[PATCH mptcp-next v2 0/7] for bpf-next

[PATCH mptcp-next v2 0/7] for bpf-next

[Geliang Tang]

v2:
 - The series is for bpf-next v5.
 - patch 1, keep bpf_mptcp_sock_from_subflow() in bpf.c
 - patch 3, Drop the 'msg' parameter of verify_sk
 - base-commit: df896c77f02a ("DO-NOT-MERGE: git markup: features
net-next-next"), export/20220517T155019
 - The last squash-to patch is for "BPF packet scheduler" series.

v1:
 - The first 10 patches is for bpf-next v5.
 - Rebased the "BPF packet scheduler" series on export branch.

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

Nicolas Rybowski (1):
  selftests/bpf: add MPTCP test base

 MAINTAINERS                                   |   1 +
 include/linux/bpf.h                           |   1 +
 include/linux/btf_ids.h                       |   3 +-
 include/net/mptcp.h                           |   6 +
 include/uapi/linux/bpf.h                      |   7 +
 kernel/bpf/verifier.c                         |   1 +
 kernel/trace/bpf_trace.c                      |   2 +
 net/core/filter.c                             |  18 ++
 net/mptcp/Makefile                            |   2 +
 net/mptcp/bpf.c                               |  21 +++
 scripts/bpf_doc.py                            |   2 +
 tools/include/uapi/linux/bpf.h                |   7 +
 tools/testing/selftests/bpf/bpf_tcp_helpers.h |  13 ++
 tools/testing/selftests/bpf/config            |   3 +
 tools/testing/selftests/bpf/network_helpers.c |  40 +++-
 tools/testing/selftests/bpf/network_helpers.h |   2 +
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 174 ++++++++++++++++++
 .../testing/selftests/bpf/progs/mptcp_sock.c  |  89 +++++++++
 18 files changed, 382 insertions(+), 10 deletions(-)
 create mode 100644 net/mptcp/bpf.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/mptcp.c
 create mode 100644 tools/testing/selftests/bpf/progs/mptcp_sock.c

-- 
2.34.1

[PATCH mptcp-next v2 1/7] bpf: add bpf_skc_to_mptcp_sock_proto

[Geliang Tang]

This patch implements a new struct bpf_func_proto, named
bpf_skc_to_mptcp_sock_proto. Define a new bpf_id BTF_SOCK_TYPE_MPTCP,
and a new helper bpf_skc_to_mptcp_sock(), which invokes another new
helper bpf_mptcp_sock_from_subflow() in net/mptcp/bpf.c to get struct
mptcp_sock from a given subflow socket.

v2: Emit BTF type, add func_id checks in verifier.c and bpf_trace.c,
remove build check for CONFIG_BPF_JIT
v3: Drop EXPORT_SYMBOL (Martin)

Co-developed-by: Nicolas Rybowski <nicolas.rybowski@tessares.net>
Signed-off-by: Nicolas Rybowski <nicolas.rybowski@tessares.net>
Co-developed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Acked-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 include/linux/bpf.h            |  1 +
 include/linux/btf_ids.h        |  3 ++-
 include/net/mptcp.h            |  6 ++++++
 include/uapi/linux/bpf.h       |  7 +++++++
 kernel/bpf/verifier.c          |  1 +
 kernel/trace/bpf_trace.c       |  2 ++
 net/core/filter.c              | 18 ++++++++++++++++++
 net/mptcp/Makefile             |  2 ++
 net/mptcp/bpf.c                | 21 +++++++++++++++++++++
 scripts/bpf_doc.py             |  2 ++
 tools/include/uapi/linux/bpf.h |  7 +++++++
 11 files changed, 69 insertions(+), 1 deletion(-)
 create mode 100644 net/mptcp/bpf.c

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index be94833d390a..f53e39065a6e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2204,6 +2204,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto;
+extern const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_proto;
 extern const struct bpf_func_proto bpf_snprintf_btf_proto;
 extern const struct bpf_func_proto bpf_snprintf_proto;
diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index bc5d9cc34e4c..335a19092368 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -178,7 +178,8 @@ extern struct btf_id_set name;
 	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock)			\
 	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock)			\
 	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock)			\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock)
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_MPTCP, mptcp_sock)
 
 enum {
 #define BTF_SOCK_TYPE(name, str) name,
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index d4ec894ce67b..4d761ad530c9 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -284,4 +284,10 @@ static inline int mptcpv6_init(void) { return 0; }
 static inline void mptcpv6_handle_mapped(struct sock *sk, bool mapped) { }
 #endif
 
+#if defined(CONFIG_MPTCP) && defined(CONFIG_BPF_SYSCALL)
+struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk);
+#else
+static inline struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk) { return NULL; }
+#endif
+
 #endif /* __NET_MPTCP_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 444fe6f1cf35..3e996e097084 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5154,6 +5154,12 @@ union bpf_attr {
  *		if not NULL, is a reference which must be released using its
  *		corresponding release function, or moved into a BPF map before
  *		program exit.
+ *
+ * struct mptcp_sock *bpf_skc_to_mptcp_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *mptcp_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or **NULL** otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5351,6 +5357,7 @@ union bpf_attr {
 	FN(skb_set_tstamp),		\
 	FN(ima_file_hash),		\
 	FN(kptr_xchg),			\
+	FN(skc_to_mptcp_sock),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 813f6ee80419..3d8790e81c48 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -509,6 +509,7 @@ static bool is_ptr_cast_function(enum bpf_func_id func_id)
 		func_id == BPF_FUNC_skc_to_tcp_sock ||
 		func_id == BPF_FUNC_skc_to_tcp6_sock ||
 		func_id == BPF_FUNC_skc_to_udp6_sock ||
+		func_id == BPF_FUNC_skc_to_mptcp_sock ||
 		func_id == BPF_FUNC_skc_to_tcp_timewait_sock ||
 		func_id == BPF_FUNC_skc_to_tcp_request_sock;
 }
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index f15b826f9899..8451fc83d031 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1688,6 +1688,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_to_udp6_sock_proto;
 	case BPF_FUNC_skc_to_unix_sock:
 		return &bpf_skc_to_unix_sock_proto;
+	case BPF_FUNC_skc_to_mptcp_sock:
+		return &bpf_skc_to_mptcp_sock_proto;
 	case BPF_FUNC_sk_storage_get:
 		return &bpf_sk_storage_get_tracing_proto;
 	case BPF_FUNC_sk_storage_delete:
diff --git a/net/core/filter.c b/net/core/filter.c
index b741b9f7e6a9..ef84a9087651 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -78,6 +78,7 @@
 #include <linux/btf_ids.h>
 #include <net/tls.h>
 #include <net/xdp.h>
+#include <net/mptcp.h>
 
 static const struct bpf_func_proto *
 bpf_sk_base_func_proto(enum bpf_func_id func_id);
@@ -11272,6 +11273,20 @@ const struct bpf_func_proto bpf_skc_to_unix_sock_proto = {
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_UNIX],
 };
 
+BPF_CALL_1(bpf_skc_to_mptcp_sock, struct sock *, sk)
+{
+	BTF_TYPE_EMIT(struct mptcp_sock);
+	return (unsigned long)bpf_mptcp_sock_from_subflow(sk);
+}
+
+const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto = {
+	.func		= bpf_skc_to_mptcp_sock,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.ret_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_MPTCP],
+};
+
 BPF_CALL_1(bpf_sock_from_file, struct file *, file)
 {
 	return (unsigned long)sock_from_file(file);
@@ -11314,6 +11329,9 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_skc_to_unix_sock:
 		func = &bpf_skc_to_unix_sock_proto;
 		break;
+	case BPF_FUNC_skc_to_mptcp_sock:
+		func = &bpf_skc_to_mptcp_sock_proto;
+		break;
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile
index cb7f53f6ab22..6e7df47c9584 100644
--- a/net/mptcp/Makefile
+++ b/net/mptcp/Makefile
@@ -10,3 +10,5 @@ obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o
 mptcp_crypto_test-objs := crypto_test.o
 mptcp_token_test-objs := token_test.o
 obj-$(CONFIG_MPTCP_KUNIT_TEST) += mptcp_crypto_test.o mptcp_token_test.o
+
+obj-$(CONFIG_BPF_SYSCALL) += bpf.o
diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
new file mode 100644
index 000000000000..5a0a84ad94af
--- /dev/null
+++ b/net/mptcp/bpf.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2020, Tessares SA.
+ * Copyright (c) 2022, SUSE.
+ *
+ * Author: Nicolas Rybowski <nicolas.rybowski@tessares.net>
+ */
+
+#define pr_fmt(fmt) "MPTCP: " fmt
+
+#include <linux/bpf.h>
+#include "protocol.h"
+
+struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk)
+{
+	if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && sk_is_mptcp(sk))
+		return mptcp_sk(mptcp_subflow_ctx(sk)->conn);
+
+	return NULL;
+}
diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py
index 096625242475..d5452f7eb996 100755
--- a/scripts/bpf_doc.py
+++ b/scripts/bpf_doc.py
@@ -633,6 +633,7 @@ class PrinterHelpers(Printer):
             'struct socket',
             'struct file',
             'struct bpf_timer',
+            'struct mptcp_sock',
     ]
     known_types = {
             '...',
@@ -682,6 +683,7 @@ class PrinterHelpers(Printer):
             'struct socket',
             'struct file',
             'struct bpf_timer',
+            'struct mptcp_sock',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 444fe6f1cf35..3e996e097084 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5154,6 +5154,12 @@ union bpf_attr {
  *		if not NULL, is a reference which must be released using its
  *		corresponding release function, or moved into a BPF map before
  *		program exit.
+ *
+ * struct mptcp_sock *bpf_skc_to_mptcp_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *mptcp_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or **NULL** otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5351,6 +5357,7 @@ union bpf_attr {
 	FN(skb_set_tstamp),		\
 	FN(ima_file_hash),		\
 	FN(kptr_xchg),			\
+	FN(skc_to_mptcp_sock),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
2.34.1

[PATCH mptcp-next v2 2/7] selftests/bpf: Enable CONFIG_IKCONFIG_PROC in config

[Geliang Tang]

CONFIG_IKCONFIG_PROC is required by BPF selftests, otherwise we get
errors like this:

 libbpf: failed to open system Kconfig
 libbpf: failed to load object 'kprobe_multi'
 libbpf: failed to load BPF skeleton 'kprobe_multi': -22

It's because /proc/config.gz is opened in bpf_object__read_kconfig_file()
in tools/lib/bpf/libbpf.c:

        file = gzopen("/proc/config.gz", "r");

So this patch enables CONFIG_IKCONFIG and CONFIG_IKCONFIG_PROC in
tools/testing/selftests/bpf/config.

Suggested-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 tools/testing/selftests/bpf/config | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 763db63a3890..8d7faff33c54 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -53,3 +53,5 @@ CONFIG_NF_DEFRAG_IPV4=y
 CONFIG_NF_DEFRAG_IPV6=y
 CONFIG_NF_CONNTRACK=y
 CONFIG_USERFAULTFD=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
-- 
2.34.1

[PATCH mptcp-next v2 3/7] selftests/bpf: add MPTCP test base

[Geliang Tang]

From: Nicolas Rybowski <nicolas.rybowski@tessares.net>

This patch adds a base for MPTCP specific tests.

It is currently limited to the is_mptcp field in case of plain TCP
connection because there is no easy way to get the subflow sk from a msk
in userspace. This implies that we cannot lookup the sk_storage attached
to the subflow sk in the sockops program.

v4:
 - add copyright 2022 (Andrii)
 - use ASSERT_* instead of CHECK_FAIL (Andrii)
 - drop SEC("version") (Andrii)
 - use is_mptcp in tcp_sock, instead of bpf_tcp_sock (Martin & Andrii)

v5:
 - Drop connect_to_mptcp_fd (Martin)
 - Use BPF test skeleton (Andrii)
 - Use ASSERT_EQ (Andrii)
 - Drop the 'msg' parameter of verify_sk

Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Co-developed-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Nicolas Rybowski <nicolas.rybowski@tessares.net>
---
 MAINTAINERS                                   |   1 +
 tools/testing/selftests/bpf/bpf_tcp_helpers.h |   1 +
 tools/testing/selftests/bpf/config            |   1 +
 tools/testing/selftests/bpf/network_helpers.c |  40 +++++--
 tools/testing/selftests/bpf/network_helpers.h |   2 +
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 112 ++++++++++++++++++
 .../testing/selftests/bpf/progs/mptcp_sock.c  |  53 +++++++++
 7 files changed, 201 insertions(+), 9 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/mptcp.c
 create mode 100644 tools/testing/selftests/bpf/progs/mptcp_sock.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 69b597aa4bc7..00e29c9f8f5f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13799,6 +13799,7 @@ 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/net/mptcp/
 
 NETWORKING [TCP]
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index b1ede6f0b821..22e0c8849a17 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -81,6 +81,7 @@ 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)
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 8d7faff33c54..a25e15d55918 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -55,3 +55,4 @@ CONFIG_NF_CONNTRACK=y
 CONFIG_USERFAULTFD=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 @@ static int __start_server(int type, const struct sockaddr *addr,
 	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..7874d8264836
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -0,0 +1,112 @@
+// 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"
+
+struct mptcp_storage {
+	__u32 invoked;
+	__u32 is_mptcp;
+};
+
+static int verify_sk(int map_fd, int client_fd, __u32 is_mptcp)
+{
+	int err, cfd = client_fd;
+	struct mptcp_storage val;
+
+	if (is_mptcp == 1)
+		return 0;
+
+	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 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;
+
+	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_sk(map_fd, client_fd, 1) :
+			  verify_sk(map_fd, client_fd, 0);
+
+	close(client_fd);
+
+out:
+	mptcp_sock__destroy(sock_skel);
+	return err;
+}
+
+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..bc09dba0b078
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_sock.c
@@ -0,0 +1,53 @@
+// 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";
+
+struct mptcp_storage {
+	__u32 invoked;
+	__u32 is_mptcp;
+};
+
+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;
+	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;
+	storage = bpf_sk_storage_get(&socket_storage_map, sk, 0,
+				     BPF_SK_STORAGE_GET_F_CREATE);
+	if (!storage)
+		return 1;
+
+	storage->invoked++;
+	storage->is_mptcp = is_mptcp;
+
+	return 1;
+}
-- 
2.34.1

[PATCH mptcp-next v2 4/7] selftests/bpf: test bpf_skc_to_mptcp_sock

[Geliang Tang]

This patch extends the MPTCP test base, to test the new helper
bpf_skc_to_mptcp_sock().

Define struct mptcp_sock in bpf_tcp_helpers.h, use bpf_skc_to_mptcp_sock
to get the msk socket in progs/mptcp_sock.c and store the infos in
socket_storage_map.

Get the infos from socket_storage_map in prog_tests/mptcp.c. Add a new
function verify_msk() to verify the infos of MPTCP socket, and rename
verify_sk() to verify_tsk() to verify TCP socket only.

v2: Add CONFIG_MPTCP check for clearer error messages

v4:
 - use ASSERT_* instead of CHECK_FAIL (Andrii)
 - drop bpf_mptcp_helpers.h (Andrii)

v5:
 - some 'ASSERT_*' were replaced in the next commit by mistake.
 - Drop CONFIG_MPTCP (Martin)
 - Use ASSERT_EQ (Andrii)

Acked-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 tools/testing/selftests/bpf/bpf_tcp_helpers.h |  5 ++++
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 27 ++++++++++++++-----
 .../testing/selftests/bpf/progs/mptcp_sock.c  | 19 ++++++++++---
 3 files changed, 41 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 22e0c8849a17..90fecafc493d 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -226,4 +226,9 @@ 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;
+
+} __attribute__((preserve_access_index));
+
 #endif
diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 7874d8264836..6f333e3aba9c 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -12,14 +12,11 @@ struct mptcp_storage {
 	__u32 is_mptcp;
 };
 
-static int verify_sk(int map_fd, int client_fd, __u32 is_mptcp)
+static int verify_tsk(int map_fd, int client_fd)
 {
 	int err, cfd = client_fd;
 	struct mptcp_storage val;
 
-	if (is_mptcp == 1)
-		return 0;
-
 	err = bpf_map_lookup_elem(map_fd, &cfd, &val);
 	if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
 		return err;
@@ -33,6 +30,24 @@ static int verify_sk(int map_fd, int client_fd, __u32 is_mptcp)
 	return err;
 }
 
+static int verify_msk(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, 1, "unexpected is_mptcp"))
+		err++;
+
+	return err;
+}
+
 static int run_test(int cgroup_fd, int server_fd, bool is_mptcp)
 {
 	int client_fd, prog_fd, map_fd, err;
@@ -64,8 +79,8 @@ static int run_test(int cgroup_fd, int server_fd, bool is_mptcp)
 		goto out;
 	}
 
-	err += is_mptcp ? verify_sk(map_fd, client_fd, 1) :
-			  verify_sk(map_fd, client_fd, 0);
+	err += is_mptcp ? verify_msk(map_fd, client_fd) :
+			  verify_tsk(map_fd, client_fd);
 
 	close(client_fd);
 
diff --git a/tools/testing/selftests/bpf/progs/mptcp_sock.c b/tools/testing/selftests/bpf/progs/mptcp_sock.c
index bc09dba0b078..dc73b3fbb50b 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_sock.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_sock.c
@@ -24,6 +24,7 @@ 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;
@@ -41,11 +42,21 @@ int _sockops(struct bpf_sock_ops *ctx)
 		return 1;
 
 	is_mptcp = bpf_core_field_exists(tsk->is_mptcp) ? tsk->is_mptcp : 0;
-	storage = bpf_sk_storage_get(&socket_storage_map, sk, 0,
-				     BPF_SK_STORAGE_GET_F_CREATE);
-	if (!storage)
-		return 1;
+	if (!is_mptcp) {
+		storage = bpf_sk_storage_get(&socket_storage_map, sk, 0,
+					     BPF_SK_STORAGE_GET_F_CREATE);
+		if (!storage)
+			return 1;
+	} 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->invoked++;
 	storage->is_mptcp = is_mptcp;
 
-- 
2.34.1

[PATCH mptcp-next v2 5/7] selftests/bpf: verify token of struct mptcp_sock

[Geliang Tang]

This patch verifies the struct member token of struct mptcp_sock. Add a
new member token in struct mptcp_storage to store the token value of the
msk socket got by bpf_skc_to_mptcp_sock(). Trace the kernel function
mptcp_pm_new_connection() by using bpf fentry prog to obtain the msk token
and save it in a global bpf variable. Pass the variable to verify_msk() to
verify it with the token saved in socket_storage_map.

v4:
 - use ASSERT_* instead of CHECK_FAIL (Andrii)
 - skip the test if 'ip mptcp monitor' is not supported (Mat)

v5:
 - Drop 'ip mptcp monitor', trace mptcp_pm_new_connection instead(Martin)
 - Use ASSERT_EQ (Andrii)

Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Acked-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 tools/testing/selftests/bpf/bpf_tcp_helpers.h  |  1 +
 tools/testing/selftests/bpf/prog_tests/mptcp.c | 15 +++++++++++++--
 tools/testing/selftests/bpf/progs/mptcp_sock.c | 16 ++++++++++++++++
 3 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 90fecafc493d..422491872619 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -229,6 +229,7 @@ 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;
 } __attribute__((preserve_access_index));
 
 #endif
diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 6f333e3aba9c..138bcc80ab9e 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -10,6 +10,7 @@
 struct mptcp_storage {
 	__u32 invoked;
 	__u32 is_mptcp;
+	__u32 token;
 };
 
 static int verify_tsk(int map_fd, int client_fd)
@@ -30,11 +31,14 @@ static int verify_tsk(int map_fd, int client_fd)
 	return err;
 }
 
-static int verify_msk(int map_fd, int client_fd)
+static int verify_msk(int map_fd, int client_fd, __u32 token)
 {
 	int err, cfd = client_fd;
 	struct mptcp_storage val;
 
+	if (!ASSERT_GT(token, 0, "invalid token"))
+		return -1;
+
 	err = bpf_map_lookup_elem(map_fd, &cfd, &val);
 	if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
 		return err;
@@ -45,6 +49,9 @@ static int verify_msk(int map_fd, int client_fd)
 	if (!ASSERT_EQ(val.is_mptcp, 1, "unexpected is_mptcp"))
 		err++;
 
+	if (!ASSERT_EQ(val.token, token, "unexpected token"))
+		err++;
+
 	return err;
 }
 
@@ -57,6 +64,10 @@ static int run_test(int cgroup_fd, int server_fd, bool is_mptcp)
 	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;
@@ -79,7 +90,7 @@ static int run_test(int cgroup_fd, int server_fd, bool is_mptcp)
 		goto out;
 	}
 
-	err += is_mptcp ? verify_msk(map_fd, client_fd) :
+	err += is_mptcp ? verify_msk(map_fd, client_fd, sock_skel->bss->token) :
 			  verify_tsk(map_fd, client_fd);
 
 	close(client_fd);
diff --git a/tools/testing/selftests/bpf/progs/mptcp_sock.c b/tools/testing/selftests/bpf/progs/mptcp_sock.c
index dc73b3fbb50b..f038b0e699a2 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_sock.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_sock.c
@@ -7,10 +7,12 @@
 #include "bpf_tcp_helpers.h"
 
 char _license[] SEC("license") = "GPL";
+__u32 token = 0;
 
 struct mptcp_storage {
 	__u32 invoked;
 	__u32 is_mptcp;
+	__u32 token;
 };
 
 struct {
@@ -47,6 +49,8 @@ int _sockops(struct bpf_sock_ops *ctx)
 					     BPF_SK_STORAGE_GET_F_CREATE);
 		if (!storage)
 			return 1;
+
+		storage->token = 0;
 	} else {
 		msk = bpf_skc_to_mptcp_sock(sk);
 		if (!msk)
@@ -56,9 +60,21 @@ int _sockops(struct bpf_sock_ops *ctx)
 					     BPF_SK_STORAGE_GET_F_CREATE);
 		if (!storage)
 			return 1;
+
+		storage->token = msk->token;
 	}
 	storage->invoked++;
 	storage->is_mptcp = is_mptcp;
 
 	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;
+}
-- 
2.34.1

[PATCH mptcp-next v2 6/7] selftests/bpf: verify ca_name of struct mptcp_sock

[Geliang Tang]

This patch verifies another member of struct mptcp_sock, ca_name. Add a
new function get_msk_ca_name() to read the sysctl tcp_congestion_control
and verify it in verify_msk().

v3: Access the sysctl through the filesystem to avoid compatibility
    issues with the busybox sysctl command.
v4: use ASSERT_* instead of CHECK_FAIL (Andrii)

Acked-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 tools/testing/selftests/bpf/bpf_tcp_helpers.h |  5 +++
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 31 +++++++++++++++++++
 .../testing/selftests/bpf/progs/mptcp_sock.c  |  4 +++
 3 files changed, 40 insertions(+)

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 422491872619..c38c66d5c1e6 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 {
@@ -230,6 +234,7 @@ struct mptcp_sock {
 	struct inet_connection_sock	sk;
 
 	__u32		token;
+	char		ca_name[TCP_CA_NAME_MAX];
 } __attribute__((preserve_access_index));
 
 #endif
diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 138bcc80ab9e..17ad1cb07339 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -7,10 +7,15 @@
 #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;
 	__u32 token;
+	char ca_name[TCP_CA_NAME_MAX];
 };
 
 static int verify_tsk(int map_fd, int client_fd)
@@ -31,14 +36,37 @@ static int verify_tsk(int map_fd, int client_fd)
 	return err;
 }
 
+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;
@@ -52,6 +80,9 @@ static int verify_msk(int map_fd, int client_fd, __u32 token)
 	if (!ASSERT_EQ(val.token, token, "unexpected token"))
 		err++;
 
+	if (!ASSERT_STRNEQ(val.ca_name, ca_name, TCP_CA_NAME_MAX, "unexpected ca_name"))
+		err++;
+
 	return err;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/mptcp_sock.c b/tools/testing/selftests/bpf/progs/mptcp_sock.c
index f038b0e699a2..6a78e7b754a8 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_sock.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_sock.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2020, Tessares SA. */
 /* Copyright (c) 2022, SUSE. */
 
+#include <string.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include "bpf_tcp_helpers.h"
@@ -13,6 +14,7 @@ struct mptcp_storage {
 	__u32 invoked;
 	__u32 is_mptcp;
 	__u32 token;
+	char ca_name[TCP_CA_NAME_MAX];
 };
 
 struct {
@@ -51,6 +53,7 @@ int _sockops(struct bpf_sock_ops *ctx)
 			return 1;
 
 		storage->token = 0;
+		bzero(storage->ca_name, TCP_CA_NAME_MAX);
 	} else {
 		msk = bpf_skc_to_mptcp_sock(sk);
 		if (!msk)
@@ -62,6 +65,7 @@ int _sockops(struct bpf_sock_ops *ctx)
 			return 1;
 
 		storage->token = msk->token;
+		memcpy(storage->ca_name, msk->ca_name, TCP_CA_NAME_MAX);
 	}
 	storage->invoked++;
 	storage->is_mptcp = is_mptcp;
-- 
2.34.1

[PATCH mptcp-next v2 7/7] selftests/bpf: verify first of struct mptcp_sock

[Geliang Tang]

This patch verifies the 'first' struct member of struct mptcp_sock, which
points to the first subflow of msk. Save 'sk' in mptcp_storage, and verify
it with 'first' in verify_msk().

v5:
 - Use ASSERT_EQ.

Acked-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 tools/testing/selftests/bpf/bpf_tcp_helpers.h  | 1 +
 tools/testing/selftests/bpf/prog_tests/mptcp.c | 5 +++++
 tools/testing/selftests/bpf/progs/mptcp_sock.c | 5 +++++
 3 files changed, 11 insertions(+)

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index c38c66d5c1e6..82a7c9de95f9 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -234,6 +234,7 @@ struct mptcp_sock {
 	struct inet_connection_sock	sk;
 
 	__u32		token;
+	struct sock	*first;
 	char		ca_name[TCP_CA_NAME_MAX];
 } __attribute__((preserve_access_index));
 
diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 17ad1cb07339..257a8668ad40 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -14,7 +14,9 @@
 struct mptcp_storage {
 	__u32 invoked;
 	__u32 is_mptcp;
+	struct sock *sk;
 	__u32 token;
+	struct sock *first;
 	char ca_name[TCP_CA_NAME_MAX];
 };
 
@@ -80,6 +82,9 @@ static int verify_msk(int map_fd, int client_fd, __u32 token)
 	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++;
 
diff --git a/tools/testing/selftests/bpf/progs/mptcp_sock.c b/tools/testing/selftests/bpf/progs/mptcp_sock.c
index 6a78e7b754a8..f638cb876424 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_sock.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_sock.c
@@ -13,7 +13,9 @@ __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];
 };
 
@@ -54,6 +56,7 @@ int _sockops(struct bpf_sock_ops *ctx)
 
 		storage->token = 0;
 		bzero(storage->ca_name, TCP_CA_NAME_MAX);
+		storage->first = NULL;
 	} else {
 		msk = bpf_skc_to_mptcp_sock(sk);
 		if (!msk)
@@ -66,9 +69,11 @@ int _sockops(struct bpf_sock_ops *ctx)
 
 		storage->token = msk->token;
 		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;
 }
-- 
2.34.1

[PATCH mptcp-next v2] Squash to "selftests/bpf: add bpf_first test"

[Geliang Tang]

Drop connect_to_mptcp_fd, use connect_to_fd instead.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 tools/testing/selftests/bpf/prog_tests/mptcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 5a689e758ed0..9d37c509d3ce 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -268,7 +268,7 @@ static void test_first(void)
 
 	system("sysctl -qw net.mptcp.scheduler=bpf_first");
 	server_fd = start_mptcp_server(AF_INET, NULL, 0, 0);
-	client_fd = connect_to_mptcp_fd(server_fd, 0);
+	client_fd = connect_to_fd(server_fd, 0);
 
 	send_data(server_fd, client_fd);
 
-- 
2.34.1

Re: Squash to "selftests/bpf: add bpf_first test": Tests Results

[MPTCP CI]

Hi Geliang,

Thank you for your modifications, that's great!

Our CI did some validations and here is its report:

- KVM Validation: normal:
  - Unstable: 1 failed test(s): selftest_mptcp_join 🔴:
  - Task: https://cirrus-ci.com/task/6468726106095616
  - Summary: https://api.cirrus-ci.com/v1/artifact/task/6468726106095616/summary/summary.txt

- KVM Validation: debug:
  - Unstable: 2 failed test(s): selftest_diag selftest_mptcp_join 🔴:
  - Task: https://cirrus-ci.com/task/5373927668056064
  - Summary: https://api.cirrus-ci.com/v1/artifact/task/5373927668056064/summary/summary.txt

Initiator: Patchew Applier
Commits: https://github.com/multipath-tcp/mptcp_net-next/commits/7137300cca2a


If there are some issues, you can reproduce them using the same environment as
the one used by the CI thanks to a docker image, e.g.:

    $ cd [kernel source code]
    $ docker run -v "${PWD}:${PWD}:rw" -w "${PWD}" --privileged --rm -it \
        --pull always mptcp/mptcp-upstream-virtme-docker:latest \
        auto-debug

For more details:

    https://github.com/multipath-tcp/mptcp-upstream-virtme-docker


Please note that despite all the efforts that have been already done to have a
stable tests suite when executed on a public CI like here, it is possible some
reported issues are not due to your modifications. Still, do not hesitate to
help us improve that ;-)

Cheers,
MPTCP GH Action bot
Bot operated by Matthieu Baerts (Tessares)

Re: [PATCH mptcp-next v2 0/7] for bpf-next

[Matthieu Baerts]

Hi Geliang,

On 19/05/2022 10:25, Geliang Tang wrote:
> v2:
>  - The series is for bpf-next v5.
>  - patch 1, keep bpf_mptcp_sock_from_subflow() in bpf.c
>  - patch 3, Drop the 'msg' parameter of verify_sk
>  - base-commit: df896c77f02a ("DO-NOT-MERGE: git markup: features
> net-next-next"), export/20220517T155019
>  - The last squash-to patch is for "BPF packet scheduler" series.

I just imported this new series in our tree.

- 7046a98c4501: "squashed" patch 1/7 in "bpf: add
bpf_skc_to_mptcp_sock_proto"
- dc043d25d647: "squashed" patch 2/7 in "selftests/bpf: Enable
CONFIG_IKCONFIG_PROC in config"
- bd3e6e2ffc15: "squashed" patch 3/7 in "selftests/bpf: add MPTCP test base"
- efa55efc427c: "squashed" patch 4/7 in "selftests/bpf: test
bpf_skc_to_mptcp_sock"
- f087e13912ad: "squashed" patch 5/7 in "selftests/bpf: verify token of
struct mptcp_sock"
- 21c0f634b797: "squashed" patch 6/7 in "selftests/bpf: verify ca_name
of struct mptcp_sock"
- d38ab51eb84e: "squashed" patch 7/7 in "selftests/bpf: verify first of
struct mptcp_sock"
- c79872213ec4: conflict in t/selftests-bpf-add-bpf_first-test
- Results: 9ceda99ef71f..5fbf0e7a331f (export)

- 4353cb87928e: "squashed" in "selftests/bpf: add bpf_first test"
- Results: 5fbf0e7a331f..086d4a4a0f34 (export)

Builds and tests are now in progress:



https://cirrus-ci.com/github/multipath-tcp/mptcp_net-next/export/20220519T141104

https://github.com/multipath-tcp/mptcp_net-next/actions/workflows/build-validation.yml?query=branch:export

Cheers,
Matt
-- 
Tessares | Belgium | Hybrid Access Solutions
www.tessares.net

[PATCH mptcp-next v2] selftests/bpf: use random netns name for mptcp

[Geliang Tang]

This patch moves the netns operations code from subtest function
test_base() to the main test function test_mptcp(), then this dedicated
test netns can be used for all the subtests. Other subtests will be
added later.

Use rand() to generate a random netns name instead of using the fixed
name "mptcp_ns" for every test.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
This patch should be merged before the commit "mptcp: refactor push_pending logic".
---
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 32 ++++++++++---------
 1 file changed, 17 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index cd0c42fff7c0..d989613c821d 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -7,8 +7,6 @@
 #include "network_helpers.h"
 #include "mptcp_sock.skel.h"
 
-#define NS_TEST "mptcp_ns"
-
 #ifndef TCP_CA_NAME_MAX
 #define TCP_CA_NAME_MAX	16
 #endif
@@ -140,20 +138,12 @@ static int run_test(int cgroup_fd, int server_fd, bool is_mptcp)
 
 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;
 
-	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"))
-		goto fail;
-
 	/* without MPTCP */
 	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
 	if (!ASSERT_GE(server_fd, 0, "start_server"))
@@ -174,16 +164,28 @@ static void test_base(void)
 	close(server_fd);
 
 fail:
-	if (nstoken)
-		close_netns(nstoken);
-
-	SYS_NOFAIL("ip netns del " NS_TEST " &> /dev/null");
-
 	close(cgroup_fd);
 }
 
 void test_mptcp(void)
 {
+	struct nstoken *nstoken = NULL;
+	char NS_TEST[32] = { 0 };
+
+	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"))
+		goto fail;
+
 	if (test__start_subtest("base"))
 		test_base();
+
+	if (nstoken)
+		close_netns(nstoken);
+fail:
+	SYS_NOFAIL("ip netns del %s &> /dev/null", NS_TEST);
 }
-- 
2.35.3

[PATCH mptcp-next v2] Squash to "selftests/bpf: Add bpf_first test"

[Geliang Tang]

Run mptcp sched test in a dedicated netns.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 50 ++++++++-----------
 1 file changed, 22 insertions(+), 28 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 77a6997fc82f..bea9c799a531 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -253,40 +253,34 @@ static void send_data(int lfd, int fd)
 #define ADDR_1	"10.0.1.1"
 #define ADDR_2	"10.0.1.2"
 
-static void sched_init(char *flags, char *sched)
+static void sched_init(char *ns, char *flags, char *sched)
 {
-	char cmd[64];
-
-	system("ip link add veth1 type veth peer name veth2");
-	snprintf(cmd, sizeof(cmd), "ip addr add %s/24 dev veth1", ADDR_1);
-	system(cmd);
-	system("ip link set veth1 up");
-	snprintf(cmd, sizeof(cmd), "ip addr add %s/24 dev veth2", ADDR_2);
-	system(cmd);
-	system("ip link set veth2 up");
-
-	snprintf(cmd, sizeof(cmd), "ip mptcp endpoint add %s %s", ADDR_2, flags);
-	system(cmd);
-	snprintf(cmd, sizeof(cmd), "sysctl -qw net.mptcp.scheduler=%s", sched);
-	system(cmd);
+	SYS_NOFAIL("ip -net %s link add veth1 type veth peer name veth2", ns);
+	SYS_NOFAIL("ip -net %s addr add %s/24 dev veth1", ns, ADDR_1);
+	SYS_NOFAIL("ip -net %s link set dev veth1 up", ns);
+	SYS_NOFAIL("ip -net %s addr add %s/24 dev veth2", ns, ADDR_2);
+	SYS_NOFAIL("ip -net %s link set dev veth2 up", ns);
+	SYS_NOFAIL("ip -net %s mptcp endpoint add %s %s", ns, ADDR_2, flags);
+	SYS_NOFAIL("ip netns exec %s sysctl -qw net.mptcp.scheduler=%s", ns, sched);
 }
 
-static void sched_cleanup(void)
+static void sched_cleanup(char *ns)
 {
-	system("sysctl -qw net.mptcp.scheduler=default");
-	system("ip mptcp endpoint flush");
-	system("ip link del veth1");
+	SYS_NOFAIL("ip netns exec %s sysctl -qw net.mptcp.scheduler=default", ns);
+	SYS_NOFAIL("ip -net %s mptcp endpoint flush", ns);
+	SYS_NOFAIL("ip -net %s link del veth1", ns);
 }
 
-static int has_bytes_sent(char *addr)
+static int has_bytes_sent(char *ns, char *addr)
 {
-	char cmd[64];
+	char cmd[128];
 
-	snprintf(cmd, sizeof(cmd), "ss -it dst %s | grep -q 'bytes_sent:'", addr);
+	snprintf(cmd, sizeof(cmd), "ip netns exec %s ss -it dst %s | grep -q bytes_sent:",
+		 ns, addr);
 	return system(cmd);
 }
 
-static void test_first(void)
+static void test_first(char *ns)
 {
 	struct mptcp_bpf_first *first_skel;
 	int server_fd, client_fd;
@@ -302,17 +296,17 @@ static void test_first(void)
 		return;
 	}
 
-	sched_init("subflow", "bpf_first");
+	sched_init(ns, "subflow", "bpf_first");
 	server_fd = start_mptcp_server(AF_INET, ADDR_1, 0, 0);
 	client_fd = connect_to_fd(server_fd, 0);
 
 	send_data(server_fd, client_fd);
-	ASSERT_OK(has_bytes_sent(ADDR_1), "has_bytes_sent addr_1");
-	ASSERT_GT(has_bytes_sent(ADDR_2), 0, "has_bytes_sent addr_2");
+	ASSERT_OK(has_bytes_sent(ns, ADDR_1), "has_bytes_sent addr_1");
+	ASSERT_GT(has_bytes_sent(ns, ADDR_2), 0, "has_bytes_sent addr_2");
 
 	close(client_fd);
 	close(server_fd);
-	sched_cleanup();
+	sched_cleanup(ns);
 	bpf_link__destroy(link);
 	mptcp_bpf_first__destroy(first_skel);
 }
@@ -334,7 +328,7 @@ void test_mptcp(void)
 	if (test__start_subtest("base"))
 		test_base();
 	if (test__start_subtest("first"))
-		test_first();
+		test_first(NS_TEST);
 
 	if (nstoken)
 		close_netns(nstoken);
-- 
2.35.3

Re: [PATCH mptcp-next v2] Squash to "selftests/bpf: Add bpf_first test"

[Matthieu Baerts]

Hi Geliang,

On 17/05/2023 10:40, Geliang Tang wrote:
> Run mptcp sched test in a dedicated netns.
> 
> Signed-off-by: Geliang Tang <geliang.tang@suse.com>
> ---
>  .../testing/selftests/bpf/prog_tests/mptcp.c  | 50 ++++++++-----------
>  1 file changed, 22 insertions(+), 28 deletions(-)
> 
> diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
> index 77a6997fc82f..bea9c799a531 100644
> --- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
> +++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
> @@ -253,40 +253,34 @@ static void send_data(int lfd, int fd)
>  #define ADDR_1	"10.0.1.1"
>  #define ADDR_2	"10.0.1.2"
>  
> -static void sched_init(char *flags, char *sched)
> +static void sched_init(char *ns, char *flags, char *sched)

I think it is cleaner to use a new netns for each test: by doing that,
we are sure to start from a fresh and controlled environment just in
case something wrong happened with the previous test. No?

So in the sched_init(), the netns is created and in sched_cleanup(), the
netns is destroyed (and no need to do anything else I guess).

I guess you can also simply use a helper to create the netns and set
NS_TEST which would be a "global" variable. WDYT?

>  {
> -	char cmd[64];
> -
> -	system("ip link add veth1 type veth peer name veth2");
> -	snprintf(cmd, sizeof(cmd), "ip addr add %s/24 dev veth1", ADDR_1);
> -	system(cmd);
> -	system("ip link set veth1 up");
> -	snprintf(cmd, sizeof(cmd), "ip addr add %s/24 dev veth2", ADDR_2);
> -	system(cmd);
> -	system("ip link set veth2 up");
> -
> -	snprintf(cmd, sizeof(cmd), "ip mptcp endpoint add %s %s", ADDR_2, flags);
> -	system(cmd);
> -	snprintf(cmd, sizeof(cmd), "sysctl -qw net.mptcp.scheduler=%s", sched);
> -	system(cmd);
> +	SYS_NOFAIL("ip -net %s link add veth1 type veth peer name veth2", ns);
> +	SYS_NOFAIL("ip -net %s addr add %s/24 dev veth1", ns, ADDR_1);
> +	SYS_NOFAIL("ip -net %s link set dev veth1 up", ns);
> +	SYS_NOFAIL("ip -net %s addr add %s/24 dev veth2", ns, ADDR_2);
> +	SYS_NOFAIL("ip -net %s link set dev veth2 up", ns);
> +	SYS_NOFAIL("ip -net %s mptcp endpoint add %s %s", ns, ADDR_2, flags);
> +	SYS_NOFAIL("ip netns exec %s sysctl -qw net.mptcp.scheduler=%s", ns, sched);

Why not using SYS() instead? By doing that, the test will be marked as
failed if one of these commands fails.

You just need to add:

  fail:
          return;

at the end I guess.

>  }
>  
> -static void sched_cleanup(void)
> +static void sched_cleanup(char *ns)>  {
> -	system("sysctl -qw net.mptcp.scheduler=default");
> -	system("ip mptcp endpoint flush");
> -	system("ip link del veth1");
> +	SYS_NOFAIL("ip netns exec %s sysctl -qw net.mptcp.scheduler=default", ns);
> +	SYS_NOFAIL("ip -net %s mptcp endpoint flush", ns);
> +	SYS_NOFAIL("ip -net %s link del veth1", ns);

Same here with SYS() to catch unexpected behaviours.

(but see above, maybe enough to just close nstoken and delete the netns)

Cheers,
Matt
-- 
Tessares | Belgium | Hybrid Access Solutions
www.tessares.net