Re: [PATCH net-next ] tcp: add new parameter tcp_inherit_buffsize to control the initial buffer size for new passive connetion

Current sndbuff/rcvbuff value of new passive connetion inherit from
listen socket.
After then, tcp_init_buffer_space() initial them with init_cwnd and 
tcp_should_expand_sndbuf() adjust them according the new cwnd.


But, For Operation & Maintenance engineer, can't control
sndbuff/rcvbuff with 
tcp_wmem/tcp_rmem sysctl parameter online. They need to migrate flows
out 
and migrate them in after restart services and turn sndbuff/rcvfuff
up.


This patch is useful for online servcie setting tcp_inherit_buffsize
with 0.
By default, keep be consistent whth before.


Signed-off-by: Shan Wei <redacted>
---
 Documentation/networking/ip-sysctl.txt |    8 ++++++++
 include/net/netns/ipv4.h               |    1 +
 net/ipv4/sysctl_net_ipv4.c             |    7 +++++++
 net/ipv4/tcp_ipv4.c                    |    1 +
 net/ipv4/tcp_minisocks.c               |    6 ++++++
 5 files changed, 23 insertions(+), 0 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt

b/Documentation/networking/ip-sysctl.txt
index 974ab47..3292bbf 100644

--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt

@@ -308,6 +308,14 @@ tcp_frto - INTEGER
 
  By default it's enabled with a non-zero value. 0 disables F-RTO.
 
+tcp_inherit_buffsize - BOOLEAN
+ For a new passive TCP connection, can use current tcp_wmem/tcp_rmem
+ parameter to set initial snd/rcv buffer size. This is useful for

online
+ services which no need to be restarted just set it with 0. By
default,
+ new passive connection inherits snd/rcv buffer size from lister
socket.
+
+ Default: 1
+
 tcp_invalid_ratelimit - INTEGER
  Limit the maximal rate for sending duplicate acknowledgments
  in response to incoming TCP packets that are for an existing

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index cd686c4..1fc85bd 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h

@@ -124,6 +124,7 @@ struct netns_ipv4 {
  int sysctl_tcp_tw_reuse;
  struct inet_timewait_death_row tcp_death_row;
  int sysctl_max_syn_backlog;
+ int sysctl_tcp_inherit_buffsize;
 
 #ifdef CONFIG_NET_L3_MASTER_DEV
  int sysctl_udp_l3mdev_accept;

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 86957e9..58a8bec 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c

@@ -1078,6 +1078,13 @@ static int

proc_tfo_blackhole_detect_timeout(struct ctl_table *table,
  .mode = 0644,
  .proc_handler = proc_dointvec
  },
+ {
+ .procname = "tcp_inherit_buffsize",
+ .data = &init_net.ipv4.sysctl_tcp_inherit_buffsize,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
  {
  .procname = "fib_multipath_use_neigh",

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cbbafe5..7a8a2bb 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c

@@ -2457,6 +2457,7 @@ static int __net_init tcp_sk_init(struct net

*net)
  net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;
 
  net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256);
+ net->ipv4.sysctl_tcp_inherit_buffsize = 1;
 
  return 0;
 fail:

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 8f6373b..6090d7e 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c

@@ -474,6 +474,12 @@ struct sock *tcp_create_openreq_child(const

struct sock *sk,
  tcp_init_xmit_timers(newsk);
  newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
 
+ if (!(sock_net(newsk)->ipv4.sysctl_tcp_inherit_buffsize) &&
+ !(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) {
+ newsk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
+ newsk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
+ }
+