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:     kuba@kernel.org
Cc:     davem@davemloft.net, edumazet@google.com, pabeni@redhat.com,
        dsahern@kernel.org, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org, Menglong Dong <imagedong@tencent.com>
Subject: [PATCH net-next 2/3] net: tcp: send zero-window when no memory
Date:   Wed, 17 May 2023 20:42:00 +0800
Message-Id: <20230517124201.441634-3-imagedong@tencent.com>
In-Reply-To: <20230517124201.441634-1-imagedong@tencent.com>
References: <20230517124201.441634-1-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.

Therefore, now we force to receive one packet on current socket when
the protocol memory is out of the limitation. Then, this socket will
stay in 'no mem' status, util protocol memory is available.

When a socket is in 'no mem' status, it's receive window will become
0, which means window shrink happens. And the sender need to handle
such window shrink properly, which is done in the next commit.

Signed-off-by: Menglong Dong <imagedong@tencent.com>
---
 include/net/sock.h    |  1 +
 net/ipv4/tcp_input.c  | 12 ++++++++++++
 net/ipv4/tcp_output.c |  7 +++++++
 3 files changed, 20 insertions(+)

diff --git a/include/net/sock.h b/include/net/sock.h
index 5edf0038867c..90db8a1d7f31 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -957,6 +957,7 @@ enum sock_flags {
 	SOCK_XDP, /* XDP is attached */
 	SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */
 	SOCK_RCVMARK, /* Receive SO_MARK  ancillary data with packet */
+	SOCK_NO_MEM, /* protocol memory limitation happened */
 };
 
 #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a057330d6f59..56e395cb4554 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5047,10 +5047,22 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 		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)) {
+			if (sysctl_tcp_wnd_shrink)
+				goto do_wnd_shrink;
+
 			reason = SKB_DROP_REASON_PROTO_MEM;
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
 			sk->sk_data_ready(sk);
 			goto drop;
+do_wnd_shrink:
+			if (sock_flag(sk, SOCK_NO_MEM)) {
+				NET_INC_STATS(sock_net(sk),
+					      LINUX_MIB_TCPRCVQDROP);
+				sk->sk_data_ready(sk);
+				goto out_of_window;
+			}
+			sk_forced_mem_schedule(sk, skb->truesize);
+			sock_set_flag(sk, SOCK_NO_MEM);
 		}
 
 		eaten = tcp_queue_rcv(sk, skb, &fragstolen);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index cfe128b81a01..21dc4f7e0a12 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -300,6 +300,13 @@ static u16 tcp_select_window(struct sock *sk)
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV);
 	}
 
+	if (sock_flag(sk, SOCK_NO_MEM)) {
+		if (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 2))
+			sock_reset_flag(sk, SOCK_NO_MEM);
+		else
+			new_win = 0;
+	}
+
 	return new_win;
 }
 
-- 
2.40.1