[PATCH v3 net-next 5/6] tcp: add tcp_comp_sack_delay_ns sysctl

[Eric Dumazet <edumazet@google.com>]

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

Its default value is 1,000,000, or 1 ms to meet TSO autosizing period.

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 Documentation/networking/ip-sysctl.txt | 7 +++++++
 include/net/netns/ipv4.h               | 1 +
 net/ipv4/sysctl_net_ipv4.c             | 7 +++++++
 net/ipv4/tcp_input.c                   | 4 ++--
 net/ipv4/tcp_ipv4.c                    | 1 +
 5 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index ea304a23c8d72c92a925d0c107bfd2bcfbbb92ec..7ba952959bca0eee4ecf81fb5837e17790db0fde 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -525,6 +525,13 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
 tcp_sack - BOOLEAN
 	Enable select acknowledgments (SACKS).
 
+tcp_comp_sack_delay_ns - LONG INTEGER
+	TCP tries to reduce number of SACK sent, using a timer
+	based on 5% of SRTT, capped by this sysctl, in nano seconds.
+	The default is 1ms, based on TSO autosizing period.
+
+	Default : 1,000,000 ns (1 ms)
+
 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 8491bc9c86b1553ab603e4363e8e38ca7ff547e0..927318243cfaa2ddd8eb423c6ba6e66253f771d3 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];
+	unsigned long sysctl_tcp_comp_sack_delay_ns;
 	struct inet_timewait_death_row tcp_death_row;
 	int sysctl_max_syn_backlog;
 	int sysctl_tcp_fastopen;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 4b195bac8ac0eefe0a224528ad854338c4f8e6e3..11fbfdc1566eca95f91360522178295318277588 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1151,6 +1151,13 @@ static struct ctl_table ipv4_net_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &one,
 	},
+	{
+		.procname	= "tcp_comp_sack_delay_ns",
+		.data		= &init_net.ipv4.sysctl_tcp_comp_sack_delay_ns,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
 	{
 		.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 cc2ac5346b92b968593f919192d543384865bcb8..6a1dae38c9558c7bc9dd31e9f16c4e8ea8c78149 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5113,13 +5113,13 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
 	if (hrtimer_is_queued(&tp->compressed_ack_timer))
 		return;
 
-	/* compress ack timer : 5 % of rtt, but no more than 1 ms */
+	/* compress ack timer : 5 % of rtt, but no more than tcp_comp_sack_delay_ns */
 
 	rtt = tp->rcv_rtt_est.rtt_us;
 	if (tp->srtt_us && tp->srtt_us < rtt)
 		rtt = tp->srtt_us;
 
-	delay = min_t(unsigned long, NSEC_PER_MSEC,
+	delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns,
 		      rtt * (NSEC_PER_USEC >> 3)/20);
 	sock_hold(sk);
 	hrtimer_start(&tp->compressed_ack_timer, ns_to_ktime(delay),
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index caf23de88f8a369c2038cecd34ce42c522487e90..a3f4647341db2eb5a63c3e9f1e8b93099aedadab 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2572,6 +2572,7 @@ static int __net_init tcp_sk_init(struct net *net)
 		       init_net.ipv4.sysctl_tcp_wmem,
 		       sizeof(init_net.ipv4.sysctl_tcp_wmem));
 	}
+	net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC;
 	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