sctp: add probe_interval in sysctl and sock/asoc/transport

PLPMTUD can be enabled by doing 'sysctl -w net.sctp.probe_interval=n'.
'n' is the interval for PLPMTUD probe timer in milliseconds, and it
can't be less than 5000 if it's not 0.

All asoc/transport's PLPMTUD in a new socket will be enabled by default.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Author: lxin

Documentation/networking/ip-sysctl.rst

@@ -2834,6 +2834,14 @@ encap_port - INTEGER
 
 	Default: 0
 
+plpmtud_probe_interval - INTEGER
+        The time interval (in milliseconds) for sending PLPMTUD probe chunks.
+        These chunks are sent at the specified interval with a variable size
+        to probe the mtu of a given path between 2 endpoints. PLPMTUD will
+        be disabled when 0 is set, and other values for it must be >= 5000.
+
+	Default: 0
+
 
 ``/proc/sys/net/core/*``
 ========================

include/net/netns/sctp.h

@@ -84,6 +84,9 @@ struct netns_sctp {
 	/* HB.interval		    - 30 seconds  */
 	unsigned int hb_interval;
 
+	/* The interval for PLPMTUD probe timer */
+	unsigned int probe_interval;
+
 	/* Association.Max.Retrans  - 10 attempts
 	 * Path.Max.Retrans	    - 5	 attempts (per destination address)
 	 * Max.Init.Retransmits	    - 8	 attempts

include/net/sctp/constants.h

@@ -424,4 +424,6 @@ enum {
  */
 #define SCTP_AUTH_RANDOM_LENGTH 32
 
+#define SCTP_PROBE_TIMER_MIN	5000
+
 #endif /* __sctp_constants_h__ */

include/net/sctp/structs.h

@@ -177,6 +177,7 @@ struct sctp_sock {
 	 * will be inherited by all new associations.
 	 */
 	__u32 hbinterval;
+	__u32 probe_interval;
 
 	__be16 udp_port;
 	__be16 encap_port;
@@ -858,6 +859,7 @@ struct sctp_transport {
 	 * the destination address every heartbeat interval.
 	 */
 	unsigned long hbinterval;
+	unsigned long probe_interval;
 
 	/* SACK delay timeout */
 	unsigned long sackdelay;
@@ -1795,6 +1797,7 @@ struct sctp_association {
 	 * will be inherited by all new transports.
 	 */
 	unsigned long hbinterval;
+	unsigned long probe_interval;
 
 	__be16 encap_port;
 

net/sctp/associola.c

@@ -98,6 +98,7 @@ static struct sctp_association *sctp_association_init(
 	 * sock configured value.
 	 */
 	asoc->hbinterval = msecs_to_jiffies(sp->hbinterval);
+	asoc->probe_interval = msecs_to_jiffies(sp->probe_interval);
 
 	asoc->encap_port = sp->encap_port;
 
@@ -625,6 +626,7 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
 	 * association configured value.
 	 */
 	peer->hbinterval = asoc->hbinterval;
+	peer->probe_interval = asoc->probe_interval;
 
 	peer->encap_port = asoc->encap_port;
 

net/sctp/socket.c

@@ -4989,6 +4989,7 @@ static int sctp_init_sock(struct sock *sk)
 	atomic_set(&sp->pd_mode, 0);
 	skb_queue_head_init(&sp->pd_lobby);
 	sp->frag_interleave = 0;
+	sp->probe_interval = net->sctp.probe_interval;
 
 	/* Create a per socket endpoint structure.  Even if we
 	 * change the data structure relationships, this may still

net/sctp/sysctl.c

@@ -55,6 +55,8 @@ static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
 				   void *buffer, size_t *lenp, loff_t *ppos);
 static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
 			     void *buffer, size_t *lenp, loff_t *ppos);
+static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write,
+				       void *buffer, size_t *lenp, loff_t *ppos);
 
 static struct ctl_table sctp_table[] = {
 	{
@@ -293,6 +295,13 @@ static struct ctl_table sctp_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "plpmtud_probe_interval",
+		.data		= &init_net.sctp.probe_interval,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_probe_interval,
+	},
 	{
 		.procname	= "udp_port",
 		.data		= &init_net.sctp.udp_port,
@@ -539,6 +548,32 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write,
 	return ret;
 }
 
+static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write,
+				       void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct ctl_table tbl;
+	int ret, new_value;
+
+	memset(&tbl, 0, sizeof(struct ctl_table));
+	tbl.maxlen = sizeof(unsigned int);
+
+	if (write)
+		tbl.data = &new_value;
+	else
+		tbl.data = &net->sctp.probe_interval;
+
+	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		if (new_value && new_value < SCTP_PROBE_TIMER_MIN)
+			return -EINVAL;
+
+		net->sctp.probe_interval = new_value;
+	}
+
+	return ret;
+}
+
 int sctp_sysctl_net_register(struct net *net)
 {
 	struct ctl_table *table;