Merge branch 'replace-tcp_set_state-tracepoint-with-inet_sock_set_state'

Yafang Shao says:

====================
replace tcp_set_state tracepoint with inet_sock_set_state

According to the discussion in the mail thread
https://patchwork.kernel.org/patch/10099243/,
tcp_set_state tracepoint is renamed to inet_sock_set_state tracepoint and is
moved to include/trace/events/sock.h.

With this new tracepoint, we can trace AF_INET/AF_INET6 sock state transitions.
As there's only one single tracepoint for inet, so I didn't create a new trace
file named trace/events/inet_sock.h, and just place it in
include/trace/events/sock.h

Currently TCP/DCCP/SCTP state transitions are traced with this tracepoint.

- Why not more protocol ?
If we really think that anonter protocol should be traced, I will modify the
code to trace it.
I just want to make the code easy and not output useless information.
====================

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

15 files changed, 167 insertions, 66 deletions

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 39efb968b7a4..0a671c32d6b9 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -291,6 +291,31 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to,
 
 int inet_sk_rebuild_header(struct sock *sk);
 
+/**
+ * inet_sk_state_load - read sk->sk_state for lockless contexts
+ * @sk: socket pointer
+ *
+ * Paired with inet_sk_state_store(). Used in places we don't hold socket lock:
+ * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ...
+ */
+static inline int inet_sk_state_load(const struct sock *sk)
+{
+	/* state change might impact lockless readers. */
+	return smp_load_acquire(&sk->sk_state);
+}
+
+/**
+ * inet_sk_state_store - update sk->sk_state
+ * @sk: socket pointer
+ * @newstate: new state
+ *
+ * Paired with inet_sk_state_load(). Should be used in contexts where
+ * state change might impact lockless readers.
+ */
+void inet_sk_state_store(struct sock *sk, int newstate);
+
+void inet_sk_set_state(struct sock *sk, int state);
+
 static inline unsigned int __inet_ehashfn(const __be32 laddr,
 					  const __u16 lport,
 					  const __be32 faddr,
diff --git a/include/net/sock.h b/include/net/sock.h
index 0a32f3ce381c..6c1db823f8b9 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2333,31 +2333,6 @@ static inline bool sk_listener(const struct sock *sk)
 	return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV);
 }
 
-/**
- * sk_state_load - read sk->sk_state for lockless contexts
- * @sk: socket pointer
- *
- * Paired with sk_state_store(). Used in places we do not hold socket lock :
- * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ...
- */
-static inline int sk_state_load(const struct sock *sk)
-{
-	return smp_load_acquire(&sk->sk_state);
-}
-
-/**
- * sk_state_store - update sk->sk_state
- * @sk: socket pointer
- * @newstate: new state
- *
- * Paired with sk_state_load(). Should be used in contexts where
- * state change might impact lockless readers.
- */
-static inline void sk_state_store(struct sock *sk, int newstate)
-{
-	smp_store_release(&sk->sk_state, newstate);
-}
-
 void sock_enable_timestamp(struct sock *sk, int flag);
 int sock_get_timestamp(struct sock *, struct timeval __user *);
 int sock_get_timestampns(struct sock *, struct timespec __user *);
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 */
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index 07cccca6cbf1..8e88a1671538 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -9,22 +9,6 @@
 #include <linux/tracepoint.h>
 #include <net/ipv6.h>
 
-#define tcp_state_name(state)	{ state, #state }
-#define show_tcp_state_name(val)			\
-	__print_symbolic(val,				\
-		tcp_state_name(TCP_ESTABLISHED),	\
-		tcp_state_name(TCP_SYN_SENT),		\
-		tcp_state_name(TCP_SYN_RECV),		\
-		tcp_state_name(TCP_FIN_WAIT1),		\
-		tcp_state_name(TCP_FIN_WAIT2),		\
-		tcp_state_name(TCP_TIME_WAIT),		\
-		tcp_state_name(TCP_CLOSE),		\
-		tcp_state_name(TCP_CLOSE_WAIT),		\
-		tcp_state_name(TCP_LAST_ACK),		\
-		tcp_state_name(TCP_LISTEN),		\
-		tcp_state_name(TCP_CLOSING),		\
-		tcp_state_name(TCP_NEW_SYN_RECV))
-
 /*
  * tcp event with arguments sk and skb
  *
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 9d43c1f40274..7a75a1d3568b 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -110,7 +110,7 @@ void dccp_set_state(struct sock *sk, const int state)
 	/* Change state AFTER socket is unhashed to avoid closed
 	 * socket sitting in hash tables.
 	 */
-	sk->sk_state = state;
+	inet_sk_set_state(sk, state);
 }
 
 EXPORT_SYMBOL_GPL(dccp_set_state);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index f00499a46927..bab98a4fedad 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 4ca46dc08e63..12410ec6f7f7 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -685,7 +685,7 @@ static void reqsk_timer_handler(struct timer_list *t)
 	int max_retries, thresh;
 	u8 defer_accept;
 
-	if (sk_state_load(sk_listener) != TCP_LISTEN)
+	if (inet_sk_state_load(sk_listener) != TCP_LISTEN)
 		goto drop;
 
 	max_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
@@ -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 f6f58108b4c5..37b7da0b975d 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 c470fec9062f..67d39b79c801 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);
 
@@ -504,7 +502,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 	sock_poll_wait(file, sk_sleep(sk), wait);
 
-	state = sk_state_load(sk);
+	state = inet_sk_state_load(sk);
 	if (state == TCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 
@@ -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]);
@@ -2920,7 +2916,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	if (sk->sk_type != SOCK_STREAM)
 		return;
 
-	info->tcpi_state = sk_state_load(sk);
+	info->tcpi_state = inet_sk_state_load(sk);
 
 	/* Report meaningful fields for all TCP states, including listeners */
 	rate = READ_ONCE(sk->sk_pacing_rate);
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index abbf0edcf6c2..81148f7a2323 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -24,7 +24,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 {
 	struct tcp_info *info = _info;
 
-	if (sk_state_load(sk) == TCP_LISTEN) {
+	if (inet_sk_state_load(sk) == TCP_LISTEN) {
 		r->idiag_rqueue = sk->sk_ack_backlog;
 		r->idiag_wqueue = sk->sk_max_ack_backlog;
 	} else if (sk->sk_type == SOCK_STREAM) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 94e28350f420..dd945b114215 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2281,7 +2281,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 		timer_expires = jiffies;
 	}
 
-	state = sk_state_load(sk);
+	state = inet_sk_state_load(sk);
 	if (state == TCP_LISTEN)
 		rx_queue = sk->sk_ack_backlog;
 	else
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7178476b3d2f..aa12a26a96c6 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1795,7 +1795,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 		timer_expires = jiffies;
 	}
 
-	state = sk_state_load(sp);
+	state = inet_sk_state_load(sp);
 	if (state == TCP_LISTEN)
 		rx_queue = sp->sk_ack_backlog;
 	else
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index ee1e601a0b11..8b3146816519 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -232,7 +232,7 @@ void sctp_endpoint_free(struct sctp_endpoint *ep)
 {
 	ep->base.dead = true;
 
-	ep->base.sk->sk_state = SCTP_SS_CLOSED;
+	inet_sk_set_state(ep->base.sk, SCTP_SS_CLOSED);
 
 	/* Unlink this endpoint, so we can't find it again! */
 	sctp_unhash_endpoint(ep);
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 16ddf2ca1438..b71e7fb0a20a 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -878,12 +878,12 @@ static void sctp_cmd_new_state(struct sctp_cmd_seq *cmds,
 		 * successfully completed a connect() call.
 		 */
 		if (sctp_state(asoc, ESTABLISHED) && sctp_sstate(sk, CLOSED))
-			sk->sk_state = SCTP_SS_ESTABLISHED;
+			inet_sk_set_state(sk, SCTP_SS_ESTABLISHED);
 
 		/* Set the RCV_SHUTDOWN flag when a SHUTDOWN is received. */
 		if (sctp_state(asoc, SHUTDOWN_RECEIVED) &&
 		    sctp_sstate(sk, ESTABLISHED)) {
-			sk->sk_state = SCTP_SS_CLOSING;
+			inet_sk_set_state(sk, SCTP_SS_CLOSING);
 			sk->sk_shutdown |= RCV_SHUTDOWN;
 		}
 	}
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 5e4100df7bae..aadcd4244d9b 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1544,7 +1544,7 @@ static void sctp_close(struct sock *sk, long timeout)
 
 	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
 	sk->sk_shutdown = SHUTDOWN_MASK;
-	sk->sk_state = SCTP_SS_CLOSING;
+	inet_sk_set_state(sk, SCTP_SS_CLOSING);
 
 	ep = sctp_sk(sk)->ep;
 
@@ -4657,7 +4657,7 @@ static void sctp_shutdown(struct sock *sk, int how)
 	if (how & SEND_SHUTDOWN && !list_empty(&ep->asocs)) {
 		struct sctp_association *asoc;
 
-		sk->sk_state = SCTP_SS_CLOSING;
+		inet_sk_set_state(sk, SCTP_SS_CLOSING);
 		asoc = list_entry(ep->asocs.next,
 				  struct sctp_association, asocs);
 		sctp_primitive_SHUTDOWN(net, asoc, NULL);
@@ -7513,13 +7513,13 @@ static int sctp_listen_start(struct sock *sk, int backlog)
 	 * sockets.
 	 *
 	 */
-	sk->sk_state = SCTP_SS_LISTENING;
+	inet_sk_set_state(sk, SCTP_SS_LISTENING);
 	if (!ep->base.bind_addr.port) {
 		if (sctp_autobind(sk))
 			return -EAGAIN;
 	} else {
 		if (sctp_get_port(sk, inet_sk(sk)->inet_num)) {
-			sk->sk_state = SCTP_SS_CLOSED;
+			inet_sk_set_state(sk, SCTP_SS_CLOSED);
 			return -EADDRINUSE;
 		}
 	}
@@ -8542,10 +8542,10 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	 * is called, set RCV_SHUTDOWN flag.
 	 */
 	if (sctp_state(assoc, CLOSED) && sctp_style(newsk, TCP)) {
-		newsk->sk_state = SCTP_SS_CLOSED;
+		inet_sk_set_state(newsk, SCTP_SS_CLOSED);
 		newsk->sk_shutdown |= RCV_SHUTDOWN;
 	} else {
-		newsk->sk_state = SCTP_SS_ESTABLISHED;
+		inet_sk_set_state(newsk, SCTP_SS_ESTABLISHED);
 	}
 
 	release_sock(newsk);