From: Eric Dumazet <edumazet@google.com>
To: "David S . Miller" <davem@davemloft.net>
Cc: netdev <netdev@vger.kernel.org>,
Eric Dumazet <edumazet@google.com>,
Eric Dumazet <eric.dumazet@gmail.com>
Subject: [PATCH net-next 15/15] tcp: Namespace-ify sysctl_tcp_frto
Date: Thu, 26 Oct 2017 16:35:26 -0700 [thread overview]
Message-ID: <20171026233526.6155-16-edumazet@google.com> (raw)
In-Reply-To: <20171026233526.6155-1-edumazet@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/netns/ipv4.h | 1 +
include/net/tcp.h | 1 -
net/ipv4/sysctl_net_ipv4.c | 14 +++++++-------
net/ipv4/tcp_input.c | 3 +--
net/ipv4/tcp_ipv4.c | 1 +
5 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 9dbb07d4eff465428817831e55c6a4922b7208fb..f4622e28db3a1484553f51709b144ee769766a28 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -141,6 +141,7 @@ struct netns_ipv4 {
int sysctl_tcp_dsack;
int sysctl_tcp_app_win;
int sysctl_tcp_adv_win_scale;
+ int sysctl_tcp_frto;
struct inet_timewait_death_row tcp_death_row;
int sysctl_max_syn_backlog;
int sysctl_tcp_fastopen;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2572b57682987dd5f3700ed47d63e7238946b9a8..19006a5d073c202995ba63199ab8cde814d6d869 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -244,7 +244,6 @@ extern int sysctl_tcp_max_orphans;
extern long sysctl_tcp_mem[3];
extern int sysctl_tcp_wmem[3];
extern int sysctl_tcp_rmem[3];
-extern int sysctl_tcp_frto;
extern int sysctl_tcp_nometrics_save;
extern int sysctl_tcp_moderate_rcvbuf;
extern int sysctl_tcp_tso_win_divisor;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index a95123e1e7da706c88bf5553b7d8ef6c2653ab50..f1bcb9b7e082c6688fad12e15be9b872ebed8151 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -437,13 +437,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec_minmax,
.extra1 = &one,
},
- {
- .procname = "tcp_frto",
- .data = &sysctl_tcp_frto,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
{
.procname = "tcp_min_rtt_wlen",
.data = &sysctl_tcp_min_rtt_wlen,
@@ -1145,6 +1138,13 @@ static struct ctl_table ipv4_net_table[] = {
.extra1 = &tcp_adv_win_scale_min,
.extra2 = &tcp_adv_win_scale_max,
},
+ {
+ .procname = "tcp_frto",
+ .data = &init_net.ipv4.sysctl_tcp_frto,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
{ }
};
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d01f390da23dcd4100271b150bd8bc143f7328cf..24950ea3094288cad8d9cd9eb0e0698d6f50e989 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -81,7 +81,6 @@
int sysctl_tcp_challenge_ack_limit = 1000;
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
-int sysctl_tcp_frto __read_mostly = 2;
int sysctl_tcp_min_rtt_wlen __read_mostly = 300;
int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
@@ -2024,7 +2023,7 @@ void tcp_enter_loss(struct sock *sk)
* falsely raise the receive window, which results in repeated
* timeouts and stop-and-go behavior.
*/
- tp->frto = sysctl_tcp_frto &&
+ tp->frto = net->ipv4.sysctl_tcp_frto &&
(new_recovery || icsk->icsk_retransmits) &&
!inet_csk(sk)->icsk_mtup.probe_size;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1fe30fb99308b3e3fd07509b509b0e3727cc5d44..49757c75821111c6d2cf413415be2c1b58482659 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2492,6 +2492,7 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.sysctl_tcp_dsack = 1;
net->ipv4.sysctl_tcp_app_win = 31;
net->ipv4.sysctl_tcp_adv_win_scale = 1;
+ net->ipv4.sysctl_tcp_frto = 2;
net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
--
2.15.0.rc2.357.g7e34df9404-goog
next prev parent reply other threads:[~2017-10-26 23:36 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-26 23:35 [PATCH net-next 00/15] tcp: move 14 sysctls to namespaces Eric Dumazet
2017-10-26 23:35 ` [PATCH net-next 01/15] tcp: Namespace-ify sysctl_tcp_early_retrans Eric Dumazet
2017-10-26 23:35 ` [PATCH net-next 02/15] tcp: Namespace-ify sysctl_tcp_recovery Eric Dumazet
2017-10-26 23:35 ` [PATCH net-next 03/15] tcp: Namespace-ify sysctl_tcp_thin_linear_timeouts Eric Dumazet
2017-10-26 23:35 ` [PATCH net-next 04/15] tcp: Namespace-ify sysctl_tcp_slow_start_after_idle Eric Dumazet
2017-10-26 23:35 ` [PATCH net-next 05/15] tcp: Namespace-ify sysctl_tcp_retrans_collapse Eric Dumazet
2017-10-26 23:35 ` [PATCH net-next 06/15] tcp: Namespace-ify sysctl_tcp_stdurg Eric Dumazet
2017-10-26 23:35 ` [PATCH net-next 07/15] tcp: Namespace-ify sysctl_tcp_rfc1337 Eric Dumazet
2017-10-26 23:35 ` [PATCH net-next 08/15] tcp: Namespace-ify sysctl_tcp_abort_on_overflow Eric Dumazet
2017-10-26 23:35 ` [PATCH net-next 09/15] tcp: Namespace-ify sysctl_tcp_fack Eric Dumazet
2017-10-26 23:35 ` [PATCH net-next 10/15] tcp: remove stale sysctl_tcp_reordering Eric Dumazet
2017-10-26 23:35 ` [PATCH net-next 11/15] tcp: Namespace-ify sysctl_tcp_max_reordering Eric Dumazet
2017-10-26 23:35 ` [PATCH net-next 12/15] tcp: Namespace-ify sysctl_tcp_dsack Eric Dumazet
2017-10-26 23:35 ` [PATCH net-next 13/15] tcp: Namespace-ify sysctl_tcp_app_win Eric Dumazet
2017-10-26 23:35 ` [PATCH net-next 14/15] tcp: Namespace-ify sysctl_tcp_adv_win_scale Eric Dumazet
2017-10-26 23:35 ` Eric Dumazet [this message]
2017-10-27 4:46 ` [PATCH net-next 00/15] tcp: move 14 sysctls to namespaces David Miller
2017-10-27 4:54 ` Eric Dumazet
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=20171026233526.6155-16-edumazet@google.com \
--to=edumazet@google.com \
--cc=davem@davemloft.net \
--cc=eric.dumazet@gmail.com \
--cc=netdev@vger.kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).