Merge branch 'sctp-rfc7829'

Xin Long says:

====================
sctp: update from rfc7829

SCTP-PF was implemented based on a Internet-Draft in 2012:

  https://tools.ietf.org/html/draft-nishida-tsvwg-sctp-failover-05

It's been updated quite a few by rfc7829 in 2016.

This patchset adds the following features:

  1. add SCTP_ADDR_POTENTIALLY_FAILED notification
  2. add pf_expose per netns/sock/asoc
  3. add SCTP_EXPOSE_POTENTIALLY_FAILED_STATE sockopt
  4. add ps_retrans per netns/sock/asoc/transport
     (Primary Path Switchover)
  5. add spt_pathcpthld for SCTP_PEER_ADDR_THLDS sockopt

v1->v2:
  - See Patch 2/5 and Patch 5/5.
v2->v3:
  - See Patch 1/5, 2/5 and 3/5.
v3->v4:
  - See Patch 1/5, 2/5, 3/5 and 4/5.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 181 insertions, 35 deletions

diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 1b9809ad7725..8f8d18abd013 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -86,6 +86,8 @@ 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);
 	asoc->rto_max = msecs_to_jiffies(sp->rtoinfo.srto_max);
@@ -627,6 +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.
@@ -786,8 +790,8 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 				  enum sctp_transport_cmd command,
 				  sctp_sn_error_t error)
 {
+	int spc_state = SCTP_ADDR_AVAILABLE;
 	bool ulp_notify = true;
-	int spc_state = 0;
 
 	/* Record the transition on the transport.  */
 	switch (command) {
@@ -796,19 +800,13 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 		 * to heartbeat success, report the SCTP_ADDR_CONFIRMED
 		 * state to the user, otherwise report SCTP_ADDR_AVAILABLE.
 		 */
-		if (SCTP_UNCONFIRMED == transport->state &&
-		    SCTP_HEARTBEAT_SUCCESS == error)
-			spc_state = SCTP_ADDR_CONFIRMED;
-		else
-			spc_state = SCTP_ADDR_AVAILABLE;
-		/* Don't inform ULP about transition from PF to
-		 * active state and set cwnd to 1 MTU, see SCTP
-		 * Quick failover draft section 5.1, point 5
-		 */
-		if (transport->state == SCTP_PF) {
+		if (transport->state == SCTP_PF &&
+		    asoc->pf_expose != SCTP_PF_EXPOSE_ENABLE)
 			ulp_notify = false;
-			transport->cwnd = asoc->pathmtu;
-		}
+		else if (transport->state == SCTP_UNCONFIRMED &&
+			 error == SCTP_HEARTBEAT_SUCCESS)
+			spc_state = SCTP_ADDR_CONFIRMED;
+
 		transport->state = SCTP_ACTIVE;
 		break;
 
@@ -817,19 +815,21 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 		 * to inactive state.  Also, release the cached route since
 		 * there may be a better route next time.
 		 */
-		if (transport->state != SCTP_UNCONFIRMED)
+		if (transport->state != SCTP_UNCONFIRMED) {
 			transport->state = SCTP_INACTIVE;
-		else {
+			spc_state = SCTP_ADDR_UNREACHABLE;
+		} else {
 			sctp_transport_dst_release(transport);
 			ulp_notify = false;
 		}
-
-		spc_state = SCTP_ADDR_UNREACHABLE;
 		break;
 
 	case SCTP_TRANSPORT_PF:
 		transport->state = SCTP_PF;
-		ulp_notify = false;
+		if (asoc->pf_expose != SCTP_PF_EXPOSE_ENABLE)
+			ulp_notify = false;
+		else
+			spc_state = SCTP_ADDR_POTENTIALLY_FAILED;
 		break;
 
 	default:
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 08d14d86ecfb..fbbf19128c2d 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1217,9 +1217,15 @@ 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;
 
+	/* Ignore pf exposure feature by default */
+	net->sctp.pf_expose = SCTP_PF_EXPOSE_UNSET;
+
 	/* Association.Max.Retrans  - 10 attempts
 	 * Path.Max.Retrans         - 5  attempts (per destination address)
 	 * Max.Init.Retransmits     - 8  attempts
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 53abb97e0061..83e4ca1fabda 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3943,18 +3943,22 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
  */
 static int sctp_setsockopt_paddr_thresholds(struct sock *sk,
 					    char __user *optval,
-					    unsigned int optlen)
+					    unsigned int optlen, bool v2)
 {
-	struct sctp_paddrthlds val;
+	struct sctp_paddrthlds_v2 val;
 	struct sctp_transport *trans;
 	struct sctp_association *asoc;
+	int len;
 
-	if (optlen < sizeof(struct sctp_paddrthlds))
+	len = v2 ? sizeof(val) : sizeof(struct sctp_paddrthlds);
+	if (optlen < len)
 		return -EINVAL;
-	if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval,
-			   sizeof(struct sctp_paddrthlds)))
+	if (copy_from_user(&val, optval, len))
 		return -EFAULT;
 
+	if (v2 && val.spt_pathpfthld > val.spt_pathcpthld)
+		return -EINVAL;
+
 	if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) {
 		trans = sctp_addr_id2transport(sk, &val.spt_address,
 					       val.spt_assoc_id);
@@ -3963,6 +3967,8 @@ static int sctp_setsockopt_paddr_thresholds(struct sock *sk,
 
 		if (val.spt_pathmaxrxt)
 			trans->pathmaxrxt = val.spt_pathmaxrxt;
+		if (v2)
+			trans->ps_retrans = val.spt_pathcpthld;
 		trans->pf_retrans = val.spt_pathpfthld;
 
 		return 0;
@@ -3978,17 +3984,23 @@ static int sctp_setsockopt_paddr_thresholds(struct sock *sk,
 				    transports) {
 			if (val.spt_pathmaxrxt)
 				trans->pathmaxrxt = val.spt_pathmaxrxt;
+			if (v2)
+				trans->ps_retrans = val.spt_pathcpthld;
 			trans->pf_retrans = val.spt_pathpfthld;
 		}
 
 		if (val.spt_pathmaxrxt)
 			asoc->pathmaxrxt = val.spt_pathmaxrxt;
+		if (v2)
+			asoc->ps_retrans = val.spt_pathcpthld;
 		asoc->pf_retrans = val.spt_pathpfthld;
 	} else {
 		struct sctp_sock *sp = sctp_sk(sk);
 
 		if (val.spt_pathmaxrxt)
 			sp->pathmaxrxt = val.spt_pathmaxrxt;
+		if (v2)
+			sp->ps_retrans = val.spt_pathcpthld;
 		sp->pf_retrans = val.spt_pathpfthld;
 	}
 
@@ -4589,6 +4601,40 @@ out:
 	return retval;
 }
 
+static int sctp_setsockopt_pf_expose(struct sock *sk,
+				     char __user *optval,
+				     unsigned int optlen)
+{
+	struct sctp_assoc_value params;
+	struct sctp_association *asoc;
+	int retval = -EINVAL;
+
+	if (optlen != sizeof(params))
+		goto out;
+
+	if (copy_from_user(&params, optval, optlen)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	if (params.assoc_value > SCTP_PF_EXPOSE_MAX)
+		goto out;
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC &&
+	    sctp_style(sk, UDP))
+		goto out;
+
+	if (asoc)
+		asoc->pf_expose = params.assoc_value;
+	else
+		sctp_sk(sk)->pf_expose = params.assoc_value;
+	retval = 0;
+
+out:
+	return retval;
+}
+
 /* API 6.2 setsockopt(), getsockopt()
  *
  * Applications use setsockopt() and getsockopt() to set or retrieve
@@ -4744,7 +4790,12 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 		retval = sctp_setsockopt_auto_asconf(sk, optval, optlen);
 		break;
 	case SCTP_PEER_ADDR_THLDS:
-		retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen);
+		retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen,
+							  false);
+		break;
+	case SCTP_PEER_ADDR_THLDS_V2:
+		retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen,
+							  true);
 		break;
 	case SCTP_RECVRCVINFO:
 		retval = sctp_setsockopt_recvrcvinfo(sk, optval, optlen);
@@ -4798,6 +4849,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 	case SCTP_ECN_SUPPORTED:
 		retval = sctp_setsockopt_ecn_supported(sk, optval, optlen);
 		break;
+	case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE:
+		retval = sctp_setsockopt_pf_expose(sk, optval, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -5041,6 +5095,8 @@ 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;
 	sp->sackfreq	= 2;
@@ -5521,8 +5577,16 @@ static int sctp_getsockopt_peer_addr_info(struct sock *sk, int len,
 
 	transport = sctp_addr_id2transport(sk, &pinfo.spinfo_address,
 					   pinfo.spinfo_assoc_id);
-	if (!transport)
-		return -EINVAL;
+	if (!transport) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	if (transport->state == SCTP_PF &&
+	    transport->asoc->pf_expose == SCTP_PF_EXPOSE_DISABLE) {
+		retval = -EACCES;
+		goto out;
+	}
 
 	pinfo.spinfo_assoc_id = sctp_assoc2id(transport->asoc);
 	pinfo.spinfo_state = transport->state;
@@ -7170,18 +7234,19 @@ static int sctp_getsockopt_assoc_ids(struct sock *sk, int len,
  * http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt
  */
 static int sctp_getsockopt_paddr_thresholds(struct sock *sk,
-					    char __user *optval,
-					    int len,
-					    int __user *optlen)
+					    char __user *optval, int len,
+					    int __user *optlen, bool v2)
 {
-	struct sctp_paddrthlds val;
+	struct sctp_paddrthlds_v2 val;
 	struct sctp_transport *trans;
 	struct sctp_association *asoc;
+	int min;
 
-	if (len < sizeof(struct sctp_paddrthlds))
+	min = v2 ? sizeof(val) : sizeof(struct sctp_paddrthlds);
+	if (len < min)
 		return -EINVAL;
-	len = sizeof(struct sctp_paddrthlds);
-	if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval, len))
+	len = min;
+	if (copy_from_user(&val, optval, len))
 		return -EFAULT;
 
 	if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) {
@@ -7192,6 +7257,7 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk,
 
 		val.spt_pathmaxrxt = trans->pathmaxrxt;
 		val.spt_pathpfthld = trans->pf_retrans;
+		val.spt_pathcpthld = trans->ps_retrans;
 
 		goto out;
 	}
@@ -7204,11 +7270,13 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk,
 	if (asoc) {
 		val.spt_pathpfthld = asoc->pf_retrans;
 		val.spt_pathmaxrxt = asoc->pathmaxrxt;
+		val.spt_pathcpthld = asoc->ps_retrans;
 	} else {
 		struct sctp_sock *sp = sctp_sk(sk);
 
 		val.spt_pathpfthld = sp->pf_retrans;
 		val.spt_pathmaxrxt = sp->pathmaxrxt;
+		val.spt_pathcpthld = sp->ps_retrans;
 	}
 
 out:
@@ -7900,6 +7968,45 @@ out:
 	return retval;
 }
 
+static int sctp_getsockopt_pf_expose(struct sock *sk, int len,
+				     char __user *optval,
+				     int __user *optlen)
+{
+	struct sctp_assoc_value params;
+	struct sctp_association *asoc;
+	int retval = -EFAULT;
+
+	if (len < sizeof(params)) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	len = sizeof(params);
+	if (copy_from_user(&params, optval, len))
+		goto out;
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC &&
+	    sctp_style(sk, UDP)) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	params.assoc_value = asoc ? asoc->pf_expose
+				  : sctp_sk(sk)->pf_expose;
+
+	if (put_user(len, optlen))
+		goto out;
+
+	if (copy_to_user(optval, &params, len))
+		goto out;
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
 static int sctp_getsockopt(struct sock *sk, int level, int optname,
 			   char __user *optval, int __user *optlen)
 {
@@ -8049,7 +8156,12 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 		retval = sctp_getsockopt_auto_asconf(sk, len, optval, optlen);
 		break;
 	case SCTP_PEER_ADDR_THLDS:
-		retval = sctp_getsockopt_paddr_thresholds(sk, optval, len, optlen);
+		retval = sctp_getsockopt_paddr_thresholds(sk, optval, len,
+							  optlen, false);
+		break;
+	case SCTP_PEER_ADDR_THLDS_V2:
+		retval = sctp_getsockopt_paddr_thresholds(sk, optval, len,
+							  optlen, true);
 		break;
 	case SCTP_GET_ASSOC_STATS:
 		retval = sctp_getsockopt_assoc_stats(sk, len, optval, optlen);
@@ -8112,6 +8224,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 	case SCTP_ECN_SUPPORTED:
 		retval = sctp_getsockopt_ecn_supported(sk, len, optval, optlen);
 		break;
+	case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE:
+		retval = sctp_getsockopt_pf_expose(sk, len, optval, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 238cf1737576..4740aa70e652 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -34,6 +34,8 @@ static int rto_alpha_min = 0;
 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 =
@@ -212,7 +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",
@@ -318,6 +329,15 @@ static struct ctl_table sctp_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "pf_expose",
+		.data		= &init_net.sctp.pf_expose,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &pf_expose_max,
+	},
 
 	{ /* sentinel */ }
 };