[PATCH v3 net-next 2/5] net: tracepoint: replace tcp_set_state tracepoint with inet_sock_set_state tracepoint

[Yafang Shao]

As sk_state is a common field for struct sock, so the state
transition tracepoint should not be a TCP specific feature.
Currently it traces all AF_INET state transition, so I rename this
tracepoint to inet_sock_set_state tracepoint with some minor changes and move it
into trace/events/sock.h.
We dont need to create a file named trace/events/inet_sock.h for this one single
tracepoint.

Two helpers are introduced to trace sk_state transition
    - void inet_sk_state_store(struct sock *sk, int newstate);
    - void inet_sk_set_state(struct sock *sk, int state);
As trace header should not be included in other header files,
so they are defined in sock.c.

The protocol such as SCTP maybe compiled as a ko, hence export
inet_sk_set_state().

Signed-off-by: Yafang Shao <laoar.shao@xxxxxxxxx>
---
 include/net/inet_sock.h         |   2 +
 include/trace/events/sock.h     | 107 ++++++++++++++++++++++++++++++++++++++++
 include/trace/events/tcp.h      |  31 ------------
 net/ipv4/af_inet.c              |  14 ++++++
 net/ipv4/inet_connection_sock.c |   6 +--
 net/ipv4/inet_hashtables.c      |   2 +-
 net/ipv4/tcp.c                  |   6 +--
 7 files changed, 128 insertions(+), 40 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 39efb96..a3431a4 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -290,6 +290,8 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to,
 #endif
 
 int inet_sk_rebuild_header(struct sock *sk);
+void inet_sk_set_state(struct sock *sk, int state);
+void inet_sk_state_store(struct sock *sk, int newstate);
 
 static inline unsigned int __inet_ehashfn(const __be32 laddr,
 					  const __u16 lport,
diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h
index ec4dade..3b9094a 100644
--- a/include/trace/events/sock.h
+++ b/include/trace/events/sock.h
@@ -6,7 +6,50 @@
 #define _TRACE_SOCK_H
 
 #include <net/sock.h>
+#include <net/ipv6.h>
 #include <linux/tracepoint.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+
+/* The protocol traced by sock_set_state */
+#define inet_protocol_names		\
+		EM(IPPROTO_TCP)			\
+		EM(IPPROTO_DCCP)		\
+		EMe(IPPROTO_SCTP)
+
+#define tcp_state_names			\
+		EM(TCP_ESTABLISHED)		\
+		EM(TCP_SYN_SENT)		\
+		EM(TCP_SYN_RECV)		\
+		EM(TCP_FIN_WAIT1)		\
+		EM(TCP_FIN_WAIT2)		\
+		EM(TCP_TIME_WAIT)		\
+		EM(TCP_CLOSE)			\
+		EM(TCP_CLOSE_WAIT)		\
+		EM(TCP_LAST_ACK)		\
+		EM(TCP_LISTEN)			\
+		EM(TCP_CLOSING)			\
+		EMe(TCP_NEW_SYN_RECV)
+
+/* enums need to be exported to user space */
+#undef EM
+#undef EMe
+#define EM(a)       TRACE_DEFINE_ENUM(a);
+#define EMe(a)      TRACE_DEFINE_ENUM(a);
+
+inet_protocol_names
+tcp_state_names
+
+#undef EM
+#undef EMe
+#define EM(a)       { a, #a },
+#define EMe(a)      { a, #a }
+
+#define show_inet_protocol_name(val)    \
+	__print_symbolic(val, inet_protocol_names)
+
+#define show_tcp_state_name(val)        \
+	__print_symbolic(val, tcp_state_names)
 
 TRACE_EVENT(sock_rcvqueue_full,
 
@@ -63,6 +106,70 @@
 		__entry->rmem_alloc)
 );
 
+TRACE_EVENT(inet_sock_set_state,
+
+	TP_PROTO(const struct sock *sk, const int oldstate, const int newstate),
+
+	TP_ARGS(sk, oldstate, newstate),
+
+	TP_STRUCT__entry(
+		__field(const void *, skaddr)
+		__field(int, oldstate)
+		__field(int, newstate)
+		__field(__u16, sport)
+		__field(__u16, dport)
+		__field(__u8, protocol)
+		__array(__u8, saddr, 4)
+		__array(__u8, daddr, 4)
+		__array(__u8, saddr_v6, 16)
+		__array(__u8, daddr_v6, 16)
+	),
+
+	TP_fast_assign(
+		struct inet_sock *inet = inet_sk(sk);
+		struct in6_addr *pin6;
+		__be32 *p32;
+
+		__entry->skaddr = sk;
+		__entry->oldstate = oldstate;
+		__entry->newstate = newstate;
+
+		__entry->protocol = sk->sk_protocol;
+		__entry->sport = ntohs(inet->inet_sport);
+		__entry->dport = ntohs(inet->inet_dport);
+
+		p32 = (__be32 *) __entry->saddr;
+		*p32 = inet->inet_saddr;
+
+		p32 = (__be32 *) __entry->daddr;
+		*p32 =  inet->inet_daddr;
+
+#if IS_ENABLED(CONFIG_IPV6)
+		if (sk->sk_family == AF_INET6) {
+			pin6 = (struct in6_addr *)__entry->saddr_v6;
+			*pin6 = sk->sk_v6_rcv_saddr;
+			pin6 = (struct in6_addr *)__entry->daddr_v6;
+			*pin6 = sk->sk_v6_daddr;
+		} else
+#endif
+		{
+			pin6 = (struct in6_addr *)__entry->saddr_v6;
+			ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);
+			pin6 = (struct in6_addr *)__entry->daddr_v6;
+			ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);
+		}
+	),
+
+	TP_printk("protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4"
+			"saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s",
+			show_inet_protocol_name(__entry->protocol),
+			__entry->sport, __entry->dport,
+			__entry->saddr, __entry->daddr,
+			__entry->saddr_v6, __entry->daddr_v6,
+			show_tcp_state_name(__entry->oldstate),
+			show_tcp_state_name(__entry->newstate))
+);
+
 #endif /* _TRACE_SOCK_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index ec52fb3..8e88a16 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -9,37 +9,6 @@
 #include <linux/tracepoint.h>
 #include <net/ipv6.h>
 
-#define tcp_state_names         \
-		EM(TCP_ESTABLISHED)     \
-		EM(TCP_SYN_SENT)        \
-		EM(TCP_SYN_RECV)        \
-		EM(TCP_FIN_WAIT1)       \
-		EM(TCP_FIN_WAIT2)       \
-		EM(TCP_TIME_WAIT)       \
-		EM(TCP_CLOSE)           \
-		EM(TCP_CLOSE_WAIT)      \
-		EM(TCP_LAST_ACK)        \
-		EM(TCP_LISTEN)          \
-		EM(TCP_CLOSING)         \
-		EMe(TCP_NEW_SYN_RECV)   \
-
-/* enums need to be exported to user space */
-#undef EM
-#undef EMe
-#define EM(a)         TRACE_DEFINE_ENUM(a);
-#define EMe(a)        TRACE_DEFINE_ENUM(a);
-
-tcp_state_names
-
-#undef EM
-#undef EMe
-#define EM(a)         tcp_state_name(a),
-#define EMe(a)        tcp_state_name(a)
-
-#define tcp_state_name(state)	{ state, #state }
-#define show_tcp_state_name(val)			\
-	__print_symbolic(val, tcp_state_names)
-
 /*
  * tcp event with arguments sk and skb
  *
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index f00499a..bab98a4 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -121,6 +121,7 @@
 #endif
 #include <net/l3mdev.h>
 
+#include <trace/events/sock.h>
 
 /* The inetsw table contains everything that inet_create needs to
  * build a new socket.
@@ -1220,6 +1221,19 @@ int inet_sk_rebuild_header(struct sock *sk)
 }
 EXPORT_SYMBOL(inet_sk_rebuild_header);
 
+void inet_sk_set_state(struct sock *sk, int state)
+{
+	trace_inet_sock_set_state(sk, sk->sk_state, state);
+	sk->sk_state = state;
+}
+EXPORT_SYMBOL(inet_sk_set_state);
+
+void inet_sk_state_store(struct sock *sk, int newstate)
+{
+	trace_inet_sock_set_state(sk, sk->sk_state, newstate);
+	smp_store_release(&sk->sk_state, newstate);
+}
+
 struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 				 netdev_features_t features)
 {
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 4ca46dc..f460fc0 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -783,7 +783,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 	if (newsk) {
 		struct inet_connection_sock *newicsk = inet_csk(newsk);
 
-		newsk->sk_state = TCP_SYN_RECV;
+		inet_sk_set_state(newsk, TCP_SYN_RECV);
 		newicsk->icsk_bind_hash = NULL;
 
 		inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port;
@@ -877,7 +877,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
 	 * It is OK, because this socket enters to hash table only
 	 * after validation is complete.
 	 */
-	sk_state_store(sk, TCP_LISTEN);
+	inet_sk_state_store(sk, TCP_LISTEN);
 	if (!sk->sk_prot->get_port(sk, inet->inet_num)) {
 		inet->inet_sport = htons(inet->inet_num);
 
@@ -888,7 +888,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
 			return 0;
 	}
 
-	sk->sk_state = TCP_CLOSE;
+	inet_sk_set_state(sk, TCP_CLOSE);
 	return err;
 }
 EXPORT_SYMBOL_GPL(inet_csk_listen_start);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index f6f5810..37b7da0 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -544,7 +544,7 @@ bool inet_ehash_nolisten(struct sock *sk, struct sock *osk)
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
 	} else {
 		percpu_counter_inc(sk->sk_prot->orphan_count);
-		sk->sk_state = TCP_CLOSE;
+		inet_sk_set_state(sk, TCP_CLOSE);
 		sock_set_flag(sk, SOCK_DEAD);
 		inet_csk_destroy_sock(sk);
 	}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c470fec..d408fb4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -283,8 +283,6 @@
 #include <asm/ioctls.h>
 #include <net/busy_poll.h>
 
-#include <trace/events/tcp.h>
-
 struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
@@ -2040,8 +2038,6 @@ void tcp_set_state(struct sock *sk, int state)
 {
 	int oldstate = sk->sk_state;
 
-	trace_tcp_set_state(sk, oldstate, state);
-
 	switch (state) {
 	case TCP_ESTABLISHED:
 		if (oldstate != TCP_ESTABLISHED)
@@ -2065,7 +2061,7 @@ void tcp_set_state(struct sock *sk, int state)
 	/* Change state AFTER socket is unhashed to avoid closed
 	 * socket sitting in hash tables.
 	 */
-	sk_state_store(sk, state);
+	inet_sk_state_store(sk, state);
 
 #ifdef STATE_TRACE
 	SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]);
-- 
1.8.3.1