Merge branch 'bpf: Force to MPTCP'

Geliang Tang says:

====================
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

v14:
 - Use getsockopt(MPTCP_INFO) to verify mptcp protocol intead of using
nstat command.

v13:
 - drop "Use random netns name for mptcp" patch.

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
====================

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

2 files changed, 181 insertions, 19 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index cd0c42fff7c0..7c0be7cf550b 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -2,17 +2,59 @@
 /* Copyright (c) 2020, Tessares SA. */
 /* Copyright (c) 2022, SUSE. */
 
+#include <linux/const.h>
+#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"
 
 #define NS_TEST "mptcp_ns"
 
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+
+#ifndef SOL_MPTCP
+#define SOL_MPTCP 284
+#endif
+#ifndef MPTCP_INFO
+#define MPTCP_INFO		1
+#endif
+#ifndef MPTCP_INFO_FLAG_FALLBACK
+#define MPTCP_INFO_FLAG_FALLBACK		_BITUL(0)
+#endif
+#ifndef MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED
+#define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED	_BITUL(1)
+#endif
+
 #ifndef TCP_CA_NAME_MAX
 #define TCP_CA_NAME_MAX	16
 #endif
 
+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;
+	__u32	mptcpi_retransmits;
+	__u64	mptcpi_bytes_retrans;
+	__u64	mptcpi_bytes_sent;
+	__u64	mptcpi_bytes_received;
+	__u64	mptcpi_bytes_acked;
+};
+
 struct mptcp_storage {
 	__u32 invoked;
 	__u32 is_mptcp;
@@ -22,6 +64,24 @@ struct mptcp_storage {
 	char ca_name[TCP_CA_NAME_MAX];
 };
 
+static struct nstoken *create_netns(void)
+{
+	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);
+}
+
 static int verify_tsk(int map_fd, int client_fd)
 {
 	int err, cfd = client_fd;
@@ -100,24 +160,14 @@ 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;
@@ -147,11 +197,8 @@ static void test_base(void)
 	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
 		return;
 
-	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 */
@@ -174,11 +221,104 @@ with_mptcp:
 	close(server_fd);
 
 fail:
-	if (nstoken)
-		close_netns(nstoken);
+	cleanup_netns(nstoken);
+	close(cgroup_fd);
+}
 
-	SYS_NOFAIL("ip netns del " NS_TEST " &> /dev/null");
+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, int client_fd)
+{
+	struct __mptcp_info info;
+	socklen_t optlen;
+	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++;
 
+	optlen = sizeof(info);
+	if (!ASSERT_OK(getsockopt(client_fd, SOL_MPTCP, MPTCP_INFO, &info, &optlen),
+		       "getsockopt(MPTCP_INFO)"))
+		return -1;
+
+	if (!ASSERT_GE(info.mptcpi_flags, 0, "unexpected mptcpi_flags"))
+		err++;
+	if (!ASSERT_FALSE(info.mptcpi_flags & MPTCP_INFO_FLAG_FALLBACK,
+			  "MPTCP fallback"))
+		err++;
+	if (!ASSERT_TRUE(info.mptcpi_flags & MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED,
+			 "no remote key received"))
+		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, client_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);
 }
 
@@ -186,4 +326,6 @@ 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;
+}