "$ns1" "$ns2";do
+		ip netns add $netns || exit $ksft_skip
+		ip -net $netns link set lo up
+		ip netns exec $netns sysctl -q net.mptcp.enabled=1
+		ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0
+		ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0
+	done
+
+	for i in `seq 1 4`; do
+		ip link add ns1eth$i netns "$ns1" type veth peer name ns2eth$i netns "$ns2"
+		ip -net "$ns1" addr add 10.0.$i.1/24 dev ns1eth$i
+		ip -net "$ns1" addr add dead:beef:$i::1/64 dev ns1eth$i nodad
+		ip -net "$ns1" link set ns1eth$i up
+
+		ip -net "$ns2" addr add 10.0.$i.2/24 dev ns2eth$i
+		ip -net "$ns2" addr add dead:beef:$i::2/64 dev ns2eth$i nodad
+		ip -net "$ns2" link set ns2eth$i up
+
+		# let $ns2 reach any $ns1 address from any interface
+		ip -net "$ns2" route add default via 10.0.$i.1 dev ns2eth$i metric 10$i
+
+		ip netns exec $ns1 ./pm_nl_ctl add 10.0.$i.1 flags signal
+		ip netns exec $ns1 ./pm_nl_ctl add dead:beef:$i::1 flags signal
+
+		ip netns exec $ns2 ./pm_nl_ctl add 10.0.$i.2 flags signal
+		ip netns exec $ns2 ./pm_nl_ctl add dead:beef:$i::2 flags signal
+	done
+
+	ip netns exec $ns1 ./pm_nl_ctl limits 8 8
+	ip netns exec $ns2 ./pm_nl_ctl limits 8 8
+
+	add_mark_rules $ns1 1
+	add_mark_rules $ns2 2
+}
+
+cleanup()
+{
+	for netns in "$ns1" "$ns2"; do
+		ip netns del $netns
+	done
+	rm -f "$cin" "$cout"
+	rm -f "$sin" "$sout"
+}
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+iptables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run all tests without iptables tool"
+	exit $ksft_skip
+fi
+
+ip6tables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run all tests without ip6tables tool"
+	exit $ksft_skip
+fi
+
+check_mark()
+{
+	local ns=$1
+	local af=$2
+
+	tables=iptables
+
+	if [ $af -eq 6 ];then
+		tables=ip6tables
+	fi
+
+	counters=$(ip netns exec $ns $tables -v -L OUTPUT | grep DROP)
+	values=${counters%DROP*}
+
+	for v in $values; do
+		if [ $v -ne 0 ]; then
+			echo "FAIL: got $tables $values in ns $ns , not 0 - not all expected packets marked" 1>&2
+			return 1
+		fi
+	done
+
+	return 0
+}
+
+print_file_err()
+{
+	ls -l "$1" 1>&2
+	echo "Trailing bytes are: "
+	tail -c 27 "$1"
+}
+
+check_transfer()
+{
+	in=$1
+	out=$2
+	what=$3
+
+	cmp "$in" "$out" > /dev/null 2>&1
+	if [ $? -ne 0 ] ;then
+		echo "[ FAIL ] $what does not match (in, out):"
+		print_file_err "$in"
+		print_file_err "$out"
+		ret=1
+
+		return 1
+	fi
+
+	return 0
+}
+
+# $1: IP address
+is_v6()
+{
+	[ -z "${1##*:*}" ]
+}
+
+do_transfer()
+{
+	listener_ns="$1"
+	connector_ns="$2"
+	cl_proto="$3"
+	srv_proto="$4"
+	connect_addr="$5"
+
+	port=12001
+
+	:> "$cout"
+	:> "$sout"
+
+	mptcp_connect="./mptcp_connect -r 20"
+
+	local local_addr
+	if is_v6 "${connect_addr}"; then
+		local_addr="::"
+	else
+		local_addr="0.0.0.0"
+	fi
+
+	timeout ${timeout_test} \
+		ip netns exec ${listener_ns} \
+			$mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} \
+				${local_addr} < "$sin" > "$sout" &
+	spid=$!
+
+	sleep 1
+
+	timeout ${timeout_test} \
+		ip netns exec ${connector_ns} \
+			$mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} \
+				$connect_addr < "$cin" > "$cout" &
+
+	cpid=$!
+
+	wait $cpid
+	retc=$?
+	wait $spid
+	rets=$?
+
+	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+		echo " client exit code $retc, server $rets" 1>&2
+		echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2
+		ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port"
+
+		echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2
+		ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port"
+
+		ret=1
+		return 1
+	fi
+
+	if [ $local_addr = "::" ];then
+		check_mark $listener_ns 6
+		check_mark $connector_ns 6
+	else
+		check_mark $listener_ns 4
+		check_mark $connector_ns 4
+	fi
+
+	check_transfer $cin $sout "file received by server"
+
+	rets=$?
+
+	if [ $retc -eq 0 ] && [ $rets -eq 0 ];then
+		return 0
+	fi
+
+	return 1
+}
+
+make_file()
+{
+	name=$1
+	who=$2
+	size=$3
+
+	dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null
+	echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
+
+	echo "Created $name (size $size KB) containing data sent by $who"
+}
+
+run_tests()
+{
+	listener_ns="$1"
+	connector_ns="$2"
+	connect_addr="$3"
+	lret=0
+
+	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr}
+
+	lret=$?
+
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		return
+	fi
+}
+
+sin=$(mktemp)
+sout=$(mktemp)
+cin=$(mktemp)
+cout=$(mktemp)
+init
+make_file "$cin" "client" 1
+make_file "$sin" "server" 1
+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
+
+exit $ret