Merge branch 'tcp-make-trace-of-reset-logic-complete'

Jason Xing says:

====================
tcp: make trace of reset logic complete

Before this, we miss some cases where the TCP layer could send RST but
we cannot trace it. So I decided to complete it :)

Link: https://lore.kernel.org/all/20240329034243.7929-1-kerneljasonxing@gmail.com/
====================

Link: https://lore.kernel.org/r/20240401073605.37335-1-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 56 insertions, 18 deletions

diff --git a/include/trace/events/net_probe_common.h b/include/trace/events/net_probe_common.h
index 5e33f91bdea373..976a58364bff15 100644
--- a/include/trace/events/net_probe_common.h
+++ b/include/trace/events/net_probe_common.h
@@ -70,14 +70,14 @@
 	TP_STORE_V4MAPPED(__entry, saddr, daddr)
 #endif
 
-#define TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb, protoh)		\
+#define TP_STORE_ADDR_PORTS_SKB_V4(skb, protoh, entry_saddr, entry_daddr) \
 	do {								\
-		struct sockaddr_in *v4 = (void *)__entry->saddr;	\
+		struct sockaddr_in *v4 = (void *)entry_saddr;		\
 									\
 		v4->sin_family = AF_INET;				\
 		v4->sin_port = protoh->source;				\
 		v4->sin_addr.s_addr = ip_hdr(skb)->saddr;		\
-		v4 = (void *)__entry->daddr;				\
+		v4 = (void *)entry_daddr;				\
 		v4->sin_family = AF_INET;				\
 		v4->sin_port = protoh->dest;				\
 		v4->sin_addr.s_addr = ip_hdr(skb)->daddr;		\
@@ -85,28 +85,30 @@
 
 #if IS_ENABLED(CONFIG_IPV6)
 
-#define TP_STORE_ADDR_PORTS_SKB(__entry, skb, protoh)			\
+#define TP_STORE_ADDR_PORTS_SKB(skb, protoh, entry_saddr, entry_daddr)	\
 	do {								\
 		const struct iphdr *iph = ip_hdr(skb);			\
 									\
 		if (iph->version == 6) {				\
-			struct sockaddr_in6 *v6 = (void *)__entry->saddr; \
+			struct sockaddr_in6 *v6 = (void *)entry_saddr;	\
 									\
 			v6->sin6_family = AF_INET6;			\
 			v6->sin6_port = protoh->source;			\
 			v6->sin6_addr = ipv6_hdr(skb)->saddr;		\
-			v6 = (void *)__entry->daddr;			\
+			v6 = (void *)entry_daddr;			\
 			v6->sin6_family = AF_INET6;			\
 			v6->sin6_port = protoh->dest;			\
 			v6->sin6_addr = ipv6_hdr(skb)->daddr;		\
 		} else							\
-			TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb, protoh); \
+			TP_STORE_ADDR_PORTS_SKB_V4(skb, protoh,		\
+						   entry_saddr,		\
+						   entry_daddr);	\
 	} while (0)
 
 #else
 
-#define TP_STORE_ADDR_PORTS_SKB(__entry, skb, protoh)		\
-	TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb, protoh)
+#define TP_STORE_ADDR_PORTS_SKB(skb, protoh, entry_saddr, entry_daddr)	\
+	TP_STORE_ADDR_PORTS_SKB_V4(skb, protoh, entry_saddr, entry_daddr)
 
 #endif
 
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index 1db95175c1e528..5c04a61a11c2c8 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -78,11 +78,47 @@ DEFINE_EVENT(tcp_event_sk_skb, tcp_retransmit_skb,
  * skb of trace_tcp_send_reset is the skb that caused RST. In case of
  * active reset, skb should be NULL
  */
-DEFINE_EVENT(tcp_event_sk_skb, tcp_send_reset,
+TRACE_EVENT(tcp_send_reset,
 
 	TP_PROTO(const struct sock *sk, const struct sk_buff *skb),
 
-	TP_ARGS(sk, skb)
+	TP_ARGS(sk, skb),
+
+	TP_STRUCT__entry(
+		__field(const void *, skbaddr)
+		__field(const void *, skaddr)
+		__field(int, state)
+		__array(__u8, saddr, sizeof(struct sockaddr_in6))
+		__array(__u8, daddr, sizeof(struct sockaddr_in6))
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		__entry->skaddr = sk;
+		/* Zero means unknown state. */
+		__entry->state = sk ? sk->sk_state : 0;
+
+		memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
+		memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
+
+		if (sk && sk_fullsock(sk)) {
+			const struct inet_sock *inet = inet_sk(sk);
+
+			TP_STORE_ADDR_PORTS(__entry, inet, sk);
+		} else if (skb) {
+			const struct tcphdr *th = (const struct tcphdr *)skb->data;
+			/*
+			 * We should reverse the 4-tuple of skb, so later
+			 * it can print the right flow direction of rst.
+			 */
+			TP_STORE_ADDR_PORTS_SKB(skb, th, entry->daddr, entry->saddr);
+		}
+	),
+
+	TP_printk("skbaddr=%p skaddr=%p src=%pISpc dest=%pISpc state=%s",
+		  __entry->skbaddr, __entry->skaddr,
+		  __entry->saddr, __entry->daddr,
+		  __entry->state ? show_tcp_state_name(__entry->state) : "UNKNOWN")
 );
 
 /*
@@ -295,7 +331,7 @@ DECLARE_EVENT_CLASS(tcp_event_skb,
 		memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
 		memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
 
-		TP_STORE_ADDR_PORTS_SKB(__entry, skb, th);
+		TP_STORE_ADDR_PORTS_SKB(skb, th, __entry->saddr, __entry->daddr);
 	),
 
 	TP_printk("skbaddr=%p src=%pISpc dest=%pISpc",
diff --git a/include/trace/events/udp.h b/include/trace/events/udp.h
index 62bebe2a6ecebd..6142be4068e29b 100644
--- a/include/trace/events/udp.h
+++ b/include/trace/events/udp.h
@@ -38,7 +38,7 @@ TRACE_EVENT(udp_fail_queue_rcv_skb,
 		memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
 		memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
 
-		TP_STORE_ADDR_PORTS_SKB(__entry, skb, uh);
+		TP_STORE_ADDR_PORTS_SKB(skb, uh, __entry->saddr, __entry->daddr);
 	),
 
 	TP_printk("rc=%d family=%s src=%pISpc dest=%pISpc", __entry->rc,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1e0a9762f92e60..56b75efcfd12bf 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -866,11 +866,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	 * routing might fail in this case. No choice here, if we choose to force
 	 * input interface, we will misroute in case of asymmetric route.
 	 */
-	if (sk) {
+	if (sk)
 		arg.bound_dev_if = sk->sk_bound_dev_if;
-		if (sk_fullsock(sk))
-			trace_tcp_send_reset(sk, skb);
-	}
+
+	trace_tcp_send_reset(sk, skb);
 
 	BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) !=
 		     offsetof(struct inet_timewait_sock, tw_bound_dev_if));
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5ae74f661d25f9..cffebaec66f1ab 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1113,7 +1113,6 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 	if (sk) {
 		oif = sk->sk_bound_dev_if;
 		if (sk_fullsock(sk)) {
-			trace_tcp_send_reset(sk, skb);
 			if (inet6_test_bit(REPFLOW, sk))
 				label = ip6_flowlabel(ipv6h);
 			priority = READ_ONCE(sk->sk_priority);
@@ -1129,6 +1128,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 			label = ip6_flowlabel(ipv6h);
 	}
 
+	trace_tcp_send_reset(sk, skb);
+
 	tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, 1,
 			     ipv6_get_dsfield(ipv6h), label, priority, txhash,
 			     &key);