[PATCH mptcp-next v12 0/5] bpf: Force to MPTCP

[PATCH mptcp-next v12 0/5] bpf: Force to MPTCP

[Geliang Tang]

As is described in the "How to use MPTCP?" section in MPTCP wiki [1]:

"Your app should create sockets with IPPROTO_MPTCP as the proto:
( socket(AF_INET, SOCK_STREAM, IPPROTO_MPTCP); ). Legacy apps can be
forced to create and use MPTCP sockets instead of TCP ones via the
mptcpize command bundled with the mptcpd daemon."

But the mptcpize (LD_PRELOAD technique) command has some limitations
[2]:

 - it doesn't work if the application is not using libc (e.g. GoLang
apps)
 - in some envs, it might not be easy to set env vars / change the way
apps are launched, e.g. on Android
 - mptcpize needs to be launched with all apps that want MPTCP: we could
have more control from BPF to enable MPTCP only for some apps or all the
ones of a netns or a cgroup, etc.
 - it is not in BPF, we cannot talk about it at netdev conf.

So this patchset attempts to use BPF to implement functions similer to
mptcpize.

The main idea is to add a hook in sys_socket() to change the protocol id
from IPPROTO_TCP (or 0) to IPPROTO_MPTCP.

[1]
https://github.com/multipath-tcp/mptcp_net-next/wiki
[2]
https://github.com/multipath-tcp/mptcp_net-next/issues/79

v12:
 - update diag_* log of update_socket_protocol.
 - add 'ip netns show' after 'ip netns del' to check if there is
a test did not clean up its netns.
 - return libbpf_get_error() instead of -EIO for the error from
open_and_load().
 - Use getsockopt(SOL_PROTOCOL) to verify mptcp protocol intead of
using 'ss -tOni'.

v11:
 - add comments about outputs of 'ss' and 'nstat'.
 - use "err = verify_mptcpify()" instead of using =+.

v10:
 - drop "#ifdef CONFIG_BPF_JIT".
 - include vmlinux.h and bpf_tracing_net.h to avoid defining some
macros.
 - drop unneeded checks for mptcp.

v9:
 - update comment for 'update_socket_protocol'.

v8:
 - drop the additional checks on the 'protocol' value after the
'update_socket_protocol()' call.

v7:
 - add __weak and __diag_* for update_socket_protocol.

v6:
 - add update_socket_protocol.

v5:
 - add bpf_mptcpify helper.

v4:
 - use lsm_cgroup/socket_create

v3:
 - patch 8: char cmd[128]; -> char cmd[256];

v2:
 - Fix build selftests errors reported by CI

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/79

Geliang Tang (5):
  bpf: Add update_socket_protocol hook
  selftests/bpf: Use random netns name for mptcp
  selftests/bpf: Add two mptcp netns helpers
  selftests/bpf: Fix error checks of mptcp open_and_load
  selftests/bpf: Add mptcpify test

 net/mptcp/bpf.c                               |  15 ++
 net/socket.c                                  |  26 +++-
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 146 +++++++++++++++---
 tools/testing/selftests/bpf/progs/mptcpify.c  |  20 +++
 4 files changed, 186 insertions(+), 21 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/progs/mptcpify.c

-- 
2.35.3

[PATCH mptcp-next v12 1/5] bpf: Add update_socket_protocol hook

[Geliang Tang]

Add a hook named update_socket_protocol in __sys_socket(), for bpf
progs to attach to and update socket protocol. One user case is to
force legacy TCP apps to create and use MPTCP sockets instead of
TCP ones.

Define a mod_ret set named bpf_mptcp_fmodret_ids, add the hook
update_socket_protocol into this set, and register it in
bpf_mptcp_kfunc_init().

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/79
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/bpf.c | 15 +++++++++++++++
 net/socket.c    | 26 +++++++++++++++++++++++++-
 2 files changed, 40 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
index 5a0a84ad94af..8a16672b94e2 100644
--- a/net/mptcp/bpf.c
+++ b/net/mptcp/bpf.c
@@ -19,3 +19,18 @@ struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk)
 
 	return NULL;
 }
+
+BTF_SET8_START(bpf_mptcp_fmodret_ids)
+BTF_ID_FLAGS(func, update_socket_protocol)
+BTF_SET8_END(bpf_mptcp_fmodret_ids)
+
+static const struct btf_kfunc_id_set bpf_mptcp_fmodret_set = {
+	.owner = THIS_MODULE,
+	.set   = &bpf_mptcp_fmodret_ids,
+};
+
+static int __init bpf_mptcp_kfunc_init(void)
+{
+	return register_btf_fmodret_id_set(&bpf_mptcp_fmodret_set);
+}
+late_initcall(bpf_mptcp_kfunc_init);
diff --git a/net/socket.c b/net/socket.c
index 2b0e54b2405c..e9b2e754a103 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1644,12 +1644,36 @@ struct file *__sys_socket_file(int family, int type, int protocol)
 	return sock_alloc_file(sock, flags, NULL);
 }
 
+/*	A hook for bpf progs to attach to and update socket protocol.
+ *
+ *	A static noinline declaration here could cause the compiler to
+ *	optimize away the function. A global noinline declaration will
+ *	keep the definition, but may optimize away the callsite.
+ *	Therefore, __weak is needed to ensure that the call is still
+ *	emitted, by telling the compiler that we don't know what the
+ *	function might eventually be.
+ *
+ *	__diag_* below are needed to dismiss the missing prototype warning.
+ */
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "A fmod_ret entry point for BPF programs");
+
+__weak noinline int update_socket_protocol(int family, int type, int protocol)
+{
+	return protocol;
+}
+
+__diag_pop();
+
 int __sys_socket(int family, int type, int protocol)
 {
 	struct socket *sock;
 	int flags;
 
-	sock = __sys_socket_create(family, type, protocol);
+	sock = __sys_socket_create(family, type,
+				   update_socket_protocol(family, type, protocol));
 	if (IS_ERR(sock))
 		return PTR_ERR(sock);
 
-- 
2.35.3

[PATCH mptcp-next v12 2/5] selftests/bpf: Use random netns name for mptcp

[Geliang Tang]

When running mptcp tests simultaneously, it fails sometimes with
"Cannot create namespace file "/var/run/netns/mptcp_ns": File exists"
errors. So this patch uses rand() to generate a random netns name
instead of using the fixed name "mptcp_ns" for every test.

Add "ip netns show" after "ip netns del" to check if there is a test
did not clean up its netns

By doing that, we can re-launch the test even if there was an issue
removing the previous netns or if by accident, a netns with this
generic name already existed on the system.

Note that using a different name each will also help adding more
subtests in future commits.

Acked-by: Yonghong Song <yonghong.song@linux.dev>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 tools/testing/selftests/bpf/prog_tests/mptcp.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index cd0c42fff7c0..b2d41024c6c2 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -7,7 +7,7 @@
 #include "network_helpers.h"
 #include "mptcp_sock.skel.h"
 
-#define NS_TEST "mptcp_ns"
+char NS_TEST[32];
 
 #ifndef TCP_CA_NAME_MAX
 #define TCP_CA_NAME_MAX	16
@@ -147,6 +147,8 @@ static void test_base(void)
 	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
 		return;
 
+	srand(time(NULL));
+	snprintf(NS_TEST, sizeof(NS_TEST), "mptcp_ns_%d", rand());
 	SYS(fail, "ip netns add %s", NS_TEST);
 	SYS(fail, "ip -net %s link set dev lo up", NS_TEST);
 
@@ -178,6 +180,7 @@ static void test_base(void)
 		close_netns(nstoken);
 
 	SYS_NOFAIL("ip netns del " NS_TEST " &> /dev/null");
+	SYS_NOFAIL("ip netns show %s", NS_TEST);
 
 	close(cgroup_fd);
 }
-- 
2.35.3

[PATCH mptcp-next v12 3/5] selftests/bpf: Add two mptcp netns helpers

[Geliang Tang]

Add two netns helpers for mptcp tests: create_netns() and
cleanup_netns(). Use them in test_base().

These new helpers will be re-used in the following commits introducing
new tests.

Acked-by: Yonghong Song <yonghong.song@linux.dev>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 37 ++++++++++++-------
 1 file changed, 24 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index b2d41024c6c2..51cbd1e14156 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -22,6 +22,27 @@ struct mptcp_storage {
 	char ca_name[TCP_CA_NAME_MAX];
 };
 
+static struct nstoken *create_netns(void)
+{
+	srand(time(NULL));
+	snprintf(NS_TEST, sizeof(NS_TEST), "mptcp_ns_%d", rand());
+	SYS(fail, "ip netns add %s", NS_TEST);
+	SYS(fail, "ip -net %s link set dev lo up", NS_TEST);
+
+	return open_netns(NS_TEST);
+fail:
+	return NULL;
+}
+
+static void cleanup_netns(struct nstoken *nstoken)
+{
+	if (nstoken)
+		close_netns(nstoken);
+
+	SYS_NOFAIL("ip netns del %s &> /dev/null", NS_TEST);
+	SYS_NOFAIL("ip netns show %s", NS_TEST);
+}
+
 static int verify_tsk(int map_fd, int client_fd)
 {
 	int err, cfd = client_fd;
@@ -147,13 +168,8 @@ static void test_base(void)
 	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
 		return;
 
-	srand(time(NULL));
-	snprintf(NS_TEST, sizeof(NS_TEST), "mptcp_ns_%d", rand());
-	SYS(fail, "ip netns add %s", NS_TEST);
-	SYS(fail, "ip -net %s link set dev lo up", NS_TEST);
-
-	nstoken = open_netns(NS_TEST);
-	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+	nstoken = create_netns();
+	if (!ASSERT_OK_PTR(nstoken, "create_netns"))
 		goto fail;
 
 	/* without MPTCP */
@@ -176,12 +192,7 @@ static void test_base(void)
 	close(server_fd);
 
 fail:
-	if (nstoken)
-		close_netns(nstoken);
-
-	SYS_NOFAIL("ip netns del " NS_TEST " &> /dev/null");
-	SYS_NOFAIL("ip netns show %s", NS_TEST);
-
+	cleanup_netns(nstoken);
 	close(cgroup_fd);
 }
 
-- 
2.35.3

[PATCH mptcp-next v12 4/5] selftests/bpf: Fix error checks of mptcp open_and_load

[Geliang Tang]

Return libbpf_get_error(), instead of -EIO, for the error from
mptcp_sock__open_and_load().

Load success means prog_fd and map_fd are always valid. So drop these
unneeded ASSERT_GE checks for them in mptcp run_test().

Acked-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 tools/testing/selftests/bpf/prog_tests/mptcp.c | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 51cbd1e14156..8cbd72981a01 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -121,24 +121,14 @@ static int run_test(int cgroup_fd, int server_fd, bool is_mptcp)
 
 	sock_skel = mptcp_sock__open_and_load();
 	if (!ASSERT_OK_PTR(sock_skel, "skel_open_load"))
-		return -EIO;
+		return libbpf_get_error(sock_skel);
 
 	err = mptcp_sock__attach(sock_skel);
 	if (!ASSERT_OK(err, "skel_attach"))
 		goto out;
 
 	prog_fd = bpf_program__fd(sock_skel->progs._sockops);
-	if (!ASSERT_GE(prog_fd, 0, "bpf_program__fd")) {
-		err = -EIO;
-		goto out;
-	}
-
 	map_fd = bpf_map__fd(sock_skel->maps.socket_storage_map);
-	if (!ASSERT_GE(map_fd, 0, "bpf_map__fd")) {
-		err = -EIO;
-		goto out;
-	}
-
 	err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_SOCK_OPS, 0);
 	if (!ASSERT_OK(err, "bpf_prog_attach"))
 		goto out;
-- 
2.35.3

[PATCH mptcp-next v12 5/5] selftests/bpf: Add mptcpify test

[Geliang Tang]

Implement a new test program mptcpify: if the family is AF_INET or
AF_INET6, the type is SOCK_STREAM, and the protocol ID is 0 or
IPPROTO_TCP, set it to IPPROTO_MPTCP. It will be hooked in
update_socket_protocol().

Extend the MPTCP test base, add a selftest test_mptcpify() for the
mptcpify case. Open and load the mptcpify test prog to mptcpify the
TCP sockets dynamically, then use start_server() and connect_to_fd()
to create a TCP socket, but actually what's created is an MPTCP
socket, which can be verified through 'getsockopt(SOL_PROTOCOL)'
and 'nstat' commands.

Acked-by: Yonghong Song <yonghong.song@linux.dev>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 102 ++++++++++++++++++
 tools/testing/selftests/bpf/progs/mptcpify.c  |  20 ++++
 2 files changed, 122 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/mptcpify.c

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 8cbd72981a01..16353a35d288 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -2,13 +2,19 @@
 /* Copyright (c) 2020, Tessares SA. */
 /* Copyright (c) 2022, SUSE. */
 
+#include <netinet/in.h>
 #include <test_progs.h>
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
 #include "mptcp_sock.skel.h"
+#include "mptcpify.skel.h"
 
 char NS_TEST[32];
 
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+
 #ifndef TCP_CA_NAME_MAX
 #define TCP_CA_NAME_MAX	16
 #endif
@@ -186,8 +192,104 @@ static void test_base(void)
 	close(cgroup_fd);
 }
 
+static void send_byte(int fd)
+{
+	char b = 0x55;
+
+	ASSERT_EQ(write(fd, &b, sizeof(b)), 1, "send single byte");
+}
+
+static int verify_mptcpify(int server_fd)
+{
+	socklen_t optlen;
+	char cmd[256];
+	int protocol;
+	int err = 0;
+
+	optlen = sizeof(protocol);
+	if (!ASSERT_OK(getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen),
+		       "getsockopt(SOL_PROTOCOL)"))
+		return -1;
+
+	if (!ASSERT_EQ(protocol, IPPROTO_MPTCP, "protocol isn't MPTCP"))
+		err++;
+
+	/* Output of nstat:
+	 *
+	 * #kernel
+	 * MPTcpExtMPCapableSYNACKRX       1                  0.0
+	 */
+	snprintf(cmd, sizeof(cmd),
+		 "ip netns exec %s nstat -asz %s | awk '%s' | grep -q '%s'",
+		 NS_TEST, "MPTcpExtMPCapableSYNACKRX",
+		 "NR==1 {next} {print $2}", "1");
+	if (!ASSERT_OK(system(cmd), "No MPTcpExtMPCapableSYNACKRX found!"))
+		err++;
+
+	return err;
+}
+
+static int run_mptcpify(int cgroup_fd)
+{
+	int server_fd, client_fd, err = 0;
+	struct mptcpify *mptcpify_skel;
+
+	mptcpify_skel = mptcpify__open_and_load();
+	if (!ASSERT_OK_PTR(mptcpify_skel, "skel_open_load"))
+		return libbpf_get_error(mptcpify_skel);
+
+	err = mptcpify__attach(mptcpify_skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto out;
+
+	/* without MPTCP */
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(server_fd, 0, "start_server")) {
+		err = -EIO;
+		goto out;
+	}
+
+	client_fd = connect_to_fd(server_fd, 0);
+	if (!ASSERT_GE(client_fd, 0, "connect to fd")) {
+		err = -EIO;
+		goto close_server;
+	}
+
+	send_byte(client_fd);
+	err = verify_mptcpify(server_fd);
+
+	close(client_fd);
+close_server:
+	close(server_fd);
+out:
+	mptcpify__destroy(mptcpify_skel);
+	return err;
+}
+
+static void test_mptcpify(void)
+{
+	struct nstoken *nstoken = NULL;
+	int cgroup_fd;
+
+	cgroup_fd = test__join_cgroup("/mptcpify");
+	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
+		return;
+
+	nstoken = create_netns();
+	if (!ASSERT_OK_PTR(nstoken, "create_netns"))
+		goto fail;
+
+	ASSERT_OK(run_mptcpify(cgroup_fd), "run_mptcpify");
+
+fail:
+	cleanup_netns(nstoken);
+	close(cgroup_fd);
+}
+
 void test_mptcp(void)
 {
 	if (test__start_subtest("base"))
 		test_base();
+	if (test__start_subtest("mptcpify"))
+		test_mptcpify();
 }
diff --git a/tools/testing/selftests/bpf/progs/mptcpify.c b/tools/testing/selftests/bpf/progs/mptcpify.c
new file mode 100644
index 000000000000..53301ae8a8f7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcpify.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023, SUSE. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include "bpf_tracing_net.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("fmod_ret/update_socket_protocol")
+int BPF_PROG(mptcpify, int family, int type, int protocol)
+{
+	if ((family == AF_INET || family == AF_INET6) &&
+	    type == SOCK_STREAM &&
+	    (!protocol || protocol == IPPROTO_TCP)) {
+		return IPPROTO_MPTCP;
+	}
+
+	return protocol;
+}
-- 
2.35.3