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, 20 insertions, 7 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index b94d1dca1094..97ec44d1df30 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -20,6 +20,7 @@
 #include <net/transp_v6.h>
 #endif
 #include <net/mptcp.h>
+
 #include "protocol.h"
 #include "mib.h"
 
@@ -307,8 +308,13 @@ static struct dst_entry *subflow_v4_route_req(const struct sock *sk,
 		return dst;
 
 	dst_release(dst);
-	if (!req->syncookie)
-		tcp_request_sock_ops.send_reset(sk, skb);
+	if (!req->syncookie) {
+		struct mptcp_ext *mpext = mptcp_get_ext(skb);
+		enum sk_rst_reason reason;
+
+		reason = sk_rst_convert_mptcp_reason(mpext->reset_reason);
+		tcp_request_sock_ops.send_reset(sk, skb, reason);
+	}
 	return NULL;
 }
 
@@ -375,8 +381,13 @@ static struct dst_entry *subflow_v6_route_req(const struct sock *sk,
 		return dst;
 
 	dst_release(dst);
-	if (!req->syncookie)
-		tcp6_request_sock_ops.send_reset(sk, skb);
+	if (!req->syncookie) {
+		struct mptcp_ext *mpext = mptcp_get_ext(skb);
+		enum sk_rst_reason reason;
+
+		reason = sk_rst_convert_mptcp_reason(mpext->reset_reason);
+		tcp6_request_sock_ops.send_reset(sk, skb, reason);
+	}
 	return NULL;
 }
 #endif
@@ -412,7 +423,7 @@ void mptcp_subflow_reset(struct sock *ssk)
 	/* must hold: tcp_done() could drop last reference on parent */
 	sock_hold(sk);
 
-	tcp_send_active_reset(ssk, GFP_ATOMIC);
+	mptcp_send_active_reset_reason(ssk);
 	tcp_done(ssk);
 	if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags))
 		mptcp_schedule_work(sk);
@@ -781,6 +792,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 	struct mptcp_subflow_request_sock *subflow_req;
 	struct mptcp_options_received mp_opt;
 	bool fallback, fallback_is_fatal;
+	enum sk_rst_reason reason;
 	struct mptcp_sock *owner;
 	struct sock *child;
 
@@ -911,7 +923,8 @@ dispose_child:
 	tcp_rsk(req)->drop_req = true;
 	inet_csk_prepare_for_destroy_sock(child);
 	tcp_done(child);
-	req->rsk_ops->send_reset(sk, skb);
+	reason = sk_rst_convert_mptcp_reason(mptcp_get_ext(skb)->reset_reason);
+	req->rsk_ops->send_reset(sk, skb, reason);
 
 	/* The last child reference will be released by the caller */
 	return child;
@@ -1348,7 +1361,7 @@ reset:
 			tcp_set_state(ssk, TCP_CLOSE);
 			while ((skb = skb_peek(&ssk->sk_receive_queue)))
 				sk_eat_skb(ssk, skb);
-			tcp_send_active_reset(ssk, GFP_ATOMIC);
+			mptcp_send_active_reset_reason(ssk);
 			WRITE_ONCE(subflow->data_avail, false);
 			return false;
 		}