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>

3 files changed, 31 insertions, 1 deletions

diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index 942b864f6135..d053d2e99876 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -334,6 +334,7 @@ typedef enum {
 typedef enum {
 	SCTP_TRANSPORT_UP,
 	SCTP_TRANSPORT_DOWN,
+	SCTP_TRANSPORT_PF,
 } sctp_transport_cmd_t;
 
 /* These are the address scopes defined mainly for IPv4 addresses
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 536e439ddf1d..fc5e60016e37 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -161,6 +161,12 @@ extern struct sctp_globals {
 	int max_retrans_path;
 	int max_retrans_init;
 
+	/* Potentially-Failed.Max.Retrans sysctl value
+	 * taken from:
+	 * http://tools.ietf.org/html/draft-nishida-tsvwg-sctp-failover-05
+	 */
+	int pf_retrans;
+
 	/*
 	 * Policy for preforming sctp/socket accounting
 	 * 0   - do socket level accounting, all assocs share sk_sndbuf
@@ -258,6 +264,7 @@ extern struct sctp_globals {
 #define sctp_sndbuf_policy	 	(sctp_globals.sndbuf_policy)
 #define sctp_rcvbuf_policy	 	(sctp_globals.rcvbuf_policy)
 #define sctp_max_retrans_path		(sctp_globals.max_retrans_path)
+#define sctp_pf_retrans			(sctp_globals.pf_retrans)
 #define sctp_max_retrans_init		(sctp_globals.max_retrans_init)
 #define sctp_sack_timeout		(sctp_globals.sack_timeout)
 #define sctp_hb_interval		(sctp_globals.hb_interval)
@@ -990,10 +997,15 @@ struct sctp_transport {
 
 	/* This is the max_retrans value for the transport and will
 	 * be initialized from the assocs value.  This can be changed
-	 * using SCTP_SET_PEER_ADDR_PARAMS socket option.
+	 * using the SCTP_SET_PEER_ADDR_PARAMS socket option.
 	 */
 	__u16 pathmaxrxt;
 
+	/* This is the partially failed retrans value for the transport
+	 * and will be initialized from the assocs value.  This can be changed
+	 * using the SCTP_PEER_ADDR_THLDS socket option
+	 */
+	int pf_retrans;
 	/* PMTU	      : The current known path MTU.  */
 	__u32 pathmtu;
 
@@ -1664,6 +1676,12 @@ struct sctp_association {
 	 */
 	int max_retrans;
 
+	/* This is the partially failed retrans value for the transport
+	 * and will be initialized from the assocs value.  This can be
+	 * changed using the SCTP_PEER_ADDR_THLDS socket option
+	 */
+	int pf_retrans;
+
 	/* Maximum number of times the endpoint will retransmit INIT  */
 	__u16 max_init_attempts;
 
diff --git a/include/net/sctp/user.h b/include/net/sctp/user.h
index 0842ef00b2fe..1b02d7ad453b 100644
--- a/include/net/sctp/user.h
+++ b/include/net/sctp/user.h
@@ -93,6 +93,7 @@ typedef __s32 sctp_assoc_t;
 #define SCTP_GET_ASSOC_NUMBER	28	/* Read only */
 #define SCTP_GET_ASSOC_ID_LIST	29	/* Read only */
 #define SCTP_AUTO_ASCONF       30
+#define SCTP_PEER_ADDR_THLDS	31
 
 /* Internal Socket Options. Some of the sctp library functions are
  * implemented using these socket options.
@@ -649,6 +650,7 @@ struct sctp_paddrinfo {
  */
 enum sctp_spinfo_state {
 	SCTP_INACTIVE,
+	SCTP_PF,
 	SCTP_ACTIVE,
 	SCTP_UNCONFIRMED,
 	SCTP_UNKNOWN = 0xffff  /* Value used for transport state unknown */
@@ -741,4 +743,13 @@ typedef struct {
 	int sd;
 } sctp_peeloff_arg_t;
 
+/*
+ *  Peer Address Thresholds socket option
+ */
+struct sctp_paddrthlds {
+	sctp_assoc_t spt_assoc_id;
+	struct sockaddr_storage spt_address;
+	__u16 spt_pathmaxrxt;
+	__u16 spt_pathpfthld;
+};
 #endif /* __net_sctp_user_h__ */