tcp: add new tcp_mtu_probe_floor sysctl

The current implementation of TCP MTU probing can considerably
underestimate the MTU on lossy connections allowing the MSS to get down to
48. We have found that in almost all of these cases on our networks these
paths can handle much larger MTUs meaning the connections are being
artificially limited. Even though TCP MTU probing can raise the MSS back up
we have seen this not to be the case causing connections to be "stuck" with
an MSS of 48 when heavy loss is present.

Prior to pushing out this change we could not keep TCP MTU probing enabled
b/c of the above reasons. Now with a reasonble floor set we've had it
enabled for the past 6 months.

The new sysctl will still default to TCP_MIN_SND_MSS (48), but gives
administrators the ability to control the floor of MSS probing.

Signed-off-by: Josh Hunt <johunt@akamai.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 18 insertions, 1 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index df33674799b5..49e95f438ed7 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -256,6 +256,12 @@ tcp_base_mss - INTEGER
 	Path MTU discovery (MTU probing).  If MTU probing is enabled,
 	this is the initial MSS used by the connection.
 
+tcp_mtu_probe_floor - INTEGER
+	If MTU probing is enabled this caps the minimum MSS used for search_low
+	for the connection.
+
+	Default : 48
+
 tcp_min_snd_mss - INTEGER
 	TCP SYN and SYNACK messages usually advertise an ADVMSS option,
 	as described in RFC 1122 and RFC 6691.
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index bc24a8ec1ce5..c0c0791b1912 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -116,6 +116,7 @@ struct netns_ipv4 {
 	int sysctl_tcp_l3mdev_accept;
 #endif
 	int sysctl_tcp_mtu_probing;
+	int sysctl_tcp_mtu_probe_floor;
 	int sysctl_tcp_base_mss;
 	int sysctl_tcp_min_snd_mss;
 	int sysctl_tcp_probe_threshold;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0b980e841927..59ded25acd04 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -820,6 +820,15 @@ static struct ctl_table ipv4_net_table[] = {
 		.extra2		= &tcp_min_snd_mss_max,
 	},
 	{
+		.procname	= "tcp_mtu_probe_floor",
+		.data		= &init_net.ipv4.sysctl_tcp_mtu_probe_floor,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &tcp_min_snd_mss_min,
+		.extra2		= &tcp_min_snd_mss_max,
+	},
+	{
 		.procname	= "tcp_probe_threshold",
 		.data		= &init_net.ipv4.sysctl_tcp_probe_threshold,
 		.maxlen		= sizeof(int),
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d57641cb3477..e0a372676329 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2637,6 +2637,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS;
 	net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD;
 	net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL;
+	net->ipv4.sysctl_tcp_mtu_probe_floor = TCP_MIN_SND_MSS;
 
 	net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME;
 	net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index c801cd37cc2a..dbd9d2d0ee63 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -154,7 +154,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 	} else {
 		mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
 		mss = min(net->ipv4.sysctl_tcp_base_mss, mss);
-		mss = max(mss, 68 - tcp_sk(sk)->tcp_header_len);
+		mss = max(mss, net->ipv4.sysctl_tcp_mtu_probe_floor);
 		mss = max(mss, net->ipv4.sysctl_tcp_min_snd_mss);
 		icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
 	}