[PATCH mptcp-next 0/2] mptcp: add freebind & transparent sockopt

[PATCH mptcp-next 0/2] mptcp: add freebind & transparent sockopt

[Florian Westphal]

This depends on IP_TOS patches that got posted recently.

First patch adds ipv4/ipv6 TRANSPARENT and FREEBIND, second
patch adds a selftest to mptcp_connect.sh.

Florian Westphal (2):
  mptcp: sockopt: add SOL_IP freebind & transparent options
  selftests: mptcp: add tproxy test case

 net/mptcp/sockopt.c                           | 66 ++++++++++++++-
 net/mptcp/subflow.c                           |  3 +-
 .../selftests/net/mptcp/mptcp_connect.c       | 51 +++++++++++-
 .../selftests/net/mptcp/mptcp_connect.sh      | 80 +++++++++++++++++++
 4 files changed, 197 insertions(+), 3 deletions(-)

-- 
2.32.0

[PATCH mptcp-next 1/2] mptcp: sockopt: add SOL_IP freebind & transparent options

[Florian Westphal]

These options also need to be set before bind, so do the sync of msk to
new ssk socket a bit earlier.

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/mptcp/sockopt.c | 66 ++++++++++++++++++++++++++++++++++++++++++++-
 net/mptcp/subflow.c |  3 ++-
 2 files changed, 67 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 74d304b7784e..9e1c68438771 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -390,6 +390,8 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 
 	switch (optname) {
 	case IPV6_V6ONLY:
+	case IPV6_TRANSPARENT:
+	case IPV6_FREEBIND:
 		lock_sock(sk);
 		ssock = __mptcp_nmpc_socket(msk);
 		if (!ssock) {
@@ -398,8 +400,24 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 		}
 
 		ret = tcp_setsockopt(ssock->sk, SOL_IPV6, optname, optval, optlen);
-		if (ret == 0)
+		if (ret != 0) {
+			release_sock(sk);
+			return ret;
+		}
+
+		sockopt_seq_inc(msk);
+
+		switch (optname) {
+		case IPV6_V6ONLY:
 			sk->sk_ipv6only = ssock->sk->sk_ipv6only;
+			break;
+		case IPV6_TRANSPARENT:
+			inet_sk(sk)->transparent = inet_sk(ssock->sk)->transparent;
+			break;
+		case IPV6_FREEBIND:
+			inet_sk(sk)->freebind = inet_sk(ssock->sk)->freebind;
+			break;
+		}
 
 		release_sock(sk);
 		break;
@@ -598,6 +616,46 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t
 	return ret;
 }
 
+static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int optname,
+						   sockptr_t optval, unsigned int optlen)
+{
+	struct sock *sk = (struct sock *)msk;
+	struct inet_sock *issk;
+	struct socket *ssock;
+	int ret, err;
+
+	err = ip_setsockopt(sk, SOL_IP, optname, optval, optlen);
+	if (err != 0)
+		return err;
+
+	lock_sock(sk);
+
+	ssock = __mptcp_nmpc_socket(msk);
+	if (!ssock) {
+		release_sock(sk);
+		return -EINVAL;
+	}
+
+	issk = inet_sk(ssock->sk);
+
+	switch (optname) {
+	case IP_FREEBIND:
+		issk->freebind = inet_sk(sk)->freebind;
+		break;
+	case IP_TRANSPARENT:
+		issk->transparent = inet_sk(sk)->transparent;
+		break;
+	default:
+		release_sock(sk);
+		WARN_ON_ONCE(1);
+		return -EOPNOTSUPP;
+	}
+
+	sockopt_seq_inc(msk);
+	release_sock(sk);
+	return ret;
+}
+
 static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname,
 				       sockptr_t optval, unsigned int optlen)
 {
@@ -628,6 +686,9 @@ static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname,
 			       sockptr_t optval, unsigned int optlen)
 {
 	switch (optname) {
+	case IP_FREEBIND:
+	case IP_TRANSPARENT:
+		return mptcp_setsockopt_sol_ip_set_transparent(msk, optname, optval, optlen);
 	case IP_TOS:
 		return mptcp_setsockopt_v4_set_tos(msk, optname, optval, optlen);
 	}
@@ -1069,6 +1130,9 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 
 	if (inet_csk(sk)->icsk_ca_ops != inet_csk(ssk)->icsk_ca_ops)
 		tcp_set_congestion_control(ssk, msk->ca_name, false, true);
+
+	inet_sk(ssk)->transparent = inet_sk(sk)->transparent;
+	inet_sk(ssk)->freebind = inet_sk(sk)->freebind;
 }
 
 static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk)
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 6172f380dfb7..72ccbd85941b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1425,6 +1425,8 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	if (addr.ss_family == AF_INET6)
 		addrlen = sizeof(struct sockaddr_in6);
 #endif
+	mptcp_sockopt_sync(msk, ssk);
+
 	ssk->sk_bound_dev_if = ifindex;
 	err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen);
 	if (err)
@@ -1441,7 +1443,6 @@ 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;
-- 
2.32.0

[PATCH mptcp-next 2/2] selftests: mptcp: add tproxy test case

[Florian Westphal]

No hard dependencies here, just skip if test environ lacks
nft binary or the needed kernel config options.

The test case spawns listener in ns2 but ns1 will connect
to the ip address of ns4.

policy routing + tproxy rule will redirect packets to ns2 instead
of forward.

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 .../selftests/net/mptcp/mptcp_connect.c       | 51 +++++++++++-
 .../selftests/net/mptcp/mptcp_connect.sh      | 80 +++++++++++++++++++
 2 files changed, 130 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 95e81d557b08..ada9b80774d4 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -75,7 +75,12 @@ struct cfg_cmsg_types {
 	unsigned int timestampns:1;
 };
 
+struct cfg_sockopt_types {
+	unsigned int transparent:1;
+};
+
 static struct cfg_cmsg_types cfg_cmsg_types;
+static struct cfg_sockopt_types cfg_sockopt_types;
 
 static void die_usage(void)
 {
@@ -93,6 +98,7 @@ static void die_usage(void)
 	fprintf(stderr, "\t-u -- check mptcp ulp\n");
 	fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n");
 	fprintf(stderr, "\t-c cmsg -- test cmsg type <cmsg>\n");
+	fprintf(stderr, "\t-o option -- test sockopt <option>\n");
 	fprintf(stderr,
 		"\t-P [saveWithPeek|saveAfterPeek] -- save data with/after MSG_PEEK form tcp socket\n");
 	exit(1);
@@ -185,6 +191,22 @@ static void set_mark(int fd, uint32_t mark)
 	}
 }
 
+static void set_transparent(int fd, int pf)
+{
+	int one = 1;
+
+	switch (pf) {
+	case AF_INET:
+		if (-1 == setsockopt(fd, SOL_IP, IP_TRANSPARENT, &one, sizeof(one)))
+			perror("IP_TRANSPARENT");
+		break;
+	case AF_INET6:
+		if (-1 == setsockopt(fd, IPPROTO_IPV6, IPV6_TRANSPARENT, &one, sizeof(one)))
+			perror("IPV6_TRANSPARENT");
+		break;
+	}
+}
+
 static int sock_listen_mptcp(const char * const listenaddr,
 			     const char * const port)
 {
@@ -212,6 +234,9 @@ static int sock_listen_mptcp(const char * const listenaddr,
 				     sizeof(one)))
 			perror("setsockopt");
 
+		if (cfg_sockopt_types.transparent)
+			set_transparent(sock, pf);
+
 		if (bind(sock, a->ai_addr, a->ai_addrlen) == 0)
 			break; /* success */
 
@@ -944,6 +969,27 @@ static void parse_cmsg_types(const char *type)
 	exit(1);
 }
 
+static void parse_setsock_options(const char *name)
+{
+	char *next = strchr(name, ',');
+	unsigned int len = 0;
+
+	if (next) {
+		parse_setsock_options(next + 1);
+		len = next - name;
+	} else {
+		len = strlen(name);
+	}
+
+	if (strncmp(name, "TRANSPARENT", len) == 0) {
+		cfg_sockopt_types.transparent = 1;
+		return;
+	}
+
+	fprintf(stderr, "Unrecognized setsockopt option %s\n", name);
+	exit(1);
+}
+
 int main_loop(void)
 {
 	int fd;
@@ -1047,7 +1093,7 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "6jr:lp:s:hut:T:m:S:R:w:M:P:c:")) != -1) {
+	while ((c = getopt(argc, argv, "6jr:lp:s:hut:T:m:S:R:w:M:P:c:o:")) != -1) {
 		switch (c) {
 		case 'j':
 			cfg_join = true;
@@ -1108,6 +1154,9 @@ static void parse_opts(int argc, char **argv)
 		case 'c':
 			parse_cmsg_types(optarg);
 			break;
+		case 'o':
+			parse_setsock_options(optarg);
+			break;
 		}
 	}
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 559173a8e387..205e9f0c4296 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -671,6 +671,82 @@ run_tests()
 	run_tests_lo $1 $2 $3 0
 }
 
+run_test_transparent()
+{
+	local connect_addr="$1"
+	local msg="$2"
+
+	local connector_ns="$ns1"
+	local listener_ns="$ns2"
+	local lret=0
+	local r6flag=""
+
+	# skip if we don't want v6
+	if ! $ipv6 && is_v6 "${connect_addr}"; then
+		return 0
+	fi
+
+ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF"
+flush ruleset
+table inet mangle {
+	chain divert {
+		type filter hook prerouting priority -150;
+
+		meta l4proto tcp socket transparent 1 meta mark set 1 accept
+		tcp dport 20000 tproxy to :20000 meta mark set 1 accept
+	}
+}
+EOF
+	if [ $? -ne 0 ]; then
+		echo "SKIP: $msg"
+		return
+	fi
+
+	local local_addr
+	if is_v6 "${connect_addr}"; then
+		local_addr="::"
+		r6flag="-6"
+	else
+		local_addr="0.0.0.0"
+	fi
+
+	ip -net "$listener_ns" $r6flag rule add fwmark 1 lookup 100
+	if [ $? -ne 0 ]; then
+		ip netns exec "$listener_ns" nft flush ruleset
+		echo "SKIP: $msg"
+		return
+	fi
+
+	ip -net "$listener_ns" route add local $local_addr/0 dev lo table 100
+	if [ $? -ne 0 ]; then
+		ip netns exec "$listener_ns" nft flush ruleset
+		ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100
+		echo "SKIP: $msg"
+		return
+	fi
+
+	echo "INFO: test $msg"
+
+	TEST_COUNT=10000
+	local extra_args="-o TRANSPARENT"
+	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP \
+		    ${connect_addr} ${local_addr} "${extra_args}"
+	lret=$?
+
+	ip netns exec "$listener_ns" nft flush ruleset
+	ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100
+	ip -net "$listener_ns" route del local $local_addr/0 dev lo table 100
+
+	if [ $lret -ne 0 ]; then
+		echo "FAIL: $msg" 1>&2
+		ret=$lret
+		return 1
+	fi
+
+	echo "PASS: $msg"
+	return 0
+}
+
 run_tests_peekmode()
 {
 	local peekmode="$1"
@@ -794,5 +870,9 @@ run_tests_peekmode "saveWithPeek"
 run_tests_peekmode "saveAfterPeek"
 stop_if_error "Tests with peek mode have failed"
 
+# connect to ns4 ip address, ns2 should intercept/proxy
+run_test_transparent 10.0.3.1 "tproxy ipv4"
+run_test_transparent dead:beef:3::1 "tproxy ipv6"
+
 display_time
 exit $ret
-- 
2.32.0

Re: [PATCH mptcp-next 2/2] selftests: mptcp: add tproxy test case

[Mat Martineau]

On Wed, 27 Oct 2021, Florian Westphal wrote:

> No hard dependencies here, just skip if test environ lacks
> nft binary or the needed kernel config options.
>
> The test case spawns listener in ns2 but ns1 will connect
> to the ip address of ns4.
>
> policy routing + tproxy rule will redirect packets to ns2 instead
> of forward.
>
> Signed-off-by: Florian Westphal <fw@strlen.de>
> ---
> .../selftests/net/mptcp/mptcp_connect.c       | 51 +++++++++++-
> .../selftests/net/mptcp/mptcp_connect.sh      | 80 +++++++++++++++++++

Hi Florian -

Could you also update tools/testing/selftests/net/mptcp/config with the 
required kconfig values? My test kernel is definitely missing 
CONFIG_NFT_TPROXY, are others required too?

Thanks,

Mat


> 2 files changed, 130 insertions(+), 1 deletion(-)
>
> diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
> index 95e81d557b08..ada9b80774d4 100644
> --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
> +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
> @@ -75,7 +75,12 @@ struct cfg_cmsg_types {
> 	unsigned int timestampns:1;
> };
>
> +struct cfg_sockopt_types {
> +	unsigned int transparent:1;
> +};
> +
> static struct cfg_cmsg_types cfg_cmsg_types;
> +static struct cfg_sockopt_types cfg_sockopt_types;
>
> static void die_usage(void)
> {
> @@ -93,6 +98,7 @@ static void die_usage(void)
> 	fprintf(stderr, "\t-u -- check mptcp ulp\n");
> 	fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n");
> 	fprintf(stderr, "\t-c cmsg -- test cmsg type <cmsg>\n");
> +	fprintf(stderr, "\t-o option -- test sockopt <option>\n");
> 	fprintf(stderr,
> 		"\t-P [saveWithPeek|saveAfterPeek] -- save data with/after MSG_PEEK form tcp socket\n");
> 	exit(1);
> @@ -185,6 +191,22 @@ static void set_mark(int fd, uint32_t mark)
> 	}
> }
>
> +static void set_transparent(int fd, int pf)
> +{
> +	int one = 1;
> +
> +	switch (pf) {
> +	case AF_INET:
> +		if (-1 == setsockopt(fd, SOL_IP, IP_TRANSPARENT, &one, sizeof(one)))
> +			perror("IP_TRANSPARENT");
> +		break;
> +	case AF_INET6:
> +		if (-1 == setsockopt(fd, IPPROTO_IPV6, IPV6_TRANSPARENT, &one, sizeof(one)))
> +			perror("IPV6_TRANSPARENT");
> +		break;
> +	}
> +}
> +
> static int sock_listen_mptcp(const char * const listenaddr,
> 			     const char * const port)
> {
> @@ -212,6 +234,9 @@ static int sock_listen_mptcp(const char * const listenaddr,
> 				     sizeof(one)))
> 			perror("setsockopt");
>
> +		if (cfg_sockopt_types.transparent)
> +			set_transparent(sock, pf);
> +
> 		if (bind(sock, a->ai_addr, a->ai_addrlen) == 0)
> 			break; /* success */
>
> @@ -944,6 +969,27 @@ static void parse_cmsg_types(const char *type)
> 	exit(1);
> }
>
> +static void parse_setsock_options(const char *name)
> +{
> +	char *next = strchr(name, ',');
> +	unsigned int len = 0;
> +
> +	if (next) {
> +		parse_setsock_options(next + 1);
> +		len = next - name;
> +	} else {
> +		len = strlen(name);
> +	}
> +
> +	if (strncmp(name, "TRANSPARENT", len) == 0) {
> +		cfg_sockopt_types.transparent = 1;
> +		return;
> +	}
> +
> +	fprintf(stderr, "Unrecognized setsockopt option %s\n", name);
> +	exit(1);
> +}
> +
> int main_loop(void)
> {
> 	int fd;
> @@ -1047,7 +1093,7 @@ static void parse_opts(int argc, char **argv)
> {
> 	int c;
>
> -	while ((c = getopt(argc, argv, "6jr:lp:s:hut:T:m:S:R:w:M:P:c:")) != -1) {
> +	while ((c = getopt(argc, argv, "6jr:lp:s:hut:T:m:S:R:w:M:P:c:o:")) != -1) {
> 		switch (c) {
> 		case 'j':
> 			cfg_join = true;
> @@ -1108,6 +1154,9 @@ static void parse_opts(int argc, char **argv)
> 		case 'c':
> 			parse_cmsg_types(optarg);
> 			break;
> +		case 'o':
> +			parse_setsock_options(optarg);
> +			break;
> 		}
> 	}
>
> diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
> index 559173a8e387..205e9f0c4296 100755
> --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
> +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
> @@ -671,6 +671,82 @@ run_tests()
> 	run_tests_lo $1 $2 $3 0
> }
>
> +run_test_transparent()
> +{
> +	local connect_addr="$1"
> +	local msg="$2"
> +
> +	local connector_ns="$ns1"
> +	local listener_ns="$ns2"
> +	local lret=0
> +	local r6flag=""
> +
> +	# skip if we don't want v6
> +	if ! $ipv6 && is_v6 "${connect_addr}"; then
> +		return 0
> +	fi
> +
> +ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF"
> +flush ruleset
> +table inet mangle {
> +	chain divert {
> +		type filter hook prerouting priority -150;
> +
> +		meta l4proto tcp socket transparent 1 meta mark set 1 accept
> +		tcp dport 20000 tproxy to :20000 meta mark set 1 accept
> +	}
> +}
> +EOF
> +	if [ $? -ne 0 ]; then
> +		echo "SKIP: $msg"
> +		return
> +	fi
> +
> +	local local_addr
> +	if is_v6 "${connect_addr}"; then
> +		local_addr="::"
> +		r6flag="-6"
> +	else
> +		local_addr="0.0.0.0"
> +	fi
> +
> +	ip -net "$listener_ns" $r6flag rule add fwmark 1 lookup 100
> +	if [ $? -ne 0 ]; then
> +		ip netns exec "$listener_ns" nft flush ruleset
> +		echo "SKIP: $msg"
> +		return
> +	fi
> +
> +	ip -net "$listener_ns" route add local $local_addr/0 dev lo table 100
> +	if [ $? -ne 0 ]; then
> +		ip netns exec "$listener_ns" nft flush ruleset
> +		ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100
> +		echo "SKIP: $msg"
> +		return
> +	fi
> +
> +	echo "INFO: test $msg"
> +
> +	TEST_COUNT=10000
> +	local extra_args="-o TRANSPARENT"
> +	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP \
> +		    ${connect_addr} ${local_addr} "${extra_args}"
> +	lret=$?
> +
> +	ip netns exec "$listener_ns" nft flush ruleset
> +	ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100
> +	ip -net "$listener_ns" route del local $local_addr/0 dev lo table 100
> +
> +	if [ $lret -ne 0 ]; then
> +		echo "FAIL: $msg" 1>&2
> +		ret=$lret
> +		return 1
> +	fi
> +
> +	echo "PASS: $msg"
> +	return 0
> +}
> +
> run_tests_peekmode()
> {
> 	local peekmode="$1"
> @@ -794,5 +870,9 @@ run_tests_peekmode "saveWithPeek"
> run_tests_peekmode "saveAfterPeek"
> stop_if_error "Tests with peek mode have failed"
>
> +# connect to ns4 ip address, ns2 should intercept/proxy
> +run_test_transparent 10.0.3.1 "tproxy ipv4"
> +run_test_transparent dead:beef:3::1 "tproxy ipv6"
> +
> display_time
> exit $ret
> -- 
> 2.32.0
>
>
>

--
Mat Martineau
Intel

Re: [PATCH mptcp-next 2/2] selftests: mptcp: add tproxy test case

[Florian Westphal]

Mat Martineau <mathew.j.martineau@linux.intel.com> wrote:
> Could you also update tools/testing/selftests/net/mptcp/config with the
> required kconfig values? My test kernel is definitely missing
> CONFIG_NFT_TPROXY, are others required too?

Probably

CONFIG_NFT_TPROXY=m
CONFIG_NFT_SOCKET=m
CONFIG_NF_TABLES_INET=y
CONFIG_IP_ADVANCED_ROUTER=y
CONFIG_IP_MULTIPLE_TABLES=y

Will send a v2.