[PATCH v3 net-next 6/6] tcp: add tcp_comp_sack_nr sysctl

[Eric Dumazet <edumazet@google.com>]

This per netns sysctl allows for TCP SACK compression fine-tuning.

This limits number of SACK that can be compressed.
Using 0 disables SACK compression.

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 Documentation/networking/ip-sysctl.txt |  6 ++++++
 include/net/netns/ipv4.h               |  1 +
 net/ipv4/sysctl_net_ipv4.c             | 10 ++++++++++
 net/ipv4/tcp_input.c                   |  3 ++-
 net/ipv4/tcp_ipv4.c                    |  1 +
 5 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 7ba952959bca0eee4ecf81fb5837e17790db0fde..924bd51327b7a8dff3503d7afccdd54e1eb5c29b 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -532,6 +532,12 @@ tcp_comp_sack_delay_ns - LONG INTEGER
 
 	Default : 1,000,000 ns (1 ms)
 
+tcp_comp_sack_nr - INTEGER
+	Max numer of SACK that can be compressed.
+	Using 0 disables SACK compression.
+
+	Detault : 44
+
 tcp_slow_start_after_idle - BOOLEAN
 	If set, provide RFC2861 behavior and time out the congestion
 	window after an idle period.  An idle period is defined at
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 927318243cfaa2ddd8eb423c6ba6e66253f771d3..661348f23ea5a3a9320b2cafcd17e23960214771 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -160,6 +160,7 @@ struct netns_ipv4 {
 	int sysctl_tcp_pacing_ca_ratio;
 	int sysctl_tcp_wmem[3];
 	int sysctl_tcp_rmem[3];
+	int sysctl_tcp_comp_sack_nr;
 	unsigned long sysctl_tcp_comp_sack_delay_ns;
 	struct inet_timewait_death_row tcp_death_row;
 	int sysctl_max_syn_backlog;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 11fbfdc1566eca95f91360522178295318277588..d2eed3ddcb0a1ad9778d96d46c685f6c60b93d8d 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -46,6 +46,7 @@ static int tcp_syn_retries_min = 1;
 static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
 static int ip_ping_group_range_min[] = { 0, 0 };
 static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
+static int comp_sack_nr_max = 255;
 
 /* obsolete */
 static int sysctl_tcp_low_latency __read_mostly;
@@ -1158,6 +1159,15 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_doulongvec_minmax,
 	},
+	{
+		.procname	= "tcp_comp_sack_nr",
+		.data		= &init_net.ipv4.sysctl_tcp_comp_sack_nr,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &comp_sack_nr_max,
+	},
 	{
 		.procname	= "udp_rmem_min",
 		.data		= &init_net.ipv4.sysctl_udp_rmem_min,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6a1dae38c9558c7bc9dd31e9f16c4e8ea8c78149..aebb29ab2fdf2ceaa182cd11928f145a886149ff 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5106,7 +5106,8 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
 		return;
 	}
 
-	if (!tcp_is_sack(tp) || tp->compressed_ack >= 44)
+	if (!tcp_is_sack(tp) ||
+	    tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
 		goto send_now;
 	tp->compressed_ack++;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a3f4647341db2eb5a63c3e9f1e8b93099aedadab..adbdb503db0c983ef4185f83b138aa51bafd15bf 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2573,6 +2573,7 @@ static int __net_init tcp_sk_init(struct net *net)
 		       sizeof(init_net.ipv4.sysctl_tcp_wmem));
 	}
 	net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC;
+	net->ipv4.sysctl_tcp_comp_sack_nr = 44;
 	net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
 	spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
 	net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60;
-- 
2.17.0.441.gb46fe60e1d-goog