From 83752e12896a72b24845c94f000e4c51b2bc5b50 Mon Sep 17 00:00:00 2001 From: Nicolas Rybowski Date: Thu, 26 Sep 2024 19:30:22 +0200 Subject: [PATCH 1/3] selftests/bpf: Add mptcp subflow example Move Nicolas' patch into bpf selftests directory. This example adds a different mark (SO_MARK) on each subflow, and changes the TCP CC only on the first subflow. From the userspace, an application can do a setsockopt() on an MPTCP socket, and typically the same value will be propagated to all subflows (paths). If someone wants to have different values per subflow, the recommended way is to use BPF. So it is good to add such example here, and make sure there is no regressions. This example shows how it is possible to: Identify the parent msk of an MPTCP subflow. Put different sockopt for each subflow of a same MPTCP connection. Here especially, two different behaviours are implemented: A socket mark (SOL_SOCKET SO_MARK) is put on each subflow of a same MPTCP connection. The order of creation of the current subflow defines its mark. The TCP CC algorithm of the very first subflow of an MPTCP connection is set to "reno". This is just to show it is possible to identify an MPTCP connection, and set socket options, from different SOL levels, per subflow. "reno" has been picked because it is built-in and usually not set as default one. It is easy to verify with 'ss' that these modifications have been applied correctly. That's what the next patch is going to do. Nicolas' code comes from: commit 4d120186e4d6 ("bpf:examples: update mptcp_set_mark_kern.c") from the MPTCP repo https://github.com/multipath-tcp/mptcp_net-next (the "scripts" branch), and it has been adapted by Geliang. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/76 Co-developed-by: Geliang Tang Signed-off-by: Geliang Tang Signed-off-by: Nicolas Rybowski Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://lore.kernel.org/r/20240926-upstream-bpf-next-20240506-mptcp-subflow-test-v7-1-d26029e15cdd@kernel.org Signed-off-by: Martin KaFai Lau --- .../selftests/bpf/progs/mptcp_subflow.c | 59 +++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/mptcp_subflow.c diff --git a/tools/testing/selftests/bpf/progs/mptcp_subflow.c b/tools/testing/selftests/bpf/progs/mptcp_subflow.c new file mode 100644 index 000000000000..2e28f4a215b5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/mptcp_subflow.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020, Tessares SA. */ +/* Copyright (c) 2024, Kylin Software */ + +/* vmlinux.h, bpf_helpers.h and other 'define' */ +#include "bpf_tracing_net.h" + +char _license[] SEC("license") = "GPL"; + +char cc[TCP_CA_NAME_MAX] = "reno"; + +/* Associate a subflow counter to each token */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); + __uint(max_entries, 100); +} mptcp_sf SEC(".maps"); + +SEC("sockops") +int mptcp_subflow(struct bpf_sock_ops *skops) +{ + __u32 init = 1, key, mark, *cnt; + struct mptcp_sock *msk; + struct bpf_sock *sk; + int err; + + if (skops->op != BPF_SOCK_OPS_TCP_CONNECT_CB) + return 1; + + sk = skops->sk; + if (!sk) + return 1; + + msk = bpf_skc_to_mptcp_sock(sk); + if (!msk) + return 1; + + key = msk->token; + cnt = bpf_map_lookup_elem(&mptcp_sf, &key); + if (cnt) { + /* A new subflow is added to an existing MPTCP connection */ + __sync_fetch_and_add(cnt, 1); + mark = *cnt; + } else { + /* A new MPTCP connection is just initiated and this is its primary subflow */ + bpf_map_update_elem(&mptcp_sf, &key, &init, BPF_ANY); + mark = init; + } + + /* Set the mark of the subflow's socket based on appearance order */ + err = bpf_setsockopt(skops, SOL_SOCKET, SO_MARK, &mark, sizeof(mark)); + if (err < 0) + return 1; + if (mark == 2) + err = bpf_setsockopt(skops, SOL_TCP, TCP_CONGESTION, cc, TCP_CA_NAME_MAX); + + return 1; +} From cd19b885106e0a24c28ef72fccc4c020782e6e7e Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 26 Sep 2024 19:30:23 +0200 Subject: [PATCH 2/3] selftests/bpf: Add getsockopt to inspect mptcp subflow This patch adds a "cgroup/getsockopt" way to inspect the subflows of an MPTCP socket, and verify the modifications done by the same BPF program in the previous commit: a different mark per subflow, and a different TCP CC set on the second one. This new hook will be used by the next commit to verify the socket options set on each subflow. This extra "cgroup/getsockopt" prog walks the msk->conn_list and use bpf_core_cast to cast a pointer for readonly. It allows to inspect all the fields of a structure. Note that on the kernel side, the MPTCP socket stores a list of subflows under 'msk->conn_list'. They can be iterated using the generic 'list' helpers. They have been imported here, with a small difference: list_for_each_entry() uses 'can_loop' to limit the number of iterations, and ease its use. Because only data need to be read here, it is enough to use this technique. It is planned to use bpf_iter, when BPF programs will be used to modify data from the different subflows. mptcp_subflow_tcp_sock() and mptcp_for_each_stubflow() helpers have also be imported. Suggested-by: Martin KaFai Lau Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://lore.kernel.org/r/20240926-upstream-bpf-next-20240506-mptcp-subflow-test-v7-2-d26029e15cdd@kernel.org Signed-off-by: Martin KaFai Lau --- MAINTAINERS | 2 +- tools/testing/selftests/bpf/progs/mptcp_bpf.h | 42 +++++++++++ .../selftests/bpf/progs/mptcp_subflow.c | 69 +++++++++++++++++++ 3 files changed, 112 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf.h diff --git a/MAINTAINERS b/MAINTAINERS index e71d066dc919..f02b7485b215 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16281,7 +16281,7 @@ F: include/net/mptcp.h F: include/trace/events/mptcp.h F: include/uapi/linux/mptcp*.h F: net/mptcp/ -F: tools/testing/selftests/bpf/*/*mptcp*.c +F: tools/testing/selftests/bpf/*/*mptcp*.[ch] F: tools/testing/selftests/net/mptcp/ NETWORKING [TCP] diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf.h b/tools/testing/selftests/bpf/progs/mptcp_bpf.h new file mode 100644 index 000000000000..3b188ccdcc40 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/mptcp_bpf.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __MPTCP_BPF_H__ +#define __MPTCP_BPF_H__ + +#include "bpf_experimental.h" + +/* list helpers from include/linux/list.h */ +static inline int list_is_head(const struct list_head *list, + const struct list_head *head) +{ + return list == head; +} + +#define list_entry(ptr, type, member) \ + container_of(ptr, type, member) + +#define list_first_entry(ptr, type, member) \ + list_entry((ptr)->next, type, member) + +#define list_next_entry(pos, member) \ + list_entry((pos)->member.next, typeof(*(pos)), member) + +#define list_entry_is_head(pos, head, member) \ + list_is_head(&pos->member, (head)) + +/* small difference: 'can_loop' has been added in the conditions */ +#define list_for_each_entry(pos, head, member) \ + for (pos = list_first_entry(head, typeof(*pos), member); \ + !list_entry_is_head(pos, head, member) && can_loop; \ + pos = list_next_entry(pos, member)) + +/* mptcp helpers from protocol.h */ +#define mptcp_for_each_subflow(__msk, __subflow) \ + list_for_each_entry(__subflow, &((__msk)->conn_list), node) + +static __always_inline struct sock * +mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow) +{ + return subflow->tcp_sock; +} + +#endif diff --git a/tools/testing/selftests/bpf/progs/mptcp_subflow.c b/tools/testing/selftests/bpf/progs/mptcp_subflow.c index 2e28f4a215b5..70302477e326 100644 --- a/tools/testing/selftests/bpf/progs/mptcp_subflow.c +++ b/tools/testing/selftests/bpf/progs/mptcp_subflow.c @@ -4,10 +4,12 @@ /* vmlinux.h, bpf_helpers.h and other 'define' */ #include "bpf_tracing_net.h" +#include "mptcp_bpf.h" char _license[] SEC("license") = "GPL"; char cc[TCP_CA_NAME_MAX] = "reno"; +int pid; /* Associate a subflow counter to each token */ struct { @@ -57,3 +59,70 @@ int mptcp_subflow(struct bpf_sock_ops *skops) return 1; } + +static int _check_getsockopt_subflow_mark(struct mptcp_sock *msk, struct bpf_sockopt *ctx) +{ + struct mptcp_subflow_context *subflow; + int i = 0; + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk; + + ssk = mptcp_subflow_tcp_sock(bpf_core_cast(subflow, + struct mptcp_subflow_context)); + + if (ssk->sk_mark != ++i) { + ctx->retval = -2; + break; + } + } + + return 1; +} + +static int _check_getsockopt_subflow_cc(struct mptcp_sock *msk, struct bpf_sockopt *ctx) +{ + struct mptcp_subflow_context *subflow; + + mptcp_for_each_subflow(msk, subflow) { + struct inet_connection_sock *icsk; + struct sock *ssk; + + ssk = mptcp_subflow_tcp_sock(bpf_core_cast(subflow, + struct mptcp_subflow_context)); + icsk = bpf_core_cast(ssk, struct inet_connection_sock); + + if (ssk->sk_mark == 2 && + __builtin_memcmp(icsk->icsk_ca_ops->name, cc, TCP_CA_NAME_MAX)) { + ctx->retval = -2; + break; + } + } + + return 1; +} + +SEC("cgroup/getsockopt") +int _getsockopt_subflow(struct bpf_sockopt *ctx) +{ + struct bpf_sock *sk = ctx->sk; + struct mptcp_sock *msk; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 1; + + if (!sk || sk->protocol != IPPROTO_MPTCP || + (!(ctx->level == SOL_SOCKET && ctx->optname == SO_MARK) && + !(ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION))) + return 1; + + msk = bpf_core_cast(sk, struct mptcp_sock); + if (msk->pm.subflows != 1) { + ctx->retval = -1; + return 1; + } + + if (ctx->optname == SO_MARK) + return _check_getsockopt_subflow_mark(msk, ctx); + return _check_getsockopt_subflow_cc(msk, ctx); +} From 9b85f11efa02f3dc78c60961c0b9cff166516464 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 26 Sep 2024 19:30:24 +0200 Subject: [PATCH 3/3] selftests/bpf: Add mptcp subflow subtest This patch adds a subtest named test_subflow in test_mptcp to load and verify the newly added MPTCP subflow BPF program. To goal is to make sure it is possible to set different socket options per subflows, while the userspace socket interface only lets the application to set the same socket options for the whole MPTCP connection and its multiple subflows. To check that, a client and a server are started in a dedicated netns, with veth interfaces to simulate multiple paths. They will exchange data to allow the creation of an additional subflow. When the different subflows are being created, the new MPTCP subflow BPF program will set some socket options: marks and TCP CC. The validation is done by the same program, when the userspace checks the value of the modified socket options. On the userspace side, it will see that the default values are still being used on the MPTCP connection, while the BPF program will see different options set per subflow of the same MPTCP connection. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/76 Signed-off-by: Geliang Tang Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://lore.kernel.org/r/20240926-upstream-bpf-next-20240506-mptcp-subflow-test-v7-3-d26029e15cdd@kernel.org Signed-off-by: Martin KaFai Lau --- .../testing/selftests/bpf/prog_tests/mptcp.c | 121 ++++++++++++++++++ 1 file changed, 121 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c index d2ca32fa3b21..be3cad2aff77 100644 --- a/tools/testing/selftests/bpf/prog_tests/mptcp.c +++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c @@ -5,12 +5,17 @@ #include #include #include +#include #include "cgroup_helpers.h" #include "network_helpers.h" #include "mptcp_sock.skel.h" #include "mptcpify.skel.h" +#include "mptcp_subflow.skel.h" #define NS_TEST "mptcp_ns" +#define ADDR_1 "10.0.1.1" +#define ADDR_2 "10.0.1.2" +#define PORT_1 10001 #ifndef IPPROTO_MPTCP #define IPPROTO_MPTCP 262 @@ -335,10 +340,126 @@ static void test_mptcpify(void) close(cgroup_fd); } +static int endpoint_init(char *flags) +{ + SYS(fail, "ip -net %s link add veth1 type veth peer name veth2", NS_TEST); + SYS(fail, "ip -net %s addr add %s/24 dev veth1", NS_TEST, ADDR_1); + SYS(fail, "ip -net %s link set dev veth1 up", NS_TEST); + SYS(fail, "ip -net %s addr add %s/24 dev veth2", NS_TEST, ADDR_2); + SYS(fail, "ip -net %s link set dev veth2 up", NS_TEST); + if (SYS_NOFAIL("ip -net %s mptcp endpoint add %s %s", NS_TEST, ADDR_2, flags)) { + printf("'ip mptcp' not supported, skip this test.\n"); + test__skip(); + goto fail; + } + + return 0; +fail: + return -1; +} + +static void wait_for_new_subflows(int fd) +{ + socklen_t len; + u8 subflows; + int err, i; + + len = sizeof(subflows); + /* Wait max 5 sec for new subflows to be created */ + for (i = 0; i < 50; i++) { + err = getsockopt(fd, SOL_MPTCP, MPTCP_INFO, &subflows, &len); + if (!err && subflows > 0) + break; + + usleep(100000); /* 0.1s */ + } +} + +static void run_subflow(void) +{ + int server_fd, client_fd, err; + char new[TCP_CA_NAME_MAX]; + char cc[TCP_CA_NAME_MAX]; + unsigned int mark; + socklen_t len; + + server_fd = start_mptcp_server(AF_INET, ADDR_1, PORT_1, 0); + if (!ASSERT_OK_FD(server_fd, "start_mptcp_server")) + return; + + client_fd = connect_to_fd(server_fd, 0); + if (!ASSERT_OK_FD(client_fd, "connect_to_fd")) + goto close_server; + + send_byte(client_fd); + wait_for_new_subflows(client_fd); + + len = sizeof(mark); + err = getsockopt(client_fd, SOL_SOCKET, SO_MARK, &mark, &len); + if (ASSERT_OK(err, "getsockopt(client_fd, SO_MARK)")) + ASSERT_EQ(mark, 0, "mark"); + + len = sizeof(new); + err = getsockopt(client_fd, SOL_TCP, TCP_CONGESTION, new, &len); + if (ASSERT_OK(err, "getsockopt(client_fd, TCP_CONGESTION)")) { + get_msk_ca_name(cc); + ASSERT_STREQ(new, cc, "cc"); + } + + close(client_fd); +close_server: + close(server_fd); +} + +static void test_subflow(void) +{ + struct mptcp_subflow *skel; + struct nstoken *nstoken; + int cgroup_fd; + + cgroup_fd = test__join_cgroup("/mptcp_subflow"); + if (!ASSERT_OK_FD(cgroup_fd, "join_cgroup: mptcp_subflow")) + return; + + skel = mptcp_subflow__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_load: mptcp_subflow")) + goto close_cgroup; + + skel->bss->pid = getpid(); + + skel->links.mptcp_subflow = + bpf_program__attach_cgroup(skel->progs.mptcp_subflow, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.mptcp_subflow, "attach mptcp_subflow")) + goto skel_destroy; + + skel->links._getsockopt_subflow = + bpf_program__attach_cgroup(skel->progs._getsockopt_subflow, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links._getsockopt_subflow, "attach _getsockopt_subflow")) + goto skel_destroy; + + nstoken = create_netns(); + if (!ASSERT_OK_PTR(nstoken, "create_netns: mptcp_subflow")) + goto skel_destroy; + + if (endpoint_init("subflow") < 0) + goto close_netns; + + run_subflow(); + +close_netns: + cleanup_netns(nstoken); +skel_destroy: + mptcp_subflow__destroy(skel); +close_cgroup: + close(cgroup_fd); +} + void test_mptcp(void) { if (test__start_subtest("base")) test_base(); if (test__start_subtest("mptcpify")) test_mptcpify(); + if (test__start_subtest("subflow")) + test_subflow(); }