Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   menglong8.dong@gmail.com
To:     edumazet@google.com, ncardwell@google.com
Cc:     davem@davemloft.net, kuba@kernel.org, pabeni@redhat.com,
        dsahern@kernel.org, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org, flyingpeng@tencent.com,
        Menglong Dong <imagedong@tencent.com>
Subject: [PATCH net-next v4 1/4] net: tcp: send zero-window ACK when no memory
Date:   Fri, 11 Aug 2023 10:55:27 +0800
Message-Id: <20230811025530.3510703-2-imagedong@tencent.com>
In-Reply-To: <20230811025530.3510703-1-imagedong@tencent.com>
References: <20230811025530.3510703-1-imagedong@tencent.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Menglong Dong <imagedong@tencent.com>

For now, skb will be dropped when no memory, which makes client keep
retrans util timeout and it's not friendly to the users.

In this patch, we reply an ACK with zero-window in this case to update
the snd_wnd of the sender to 0. Therefore, the sender won't timeout the
connection and will probe the zero-window with the retransmits.

Signed-off-by: Menglong Dong <imagedong@tencent.com>
---
v3:
- refactor the code to avoid code duplication
v2:
- send 0 rwin ACK for the receive queue empty case when necessary
- send the ACK immediately by using the ICSK_ACK_NOW flag
---
 include/net/inet_connection_sock.h |  3 ++-
 net/ipv4/tcp_input.c               | 18 ++++++++++++------
 net/ipv4/tcp_output.c              | 14 +++++++++++---
 3 files changed, 25 insertions(+), 10 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index c2b15f7e5516..be3c858a2ebb 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -164,7 +164,8 @@ enum inet_csk_ack_state_t {
 	ICSK_ACK_TIMER  = 2,
 	ICSK_ACK_PUSHED = 4,
 	ICSK_ACK_PUSHED2 = 8,
-	ICSK_ACK_NOW = 16	/* Send the next ACK immediately (once) */
+	ICSK_ACK_NOW = 16,	/* Send the next ACK immediately (once) */
+	ICSK_ACK_NOMEM = 32,
 };
 
 void inet_csk_init_xmit_timers(struct sock *sk,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8e96ebe373d7..2ac059483410 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5059,13 +5059,19 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 
 		/* Ok. In sequence. In window. */
 queue_and_out:
-		if (skb_queue_len(&sk->sk_receive_queue) == 0)
-			sk_forced_mem_schedule(sk, skb->truesize);
-		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
-			reason = SKB_DROP_REASON_PROTO_MEM;
-			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
+		if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
+			/* TODO: maybe ratelimit these WIN 0 ACK ? */
+			inet_csk(sk)->icsk_ack.pending |=
+					(ICSK_ACK_NOMEM | ICSK_ACK_NOW);
+			inet_csk_schedule_ack(sk);
 			sk->sk_data_ready(sk);
-			goto drop;
+
+			if (skb_queue_len(&sk->sk_receive_queue)) {
+				reason = SKB_DROP_REASON_PROTO_MEM;
+				NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
+				goto drop;
+			}
+			sk_forced_mem_schedule(sk, skb->truesize);
 		}
 
 		eaten = tcp_queue_rcv(sk, skb, &fragstolen);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c5412ee77fc8..769a558159ee 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -257,11 +257,19 @@ EXPORT_SYMBOL(tcp_select_initial_window);
 static u16 tcp_select_window(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 old_win = tp->rcv_wnd;
-	u32 cur_win = tcp_receive_window(tp);
-	u32 new_win = __tcp_select_window(sk);
 	struct net *net = sock_net(sk);
+	u32 old_win = tp->rcv_wnd;
+	u32 cur_win, new_win;
+
+	/* Make the window 0 if we failed to queue the data because we
+	 * are out of memory. The window is temporary, so we don't store
+	 * it on the socket.
+	 */
+	if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM))
+		return 0;
 
+	cur_win = tcp_receive_window(tp);
+	new_win = __tcp_select_window(sk);
 	if (new_win < cur_win) {
 		/* Danger Will Robinson!
 		 * Don't update rcv_wup/rcv_wnd here or else
-- 
2.40.1