[RFC 2/3] tcp: Use mtu probes if RACK is enabled

[Leonard Crestez]

RACK allows detecting a loss in 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                  | 22 +++++++++++++++++++++-
 5 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 108a5ee227d3..4f6ac69f61e7 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -325,10 +325,15 @@ tcp_mtu_probe_floor - INTEGER
 tcp_mtu_probe_autocork - BOOLEAN
 	Take into account mtu probe size when accumulating data via autocorking.
 
 	Default: 1
 
+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 3a2d8bf2b20a..298e65d8605c 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -113,10 +113,11 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_l3mdev_accept;
 #endif
 	u8 sysctl_tcp_mtu_probing;
 	int sysctl_tcp_mtu_probe_floor;
 	int sysctl_tcp_mtu_probe_autocork;
+	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 e19176c17973..f9366f35ff9c 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -834,10 +834,17 @@ static struct ctl_table ipv4_net_table[] = {
 		.data		= &init_net.ipv4.sysctl_tcp_mtu_probe_autocork,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.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 7e75423c08c9..4928fcd6e233 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2890,10 +2890,11 @@ 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_mtu_probe_autocork = 1;
+	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 5a320d792ec4..7cd1e8fd9749 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2311,27 +2311,47 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
 	}
 
 	return true;
 }
 
+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);
+}
+
 /* Calculate the size of an MTU probe
  * Probing the MTU requires one packets 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.
  */
 int tcp_mtu_probe_size_needed(struct sock *sk, int *probe_size)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct net *net = sock_net(sk);
 	int probe_size_val;
 	int size_needed;
 
 	/* This might be a little slow: */
 	probe_size_val = tcp_mtu_to_mss(sk, (icsk->icsk_mtup.search_high + icsk->icsk_mtup.search_low) >> 1);
 	if (probe_size)
 		*probe_size = probe_size_val;
-	size_needed = probe_size_val + (tp->reordering + 1) * tp->mss_cache;
+
+	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_val + 2 * tp->mss_cache;
+	} else {
+		/* Without RACK send enough extra packets to trigger fast retransmit
+		 * This is dynamic DupThresh + 1
+		 */
+		size_needed = probe_size_val + (tp->reordering + 1) * tp->mss_cache;
+	}
 
 	return size_needed;
 }
 
 /* Create a new MTU probe if we are ready.
-- 
2.25.1