ipv4: Create probe timer for tcp PMTU as per RFC4821

As per RFC4821 7.3.  Selecting Probe Size, a probe timer should
be armed once probing has converged. Once this timer expired,
probing again to take advantage of any path PMTU change. The
recommended probing interval is 10 minutes per RFC1981. Probing
interval could be sysctled by sysctl_tcp_probe_interval.

Eric Dumazet suggested to implement pseudo timer based on 32bits
jiffies tcp_time_stamp instead of using classic timer for such
rare event.

Signed-off-by: Fan Du <fan.du@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 51 insertions, 2 deletions

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 5976bdecf58b..b9a6b0a94cc6 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -126,6 +126,8 @@ struct inet_connection_sock {
 
 		/* Information on the current probe. */
 		int		  probe_size;
+
+		u32		  probe_timestamp;
 	} icsk_mtup;
 	u32			  icsk_ca_priv[16];
 	u32			  icsk_user_timeout;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index e051d399fa17..8f3a1a1a5a94 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -88,6 +88,7 @@ struct netns_ipv4 {
 	int sysctl_tcp_mtu_probing;
 	int sysctl_tcp_base_mss;
 	int sysctl_tcp_probe_threshold;
+	u32 sysctl_tcp_probe_interval;
 
 	struct ping_group_range ping_group_range;
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 1ad82e334e27..2e11e38205c2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -67,6 +67,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 /* The least MTU to use for probing */
 #define TCP_BASE_MSS		1024
 
+/* probing interval, default to 10 minutes as per RFC4821 */
+#define TCP_PROBE_INTERVAL	600
+
 /* Specify interval when tcp mtu probing will stop */
 #define TCP_PROBE_THRESHOLD	8
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d3c09c12ee81..fdf899163d44 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -890,6 +890,13 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "tcp_probe_interval",
+		.data		= &init_net.ipv4.sysctl_tcp_probe_interval,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{ }
 };
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 35790d977a2b..f0c6fc32bfa8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2461,6 +2461,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_ecn = 2;
 	net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
 	net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD;
+	net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL;
 	return 0;
 
 fail:
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ed024cbb097f..5a73ad5afaf7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1354,6 +1354,8 @@ void tcp_mtup_init(struct sock *sk)
 			       icsk->icsk_af_ops->net_header_len;
 	icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss);
 	icsk->icsk_mtup.probe_size = 0;
+	if (icsk->icsk_mtup.enabled)
+		icsk->icsk_mtup.probe_timestamp = tcp_time_stamp;
 }
 EXPORT_SYMBOL(tcp_mtup_init);
 
@@ -1828,6 +1830,31 @@ send_now:
 	return false;
 }
 
+static inline void tcp_mtu_check_reprobe(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct net *net = sock_net(sk);
+	u32 interval;
+	s32 delta;
+
+	interval = net->ipv4.sysctl_tcp_probe_interval;
+	delta = tcp_time_stamp - icsk->icsk_mtup.probe_timestamp;
+	if (unlikely(delta >= interval * HZ)) {
+		int mss = tcp_current_mss(sk);
+
+		/* Update current search range */
+		icsk->icsk_mtup.probe_size = 0;
+		icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp +
+			sizeof(struct tcphdr) +
+			icsk->icsk_af_ops->net_header_len;
+		icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
+
+		/* Update probe time stamp */
+		icsk->icsk_mtup.probe_timestamp = tcp_time_stamp;
+	}
+}
+
 /* 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
@@ -1870,9 +1897,16 @@ static int tcp_mtu_probe(struct sock *sk)
 				    icsk->icsk_mtup.search_low) >> 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.
+	 */
 	if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) ||
-	    interval < max(1, net->ipv4.sysctl_tcp_probe_threshold)) {
-		/* TODO: set timer for probe_converge_event */
+		interval < net->ipv4.sysctl_tcp_probe_threshold) {
+		/* Check whether enough time has elaplased for
+		 * another round of probing.
+		 */
+		tcp_mtu_check_reprobe(sk);
 		return -1;
 	}
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 0732b787904e..15505936511d 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -107,6 +107,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 	if (net->ipv4.sysctl_tcp_mtu_probing) {
 		if (!icsk->icsk_mtup.enabled) {
 			icsk->icsk_mtup.enabled = 1;
+			icsk->icsk_mtup.probe_timestamp = tcp_time_stamp;
 			tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		} else {
 			struct net *net = sock_net(sk);