Merge branch 'implement-reset-reason-mechanism-to-detect'

Jason Xing says:

====================
Implement reset reason mechanism to detect

From: Jason Xing <kernelxing@tencent.com>

In production, there are so many cases about why the RST skb is sent but
we don't have a very convenient/fast method to detect the exact underlying
reasons.

RST is implemented in two kinds: passive kind (like tcp_v4_send_reset())
and active kind (like tcp_send_active_reset()). The former can be traced
carefully 1) in TCP, with the help of drop reasons, which is based on
Eric's idea[1], 2) in MPTCP, with the help of reset options defined in
RFC 8684. The latter is relatively independent, which should be
implemented on our own, such as active reset reasons which can not be
replace by skb drop reason or something like this.

In this series, I focus on the fundamental implement mostly about how
the rstreason mechanism works and give the detailed passive part as an
example, not including the active reset part. In future, we can go
further and refine those NOT_SPECIFIED reasons.

Here are some examples when tracing:
<idle>-0       [002] ..s1.  1830.262425: tcp_send_reset: skbaddr=x
        skaddr=x src=x dest=x state=x reason=NOT_SPECIFIED
<idle>-0       [002] ..s1.  1830.262425: tcp_send_reset: skbaddr=x
        skaddr=x src=x dest=x state=x reason=NO_SOCKET

[1]
Link: https://lore.kernel.org/all/CANn89iJw8x-LqgsWOeJQQvgVg6DnL5aBRLi10QN2WBdr+X4k=w@mail.gmail.com/
====================

Link: https://lore.kernel.org/r/20240425031340.46946-1-kerneljasonxing@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

1 files changed, 11 insertions, 6 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e06f0cd04f7e..0427deca3e0e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -70,6 +70,7 @@
 #include <net/xfrm.h>
 #include <net/secure_seq.h>
 #include <net/busy_poll.h>
+#include <net/rstreason.h>
 
 #include <linux/inet.h>
 #include <linux/ipv6.h>
@@ -723,7 +724,8 @@ out:
  *	Exception: precedence violation. We do not implement it in any case.
  */
 
-static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
+static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
+			      enum sk_rst_reason reason)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
 	struct {
@@ -869,7 +871,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	if (sk)
 		arg.bound_dev_if = sk->sk_bound_dev_if;
 
-	trace_tcp_send_reset(sk, skb);
+	trace_tcp_send_reset(sk, skb, reason);
 
 	BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) !=
 		     offsetof(struct inet_timewait_sock, tw_bound_dev_if));
@@ -1934,7 +1936,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 	return 0;
 
 reset:
-	tcp_v4_send_reset(rsk, skb);
+	tcp_v4_send_reset(rsk, skb, sk_rst_convert_drop_reason(reason));
 discard:
 	kfree_skb_reason(skb, reason);
 	/* Be careful here. If this function gets more complicated and
@@ -2285,7 +2287,10 @@ lookup:
 		} else {
 			drop_reason = tcp_child_process(sk, nsk, skb);
 			if (drop_reason) {
-				tcp_v4_send_reset(nsk, skb);
+				enum sk_rst_reason rst_reason;
+
+				rst_reason = sk_rst_convert_drop_reason(drop_reason);
+				tcp_v4_send_reset(nsk, skb, rst_reason);
 				goto discard_and_relse;
 			}
 			sock_put(sk);
@@ -2364,7 +2369,7 @@ csum_error:
 bad_packet:
 		__TCP_INC_STATS(net, TCP_MIB_INERRS);
 	} else {
-		tcp_v4_send_reset(NULL, skb);
+		tcp_v4_send_reset(NULL, skb, sk_rst_convert_drop_reason(drop_reason));
 	}
 
 discard_it:
@@ -2416,7 +2421,7 @@ do_time_wait:
 		tcp_v4_timewait_ack(sk, skb);
 		break;
 	case TCP_TW_RST:
-		tcp_v4_send_reset(sk, skb);
+		tcp_v4_send_reset(sk, skb, sk_rst_convert_drop_reason(drop_reason));
 		inet_twsk_deschedule_put(inet_twsk(sk));
 		goto discard_it;
 	case TCP_TW_SUCCESS:;