net: tracepoint: replace tcp_set_state tracepoint with inet_sock_set_state tracepoint

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@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 107 insertions, 0 deletions

diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h
index ec4dade24466..3b9094a07b80 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 @@ TRACE_EVENT(sock_exceed_buf_limit,
 		__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 */