Merge branch 'bpf: mptcp: Support for mptcp_sock'

Mat Martineau says:

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

This patch set adds BPF access to mptcp_sock structures, along with
associated self tests. You may recognize some of the code from earlier
(https://lore.kernel.org/bpf/20200918121046.190240-6-nicolas.rybowski@tessares.net/)
but it has been reworked quite a bit.

v1 -> v2: Emit BTF type, add func_id checks in verifier.c and bpf_trace.c,
remove build check for CONFIG_BPF_JIT, add selftest check for CONFIG_MPTCP,
and add a patch to include CONFIG_IKCONFIG/CONFIG_IKCONFIG_PROC for the
BPF self tests.

v2 -> v3: Access sysctl through the filesystem to work around CI use of
the more limited busybox sysctl command.

v3 -> v4: Dropped special case kernel code for tcp_sock is_mptcp, use
existing bpf_tcp_helpers.h, and add check for 'ip mptcp monitor' support.

v4 -> v5: Use BPF test skeleton, more consistent use of ASSERT macros,
drop some unnecessary parameters / checks, and use tracing to acquire
MPTCP token.

Geliang Tang (6):
  bpf: add bpf_skc_to_mptcp_sock_proto
  selftests/bpf: Enable CONFIG_IKCONFIG_PROC in config
  selftests/bpf: test bpf_skc_to_mptcp_sock
  selftests/bpf: verify token of struct mptcp_sock
  selftests/bpf: verify ca_name of struct mptcp_sock
  selftests/bpf: verify first of struct mptcp_sock
====================

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

6 files changed, 311 insertions, 9 deletions

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index b1ede6f0b821..82a7c9de95f9 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -16,6 +16,10 @@ BPF_PROG(name, args)
 #define SOL_TCP 6
 #endif
 
+#ifndef TCP_CA_NAME_MAX
+#define TCP_CA_NAME_MAX	16
+#endif
+
 #define tcp_jiffies32 ((__u32)bpf_jiffies64())
 
 struct sock_common {
@@ -81,6 +85,7 @@ struct tcp_sock {
 	__u32	lsndtime;
 	__u32	prior_cwnd;
 	__u64	tcp_mstamp;	/* most recent packet received/sent */
+	bool	is_mptcp;
 } __attribute__((preserve_access_index));
 
 static __always_inline struct inet_connection_sock *inet_csk(const struct sock *sk)
@@ -225,4 +230,12 @@ static __always_inline bool tcp_cc_eq(const char *a, const char *b)
 extern __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked) __ksym;
 extern void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked) __ksym;
 
+struct mptcp_sock {
+	struct inet_connection_sock	sk;
+
+	__u32		token;
+	struct sock	*first;
+	char		ca_name[TCP_CA_NAME_MAX];
+} __attribute__((preserve_access_index));
+
 #endif
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 08c6e5a66d87..3b3edc0fc8a6 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -54,3 +54,6 @@ CONFIG_NF_DEFRAG_IPV6=y
 CONFIG_NF_CONNTRACK=y
 CONFIG_USERFAULTFD=y
 CONFIG_FPROBE=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_MPTCP=y
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 2bb1f9b3841d..59cf81ec55af 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -21,6 +21,10 @@
 #include "network_helpers.h"
 #include "test_progs.h"
 
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+
 #define clean_errno() (errno == 0 ? "None" : strerror(errno))
 #define log_err(MSG, ...) ({						\
 			int __save = errno;				\
@@ -73,13 +77,13 @@ int settimeo(int fd, int timeout_ms)
 
 #define save_errno_close(fd) ({ int __save = errno; close(fd); errno = __save; })
 
-static int __start_server(int type, const struct sockaddr *addr,
+static int __start_server(int type, int protocol, const struct sockaddr *addr,
 			  socklen_t addrlen, int timeout_ms, bool reuseport)
 {
 	int on = 1;
 	int fd;
 
-	fd = socket(addr->sa_family, type, 0);
+	fd = socket(addr->sa_family, type, protocol);
 	if (fd < 0) {
 		log_err("Failed to create server socket");
 		return -1;
@@ -113,8 +117,8 @@ error_close:
 	return -1;
 }
 
-int start_server(int family, int type, const char *addr_str, __u16 port,
-		 int timeout_ms)
+static int start_server_proto(int family, int type, int protocol,
+			      const char *addr_str, __u16 port, int timeout_ms)
 {
 	struct sockaddr_storage addr;
 	socklen_t addrlen;
@@ -122,10 +126,23 @@ int start_server(int family, int type, const char *addr_str, __u16 port,
 	if (make_sockaddr(family, addr_str, port, &addr, &addrlen))
 		return -1;
 
-	return __start_server(type, (struct sockaddr *)&addr,
+	return __start_server(type, protocol, (struct sockaddr *)&addr,
 			      addrlen, timeout_ms, false);
 }
 
+int start_server(int family, int type, const char *addr_str, __u16 port,
+		 int timeout_ms)
+{
+	return start_server_proto(family, type, 0, addr_str, port, timeout_ms);
+}
+
+int start_mptcp_server(int family, const char *addr_str, __u16 port,
+		       int timeout_ms)
+{
+	return start_server_proto(family, SOCK_STREAM, IPPROTO_MPTCP, addr_str,
+				  port, timeout_ms);
+}
+
 int *start_reuseport_server(int family, int type, const char *addr_str,
 			    __u16 port, int timeout_ms, unsigned int nr_listens)
 {
@@ -144,7 +161,7 @@ int *start_reuseport_server(int family, int type, const char *addr_str,
 	if (!fds)
 		return NULL;
 
-	fds[0] = __start_server(type, (struct sockaddr *)&addr, addrlen,
+	fds[0] = __start_server(type, 0, (struct sockaddr *)&addr, addrlen,
 				timeout_ms, true);
 	if (fds[0] == -1)
 		goto close_fds;
@@ -154,7 +171,7 @@ int *start_reuseport_server(int family, int type, const char *addr_str,
 		goto close_fds;
 
 	for (; nr_fds < nr_listens; nr_fds++) {
-		fds[nr_fds] = __start_server(type, (struct sockaddr *)&addr,
+		fds[nr_fds] = __start_server(type, 0, (struct sockaddr *)&addr,
 					     addrlen, timeout_ms, true);
 		if (fds[nr_fds] == -1)
 			goto close_fds;
@@ -247,7 +264,7 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
 	struct sockaddr_storage addr;
 	struct sockaddr_in *addr_in;
 	socklen_t addrlen, optlen;
-	int fd, type;
+	int fd, type, protocol;
 
 	if (!opts)
 		opts = &default_opts;
@@ -258,6 +275,11 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
 		return -1;
 	}
 
+	if (getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen)) {
+		log_err("getsockopt(SOL_PROTOCOL)");
+		return -1;
+	}
+
 	addrlen = sizeof(addr);
 	if (getsockname(server_fd, (struct sockaddr *)&addr, &addrlen)) {
 		log_err("Failed to get server addr");
@@ -265,7 +287,7 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
 	}
 
 	addr_in = (struct sockaddr_in *)&addr;
-	fd = socket(addr_in->sin_family, type, 0);
+	fd = socket(addr_in->sin_family, type, protocol);
 	if (fd < 0) {
 		log_err("Failed to create client socket");
 		return -1;
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index a4b3b2f9877b..f882c691b790 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -42,6 +42,8 @@ extern struct ipv6_packet pkt_v6;
 int settimeo(int fd, int timeout_ms);
 int start_server(int family, int type, const char *addr, __u16 port,
 		 int timeout_ms);
+int start_mptcp_server(int family, const char *addr, __u16 port,
+		       int timeout_ms);
 int *start_reuseport_server(int family, int type, const char *addr_str,
 			    __u16 port, int timeout_ms,
 			    unsigned int nr_listens);
diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
new file mode 100644
index 000000000000..59f08d6d1d53
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020, Tessares SA. */
+/* Copyright (c) 2022, SUSE. */
+
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+#include "mptcp_sock.skel.h"
+
+#ifndef TCP_CA_NAME_MAX
+#define TCP_CA_NAME_MAX	16
+#endif
+
+struct mptcp_storage {
+	__u32 invoked;
+	__u32 is_mptcp;
+	struct sock *sk;
+	__u32 token;
+	struct sock *first;
+	char ca_name[TCP_CA_NAME_MAX];
+};
+
+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 -EIO;
+
+	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;
+
+	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)
+{
+	int server_fd, cgroup_fd;
+
+	cgroup_fd = test__join_cgroup("/mptcp");
+	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
+		return;
+
+	/* 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 close_cgroup_fd;
+
+	ASSERT_OK(run_test(cgroup_fd, server_fd, true), "run_test mptcp");
+
+	close(server_fd);
+
+close_cgroup_fd:
+	close(cgroup_fd);
+}
+
+void test_mptcp(void)
+{
+	if (test__start_subtest("base"))
+		test_base();
+}
diff --git a/tools/testing/selftests/bpf/progs/mptcp_sock.c b/tools/testing/selftests/bpf/progs/mptcp_sock.c
new file mode 100644
index 000000000000..91a0d7eff2ac
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_sock.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020, Tessares SA. */
+/* Copyright (c) 2022, SUSE. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+__u32 token = 0;
+
+struct mptcp_storage {
+	__u32 invoked;
+	__u32 is_mptcp;
+	struct sock *sk;
+	__u32 token;
+	struct sock *first;
+	char ca_name[TCP_CA_NAME_MAX];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct mptcp_storage);
+} socket_storage_map SEC(".maps");
+
+SEC("sockops")
+int _sockops(struct bpf_sock_ops *ctx)
+{
+	struct mptcp_storage *storage;
+	struct mptcp_sock *msk;
+	int op = (int)ctx->op;
+	struct tcp_sock *tsk;
+	struct bpf_sock *sk;
+	bool is_mptcp;
+
+	if (op != BPF_SOCK_OPS_TCP_CONNECT_CB)
+		return 1;
+
+	sk = ctx->sk;
+	if (!sk)
+		return 1;
+
+	tsk = bpf_skc_to_tcp_sock(sk);
+	if (!tsk)
+		return 1;
+
+	is_mptcp = bpf_core_field_exists(tsk->is_mptcp) ? tsk->is_mptcp : 0;
+	if (!is_mptcp) {
+		storage = bpf_sk_storage_get(&socket_storage_map, sk, 0,
+					     BPF_SK_STORAGE_GET_F_CREATE);
+		if (!storage)
+			return 1;
+
+		storage->token = 0;
+		__builtin_memset(storage->ca_name, 0, TCP_CA_NAME_MAX);
+		storage->first = NULL;
+	} else {
+		msk = bpf_skc_to_mptcp_sock(sk);
+		if (!msk)
+			return 1;
+
+		storage = bpf_sk_storage_get(&socket_storage_map, msk, 0,
+					     BPF_SK_STORAGE_GET_F_CREATE);
+		if (!storage)
+			return 1;
+
+		storage->token = msk->token;
+		__builtin_memcpy(storage->ca_name, msk->ca_name, TCP_CA_NAME_MAX);
+		storage->first = msk->first;
+	}
+	storage->invoked++;
+	storage->is_mptcp = is_mptcp;
+	storage->sk = (struct sock *)sk;
+
+	return 1;
+}
+
+SEC("fentry/mptcp_pm_new_connection")
+int BPF_PROG(trace_mptcp_pm_new_connection, struct mptcp_sock *msk,
+	     const struct sock *ssk, int server_side)
+{
+	if (!server_side)
+		token = msk->token;
+
+	return 0;
+}