[PATCH mptcp-next 00/15] update bpf patches on export branch

[PATCH mptcp-next 00/15] update bpf patches on export branch

[Geliang Tang]

- drop bpf_mptcp_helpers.h (Andrii)
- patch 6, skip the test if 'ip mptcp monitor' is not supported (Mat)

base-commit: bcf89bc9c28e ("DO-NOT-MERGE: git markup: features
net-next-next") on export/20220510T054929

Geliang Tang (13):
  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
  mptcp: add struct mptcp_sched_ops
  mptcp: add a new sysctl scheduler
  mptcp: add sched in mptcp_sock
  mptcp: add get_subflow wrappers
  mptcp: add bpf_mptcp_sched_ops
  selftests/bpf: add bpf_first scheduler
  selftests/bpf: add bpf_first test

Nicolas Rybowski (2):
  bpf: expose is_mptcp flag to bpf_tcp_sock
  selftests/bpf: add MPTCP test base

 Documentation/networking/mptcp-sysctl.rst     |   8 +
 MAINTAINERS                                   |   1 +
 include/linux/bpf.h                           |   1 +
 include/linux/btf_ids.h                       |   3 +-
 include/net/mptcp.h                           |  25 ++
 include/uapi/linux/bpf.h                      |   8 +
 kernel/bpf/bpf_struct_ops_types.h             |   4 +
 kernel/bpf/verifier.c                         |   1 +
 kernel/trace/bpf_trace.c                      |   2 +
 net/core/filter.c                             |  27 +-
 net/mptcp/Makefile                            |   4 +-
 net/mptcp/bpf.c                               | 175 ++++++++
 net/mptcp/ctrl.c                              |  14 +
 net/mptcp/protocol.c                          |  32 +-
 net/mptcp/protocol.h                          |  12 +
 net/mptcp/sched.c                             | 141 +++++++
 scripts/bpf_doc.py                            |   2 +
 tools/include/uapi/linux/bpf.h                |   8 +
 tools/testing/selftests/bpf/bpf_tcp_helpers.h |  31 ++
 tools/testing/selftests/bpf/config            |   3 +
 tools/testing/selftests/bpf/network_helpers.c |  43 +-
 tools/testing/selftests/bpf/network_helpers.h |   4 +
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 378 ++++++++++++++++++
 .../selftests/bpf/progs/mptcp_bpf_first.c     |  32 ++
 .../testing/selftests/bpf/progs/mptcp_sock.c  |  80 ++++
 25 files changed, 1009 insertions(+), 30 deletions(-)
 create mode 100644 net/mptcp/bpf.c
 create mode 100644 net/mptcp/sched.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/mptcp.c
 create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
 create mode 100644 tools/testing/selftests/bpf/progs/mptcp_sock.c

-- 
2.34.1

[PATCH mptcp-next 01/15] bpf: expose is_mptcp flag to bpf_tcp_sock

[Geliang Tang]

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

is_mptcp is a field from struct tcp_sock used to indicate that the
current tcp_sock is part of the MPTCP protocol.

In this protocol, a first socket (mptcp_sock) is created with
sk_protocol set to IPPROTO_MPTCP (=262) for control purpose but it
isn't directly on the wire. This is the role of the subflow (kernel)
sockets which are classical tcp_sock with sk_protocol set to
IPPROTO_TCP. The only way to differentiate such sockets from plain TCP
sockets is the is_mptcp field from tcp_sock.

Such an exposure in BPF is thus required to be able to differentiate
plain TCP sockets from MPTCP subflow sockets in BPF_PROG_TYPE_SOCK_OPS
programs.

The choice has been made to silently pass the case when CONFIG_MPTCP is
unset by defaulting is_mptcp to 0 in order to make BPF independent of
the MPTCP configuration. Another solution is to make the verifier fail
in 'bpf_tcp_sock_is_valid_ctx_access' but this will add an additional
'#ifdef CONFIG_MPTCP' in the BPF code and a same injected BPF program
will not run if MPTCP is not set.

An example use-case is provided in
https://github.com/multipath-tcp/mptcp_net-next/tree/scripts/bpf/examples

Suggested-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Acked-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Nicolas Rybowski <nicolas.rybowski@tessares.net>
---
 include/uapi/linux/bpf.h       | 1 +
 net/core/filter.c              | 9 ++++++++-
 tools/include/uapi/linux/bpf.h | 1 +
 3 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 444fe6f1cf35..7043f3641534 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5706,6 +5706,7 @@ struct bpf_tcp_sock {
 	__u32 delivered;	/* Total data packets delivered incl. rexmits */
 	__u32 delivered_ce;	/* Like the above but only ECE marked packets */
 	__u32 icsk_retransmits;	/* Number of unrecovered [RTO] timeouts */
+	__u32 is_mptcp;		/* Is MPTCP subflow? */
 };
 
 struct bpf_sock_tuple {
diff --git a/net/core/filter.c b/net/core/filter.c
index b741b9f7e6a9..b474e5bd1458 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6754,7 +6754,7 @@ bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 				  struct bpf_insn_access_aux *info)
 {
 	if (off < 0 || off >= offsetofend(struct bpf_tcp_sock,
-					  icsk_retransmits))
+					  is_mptcp))
 		return false;
 
 	if (off % size != 0)
@@ -6888,6 +6888,13 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct bpf_tcp_sock, icsk_retransmits):
 		BPF_INET_SOCK_GET_COMMON(icsk_retransmits);
 		break;
+	case offsetof(struct bpf_tcp_sock, is_mptcp):
+#ifdef CONFIG_MPTCP
+		BPF_TCP_SOCK_GET_COMMON(is_mptcp);
+#else
+		*insn++ = BPF_MOV32_IMM(si->dst_reg, 0);
+#endif
+		break;
 	}
 
 	return insn - insn_buf;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 444fe6f1cf35..7043f3641534 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5706,6 +5706,7 @@ struct bpf_tcp_sock {
 	__u32 delivered;	/* Total data packets delivered incl. rexmits */
 	__u32 delivered_ce;	/* Like the above but only ECE marked packets */
 	__u32 icsk_retransmits;	/* Number of unrecovered [RTO] timeouts */
+	__u32 is_mptcp;		/* Is MPTCP subflow? */
 };
 
 struct bpf_sock_tuple {
-- 
2.34.1

[PATCH mptcp-next 02/15] 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

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                | 22 ++++++++++++++++++++++
 scripts/bpf_doc.py             |  2 ++
 tools/include/uapi/linux/bpf.h |  7 +++++++
 11 files changed, 70 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 7043f3641534..56a66778dc28 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 b474e5bd1458..b39e4af9a0ec 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);
@@ -11279,6 +11280,20 @@ 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);
@@ -11321,6 +11336,9 @@ 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..535602ba2582
--- /dev/null
+++ b/net/mptcp/bpf.c
@@ -0,0 +1,22 @@
+// 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;
+}
+EXPORT_SYMBOL(bpf_mptcp_sock_from_subflow);
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 7043f3641534..56a66778dc28 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 03/15] 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 04/15] 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)

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/config            |   1 +
 tools/testing/selftests/bpf/network_helpers.c |  43 ++++--
 tools/testing/selftests/bpf/network_helpers.h |   4 +
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 136 ++++++++++++++++++
 .../testing/selftests/bpf/progs/mptcp_sock.c  |  50 +++++++
 6 files changed, 227 insertions(+), 8 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 0ea12c2b53f3..fe03a22d7fe1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13798,6 +13798,7 @@ 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/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..c9a2e39e34fc 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;
@@ -265,7 +282,7 @@ 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, opts->protocol);
 	if (fd < 0) {
 		log_err("Failed to create client socket");
 		return -1;
@@ -298,6 +315,16 @@ int connect_to_fd(int server_fd, int timeout_ms)
 	return connect_to_fd_opts(server_fd, &opts);
 }
 
+int connect_to_mptcp_fd(int server_fd, int timeout_ms)
+{
+	struct network_helper_opts opts = {
+		.timeout_ms = timeout_ms,
+		.protocol = IPPROTO_MPTCP,
+	};
+
+	return connect_to_fd_opts(server_fd, &opts);
+}
+
 int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms)
 {
 	struct sockaddr_storage addr;
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index a4b3b2f9877b..e0feb115b2ae 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -21,6 +21,7 @@ struct network_helper_opts {
 	const char *cc;
 	int timeout_ms;
 	bool must_fail;
+	int protocol;
 };
 
 /* ipv4 test vector */
@@ -42,11 +43,14 @@ 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);
 void free_fds(int *fds, unsigned int nr_close_fds);
 int connect_to_fd(int server_fd, int timeout_ms);
+int connect_to_mptcp_fd(int server_fd, int timeout_ms);
 int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts);
 int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms);
 int fastopen_connect(int server_fd, const char *data, unsigned int data_len,
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..cb0389ca8690
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -0,0 +1,136 @@
+// 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"
+
+struct mptcp_storage {
+	__u32 invoked;
+	__u32 is_mptcp;
+};
+
+static int verify_sk(int map_fd, int client_fd, const char *msg, __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 (val.invoked != 1) {
+		log_err("%s: unexpected invoked count %d != 1",
+			msg, val.invoked);
+		err++;
+	}
+
+	if (val.is_mptcp != 0) {
+		log_err("%s: unexpected bpf_tcp_sock.is_mptcp %d != 0",
+			msg, val.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 bpf_program *prog;
+	struct bpf_object *obj;
+	struct bpf_map *map;
+
+	obj = bpf_object__open("./mptcp_sock.o");
+	if (libbpf_get_error(obj))
+		return -EIO;
+
+	err = bpf_object__load(obj);
+	if (!ASSERT_OK(err, "bpf_object__load"))
+		goto out;
+
+	prog = bpf_object__find_program_by_name(obj, "_sockops");
+	if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name")) {
+		err = -EIO;
+		goto out;
+	}
+
+	prog_fd = bpf_program__fd(prog);
+	if (!ASSERT_GE(prog_fd, 0, "bpf_program__fd")) {
+		err = -EIO;
+		goto out;
+	}
+
+	map = bpf_object__find_map_by_name(obj, "socket_storage_map");
+	if (!ASSERT_OK_PTR(map, "bpf_object__find_map_by_name")) {
+		err = -EIO;
+		goto out;
+	}
+
+	map_fd = bpf_map__fd(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 = is_mptcp ? connect_to_mptcp_fd(server_fd, 0) :
+			       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, "MPTCP subflow socket", 1) :
+			  verify_sk(map_fd, client_fd, "plain TCP socket", 0);
+
+	close(client_fd);
+
+out:
+	bpf_object__close(obj);
+	return err;
+}
+
+void test_base(void)
+{
+	int server_fd, cgroup_fd;
+
+	cgroup_fd = test__join_cgroup("/mptcp");
+	if (CHECK_FAIL(cgroup_fd < 0))
+		return;
+
+	/* without MPTCP */
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
+	if (CHECK_FAIL(server_fd < 0))
+		goto with_mptcp;
+
+	CHECK_FAIL(run_test(cgroup_fd, server_fd, false));
+
+	close(server_fd);
+
+with_mptcp:
+	/* with MPTCP */
+	server_fd = start_mptcp_server(AF_INET, NULL, 0, 0);
+	if (CHECK_FAIL(server_fd < 0))
+		goto close_cgroup_fd;
+
+	CHECK_FAIL(run_test(cgroup_fd, server_fd, true));
+
+	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..19f5f8a183f5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_sock.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020, Tessares SA. */
+/* Copyright (c) 2022, SUSE. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_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;
+	struct bpf_tcp_sock *tcp_sk;
+	int op = (int)ctx->op;
+	struct bpf_sock *sk;
+
+	if (op != BPF_SOCK_OPS_TCP_CONNECT_CB)
+		return 1;
+
+	sk = ctx->sk;
+	if (!sk)
+		return 1;
+
+	tcp_sk = bpf_tcp_sock(sk);
+	if (!tcp_sk)
+		return 1;
+
+	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 = tcp_sk->is_mptcp;
+
+	return 1;
+}
-- 
2.34.1

[PATCH mptcp-next 05/15] 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)

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  | 45 ++++++++++++++-----
 .../testing/selftests/bpf/progs/mptcp_sock.c  | 24 ++++++++--
 3 files changed, 59 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index b1ede6f0b821..a43b1afe22bd 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -225,4 +225,9 @@ 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 cb0389ca8690..02e7fd8918e6 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -11,14 +11,12 @@ struct mptcp_storage {
 	__u32 is_mptcp;
 };
 
-static int verify_sk(int map_fd, int client_fd, const char *msg, __u32 is_mptcp)
+static int verify_tsk(int map_fd, int client_fd)
 {
+	char *msg = "plain TCP socket";
 	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;
@@ -38,6 +36,31 @@ static int verify_sk(int map_fd, int client_fd, const char *msg, __u32 is_mptcp)
 	return err;
 }
 
+static int verify_msk(int map_fd, int client_fd)
+{
+	char *msg = "MPTCP subflow socket";
+	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 (val.invoked != 1) {
+		log_err("%s: unexpected invoked count %d != 1",
+			msg, val.invoked);
+		err++;
+	}
+
+	if (val.is_mptcp != 1) {
+		log_err("%s: unexpected bpf_tcp_sock.is_mptcp %d != 1",
+			msg, val.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;
@@ -88,8 +111,8 @@ static int run_test(int cgroup_fd, int server_fd, bool is_mptcp)
 		goto out;
 	}
 
-	err += is_mptcp ? verify_sk(map_fd, client_fd, "MPTCP subflow socket", 1) :
-			  verify_sk(map_fd, client_fd, "plain TCP socket", 0);
+	err += is_mptcp ? verify_msk(map_fd, client_fd) :
+			  verify_tsk(map_fd, client_fd);
 
 	close(client_fd);
 
@@ -103,25 +126,25 @@ void test_base(void)
 	int server_fd, cgroup_fd;
 
 	cgroup_fd = test__join_cgroup("/mptcp");
-	if (CHECK_FAIL(cgroup_fd < 0))
+	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
 		return;
 
 	/* without MPTCP */
 	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
-	if (CHECK_FAIL(server_fd < 0))
+	if (!ASSERT_GE(server_fd, 0, "start_server"))
 		goto with_mptcp;
 
-	CHECK_FAIL(run_test(cgroup_fd, server_fd, false));
+	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 (CHECK_FAIL(server_fd < 0))
+	if (!ASSERT_GE(server_fd, 0, "start_mptcp_server"))
 		goto close_cgroup_fd;
 
-	CHECK_FAIL(run_test(cgroup_fd, server_fd, true));
+	ASSERT_OK(run_test(cgroup_fd, server_fd, true), "run_test mptcp");
 
 	close(server_fd);
 
diff --git a/tools/testing/selftests/bpf/progs/mptcp_sock.c b/tools/testing/selftests/bpf/progs/mptcp_sock.c
index 19f5f8a183f5..dd2448d1e7fc 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_sock.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_sock.c
@@ -4,8 +4,10 @@
 
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_tcp_helpers.h"
 
 char _license[] SEC("license") = "GPL";
+extern bool CONFIG_MPTCP __kconfig;
 
 struct mptcp_storage {
 	__u32 invoked;
@@ -24,6 +26,7 @@ int _sockops(struct bpf_sock_ops *ctx)
 {
 	struct mptcp_storage *storage;
 	struct bpf_tcp_sock *tcp_sk;
+	struct mptcp_sock *msk;
 	int op = (int)ctx->op;
 	struct bpf_sock *sk;
 
@@ -38,11 +41,24 @@ int _sockops(struct bpf_sock_ops *ctx)
 	if (!tcp_sk)
 		return 1;
 
-	storage = bpf_sk_storage_get(&socket_storage_map, sk, 0,
-				     BPF_SK_STORAGE_GET_F_CREATE);
-	if (!storage)
-		return 1;
+	if (!tcp_sk->is_mptcp) {
+		storage = bpf_sk_storage_get(&socket_storage_map, sk, 0,
+					     BPF_SK_STORAGE_GET_F_CREATE);
+		if (!storage)
+			return 1;
+	} else {
+		if (!CONFIG_MPTCP)
+			return 1;
+
+		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 = tcp_sk->is_mptcp;
 
-- 
2.34.1

[PATCH mptcp-next 06/15] selftests/bpf: verify token of struct mptcp_sock

[Geliang Tang]

This patch verifies the struct member token of struct mptcp_sock. Add a
new function get_msk_token() to parse the msk token from the output of
the command 'ip mptcp monitor', and verify it in verify_msk().

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

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 +
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 64 +++++++++++++++++++
 .../testing/selftests/bpf/progs/mptcp_sock.c  |  5 ++
 3 files changed, 70 insertions(+)

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index a43b1afe22bd..eee49cca092a 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -228,6 +228,7 @@ 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 02e7fd8918e6..ac98aa314123 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -9,8 +9,11 @@
 struct mptcp_storage {
 	__u32 invoked;
 	__u32 is_mptcp;
+	__u32 token;
 };
 
+static char monitor_log_path[64];
+
 static int verify_tsk(int map_fd, int client_fd)
 {
 	char *msg = "plain TCP socket";
@@ -36,11 +39,52 @@ static int verify_tsk(int map_fd, int client_fd)
 	return err;
 }
 
+/*
+ * Parse the token from the output of 'ip mptcp monitor':
+ *
+ * [       CREATED] token=3ca933d3 remid=0 locid=0 saddr4=127.0.0.1 ...
+ * [       CREATED] token=2ab57040 remid=0 locid=0 saddr4=127.0.0.1 ...
+ */
+static __u32 get_msk_token(void)
+{
+	char *prefix = "[       CREATED] token=";
+	char buf[BUFSIZ] = {};
+	__u32 token = 0;
+	ssize_t len;
+	int fd;
+
+	sync();
+
+	fd = open(monitor_log_path, O_RDONLY);
+	if (!ASSERT_GE(fd, 0, "Failed to open monitor_log_path"))
+		return token;
+
+	len = read(fd, buf, sizeof(buf));
+	if (!ASSERT_GT(len, 0, "Failed to read monitor_log_path"))
+		goto err;
+
+	if (strncmp(buf, prefix, strlen(prefix))) {
+		log_err("Invalid prefix %s", buf);
+		goto err;
+	}
+
+	token = strtol(buf + strlen(prefix), NULL, 16);
+
+err:
+	close(fd);
+	return token;
+}
+
 static int verify_msk(int map_fd, int client_fd)
 {
 	char *msg = "MPTCP subflow socket";
 	int err, cfd = client_fd;
 	struct mptcp_storage val;
+	__u32 token;
+
+	token = get_msk_token();
+	if (!ASSERT_GT(token, 0, "Unexpected token"))
+		return -1;
 
 	err = bpf_map_lookup_elem(map_fd, &cfd, &val);
 	if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
@@ -58,6 +102,12 @@ static int verify_msk(int map_fd, int client_fd)
 		err++;
 	}
 
+	if (val.token != token) {
+		log_err("Unexpected mptcp_sock.token %x != %x",
+			val.token, token);
+		err++;
+	}
+
 	return err;
 }
 
@@ -123,6 +173,7 @@ static int run_test(int cgroup_fd, int server_fd, bool is_mptcp)
 
 void test_base(void)
 {
+	char cmd[256], tmp_dir[] = "/tmp/XXXXXX";
 	int server_fd, cgroup_fd;
 
 	cgroup_fd = test__join_cgroup("/mptcp");
@@ -140,6 +191,17 @@ void test_base(void)
 
 with_mptcp:
 	/* with MPTCP */
+	if (system("ip mptcp help 2>&1 | grep -q monitor")) {
+		test__skip();
+		goto close_cgroup_fd;
+	}
+	if (!ASSERT_OK_PTR(mkdtemp(tmp_dir), "mkdtemp"))
+		goto close_cgroup_fd;
+	snprintf(monitor_log_path, sizeof(monitor_log_path),
+		 "%s/ip_mptcp_monitor", tmp_dir);
+	snprintf(cmd, sizeof(cmd), "ip mptcp monitor > %s &", monitor_log_path);
+	if (!ASSERT_OK(system(cmd), "ip mptcp monitor"))
+		goto close_cgroup_fd;
 	server_fd = start_mptcp_server(AF_INET, NULL, 0, 0);
 	if (!ASSERT_GE(server_fd, 0, "start_mptcp_server"))
 		goto close_cgroup_fd;
@@ -147,6 +209,8 @@ void test_base(void)
 	ASSERT_OK(run_test(cgroup_fd, server_fd, true), "run_test mptcp");
 
 	close(server_fd);
+	snprintf(cmd, sizeof(cmd), "rm -rf %s", tmp_dir);
+	system(cmd);
 
 close_cgroup_fd:
 	close(cgroup_fd);
diff --git a/tools/testing/selftests/bpf/progs/mptcp_sock.c b/tools/testing/selftests/bpf/progs/mptcp_sock.c
index dd2448d1e7fc..2a0decd78a0d 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_sock.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_sock.c
@@ -12,6 +12,7 @@ extern bool CONFIG_MPTCP __kconfig;
 struct mptcp_storage {
 	__u32 invoked;
 	__u32 is_mptcp;
+	__u32 token;
 };
 
 struct {
@@ -46,6 +47,8 @@ int _sockops(struct bpf_sock_ops *ctx)
 					     BPF_SK_STORAGE_GET_F_CREATE);
 		if (!storage)
 			return 1;
+
+		storage->token = 0;
 	} else {
 		if (!CONFIG_MPTCP)
 			return 1;
@@ -58,6 +61,8 @@ 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 = tcp_sk->is_mptcp;
-- 
2.34.1

[PATCH mptcp-next 07/15] 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  | 34 +++++++++++++++++++
 .../testing/selftests/bpf/progs/mptcp_sock.c  |  4 +++
 3 files changed, 43 insertions(+)

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index eee49cca092a..f882915b2553 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 {
@@ -229,6 +233,7 @@ 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 ac98aa314123..2ff7f18ea0ce 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -6,10 +6,15 @@
 #include "cgroup_helpers.h"
 #include "network_helpers.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 char monitor_log_path[64];
@@ -75,17 +80,40 @@ static __u32 get_msk_token(void)
 	return token;
 }
 
+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)
 {
 	char *msg = "MPTCP subflow socket";
 	int err, cfd = client_fd;
 	struct mptcp_storage val;
+	char ca_name[TCP_CA_NAME_MAX];
 	__u32 token;
 
 	token = get_msk_token();
 	if (!ASSERT_GT(token, 0, "Unexpected 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;
@@ -108,6 +136,12 @@ static int verify_msk(int map_fd, int client_fd)
 		err++;
 	}
 
+	if (strncmp(val.ca_name, ca_name, TCP_CA_NAME_MAX)) {
+		log_err("Unexpected mptcp_sock.ca_name %s != %s",
+			val.ca_name, 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 2a0decd78a0d..52448912fe5d 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 {
@@ -49,6 +51,7 @@ int _sockops(struct bpf_sock_ops *ctx)
 			return 1;
 
 		storage->token = 0;
+		bzero(storage->ca_name, TCP_CA_NAME_MAX);
 	} else {
 		if (!CONFIG_MPTCP)
 			return 1;
@@ -63,6 +66,7 @@ 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 = tcp_sk->is_mptcp;
-- 
2.34.1

[PATCH mptcp-next 08/15] 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().

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 | 8 ++++++++
 tools/testing/selftests/bpf/progs/mptcp_sock.c | 5 +++++
 3 files changed, 14 insertions(+)

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index f882915b2553..f1044778455b 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -233,6 +233,7 @@ 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 2ff7f18ea0ce..51a3e17acb9e 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -13,7 +13,9 @@
 struct mptcp_storage {
 	__u32 invoked;
 	__u32 is_mptcp;
+	struct sock *sk;
 	__u32 token;
+	struct sock *first;
 	char ca_name[TCP_CA_NAME_MAX];
 };
 
@@ -136,6 +138,12 @@ static int verify_msk(int map_fd, int client_fd)
 		err++;
 	}
 
+	if (val.first != val.sk) {
+		log_err("Unexpected mptcp_sock.first %p != %p",
+			val.first, val.sk);
+		err++;
+	}
+
 	if (strncmp(val.ca_name, ca_name, TCP_CA_NAME_MAX)) {
 		log_err("Unexpected mptcp_sock.ca_name %s != %s",
 			val.ca_name, ca_name);
diff --git a/tools/testing/selftests/bpf/progs/mptcp_sock.c b/tools/testing/selftests/bpf/progs/mptcp_sock.c
index 52448912fe5d..4c939e04b391 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_sock.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_sock.c
@@ -13,7 +13,9 @@ extern bool CONFIG_MPTCP __kconfig;
 struct mptcp_storage {
 	__u32 invoked;
 	__u32 is_mptcp;
+	struct sock *sk;
 	__u32 token;
+	struct sock *first;
 	char ca_name[TCP_CA_NAME_MAX];
 };
 
@@ -52,6 +54,7 @@ int _sockops(struct bpf_sock_ops *ctx)
 
 		storage->token = 0;
 		bzero(storage->ca_name, TCP_CA_NAME_MAX);
+		storage->first = NULL;
 	} else {
 		if (!CONFIG_MPTCP)
 			return 1;
@@ -67,9 +70,11 @@ 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 = tcp_sk->is_mptcp;
+	storage->sk = (struct sock *)sk;
 
 	return 1;
 }
-- 
2.34.1

[PATCH mptcp-next 09/15] mptcp: add struct mptcp_sched_ops

[Geliang Tang]

This patch defines struct mptcp_sched_ops, which has three struct members,
name, owner and list, and three function pointers, init, release and
get_subflow.

Add the scheduler registering, unregistering and finding functions to add,
delete and find a packet scheduler on the global list mptcp_sched_list.

For supporting a "redundant" packet scheduler in the future, this patch
adds a flag in struct mptcp_sched_data named call_again to indicate that
get_subflow() function needs to be called again.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 include/net/mptcp.h                           | 19 +++++++
 net/mptcp/Makefile                            |  2 +-
 net/mptcp/protocol.h                          |  3 +
 net/mptcp/sched.c                             | 56 +++++++++++++++++++
 tools/testing/selftests/bpf/bpf_tcp_helpers.h | 18 ++++++
 5 files changed, 97 insertions(+), 1 deletion(-)
 create mode 100644 net/mptcp/sched.c

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 4d761ad530c9..b596ba7a8494 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -95,6 +95,25 @@ struct mptcp_out_options {
 #endif
 };
 
+#define MPTCP_SCHED_NAME_MAX	16
+
+struct mptcp_sched_data {
+	struct sock	*sock;
+	bool		call_again;
+};
+
+struct mptcp_sched_ops {
+	void (*get_subflow)(const struct mptcp_sock *msk, bool reinject,
+			    struct mptcp_sched_data *data);
+
+	char			name[MPTCP_SCHED_NAME_MAX];
+	struct module		*owner;
+	struct list_head	list;
+
+	void (*init)(const struct mptcp_sock *msk);
+	void (*release)(const struct mptcp_sock *msk);
+} ____cacheline_aligned_in_smp;
+
 #ifdef CONFIG_MPTCP
 extern struct request_sock_ops mptcp_subflow_request_sock_ops;
 
diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile
index 6e7df47c9584..8a7f68efa35f 100644
--- a/net/mptcp/Makefile
+++ b/net/mptcp/Makefile
@@ -2,7 +2,7 @@
 obj-$(CONFIG_MPTCP) += mptcp.o
 
 mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \
-	   mib.o pm_netlink.o sockopt.o pm_userspace.o
+	   mib.o pm_netlink.o sockopt.o pm_userspace.o sched.o
 
 obj-$(CONFIG_SYN_COOKIES) += syncookies.o
 obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 06b8ebc15204..2f6c4486a009 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -621,6 +621,9 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock);
 void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 			 struct sockaddr_storage *addr,
 			 unsigned short family);
+struct mptcp_sched_ops *mptcp_sched_find(const char *name);
+int mptcp_register_scheduler(struct mptcp_sched_ops *sched);
+void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched);
 
 static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
new file mode 100644
index 000000000000..c5d3bbafba71
--- /dev/null
+++ b/net/mptcp/sched.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2022, SUSE.
+ */
+
+#define pr_fmt(fmt) "MPTCP: " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
+#include "protocol.h"
+
+static DEFINE_SPINLOCK(mptcp_sched_list_lock);
+static LIST_HEAD(mptcp_sched_list);
+
+/* Must be called with rcu read lock held */
+struct mptcp_sched_ops *mptcp_sched_find(const char *name)
+{
+	struct mptcp_sched_ops *sched, *ret = NULL;
+
+	list_for_each_entry_rcu(sched, &mptcp_sched_list, list) {
+		if (!strcmp(sched->name, name)) {
+			ret = sched;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
+{
+	if (!sched->get_subflow)
+		return -EINVAL;
+
+	spin_lock(&mptcp_sched_list_lock);
+	if (mptcp_sched_find(sched->name)) {
+		spin_unlock(&mptcp_sched_list_lock);
+		return -EEXIST;
+	}
+	list_add_tail_rcu(&sched->list, &mptcp_sched_list);
+	spin_unlock(&mptcp_sched_list_lock);
+
+	pr_debug("%s registered", sched->name);
+	return 0;
+}
+
+void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched)
+{
+	spin_lock(&mptcp_sched_list_lock);
+	list_del_rcu(&sched->list);
+	spin_unlock(&mptcp_sched_list_lock);
+}
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index f1044778455b..ff4d57993e10 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -229,6 +229,24 @@ 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;
 
+#define MPTCP_SCHED_NAME_MAX	16
+
+struct mptcp_sched_data {
+	struct sock	*sock;
+	bool		call_again;
+};
+
+struct mptcp_sched_ops {
+	char name[MPTCP_SCHED_NAME_MAX];
+
+	void (*init)(const struct mptcp_sock *msk);
+	void (*release)(const struct mptcp_sock *msk);
+
+	void (*get_subflow)(const struct mptcp_sock *msk, bool reinject,
+			    struct mptcp_sched_data *data);
+	void *owner;
+};
+
 struct mptcp_sock {
 	struct inet_connection_sock	sk;
 
-- 
2.34.1

[PATCH mptcp-next 10/15] mptcp: add a new sysctl scheduler

[Geliang Tang]

This patch adds a new sysctl, named scheduler, to support for selection
of different schedulers. Export mptcp_get_scheduler helper to get this
sysctl.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 Documentation/networking/mptcp-sysctl.rst |  8 ++++++++
 net/mptcp/ctrl.c                          | 14 ++++++++++++++
 net/mptcp/protocol.h                      |  1 +
 3 files changed, 23 insertions(+)

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index e263dfcc4b40..d9e69fdc7ea3 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -75,3 +75,11 @@ stale_loss_cnt - INTEGER
 	This is a per-namespace sysctl.
 
 	Default: 4
+
+scheduler - STRING
+	Select the scheduler of your choice.
+
+	Support for selection of different schedulers. This is a per-namespace
+	sysctl.
+
+	Default: "default"
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index ae20b7d92e28..c46c22a84d23 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -32,6 +32,7 @@ struct mptcp_pernet {
 	u8 checksum_enabled;
 	u8 allow_join_initial_addr_port;
 	u8 pm_type;
+	char scheduler[MPTCP_SCHED_NAME_MAX];
 };
 
 static struct mptcp_pernet *mptcp_get_pernet(const struct net *net)
@@ -69,6 +70,11 @@ int mptcp_get_pm_type(const struct net *net)
 	return mptcp_get_pernet(net)->pm_type;
 }
 
+const char *mptcp_get_scheduler(const struct net *net)
+{
+	return mptcp_get_pernet(net)->scheduler;
+}
+
 static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 {
 	pernet->mptcp_enabled = 1;
@@ -77,6 +83,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 	pernet->allow_join_initial_addr_port = 1;
 	pernet->stale_loss_cnt = 4;
 	pernet->pm_type = MPTCP_PM_TYPE_KERNEL;
+	strcpy(pernet->scheduler, "default");
 }
 
 #ifdef CONFIG_SYSCTL
@@ -128,6 +135,12 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.extra1       = SYSCTL_ZERO,
 		.extra2       = &mptcp_pm_type_max
 	},
+	{
+		.procname = "scheduler",
+		.maxlen	= MPTCP_SCHED_NAME_MAX,
+		.mode = 0644,
+		.proc_handler = proc_dostring,
+	},
 	{}
 };
 
@@ -149,6 +162,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 	table[3].data = &pernet->allow_join_initial_addr_port;
 	table[4].data = &pernet->stale_loss_cnt;
 	table[5].data = &pernet->pm_type;
+	table[6].data = &pernet->scheduler;
 
 	hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table);
 	if (!hdr)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 2f6c4486a009..b52cef5fdd9c 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -596,6 +596,7 @@ int mptcp_is_checksum_enabled(const struct net *net);
 int mptcp_allow_join_id0(const struct net *net);
 unsigned int mptcp_stale_loss_cnt(const struct net *net);
 int mptcp_get_pm_type(const struct net *net);
+const char *mptcp_get_scheduler(const struct net *net);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 				     struct mptcp_options_received *mp_opt);
 bool __mptcp_retransmit_pending_data(struct sock *sk);
-- 
2.34.1

[PATCH mptcp-next 11/15] mptcp: add sched in mptcp_sock

[Geliang Tang]

This patch adds a new struct member sched in struct mptcp_sock.
And two helpers mptcp_init_sched() and mptcp_release_sched() to
init and release it.

Init it with the sysctl scheduler in mptcp_init_sock(), copy the
scheduler from the parent in mptcp_sk_clone(), and release it in
__mptcp_destroy_sock().

Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c                          |  7 ++++
 net/mptcp/protocol.h                          |  4 +++
 net/mptcp/sched.c                             | 33 +++++++++++++++++++
 tools/testing/selftests/bpf/bpf_tcp_helpers.h |  1 +
 4 files changed, 45 insertions(+)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 921d67174e49..3e9246822412 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2657,6 +2657,11 @@ static int mptcp_init_sock(struct sock *sk)
 	if (ret)
 		return ret;
 
+	ret = mptcp_init_sched(mptcp_sk(sk),
+			       mptcp_sched_find(mptcp_get_scheduler(net)));
+	if (ret)
+		return ret;
+
 	/* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will
 	 * propagate the correct value
 	 */
@@ -2812,6 +2817,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	mptcp_stop_timer(sk);
 	sk_stop_timer(sk, &sk->sk_timer);
 	msk->pm.status = 0;
+	mptcp_release_sched(msk);
 
 	/* clears msk->subflow, allowing the following loop to close
 	 * even the initial subflow
@@ -2985,6 +2991,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 	msk->snd_una = msk->write_seq;
 	msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
 	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
+	mptcp_init_sched(msk, mptcp_sk(sk)->sched);
 
 	if (mp_opt->suboptions & OPTIONS_MPTCP_MPC) {
 		msk->can_ack = true;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index b52cef5fdd9c..85dd69b8d9d5 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -298,6 +298,7 @@ struct mptcp_sock {
 	struct socket	*subflow; /* outgoing connect/listener/!mp_capable */
 	struct sock	*first;
 	struct mptcp_pm_data	pm;
+	struct mptcp_sched_ops	*sched;
 	struct {
 		u32	space;	/* bytes copied in last measurement window */
 		u32	copied; /* bytes copied in this measurement window */
@@ -625,6 +626,9 @@ void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 struct mptcp_sched_ops *mptcp_sched_find(const char *name);
 int mptcp_register_scheduler(struct mptcp_sched_ops *sched);
 void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched);
+int mptcp_init_sched(struct mptcp_sock *msk,
+		     struct mptcp_sched_ops *sched);
+void mptcp_release_sched(struct mptcp_sock *msk);
 
 static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index c5d3bbafba71..53773668b5ee 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -54,3 +54,36 @@ void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched)
 	list_del_rcu(&sched->list);
 	spin_unlock(&mptcp_sched_list_lock);
 }
+
+int mptcp_init_sched(struct mptcp_sock *msk,
+		     struct mptcp_sched_ops *sched)
+{
+	if (!sched)
+		goto out;
+
+	if (!bpf_try_module_get(sched, sched->owner))
+		return -EBUSY;
+
+	msk->sched = sched;
+	if (msk->sched->init)
+		msk->sched->init(msk);
+
+	pr_debug("sched=%s", msk->sched->name);
+
+out:
+	return 0;
+}
+
+void mptcp_release_sched(struct mptcp_sock *msk)
+{
+	struct mptcp_sched_ops *sched = msk->sched;
+
+	if (!sched)
+		return;
+
+	msk->sched = NULL;
+	if (sched->release)
+		sched->release(msk);
+
+	bpf_module_put(sched, sched->owner);
+}
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index ff4d57993e10..1ef66a16771c 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -252,6 +252,7 @@ struct mptcp_sock {
 
 	__u32		token;
 	struct sock	*first;
+	struct mptcp_sched_ops *sched;
 	char		ca_name[TCP_CA_NAME_MAX];
 } __attribute__((preserve_access_index));
 
-- 
2.34.1

[PATCH mptcp-next 12/15] mptcp: add get_subflow wrappers

[Geliang Tang]

This patch defines two new wrappers mptcp_sched_get_send() and
mptcp_sched_get_retrans(), invoke get_subflow() of msk->sched
in them. Use them instead of using mptcp_subflow_get_send() or
mptcp_subflow_get_retrans() directly.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c | 25 +++++----------------
 net/mptcp/protocol.h |  4 ++++
 net/mptcp/sched.c    | 52 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 62 insertions(+), 19 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3e9246822412..ea3c93322592 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1427,7 +1427,7 @@ bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
  * returns the subflow that will transmit the next DSS
  * additionally updates the rtx timeout
  */
-static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
+struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 {
 	struct subflow_send_info send_info[SSK_MODE_MAX];
 	struct mptcp_subflow_context *subflow;
@@ -1438,14 +1438,6 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 	u64 linger_time;
 	long tout = 0;
 
-	sock_owned_by_me(sk);
-
-	if (__mptcp_check_fallback(msk)) {
-		if (!msk->first)
-			return NULL;
-		return sk_stream_memory_free(msk->first) ? msk->first : NULL;
-	}
-
 	/* re-use last subflow, if the burst allow that */
 	if (msk->last_snd && msk->snd_burst > 0 &&
 	    sk_stream_memory_free(msk->last_snd) &&
@@ -1575,7 +1567,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 			int ret = 0;
 
 			prev_ssk = ssk;
-			ssk = mptcp_subflow_get_send(msk);
+			ssk = mptcp_sched_get_send(msk);
 
 			/* First check. If the ssk has changed since
 			 * the last round, release prev_ssk
@@ -1642,7 +1634,7 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
 			 * check for a different subflow usage only after
 			 * spooling the first chunk of data
 			 */
-			xmit_ssk = first ? ssk : mptcp_subflow_get_send(mptcp_sk(sk));
+			xmit_ssk = first ? ssk : mptcp_sched_get_send(mptcp_sk(sk));
 			if (!xmit_ssk)
 				goto out;
 			if (xmit_ssk != ssk) {
@@ -2216,17 +2208,12 @@ static void mptcp_timeout_timer(struct timer_list *t)
  *
  * A backup subflow is returned only if that is the only kind available.
  */
-static struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
+struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
 {
 	struct sock *backup = NULL, *pick = NULL;
 	struct mptcp_subflow_context *subflow;
 	int min_stale_count = INT_MAX;
 
-	sock_owned_by_me((const struct sock *)msk);
-
-	if (__mptcp_check_fallback(msk))
-		return NULL;
-
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
@@ -2479,7 +2466,7 @@ static void __mptcp_retrans(struct sock *sk)
 	mptcp_clean_una_wakeup(sk);
 
 	/* first check ssk: need to kick "stale" logic */
-	ssk = mptcp_subflow_get_retrans(msk);
+	ssk = mptcp_sched_get_retrans(msk);
 	dfrag = mptcp_rtx_head(sk);
 	if (!dfrag) {
 		if (mptcp_data_fin_enabled(msk)) {
@@ -3128,7 +3115,7 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk)
 		return;
 
 	if (!sock_owned_by_user(sk)) {
-		struct sock *xmit_ssk = mptcp_subflow_get_send(mptcp_sk(sk));
+		struct sock *xmit_ssk = mptcp_sched_get_send(mptcp_sk(sk));
 
 		if (xmit_ssk == ssk)
 			__mptcp_subflow_push_pending(sk, ssk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 85dd69b8d9d5..59a23838782f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -629,6 +629,10 @@ void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched);
 int mptcp_init_sched(struct mptcp_sock *msk,
 		     struct mptcp_sched_ops *sched);
 void mptcp_release_sched(struct mptcp_sock *msk);
+struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk);
+struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk);
+struct sock *mptcp_sched_get_send(struct mptcp_sock *msk);
+struct sock *mptcp_sched_get_retrans(struct mptcp_sock *msk);
 
 static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 53773668b5ee..3ceb721e6489 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -87,3 +87,55 @@ void mptcp_release_sched(struct mptcp_sock *msk)
 
 	bpf_module_put(sched, sched->owner);
 }
+
+static int mptcp_sched_data_init(struct mptcp_sock *msk,
+				 struct mptcp_sched_data *data)
+{
+	data->sock = NULL;
+	data->call_again = 0;
+
+	return 0;
+}
+
+struct sock *mptcp_sched_get_send(struct mptcp_sock *msk)
+{
+	struct mptcp_sched_data data;
+
+	sock_owned_by_me((struct sock *)msk);
+
+	/* the following check is moved out of mptcp_subflow_get_send */
+	if (__mptcp_check_fallback(msk)) {
+		if (!msk->first)
+			return NULL;
+		return sk_stream_memory_free(msk->first) ? msk->first : NULL;
+	}
+
+	if (!msk->sched)
+		return mptcp_subflow_get_send(msk);
+
+	mptcp_sched_data_init(msk, &data);
+	msk->sched->get_subflow(msk, false, &data);
+
+	msk->last_snd = data.sock;
+	return data.sock;
+}
+
+struct sock *mptcp_sched_get_retrans(struct mptcp_sock *msk)
+{
+	struct mptcp_sched_data data;
+
+	sock_owned_by_me((const struct sock *)msk);
+
+	/* the following check is moved out of mptcp_subflow_get_retrans */
+	if (__mptcp_check_fallback(msk))
+		return NULL;
+
+	if (!msk->sched)
+		return mptcp_subflow_get_retrans(msk);
+
+	mptcp_sched_data_init(msk, &data);
+	msk->sched->get_subflow(msk, true, &data);
+
+	msk->last_snd = data.sock;
+	return data.sock;
+}
-- 
2.34.1

[PATCH mptcp-next 13/15] mptcp: add bpf_mptcp_sched_ops

[Geliang Tang]

This patch implements a new struct bpf_struct_ops, bpf_mptcp_sched_ops.
Register and unregister the bpf scheduler in .reg and .unreg.

This MPTCP BPF scheduler implementation is similar to BPF TCP CC. And
net/ipv4/bpf_tcp_ca.c is a frame of reference for this patch.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 kernel/bpf/bpf_struct_ops_types.h |   4 +
 net/mptcp/bpf.c                   | 153 ++++++++++++++++++++++++++++++
 2 files changed, 157 insertions(+)

diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h
index 5678a9ddf817..5a6b0c0d8d3d 100644
--- a/kernel/bpf/bpf_struct_ops_types.h
+++ b/kernel/bpf/bpf_struct_ops_types.h
@@ -8,5 +8,9 @@ BPF_STRUCT_OPS_TYPE(bpf_dummy_ops)
 #ifdef CONFIG_INET
 #include <net/tcp.h>
 BPF_STRUCT_OPS_TYPE(tcp_congestion_ops)
+#ifdef CONFIG_MPTCP
+#include <net/mptcp.h>
+BPF_STRUCT_OPS_TYPE(mptcp_sched_ops)
+#endif
 #endif
 #endif
diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
index 535602ba2582..b7cde38f7a6b 100644
--- a/net/mptcp/bpf.c
+++ b/net/mptcp/bpf.c
@@ -10,8 +10,161 @@
 #define pr_fmt(fmt) "MPTCP: " fmt
 
 #include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
 #include "protocol.h"
 
+#ifdef CONFIG_BPF_JIT
+extern struct bpf_struct_ops bpf_mptcp_sched_ops;
+extern struct btf *btf_vmlinux;
+static const struct btf_type *mptcp_sched_type __read_mostly;
+static u32 mptcp_sched_id;
+
+static u32 optional_ops[] = {
+	offsetof(struct mptcp_sched_ops, init),
+	offsetof(struct mptcp_sched_ops, release),
+};
+
+static const struct bpf_func_proto *
+bpf_mptcp_sched_get_func_proto(enum bpf_func_id func_id,
+			       const struct bpf_prog *prog)
+{
+	return bpf_base_func_proto(func_id);
+}
+
+static int bpf_mptcp_sched_btf_struct_access(struct bpf_verifier_log *log,
+					     const struct btf *btf,
+					     const struct btf_type *t, int off,
+					     int size, enum bpf_access_type atype,
+					     u32 *next_btf_id,
+					     enum bpf_type_flag *flag)
+{
+	size_t end;
+
+	if (atype == BPF_READ)
+		return btf_struct_access(log, btf, t, off, size, atype,
+					 next_btf_id, flag);
+
+	if (t != mptcp_sched_type) {
+		bpf_log(log, "only access to mptcp_sched_data is supported\n");
+		return -EACCES;
+	}
+
+	switch (off) {
+	case offsetof(struct mptcp_sched_data, sock):
+		end = offsetofend(struct mptcp_sched_data, sock);
+		break;
+	case offsetof(struct mptcp_sched_data, call_again):
+		end = offsetofend(struct mptcp_sched_data, call_again);
+		break;
+	default:
+		bpf_log(log, "no write support to mptcp_sched_data at off %d\n", off);
+		return -EACCES;
+	}
+
+	if (off + size > end) {
+		bpf_log(log, "access beyond mptcp_sched_data at off %u size %u ended at %zu",
+			off, size, end);
+		return -EACCES;
+	}
+
+	return NOT_INIT;
+}
+
+static const struct bpf_verifier_ops bpf_mptcp_sched_verifier_ops = {
+	.get_func_proto		= bpf_mptcp_sched_get_func_proto,
+	.is_valid_access	= bpf_tracing_btf_ctx_access,
+	.btf_struct_access	= bpf_mptcp_sched_btf_struct_access,
+};
+
+static int bpf_mptcp_sched_reg(void *kdata)
+{
+	return mptcp_register_scheduler(kdata);
+}
+
+static void bpf_mptcp_sched_unreg(void *kdata)
+{
+	mptcp_unregister_scheduler(kdata);
+}
+
+static int bpf_mptcp_sched_check_member(const struct btf_type *t,
+					const struct btf_member *member)
+{
+	return 0;
+}
+
+static bool is_optional(u32 member_offset)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(optional_ops); i++) {
+		if (member_offset == optional_ops[i])
+			return true;
+	}
+
+	return false;
+}
+
+static int bpf_mptcp_sched_init_member(const struct btf_type *t,
+				       const struct btf_member *member,
+				       void *kdata, const void *udata)
+{
+	const struct mptcp_sched_ops *usched;
+	struct mptcp_sched_ops *sched;
+	int prog_fd;
+	u32 moff;
+
+	usched = (const struct mptcp_sched_ops *)udata;
+	sched = (struct mptcp_sched_ops *)kdata;
+
+	moff = __btf_member_bit_offset(t, member) / 8;
+	switch (moff) {
+	case offsetof(struct mptcp_sched_ops, name):
+		if (bpf_obj_name_cpy(sched->name, usched->name,
+				     sizeof(sched->name)) <= 0)
+			return -EINVAL;
+		if (mptcp_sched_find(usched->name))
+			return -EEXIST;
+		return 1;
+	}
+
+	if (!btf_type_resolve_func_ptr(btf_vmlinux, member->type, NULL))
+		return 0;
+
+	/* Ensure bpf_prog is provided for compulsory func ptr */
+	prog_fd = (int)(*(unsigned long *)(udata + moff));
+	if (!prog_fd && !is_optional(moff))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int bpf_mptcp_sched_init(struct btf *btf)
+{
+	s32 type_id;
+
+	type_id = btf_find_by_name_kind(btf, "mptcp_sched_data",
+					BTF_KIND_STRUCT);
+	if (type_id < 0)
+		return -EINVAL;
+	mptcp_sched_id = type_id;
+	mptcp_sched_type = btf_type_by_id(btf, mptcp_sched_id);
+
+	return 0;
+}
+
+struct bpf_struct_ops bpf_mptcp_sched_ops = {
+	.verifier_ops	= &bpf_mptcp_sched_verifier_ops,
+	.reg		= bpf_mptcp_sched_reg,
+	.unreg		= bpf_mptcp_sched_unreg,
+	.check_member	= bpf_mptcp_sched_check_member,
+	.init_member	= bpf_mptcp_sched_init_member,
+	.init		= bpf_mptcp_sched_init,
+	.name		= "mptcp_sched_ops",
+};
+#endif /* CONFIG_BPF_JIT */
+
 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))
-- 
2.34.1

[PATCH mptcp-next 14/15] selftests/bpf: add bpf_first scheduler

[Geliang Tang]

This patch implements the simplest MPTCP scheduler, named bpf_first,
which always picks the first subflow to send data. It's a sample of
MPTCP BPF scheduler implementations.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 .../selftests/bpf/progs/mptcp_bpf_first.c     | 32 +++++++++++++++++++
 1 file changed, 32 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_first.c

diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
new file mode 100644
index 000000000000..fd67b5f42964
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022, SUSE. */
+
+#include <linux/bpf.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops/mptcp_sched_first_init")
+void BPF_PROG(mptcp_sched_first_init, const struct mptcp_sock *msk)
+{
+}
+
+SEC("struct_ops/mptcp_sched_first_release")
+void BPF_PROG(mptcp_sched_first_release, const struct mptcp_sock *msk)
+{
+}
+
+void BPF_STRUCT_OPS(bpf_first_get_subflow, const struct mptcp_sock *msk,
+		    bool reinject, struct mptcp_sched_data *data)
+{
+	data->sock = msk->first;
+	data->call_again = 0;
+}
+
+SEC(".struct_ops")
+struct mptcp_sched_ops first = {
+	.init		= (void *)mptcp_sched_first_init,
+	.release	= (void *)mptcp_sched_first_release,
+	.get_subflow	= (void *)bpf_first_get_subflow,
+	.name		= "bpf_first",
+};
-- 
2.34.1

[PATCH mptcp-next 15/15] selftests/bpf: add bpf_first test

[Geliang Tang]

This patch expends the MPTCP test base to support MPTCP packet
scheduler tests. Add the bpf_first scheduler test in it. Use sysctl
to set net.mptcp.scheduler to use this sched.

Some code in send_data() is from prog_tests/bpf_tcp_ca.c.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 113 ++++++++++++++++++
 1 file changed, 113 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 51a3e17acb9e..93a5739712ce 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -5,6 +5,7 @@
 #include <test_progs.h>
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
+#include "mptcp_bpf_first.skel.h"
 
 #ifndef TCP_CA_NAME_MAX
 #define TCP_CA_NAME_MAX	16
@@ -20,6 +21,8 @@ struct mptcp_storage {
 };
 
 static char monitor_log_path[64];
+static const unsigned int total_bytes = 10 * 1024 * 1024;
+static int stop, duration;
 
 static int verify_tsk(int map_fd, int client_fd)
 {
@@ -258,8 +261,118 @@ void test_base(void)
 	close(cgroup_fd);
 }
 
+static void *server(void *arg)
+{
+	int lfd = (int)(long)arg, err = 0, fd;
+	ssize_t nr_sent = 0, bytes = 0;
+	char batch[1500];
+
+	fd = accept(lfd, NULL, NULL);
+	while (fd == -1) {
+		if (errno == EINTR)
+			continue;
+		err = -errno;
+		goto done;
+	}
+
+	if (settimeo(fd, 0)) {
+		err = -errno;
+		goto done;
+	}
+
+	while (bytes < total_bytes && !READ_ONCE(stop)) {
+		nr_sent = send(fd, &batch,
+			       MIN(total_bytes - bytes, sizeof(batch)), 0);
+		if (nr_sent == -1 && errno == EINTR)
+			continue;
+		if (nr_sent == -1) {
+			err = -errno;
+			break;
+		}
+		bytes += nr_sent;
+	}
+
+	CHECK(bytes != total_bytes, "send", "%zd != %u nr_sent:%zd errno:%d\n",
+	      bytes, total_bytes, nr_sent, errno);
+
+done:
+	if (fd >= 0)
+		close(fd);
+	if (err) {
+		WRITE_ONCE(stop, 1);
+		return ERR_PTR(err);
+	}
+	return NULL;
+}
+
+static void send_data(int lfd, int fd)
+{
+	ssize_t nr_recv = 0, bytes = 0;
+	pthread_t srv_thread;
+	void *thread_ret;
+	char batch[1500];
+	int err;
+
+	WRITE_ONCE(stop, 0);
+
+	err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd);
+	if (CHECK(err != 0, "pthread_create", "err:%d errno:%d\n", err, errno))
+		return;
+
+	/* recv total_bytes */
+	while (bytes < total_bytes && !READ_ONCE(stop)) {
+		nr_recv = recv(fd, &batch,
+			       MIN(total_bytes - bytes, sizeof(batch)), 0);
+		if (nr_recv == -1 && errno == EINTR)
+			continue;
+		if (nr_recv == -1)
+			break;
+		bytes += nr_recv;
+	}
+
+	CHECK(bytes != total_bytes, "recv", "%zd != %u nr_recv:%zd errno:%d\n",
+	      bytes, total_bytes, nr_recv, errno);
+
+	WRITE_ONCE(stop, 1);
+
+	pthread_join(srv_thread, &thread_ret);
+	CHECK(IS_ERR(thread_ret), "pthread_join", "thread_ret:%ld",
+	      PTR_ERR(thread_ret));
+}
+
+static void test_first(void)
+{
+	struct mptcp_bpf_first *first_skel;
+	int server_fd, client_fd;
+	struct bpf_link *link;
+
+	first_skel = mptcp_bpf_first__open_and_load();
+	if (!ASSERT_OK_PTR(first_skel, "bpf_first__open_and_load"))
+		return;
+
+	link = bpf_map__attach_struct_ops(first_skel->maps.first);
+	if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops")) {
+		mptcp_bpf_first__destroy(first_skel);
+		return;
+	}
+
+	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);
+
+	send_data(server_fd, client_fd);
+
+	close(client_fd);
+	close(server_fd);
+	system("sysctl -qw net.mptcp.scheduler=default");
+	bpf_link__destroy(link);
+	mptcp_bpf_first__destroy(first_skel);
+}
+
 void test_mptcp(void)
 {
 	if (test__start_subtest("base"))
 		test_base();
+	if (test__start_subtest("first"))
+		test_first();
 }
-- 
2.34.1