sctp: Implement quick failover draft from tsvwg

I've seen several attempts recently made to do quick failover of sctp transports
by reducing various retransmit timers and counters.  While its possible to
implement a faster failover on multihomed sctp associations, its not
particularly robust, in that it can lead to unneeded retransmits, as well as
false connection failures due to intermittent latency on a network.

Instead, lets implement the new ietf quick failover draft found here:
http://tools.ietf.org/html/draft-nishida-tsvwg-sctp-failover-05

This will let the sctp stack identify transports that have had a small number of
errors, and avoid using them quickly until their reliability can be
re-established.  I've tested this out on two virt guests connected via multiple
isolated virt networks and believe its in compliance with the above draft and
works well.

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Vlad Yasevich <vyasevich@gmail.com>
CC: Sridhar Samudrala <sri@us.ibm.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: linux-sctp@vger.kernel.org
CC: joe@perches.com
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 101 insertions, 0 deletions

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 5d488cdcf679..5e259817a7f3 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3478,6 +3478,56 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
 }
 
 
+/*
+ * SCTP_PEER_ADDR_THLDS
+ *
+ * This option allows us to alter the partially failed threshold for one or all
+ * transports in an association.  See Section 6.1 of:
+ * http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt
+ */
+static int sctp_setsockopt_paddr_thresholds(struct sock *sk,
+					    char __user *optval,
+					    unsigned int optlen)
+{
+	struct sctp_paddrthlds val;
+	struct sctp_transport *trans;
+	struct sctp_association *asoc;
+
+	if (optlen < sizeof(struct sctp_paddrthlds))
+		return -EINVAL;
+	if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval,
+			   sizeof(struct sctp_paddrthlds)))
+		return -EFAULT;
+
+
+	if (sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) {
+		asoc = sctp_id2assoc(sk, val.spt_assoc_id);
+		if (!asoc)
+			return -ENOENT;
+		list_for_each_entry(trans, &asoc->peer.transport_addr_list,
+				    transports) {
+			if (val.spt_pathmaxrxt)
+				trans->pathmaxrxt = val.spt_pathmaxrxt;
+			trans->pf_retrans = val.spt_pathpfthld;
+		}
+
+		if (val.spt_pathmaxrxt)
+			asoc->pathmaxrxt = val.spt_pathmaxrxt;
+		asoc->pf_retrans = val.spt_pathpfthld;
+	} else {
+		trans = sctp_addr_id2transport(sk, &val.spt_address,
+					       val.spt_assoc_id);
+		if (!trans)
+			return -ENOENT;
+
+		if (val.spt_pathmaxrxt)
+			trans->pathmaxrxt = val.spt_pathmaxrxt;
+		trans->pf_retrans = val.spt_pathpfthld;
+	}
+
+	return 0;
+}
+
 /* API 6.2 setsockopt(), getsockopt()
  *
  * Applications use setsockopt() and getsockopt() to set or retrieve
@@ -3627,6 +3677,9 @@ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname,
 	case SCTP_AUTO_ASCONF:
 		retval = sctp_setsockopt_auto_asconf(sk, optval, optlen);
 		break;
+	case SCTP_PEER_ADDR_THLDS:
+		retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -5498,6 +5551,51 @@ static int sctp_getsockopt_assoc_ids(struct sock *sk, int len,
 	return 0;
 }
 
+/*
+ * SCTP_PEER_ADDR_THLDS
+ *
+ * This option allows us to fetch the partially failed threshold for one or all
+ * transports in an association.  See Section 6.1 of:
+ * 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)
+{
+	struct sctp_paddrthlds val;
+	struct sctp_transport *trans;
+	struct sctp_association *asoc;
+
+	if (len < sizeof(struct sctp_paddrthlds))
+		return -EINVAL;
+	len = sizeof(struct sctp_paddrthlds);
+	if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval, len))
+		return -EFAULT;
+
+	if (sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) {
+		asoc = sctp_id2assoc(sk, val.spt_assoc_id);
+		if (!asoc)
+			return -ENOENT;
+
+		val.spt_pathpfthld = asoc->pf_retrans;
+		val.spt_pathmaxrxt = asoc->pathmaxrxt;
+	} else {
+		trans = sctp_addr_id2transport(sk, &val.spt_address,
+					       val.spt_assoc_id);
+		if (!trans)
+			return -ENOENT;
+
+		val.spt_pathmaxrxt = trans->pathmaxrxt;
+		val.spt_pathpfthld = trans->pf_retrans;
+	}
+
+	if (put_user(len, optlen) || copy_to_user(optval, &val, len))
+		return -EFAULT;
+
+	return 0;
+}
+
 SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname,
 				char __user *optval, int __user *optlen)
 {
@@ -5636,6 +5734,9 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname,
 	case SCTP_AUTO_ASCONF:
 		retval = sctp_getsockopt_auto_asconf(sk, len, optval, optlen);
 		break;
+	case SCTP_PEER_ADDR_THLDS:
+		retval = sctp_getsockopt_paddr_thresholds(sk, optval, len, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;