[PATCH mptcp-next 00/17] for bpf-next

[PATCH mptcp-next 00/17] for bpf-next

[Geliang Tang]

- The first 10 patches is for bpf-next v5.
- Rebased the "BPF packet scheduler" series on export branch.
- base-commit: df896c77f02a ("DO-NOT-MERGE: git markup: features
net-next-next"), export/20220517T155019

Geliang Tang (16):
  mptcp: move MPTCPOPT_HMAC_LEN to net/mptcp.h
  mptcp: move mptcp_subflow_context in net/mptcp.h
  bpf: add bpf_mptcp_sock_from_subflow helper
  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 (1):
  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                           | 131 +++++++-
 include/uapi/linux/bpf.h                      |   7 +
 kernel/bpf/bpf_struct_ops_types.h             |   4 +
 kernel/bpf/verifier.c                         |   1 +
 kernel/trace/bpf_trace.c                      |   2 +
 net/core/filter.c                             |  18 ++
 net/mptcp/Makefile                            |   6 +-
 net/mptcp/bpf.c                               | 162 ++++++++++
 net/mptcp/ctrl.c                              |  14 +
 net/mptcp/protocol.c                          |  32 +-
 net/mptcp/protocol.h                          | 106 +------
 net/mptcp/sched.c                             | 141 +++++++++
 scripts/bpf_doc.py                            |   2 +
 tools/include/uapi/linux/bpf.h                |   7 +
 tools/testing/selftests/bpf/bpf_tcp_helpers.h |  32 ++
 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  | 288 ++++++++++++++++++
 .../selftests/bpf/progs/mptcp_bpf_first.c     |  32 ++
 .../testing/selftests/bpf/progs/mptcp_sock.c  |  89 ++++++
 25 files changed, 1007 insertions(+), 125 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 01/17] mptcp: move MPTCPOPT_HMAC_LEN to net/mptcp.h

[Geliang Tang]

Move macro MPTCPOPT_HMAC_LEN definition from net/mptcp/protocol.h to
include/net/mptcp.h.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 include/net/mptcp.h  | 3 ++-
 net/mptcp/protocol.h | 1 -
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index d4ec894ce67b..4713757e36c1 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -39,6 +39,7 @@ struct mptcp_ext {
 			infinite_map:1;
 };
 
+#define MPTCPOPT_HMAC_LEN	20
 #define MPTCP_RM_IDS_MAX	8
 
 struct mptcp_rm_list {
@@ -89,7 +90,7 @@ struct mptcp_out_options {
 			u32 nonce;
 			u32 token;
 			u64 thmac;
-			u8 hmac[20];
+			u8 hmac[MPTCPOPT_HMAC_LEN];
 		};
 	};
 #endif
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 200f89f6d62f..8f03775a2f22 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -83,7 +83,6 @@
 
 /* MPTCP MP_JOIN flags */
 #define MPTCPOPT_BACKUP		BIT(0)
-#define MPTCPOPT_HMAC_LEN	20
 #define MPTCPOPT_THMAC_LEN	8
 
 /* MPTCP MP_CAPABLE flags */
-- 
2.34.1

[PATCH mptcp-next 02/17] mptcp: move mptcp_subflow_context in net/mptcp.h

[Geliang Tang]

Move struct mptcp_subflow_context definition from net/mptcp/protocol.h
to include/net/mptcp.h. And move the related struct mptcp_data_avail and
function mptcp_subflow_ctx() too.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 include/net/mptcp.h  | 91 ++++++++++++++++++++++++++++++++++++++++++++
 net/mptcp/protocol.h | 88 ------------------------------------------
 2 files changed, 91 insertions(+), 88 deletions(-)

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 4713757e36c1..9422b6d2a268 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -40,6 +40,86 @@ struct mptcp_ext {
 };
 
 #define MPTCPOPT_HMAC_LEN	20
+
+enum mptcp_data_avail {
+	MPTCP_SUBFLOW_NODATA,
+	MPTCP_SUBFLOW_DATA_AVAIL,
+};
+
+/* MPTCP subflow context */
+struct mptcp_subflow_context {
+	struct	list_head node;/* conn_list of subflows */
+
+	struct_group(reset,
+
+	unsigned long avg_pacing_rate; /* protected by msk socket lock */
+	u64	local_key;
+	u64	remote_key;
+	u64	idsn;
+	u64	map_seq;
+	u32	snd_isn;
+	u32	token;
+	u32	rel_write_seq;
+	u32	map_subflow_seq;
+	u32	ssn_offset;
+	u32	map_data_len;
+	__wsum	map_data_csum;
+	u32	map_csum_len;
+	u32	request_mptcp : 1,  /* send MP_CAPABLE */
+		request_join : 1,   /* send MP_JOIN */
+		request_bkup : 1,
+		mp_capable : 1,	    /* remote is MPTCP capable */
+		mp_join : 1,	    /* remote is JOINing */
+		fully_established : 1,	    /* path validated */
+		pm_notified : 1,    /* PM hook called for established status */
+		conn_finished : 1,
+		map_valid : 1,
+		map_csum_reqd : 1,
+		map_data_fin : 1,
+		mpc_map : 1,
+		backup : 1,
+		send_mp_prio : 1,
+		send_mp_fail : 1,
+		send_fastclose : 1,
+		send_infinite_map : 1,
+		rx_eof : 1,
+		can_ack : 1,        /* only after processing the remote a key */
+		disposable : 1,	    /* ctx can be free at ulp release time */
+		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
+		local_id_valid : 1, /* local_id is correctly initialized */
+		valid_csum_seen : 1;        /* at least one csum validated */
+	enum mptcp_data_avail data_avail;
+	bool	mp_fail_response_expect;
+	u32	remote_nonce;
+	u64	thmac;
+	u32	local_nonce;
+	u32	remote_token;
+	u8	hmac[MPTCPOPT_HMAC_LEN];
+	u8	local_id;
+	u8	remote_id;
+	u8	reset_seen:1;
+	u8	reset_transient:1;
+	u8	reset_reason:4;
+	u8	stale_count;
+
+	long	delegated_status;
+
+	);
+
+	struct	list_head delegated_node;   /* link into delegated_action, protected by local BH */
+
+	u32	setsockopt_seq;
+	u32	stale_rcv_tstamp;
+
+	struct	sock *tcp_sock;	    /* tcp sk backpointer */
+	struct	sock *conn;	    /* parent mptcp_sock */
+	const	struct inet_connection_sock_af_ops *icsk_af_ops;
+	void	(*tcp_state_change)(struct sock *sk);
+	void	(*tcp_error_report)(struct sock *sk);
+
+	struct	rcu_head rcu;
+};
+
 #define MPTCP_RM_IDS_MAX	8
 
 struct mptcp_rm_list {
@@ -198,6 +278,15 @@ static inline __be32 mptcp_reset_option(const struct sk_buff *skb)
 
 	return htonl(0u);
 }
+
+static inline struct mptcp_subflow_context *
+mptcp_subflow_ctx(const struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	/* Use RCU on icsk_ulp_data only for sock diag code */
+	return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data;
+}
 #else
 
 static inline void mptcp_init(void)
@@ -275,6 +364,8 @@ static inline int mptcp_subflow_init_cookie_req(struct request_sock *req,
 }
 
 static inline __be32 mptcp_reset_option(const struct sk_buff *skb)  { return htonl(0u); }
+static inline struct mptcp_subflow_context *
+mptcp_subflow_ctx(const struct sock *sk) { return NULL; }
 #endif /* CONFIG_MPTCP */
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 8f03775a2f22..cc24756cedfe 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -409,11 +409,6 @@ mptcp_subflow_rsk(const struct request_sock *rsk)
 	return (struct mptcp_subflow_request_sock *)rsk;
 }
 
-enum mptcp_data_avail {
-	MPTCP_SUBFLOW_NODATA,
-	MPTCP_SUBFLOW_DATA_AVAIL,
-};
-
 struct mptcp_delegated_action {
 	struct napi_struct napi;
 	struct list_head head;
@@ -424,89 +419,6 @@ DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
 #define MPTCP_DELEGATE_SEND		0
 #define MPTCP_DELEGATE_ACK		1
 
-/* MPTCP subflow context */
-struct mptcp_subflow_context {
-	struct	list_head node;/* conn_list of subflows */
-
-	struct_group(reset,
-
-	unsigned long avg_pacing_rate; /* protected by msk socket lock */
-	u64	local_key;
-	u64	remote_key;
-	u64	idsn;
-	u64	map_seq;
-	u32	snd_isn;
-	u32	token;
-	u32	rel_write_seq;
-	u32	map_subflow_seq;
-	u32	ssn_offset;
-	u32	map_data_len;
-	__wsum	map_data_csum;
-	u32	map_csum_len;
-	u32	request_mptcp : 1,  /* send MP_CAPABLE */
-		request_join : 1,   /* send MP_JOIN */
-		request_bkup : 1,
-		mp_capable : 1,	    /* remote is MPTCP capable */
-		mp_join : 1,	    /* remote is JOINing */
-		fully_established : 1,	    /* path validated */
-		pm_notified : 1,    /* PM hook called for established status */
-		conn_finished : 1,
-		map_valid : 1,
-		map_csum_reqd : 1,
-		map_data_fin : 1,
-		mpc_map : 1,
-		backup : 1,
-		send_mp_prio : 1,
-		send_mp_fail : 1,
-		send_fastclose : 1,
-		send_infinite_map : 1,
-		rx_eof : 1,
-		can_ack : 1,        /* only after processing the remote a key */
-		disposable : 1,	    /* ctx can be free at ulp release time */
-		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
-		local_id_valid : 1, /* local_id is correctly initialized */
-		valid_csum_seen : 1;        /* at least one csum validated */
-	enum mptcp_data_avail data_avail;
-	bool	mp_fail_response_expect;
-	u32	remote_nonce;
-	u64	thmac;
-	u32	local_nonce;
-	u32	remote_token;
-	u8	hmac[MPTCPOPT_HMAC_LEN];
-	u8	local_id;
-	u8	remote_id;
-	u8	reset_seen:1;
-	u8	reset_transient:1;
-	u8	reset_reason:4;
-	u8	stale_count;
-
-	long	delegated_status;
-
-	);
-
-	struct	list_head delegated_node;   /* link into delegated_action, protected by local BH */
-
-	u32	setsockopt_seq;
-	u32	stale_rcv_tstamp;
-
-	struct	sock *tcp_sock;	    /* tcp sk backpointer */
-	struct	sock *conn;	    /* parent mptcp_sock */
-	const	struct inet_connection_sock_af_ops *icsk_af_ops;
-	void	(*tcp_state_change)(struct sock *sk);
-	void	(*tcp_error_report)(struct sock *sk);
-
-	struct	rcu_head rcu;
-};
-
-static inline struct mptcp_subflow_context *
-mptcp_subflow_ctx(const struct sock *sk)
-{
-	struct inet_connection_sock *icsk = inet_csk(sk);
-
-	/* Use RCU on icsk_ulp_data only for sock diag code */
-	return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data;
-}
-
 static inline struct sock *
 mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow)
 {
-- 
2.34.1

[PATCH mptcp-next 03/17] bpf: add bpf_mptcp_sock_from_subflow helper

[Geliang Tang]

This patch implements the helper bpf_mptcp_sock_from_subflow(), to get
the MPTCP socket from a given TCP subflow socket.

Move the inline function mptcp_sk() from net/mptcp/protocol.h to
include/net/mptcp.h.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 include/net/mptcp.h  | 18 ++++++++++++++++++
 net/mptcp/protocol.h |  5 -----
 2 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 9422b6d2a268..a267cff36197 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -287,6 +287,11 @@ mptcp_subflow_ctx(const struct sock *sk)
 	/* Use RCU on icsk_ulp_data only for sock diag code */
 	return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data;
 }
+
+static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
+{
+	return (struct mptcp_sock *)sk;
+}
 #else
 
 static inline void mptcp_init(void)
@@ -366,6 +371,7 @@ static inline int mptcp_subflow_init_cookie_req(struct request_sock *req,
 static inline __be32 mptcp_reset_option(const struct sk_buff *skb)  { return htonl(0u); }
 static inline struct mptcp_subflow_context *
 mptcp_subflow_ctx(const struct sock *sk) { return NULL; }
+static inline struct mptcp_sock *mptcp_sk(const struct sock *sk) { return NULL; }
 #endif /* CONFIG_MPTCP */
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
@@ -376,4 +382,16 @@ 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)
+static inline 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;
+}
+#else
+static inline struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk) { return NULL; }
+#endif
+
 #endif /* __NET_MPTCP_H */
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index cc24756cedfe..2fc8aaf5cb05 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -318,11 +318,6 @@ static inline void msk_owned_by_me(const struct mptcp_sock *msk)
 	sock_owned_by_me((const struct sock *)msk);
 }
 
-static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
-{
-	return (struct mptcp_sock *)sk;
-}
-
 /* the msk socket don't use the backlog, also account for the bulk
  * free memory
  */
-- 
2.34.1

[PATCH mptcp-next 04/17] 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 bpf.c, define bpf_mptcp_sock_from_subflow() in mptcp.h (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/uapi/linux/bpf.h       |  7 +++++++
 kernel/bpf/verifier.c          |  1 +
 kernel/trace/bpf_trace.c       |  2 ++
 net/core/filter.c              | 18 ++++++++++++++++++
 scripts/bpf_doc.py             |  2 ++
 tools/include/uapi/linux/bpf.h |  7 +++++++
 8 files changed, 40 insertions(+), 1 deletion(-)

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/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/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 05/17] 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 06/17] 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)

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..59113eb982e0
--- /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, 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 (!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, "MPTCP subflow socket", 1) :
+			  verify_sk(map_fd, client_fd, "plain TCP socket", 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 07/17] 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 59113eb982e0..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, const char *msg, __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, const char *msg, __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, "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);
 
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 08/17] 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)

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 09/17] 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 10/17] 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 11/17] 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 a267cff36197..6e872d0a35af 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -176,6 +176,25 @@ 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 cb7f53f6ab22..b68eddf4639a 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 2fc8aaf5cb05..86efc5a6d878 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -527,6 +527,9 @@ 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 82a7c9de95f9..bca318d2cc78 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -230,6 +230,24 @@ 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 12/17] 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 86efc5a6d878..86a5ff5d3fc8 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -502,6 +502,7 @@ 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 13/17] 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 17e13396024a..b7b7fbd2cab7 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2643,6 +2643,11 @@ 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
 	 */
@@ -2798,6 +2803,7 @@ 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
@@ -2971,6 +2977,7 @@ 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 86a5ff5d3fc8..57a92db1e85b 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -296,6 +296,7 @@ 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 */
@@ -531,6 +532,9 @@ 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 bca318d2cc78..aca4e3c6ac48 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -253,6 +253,7 @@ 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 14/17] 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 b7b7fbd2cab7..4c10c88d170d 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) {
@@ -2203,17 +2195,12 @@ 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);
 
@@ -2466,7 +2453,7 @@ 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)) {
@@ -3114,7 +3101,7 @@ 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 57a92db1e85b..9649d367d363 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -535,6 +535,10 @@ 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 15/17] 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/Makefile                |   4 +
 net/mptcp/bpf.c                   | 162 ++++++++++++++++++++++++++++++
 3 files changed, 170 insertions(+)
 create mode 100644 net/mptcp/bpf.c

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/Makefile b/net/mptcp/Makefile
index b68eddf4639a..702b86e8ecb0 100644
--- a/net/mptcp/Makefile
+++ b/net/mptcp/Makefile
@@ -10,3 +10,7 @@ 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
+
+ifeq ($(CONFIG_BPF_JIT),y)
+obj-$(CONFIG_BPF_SYSCALL) += bpf.o
+endif
diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
new file mode 100644
index 000000000000..7de0c1ad313d
--- /dev/null
+++ b/net/mptcp/bpf.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2020, Tessares SA.
+ * Copyright (c) 2022, SUSE.
+ */
+
+#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"
+
+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",
+};
-- 
2.34.1

[PATCH mptcp-next 16/17] 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 17/17] 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  | 114 ++++++++++++++++++
 1 file changed, 114 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 257a8668ad40..9d37c509d3ce 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -6,6 +6,7 @@
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
 #include "mptcp_sock.skel.h"
+#include "mptcp_bpf_first.skel.h"
 
 #ifndef TCP_CA_NAME_MAX
 #define TCP_CA_NAME_MAX	16
@@ -20,6 +21,9 @@ struct mptcp_storage {
 	char ca_name[TCP_CA_NAME_MAX];
 };
 
+static const unsigned int total_bytes = 10 * 1024 * 1024;
+static int stop, duration;
+
 static int verify_tsk(int map_fd, int client_fd)
 {
 	int err, cfd = client_fd;
@@ -167,8 +171,118 @@ 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_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

Re: [PATCH mptcp-next 08/17] 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().

Please update the commit log:

'''
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.
'''

Re: [PATCH mptcp-next 02/17] mptcp: move mptcp_subflow_context in net/mptcp.h

[Geliang Tang]

Please update the subject:

'''
mptcp: move mptcp_subflow_context to net/mptcp.h
'''

Re: [PATCH mptcp-next 00/17] for bpf-next

[Matthieu Baerts]

Hi Geliang,

Thank you for this series.

On 18/05/2022 08:10, Geliang Tang wrote:
> - The first 10 patches is for bpf-next v5.
> - Rebased the "BPF packet scheduler" series on export branch.
> - base-commit: df896c77f02a ("DO-NOT-MERGE: git markup: features
> net-next-next"), export/20220517T155019

Does this correspond to what I should get if I apply all the Squash-to
patch you sent yesterday?
Or are there differences on top of that?

On my side, it is easier to apply squash-to patch and re-apply an
updated series which is already in our tree.
Of course if the conflicts are complex, you can send your version on a
public Git repo for me to compare.

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

Re: [PATCH mptcp-next 00/17] for bpf-next

[Geliang Tang]

Hi Matt,

Matthieu Baerts <matthieu.baerts@tessares.net> 于2022年5月18日周三 18:59写道：
>
> Hi Geliang,
>
> Thank you for this series.
>
> On 18/05/2022 08:10, Geliang Tang wrote:
> > - The first 10 patches is for bpf-next v5.
> > - Rebased the "BPF packet scheduler" series on export branch.
> > - base-commit: df896c77f02a ("DO-NOT-MERGE: git markup: features
> > net-next-next"), export/20220517T155019
>
> Does this correspond to what I should get if I apply all the Squash-to
> patch you sent yesterday?
> Or are there differences on top of that?

This series addresses all BPF maintainers‘ comments for v4. It makes
the squash-to patches I sent yesterday superseded. I found it's hard
to send them as squash-to patches because there are too many
differences. So I sent this new series. I think it's much easier for
Mat to review and upstream.

>
> On my side, it is easier to apply squash-to patch and re-apply an
> updated series which is already in our tree.
> Of course if the conflicts are complex, you can send your version on a
> public Git repo for me to compare.

I suggest we skip merging this version into our export branch. I guess
BPF maintainers will give some comments for this v5 too. When this
series is accepted at last, then I'll split them as squash-to patches,
and send to you for merging into our export branch.

Thanks,
-Geliang

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

Re: [PATCH mptcp-next 02/17] mptcp: move mptcp_subflow_context in net/mptcp.h

[Mat Martineau]

On Wed, 18 May 2022, Geliang Tang wrote:

> Move struct mptcp_subflow_context definition from net/mptcp/protocol.h
> to include/net/mptcp.h. And move the related struct mptcp_data_avail and
> function mptcp_subflow_ctx() too.
>
> Signed-off-by: Geliang Tang <geliang.tang@suse.com>

I'm not sure I agree with moving all of this just because Martin asked 
about an inline function. I'll follow up on the netdev email thread.

- Mat

> ---
> include/net/mptcp.h  | 91 ++++++++++++++++++++++++++++++++++++++++++++
> net/mptcp/protocol.h | 88 ------------------------------------------
> 2 files changed, 91 insertions(+), 88 deletions(-)
>
> diff --git a/include/net/mptcp.h b/include/net/mptcp.h
> index 4713757e36c1..9422b6d2a268 100644
> --- a/include/net/mptcp.h
> +++ b/include/net/mptcp.h
> @@ -40,6 +40,86 @@ struct mptcp_ext {
> };
>
> #define MPTCPOPT_HMAC_LEN	20
> +
> +enum mptcp_data_avail {
> +	MPTCP_SUBFLOW_NODATA,
> +	MPTCP_SUBFLOW_DATA_AVAIL,
> +};
> +
> +/* MPTCP subflow context */
> +struct mptcp_subflow_context {
> +	struct	list_head node;/* conn_list of subflows */
> +
> +	struct_group(reset,
> +
> +	unsigned long avg_pacing_rate; /* protected by msk socket lock */
> +	u64	local_key;
> +	u64	remote_key;
> +	u64	idsn;
> +	u64	map_seq;
> +	u32	snd_isn;
> +	u32	token;
> +	u32	rel_write_seq;
> +	u32	map_subflow_seq;
> +	u32	ssn_offset;
> +	u32	map_data_len;
> +	__wsum	map_data_csum;
> +	u32	map_csum_len;
> +	u32	request_mptcp : 1,  /* send MP_CAPABLE */
> +		request_join : 1,   /* send MP_JOIN */
> +		request_bkup : 1,
> +		mp_capable : 1,	    /* remote is MPTCP capable */
> +		mp_join : 1,	    /* remote is JOINing */
> +		fully_established : 1,	    /* path validated */
> +		pm_notified : 1,    /* PM hook called for established status */
> +		conn_finished : 1,
> +		map_valid : 1,
> +		map_csum_reqd : 1,
> +		map_data_fin : 1,
> +		mpc_map : 1,
> +		backup : 1,
> +		send_mp_prio : 1,
> +		send_mp_fail : 1,
> +		send_fastclose : 1,
> +		send_infinite_map : 1,
> +		rx_eof : 1,
> +		can_ack : 1,        /* only after processing the remote a key */
> +		disposable : 1,	    /* ctx can be free at ulp release time */
> +		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
> +		local_id_valid : 1, /* local_id is correctly initialized */
> +		valid_csum_seen : 1;        /* at least one csum validated */
> +	enum mptcp_data_avail data_avail;
> +	bool	mp_fail_response_expect;
> +	u32	remote_nonce;
> +	u64	thmac;
> +	u32	local_nonce;
> +	u32	remote_token;
> +	u8	hmac[MPTCPOPT_HMAC_LEN];
> +	u8	local_id;
> +	u8	remote_id;
> +	u8	reset_seen:1;
> +	u8	reset_transient:1;
> +	u8	reset_reason:4;
> +	u8	stale_count;
> +
> +	long	delegated_status;
> +
> +	);
> +
> +	struct	list_head delegated_node;   /* link into delegated_action, protected by local BH */
> +
> +	u32	setsockopt_seq;
> +	u32	stale_rcv_tstamp;
> +
> +	struct	sock *tcp_sock;	    /* tcp sk backpointer */
> +	struct	sock *conn;	    /* parent mptcp_sock */
> +	const	struct inet_connection_sock_af_ops *icsk_af_ops;
> +	void	(*tcp_state_change)(struct sock *sk);
> +	void	(*tcp_error_report)(struct sock *sk);
> +
> +	struct	rcu_head rcu;
> +};
> +
> #define MPTCP_RM_IDS_MAX	8
>
> struct mptcp_rm_list {
> @@ -198,6 +278,15 @@ static inline __be32 mptcp_reset_option(const struct sk_buff *skb)
>
> 	return htonl(0u);
> }
> +
> +static inline struct mptcp_subflow_context *
> +mptcp_subflow_ctx(const struct sock *sk)
> +{
> +	struct inet_connection_sock *icsk = inet_csk(sk);
> +
> +	/* Use RCU on icsk_ulp_data only for sock diag code */
> +	return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data;
> +}
> #else
>
> static inline void mptcp_init(void)
> @@ -275,6 +364,8 @@ static inline int mptcp_subflow_init_cookie_req(struct request_sock *req,
> }
>
> static inline __be32 mptcp_reset_option(const struct sk_buff *skb)  { return htonl(0u); }
> +static inline struct mptcp_subflow_context *
> +mptcp_subflow_ctx(const struct sock *sk) { return NULL; }
> #endif /* CONFIG_MPTCP */
>
> #if IS_ENABLED(CONFIG_MPTCP_IPV6)
> diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
> index 8f03775a2f22..cc24756cedfe 100644
> --- a/net/mptcp/protocol.h
> +++ b/net/mptcp/protocol.h
> @@ -409,11 +409,6 @@ mptcp_subflow_rsk(const struct request_sock *rsk)
> 	return (struct mptcp_subflow_request_sock *)rsk;
> }
>
> -enum mptcp_data_avail {
> -	MPTCP_SUBFLOW_NODATA,
> -	MPTCP_SUBFLOW_DATA_AVAIL,
> -};
> -
> struct mptcp_delegated_action {
> 	struct napi_struct napi;
> 	struct list_head head;
> @@ -424,89 +419,6 @@ DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
> #define MPTCP_DELEGATE_SEND		0
> #define MPTCP_DELEGATE_ACK		1
>
> -/* MPTCP subflow context */
> -struct mptcp_subflow_context {
> -	struct	list_head node;/* conn_list of subflows */
> -
> -	struct_group(reset,
> -
> -	unsigned long avg_pacing_rate; /* protected by msk socket lock */
> -	u64	local_key;
> -	u64	remote_key;
> -	u64	idsn;
> -	u64	map_seq;
> -	u32	snd_isn;
> -	u32	token;
> -	u32	rel_write_seq;
> -	u32	map_subflow_seq;
> -	u32	ssn_offset;
> -	u32	map_data_len;
> -	__wsum	map_data_csum;
> -	u32	map_csum_len;
> -	u32	request_mptcp : 1,  /* send MP_CAPABLE */
> -		request_join : 1,   /* send MP_JOIN */
> -		request_bkup : 1,
> -		mp_capable : 1,	    /* remote is MPTCP capable */
> -		mp_join : 1,	    /* remote is JOINing */
> -		fully_established : 1,	    /* path validated */
> -		pm_notified : 1,    /* PM hook called for established status */
> -		conn_finished : 1,
> -		map_valid : 1,
> -		map_csum_reqd : 1,
> -		map_data_fin : 1,
> -		mpc_map : 1,
> -		backup : 1,
> -		send_mp_prio : 1,
> -		send_mp_fail : 1,
> -		send_fastclose : 1,
> -		send_infinite_map : 1,
> -		rx_eof : 1,
> -		can_ack : 1,        /* only after processing the remote a key */
> -		disposable : 1,	    /* ctx can be free at ulp release time */
> -		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
> -		local_id_valid : 1, /* local_id is correctly initialized */
> -		valid_csum_seen : 1;        /* at least one csum validated */
> -	enum mptcp_data_avail data_avail;
> -	bool	mp_fail_response_expect;
> -	u32	remote_nonce;
> -	u64	thmac;
> -	u32	local_nonce;
> -	u32	remote_token;
> -	u8	hmac[MPTCPOPT_HMAC_LEN];
> -	u8	local_id;
> -	u8	remote_id;
> -	u8	reset_seen:1;
> -	u8	reset_transient:1;
> -	u8	reset_reason:4;
> -	u8	stale_count;
> -
> -	long	delegated_status;
> -
> -	);
> -
> -	struct	list_head delegated_node;   /* link into delegated_action, protected by local BH */
> -
> -	u32	setsockopt_seq;
> -	u32	stale_rcv_tstamp;
> -
> -	struct	sock *tcp_sock;	    /* tcp sk backpointer */
> -	struct	sock *conn;	    /* parent mptcp_sock */
> -	const	struct inet_connection_sock_af_ops *icsk_af_ops;
> -	void	(*tcp_state_change)(struct sock *sk);
> -	void	(*tcp_error_report)(struct sock *sk);
> -
> -	struct	rcu_head rcu;
> -};
> -
> -static inline struct mptcp_subflow_context *
> -mptcp_subflow_ctx(const struct sock *sk)
> -{
> -	struct inet_connection_sock *icsk = inet_csk(sk);
> -
> -	/* Use RCU on icsk_ulp_data only for sock diag code */
> -	return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data;
> -}
> -
> static inline struct sock *
> mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow)
> {
> -- 
> 2.34.1
>
>
>

--
Mat Martineau
Intel

Re: [PATCH mptcp-next 02/17] mptcp: move mptcp_subflow_context in net/mptcp.h

[Geliang Tang]

> > Move struct mptcp_subflow_context definition from net/mptcp/protocol.h
> > to include/net/mptcp.h. And move the related struct mptcp_data_avail and
> > function mptcp_subflow_ctx() too.
> >
> > Signed-off-by: Geliang Tang <geliang.tang@suse.com>
>
> I'm not sure I agree with moving all of this just because Martin asked
> about an inline function. I'll follow up on the netdev email thread.

Mat, I removed the first three patches in v2. Could patch 1 still be
used as an effective cleanup?

Thanks,
-Geliang

>
> - Mat
>
> > ---
> > include/net/mptcp.h  | 91 ++++++++++++++++++++++++++++++++++++++++++++
> > net/mptcp/protocol.h | 88 ------------------------------------------
> > 2 files changed, 91 insertions(+), 88 deletions(-)
> >
> > diff --git a/include/net/mptcp.h b/include/net/mptcp.h
> > index 4713757e36c1..9422b6d2a268 100644
> > --- a/include/net/mptcp.h
> > +++ b/include/net/mptcp.h
> > @@ -40,6 +40,86 @@ struct mptcp_ext {
> > };
> >
> > #define MPTCPOPT_HMAC_LEN     20
> > +
> > +enum mptcp_data_avail {
> > +     MPTCP_SUBFLOW_NODATA,
> > +     MPTCP_SUBFLOW_DATA_AVAIL,
> > +};
> > +
> > +/* MPTCP subflow context */
> > +struct mptcp_subflow_context {
> > +     struct  list_head node;/* conn_list of subflows */
> > +
> > +     struct_group(reset,
> > +
> > +     unsigned long avg_pacing_rate; /* protected by msk socket lock */
> > +     u64     local_key;
> > +     u64     remote_key;
> > +     u64     idsn;
> > +     u64     map_seq;
> > +     u32     snd_isn;
> > +     u32     token;
> > +     u32     rel_write_seq;
> > +     u32     map_subflow_seq;
> > +     u32     ssn_offset;
> > +     u32     map_data_len;
> > +     __wsum  map_data_csum;
> > +     u32     map_csum_len;
> > +     u32     request_mptcp : 1,  /* send MP_CAPABLE */
> > +             request_join : 1,   /* send MP_JOIN */
> > +             request_bkup : 1,
> > +             mp_capable : 1,     /* remote is MPTCP capable */
> > +             mp_join : 1,        /* remote is JOINing */
> > +             fully_established : 1,      /* path validated */
> > +             pm_notified : 1,    /* PM hook called for established status */
> > +             conn_finished : 1,
> > +             map_valid : 1,
> > +             map_csum_reqd : 1,
> > +             map_data_fin : 1,
> > +             mpc_map : 1,
> > +             backup : 1,
> > +             send_mp_prio : 1,
> > +             send_mp_fail : 1,
> > +             send_fastclose : 1,
> > +             send_infinite_map : 1,
> > +             rx_eof : 1,
> > +             can_ack : 1,        /* only after processing the remote a key */
> > +             disposable : 1,     /* ctx can be free at ulp release time */
> > +             stale : 1,          /* unable to snd/rcv data, do not use for xmit */
> > +             local_id_valid : 1, /* local_id is correctly initialized */
> > +             valid_csum_seen : 1;        /* at least one csum validated */
> > +     enum mptcp_data_avail data_avail;
> > +     bool    mp_fail_response_expect;
> > +     u32     remote_nonce;
> > +     u64     thmac;
> > +     u32     local_nonce;
> > +     u32     remote_token;
> > +     u8      hmac[MPTCPOPT_HMAC_LEN];
> > +     u8      local_id;
> > +     u8      remote_id;
> > +     u8      reset_seen:1;
> > +     u8      reset_transient:1;
> > +     u8      reset_reason:4;
> > +     u8      stale_count;
> > +
> > +     long    delegated_status;
> > +
> > +     );
> > +
> > +     struct  list_head delegated_node;   /* link into delegated_action, protected by local BH */
> > +
> > +     u32     setsockopt_seq;
> > +     u32     stale_rcv_tstamp;
> > +
> > +     struct  sock *tcp_sock;     /* tcp sk backpointer */
> > +     struct  sock *conn;         /* parent mptcp_sock */
> > +     const   struct inet_connection_sock_af_ops *icsk_af_ops;
> > +     void    (*tcp_state_change)(struct sock *sk);
> > +     void    (*tcp_error_report)(struct sock *sk);
> > +
> > +     struct  rcu_head rcu;
> > +};
> > +
> > #define MPTCP_RM_IDS_MAX      8
> >
> > struct mptcp_rm_list {
> > @@ -198,6 +278,15 @@ static inline __be32 mptcp_reset_option(const struct sk_buff *skb)
> >
> >       return htonl(0u);
> > }
> > +
> > +static inline struct mptcp_subflow_context *
> > +mptcp_subflow_ctx(const struct sock *sk)
> > +{
> > +     struct inet_connection_sock *icsk = inet_csk(sk);
> > +
> > +     /* Use RCU on icsk_ulp_data only for sock diag code */
> > +     return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data;
> > +}
> > #else
> >
> > static inline void mptcp_init(void)
> > @@ -275,6 +364,8 @@ static inline int mptcp_subflow_init_cookie_req(struct request_sock *req,
> > }
> >
> > static inline __be32 mptcp_reset_option(const struct sk_buff *skb)  { return htonl(0u); }
> > +static inline struct mptcp_subflow_context *
> > +mptcp_subflow_ctx(const struct sock *sk) { return NULL; }
> > #endif /* CONFIG_MPTCP */
> >
> > #if IS_ENABLED(CONFIG_MPTCP_IPV6)
> > diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
> > index 8f03775a2f22..cc24756cedfe 100644
> > --- a/net/mptcp/protocol.h
> > +++ b/net/mptcp/protocol.h
> > @@ -409,11 +409,6 @@ mptcp_subflow_rsk(const struct request_sock *rsk)
> >       return (struct mptcp_subflow_request_sock *)rsk;
> > }
> >
> > -enum mptcp_data_avail {
> > -     MPTCP_SUBFLOW_NODATA,
> > -     MPTCP_SUBFLOW_DATA_AVAIL,
> > -};
> > -
> > struct mptcp_delegated_action {
> >       struct napi_struct napi;
> >       struct list_head head;
> > @@ -424,89 +419,6 @@ DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
> > #define MPTCP_DELEGATE_SEND           0
> > #define MPTCP_DELEGATE_ACK            1
> >
> > -/* MPTCP subflow context */
> > -struct mptcp_subflow_context {
> > -     struct  list_head node;/* conn_list of subflows */
> > -
> > -     struct_group(reset,
> > -
> > -     unsigned long avg_pacing_rate; /* protected by msk socket lock */
> > -     u64     local_key;
> > -     u64     remote_key;
> > -     u64     idsn;
> > -     u64     map_seq;
> > -     u32     snd_isn;
> > -     u32     token;
> > -     u32     rel_write_seq;
> > -     u32     map_subflow_seq;
> > -     u32     ssn_offset;
> > -     u32     map_data_len;
> > -     __wsum  map_data_csum;
> > -     u32     map_csum_len;
> > -     u32     request_mptcp : 1,  /* send MP_CAPABLE */
> > -             request_join : 1,   /* send MP_JOIN */
> > -             request_bkup : 1,
> > -             mp_capable : 1,     /* remote is MPTCP capable */
> > -             mp_join : 1,        /* remote is JOINing */
> > -             fully_established : 1,      /* path validated */
> > -             pm_notified : 1,    /* PM hook called for established status */
> > -             conn_finished : 1,
> > -             map_valid : 1,
> > -             map_csum_reqd : 1,
> > -             map_data_fin : 1,
> > -             mpc_map : 1,
> > -             backup : 1,
> > -             send_mp_prio : 1,
> > -             send_mp_fail : 1,
> > -             send_fastclose : 1,
> > -             send_infinite_map : 1,
> > -             rx_eof : 1,
> > -             can_ack : 1,        /* only after processing the remote a key */
> > -             disposable : 1,     /* ctx can be free at ulp release time */
> > -             stale : 1,          /* unable to snd/rcv data, do not use for xmit */
> > -             local_id_valid : 1, /* local_id is correctly initialized */
> > -             valid_csum_seen : 1;        /* at least one csum validated */
> > -     enum mptcp_data_avail data_avail;
> > -     bool    mp_fail_response_expect;
> > -     u32     remote_nonce;
> > -     u64     thmac;
> > -     u32     local_nonce;
> > -     u32     remote_token;
> > -     u8      hmac[MPTCPOPT_HMAC_LEN];
> > -     u8      local_id;
> > -     u8      remote_id;
> > -     u8      reset_seen:1;
> > -     u8      reset_transient:1;
> > -     u8      reset_reason:4;
> > -     u8      stale_count;
> > -
> > -     long    delegated_status;
> > -
> > -     );
> > -
> > -     struct  list_head delegated_node;   /* link into delegated_action, protected by local BH */
> > -
> > -     u32     setsockopt_seq;
> > -     u32     stale_rcv_tstamp;
> > -
> > -     struct  sock *tcp_sock;     /* tcp sk backpointer */
> > -     struct  sock *conn;         /* parent mptcp_sock */
> > -     const   struct inet_connection_sock_af_ops *icsk_af_ops;
> > -     void    (*tcp_state_change)(struct sock *sk);
> > -     void    (*tcp_error_report)(struct sock *sk);
> > -
> > -     struct  rcu_head rcu;
> > -};
> > -
> > -static inline struct mptcp_subflow_context *
> > -mptcp_subflow_ctx(const struct sock *sk)
> > -{
> > -     struct inet_connection_sock *icsk = inet_csk(sk);
> > -
> > -     /* Use RCU on icsk_ulp_data only for sock diag code */
> > -     return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data;
> > -}
> > -
> > static inline struct sock *
> > mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow)
> > {
> > --
> > 2.34.1
> >
> >
> >
>
> --
> Mat Martineau
> Intel
>

Re: [PATCH mptcp-next 02/17] mptcp: move mptcp_subflow_context in net/mptcp.h

[Mat Martineau]

On Thu, 19 May 2022, Geliang Tang wrote:

>>> Move struct mptcp_subflow_context definition from net/mptcp/protocol.h
>>> to include/net/mptcp.h. And move the related struct mptcp_data_avail and
>>> function mptcp_subflow_ctx() too.
>>>
>>> Signed-off-by: Geliang Tang <geliang.tang@suse.com>
>>
>> I'm not sure I agree with moving all of this just because Martin asked
>> about an inline function. I'll follow up on the netdev email thread.
>
> Mat, I removed the first three patches in v2. Could patch 1 still be
> used as an effective cleanup?

Sure, I'll update that in patchwork.


--
Mat Martineau
Intel

Re: [PATCH mptcp-next 01/17] mptcp: move MPTCPOPT_HMAC_LEN to net/mptcp.h

[Mat Martineau]

On Wed, 18 May 2022, Geliang Tang wrote:

> Move macro MPTCPOPT_HMAC_LEN definition from net/mptcp/protocol.h to
> include/net/mptcp.h.
>
> Signed-off-by: Geliang Tang <geliang.tang@suse.com>

This one's fine for the mptcp tree (will upstream to net-next):

Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>

> ---
> include/net/mptcp.h  | 3 ++-
> net/mptcp/protocol.h | 1 -
> 2 files changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/include/net/mptcp.h b/include/net/mptcp.h
> index d4ec894ce67b..4713757e36c1 100644
> --- a/include/net/mptcp.h
> +++ b/include/net/mptcp.h
> @@ -39,6 +39,7 @@ struct mptcp_ext {
> 			infinite_map:1;
> };
>
> +#define MPTCPOPT_HMAC_LEN	20
> #define MPTCP_RM_IDS_MAX	8
>
> struct mptcp_rm_list {
> @@ -89,7 +90,7 @@ struct mptcp_out_options {
> 			u32 nonce;
> 			u32 token;
> 			u64 thmac;
> -			u8 hmac[20];
> +			u8 hmac[MPTCPOPT_HMAC_LEN];
> 		};
> 	};
> #endif
> diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
> index 200f89f6d62f..8f03775a2f22 100644
> --- a/net/mptcp/protocol.h
> +++ b/net/mptcp/protocol.h
> @@ -83,7 +83,6 @@
>
> /* MPTCP MP_JOIN flags */
> #define MPTCPOPT_BACKUP		BIT(0)
> -#define MPTCPOPT_HMAC_LEN	20
> #define MPTCPOPT_THMAC_LEN	8
>
> /* MPTCP MP_CAPABLE flags */
> -- 
> 2.34.1
>
>
>

--
Mat Martineau
Intel

Re: [PATCH mptcp-next 01/17] mptcp: move MPTCPOPT_HMAC_LEN to net/mptcp.h

[Matthieu Baerts]

Hi Geliang, Mat,

On 19/05/2022 17:06, Mat Martineau wrote:
> On Wed, 18 May 2022, Geliang Tang wrote:
> 
>> Move macro MPTCPOPT_HMAC_LEN definition from net/mptcp/protocol.h to
>> include/net/mptcp.h.
>>
>> Signed-off-by: Geliang Tang <geliang.tang@suse.com>
> 
> This one's fine for the mptcp tree (will upstream to net-next):
> 
> Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>

Thank you for the patch and the review!

Now in our tree (feat. for net-next) with Mat's RvB tag:

New patches for t/upstream:

- e4afdbb036ca: mptcp: move MPTCPOPT_HMAC_LEN to net/mptcp.h

- Results: 086d4a4a0f34..52d9427a77d9 (export)

Builds and tests are now in progress:



https://cirrus-ci.com/github/multipath-tcp/mptcp_net-next/export/20220519T160645

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