sctp: add support for Primary Path Switchover

This is a new feature defined in section 5 of rfc7829: "Primary Path
Switchover". By introducing a new tunable parameter:

  Primary.Switchover.Max.Retrans (PSMR)

The primary path will be changed to another active path when the path
error counter on the old primary path exceeds PSMR, so that "the SCTP
sender is allowed to continue data transmission on a new working path
even when the old primary destination address becomes active again".

This patch is to add this tunable parameter, 'ps_retrans' per netns,
sock, asoc and transport. It also allows a user to change ps_retrans
per netns by sysctl, and ps_retrans per sock/asoc/transport will be
initialized with it.

The check will be done in sctp_do_8_2_transport_strike() when this
feature is enabled.

Note this feature is disabled by initializing 'ps_retrans' per netns
as 0xffff by default, and its value can't be less than 'pf_retrans'
when changing by sysctl.

v3->v4:
  - add define SCTP_PS_RETRANS_MAX 0xffff, and use it on extra2 of
    sysctl 'ps_retrans'.
  - add a new entry for ps_retrans on ip-sysctl.txt.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 23 insertions, 1 deletions

diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index ad7a74e942d3..8f8d18abd013 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -86,6 +86,7 @@ static struct sctp_association *sctp_association_init(
 	 */
 	asoc->max_retrans = sp->assocparams.sasoc_asocmaxrxt;
 	asoc->pf_retrans  = sp->pf_retrans;
+	asoc->ps_retrans  = sp->ps_retrans;
 	asoc->pf_expose   = sp->pf_expose;
 
 	asoc->rto_initial = msecs_to_jiffies(sp->rtoinfo.srto_initial);
@@ -628,6 +629,8 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
 
 	/* And the partial failure retrans threshold */
 	peer->pf_retrans = asoc->pf_retrans;
+	/* And the primary path switchover retrans threshold */
+	peer->ps_retrans = asoc->ps_retrans;
 
 	/* Initialize the peer's SACK delay timeout based on the
 	 * association configured value.
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index f86be7bf0972..fbbf19128c2d 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1217,6 +1217,9 @@ static int __net_init sctp_defaults_init(struct net *net)
 	/* Max.Burst		    - 4 */
 	net->sctp.max_burst			= SCTP_DEFAULT_MAX_BURST;
 
+	/* Disable of Primary Path Switchover by default */
+	net->sctp.ps_retrans = SCTP_PS_RETRANS_MAX;
+
 	/* Enable pf state by default */
 	net->sctp.pf_enable = 1;
 
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index e52b2128e43b..acd737d4c0e0 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -567,6 +567,11 @@ static void sctp_do_8_2_transport_strike(struct sctp_cmd_seq *commands,
 					     SCTP_FAILED_THRESHOLD);
 	}
 
+	if (transport->error_count > transport->ps_retrans &&
+	    asoc->peer.primary_path == transport &&
+	    asoc->peer.active_path != transport)
+		sctp_assoc_set_primary(asoc, asoc->peer.active_path);
+
 	/* E2) For the destination address for which the timer
 	 * expires, set RTO <- RTO * 2 ("back off the timer").  The
 	 * maximum value discussed in rule C7 above (RTO.max) may be
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 74c4e62ac741..64452ee410da 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5078,6 +5078,7 @@ static int sctp_init_sock(struct sock *sk)
 	sp->hbinterval  = net->sctp.hb_interval;
 	sp->pathmaxrxt  = net->sctp.max_retrans_path;
 	sp->pf_retrans  = net->sctp.pf_retrans;
+	sp->ps_retrans  = net->sctp.ps_retrans;
 	sp->pf_expose   = net->sctp.pf_expose;
 	sp->pathmtu     = 0; /* allow default discovery */
 	sp->sackdelay   = net->sctp.sack_timeout;
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 5d1ad44a29d1..4740aa70e652 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -35,6 +35,7 @@ static int rto_beta_min = 0;
 static int rto_alpha_max = 1000;
 static int rto_beta_max = 1000;
 static int pf_expose_max = SCTP_PF_EXPOSE_MAX;
+static int ps_retrans_max = SCTP_PS_RETRANS_MAX;
 
 static unsigned long max_autoclose_min = 0;
 static unsigned long max_autoclose_max =
@@ -213,7 +214,16 @@ static struct ctl_table sctp_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_INT_MAX,
+		.extra2		= &init_net.sctp.ps_retrans,
+	},
+	{
+		.procname	= "ps_retrans",
+		.data		= &init_net.sctp.ps_retrans,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &init_net.sctp.pf_retrans,
+		.extra2		= &ps_retrans_max,
 	},
 	{
 		.procname	= "sndbuf_policy",