All of lore.kernel.org
 help / color / mirror / Atom feed
From: menglong8.dong@gmail.com
To: edumazet@google.com
Cc: rostedt@goodmis.org, mingo@redhat.com, davem@davemloft.net,
	yoshfuji@linux-ipv6.org, dsahern@kernel.org, kuba@kernel.org,
	pabeni@redhat.com, imagedong@tencent.com, kafai@fb.com,
	talalahmad@google.com, keescook@chromium.org,
	dongli.zhang@oracle.com, linux-kernel@vger.kernel.org,
	netdev@vger.kernel.org
Subject: [PATCH net-next 7/9] net: tcp: add skb drop reasons to tcp connect requesting
Date: Mon, 16 May 2022 11:45:17 +0800	[thread overview]
Message-ID: <20220516034519.184876-8-imagedong@tencent.com> (raw)
In-Reply-To: <20220516034519.184876-1-imagedong@tencent.com>

From: Menglong Dong <imagedong@tencent.com>

In order to get skb drop reasons during tcp connect requesting code path,
we have to pass the pointer of the 'reason' as a new function argument of
conn_request() in 'struct inet_connection_sock_af_ops'. As the return
value of conn_request() can be positive or negative or 0, it's not
flexible to make it return drop reasons.

As the return value of tcp_conn_request() is 0, so we can treat it as bool
and make it return the skb drop reasons.

The new drop reasons 'LISTENOVERFLOWS' and 'TCP_REQQFULLDROP' are added,
which are used for 'accept queue' and 'request queue' full.

Signed-off-by: Menglong Dong <imagedong@tencent.com>
---
 include/linux/skbuff.h             | 10 ++++++++++
 include/net/inet_connection_sock.h |  3 ++-
 include/net/tcp.h                  |  9 +++++----
 net/dccp/input.c                   |  3 ++-
 net/dccp/ipv4.c                    |  3 ++-
 net/dccp/ipv6.c                    |  3 ++-
 net/ipv4/tcp_input.c               | 27 ++++++++++++++++++---------
 net/ipv4/tcp_ipv4.c                |  9 ++++++---
 net/ipv6/tcp_ipv6.c                | 12 ++++++++----
 net/mptcp/subflow.c                |  6 ++++--
 10 files changed, 59 insertions(+), 26 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 736899cc6a13..4578bbab5a3e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -552,6 +552,14 @@ struct sk_buff;
  * SKB_DROP_REASON_SOCKET_DESTROYED
  *	socket is destroyed and the skb in its receive or send queue
  *	are all dropped
+ *
+ * SKB_DROP_REASON_LISTENOVERFLOWS
+ *	accept queue of the listen socket is full, corresponding to
+ *	LINUX_MIB_LISTENOVERFLOWS
+ *
+ * SKB_DROP_REASON_TCP_REQQFULLDROP
+ *	request queue of the listen socket is full, corresponding to
+ *	LINUX_MIB_TCPREQQFULLDROP
  */
 #define __DEFINE_SKB_DROP_REASON(FN)	\
 	FN(NOT_SPECIFIED)		\
@@ -621,6 +629,8 @@ struct sk_buff;
 	FN(SOCKET_DESTROYED)		\
 	FN(TCP_PAWSACTIVEREJECTED)	\
 	FN(TCP_ABORTONDATA)		\
+	FN(LISTENOVERFLOWS)		\
+	FN(TCP_REQQFULLDROP)		\
 	FN(MAX)
 
 /* The reason of skb drop, which is used in kfree_skb_reason().
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 3908296d103f..0600280f308e 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -36,7 +36,8 @@ struct inet_connection_sock_af_ops {
 	void	    (*send_check)(struct sock *sk, struct sk_buff *skb);
 	int	    (*rebuild_header)(struct sock *sk);
 	void	    (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb);
-	int	    (*conn_request)(struct sock *sk, struct sk_buff *skb);
+	int	    (*conn_request)(struct sock *sk, struct sk_buff *skb,
+				    enum skb_drop_reason *reason);
 	struct sock *(*syn_recv_sock)(const struct sock *sk, struct sk_buff *skb,
 				      struct request_sock *req,
 				      struct dst_entry *dst,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index ea0eb2d4a743..082dd0627e2e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -445,7 +445,8 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb);
 void tcp_v4_mtu_reduced(struct sock *sk);
 void tcp_req_err(struct sock *sk, u32 seq, bool abort);
 void tcp_ld_RTO_revert(struct sock *sk, u32 seq);
-int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
+int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb,
+			enum skb_drop_reason *reason);
 struct sock *tcp_create_openreq_child(const struct sock *sk,
 				      struct request_sock *req,
 				      struct sk_buff *skb);
@@ -2036,9 +2037,9 @@ void tcp4_proc_exit(void);
 #endif
 
 int tcp_rtx_synack(const struct sock *sk, struct request_sock *req);
-int tcp_conn_request(struct request_sock_ops *rsk_ops,
-		     const struct tcp_request_sock_ops *af_ops,
-		     struct sock *sk, struct sk_buff *skb);
+enum skb_drop_reason tcp_conn_request(struct request_sock_ops *rsk_ops,
+				      const struct tcp_request_sock_ops *af_ops,
+				      struct sock *sk, struct sk_buff *skb);
 
 /* TCP af-specific functions */
 struct tcp_sock_af_ops {
diff --git a/net/dccp/input.c b/net/dccp/input.c
index 2cbb757a894f..e12baa56ca59 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -576,6 +576,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	const int old_state = sk->sk_state;
 	bool acceptable;
 	int queued = 0;
+	SKB_DR(reason);
 
 	/*
 	 *  Step 3: Process LISTEN state
@@ -606,7 +607,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 			 */
 			rcu_read_lock();
 			local_bh_disable();
-			acceptable = inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) >= 0;
+			acceptable = inet_csk(sk)->icsk_af_ops->conn_request(sk, skb, &reason) >= 0;
 			local_bh_enable();
 			rcu_read_unlock();
 			if (!acceptable)
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 82696ab86f74..c689385229f0 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -581,7 +581,8 @@ static struct request_sock_ops dccp_request_sock_ops __read_mostly = {
 	.syn_ack_timeout = dccp_syn_ack_timeout,
 };
 
-int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
+int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb,
+			 enum skb_drop_reason *reason)
 {
 	struct inet_request_sock *ireq;
 	struct request_sock *req;
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 4d95b6400915..abc82dda4b5b 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -314,7 +314,8 @@ static struct request_sock_ops dccp6_request_sock_ops = {
 	.syn_ack_timeout = dccp_syn_ack_timeout,
 };
 
-static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
+static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb,
+				enum skb_drop_reason *reason)
 {
 	struct request_sock *req;
 	struct dccp_request_sock *dreq;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4717af0eaea7..be6275c56b59 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6455,13 +6455,17 @@ enum skb_drop_reason tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			 */
 			rcu_read_lock();
 			local_bh_disable();
-			acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0;
+			reason = SKB_NOT_DROPPED_YET;
+			acceptable = icsk->icsk_af_ops->conn_request(sk, skb, &reason) >= 0;
 			local_bh_enable();
 			rcu_read_unlock();
 
 			if (!acceptable)
-				return SKB_DROP_REASON_NOT_SPECIFIED;
-			consume_skb(skb);
+				return reason ?: SKB_DROP_REASON_NOT_SPECIFIED;
+			if (reason)
+				kfree_skb_reason(skb, reason);
+			else
+				consume_skb(skb);
 			return SKB_NOT_DROPPED_YET;
 		}
 		SKB_DR_SET(reason, TCP_FLAGS);
@@ -6881,9 +6885,9 @@ u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops,
 }
 EXPORT_SYMBOL_GPL(tcp_get_syncookie_mss);
 
-int tcp_conn_request(struct request_sock_ops *rsk_ops,
-		     const struct tcp_request_sock_ops *af_ops,
-		     struct sock *sk, struct sk_buff *skb)
+enum skb_drop_reason tcp_conn_request(struct request_sock_ops *rsk_ops,
+				      const struct tcp_request_sock_ops *af_ops,
+				      struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_fastopen_cookie foc = { .len = -1 };
 	__u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn;
@@ -6895,6 +6899,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	bool want_cookie = false;
 	struct dst_entry *dst;
 	struct flowi fl;
+	SKB_DR(reason);
 
 	/* TW buckets are converted to open requests without
 	 * limitations, they conserve resources and peer is
@@ -6903,12 +6908,15 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	if ((net->ipv4.sysctl_tcp_syncookies == 2 ||
 	     inet_csk_reqsk_queue_is_full(sk)) && !isn) {
 		want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name);
-		if (!want_cookie)
+		if (!want_cookie) {
+			SKB_DR_SET(reason, TCP_REQQFULLDROP);
 			goto drop;
+		}
 	}
 
 	if (sk_acceptq_is_full(sk)) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
+		SKB_DR_SET(reason, LISTENOVERFLOWS);
 		goto drop;
 	}
 
@@ -6964,6 +6972,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			 */
 			pr_drop_req(req, ntohs(tcp_hdr(skb)->source),
 				    rsk_ops->family);
+			SKB_DR_SET(reason, TCP_REQQFULLDROP);
 			goto drop_and_release;
 		}
 
@@ -7016,7 +7025,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		}
 	}
 	reqsk_put(req);
-	return 0;
+	return SKB_NOT_DROPPED_YET;
 
 drop_and_release:
 	dst_release(dst);
@@ -7024,6 +7033,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	__reqsk_free(req);
 drop:
 	tcp_listendrop(sk);
-	return 0;
+	return reason;
 }
 EXPORT_SYMBOL(tcp_conn_request);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 12a18c5035f4..708f92b03f42 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1458,17 +1458,20 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
 	.send_synack	=	tcp_v4_send_synack,
 };
 
-int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
+int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb,
+			enum skb_drop_reason *reason)
 {
 	/* Never answer to SYNs send to broadcast or multicast */
 	if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
 		goto drop;
 
-	return tcp_conn_request(&tcp_request_sock_ops,
-				&tcp_request_sock_ipv4_ops, sk, skb);
+	*reason = tcp_conn_request(&tcp_request_sock_ops,
+				   &tcp_request_sock_ipv4_ops, sk, skb);
+	return *reason;
 
 drop:
 	tcp_listendrop(sk);
+	*reason = SKB_DROP_REASON_IP_INADDRERRORS;
 	return 0;
 }
 EXPORT_SYMBOL(tcp_v4_conn_request);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d8236d51dd47..27c51991bd54 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1148,24 +1148,28 @@ u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph,
 	return mss;
 }
 
-static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
+static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb,
+			       enum skb_drop_reason *reason)
 {
 	if (skb->protocol == htons(ETH_P_IP))
-		return tcp_v4_conn_request(sk, skb);
+		return tcp_v4_conn_request(sk, skb, reason);
 
 	if (!ipv6_unicast_destination(skb))
 		goto drop;
 
 	if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) {
 		__IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS);
+		*reason = SKB_DROP_REASON_IP_INADDRERRORS;
 		return 0;
 	}
 
-	return tcp_conn_request(&tcp6_request_sock_ops,
-				&tcp_request_sock_ipv6_ops, sk, skb);
+	*reason = tcp_conn_request(&tcp6_request_sock_ops,
+				   &tcp_request_sock_ipv6_ops, sk, skb);
+	return *reason;
 
 drop:
 	tcp_listendrop(sk);
+	*reason = SKB_DROP_REASON_IP_INADDRERRORS;
 	return 0; /* don't send reset */
 }
 
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 6d59336a8e1e..267f4e47236a 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -532,7 +532,8 @@ static int subflow_v6_rebuild_header(struct sock *sk)
 struct request_sock_ops mptcp_subflow_request_sock_ops;
 static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops __ro_after_init;
 
-static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb)
+static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb,
+				   enum skb_drop_reason *reason)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 
@@ -556,7 +557,8 @@ static struct inet_connection_sock_af_ops subflow_v6_specific __ro_after_init;
 static struct inet_connection_sock_af_ops subflow_v6m_specific __ro_after_init;
 static struct proto tcpv6_prot_override;
 
-static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
+static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb,
+				   enum skb_drop_reason *reason)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 
-- 
2.36.1


  parent reply	other threads:[~2022-05-16  3:47 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-05-16  3:45 [PATCH net-next 0/9] net: tcp: add skb drop reasons to tcp state change menglong8.dong
2022-05-16  3:45 ` [PATCH net-next 1/9] net: skb: introduce __DEFINE_SKB_DROP_REASON() to simply the code menglong8.dong
2022-05-16  3:45 ` [PATCH net-next 2/9] net: skb: introduce __skb_queue_purge_reason() menglong8.dong
2022-05-16  3:45 ` [PATCH net-next 3/9] net: sock: introduce sk_stream_kill_queues_reason() menglong8.dong
2022-05-16  3:45 ` [PATCH net-next 4/9] net: inet: add skb drop reason to inet_csk_destroy_sock() menglong8.dong
2022-05-16  3:45 ` [PATCH net-next 5/9] net: tcp: make tcp_rcv_synsent_state_process() return drop reasons menglong8.dong
2022-05-16  3:45 ` [PATCH net-next 6/9] net: tcp: make tcp_rcv_state_process() return drop reason menglong8.dong
2022-05-16  3:45 ` menglong8.dong [this message]
2022-05-16  6:34   ` [PATCH net-next 7/9] net: tcp: add skb drop reasons to tcp connect requesting kernel test robot
2022-05-16 12:54   ` kernel test robot
2022-05-16  3:45 ` [PATCH net-next 8/9] net: tcp: add skb drop reasons to tcp tw code path menglong8.dong
2022-05-16  4:22   ` Eric Dumazet
2022-05-16  4:54     ` Menglong Dong
2022-05-16 15:30   ` kernel test robot
2022-05-16  3:45 ` [PATCH net-next 9/9] net: tcp: add skb drop reasons to route_req() menglong8.dong

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220516034519.184876-8-imagedong@tencent.com \
    --to=menglong8.dong@gmail.com \
    --cc=davem@davemloft.net \
    --cc=dongli.zhang@oracle.com \
    --cc=dsahern@kernel.org \
    --cc=edumazet@google.com \
    --cc=imagedong@tencent.com \
    --cc=kafai@fb.com \
    --cc=keescook@chromium.org \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=rostedt@goodmis.org \
    --cc=talalahmad@google.com \
    --cc=yoshfuji@linux-ipv6.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.