[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20230807134547.2782227-1-imagedong@tencent.com>
Date: Mon, 7 Aug 2023 21:45:44 +0800
From: menglong8.dong@...il.com
To: edumazet@...gle.com,
ncardwell@...gle.com
Cc: davem@...emloft.net,
kuba@...nel.org,
pabeni@...hat.com,
dsahern@...nel.org,
netdev@...r.kernel.org,
linux-kernel@...r.kernel.org,
Menglong Dong <imagedong@...cent.com>
Subject: [PATCH net-next v2 0/3]net: tcp: support probing OOM
From: Menglong Dong <imagedong@...cent.com>
In this series, we make some small changes to make the tcp retransmission
become zero-window probes if the receiver drops the skb because of memory
pressure.
In the 1st patch, we reply a zero-window ACK if the skb is dropped
because out of memory, instead of dropping the skb silently.
In the 2nd patch, we allow a zero-window ACK to update the window.
In the 3rd patch, we check the timeout of a probing socket with
'(u32)icsk->icsk_timeout', instead of 'tcp_jiffies32'. This is more like
a bugfix.
After these changes, the tcp can probe the OOM of the receiver forever.
Changes since v1:
- send 0 rwin ACK for the receive queue empty case when necessary in the
1st patch
- send the ACK immediately by using the ICSK_ACK_NOW flag in the 1st
patch
- consider the case of the connection restart from idle, as Neal comment,
in the 3rd patch
Menglong Dong (3):
net: tcp: send zero-window ACK when no memory
net: tcp: allow zero-window ACK update the window
net: tcp: fix unexcepted socket die when snd_wnd is 0
include/net/inet_connection_sock.h | 3 ++-
net/ipv4/tcp_input.c | 16 ++++++++++++----
net/ipv4/tcp_output.c | 14 +++++++++++---
net/ipv4/tcp_timer.c | 10 +++++++++-
4 files changed, 34 insertions(+), 9 deletions(-)
--
2.40.1
Powered by blists - more mailing lists