---

yaml
---
r: 315773
b: refs/heads/master
c: fd183f6
h: refs/heads/master
i:
  315771: 798bf53
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 76886596921dd0e058f7f0a16de6151629390d15
+refs/heads/master: fd183f6a73fc0ff3e32c636dbb539e35d4c530c9

trunk/Documentation/networking/ip-sysctl.txt

@@ -1440,6 +1440,20 @@ path_max_retrans - INTEGER
 
 	Default: 5
 
+pf_retrans - INTEGER
+	The number of retransmissions that will be attempted on a given path
+	before traffic is redirected to an alternate transport (should one
+	exist).  Note this is distinct from path_max_retrans, as a path that
+	passes the pf_retrans threshold can still be used.  Its only
+	deprioritized when a transmission path is selected by the stack.  This
+	setting is primarily used to enable fast failover mechanisms without
+	having to reduce path_max_retrans to a very low value.  See:
+	http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt
+	for details.  Note also that a value of pf_retrans > path_max_retrans
+	disables this feature
+
+	Default: 0
+
 rto_initial - INTEGER
 	The initial round trip timeout value in milliseconds that will be used
 	in calculating round trip times.  This is the initial time interval

trunk/drivers/net/dummy.c

@@ -63,10 +63,10 @@ static struct rtnl_link_stats64 *dummy_get_stats64(struct net_device *dev,
 
 		dstats = per_cpu_ptr(dev->dstats, i);
 		do {
-			start = u64_stats_fetch_begin(&dstats->syncp);
+			start = u64_stats_fetch_begin_bh(&dstats->syncp);
 			tbytes = dstats->tx_bytes;
 			tpackets = dstats->tx_packets;
-		} while (u64_stats_fetch_retry(&dstats->syncp, start));
+		} while (u64_stats_fetch_retry_bh(&dstats->syncp, start));
 		stats->tx_bytes += tbytes;
 		stats->tx_packets += tpackets;
 	}

trunk/drivers/net/ethernet/neterion/vxge/vxge-main.c

@@ -3131,12 +3131,12 @@ vxge_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *net_stats)
 		u64 packets, bytes, multicast;
 
 		do {
-			start = u64_stats_fetch_begin(&rxstats->syncp);
+			start = u64_stats_fetch_begin_bh(&rxstats->syncp);
 
 			packets   = rxstats->rx_frms;
 			multicast = rxstats->rx_mcast;
 			bytes     = rxstats->rx_bytes;
-		} while (u64_stats_fetch_retry(&rxstats->syncp, start));
+		} while (u64_stats_fetch_retry_bh(&rxstats->syncp, start));
 
 		net_stats->rx_packets += packets;
 		net_stats->rx_bytes += bytes;
@@ -3146,11 +3146,11 @@ vxge_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *net_stats)
 		net_stats->rx_dropped += rxstats->rx_dropped;
 
 		do {
-			start = u64_stats_fetch_begin(&txstats->syncp);
+			start = u64_stats_fetch_begin_bh(&txstats->syncp);
 
 			packets = txstats->tx_frms;
 			bytes   = txstats->tx_bytes;
-		} while (u64_stats_fetch_retry(&txstats->syncp, start));
+		} while (u64_stats_fetch_retry_bh(&txstats->syncp, start));
 
 		net_stats->tx_packets += packets;
 		net_stats->tx_bytes += bytes;

trunk/drivers/net/loopback.c

@@ -107,10 +107,10 @@ static struct rtnl_link_stats64 *loopback_get_stats64(struct net_device *dev,
 
 		lb_stats = per_cpu_ptr(dev->lstats, i);
 		do {
-			start = u64_stats_fetch_begin(&lb_stats->syncp);
+			start = u64_stats_fetch_begin_bh(&lb_stats->syncp);
 			tbytes = lb_stats->bytes;
 			tpackets = lb_stats->packets;
-		} while (u64_stats_fetch_retry(&lb_stats->syncp, start));
+		} while (u64_stats_fetch_retry_bh(&lb_stats->syncp, start));
 		bytes   += tbytes;
 		packets += tpackets;
 	}

trunk/drivers/net/virtio_net.c

@@ -704,16 +704,16 @@ static struct rtnl_link_stats64 *virtnet_stats(struct net_device *dev,
 		u64 tpackets, tbytes, rpackets, rbytes;
 
 		do {
-			start = u64_stats_fetch_begin(&stats->tx_syncp);
+			start = u64_stats_fetch_begin_bh(&stats->tx_syncp);
 			tpackets = stats->tx_packets;
 			tbytes   = stats->tx_bytes;
-		} while (u64_stats_fetch_retry(&stats->tx_syncp, start));
+		} while (u64_stats_fetch_retry_bh(&stats->tx_syncp, start));
 
 		do {
-			start = u64_stats_fetch_begin(&stats->rx_syncp);
+			start = u64_stats_fetch_begin_bh(&stats->rx_syncp);
 			rpackets = stats->rx_packets;
 			rbytes   = stats->rx_bytes;
-		} while (u64_stats_fetch_retry(&stats->rx_syncp, start));
+		} while (u64_stats_fetch_retry_bh(&stats->rx_syncp, start));
 
 		tot->rx_packets += rpackets;
 		tot->tx_packets += tpackets;

trunk/drivers/net/wimax/i2400m/control.c

@@ -130,7 +130,7 @@ ssize_t i2400m_tlv_match(const struct i2400m_tlv_hdr *tlv,
 	    && le16_to_cpu(tlv->length) + sizeof(*tlv) != tlv_size) {
 		size_t size = le16_to_cpu(tlv->length) + sizeof(*tlv);
 		printk(KERN_WARNING "W: tlv type 0x%x mismatched because of "
-		       "size (got %zu vs %zu expected)\n",
+		       "size (got %zu vs %zd expected)\n",
 		       tlv_type, size, tlv_size);
 		return size;
 	}
@@ -235,7 +235,7 @@ const struct i2400m_tlv_hdr *i2400m_tlv_find(
 			break;
 		if (match > 0)
 			dev_warn(dev, "TLV type 0x%04x found with size "
-				 "mismatch (%zu vs %zu needed)\n",
+				 "mismatch (%zu vs %zd needed)\n",
 				 tlv_type, match, tlv_size);
 	}
 	return tlv;

trunk/drivers/net/wimax/i2400m/usb-fw.c

@@ -212,7 +212,7 @@ ssize_t i2400mu_bus_bm_cmd_send(struct i2400m *i2400m,
 	}
 	if (result != cmd_size) {		/* all was transferred? */
 		dev_err(dev, "boot-mode cmd %d: incomplete transfer "
-			"(%zu vs %zu submitted)\n",  opcode, result, cmd_size);
+			"(%zd vs %zu submitted)\n",  opcode, result, cmd_size);
 		result = -EIO;
 		goto error_cmd_size;
 	}

trunk/drivers/vhost/net.c

@@ -823,14 +823,14 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
 			return -EFAULT;
 		return vhost_net_set_backend(n, backend.index, backend.fd);
 	case VHOST_GET_FEATURES:
-		features = VHOST_FEATURES;
+		features = VHOST_NET_FEATURES;
 		if (copy_to_user(featurep, &features, sizeof features))
 			return -EFAULT;
 		return 0;
 	case VHOST_SET_FEATURES:
 		if (copy_from_user(&features, featurep, sizeof features))
 			return -EFAULT;
-		if (features & ~VHOST_FEATURES)
+		if (features & ~VHOST_NET_FEATURES)
 			return -EOPNOTSUPP;
 		return vhost_net_set_features(n, features);
 	case VHOST_RESET_OWNER:

trunk/drivers/vhost/test.c

@@ -261,14 +261,14 @@ static long vhost_test_ioctl(struct file *f, unsigned int ioctl,
 			return -EFAULT;
 		return vhost_test_run(n, test);
 	case VHOST_GET_FEATURES:
-		features = VHOST_FEATURES;
+		features = VHOST_NET_FEATURES;
 		if (copy_to_user(featurep, &features, sizeof features))
 			return -EFAULT;
 		return 0;
 	case VHOST_SET_FEATURES:
 		if (copy_from_user(&features, featurep, sizeof features))
 			return -EFAULT;
-		if (features & ~VHOST_FEATURES)
+		if (features & ~VHOST_NET_FEATURES)
 			return -EOPNOTSUPP;
 		return vhost_test_set_features(n, features);
 	case VHOST_RESET_OWNER:

trunk/drivers/vhost/vhost.c

@@ -64,7 +64,7 @@ static int vhost_poll_wakeup(wait_queue_t *wait, unsigned mode, int sync,
 	return 0;
 }
 
-static void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn)
+void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn)
 {
 	INIT_LIST_HEAD(&work->node);
 	work->fn = fn;
@@ -137,8 +137,7 @@ void vhost_poll_flush(struct vhost_poll *poll)
 	vhost_work_flush(poll->dev, &poll->work);
 }
 
-static inline void vhost_work_queue(struct vhost_dev *dev,
-				    struct vhost_work *work)
+void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work)
 {
 	unsigned long flags;
 

trunk/drivers/vhost/vhost.h

@@ -43,6 +43,9 @@ struct vhost_poll {
 	struct vhost_dev	 *dev;
 };
 
+void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn);
+void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work);
+
 void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
 		     unsigned long mask, struct vhost_dev *dev);
 void vhost_poll_start(struct vhost_poll *poll, struct file *file);
@@ -201,7 +204,8 @@ enum {
 	VHOST_FEATURES = (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) |
 			 (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
 			 (1ULL << VIRTIO_RING_F_EVENT_IDX) |
-			 (1ULL << VHOST_F_LOG_ALL) |
+			 (1ULL << VHOST_F_LOG_ALL),
+	VHOST_NET_FEATURES = VHOST_FEATURES |
 			 (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
 			 (1ULL << VIRTIO_NET_F_MRG_RXBUF),
 };

trunk/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

trunk/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;
 

trunk/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__ */

trunk/net/bridge/br_device.c

@@ -127,9 +127,9 @@ static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev,
 		const struct br_cpu_netstats *bstats
 			= per_cpu_ptr(br->stats, cpu);
 		do {
-			start = u64_stats_fetch_begin(&bstats->syncp);
+			start = u64_stats_fetch_begin_bh(&bstats->syncp);
 			memcpy(&tmp, bstats, sizeof(tmp));
-		} while (u64_stats_fetch_retry(&bstats->syncp, start));
+		} while (u64_stats_fetch_retry_bh(&bstats->syncp, start));
 		sum.tx_bytes   += tmp.tx_bytes;
 		sum.tx_packets += tmp.tx_packets;
 		sum.rx_bytes   += tmp.rx_bytes;

trunk/net/ipv4/ip_output.c

@@ -1476,7 +1476,8 @@ static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = {
 		.sk_allocation	= GFP_ATOMIC,
 		.sk_flags	= (1UL << SOCK_USE_WRITE_QUEUE),
 	},
-	.pmtudisc = IP_PMTUDISC_WANT,
+	.pmtudisc	= IP_PMTUDISC_WANT,
+	.uc_ttl		= -1,
 };
 
 void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,

trunk/net/sctp/associola.c

@@ -124,6 +124,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
 	 * socket values.
 	 */
 	asoc->max_retrans = sp->assocparams.sasoc_asocmaxrxt;
+	asoc->pf_retrans  = sctp_pf_retrans;
+
 	asoc->rto_initial = msecs_to_jiffies(sp->rtoinfo.srto_initial);
 	asoc->rto_max = msecs_to_jiffies(sp->rtoinfo.srto_max);
 	asoc->rto_min = msecs_to_jiffies(sp->rtoinfo.srto_min);
@@ -686,6 +688,9 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
 	/* Set the path max_retrans.  */
 	peer->pathmaxrxt = asoc->pathmaxrxt;
 
+	/* And the partial failure retrnas threshold */
+	peer->pf_retrans = asoc->pf_retrans;
+
 	/* Initialize the peer's SACK delay timeout based on the
 	 * association configured value.
 	 */
@@ -841,6 +846,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 	struct sctp_ulpevent *event;
 	struct sockaddr_storage addr;
 	int spc_state = 0;
+	bool ulp_notify = true;
 
 	/* Record the transition on the transport.  */
 	switch (command) {
@@ -854,6 +860,14 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 			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, see SCTP
+		 * Quick failover draft section 5.1, point 5
+		 */
+		if (transport->state == SCTP_PF) {
+			ulp_notify = false;
+			transport->cwnd = 1;
+		}
 		transport->state = SCTP_ACTIVE;
 		break;
 
@@ -872,19 +886,27 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 		spc_state = SCTP_ADDR_UNREACHABLE;
 		break;
 
+	case SCTP_TRANSPORT_PF:
+		transport->state = SCTP_PF;
+		ulp_notify = false;
+		break;
+
 	default:
 		return;
 	}
 
 	/* Generate and send a SCTP_PEER_ADDR_CHANGE notification to the
 	 * user.
 	 */
-	memset(&addr, 0, sizeof(struct sockaddr_storage));
-	memcpy(&addr, &transport->ipaddr, transport->af_specific->sockaddr_len);
-	event = sctp_ulpevent_make_peer_addr_change(asoc, &addr,
-				0, spc_state, error, GFP_ATOMIC);
-	if (event)
-		sctp_ulpq_tail_event(&asoc->ulpq, event);
+	if (ulp_notify) {
+		memset(&addr, 0, sizeof(struct sockaddr_storage));
+		memcpy(&addr, &transport->ipaddr,
+		       transport->af_specific->sockaddr_len);
+		event = sctp_ulpevent_make_peer_addr_change(asoc, &addr,
+					0, spc_state, error, GFP_ATOMIC);
+		if (event)
+			sctp_ulpq_tail_event(&asoc->ulpq, event);
+	}
 
 	/* Select new active and retran paths. */
 
@@ -900,7 +922,8 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 			transports) {
 
 		if ((t->state == SCTP_INACTIVE) ||
-		    (t->state == SCTP_UNCONFIRMED))
+		    (t->state == SCTP_UNCONFIRMED) ||
+		    (t->state == SCTP_PF))
 			continue;
 		if (!first || t->last_time_heard > first->last_time_heard) {
 			second = first;