[RFCv2 1/3] tcp: Use smaller mtu probes if RACK is enabled

[Leonard Crestez]

RACK allows detecting a loss in rtt + min_rtt / 4 based on just one
extra packet. If enabled use this instead of relying of fast retransmit.

Suggested-by: Neal Cardwell <ncardwell@xxxxxxxxxx>
Signed-off-by: Leonard Crestez <cdleonard@xxxxxxxxx>
---
 Documentation/networking/ip-sysctl.rst |  5 +++++
 include/net/netns/ipv4.h               |  1 +
 net/ipv4/sysctl_net_ipv4.c             |  7 +++++++
 net/ipv4/tcp_ipv4.c                    |  1 +
 net/ipv4/tcp_output.c                  | 26 +++++++++++++++++++++++++-
 5 files changed, 39 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index a5c250044500..7ab52a105a5d 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -349,10 +349,15 @@ 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_mtu_probe_rack - BOOLEAN
+	Try to use shorter probes if RACK is also enabled
+
+	Default: 1
+
 tcp_min_snd_mss - INTEGER
 	TCP SYN and SYNACK messages usually advertise an ADVMSS option,
 	as described in RFC 1122 and RFC 6691.
 
 	If this ADVMSS option is smaller than tcp_min_snd_mss,
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 746c80cd4257..b4ff12f25a7f 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -112,10 +112,11 @@ struct netns_ipv4 {
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	u8 sysctl_tcp_l3mdev_accept;
 #endif
 	u8 sysctl_tcp_mtu_probing;
 	int sysctl_tcp_mtu_probe_floor;
+	int sysctl_tcp_mtu_probe_rack;
 	int sysctl_tcp_base_mss;
 	int sysctl_tcp_min_snd_mss;
 	int sysctl_tcp_probe_threshold;
 	u32 sysctl_tcp_probe_interval;
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 4fa77f182dcb..275c91fb9cf8 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -847,10 +847,17 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &tcp_min_snd_mss_min,
 		.extra2		= &tcp_min_snd_mss_max,
 	},
+	{
+		.procname	= "tcp_mtu_probe_rack",
+		.data		= &init_net.ipv4.sysctl_tcp_mtu_probe_rack,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{
 		.procname	= "tcp_probe_threshold",
 		.data		= &init_net.ipv4.sysctl_tcp_probe_threshold,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4f5b68a90be9..ed8af4a7325b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2892,10 +2892,11 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
 	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_mtu_probe_rack = 1;
 
 	net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME;
 	net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES;
 	net->ipv4.sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL;
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bde781f46b41..9691f435477b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2311,10 +2311,19 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
 	}
 
 	return true;
 }
 
+/* Check if rack is supported for current connection */
+static int tcp_mtu_probe_is_rack(const struct sock *sk)
+{
+	struct net *net = sock_net(sk);
+
+	return (net->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION &&
+			net->ipv4.sysctl_tcp_mtu_probe_rack);
+}
+
 /* Create a new MTU probe if we are ready.
  * MTU probe is regularly attempting to increase the path MTU by
  * deliberately sending larger packets.  This discovers routing
  * changes resulting in larger path MTUs.
  *
@@ -2351,11 +2360,26 @@ static int tcp_mtu_probe(struct sock *sk)
 	 * smaller than a threshold, backoff from probing.
 	 */
 	mss_now = tcp_current_mss(sk);
 	probe_size = tcp_mtu_to_mss(sk, (icsk->icsk_mtup.search_high +
 				    icsk->icsk_mtup.search_low) >> 1);
-	size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
+	/* Probing the MTU requires one packet which is larger that current MSS as well
+	 * as enough following mtu-sized packets to ensure that a probe loss can be
+	 * detected without a full Retransmit Time Out.
+	 */
+	if (tcp_mtu_probe_is_rack(sk)) {
+		/* RACK allows recovering in min_rtt / 4 based on just one extra packet
+		 * Use two to account for unrelated losses
+		 */
+		size_needed = probe_size + 2 * tp->mss_cache;
+	} else {
+		/* Without RACK send enough extra packets to trigger fast retransmit
+		 * This is dynamic DupThresh + 1
+		 */
+		size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
+	}
+
 	interval = icsk->icsk_mtup.search_high - icsk->icsk_mtup.search_low;
 	/* When misfortune happens, we are reprobing actively,
 	 * and then reprobe timer has expired. We stick with current
 	 * probing process by not resetting search range to its orignal.
 	 */
-- 
2.25.1