Contributors: 8
Author Tokens Token Proportion Commits Commit Proportion
Geliang Tang 682 46.02% 11 52.38%
Nicolas Rybowski 573 38.66% 1 4.76%
Jussi Mäki 101 6.82% 1 4.76%
Hangbin Liu 76 5.13% 1 4.76%
Martin KaFai Lau 27 1.82% 4 19.05%
Toke Höiland-Jörgensen 15 1.01% 1 4.76%
Stanislav Fomichev 6 0.40% 1 4.76%
Daniel Borkmann 2 0.13% 1 4.76%
Total 1482 21 


// SPDX-License-Identifier: GPL-2.0
/* 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;
	struct sock *sk;
	__u32 token;
	struct sock *first;
	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", NS_TEST);
}

static int start_mptcp_server(int family, const char *addr_str, __u16 port,
			      int timeout_ms)
{
	struct network_helper_opts opts = {
		.timeout_ms	= timeout_ms,
		.proto		= IPPROTO_MPTCP,
	};

	return start_server_str(family, SOCK_STREAM, addr_str, port, &opts);
}

static int verify_tsk(int map_fd, int client_fd)
{
	int err, cfd = client_fd;
	struct mptcp_storage val;

	err = bpf_map_lookup_elem(map_fd, &cfd, &val);
	if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
		return err;

	if (!ASSERT_EQ(val.invoked, 1, "unexpected invoked count"))
		err++;

	if (!ASSERT_EQ(val.is_mptcp, 0, "unexpected is_mptcp"))
		err++;

	return err;
}

static void get_msk_ca_name(char ca_name[])
{
	size_t len;
	int fd;

	fd = open("/proc/sys/net/ipv4/tcp_congestion_control", O_RDONLY);
	if (!ASSERT_GE(fd, 0, "failed to open tcp_congestion_control"))
		return;

	len = read(fd, ca_name, TCP_CA_NAME_MAX);
	if (!ASSERT_GT(len, 0, "failed to read ca_name"))
		goto err;

	if (len > 0 && ca_name[len - 1] == '\n')
		ca_name[len - 1] = '\0';

err:
	close(fd);
}

static int verify_msk(int map_fd, int client_fd, __u32 token)
{
	char ca_name[TCP_CA_NAME_MAX];
	int err, cfd = client_fd;
	struct mptcp_storage val;

	if (!ASSERT_GT(token, 0, "invalid token"))
		return -1;

	get_msk_ca_name(ca_name);

	err = bpf_map_lookup_elem(map_fd, &cfd, &val);
	if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
		return err;

	if (!ASSERT_EQ(val.invoked, 1, "unexpected invoked count"))
		err++;

	if (!ASSERT_EQ(val.is_mptcp, 1, "unexpected is_mptcp"))
		err++;

	if (!ASSERT_EQ(val.token, token, "unexpected token"))
		err++;

	if (!ASSERT_EQ(val.first, val.sk, "unexpected first"))
		err++;

	if (!ASSERT_STRNEQ(val.ca_name, ca_name, TCP_CA_NAME_MAX, "unexpected ca_name"))
		err++;

	return err;
}

static int run_test(int cgroup_fd, int server_fd, bool is_mptcp)
{
	int client_fd, prog_fd, map_fd, err;
	struct mptcp_sock *sock_skel;

	sock_skel = mptcp_sock__open_and_load();
	if (!ASSERT_OK_PTR(sock_skel, "skel_open_load"))
		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);
	map_fd = bpf_map__fd(sock_skel->maps.socket_storage_map);
	err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_SOCK_OPS, 0);
	if (!ASSERT_OK(err, "bpf_prog_attach"))
		goto out;

	client_fd = connect_to_fd(server_fd, 0);
	if (!ASSERT_GE(client_fd, 0, "connect to fd")) {
		err = -EIO;
		goto out;
	}

	err += is_mptcp ? verify_msk(map_fd, client_fd, sock_skel->bss->token) :
			  verify_tsk(map_fd, client_fd);

	close(client_fd);

out:
	mptcp_sock__destroy(sock_skel);
	return err;
}

static void test_base(void)
{
	struct nstoken *nstoken = NULL;
	int server_fd, cgroup_fd;

	cgroup_fd = test__join_cgroup("/mptcp");
	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
		return;

	nstoken = create_netns();
	if (!ASSERT_OK_PTR(nstoken, "create_netns"))
		goto fail;

	/* without MPTCP */
	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
	if (!ASSERT_GE(server_fd, 0, "start_server"))
		goto with_mptcp;

	ASSERT_OK(run_test(cgroup_fd, server_fd, false), "run_test tcp");

	close(server_fd);

with_mptcp:
	/* with MPTCP */
	server_fd = start_mptcp_server(AF_INET, NULL, 0, 0);
	if (!ASSERT_GE(server_fd, 0, "start_mptcp_server"))
		goto fail;

	ASSERT_OK(run_test(cgroup_fd, server_fd, true), "run_test mptcp");

	close(server_fd);

fail:
	cleanup_netns(nstoken);
	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, 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);

	mptcpify_skel->bss->pid = getpid();

	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);
}

void test_mptcp(void)
{
	if (test__start_subtest("base"))
		test_base();
	if (test__start_subtest("mptcpify"))
		test_mptcpify();
}