Add a tracepoint to monitor TCP congestion window adjustments through the
tcp_cwnd_reduction() function. This tracepoint helps track:
  - TCP window size fluctuations
  - Active socket behavior
  - Congestion window reduction events

Meta has been using BPF programs to monitor this function for years. By
adding a proper tracepoint, we provide a stable API for all users who
need to monitor TCP congestion window behavior.

The tracepoint captures:
  - Socket source and destination IPs
  - Number of newly acknowledged packets
  - Number of newly lost packets
  - Packets in flight

Here is an example of a tracepoint when viewed in the trace buffer:

tcp_cwnd_reduction: src=[2401:db00:3021:10e1:face:0:32a:0]:45904 
dest=[2401:db00:3021:1fb:face:0:23:0]:5201 newly_lost=0 newly_acked_sacked=27 
in_flight=34

CC: Yonghong Song <yonghong.s...@linux.dev>
CC: Song Liu <s...@kernel.org>
CC: Martin KaFai Lau <martin....@kernel.org>
Signed-off-by: Breno Leitao <lei...@debian.org>
---
 include/trace/events/tcp.h | 34 ++++++++++++++++++++++++++++++++++
 net/ipv4/tcp_input.c       |  2 ++
 2 files changed, 36 insertions(+)

diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index 
a27c4b619dffd7dcc72fffa71bf0fd5e34fe6681..b3a636658b39721cca843c0000eaa573cf4d09d5
 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -259,6 +259,40 @@ TRACE_EVENT(tcp_retransmit_synack,
                  __entry->saddr_v6, __entry->daddr_v6)
 );
 
+TRACE_EVENT(tcp_cwnd_reduction,
+
+       TP_PROTO(const struct sock *sk, const int newly_acked_sacked,
+                const int newly_lost, const int flag),
+
+       TP_ARGS(sk, newly_acked_sacked, newly_lost, flag),
+
+       TP_STRUCT__entry(
+               __array(__u8, saddr, sizeof(struct sockaddr_in6))
+               __array(__u8, daddr, sizeof(struct sockaddr_in6))
+               __field(int, in_flight)
+
+               __field(int, newly_acked_sacked)
+               __field(int, newly_lost)
+       ),
+
+       TP_fast_assign(
+               const struct inet_sock *inet = inet_sk(sk);
+               const struct tcp_sock *tp = tcp_sk(sk);
+
+               memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
+               memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
+
+               TP_STORE_ADDR_PORTS(__entry, inet, sk);
+               __entry->in_flight = tcp_packets_in_flight(tp);
+               __entry->newly_lost = newly_lost;
+               __entry->newly_acked_sacked = newly_acked_sacked;
+       ),
+
+       TP_printk("src=%pISpc dest=%pISpc newly_lost=%d newly_acked_sacked=%d 
in_flight=%d",
+                 __entry->saddr, __entry->daddr, __entry->newly_lost,
+                 __entry->newly_acked_sacked, __entry->in_flight)
+);
+
 #include <trace/events/net_probe_common.h>
 
 TRACE_EVENT(tcp_probe,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 
4811727b8a02258ec6fa1fd129beecf7cbb0f90e..fc88c511e81bc12ec57e8dc3e9185a920d1bd079
 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2710,6 +2710,8 @@ void tcp_cwnd_reduction(struct sock *sk, int 
newly_acked_sacked, int newly_lost,
        if (newly_acked_sacked <= 0 || WARN_ON_ONCE(!tp->prior_cwnd))
                return;
 
+       trace_tcp_cwnd_reduction(sk, newly_acked_sacked, newly_lost, flag);
+
        tp->prr_delivered += newly_acked_sacked;
        if (delta < 0) {
                u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered +

---
base-commit: 96e12defe5a8fa3f3a10e3ef1d20fee503245a10
change-id: 20250120-cwnd_tracepoint-2e11c996a9cb

Best regards,
-- 
Breno Leitao <lei...@debian.org>


Reply via email to