tcp: Add tracepoint for tcp_set_ca_state

The congestion status of a tcp flow may be updated since there
is congestion between tcp sender and receiver. It makes sense to
add tracepoint for congestion status set function to summate cc
status duration and evaluate the performance of network
and congestion algorithm. the backgound of this patch is below.

Link: https://github.com/iovisor/bcc/pull/3899

Signed-off-by: Ping Gan <jacky_gam_2001@163.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20220406010956.19656-1-jacky_gam_2001@163.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 60 insertions, 9 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 54aa2f02bb63..6d50a662bf89 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1139,15 +1139,6 @@ static inline bool tcp_ca_needs_ecn(const struct sock *sk)
 	return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN;
 }
 
-static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
-{
-	struct inet_connection_sock *icsk = inet_csk(sk);
-
-	if (icsk->icsk_ca_ops->set_state)
-		icsk->icsk_ca_ops->set_state(sk, ca_state);
-	icsk->icsk_ca_state = ca_state;
-}
-
 static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1156,6 +1147,9 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
 		icsk->icsk_ca_ops->cwnd_event(sk, event);
 }
 
+/* From tcp_cong.c */
+void tcp_set_ca_state(struct sock *sk, const u8 ca_state);
+
 /* From tcp_rate.c */
 void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb);
 void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index edcd6369de10..901b440238d5 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -371,6 +371,51 @@ DEFINE_EVENT(tcp_event_skb, tcp_bad_csum,
 	TP_ARGS(skb)
 );
 
+TRACE_EVENT(tcp_cong_state_set,
+
+	TP_PROTO(struct sock *sk, const u8 ca_state),
+
+	TP_ARGS(sk, ca_state),
+
+	TP_STRUCT__entry(
+		__field(const void *, skaddr)
+		__field(__u16, sport)
+		__field(__u16, dport)
+		__array(__u8, saddr, 4)
+		__array(__u8, daddr, 4)
+		__array(__u8, saddr_v6, 16)
+		__array(__u8, daddr_v6, 16)
+		__field(__u8, cong_state)
+	),
+
+	TP_fast_assign(
+		struct inet_sock *inet = inet_sk(sk);
+		__be32 *p32;
+
+		__entry->skaddr = sk;
+
+		__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;
+
+		TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr,
+			   sk->sk_v6_rcv_saddr, sk->sk_v6_daddr);
+
+		__entry->cong_state = ca_state;
+	),
+
+	TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u",
+		  __entry->sport, __entry->dport,
+		  __entry->saddr, __entry->daddr,
+		  __entry->saddr_v6, __entry->daddr_v6,
+		  __entry->cong_state)
+);
+
 #endif /* _TRACE_TCP_H */
 
 /* This part must be outside protection */
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index d854bcfb9906..d3cae40749e8 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -16,6 +16,7 @@
 #include <linux/gfp.h>
 #include <linux/jhash.h>
 #include <net/tcp.h>
+#include <trace/events/tcp.h>
 
 static DEFINE_SPINLOCK(tcp_cong_list_lock);
 static LIST_HEAD(tcp_cong_list);
@@ -33,6 +34,17 @@ struct tcp_congestion_ops *tcp_ca_find(const char *name)
 	return NULL;
 }
 
+void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	trace_tcp_cong_state_set(sk, ca_state);
+
+	if (icsk->icsk_ca_ops->set_state)
+		icsk->icsk_ca_ops->set_state(sk, ca_state);
+	icsk->icsk_ca_state = ca_state;
+}
+
 /* Must be called with rcu lock held */
 static struct tcp_congestion_ops *tcp_ca_find_autoload(struct net *net,
 						       const char *name)